diff --git a/corpus/README.md b/corpus/README.md index b1cb4fb..48dce88 100644 --- a/corpus/README.md +++ b/corpus/README.md @@ -36,12 +36,14 @@ The model compiler derives each single-byte encoding's case-folding byte map through iconv, applies the detector's whitespace normalization, and emits 64 sorted detector-ready trigrams into `src/encoding/models/generated.ts`. It also learns Laplace-smoothed high-byte distributions from the training split. The -evaluator uses byte likelihood to rank candidates whose trigram hit rates are -statistically competitive at a 95% margin. `models:evaluate` reports every -held-out test document, while `models:verify` checks reproducibility and fails if -any encoding or language result is incorrect. A different encoding label is -accepted only when both encodings decode the actual held-out bytes identically; -the report distinguishes these byte-equivalent results from exact matches. -CP949 is excluded because its -multibyte recogniser requires character frequency data rather than byte -trigrams. +compiler evaluator and library runtime share the normalization, trigram, +byte-likelihood, confidence, candidate-prefiltering, and tie-breaking +implementation in `src/encoding/sbcs-scoring.ts`. Candidates whose trigram hit +rates are statistically competitive at a 95% margin are ranked by byte +likelihood and deterministic encoding-family preferences. `models:evaluate` +reports every held-out test document, while `models:verify` checks +reproducibility and fails if any encoding or language result is incorrect. A +different encoding label is accepted only when both encodings decode the actual +held-out bytes identically; the report distinguishes these byte-equivalent +results from exact matches. CP949 is excluded because its multibyte recogniser +requires character frequency data rather than byte trigrams. diff --git a/corpus/model-evaluation.json b/corpus/model-evaluation.json index 013725c..3021440 100644 --- a/corpus/model-evaluation.json +++ b/corpus/model-evaluation.json @@ -1,11 +1,11 @@ { "summary": { "tests": 66, - "encodingExact": 44, - "encodingEquivalent": 22, + "encodingExact": 46, + "encodingEquivalent": 20, "encodingCorrect": 66, "languageCorrect": 66, - "topScoreTies": 34 + "topScoreTies": 37 }, "confusion": { "CP850": { @@ -21,8 +21,7 @@ "IBM866": 1 }, "ISO-8859-1": { - "ISO-8859-1": 8, - "ISO-8859-15": 2 + "ISO-8859-1": 10 }, "ISO-8859-10": { "ISO-8859-10": 1 @@ -80,8 +79,7 @@ "windows-1251": 1 }, "windows-1252": { - "ISO-8859-1": 8, - "ISO-8859-15": 2 + "ISO-8859-1": 10 }, "windows-1253": { "ISO-8859-7": 1 @@ -116,8 +114,8 @@ }, "predicted": { "encoding": "CP850", - "confidence": 73, "language": "de", + "confidence": 73, "byteLogLikelihood": -3.169712077519, "hits": 53, "total": 216, @@ -131,35 +129,35 @@ "candidates": [ { "encoding": "CP850", - "confidence": 73, "language": "de", + "confidence": 73, "byteLogLikelihood": -3.169712077519, "hits": 53, "total": 216, "hitRate": 0.24537037037037038 }, { - "encoding": "ISO-8859-1", - "confidence": 72, + "encoding": "windows-1252", "language": "de", + "confidence": 72, "byteLogLikelihood": -5.003946305945, "hits": 52, "total": 215, "hitRate": 0.24186046511627907 }, { - "encoding": "windows-1252", - "confidence": 72, + "encoding": "ISO-8859-15", "language": "de", + "confidence": 72, "byteLogLikelihood": -5.003946305945, "hits": 52, "total": 215, "hitRate": 0.24186046511627907 }, { - "encoding": "ISO-8859-15", - "confidence": 72, + "encoding": "ISO-8859-1", "language": "de", + "confidence": 72, "byteLogLikelihood": -5.003946305945, "hits": 52, "total": 215, @@ -167,8 +165,8 @@ }, { "encoding": "macintosh", - "confidence": 70, "language": "de", + "confidence": 70, "byteLogLikelihood": -5.003946305945, "hits": 51, "total": 216, @@ -176,8 +174,8 @@ }, { "encoding": "ISO-8859-14", - "confidence": 22, "language": "cy", + "confidence": 22, "byteLogLikelihood": -4.912654885736, "hits": 16, "total": 215, @@ -185,8 +183,8 @@ }, { "encoding": "ISO-8859-2", - "confidence": 13, "language": "ro", + "confidence": 13, "byteLogLikelihood": -5.176149732574, "hits": 10, "total": 215, @@ -194,8 +192,8 @@ }, { "encoding": "ISO-8859-9", - "confidence": 13, "language": "tr", + "confidence": 13, "byteLogLikelihood": -5.075173815234, "hits": 10, "total": 215, @@ -203,80 +201,26 @@ }, { "encoding": "windows-1250", - "confidence": 13, "language": "ro", - "byteLogLikelihood": -5.176149732574, - "hits": 10, - "total": 215, - "hitRate": 0.046511627906976744 - }, - { - "encoding": "windows-1254", "confidence": 13, - "language": "tr", - "byteLogLikelihood": -5.075173815234, + "byteLogLikelihood": -5.176149732574, "hits": 10, "total": 215, "hitRate": 0.046511627906976744 }, { "encoding": "windows-1257", - "confidence": 11, "language": "lv", - "byteLogLikelihood": -5.19295685089, - "hits": 8, - "total": 215, - "hitRate": 0.037209302325581395 - }, - { - "encoding": "ISO-8859-4", "confidence": 11, - "language": "lv", "byteLogLikelihood": -5.19295685089, "hits": 8, "total": 215, "hitRate": 0.037209302325581395 }, - { - "encoding": "ISO-8859-16", - "confidence": 11, - "language": "ro", - "byteLogLikelihood": -5.220355825078, - "hits": 8, - "total": 215, - "hitRate": 0.037209302325581395 - }, - { - "encoding": "windows-1258", - "confidence": 6, - "language": "vi", - "byteLogLikelihood": -5.172849867117, - "hits": 5, - "total": 215, - "hitRate": 0.023255813953488372 - }, - { - "encoding": "ISO-8859-3", - "confidence": 5, - "language": "mt", - "byteLogLikelihood": -5.105945473901, - "hits": 4, - "total": 215, - "hitRate": 0.018604651162790697 - }, - { - "encoding": "CP852", - "confidence": 5, - "language": "pl", - "byteLogLikelihood": -5.087596335232, - "hits": 4, - "total": 216, - "hitRate": 0.018518518518518517 - }, { "encoding": "ISO-8859-10", - "confidence": 4, "language": "is", + "confidence": 4, "byteLogLikelihood": -4.97295762689, "hits": 3, "total": 215, @@ -284,138 +228,12 @@ }, { "encoding": "ISO-8859-13", - "confidence": 2, "language": "lt", + "confidence": 2, "byteLogLikelihood": -5.00843944931, "hits": 2, "total": 215, "hitRate": 0.009302325581395349 - }, - { - "encoding": "ISO-8859-5", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.099525732258, - "hits": 0, - "total": 215, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-6", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -5.729917997667, - "hits": 0, - "total": 215, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-7", - "confidence": 0, - "language": "el", - "byteLogLikelihood": -5.542674768484, - "hits": 0, - "total": 215, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-8", - "confidence": 0, - "language": "he", - "byteLogLikelihood": -5.504753627871, - "hits": 0, - "total": 215, - "hitRate": 0 - }, - { - "encoding": "windows-1251", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.219881518497, - "hits": 0, - "total": 215, - "hitRate": 0 - }, - { - "encoding": "windows-1253", - "confidence": 0, - "language": "el", - "byteLogLikelihood": -5.542674768484, - "hits": 0, - "total": 215, - "hitRate": 0 - }, - { - "encoding": "windows-1255", - "confidence": 0, - "language": "he", - "byteLogLikelihood": -5.504753627871, - "hits": 0, - "total": 215, - "hitRate": 0 - }, - { - "encoding": "windows-1256", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -5.511862527725, - "hits": 0, - "total": 215, - "hitRate": 0 - }, - { - "encoding": "windows-874", - "confidence": 0, - "language": "th", - "byteLogLikelihood": -5.737138560752, - "hits": 0, - "total": 215, - "hitRate": 0 - }, - { - "encoding": "KOI8-R", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.692083742507, - "hits": 0, - "total": 215, - "hitRate": 0 - }, - { - "encoding": "KOI8-U", - "confidence": 0, - "language": "uk", - "byteLogLikelihood": -6.650279048587, - "hits": 0, - "total": 215, - "hitRate": 0 - }, - { - "encoding": "IBM866", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.695189876932, - "hits": 0, - "total": 216, - "hitRate": 0 - }, - { - "encoding": "IBM855", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.428281637736, - "hits": 0, - "total": 216, - "hitRate": 0 - }, - { - "encoding": "x-mac-cyrillic", - "confidence": 0, - "language": "uk", - "byteLogLikelihood": -5.621314697937, - "hits": 0, - "total": 216, - "hitRate": 0 } ] }, @@ -426,8 +244,8 @@ }, "predicted": { "encoding": "CP850", - "confidence": 61, "language": "es", + "confidence": 61, "byteLogLikelihood": -3.834657935767, "hits": 41, "total": 200, @@ -441,8 +259,8 @@ "candidates": [ { "encoding": "CP850", - "confidence": 61, "language": "es", + "confidence": 61, "byteLogLikelihood": -3.834657935767, "hits": 41, "total": 200, @@ -450,8 +268,8 @@ }, { "encoding": "ISO-8859-1", - "confidence": 58, "language": "es", + "confidence": 58, "byteLogLikelihood": -4.948759890378, "hits": 39, "total": 199, @@ -459,8 +277,8 @@ }, { "encoding": "windows-1252", - "confidence": 58, "language": "es", + "confidence": 58, "byteLogLikelihood": -4.948759890378, "hits": 39, "total": 199, @@ -468,8 +286,8 @@ }, { "encoding": "macintosh", - "confidence": 58, "language": "es", + "confidence": 58, "byteLogLikelihood": -4.948759890378, "hits": 39, "total": 199, @@ -477,8 +295,8 @@ }, { "encoding": "ISO-8859-15", - "confidence": 58, "language": "es", + "confidence": 58, "byteLogLikelihood": -4.948759890378, "hits": 39, "total": 199, @@ -486,215 +304,44 @@ }, { "encoding": "windows-1257", - "confidence": 25, "language": "lv", - "byteLogLikelihood": -5.19295685089, - "hits": 17, - "total": 199, - "hitRate": 0.08542713567839195 - }, - { - "encoding": "ISO-8859-4", "confidence": 25, - "language": "lv", "byteLogLikelihood": -5.19295685089, "hits": 17, "total": 199, "hitRate": 0.08542713567839195 }, - { - "encoding": "ISO-8859-13", - "confidence": 19, - "language": "lt", - "byteLogLikelihood": -5.123963979403, - "hits": 13, - "total": 199, - "hitRate": 0.06532663316582915 - }, { "encoding": "ISO-8859-14", - "confidence": 16, "language": "cy", + "confidence": 16, "byteLogLikelihood": -4.912654885736, "hits": 11, "total": 199, "hitRate": 0.05527638190954774 }, - { - "encoding": "ISO-8859-2", - "confidence": 15, - "language": "ro", - "byteLogLikelihood": -5.176149732574, - "hits": 10, - "total": 199, - "hitRate": 0.05025125628140704 - }, - { - "encoding": "windows-1250", - "confidence": 15, - "language": "ro", - "byteLogLikelihood": -5.176149732574, - "hits": 10, - "total": 199, - "hitRate": 0.05025125628140704 - }, { "encoding": "ISO-8859-16", - "confidence": 15, "language": "ro", + "confidence": 15, "byteLogLikelihood": -4.952116173006, "hits": 10, "total": 199, "hitRate": 0.05025125628140704 }, { - "encoding": "ISO-8859-9", - "confidence": 7, - "language": "tr", - "byteLogLikelihood": -5.075173815234, - "hits": 5, + "encoding": "windows-874", + "language": "th", + "confidence": 0, + "byteLogLikelihood": -4.61627103998, + "hits": 0, "total": 199, - "hitRate": 0.02512562814070352 - }, - { - "encoding": "windows-1254", - "confidence": 7, - "language": "tr", - "byteLogLikelihood": -5.075173815234, - "hits": 5, - "total": 199, - "hitRate": 0.02512562814070352 - }, - { - "encoding": "windows-1258", - "confidence": 7, - "language": "vi", - "byteLogLikelihood": -5.497168225293, - "hits": 5, - "total": 199, - "hitRate": 0.02512562814070352 - }, - { - "encoding": "CP852", - "confidence": 7, - "language": "pl", - "byteLogLikelihood": -5.087596335232, - "hits": 5, - "total": 200, - "hitRate": 0.025 - }, - { - "encoding": "ISO-8859-10", - "confidence": 4, - "language": "is", - "byteLogLikelihood": -5.204006687077, - "hits": 3, - "total": 199, - "hitRate": 0.01507537688442211 - }, - { - "encoding": "ISO-8859-5", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.692083742507, - "hits": 0, - "total": 199, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-6", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -6.113682179832, - "hits": 0, - "total": 199, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-7", - "confidence": 0, - "language": "el", - "byteLogLikelihood": -6.120297418951, - "hits": 0, - "total": 199, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-8", - "confidence": 0, - "language": "he", - "byteLogLikelihood": -5.932245187448, - "hits": 0, - "total": 199, - "hitRate": 0 - }, - { - "encoding": "windows-1251", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.692083742507, - "hits": 0, - "total": 199, - "hitRate": 0 - }, - { - "encoding": "windows-1253", - "confidence": 0, - "language": "el", - "byteLogLikelihood": -6.120297418951, - "hits": 0, - "total": 199, - "hitRate": 0 - }, - { - "encoding": "windows-1255", - "confidence": 0, - "language": "he", - "byteLogLikelihood": -5.932245187448, - "hits": 0, - "total": 199, - "hitRate": 0 - }, - { - "encoding": "windows-1256", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -6.113682179832, - "hits": 0, - "total": 199, - "hitRate": 0 - }, - { - "encoding": "windows-874", - "confidence": 0, - "language": "th", - "byteLogLikelihood": -4.61627103998, - "hits": 0, - "total": 199, - "hitRate": 0 - }, - { - "encoding": "KOI8-R", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.692083742507, - "hits": 0, - "total": 199, - "hitRate": 0 - }, - { - "encoding": "KOI8-U", - "confidence": 0, - "language": "uk", - "byteLogLikelihood": -6.351652470383, - "hits": 0, - "total": 199, - "hitRate": 0 + "hitRate": 0 }, { "encoding": "IBM866", - "confidence": 0, "language": "ru", + "confidence": 0, "byteLogLikelihood": -3.374008967132, "hits": 0, "total": 200, @@ -702,26 +349,17 @@ }, { "encoding": "IBM855", - "confidence": 0, "language": "sr", + "confidence": 0, "byteLogLikelihood": -4.64715417232, "hits": 0, "total": 200, "hitRate": 0 }, - { - "encoding": "x-mac-cyrillic", - "confidence": 0, - "language": "uk", - "byteLogLikelihood": -6.650279048587, - "hits": 0, - "total": 199, - "hitRate": 0 - }, { "encoding": "ISO-8859-3", - "confidence": 0, "language": "mt", + "confidence": 0, "byteLogLikelihood": -4.759371883621, "hits": 0, "total": 199, @@ -736,8 +374,8 @@ }, "predicted": { "encoding": "CP850", - "confidence": 77, "language": "fr", + "confidence": 77, "byteLogLikelihood": -2.06619631493, "hits": 59, "total": 228, @@ -751,35 +389,35 @@ "candidates": [ { "encoding": "CP850", - "confidence": 77, "language": "fr", + "confidence": 77, "byteLogLikelihood": -2.06619631493, "hits": 59, "total": 228, "hitRate": 0.25877192982456143 }, { - "encoding": "ISO-8859-1", - "confidence": 75, + "encoding": "windows-1252", "language": "fr", + "confidence": 75, "byteLogLikelihood": -5.010635294096, "hits": 56, "total": 224, "hitRate": 0.25 }, { - "encoding": "windows-1252", - "confidence": 75, + "encoding": "ISO-8859-15", "language": "fr", + "confidence": 75, "byteLogLikelihood": -5.010635294096, "hits": 56, "total": 224, "hitRate": 0.25 }, { - "encoding": "ISO-8859-15", - "confidence": 75, + "encoding": "ISO-8859-1", "language": "fr", + "confidence": 75, "byteLogLikelihood": -5.010635294096, "hits": 56, "total": 224, @@ -787,8 +425,8 @@ }, { "encoding": "macintosh", - "confidence": 71, "language": "fr", + "confidence": 71, "byteLogLikelihood": -5.010635294096, "hits": 54, "total": 228, @@ -796,8 +434,8 @@ }, { "encoding": "ISO-8859-2", - "confidence": 12, "language": "ro", + "confidence": 12, "byteLogLikelihood": -5.176149732574, "hits": 9, "total": 224, @@ -805,62 +443,26 @@ }, { "encoding": "windows-1250", - "confidence": 12, "language": "ro", - "byteLogLikelihood": -5.176149732574, - "hits": 9, - "total": 224, - "hitRate": 0.04017857142857143 - }, - { - "encoding": "ISO-8859-10", - "confidence": 12, - "language": "is", - "byteLogLikelihood": -5.204006687077, - "hits": 9, - "total": 224, - "hitRate": 0.04017857142857143 - }, - { - "encoding": "ISO-8859-16", "confidence": 12, - "language": "ro", - "byteLogLikelihood": -5.220355825078, + "byteLogLikelihood": -5.176149732574, "hits": 9, "total": 224, "hitRate": 0.04017857142857143 }, { "encoding": "windows-1257", - "confidence": 9, "language": "lv", - "byteLogLikelihood": -5.19295685089, - "hits": 7, - "total": 224, - "hitRate": 0.03125 - }, - { - "encoding": "ISO-8859-4", "confidence": 9, - "language": "lv", "byteLogLikelihood": -5.19295685089, "hits": 7, "total": 224, "hitRate": 0.03125 }, - { - "encoding": "ISO-8859-3", - "confidence": 8, - "language": "mt", - "byteLogLikelihood": -5.105945473901, - "hits": 6, - "total": 224, - "hitRate": 0.026785714285714284 - }, { "encoding": "CP852", - "confidence": 7, "language": "pl", + "confidence": 7, "byteLogLikelihood": -5.087596335232, "hits": 6, "total": 228, @@ -868,8 +470,8 @@ }, { "encoding": "ISO-8859-9", - "confidence": 6, "language": "tr", + "confidence": 6, "byteLogLikelihood": -5.075173815234, "hits": 5, "total": 224, @@ -877,219 +479,66 @@ }, { "encoding": "windows-1254", - "confidence": 6, "language": "tr", - "byteLogLikelihood": -5.075173815234, - "hits": 5, - "total": 224, - "hitRate": 0.022321428571428572 - }, - { - "encoding": "windows-1258", "confidence": 6, - "language": "vi", - "byteLogLikelihood": -5.497168225293, + "byteLogLikelihood": -5.075173815234, "hits": 5, "total": 224, "hitRate": 0.022321428571428572 }, - { - "encoding": "ISO-8859-13", - "confidence": 5, - "language": "lt", - "byteLogLikelihood": -5.123963979403, - "hits": 4, - "total": 224, - "hitRate": 0.017857142857142856 - }, { "encoding": "ISO-8859-14", - "confidence": 4, "language": "cy", + "confidence": 4, "byteLogLikelihood": -4.912654885736, "hits": 3, "total": 224, "hitRate": 0.013392857142857142 + } + ] + }, + { + "expected": { + "encoding": "CP852", + "language": "pl" + }, + "predicted": { + "encoding": "CP852", + "language": "pl", + "confidence": 40, + "byteLogLikelihood": -3.52910527172, + "hits": 25, + "total": 184, + "hitRate": 0.1358695652173913 + }, + "encodingExact": true, + "encodingEquivalent": false, + "encodingCorrect": true, + "languageCorrect": true, + "tiedAtTop": 1, + "candidates": [ + { + "encoding": "CP852", + "language": "pl", + "confidence": 40, + "byteLogLikelihood": -3.52910527172, + "hits": 25, + "total": 184, + "hitRate": 0.1358695652173913 }, { - "encoding": "ISO-8859-5", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.692083742507, - "hits": 0, - "total": 224, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-6", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -6.113682179832, - "hits": 0, - "total": 224, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-7", - "confidence": 0, - "language": "el", - "byteLogLikelihood": -6.120297418951, - "hits": 0, - "total": 224, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-8", - "confidence": 0, - "language": "he", - "byteLogLikelihood": -5.932245187448, - "hits": 0, - "total": 224, - "hitRate": 0 - }, - { - "encoding": "windows-1251", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.692083742507, - "hits": 0, - "total": 224, - "hitRate": 0 - }, - { - "encoding": "windows-1253", - "confidence": 0, - "language": "el", - "byteLogLikelihood": -6.120297418951, - "hits": 0, - "total": 224, - "hitRate": 0 - }, - { - "encoding": "windows-1255", - "confidence": 0, - "language": "he", - "byteLogLikelihood": -5.932245187448, - "hits": 0, - "total": 224, - "hitRate": 0 - }, - { - "encoding": "windows-1256", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -6.113682179832, - "hits": 0, - "total": 224, - "hitRate": 0 - }, - { - "encoding": "windows-874", - "confidence": 0, - "language": "th", - "byteLogLikelihood": -6.061456918928, - "hits": 0, - "total": 224, - "hitRate": 0 - }, - { - "encoding": "KOI8-R", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.692083742507, - "hits": 0, - "total": 224, - "hitRate": 0 - }, - { - "encoding": "KOI8-U", - "confidence": 0, - "language": "uk", - "byteLogLikelihood": -6.650279048587, - "hits": 0, - "total": 224, - "hitRate": 0 - }, - { - "encoding": "IBM866", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.998936561947, - "hits": 0, - "total": 228, - "hitRate": 0 - }, - { - "encoding": "IBM855", - "confidence": 0, - "language": "sr", - "byteLogLikelihood": -6.520621127559, - "hits": 0, - "total": 228, - "hitRate": 0 - }, - { - "encoding": "x-mac-cyrillic", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.998936561947, - "hits": 0, - "total": 228, - "hitRate": 0 - } - ] - }, - { - "expected": { - "encoding": "CP852", - "language": "pl" - }, - "predicted": { - "encoding": "CP852", - "confidence": 40, - "language": "pl", - "byteLogLikelihood": -3.52910527172, - "hits": 25, - "total": 184, - "hitRate": 0.1358695652173913 - }, - "encodingExact": true, - "encodingEquivalent": false, - "encodingCorrect": true, - "languageCorrect": true, - "tiedAtTop": 2, - "candidates": [ - { - "encoding": "CP852", - "confidence": 40, - "language": "pl", - "byteLogLikelihood": -3.52910527172, - "hits": 25, - "total": 184, - "hitRate": 0.1358695652173913 - }, - { - "encoding": "windows-1250", - "confidence": 40, - "language": "pl", - "byteLogLikelihood": -5.087596335232, - "hits": 25, - "total": 184, - "hitRate": 0.1358695652173913 - }, - { - "encoding": "ISO-8859-2", - "confidence": 37, - "language": "pl", - "byteLogLikelihood": -5.087596335232, - "hits": 23, - "total": 184, - "hitRate": 0.125 + "encoding": "ISO-8859-2", + "language": "pl", + "confidence": 37, + "byteLogLikelihood": -5.087596335232, + "hits": 23, + "total": 184, + "hitRate": 0.125 }, { "encoding": "ISO-8859-1", - "confidence": 8, "language": "it", + "confidence": 8, "byteLogLikelihood": -4.919980925828, "hits": 5, "total": 183, @@ -1097,8 +546,8 @@ }, { "encoding": "windows-1252", - "confidence": 8, "language": "it", + "confidence": 8, "byteLogLikelihood": -4.919980925828, "hits": 5, "total": 183, @@ -1106,8 +555,8 @@ }, { "encoding": "windows-1257", - "confidence": 6, "language": "et", + "confidence": 6, "byteLogLikelihood": -4.536305162191, "hits": 4, "total": 183, @@ -1115,98 +564,44 @@ }, { "encoding": "macintosh", - "confidence": 6, "language": "fr", + "confidence": 6, "byteLogLikelihood": -5.010635294096, "hits": 4, "total": 182, "hitRate": 0.02197802197802198 }, - { - "encoding": "ISO-8859-13", - "confidence": 6, - "language": "lt", - "byteLogLikelihood": -5.123963979403, - "hits": 4, - "total": 183, - "hitRate": 0.02185792349726776 - }, { "encoding": "ISO-8859-15", - "confidence": 6, "language": "es", + "confidence": 6, "byteLogLikelihood": -4.948759890378, "hits": 4, "total": 183, "hitRate": 0.02185792349726776 }, - { - "encoding": "windows-1258", - "confidence": 4, - "language": "vi", - "byteLogLikelihood": -5.497168225293, - "hits": 3, - "total": 183, - "hitRate": 0.01639344262295082 - }, - { - "encoding": "ISO-8859-3", - "confidence": 4, - "language": "mt", - "byteLogLikelihood": -5.105945473901, - "hits": 3, - "total": 183, - "hitRate": 0.01639344262295082 - }, - { - "encoding": "ISO-8859-4", - "confidence": 4, - "language": "lv", - "byteLogLikelihood": -5.19295685089, - "hits": 3, - "total": 184, - "hitRate": 0.016304347826086956 - }, { "encoding": "CP850", - "confidence": 4, "language": "fr", + "confidence": 4, "byteLogLikelihood": -5.010635294096, "hits": 3, "total": 184, "hitRate": 0.016304347826086956 }, - { - "encoding": "ISO-8859-10", - "confidence": 3, - "language": "is", - "byteLogLikelihood": -5.204006687077, - "hits": 2, - "total": 184, - "hitRate": 0.010869565217391304 - }, { "encoding": "ISO-8859-14", - "confidence": 3, "language": "cy", + "confidence": 3, "byteLogLikelihood": -4.912654885736, "hits": 2, "total": 184, "hitRate": 0.010869565217391304 }, - { - "encoding": "ISO-8859-16", - "confidence": 3, - "language": "ro", - "byteLogLikelihood": -5.220355825078, - "hits": 2, - "total": 183, - "hitRate": 0.01092896174863388 - }, { "encoding": "ISO-8859-9", - "confidence": 1, "language": "tr", + "confidence": 1, "byteLogLikelihood": -5.075173815234, "hits": 1, "total": 183, @@ -1214,137 +609,150 @@ }, { "encoding": "windows-1254", - "confidence": 1, "language": "tr", + "confidence": 1, "byteLogLikelihood": -5.075173815234, "hits": 1, "total": 183, "hitRate": 0.00546448087431694 }, { - "encoding": "ISO-8859-5", - "confidence": 0, + "encoding": "IBM866", "language": "ru", - "byteLogLikelihood": -6.692083742507, + "confidence": 0, + "byteLogLikelihood": -5.085936520567, "hits": 0, "total": 184, "hitRate": 0 + } + ] + }, + { + "expected": { + "encoding": "IBM855", + "language": "ru" + }, + "predicted": { + "encoding": "IBM855", + "language": "ru", + "confidence": 43, + "byteLogLikelihood": -3.313760777855, + "hits": 26, + "total": 179, + "hitRate": 0.1452513966480447 + }, + "encodingExact": true, + "encodingEquivalent": false, + "encodingCorrect": true, + "languageCorrect": true, + "tiedAtTop": 1, + "candidates": [ + { + "encoding": "IBM855", + "language": "ru", + "confidence": 43, + "byteLogLikelihood": -3.313760777855, + "hits": 26, + "total": 179, + "hitRate": 0.1452513966480447 }, { - "encoding": "ISO-8859-6", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -5.311255977022, - "hits": 0, - "total": 183, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-7", - "confidence": 0, - "language": "el", - "byteLogLikelihood": -5.762644549521, - "hits": 0, - "total": 183, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-8", - "confidence": 0, - "language": "he", - "byteLogLikelihood": -5.302642222102, - "hits": 0, - "total": 183, - "hitRate": 0 + "encoding": "ISO-8859-14", + "language": "cy", + "confidence": 1, + "byteLogLikelihood": -4.908064507057, + "hits": 1, + "total": 174, + "hitRate": 0.005747126436781609 }, { - "encoding": "windows-1251", + "encoding": "ISO-8859-1", + "language": "pt", "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.005185419538, + "byteLogLikelihood": -4.789358524023, "hits": 0, - "total": 184, + "total": 139, "hitRate": 0 }, { - "encoding": "windows-1253", + "encoding": "ISO-8859-2", + "language": "hu", "confidence": 0, - "language": "el", - "byteLogLikelihood": -5.762644549521, + "byteLogLikelihood": -4.901389021393, "hits": 0, - "total": 183, + "total": 165, "hitRate": 0 }, { - "encoding": "windows-1255", + "encoding": "windows-1250", + "language": "hu", "confidence": 0, - "language": "he", - "byteLogLikelihood": -5.302642222102, + "byteLogLikelihood": -4.901389021393, "hits": 0, - "total": 183, + "total": 141, "hitRate": 0 }, { - "encoding": "windows-1256", + "encoding": "windows-1252", + "language": "pt", "confidence": 0, - "language": "ar", - "byteLogLikelihood": -5.54369343373, + "byteLogLikelihood": -4.789358524023, "hits": 0, - "total": 183, + "total": 141, "hitRate": 0 }, { - "encoding": "windows-874", + "encoding": "windows-1257", + "language": "lt", "confidence": 0, - "language": "th", - "byteLogLikelihood": -5.549771342707, + "byteLogLikelihood": -4.913061957297, "hits": 0, - "total": 184, + "total": 149, "hitRate": 0 }, { - "encoding": "KOI8-R", + "encoding": "macintosh", + "language": "es", "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.538051035716, + "byteLogLikelihood": -4.934208734237, "hits": 0, - "total": 183, + "total": 73, "hitRate": 0 }, { - "encoding": "KOI8-U", + "encoding": "ISO-8859-3", + "language": "mt", "confidence": 0, - "language": "uk", - "byteLogLikelihood": -6.496246341796, + "byteLogLikelihood": -5.011017819902, "hits": 0, - "total": 183, + "total": 123, "hitRate": 0 }, { - "encoding": "IBM866", + "encoding": "ISO-8859-13", + "language": "lt", "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.085936520567, + "byteLogLikelihood": -4.913061957297, "hits": 0, - "total": 184, + "total": 149, "hitRate": 0 }, { - "encoding": "IBM855", + "encoding": "ISO-8859-15", + "language": "es", "confidence": 0, - "language": "sr", - "byteLogLikelihood": -5.780131236409, + "byteLogLikelihood": -4.805721913065, "hits": 0, - "total": 184, + "total": 160, "hitRate": 0 }, { - "encoding": "x-mac-cyrillic", + "encoding": "CP850", + "language": "es", "confidence": 0, - "language": "uk", - "byteLogLikelihood": -5.963380725619, + "byteLogLikelihood": -4.829101213886, "hits": 0, - "total": 183, + "total": 167, "hitRate": 0 } ] @@ -1352,16 +760,16 @@ { "expected": { "encoding": "IBM855", - "language": "ru" + "language": "sr" }, "predicted": { "encoding": "IBM855", - "confidence": 43, - "language": "ru", - "byteLogLikelihood": -3.313760777855, - "hits": 26, - "total": 179, - "hitRate": 0.1452513966480447 + "language": "sr", + "confidence": 28, + "byteLogLikelihood": -3.307897947426, + "hits": 16, + "total": 166, + "hitRate": 0.0963855421686747 }, "encodingExact": true, "encodingEquivalent": false, @@ -1371,910 +779,890 @@ "candidates": [ { "encoding": "IBM855", - "confidence": 43, - "language": "ru", - "byteLogLikelihood": -3.313760777855, - "hits": 26, - "total": 179, - "hitRate": 0.1452513966480447 - }, - { - "encoding": "KOI8-U", - "confidence": 12, - "language": "uk", - "byteLogLikelihood": -5.728613539801, - "hits": 7, - "total": 171, - "hitRate": 0.04093567251461988 + "language": "sr", + "confidence": 28, + "byteLogLikelihood": -3.307897947426, + "hits": 16, + "total": 166, + "hitRate": 0.0963855421686747 }, { "encoding": "IBM866", - "confidence": 11, - "language": "ru", - "byteLogLikelihood": -5.08851401058, - "hits": 5, - "total": 130, - "hitRate": 0.038461538461538464 - }, - { - "encoding": "windows-874", - "confidence": 10, - "language": "th", - "byteLogLikelihood": -5.027512765832, - "hits": 5, - "total": 146, - "hitRate": 0.03424657534246575 - }, - { - "encoding": "KOI8-R", - "confidence": 10, "language": "ru", - "byteLogLikelihood": -6.090200292669, - "hits": 5, - "total": 140, - "hitRate": 0.03571428571428571 - }, - { - "encoding": "ISO-8859-7", - "confidence": 6, - "language": "el", - "byteLogLikelihood": -5.19500629466, - "hits": 3, - "total": 138, - "hitRate": 0.021739130434782608 - }, - { - "encoding": "windows-1253", - "confidence": 6, - "language": "el", - "byteLogLikelihood": -5.19500629466, - "hits": 3, - "total": 139, - "hitRate": 0.02158273381294964 - }, - { - "encoding": "x-mac-cyrillic", - "confidence": 4, - "language": "uk", - "byteLogLikelihood": -5.827543836069, - "hits": 2, + "confidence": 26, + "byteLogLikelihood": -4.750368103744, + "hits": 12, "total": 137, - "hitRate": 0.014598540145985401 - }, - { - "encoding": "ISO-8859-5", - "confidence": 1, - "language": "ru", - "byteLogLikelihood": -5.217274879676, - "hits": 1, - "total": 175, - "hitRate": 0.005714285714285714 - }, - { - "encoding": "ISO-8859-10", - "confidence": 1, - "language": "is", - "byteLogLikelihood": -5.06395526639, - "hits": 1, - "total": 160, - "hitRate": 0.00625 - }, - { - "encoding": "ISO-8859-14", - "confidence": 1, - "language": "cy", - "byteLogLikelihood": -4.908064507057, - "hits": 1, - "total": 174, - "hitRate": 0.005747126436781609 + "hitRate": 0.08759124087591241 }, { "encoding": "ISO-8859-1", - "confidence": 0, "language": "pt", - "byteLogLikelihood": -4.789358524023, + "confidence": 0, + "byteLogLikelihood": -4.764166439133, "hits": 0, - "total": 139, + "total": 104, "hitRate": 0 }, { "encoding": "ISO-8859-2", - "confidence": 0, "language": "hu", - "byteLogLikelihood": -4.901389021393, + "confidence": 0, + "byteLogLikelihood": -4.902465386166, "hits": 0, - "total": 165, + "total": 128, "hitRate": 0 }, { - "encoding": "ISO-8859-6", + "encoding": "windows-1250", + "language": "hu", "confidence": 0, - "language": "ar", - "byteLogLikelihood": -5.523443710193, + "byteLogLikelihood": -4.902465386166, "hits": 0, "total": 110, "hitRate": 0 }, { - "encoding": "ISO-8859-8", + "encoding": "windows-1252", + "language": "pt", "confidence": 0, - "language": "he", - "byteLogLikelihood": -5.21454182173, + "byteLogLikelihood": -4.764166439133, "hits": 0, - "total": 84, + "total": 110, "hitRate": 0 }, { - "encoding": "ISO-8859-9", + "encoding": "windows-1257", + "language": "et", "confidence": 0, - "language": "tr", - "byteLogLikelihood": -5.033184680772, + "byteLogLikelihood": -4.902859191011, "hits": 0, - "total": 139, + "total": 136, "hitRate": 0 }, { - "encoding": "windows-1250", + "encoding": "macintosh", + "language": "es", "confidence": 0, - "language": "hu", - "byteLogLikelihood": -4.901389021393, + "byteLogLikelihood": -4.933799879287, "hits": 0, - "total": 141, + "total": 73, "hitRate": 0 }, { - "encoding": "windows-1251", + "encoding": "ISO-8859-13", + "language": "lt", "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.690578567068, + "byteLogLikelihood": -4.940581981725, "hits": 0, - "total": 156, + "total": 132, "hitRate": 0 }, { - "encoding": "windows-1252", + "encoding": "ISO-8859-14", + "language": "cy", "confidence": 0, - "language": "pt", - "byteLogLikelihood": -4.789358524023, + "byteLogLikelihood": -4.907668215372, "hits": 0, - "total": 141, + "total": 157, "hitRate": 0 }, { - "encoding": "windows-1254", + "encoding": "ISO-8859-15", + "language": "es", "confidence": 0, - "language": "tr", - "byteLogLikelihood": -5.033184680772, + "byteLogLikelihood": -4.832419313648, "hits": 0, - "total": 141, + "total": 138, "hitRate": 0 }, { - "encoding": "windows-1255", + "encoding": "CP850", + "language": "es", "confidence": 0, - "language": "he", - "byteLogLikelihood": -5.21454182173, + "byteLogLikelihood": -4.704589417548, "hits": 0, - "total": 102, + "total": 150, "hitRate": 0 + } + ] + }, + { + "expected": { + "encoding": "IBM866", + "language": "ru" + }, + "predicted": { + "encoding": "IBM866", + "language": "ru", + "confidence": 41, + "byteLogLikelihood": -3.313760777855, + "hits": 25, + "total": 179, + "hitRate": 0.13966480446927373 + }, + "encodingExact": true, + "encodingEquivalent": false, + "encodingCorrect": true, + "languageCorrect": true, + "tiedAtTop": 1, + "candidates": [ + { + "encoding": "IBM866", + "language": "ru", + "confidence": 41, + "byteLogLikelihood": -3.313760777855, + "hits": 25, + "total": 179, + "hitRate": 0.13966480446927373 }, { - "encoding": "windows-1256", + "encoding": "ISO-8859-14", + "language": "cy", + "confidence": 1, + "byteLogLikelihood": -4.83002806951, + "hits": 1, + "total": 169, + "hitRate": 0.005917159763313609 + }, + { + "encoding": "ISO-8859-1", + "language": "it", "confidence": 0, - "language": "ar", - "byteLogLikelihood": -5.354655838496, + "byteLogLikelihood": -4.841944488282, "hits": 0, - "total": 135, + "total": 81, "hitRate": 0 }, { - "encoding": "windows-1257", + "encoding": "ISO-8859-2", + "language": "hu", "confidence": 0, - "language": "lt", - "byteLogLikelihood": -4.913061957297, + "byteLogLikelihood": -4.941337938888, "hits": 0, - "total": 149, + "total": 145, "hitRate": 0 }, { - "encoding": "windows-1258", + "encoding": "windows-1250", + "language": "hu", "confidence": 0, - "language": "vi", - "byteLogLikelihood": -5.237936257135, + "byteLogLikelihood": -4.941337938888, "hits": 0, - "total": 134, + "total": 117, "hitRate": 0 }, { - "encoding": "macintosh", + "encoding": "windows-1252", + "language": "it", "confidence": 0, - "language": "es", - "byteLogLikelihood": -4.934208734237, + "byteLogLikelihood": -4.841944488282, "hits": 0, - "total": 73, + "total": 82, "hitRate": 0 }, { - "encoding": "ISO-8859-3", + "encoding": "windows-1257", + "language": "lv", "confidence": 0, - "language": "mt", - "byteLogLikelihood": -5.011017819902, + "byteLogLikelihood": -4.928541579896, "hits": 0, - "total": 123, + "total": 117, "hitRate": 0 }, { - "encoding": "ISO-8859-4", + "encoding": "macintosh", + "language": "es", "confidence": 0, - "language": "lv", - "byteLogLikelihood": -5.171130116678, + "byteLogLikelihood": -4.944169511699, "hits": 0, - "total": 169, + "total": 67, "hitRate": 0 }, { "encoding": "ISO-8859-13", - "confidence": 0, "language": "lt", - "byteLogLikelihood": -4.913061957297, + "confidence": 0, + "byteLogLikelihood": -4.939479070188, "hits": 0, - "total": 149, + "total": 116, "hitRate": 0 }, { "encoding": "ISO-8859-15", - "confidence": 0, "language": "es", - "byteLogLikelihood": -4.805721913065, - "hits": 0, - "total": 160, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-16", "confidence": 0, - "language": "ro", - "byteLogLikelihood": -5.025462977445, + "byteLogLikelihood": -4.848242748706, "hits": 0, - "total": 162, + "total": 111, "hitRate": 0 }, { "encoding": "CP850", - "confidence": 0, "language": "es", - "byteLogLikelihood": -4.829101213886, + "confidence": 0, + "byteLogLikelihood": -4.677183836449, "hits": 0, - "total": 167, + "total": 130, "hitRate": 0 }, { "encoding": "CP852", - "confidence": 0, "language": "pl", - "byteLogLikelihood": -5.06627927679, + "confidence": 0, + "byteLogLikelihood": -4.699618505771, "hits": 0, - "total": 178, + "total": 166, "hitRate": 0 } ] }, { "expected": { - "encoding": "IBM855", - "language": "sr" + "encoding": "ISO-8859-1", + "language": "da" }, "predicted": { - "encoding": "IBM855", - "confidence": 28, - "language": "sr", - "byteLogLikelihood": -3.307897947426, - "hits": 16, - "total": 166, - "hitRate": 0.0963855421686747 + "encoding": "ISO-8859-1", + "language": "da", + "confidence": 52, + "byteLogLikelihood": -3.146558879633, + "hits": 21, + "total": 120, + "hitRate": 0.175 }, "encodingExact": true, "encodingEquivalent": false, "encodingCorrect": true, "languageCorrect": true, - "tiedAtTop": 1, + "tiedAtTop": 2, "candidates": [ { - "encoding": "IBM855", - "confidence": 28, - "language": "sr", - "byteLogLikelihood": -3.307897947426, - "hits": 16, - "total": 166, - "hitRate": 0.0963855421686747 - }, - { - "encoding": "IBM866", - "confidence": 26, - "language": "ru", - "byteLogLikelihood": -4.750368103744, - "hits": 12, - "total": 137, - "hitRate": 0.08759124087591241 + "encoding": "ISO-8859-1", + "language": "da", + "confidence": 52, + "byteLogLikelihood": -3.146558879633, + "hits": 21, + "total": 120, + "hitRate": 0.175 }, { - "encoding": "windows-874", - "confidence": 35, - "language": "th", - "byteLogLikelihood": -5.092901405888, - "hits": 15, - "total": 128, - "hitRate": 0.1171875 + "encoding": "windows-1252", + "language": "da", + "confidence": 52, + "byteLogLikelihood": -3.146558879633, + "hits": 21, + "total": 120, + "hitRate": 0.175 }, { - "encoding": "KOI8-R", - "confidence": 11, - "language": "ru", - "byteLogLikelihood": -6.207100144751, + "encoding": "ISO-8859-2", + "language": "ro", + "confidence": 10, + "byteLogLikelihood": -5.176149732574, "hits": 4, - "total": 104, - "hitRate": 0.038461538461538464 + "total": 120, + "hitRate": 0.03333333333333333 }, { - "encoding": "KOI8-U", - "confidence": 9, - "language": "uk", - "byteLogLikelihood": -5.956096731591, + "encoding": "windows-1250", + "language": "ro", + "confidence": 10, + "byteLogLikelihood": -5.176149732574, "hits": 4, - "total": 130, - "hitRate": 0.03076923076923077 + "total": 120, + "hitRate": 0.03333333333333333 }, { - "encoding": "x-mac-cyrillic", - "confidence": 8, - "language": "uk", - "byteLogLikelihood": -5.930887805719, - "hits": 3, - "total": 112, - "hitRate": 0.026785714285714284 + "encoding": "windows-1257", + "language": "et", + "confidence": 10, + "byteLogLikelihood": -4.934473933131, + "hits": 4, + "total": 120, + "hitRate": 0.03333333333333333 }, { - "encoding": "ISO-8859-8", - "confidence": 4, - "language": "he", - "byteLogLikelihood": -5.427107080966, + "encoding": "ISO-8859-3", + "language": "mt", + "confidence": 2, + "byteLogLikelihood": -4.658005606594, "hits": 1, - "total": 64, - "hitRate": 0.015625 + "total": 120, + "hitRate": 0.008333333333333333 }, { - "encoding": "windows-1255", - "confidence": 3, - "language": "he", - "byteLogLikelihood": -5.427107080966, + "encoding": "ISO-8859-13", + "language": "lt", + "confidence": 2, + "byteLogLikelihood": -4.145958228046, "hits": 1, - "total": 80, - "hitRate": 0.0125 + "total": 120, + "hitRate": 0.008333333333333333 }, { - "encoding": "ISO-8859-1", + "encoding": "ISO-8859-7", + "language": "el", "confidence": 0, - "language": "pt", - "byteLogLikelihood": -4.764166439133, + "byteLogLikelihood": -4.689401143463, "hits": 0, - "total": 104, + "total": 120, "hitRate": 0 }, { - "encoding": "ISO-8859-2", + "encoding": "ISO-8859-8", + "language": "he", "confidence": 0, - "language": "hu", - "byteLogLikelihood": -4.902465386166, + "byteLogLikelihood": -3.231348206195, "hits": 0, - "total": 128, + "total": 120, "hitRate": 0 }, { - "encoding": "ISO-8859-5", - "confidence": 0, + "encoding": "windows-1251", "language": "ru", - "byteLogLikelihood": -5.640443286036, + "confidence": 0, + "byteLogLikelihood": -4.288232392491, "hits": 0, - "total": 157, + "total": 120, "hitRate": 0 }, { - "encoding": "ISO-8859-6", + "encoding": "windows-1255", + "language": "he", "confidence": 0, - "language": "ar", - "byteLogLikelihood": -5.592489718341, + "byteLogLikelihood": -3.231348206195, "hits": 0, - "total": 84, + "total": 120, "hitRate": 0 }, { - "encoding": "ISO-8859-7", + "encoding": "x-mac-cyrillic", + "language": "ru", "confidence": 0, - "language": "el", - "byteLogLikelihood": -5.3747848425, + "byteLogLikelihood": -4.288232392491, "hits": 0, - "total": 103, + "total": 120, "hitRate": 0 + } + ] + }, + { + "expected": { + "encoding": "ISO-8859-1", + "language": "de" + }, + "predicted": { + "encoding": "ISO-8859-1", + "language": "de", + "confidence": 73, + "byteLogLikelihood": -3.169712077519, + "hits": 53, + "total": 216, + "hitRate": 0.24537037037037038 + }, + "encodingExact": true, + "encodingEquivalent": false, + "encodingCorrect": true, + "languageCorrect": true, + "tiedAtTop": 3, + "candidates": [ + { + "encoding": "ISO-8859-1", + "language": "de", + "confidence": 73, + "byteLogLikelihood": -3.169712077519, + "hits": 53, + "total": 216, + "hitRate": 0.24537037037037038 + }, + { + "encoding": "ISO-8859-15", + "language": "de", + "confidence": 73, + "byteLogLikelihood": -3.169712077519, + "hits": 53, + "total": 216, + "hitRate": 0.24537037037037038 + }, + { + "encoding": "windows-1252", + "language": "de", + "confidence": 73, + "byteLogLikelihood": -3.169712077519, + "hits": 53, + "total": 216, + "hitRate": 0.24537037037037038 }, { "encoding": "ISO-8859-9", - "confidence": 0, "language": "tr", - "byteLogLikelihood": -5.028189084099, - "hits": 0, - "total": 104, - "hitRate": 0 + "confidence": 12, + "byteLogLikelihood": -4.5258676709, + "hits": 9, + "total": 216, + "hitRate": 0.041666666666666664 }, { - "encoding": "windows-1250", + "encoding": "windows-1257", + "language": "lv", + "confidence": 9, + "byteLogLikelihood": -5.19295685089, + "hits": 7, + "total": 216, + "hitRate": 0.032407407407407406 + }, + { + "encoding": "ISO-8859-6", + "language": "ar", "confidence": 0, - "language": "hu", - "byteLogLikelihood": -4.902465386166, + "byteLogLikelihood": -4.007313397456, "hits": 0, - "total": 110, + "total": 216, "hitRate": 0 }, { - "encoding": "windows-1251", + "encoding": "ISO-8859-7", + "language": "el", "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.910594216272, + "byteLogLikelihood": -4.349754587225, "hits": 0, - "total": 144, + "total": 216, "hitRate": 0 }, { - "encoding": "windows-1252", + "encoding": "ISO-8859-8", + "language": "he", "confidence": 0, - "language": "pt", - "byteLogLikelihood": -4.764166439133, + "byteLogLikelihood": -4.279537403415, "hits": 0, - "total": 110, + "total": 216, "hitRate": 0 }, { "encoding": "windows-1253", - "confidence": 0, "language": "el", - "byteLogLikelihood": -5.3747848425, + "confidence": 0, + "byteLogLikelihood": -4.349754587225, "hits": 0, - "total": 107, + "total": 216, "hitRate": 0 }, { - "encoding": "windows-1254", + "encoding": "windows-1255", + "language": "he", "confidence": 0, - "language": "tr", - "byteLogLikelihood": -5.028189084099, + "byteLogLikelihood": -4.279537403415, "hits": 0, - "total": 104, + "total": 216, "hitRate": 0 }, { "encoding": "windows-1256", - "confidence": 0, "language": "ar", - "byteLogLikelihood": -5.564612100894, + "confidence": 0, + "byteLogLikelihood": -4.318835143108, "hits": 0, - "total": 108, + "total": 216, "hitRate": 0 }, { - "encoding": "windows-1257", + "encoding": "x-mac-cyrillic", + "language": "uk", "confidence": 0, - "language": "et", - "byteLogLikelihood": -4.902859191011, + "byteLogLikelihood": -3.629332579687, "hits": 0, - "total": 136, + "total": 216, "hitRate": 0 + } + ] + }, + { + "expected": { + "encoding": "ISO-8859-1", + "language": "en" + }, + "predicted": { + "encoding": "ISO-8859-1", + "language": "en", + "confidence": 47, + "byteLogLikelihood": -3.310543013394, + "hits": 21, + "total": 132, + "hitRate": 0.1590909090909091 + }, + "encodingExact": true, + "encodingEquivalent": false, + "encodingCorrect": true, + "languageCorrect": true, + "tiedAtTop": 2, + "candidates": [ + { + "encoding": "ISO-8859-1", + "language": "en", + "confidence": 47, + "byteLogLikelihood": -3.310543013394, + "hits": 21, + "total": 132, + "hitRate": 0.1590909090909091 }, { - "encoding": "windows-1258", - "confidence": 0, - "language": "vi", - "byteLogLikelihood": -5.23021689626, - "hits": 0, - "total": 103, - "hitRate": 0 + "encoding": "ISO-8859-15", + "language": "fr", + "confidence": 29, + "byteLogLikelihood": -2.06619631493, + "hits": 13, + "total": 132, + "hitRate": 0.09848484848484848 }, { - "encoding": "macintosh", - "confidence": 0, - "language": "es", - "byteLogLikelihood": -4.933799879287, - "hits": 0, - "total": 73, - "hitRate": 0 + "encoding": "windows-1252", + "language": "en", + "confidence": 47, + "byteLogLikelihood": -3.310543013394, + "hits": 21, + "total": 132, + "hitRate": 0.1590909090909091 }, { - "encoding": "ISO-8859-3", - "confidence": 0, - "language": "mt", - "byteLogLikelihood": -4.97248951392, - "hits": 0, - "total": 99, - "hitRate": 0 + "encoding": "ISO-8859-2", + "language": "cs", + "confidence": 9, + "byteLogLikelihood": -3.54961738678, + "hits": 4, + "total": 132, + "hitRate": 0.030303030303030304 }, { - "encoding": "ISO-8859-4", - "confidence": 0, - "language": "lv", - "byteLogLikelihood": -5.19295685089, - "hits": 0, - "total": 131, - "hitRate": 0 + "encoding": "windows-1250", + "language": "cs", + "confidence": 9, + "byteLogLikelihood": -3.54961738678, + "hits": 4, + "total": 132, + "hitRate": 0.030303030303030304 }, { - "encoding": "ISO-8859-10", + "encoding": "ISO-8859-7", + "language": "el", "confidence": 0, - "language": "is", - "byteLogLikelihood": -5.076797848077, + "byteLogLikelihood": -2.654561516151, "hits": 0, - "total": 145, + "total": 132, "hitRate": 0 }, { - "encoding": "ISO-8859-13", + "encoding": "ISO-8859-8", + "language": "he", "confidence": 0, - "language": "lt", - "byteLogLikelihood": -4.940581981725, + "byteLogLikelihood": -2.405884662832, "hits": 0, "total": 132, "hitRate": 0 }, { - "encoding": "ISO-8859-14", + "encoding": "windows-1253", + "language": "el", "confidence": 0, - "language": "cy", - "byteLogLikelihood": -4.907668215372, + "byteLogLikelihood": -2.654561516151, "hits": 0, - "total": 157, + "total": 132, "hitRate": 0 }, { - "encoding": "ISO-8859-15", + "encoding": "windows-1255", + "language": "he", "confidence": 0, - "language": "es", - "byteLogLikelihood": -4.832419313648, + "byteLogLikelihood": -2.405884662832, "hits": 0, - "total": 138, + "total": 132, "hitRate": 0 }, { - "encoding": "ISO-8859-16", + "encoding": "windows-874", + "language": "th", "confidence": 0, - "language": "ro", - "byteLogLikelihood": -5.086009867584, + "byteLogLikelihood": -3.57655026914, "hits": 0, - "total": 142, + "total": 131, "hitRate": 0 }, { - "encoding": "CP850", + "encoding": "x-mac-cyrillic", + "language": "uk", "confidence": 0, - "language": "es", - "byteLogLikelihood": -4.704589417548, + "byteLogLikelihood": -4.252383775789, "hits": 0, - "total": 150, + "total": 132, "hitRate": 0 }, { - "encoding": "CP852", + "encoding": "ISO-8859-10", + "language": "is", "confidence": 0, - "language": "pl", - "byteLogLikelihood": -5.064438955197, + "byteLogLikelihood": -4.510859506517, "hits": 0, - "total": 165, + "total": 132, "hitRate": 0 } ] }, { "expected": { - "encoding": "IBM866", - "language": "ru" + "encoding": "ISO-8859-1", + "language": "es" }, "predicted": { - "encoding": "IBM866", - "confidence": 41, - "language": "ru", - "byteLogLikelihood": -3.313760777855, - "hits": 25, - "total": 179, - "hitRate": 0.13966480446927373 + "encoding": "ISO-8859-1", + "language": "es", + "confidence": 61, + "byteLogLikelihood": -3.834657935767, + "hits": 41, + "total": 200, + "hitRate": 0.205 }, "encodingExact": true, "encodingEquivalent": false, "encodingCorrect": true, "languageCorrect": true, - "tiedAtTop": 1, + "tiedAtTop": 3, "candidates": [ { - "encoding": "IBM866", - "confidence": 41, - "language": "ru", - "byteLogLikelihood": -3.313760777855, - "hits": 25, - "total": 179, - "hitRate": 0.13966480446927373 - }, - { - "encoding": "KOI8-R", - "confidence": 23, - "language": "ru", - "byteLogLikelihood": -6.620542862927, - "hits": 6, - "total": 77, - "hitRate": 0.07792207792207792 - }, - { - "encoding": "x-mac-cyrillic", - "confidence": 15, - "language": "ru", - "byteLogLikelihood": -5.792699163742, - "hits": 7, - "total": 133, - "hitRate": 0.05263157894736842 - }, - { - "encoding": "KOI8-U", - "confidence": 11, - "language": "uk", - "byteLogLikelihood": -6.434389971368, - "hits": 4, - "total": 103, - "hitRate": 0.038834951456310676 - }, - { - "encoding": "windows-874", - "confidence": 9, - "language": "th", - "byteLogLikelihood": -5.160775609519, - "hits": 5, - "total": 165, - "hitRate": 0.030303030303030304 + "encoding": "ISO-8859-1", + "language": "es", + "confidence": 61, + "byteLogLikelihood": -3.834657935767, + "hits": 41, + "total": 200, + "hitRate": 0.205 }, { - "encoding": "IBM855", - "confidence": 8, - "language": "sr", - "byteLogLikelihood": -5.021646546946, - "hits": 5, - "total": 169, - "hitRate": 0.029585798816568046 + "encoding": "ISO-8859-15", + "language": "es", + "confidence": 61, + "byteLogLikelihood": -3.834657935767, + "hits": 41, + "total": 200, + "hitRate": 0.205 }, { - "encoding": "windows-1251", - "confidence": 7, - "language": "ru", - "byteLogLikelihood": -5.801879921101, - "hits": 4, - "total": 153, - "hitRate": 0.026143790849673203 + "encoding": "windows-1252", + "language": "es", + "confidence": 61, + "byteLogLikelihood": -3.834657935767, + "hits": 41, + "total": 200, + "hitRate": 0.205 }, { - "encoding": "windows-1253", - "confidence": 6, - "language": "el", - "byteLogLikelihood": -5.523099191635, - "hits": 2, - "total": 89, - "hitRate": 0.02247191011235955 + "encoding": "ISO-8859-2", + "language": "ro", + "confidence": 15, + "byteLogLikelihood": -5.176149732574, + "hits": 10, + "total": 200, + "hitRate": 0.05 }, { - "encoding": "ISO-8859-5", - "confidence": 3, - "language": "ru", - "byteLogLikelihood": -5.798412758856, - "hits": 2, - "total": 174, - "hitRate": 0.011494252873563218 + "encoding": "windows-1250", + "language": "ro", + "confidence": 15, + "byteLogLikelihood": -5.176149732574, + "hits": 10, + "total": 200, + "hitRate": 0.05 }, { "encoding": "ISO-8859-7", - "confidence": 3, "language": "el", - "byteLogLikelihood": -5.523099191635, - "hits": 1, - "total": 81, - "hitRate": 0.012345679012345678 - }, - { - "encoding": "ISO-8859-10", - "confidence": 1, - "language": "is", - "byteLogLikelihood": -5.103902669993, - "hits": 1, - "total": 173, - "hitRate": 0.005780346820809248 - }, - { - "encoding": "ISO-8859-14", - "confidence": 1, - "language": "cy", - "byteLogLikelihood": -4.83002806951, - "hits": 1, - "total": 169, - "hitRate": 0.005917159763313609 - }, - { - "encoding": "ISO-8859-1", - "confidence": 0, - "language": "it", - "byteLogLikelihood": -4.841944488282, - "hits": 0, - "total": 81, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-2", - "confidence": 0, - "language": "hu", - "byteLogLikelihood": -4.941337938888, - "hits": 0, - "total": 145, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-6", "confidence": 0, - "language": "ar", - "byteLogLikelihood": -5.82555458734, + "byteLogLikelihood": -3.106555532888, "hits": 0, - "total": 57, + "total": 200, "hitRate": 0 }, { "encoding": "ISO-8859-8", - "confidence": 0, "language": "he", - "byteLogLikelihood": -5.371812787625, - "hits": 0, - "total": 75, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-9", - "confidence": 0, - "language": "tr", - "byteLogLikelihood": -5.062286993055, - "hits": 0, - "total": 81, - "hitRate": 0 - }, - { - "encoding": "windows-1250", "confidence": 0, - "language": "hu", - "byteLogLikelihood": -4.941337938888, + "byteLogLikelihood": -3.411159813207, "hits": 0, - "total": 117, + "total": 200, "hitRate": 0 }, { - "encoding": "windows-1252", + "encoding": "windows-1251", + "language": "ru", "confidence": 0, - "language": "it", - "byteLogLikelihood": -4.841944488282, + "byteLogLikelihood": -3.336328204376, "hits": 0, - "total": 82, + "total": 200, "hitRate": 0 }, { - "encoding": "windows-1254", + "encoding": "windows-1253", + "language": "el", "confidence": 0, - "language": "tr", - "byteLogLikelihood": -5.062286993055, + "byteLogLikelihood": -3.106555532888, "hits": 0, - "total": 81, + "total": 200, "hitRate": 0 }, { "encoding": "windows-1255", - "confidence": 0, "language": "he", - "byteLogLikelihood": -5.371812787625, + "confidence": 0, + "byteLogLikelihood": -3.411159813207, "hits": 0, - "total": 75, + "total": 200, "hitRate": 0 }, { "encoding": "windows-1256", - "confidence": 0, "language": "ar", - "byteLogLikelihood": -5.857645252562, - "hits": 0, - "total": 82, - "hitRate": 0 - }, - { - "encoding": "windows-1257", "confidence": 0, - "language": "lv", - "byteLogLikelihood": -4.928541579896, + "byteLogLikelihood": -3.300604963183, "hits": 0, - "total": 117, + "total": 200, "hitRate": 0 }, { - "encoding": "windows-1258", + "encoding": "x-mac-cyrillic", + "language": "ru", "confidence": 0, - "language": "vi", - "byteLogLikelihood": -5.078371422345, + "byteLogLikelihood": -3.336328204376, "hits": 0, - "total": 76, + "total": 200, "hitRate": 0 + } + ] + }, + { + "expected": { + "encoding": "ISO-8859-1", + "language": "fr" + }, + "predicted": { + "encoding": "ISO-8859-1", + "language": "fr", + "confidence": 77, + "byteLogLikelihood": -2.06619631493, + "hits": 59, + "total": 228, + "hitRate": 0.25877192982456143 + }, + "encodingExact": true, + "encodingEquivalent": false, + "encodingCorrect": true, + "languageCorrect": true, + "tiedAtTop": 3, + "candidates": [ + { + "encoding": "ISO-8859-1", + "language": "fr", + "confidence": 77, + "byteLogLikelihood": -2.06619631493, + "hits": 59, + "total": 228, + "hitRate": 0.25877192982456143 }, { - "encoding": "macintosh", - "confidence": 0, - "language": "es", - "byteLogLikelihood": -4.944169511699, - "hits": 0, - "total": 67, - "hitRate": 0 + "encoding": "ISO-8859-15", + "language": "fr", + "confidence": 77, + "byteLogLikelihood": -2.06619631493, + "hits": 59, + "total": 228, + "hitRate": 0.25877192982456143 }, { - "encoding": "ISO-8859-3", - "confidence": 0, - "language": "mt", - "byteLogLikelihood": -5.096764716542, - "hits": 0, - "total": 116, - "hitRate": 0 + "encoding": "windows-1252", + "language": "fr", + "confidence": 77, + "byteLogLikelihood": -2.06619631493, + "hits": 59, + "total": 228, + "hitRate": 0.25877192982456143 }, { - "encoding": "ISO-8859-4", + "encoding": "ISO-8859-2", + "language": "ro", + "confidence": 11, + "byteLogLikelihood": -5.176149732574, + "hits": 9, + "total": 228, + "hitRate": 0.039473684210526314 + }, + { + "encoding": "windows-1250", + "language": "ro", + "confidence": 11, + "byteLogLikelihood": -5.176149732574, + "hits": 9, + "total": 228, + "hitRate": 0.039473684210526314 + }, + { + "encoding": "ISO-8859-10", + "language": "is", + "confidence": 10, + "byteLogLikelihood": -4.510859506517, + "hits": 8, + "total": 228, + "hitRate": 0.03508771929824561 + }, + { + "encoding": "ISO-8859-7", + "language": "el", "confidence": 0, - "language": "lv", - "byteLogLikelihood": -4.979786266462, + "byteLogLikelihood": -2.654561516151, "hits": 0, - "total": 148, + "total": 228, "hitRate": 0 }, { - "encoding": "ISO-8859-13", + "encoding": "ISO-8859-8", + "language": "he", "confidence": 0, - "language": "lt", - "byteLogLikelihood": -4.939479070188, + "byteLogLikelihood": -2.405884662832, "hits": 0, - "total": 116, + "total": 228, "hitRate": 0 }, { - "encoding": "ISO-8859-15", + "encoding": "windows-1253", + "language": "el", "confidence": 0, - "language": "es", - "byteLogLikelihood": -4.848242748706, + "byteLogLikelihood": -2.654561516151, "hits": 0, - "total": 111, + "total": 228, "hitRate": 0 }, { - "encoding": "ISO-8859-16", + "encoding": "windows-1255", + "language": "he", "confidence": 0, - "language": "ro", - "byteLogLikelihood": -4.987878406509, + "byteLogLikelihood": -2.405884662832, "hits": 0, - "total": 144, + "total": 228, "hitRate": 0 }, { - "encoding": "CP850", + "encoding": "windows-874", + "language": "th", "confidence": 0, - "language": "es", - "byteLogLikelihood": -4.677183836449, + "byteLogLikelihood": -3.57655026914, "hits": 0, - "total": 130, + "total": 224, "hitRate": 0 }, { - "encoding": "CP852", + "encoding": "x-mac-cyrillic", + "language": "uk", "confidence": 0, - "language": "pl", - "byteLogLikelihood": -4.699618505771, + "byteLogLikelihood": -4.252383775789, "hits": 0, - "total": 166, + "total": 228, "hitRate": 0 } ] @@ -2282,16 +1670,16 @@ { "expected": { "encoding": "ISO-8859-1", - "language": "da" + "language": "it" }, "predicted": { "encoding": "ISO-8859-1", - "confidence": 52, - "language": "da", - "byteLogLikelihood": -3.146558879633, - "hits": 21, - "total": 120, - "hitRate": 0.175 + "language": "it", + "confidence": 58, + "byteLogLikelihood": -3.533686564708, + "hits": 31, + "total": 159, + "hitRate": 0.1949685534591195 }, "encodingExact": true, "encodingEquivalent": false, @@ -2301,290 +1689,240 @@ "candidates": [ { "encoding": "ISO-8859-1", - "confidence": 52, - "language": "da", - "byteLogLikelihood": -3.146558879633, - "hits": 21, - "total": 120, - "hitRate": 0.175 + "language": "it", + "confidence": 58, + "byteLogLikelihood": -3.533686564708, + "hits": 31, + "total": 159, + "hitRate": 0.1949685534591195 }, { "encoding": "windows-1252", - "confidence": 52, - "language": "da", - "byteLogLikelihood": -3.146558879633, - "hits": 21, - "total": 120, - "hitRate": 0.175 - }, - { - "encoding": "macintosh", - "confidence": 30, - "language": "de", - "byteLogLikelihood": -5.003946305945, - "hits": 12, - "total": 120, - "hitRate": 0.1 - }, - { - "encoding": "ISO-8859-15", - "confidence": 30, - "language": "de", - "byteLogLikelihood": -5.003946305945, - "hits": 12, - "total": 120, - "hitRate": 0.1 + "language": "it", + "confidence": 58, + "byteLogLikelihood": -3.533686564708, + "hits": 31, + "total": 159, + "hitRate": 0.1949685534591195 }, { - "encoding": "CP850", - "confidence": 30, - "language": "de", - "byteLogLikelihood": -5.003946305945, - "hits": 12, - "total": 120, - "hitRate": 0.1 + "encoding": "windows-1258", + "language": "vi", + "confidence": 16, + "byteLogLikelihood": -3.012261575505, + "hits": 9, + "total": 159, + "hitRate": 0.05660377358490566 }, { - "encoding": "ISO-8859-14", + "encoding": "windows-1257", + "language": "lv", "confidence": 15, - "language": "cy", - "byteLogLikelihood": -4.912654885736, - "hits": 6, - "total": 120, - "hitRate": 0.05 + "byteLogLikelihood": -5.19295685089, + "hits": 8, + "total": 159, + "hitRate": 0.050314465408805034 }, { - "encoding": "ISO-8859-16", + "encoding": "ISO-8859-4", + "language": "lv", "confidence": 15, - "language": "ro", - "byteLogLikelihood": -5.220355825078, - "hits": 6, - "total": 120, - "hitRate": 0.05 - }, - { - "encoding": "ISO-8859-2", - "confidence": 10, - "language": "ro", - "byteLogLikelihood": -5.176149732574, - "hits": 4, - "total": 120, - "hitRate": 0.03333333333333333 + "byteLogLikelihood": -1.974081026022, + "hits": 8, + "total": 159, + "hitRate": 0.050314465408805034 }, { - "encoding": "ISO-8859-9", - "confidence": 10, - "language": "tr", - "byteLogLikelihood": -5.075173815234, - "hits": 4, - "total": 120, - "hitRate": 0.03333333333333333 + "encoding": "ISO-8859-13", + "language": "lt", + "confidence": 3, + "byteLogLikelihood": -3.332204510175, + "hits": 2, + "total": 159, + "hitRate": 0.012578616352201259 }, { - "encoding": "windows-1250", - "confidence": 10, - "language": "ro", - "byteLogLikelihood": -5.176149732574, - "hits": 4, - "total": 120, - "hitRate": 0.03333333333333333 + "encoding": "ISO-8859-5", + "language": "ru", + "confidence": 0, + "byteLogLikelihood": -2.954414124223, + "hits": 0, + "total": 159, + "hitRate": 0 }, { - "encoding": "windows-1254", - "confidence": 10, - "language": "tr", - "byteLogLikelihood": -5.075173815234, - "hits": 4, - "total": 120, - "hitRate": 0.03333333333333333 + "encoding": "ISO-8859-8", + "language": "he", + "confidence": 0, + "byteLogLikelihood": -3.629660094454, + "hits": 0, + "total": 159, + "hitRate": 0 }, { - "encoding": "windows-1257", - "confidence": 10, - "language": "et", - "byteLogLikelihood": -4.934473933131, - "hits": 4, - "total": 120, - "hitRate": 0.03333333333333333 + "encoding": "windows-1251", + "language": "ru", + "confidence": 0, + "byteLogLikelihood": -2.533200659147, + "hits": 0, + "total": 159, + "hitRate": 0 }, { - "encoding": "windows-1258", - "confidence": 7, - "language": "vi", - "byteLogLikelihood": -5.497168225293, - "hits": 3, - "total": 120, - "hitRate": 0.025 + "encoding": "windows-874", + "language": "th", + "confidence": 0, + "byteLogLikelihood": -3.496507561466, + "hits": 0, + "total": 159, + "hitRate": 0 }, { - "encoding": "ISO-8859-10", - "confidence": 7, - "language": "is", - "byteLogLikelihood": -4.717529149813, - "hits": 3, - "total": 120, - "hitRate": 0.025 + "encoding": "IBM866", + "language": "ru", + "confidence": 0, + "byteLogLikelihood": -2.954414124223, + "hits": 0, + "total": 159, + "hitRate": 0 }, { - "encoding": "CP852", - "confidence": 5, - "language": "pl", - "byteLogLikelihood": -5.087596335232, - "hits": 2, - "total": 120, - "hitRate": 0.016666666666666666 + "encoding": "x-mac-cyrillic", + "language": "ru", + "confidence": 0, + "byteLogLikelihood": -2.533200659147, + "hits": 0, + "total": 159, + "hitRate": 0 + } + ] + }, + { + "expected": { + "encoding": "ISO-8859-1", + "language": "nl" + }, + "predicted": { + "encoding": "ISO-8859-1", + "language": "nl", + "confidence": 83, + "byteLogLikelihood": -3.295836866004, + "hits": 42, + "total": 151, + "hitRate": 0.2781456953642384 + }, + "encodingExact": true, + "encodingEquivalent": false, + "encodingCorrect": true, + "languageCorrect": true, + "tiedAtTop": 2, + "candidates": [ + { + "encoding": "ISO-8859-1", + "language": "nl", + "confidence": 83, + "byteLogLikelihood": -3.295836866004, + "hits": 42, + "total": 151, + "hitRate": 0.2781456953642384 }, { - "encoding": "ISO-8859-3", - "confidence": 2, - "language": "mt", - "byteLogLikelihood": -4.658005606594, - "hits": 1, - "total": 120, - "hitRate": 0.008333333333333333 + "encoding": "ISO-8859-15", + "language": "de", + "confidence": 63, + "byteLogLikelihood": -5.003946305945, + "hits": 32, + "total": 151, + "hitRate": 0.2119205298013245 }, { - "encoding": "ISO-8859-4", - "confidence": 2, - "language": "lv", - "byteLogLikelihood": -5.19295685089, - "hits": 1, - "total": 120, - "hitRate": 0.008333333333333333 + "encoding": "windows-1252", + "language": "nl", + "confidence": 83, + "byteLogLikelihood": -3.295836866004, + "hits": 42, + "total": 151, + "hitRate": 0.2781456953642384 }, { - "encoding": "ISO-8859-13", - "confidence": 2, - "language": "lt", - "byteLogLikelihood": -4.145958228046, - "hits": 1, - "total": 120, - "hitRate": 0.008333333333333333 + "encoding": "ISO-8859-2", + "language": "ro", + "confidence": 13, + "byteLogLikelihood": -5.176149732574, + "hits": 7, + "total": 151, + "hitRate": 0.046357615894039736 }, { - "encoding": "ISO-8859-5", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.825649766807, - "hits": 0, - "total": 120, - "hitRate": 0 + "encoding": "windows-1250", + "language": "ro", + "confidence": 13, + "byteLogLikelihood": -5.176149732574, + "hits": 7, + "total": 151, + "hitRate": 0.046357615894039736 }, { - "encoding": "ISO-8859-6", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -4.736335095675, - "hits": 0, - "total": 120, - "hitRate": 0 + "encoding": "ISO-8859-10", + "language": "is", + "confidence": 11, + "byteLogLikelihood": -4.510859506517, + "hits": 6, + "total": 151, + "hitRate": 0.039735099337748346 }, { "encoding": "ISO-8859-7", - "confidence": 0, "language": "el", - "byteLogLikelihood": -4.689401143463, + "confidence": 0, + "byteLogLikelihood": -2.654561516151, "hits": 0, - "total": 120, + "total": 151, "hitRate": 0 }, { "encoding": "ISO-8859-8", - "confidence": 0, "language": "he", - "byteLogLikelihood": -3.231348206195, - "hits": 0, - "total": 120, - "hitRate": 0 - }, - { - "encoding": "windows-1251", "confidence": 0, - "language": "ru", - "byteLogLikelihood": -4.288232392491, + "byteLogLikelihood": -2.405884662832, "hits": 0, - "total": 120, + "total": 151, "hitRate": 0 }, { "encoding": "windows-1253", - "confidence": 0, "language": "el", - "byteLogLikelihood": -4.689401143463, + "confidence": 0, + "byteLogLikelihood": -2.654561516151, "hits": 0, - "total": 120, + "total": 151, "hitRate": 0 }, { "encoding": "windows-1255", - "confidence": 0, "language": "he", - "byteLogLikelihood": -3.231348206195, - "hits": 0, - "total": 120, - "hitRate": 0 - }, - { - "encoding": "windows-1256", "confidence": 0, - "language": "ar", - "byteLogLikelihood": -4.861023356308, + "byteLogLikelihood": -2.405884662832, "hits": 0, - "total": 120, + "total": 151, "hitRate": 0 }, { "encoding": "windows-874", - "confidence": 0, "language": "th", - "byteLogLikelihood": -5.888170123788, - "hits": 0, - "total": 120, - "hitRate": 0 - }, - { - "encoding": "KOI8-R", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.518796947367, - "hits": 0, - "total": 120, - "hitRate": 0 - }, - { - "encoding": "KOI8-U", - "confidence": 0, - "language": "uk", - "byteLogLikelihood": -6.476992253447, - "hits": 0, - "total": 120, - "hitRate": 0 - }, - { - "encoding": "IBM866", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.825649766807, - "hits": 0, - "total": 120, - "hitRate": 0 - }, - { - "encoding": "IBM855", "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.685745819823, + "byteLogLikelihood": -3.57655026914, "hits": 0, - "total": 120, + "total": 150, "hitRate": 0 }, { "encoding": "x-mac-cyrillic", + "language": "uk", "confidence": 0, - "language": "ru", - "byteLogLikelihood": -4.288232392491, + "byteLogLikelihood": -4.252383775789, "hits": 0, - "total": 120, + "total": 151, "hitRate": 0 } ] @@ -2592,309 +1930,259 @@ { "expected": { "encoding": "ISO-8859-1", - "language": "de" + "language": "no" }, "predicted": { "encoding": "ISO-8859-1", - "confidence": 73, - "language": "de", - "byteLogLikelihood": -3.169712077519, - "hits": 53, - "total": 216, - "hitRate": 0.24537037037037038 + "language": "no", + "confidence": 47, + "byteLogLikelihood": -3.052495812716, + "hits": 18, + "total": 114, + "hitRate": 0.15789473684210525 }, "encodingExact": true, "encodingEquivalent": false, "encodingCorrect": true, "languageCorrect": true, - "tiedAtTop": 3, + "tiedAtTop": 2, "candidates": [ { "encoding": "ISO-8859-1", - "confidence": 73, - "language": "de", - "byteLogLikelihood": -3.169712077519, - "hits": 53, - "total": 216, - "hitRate": 0.24537037037037038 + "language": "no", + "confidence": 47, + "byteLogLikelihood": -3.052495812716, + "hits": 18, + "total": 114, + "hitRate": 0.15789473684210525 }, { "encoding": "windows-1252", - "confidence": 73, - "language": "de", - "byteLogLikelihood": -3.169712077519, - "hits": 53, - "total": 216, - "hitRate": 0.24537037037037038 + "language": "no", + "confidence": 47, + "byteLogLikelihood": -3.052495812716, + "hits": 18, + "total": 114, + "hitRate": 0.15789473684210525 }, { - "encoding": "ISO-8859-15", - "confidence": 73, - "language": "de", - "byteLogLikelihood": -3.169712077519, - "hits": 53, - "total": 216, - "hitRate": 0.24537037037037038 + "encoding": "ISO-8859-2", + "language": "cs", + "confidence": 7, + "byteLogLikelihood": -4.354336342997, + "hits": 3, + "total": 114, + "hitRate": 0.02631578947368421 }, { - "encoding": "macintosh", - "confidence": 72, - "language": "de", - "byteLogLikelihood": -5.003946305945, - "hits": 52, - "total": 215, - "hitRate": 0.24186046511627907 - }, - { - "encoding": "CP850", - "confidence": 70, - "language": "de", - "byteLogLikelihood": -5.003946305945, - "hits": 51, - "total": 216, - "hitRate": 0.2361111111111111 - }, - { - "encoding": "ISO-8859-14", - "confidence": 20, - "language": "cy", - "byteLogLikelihood": -4.912654885736, - "hits": 15, - "total": 216, - "hitRate": 0.06944444444444445 - }, - { - "encoding": "ISO-8859-2", - "confidence": 13, - "language": "ro", - "byteLogLikelihood": -5.176149732574, - "hits": 10, - "total": 216, - "hitRate": 0.046296296296296294 - }, - { - "encoding": "windows-1250", - "confidence": 13, - "language": "ro", - "byteLogLikelihood": -5.176149732574, - "hits": 10, - "total": 216, - "hitRate": 0.046296296296296294 - }, - { - "encoding": "ISO-8859-9", - "confidence": 12, - "language": "tr", - "byteLogLikelihood": -4.5258676709, - "hits": 9, - "total": 216, - "hitRate": 0.041666666666666664 - }, - { - "encoding": "windows-1254", - "confidence": 12, - "language": "tr", - "byteLogLikelihood": -4.5258676709, - "hits": 9, - "total": 216, - "hitRate": 0.041666666666666664 - }, - { - "encoding": "ISO-8859-16", - "confidence": 11, - "language": "ro", - "byteLogLikelihood": -5.220355825078, - "hits": 8, - "total": 216, - "hitRate": 0.037037037037037035 - }, - { - "encoding": "windows-1257", - "confidence": 9, - "language": "lv", - "byteLogLikelihood": -5.19295685089, - "hits": 7, - "total": 216, - "hitRate": 0.032407407407407406 - }, - { - "encoding": "ISO-8859-4", - "confidence": 9, - "language": "lv", - "byteLogLikelihood": -5.19295685089, - "hits": 7, - "total": 216, - "hitRate": 0.032407407407407406 - }, - { - "encoding": "CP852", - "confidence": 6, - "language": "pl", - "byteLogLikelihood": -5.087596335232, - "hits": 5, - "total": 216, - "hitRate": 0.023148148148148147 - }, - { - "encoding": "windows-1258", - "confidence": 5, - "language": "vi", - "byteLogLikelihood": -5.497168225293, - "hits": 4, - "total": 216, - "hitRate": 0.018518518518518517 + "encoding": "windows-1257", + "language": "et", + "confidence": 7, + "byteLogLikelihood": -4.934473933131, + "hits": 3, + "total": 114, + "hitRate": 0.02631578947368421 }, { "encoding": "ISO-8859-3", - "confidence": 5, "language": "mt", - "byteLogLikelihood": -5.105945473901, - "hits": 4, - "total": 216, - "hitRate": 0.018518518518518517 + "confidence": 2, + "byteLogLikelihood": -4.210065739287, + "hits": 1, + "total": 114, + "hitRate": 0.008771929824561403 }, { "encoding": "ISO-8859-13", - "confidence": 2, "language": "lt", - "byteLogLikelihood": -5.123963979403, - "hits": 2, - "total": 216, - "hitRate": 0.009259259259259259 - }, - { - "encoding": "ISO-8859-10", - "confidence": 1, - "language": "is", - "byteLogLikelihood": -5.204006687077, + "confidence": 2, + "byteLogLikelihood": -4.319245023186, "hits": 1, - "total": 216, - "hitRate": 0.004629629629629629 + "total": 114, + "hitRate": 0.008771929824561403 }, { - "encoding": "ISO-8859-5", + "encoding": "ISO-8859-7", + "language": "el", "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.162408104115, + "byteLogLikelihood": -4.154384602589, "hits": 0, - "total": 216, + "total": 114, "hitRate": 0 }, { - "encoding": "ISO-8859-6", + "encoding": "ISO-8859-8", + "language": "he", "confidence": 0, - "language": "ar", - "byteLogLikelihood": -4.007313397456, + "byteLogLikelihood": -2.647504477241, "hits": 0, - "total": 216, + "total": 114, "hitRate": 0 }, { - "encoding": "ISO-8859-7", + "encoding": "windows-1251", + "language": "ru", "confidence": 0, - "language": "el", - "byteLogLikelihood": -4.349754587225, + "byteLogLikelihood": -3.753215851617, "hits": 0, - "total": 216, + "total": 114, "hitRate": 0 }, { - "encoding": "ISO-8859-8", + "encoding": "windows-1253", + "language": "el", "confidence": 0, - "language": "he", - "byteLogLikelihood": -4.279537403415, + "byteLogLikelihood": -4.154384602589, "hits": 0, - "total": 216, + "total": 114, "hitRate": 0 }, { - "encoding": "windows-1251", + "encoding": "windows-1255", + "language": "he", "confidence": 0, - "language": "ru", - "byteLogLikelihood": -4.542402054434, + "byteLogLikelihood": -2.647504477241, "hits": 0, - "total": 216, + "total": 114, "hitRate": 0 }, { - "encoding": "windows-1253", + "encoding": "x-mac-cyrillic", + "language": "ru", "confidence": 0, - "language": "el", - "byteLogLikelihood": -4.349754587225, + "byteLogLikelihood": -3.753215851617, "hits": 0, - "total": 216, + "total": 114, "hitRate": 0 + } + ] + }, + { + "expected": { + "encoding": "ISO-8859-1", + "language": "pt" + }, + "predicted": { + "encoding": "ISO-8859-1", + "language": "pt", + "confidence": 50, + "byteLogLikelihood": -4.059947322987, + "hits": 24, + "total": 143, + "hitRate": 0.16783216783216784 + }, + "encodingExact": true, + "encodingEquivalent": false, + "encodingCorrect": true, + "languageCorrect": true, + "tiedAtTop": 2, + "candidates": [ + { + "encoding": "ISO-8859-1", + "language": "pt", + "confidence": 50, + "byteLogLikelihood": -4.059947322987, + "hits": 24, + "total": 143, + "hitRate": 0.16783216783216784 }, { - "encoding": "windows-1255", + "encoding": "windows-1252", + "language": "pt", + "confidence": 50, + "byteLogLikelihood": -4.059947322987, + "hits": 24, + "total": 143, + "hitRate": 0.16783216783216784 + }, + { + "encoding": "ISO-8859-2", + "language": "hu", + "confidence": 10, + "byteLogLikelihood": -3.361609233757, + "hits": 5, + "total": 143, + "hitRate": 0.03496503496503497 + }, + { + "encoding": "windows-1250", + "language": "hu", + "confidence": 10, + "byteLogLikelihood": -3.361609233757, + "hits": 5, + "total": 143, + "hitRate": 0.03496503496503497 + }, + { + "encoding": "ISO-8859-7", + "language": "el", "confidence": 0, - "language": "he", - "byteLogLikelihood": -4.279537403415, + "byteLogLikelihood": -3.017269736716, "hits": 0, - "total": 216, + "total": 143, "hitRate": 0 }, { - "encoding": "windows-1256", + "encoding": "ISO-8859-8", + "language": "he", "confidence": 0, - "language": "ar", - "byteLogLikelihood": -4.318835143108, + "byteLogLikelihood": -3.50352863905, "hits": 0, - "total": 216, + "total": 143, "hitRate": 0 }, { - "encoding": "windows-874", + "encoding": "windows-1251", + "language": "ru", "confidence": 0, - "language": "th", - "byteLogLikelihood": -5.657121063601, + "byteLogLikelihood": -3.846220145127, "hits": 0, - "total": 216, + "total": 143, "hitRate": 0 }, { - "encoding": "KOI8-R", + "encoding": "windows-1253", + "language": "el", "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.28774788718, + "byteLogLikelihood": -3.017269736716, "hits": 0, - "total": 216, + "total": 143, "hitRate": 0 }, { - "encoding": "KOI8-U", + "encoding": "windows-1255", + "language": "he", "confidence": 0, - "language": "uk", - "byteLogLikelihood": -6.245943193261, + "byteLogLikelihood": -3.50352863905, "hits": 0, - "total": 216, + "total": 143, "hitRate": 0 }, { - "encoding": "IBM866", + "encoding": "windows-1256", + "language": "ar", "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.692083742507, + "byteLogLikelihood": -3.503504267293, "hits": 0, - "total": 216, + "total": 143, "hitRate": 0 }, { "encoding": "IBM855", - "confidence": 0, "language": "sr", - "byteLogLikelihood": -5.942998477092, + "confidence": 0, + "byteLogLikelihood": -3.774998078834, "hits": 0, - "total": 216, + "total": 143, "hitRate": 0 }, { "encoding": "x-mac-cyrillic", - "confidence": 0, "language": "uk", - "byteLogLikelihood": -3.629332579687, + "confidence": 0, + "byteLogLikelihood": -3.766179593299, "hits": 0, - "total": 216, + "total": 143, "hitRate": 0 } ] @@ -2902,3774 +2190,2914 @@ { "expected": { "encoding": "ISO-8859-1", - "language": "en" + "language": "sv" }, "predicted": { - "encoding": "ISO-8859-15", - "confidence": 29, - "language": "en", - "byteLogLikelihood": -2.06619631493, - "hits": 13, - "total": 132, - "hitRate": 0.09848484848484848 + "encoding": "ISO-8859-1", + "language": "sv", + "confidence": 50, + "byteLogLikelihood": -3.23645137845, + "hits": 23, + "total": 136, + "hitRate": 0.16911764705882354 }, - "encodingExact": false, - "encodingEquivalent": true, + "encodingExact": true, + "encodingEquivalent": false, "encodingCorrect": true, "languageCorrect": true, - "tiedAtTop": 1, + "tiedAtTop": 2, "candidates": [ - { - "encoding": "ISO-8859-15", - "confidence": 29, - "language": "fr", - "byteLogLikelihood": -2.06619631493, - "hits": 13, - "total": 132, - "hitRate": 0.09848484848484848 - }, { "encoding": "ISO-8859-1", - "confidence": 47, - "language": "en", - "byteLogLikelihood": -3.310543013394, - "hits": 21, - "total": 132, - "hitRate": 0.1590909090909091 + "language": "sv", + "confidence": 50, + "byteLogLikelihood": -3.23645137845, + "hits": 23, + "total": 136, + "hitRate": 0.16911764705882354 }, { "encoding": "windows-1252", - "confidence": 47, - "language": "en", - "byteLogLikelihood": -3.310543013394, - "hits": 21, - "total": 132, - "hitRate": 0.1590909090909091 - }, - { - "encoding": "macintosh", - "confidence": 27, - "language": "fr", - "byteLogLikelihood": -5.010635294096, - "hits": 12, - "total": 132, - "hitRate": 0.09090909090909091 + "language": "sv", + "confidence": 50, + "byteLogLikelihood": -3.23645137845, + "hits": 23, + "total": 136, + "hitRate": 0.16911764705882354 }, { - "encoding": "CP850", - "confidence": 27, - "language": "fr", - "byteLogLikelihood": -5.010635294096, - "hits": 12, - "total": 132, - "hitRate": 0.09090909090909091 + "encoding": "ISO-8859-15", + "language": "de", + "confidence": 17, + "byteLogLikelihood": -4.137512330246, + "hits": 8, + "total": 136, + "hitRate": 0.058823529411764705 }, { "encoding": "windows-1257", - "confidence": 11, - "language": "et", - "byteLogLikelihood": -4.934473933131, - "hits": 5, - "total": 132, - "hitRate": 0.03787878787878788 - }, - { - "encoding": "ISO-8859-14", - "confidence": 11, - "language": "cy", - "byteLogLikelihood": -4.912654885736, - "hits": 5, - "total": 132, - "hitRate": 0.03787878787878788 - }, - { - "encoding": "ISO-8859-2", - "confidence": 9, - "language": "cs", - "byteLogLikelihood": -3.54961738678, - "hits": 4, - "total": 132, - "hitRate": 0.030303030303030304 - }, - { - "encoding": "windows-1250", - "confidence": 9, - "language": "cs", - "byteLogLikelihood": -3.54961738678, - "hits": 4, - "total": 132, - "hitRate": 0.030303030303030304 - }, - { - "encoding": "windows-1258", - "confidence": 9, - "language": "vi", - "byteLogLikelihood": -5.497168225293, - "hits": 4, - "total": 132, - "hitRate": 0.030303030303030304 - }, - { - "encoding": "ISO-8859-16", - "confidence": 9, - "language": "ro", - "byteLogLikelihood": -5.220355825078, - "hits": 4, - "total": 132, - "hitRate": 0.030303030303030304 - }, - { - "encoding": "ISO-8859-4", - "confidence": 6, - "language": "lv", - "byteLogLikelihood": -5.19295685089, - "hits": 3, - "total": 132, - "hitRate": 0.022727272727272728 - }, - { - "encoding": "ISO-8859-9", - "confidence": 4, - "language": "tr", - "byteLogLikelihood": -5.075173815234, - "hits": 2, - "total": 132, - "hitRate": 0.015151515151515152 - }, - { - "encoding": "windows-1254", + "language": "lt", "confidence": 4, - "language": "tr", - "byteLogLikelihood": -5.075173815234, + "byteLogLikelihood": -5.123963979403, "hits": 2, - "total": 132, - "hitRate": 0.015151515151515152 + "total": 136, + "hitRate": 0.014705882352941176 }, { "encoding": "ISO-8859-3", - "confidence": 4, "language": "mt", - "byteLogLikelihood": -5.105945473901, - "hits": 2, - "total": 132, - "hitRate": 0.015151515151515152 - }, - { - "encoding": "CP852", "confidence": 4, - "language": "pl", - "byteLogLikelihood": -5.087596335232, + "byteLogLikelihood": -4.210065739287, "hits": 2, - "total": 132, - "hitRate": 0.015151515151515152 - }, - { - "encoding": "ISO-8859-13", - "confidence": 2, - "language": "lt", - "byteLogLikelihood": -5.123963979403, - "hits": 1, - "total": 132, - "hitRate": 0.007575757575757576 - }, - { - "encoding": "ISO-8859-5", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.593471453839, - "hits": 0, - "total": 132, - "hitRate": 0 + "total": 136, + "hitRate": 0.014705882352941176 }, { "encoding": "ISO-8859-6", - "confidence": 0, "language": "ar", - "byteLogLikelihood": -6.113682179832, + "confidence": 0, + "byteLogLikelihood": -3.287368473007, "hits": 0, - "total": 132, + "total": 136, "hitRate": 0 }, { "encoding": "ISO-8859-7", - "confidence": 0, "language": "el", - "byteLogLikelihood": -2.654561516151, + "confidence": 0, + "byteLogLikelihood": -3.876181596107, "hits": 0, - "total": 132, + "total": 136, "hitRate": 0 }, { "encoding": "ISO-8859-8", - "confidence": 0, "language": "he", - "byteLogLikelihood": -2.405884662832, + "confidence": 0, + "byteLogLikelihood": -3.066153183614, "hits": 0, - "total": 132, + "total": 136, "hitRate": 0 }, { "encoding": "windows-1251", - "confidence": 0, "language": "ru", - "byteLogLikelihood": -4.612642200827, + "confidence": 0, + "byteLogLikelihood": -3.393743210995, "hits": 0, - "total": 132, + "total": 136, "hitRate": 0 }, { "encoding": "windows-1253", - "confidence": 0, "language": "el", - "byteLogLikelihood": -2.654561516151, + "confidence": 0, + "byteLogLikelihood": -3.876181596107, "hits": 0, - "total": 132, + "total": 136, "hitRate": 0 }, { "encoding": "windows-1255", - "confidence": 0, "language": "he", - "byteLogLikelihood": -2.405884662832, - "hits": 0, - "total": 132, - "hitRate": 0 - }, - { - "encoding": "windows-1256", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -6.113682179832, - "hits": 0, - "total": 132, - "hitRate": 0 - }, - { - "encoding": "windows-874", "confidence": 0, - "language": "th", - "byteLogLikelihood": -3.57655026914, + "byteLogLikelihood": -3.066153183614, "hits": 0, - "total": 131, + "total": 136, "hitRate": 0 }, { - "encoding": "KOI8-R", - "confidence": 0, + "encoding": "x-mac-cyrillic", "language": "ru", - "byteLogLikelihood": -6.692083742507, - "hits": 0, - "total": 132, - "hitRate": 0 - }, - { - "encoding": "KOI8-U", - "confidence": 0, - "language": "uk", - "byteLogLikelihood": -6.650279048587, - "hits": 0, - "total": 132, - "hitRate": 0 - }, - { - "encoding": "IBM866", "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.593471453839, + "byteLogLikelihood": -3.393743210995, "hits": 0, - "total": 132, - "hitRate": 0 - }, - { - "encoding": "IBM855", - "confidence": 0, - "language": "sr", - "byteLogLikelihood": -4.728861658331, - "hits": 0, - "total": 132, - "hitRate": 0 - }, - { - "encoding": "x-mac-cyrillic", - "confidence": 0, - "language": "uk", - "byteLogLikelihood": -4.252383775789, - "hits": 0, - "total": 132, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-10", - "confidence": 0, - "language": "is", - "byteLogLikelihood": -4.510859506517, - "hits": 0, - "total": 132, + "total": 136, "hitRate": 0 } ] }, { "expected": { - "encoding": "ISO-8859-1", - "language": "es" + "encoding": "ISO-8859-10", + "language": "is" }, "predicted": { - "encoding": "ISO-8859-1", - "confidence": 61, - "language": "es", - "byteLogLikelihood": -3.834657935767, - "hits": 41, - "total": 200, - "hitRate": 0.205 + "encoding": "ISO-8859-10", + "language": "is", + "confidence": 38, + "byteLogLikelihood": -3.025836278694, + "hits": 22, + "total": 171, + "hitRate": 0.1286549707602339 }, "encodingExact": true, "encodingEquivalent": false, "encodingCorrect": true, "languageCorrect": true, - "tiedAtTop": 3, + "tiedAtTop": 1, "candidates": [ { - "encoding": "ISO-8859-1", - "confidence": 61, - "language": "es", - "byteLogLikelihood": -3.834657935767, - "hits": 41, - "total": 200, - "hitRate": 0.205 - }, - { - "encoding": "windows-1252", - "confidence": 61, - "language": "es", - "byteLogLikelihood": -3.834657935767, - "hits": 41, - "total": 200, - "hitRate": 0.205 - }, - { - "encoding": "ISO-8859-15", - "confidence": 61, - "language": "es", - "byteLogLikelihood": -3.834657935767, - "hits": 41, - "total": 200, - "hitRate": 0.205 - }, - { - "encoding": "macintosh", - "confidence": 58, - "language": "es", - "byteLogLikelihood": -4.948759890378, - "hits": 39, - "total": 199, - "hitRate": 0.19597989949748743 + "encoding": "ISO-8859-10", + "language": "is", + "confidence": 38, + "byteLogLikelihood": -3.025836278694, + "hits": 22, + "total": 171, + "hitRate": 0.1286549707602339 }, { - "encoding": "CP850", - "confidence": 58, - "language": "es", - "byteLogLikelihood": -4.948759890378, - "hits": 39, - "total": 200, - "hitRate": 0.195 + "encoding": "ISO-8859-1", + "language": "sv", + "confidence": 14, + "byteLogLikelihood": -4.633646206449, + "hits": 8, + "total": 171, + "hitRate": 0.04678362573099415 }, { "encoding": "windows-1257", - "confidence": 24, - "language": "lv", - "byteLogLikelihood": -5.19295685089, - "hits": 16, - "total": 200, - "hitRate": 0.08 - }, - { - "encoding": "ISO-8859-4", - "confidence": 24, - "language": "lv", - "byteLogLikelihood": -5.009854802779, - "hits": 16, - "total": 200, - "hitRate": 0.08 + "language": "lt", + "confidence": 7, + "byteLogLikelihood": -3.989583472462, + "hits": 4, + "total": 171, + "hitRate": 0.023391812865497075 }, { "encoding": "ISO-8859-13", - "confidence": 19, "language": "lt", - "byteLogLikelihood": -4.892914919217, - "hits": 13, - "total": 200, - "hitRate": 0.065 - }, - { - "encoding": "ISO-8859-14", - "confidence": 16, - "language": "cy", - "byteLogLikelihood": -4.912654885736, - "hits": 11, - "total": 200, - "hitRate": 0.055 + "confidence": 7, + "byteLogLikelihood": -3.989583472462, + "hits": 4, + "total": 171, + "hitRate": 0.023391812865497075 }, { "encoding": "ISO-8859-2", - "confidence": 15, - "language": "ro", - "byteLogLikelihood": -5.176149732574, - "hits": 10, - "total": 200, - "hitRate": 0.05 + "language": "cs", + "confidence": 3, + "byteLogLikelihood": -4.497848163857, + "hits": 2, + "total": 171, + "hitRate": 0.011695906432748537 }, { "encoding": "windows-1250", - "confidence": 15, - "language": "ro", - "byteLogLikelihood": -5.176149732574, - "hits": 10, - "total": 200, - "hitRate": 0.05 - }, - { - "encoding": "ISO-8859-16", - "confidence": 15, - "language": "ro", - "byteLogLikelihood": -5.220355825078, - "hits": 10, - "total": 200, - "hitRate": 0.05 - }, - { - "encoding": "ISO-8859-9", - "confidence": 7, - "language": "tr", - "byteLogLikelihood": -5.075173815234, - "hits": 5, - "total": 200, - "hitRate": 0.025 - }, - { - "encoding": "windows-1254", - "confidence": 7, - "language": "tr", - "byteLogLikelihood": -5.075173815234, - "hits": 5, - "total": 200, - "hitRate": 0.025 - }, - { - "encoding": "CP852", - "confidence": 7, - "language": "pl", - "byteLogLikelihood": -5.087596335232, - "hits": 5, - "total": 200, - "hitRate": 0.025 - }, - { - "encoding": "windows-1258", - "confidence": 4, - "language": "vi", - "byteLogLikelihood": -4.848531508941, - "hits": 3, - "total": 200, - "hitRate": 0.015 - }, - { - "encoding": "ISO-8859-10", - "confidence": 4, - "language": "is", - "byteLogLikelihood": -3.846028832089, - "hits": 3, - "total": 200, - "hitRate": 0.015 - }, - { - "encoding": "ISO-8859-5", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -4.977292083619, - "hits": 0, - "total": 200, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-6", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -5.346153815501, - "hits": 0, - "total": 200, - "hitRate": 0 + "language": "cs", + "confidence": 3, + "byteLogLikelihood": -4.497848163857, + "hits": 2, + "total": 171, + "hitRate": 0.011695906432748537 }, { "encoding": "ISO-8859-7", - "confidence": 0, "language": "el", - "byteLogLikelihood": -3.106555532888, + "confidence": 0, + "byteLogLikelihood": -3.963723644165, "hits": 0, - "total": 200, + "total": 171, "hitRate": 0 }, { "encoding": "ISO-8859-8", - "confidence": 0, "language": "he", - "byteLogLikelihood": -3.411159813207, + "confidence": 0, + "byteLogLikelihood": -4.249634019938, "hits": 0, - "total": 200, + "total": 171, "hitRate": 0 }, { "encoding": "windows-1251", - "confidence": 0, "language": "ru", - "byteLogLikelihood": -3.336328204376, + "confidence": 0, + "byteLogLikelihood": -3.84046735452, "hits": 0, - "total": 200, + "total": 171, "hitRate": 0 }, { "encoding": "windows-1253", - "confidence": 0, "language": "el", - "byteLogLikelihood": -3.106555532888, + "confidence": 0, + "byteLogLikelihood": -3.963723644165, "hits": 0, - "total": 200, + "total": 171, "hitRate": 0 }, { "encoding": "windows-1255", - "confidence": 0, "language": "he", - "byteLogLikelihood": -3.411159813207, + "confidence": 0, + "byteLogLikelihood": -4.249634019938, "hits": 0, - "total": 200, + "total": 171, "hitRate": 0 }, { - "encoding": "windows-1256", + "encoding": "x-mac-cyrillic", + "language": "uk", "confidence": 0, - "language": "ar", - "byteLogLikelihood": -3.300604963183, + "byteLogLikelihood": -3.733983711968, "hits": 0, - "total": 200, + "total": 171, "hitRate": 0 + } + ] + }, + { + "expected": { + "encoding": "ISO-8859-13", + "language": "lt" + }, + "predicted": { + "encoding": "windows-1257", + "language": "lt", + "confidence": 34, + "byteLogLikelihood": -3.200530207132, + "hits": 20, + "total": 173, + "hitRate": 0.11560693641618497 + }, + "encodingExact": false, + "encodingEquivalent": true, + "encodingCorrect": true, + "languageCorrect": true, + "tiedAtTop": 2, + "candidates": [ + { + "encoding": "windows-1257", + "language": "lt", + "confidence": 34, + "byteLogLikelihood": -3.200530207132, + "hits": 20, + "total": 173, + "hitRate": 0.11560693641618497 }, { - "encoding": "windows-874", - "confidence": 0, - "language": "th", - "byteLogLikelihood": -5.412820202576, - "hits": 0, - "total": 200, - "hitRate": 0 + "encoding": "ISO-8859-13", + "language": "lt", + "confidence": 34, + "byteLogLikelihood": -3.200530207132, + "hits": 20, + "total": 173, + "hitRate": 0.11560693641618497 }, { - "encoding": "KOI8-R", + "encoding": "ISO-8859-4", + "language": "lv", + "confidence": 22, + "byteLogLikelihood": -4.610398759565, + "hits": 13, + "total": 173, + "hitRate": 0.07514450867052024 + }, + { + "encoding": "ISO-8859-1", + "language": "es", + "confidence": 12, + "byteLogLikelihood": -4.948759890378, + "hits": 7, + "total": 173, + "hitRate": 0.04046242774566474 + }, + { + "encoding": "windows-1252", + "language": "es", + "confidence": 12, + "byteLogLikelihood": -4.948759890378, + "hits": 7, + "total": 173, + "hitRate": 0.04046242774566474 + }, + { + "encoding": "ISO-8859-10", + "language": "is", + "confidence": 1, + "byteLogLikelihood": -4.416382325607, + "hits": 1, + "total": 173, + "hitRate": 0.005780346820809248 + }, + { + "encoding": "ISO-8859-7", + "language": "el", "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.692083742507, + "byteLogLikelihood": -4.472500251122, "hits": 0, - "total": 200, + "total": 173, "hitRate": 0 }, { - "encoding": "KOI8-U", + "encoding": "ISO-8859-8", + "language": "he", "confidence": 0, - "language": "uk", - "byteLogLikelihood": -6.303705458307, + "byteLogLikelihood": -4.444220754634, "hits": 0, - "total": 200, + "total": 171, "hitRate": 0 }, { - "encoding": "IBM866", - "confidence": 0, + "encoding": "windows-1251", "language": "ru", - "byteLogLikelihood": -4.977292083619, + "confidence": 0, + "byteLogLikelihood": -3.531827362419, "hits": 0, - "total": 200, + "total": 173, "hitRate": 0 }, { - "encoding": "IBM855", + "encoding": "windows-1253", + "language": "el", "confidence": 0, - "language": "ru", - "byteLogLikelihood": -4.203740544852, + "byteLogLikelihood": -4.472500251122, "hits": 0, - "total": 200, + "total": 173, "hitRate": 0 }, { - "encoding": "x-mac-cyrillic", + "encoding": "windows-1255", + "language": "he", "confidence": 0, - "language": "ru", - "byteLogLikelihood": -3.336328204376, + "byteLogLikelihood": -4.444220754634, "hits": 0, - "total": 200, + "total": 171, "hitRate": 0 }, { - "encoding": "ISO-8859-3", + "encoding": "x-mac-cyrillic", + "language": "uk", "confidence": 0, - "language": "mt", - "byteLogLikelihood": -5.105945473901, + "byteLogLikelihood": -3.441328843196, "hits": 0, - "total": 200, + "total": 173, "hitRate": 0 } ] }, { "expected": { - "encoding": "ISO-8859-1", - "language": "fr" + "encoding": "ISO-8859-14", + "language": "cy" }, "predicted": { - "encoding": "ISO-8859-1", - "confidence": 77, - "language": "fr", - "byteLogLikelihood": -2.06619631493, - "hits": 59, - "total": 228, - "hitRate": 0.25877192982456143 + "encoding": "ISO-8859-14", + "language": "cy", + "confidence": 50, + "byteLogLikelihood": -3.988458644989, + "hits": 32, + "total": 189, + "hitRate": 0.1693121693121693 }, "encodingExact": true, "encodingEquivalent": false, "encodingCorrect": true, "languageCorrect": true, - "tiedAtTop": 3, + "tiedAtTop": 1, "candidates": [ { - "encoding": "ISO-8859-1", - "confidence": 77, - "language": "fr", - "byteLogLikelihood": -2.06619631493, - "hits": 59, - "total": 228, - "hitRate": 0.25877192982456143 - }, - { - "encoding": "windows-1252", - "confidence": 77, - "language": "fr", - "byteLogLikelihood": -2.06619631493, - "hits": 59, - "total": 228, - "hitRate": 0.25877192982456143 - }, - { - "encoding": "ISO-8859-15", - "confidence": 77, - "language": "fr", - "byteLogLikelihood": -2.06619631493, - "hits": 59, - "total": 228, - "hitRate": 0.25877192982456143 - }, - { - "encoding": "macintosh", - "confidence": 71, - "language": "fr", - "byteLogLikelihood": -5.010635294096, - "hits": 54, - "total": 228, - "hitRate": 0.23684210526315788 + "encoding": "ISO-8859-14", + "language": "cy", + "confidence": 50, + "byteLogLikelihood": -3.988458644989, + "hits": 32, + "total": 189, + "hitRate": 0.1693121693121693 }, { - "encoding": "CP850", - "confidence": 71, - "language": "fr", - "byteLogLikelihood": -5.010635294096, - "hits": 54, - "total": 228, - "hitRate": 0.23684210526315788 + "encoding": "windows-1258", + "language": "vi", + "confidence": 14, + "byteLogLikelihood": -4.34192292436, + "hits": 9, + "total": 188, + "hitRate": 0.047872340425531915 }, { "encoding": "ISO-8859-2", - "confidence": 11, - "language": "ro", - "byteLogLikelihood": -5.176149732574, - "hits": 9, - "total": 228, - "hitRate": 0.039473684210526314 + "language": "cs", + "confidence": 9, + "byteLogLikelihood": -5.159055299215, + "hits": 6, + "total": 189, + "hitRate": 0.031746031746031744 }, { "encoding": "windows-1250", - "confidence": 11, - "language": "ro", - "byteLogLikelihood": -5.176149732574, - "hits": 9, - "total": 228, - "hitRate": 0.039473684210526314 + "language": "cs", + "confidence": 9, + "byteLogLikelihood": -5.159055299215, + "hits": 6, + "total": 189, + "hitRate": 0.031746031746031744 + }, + { + "encoding": "windows-1257", + "language": "et", + "confidence": 6, + "byteLogLikelihood": -4.934473933131, + "hits": 4, + "total": 189, + "hitRate": 0.021164021164021163 }, { "encoding": "ISO-8859-10", - "confidence": 10, "language": "is", - "byteLogLikelihood": -4.510859506517, - "hits": 8, - "total": 228, - "hitRate": 0.03508771929824561 + "confidence": 4, + "byteLogLikelihood": -4.009500374258, + "hits": 3, + "total": 189, + "hitRate": 0.015873015873015872 }, { - "encoding": "ISO-8859-16", - "confidence": 10, - "language": "ro", - "byteLogLikelihood": -5.220355825078, - "hits": 8, - "total": 228, - "hitRate": 0.03508771929824561 + "encoding": "ISO-8859-13", + "language": "lt", + "confidence": 1, + "byteLogLikelihood": -3.647025046455, + "hits": 1, + "total": 189, + "hitRate": 0.005291005291005291 }, { - "encoding": "windows-1257", - "confidence": 7, - "language": "lv", - "byteLogLikelihood": -5.19295685089, - "hits": 6, - "total": 228, - "hitRate": 0.02631578947368421 - }, - { - "encoding": "ISO-8859-4", - "confidence": 7, - "language": "lv", - "byteLogLikelihood": -5.19295685089, - "hits": 6, - "total": 228, - "hitRate": 0.02631578947368421 - }, - { - "encoding": "CP852", - "confidence": 7, - "language": "pl", - "byteLogLikelihood": -5.087596335232, - "hits": 6, - "total": 228, - "hitRate": 0.02631578947368421 - }, - { - "encoding": "ISO-8859-9", - "confidence": 5, - "language": "tr", - "byteLogLikelihood": -5.075173815234, - "hits": 4, - "total": 228, - "hitRate": 0.017543859649122806 - }, - { - "encoding": "windows-1254", - "confidence": 5, - "language": "tr", - "byteLogLikelihood": -5.075173815234, - "hits": 4, - "total": 228, - "hitRate": 0.017543859649122806 - }, - { - "encoding": "windows-1258", - "confidence": 5, - "language": "vi", - "byteLogLikelihood": -5.497168225293, - "hits": 4, - "total": 228, - "hitRate": 0.017543859649122806 - }, - { - "encoding": "ISO-8859-3", - "confidence": 5, - "language": "mt", - "byteLogLikelihood": -5.105945473901, - "hits": 4, - "total": 228, - "hitRate": 0.017543859649122806 - }, - { - "encoding": "ISO-8859-13", - "confidence": 5, - "language": "lt", - "byteLogLikelihood": -5.123963979403, - "hits": 4, - "total": 228, - "hitRate": 0.017543859649122806 - }, - { - "encoding": "ISO-8859-14", - "confidence": 3, - "language": "cy", - "byteLogLikelihood": -4.912654885736, - "hits": 3, - "total": 228, - "hitRate": 0.013157894736842105 - }, - { - "encoding": "ISO-8859-5", + "encoding": "ISO-8859-7", + "language": "el", "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.593471453839, + "byteLogLikelihood": -4.254156765951, "hits": 0, - "total": 228, + "total": 189, "hitRate": 0 }, { - "encoding": "ISO-8859-6", + "encoding": "windows-1251", + "language": "ru", "confidence": 0, - "language": "ar", - "byteLogLikelihood": -6.113682179832, + "byteLogLikelihood": -3.467895804539, "hits": 0, - "total": 228, + "total": 189, "hitRate": 0 }, { - "encoding": "ISO-8859-7", - "confidence": 0, + "encoding": "windows-1253", "language": "el", - "byteLogLikelihood": -2.654561516151, + "confidence": 0, + "byteLogLikelihood": -4.254156765951, "hits": 0, - "total": 228, + "total": 189, "hitRate": 0 }, { - "encoding": "ISO-8859-8", + "encoding": "x-mac-cyrillic", + "language": "uk", "confidence": 0, - "language": "he", - "byteLogLikelihood": -2.405884662832, + "byteLogLikelihood": -3.255815902698, "hits": 0, - "total": 228, + "total": 189, "hitRate": 0 }, { - "encoding": "windows-1251", + "encoding": "ISO-8859-16", + "language": "ro", "confidence": 0, - "language": "ru", - "byteLogLikelihood": -4.612642200827, + "byteLogLikelihood": -3.903274585551, "hits": 0, - "total": 228, + "total": 189, "hitRate": 0 + } + ] + }, + { + "expected": { + "encoding": "ISO-8859-15", + "language": "de" + }, + "predicted": { + "encoding": "ISO-8859-1", + "language": "de", + "confidence": 73, + "byteLogLikelihood": -3.169712077519, + "hits": 53, + "total": 216, + "hitRate": 0.24537037037037038 + }, + "encodingExact": false, + "encodingEquivalent": true, + "encodingCorrect": true, + "languageCorrect": true, + "tiedAtTop": 3, + "candidates": [ + { + "encoding": "ISO-8859-1", + "language": "de", + "confidence": 73, + "byteLogLikelihood": -3.169712077519, + "hits": 53, + "total": 216, + "hitRate": 0.24537037037037038 }, { - "encoding": "windows-1253", - "confidence": 0, - "language": "el", - "byteLogLikelihood": -2.654561516151, - "hits": 0, - "total": 228, - "hitRate": 0 + "encoding": "ISO-8859-15", + "language": "de", + "confidence": 73, + "byteLogLikelihood": -3.169712077519, + "hits": 53, + "total": 216, + "hitRate": 0.24537037037037038 }, { - "encoding": "windows-1255", - "confidence": 0, - "language": "he", - "byteLogLikelihood": -2.405884662832, - "hits": 0, - "total": 228, - "hitRate": 0 + "encoding": "windows-1252", + "language": "de", + "confidence": 73, + "byteLogLikelihood": -3.169712077519, + "hits": 53, + "total": 216, + "hitRate": 0.24537037037037038 }, { - "encoding": "windows-1256", - "confidence": 0, + "encoding": "ISO-8859-9", + "language": "tr", + "confidence": 12, + "byteLogLikelihood": -4.5258676709, + "hits": 9, + "total": 216, + "hitRate": 0.041666666666666664 + }, + { + "encoding": "windows-1257", + "language": "lv", + "confidence": 9, + "byteLogLikelihood": -5.19295685089, + "hits": 7, + "total": 216, + "hitRate": 0.032407407407407406 + }, + { + "encoding": "ISO-8859-6", "language": "ar", - "byteLogLikelihood": -6.113682179832, + "confidence": 0, + "byteLogLikelihood": -4.007313397456, "hits": 0, - "total": 228, + "total": 216, "hitRate": 0 }, { - "encoding": "windows-874", + "encoding": "ISO-8859-7", + "language": "el", "confidence": 0, - "language": "th", - "byteLogLikelihood": -3.57655026914, + "byteLogLikelihood": -4.349754587225, "hits": 0, - "total": 224, + "total": 216, "hitRate": 0 }, { - "encoding": "KOI8-R", + "encoding": "ISO-8859-8", + "language": "he", "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.692083742507, + "byteLogLikelihood": -4.279537403415, "hits": 0, - "total": 228, + "total": 216, "hitRate": 0 }, { - "encoding": "KOI8-U", + "encoding": "windows-1253", + "language": "el", "confidence": 0, - "language": "uk", - "byteLogLikelihood": -6.650279048587, + "byteLogLikelihood": -4.349754587225, "hits": 0, - "total": 228, + "total": 216, "hitRate": 0 }, { - "encoding": "IBM866", + "encoding": "windows-1255", + "language": "he", "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.593471453839, + "byteLogLikelihood": -4.279537403415, "hits": 0, - "total": 228, + "total": 216, "hitRate": 0 }, { - "encoding": "IBM855", + "encoding": "windows-1256", + "language": "ar", "confidence": 0, - "language": "sr", - "byteLogLikelihood": -4.728861658331, + "byteLogLikelihood": -4.318835143108, "hits": 0, - "total": 228, + "total": 216, "hitRate": 0 }, { "encoding": "x-mac-cyrillic", - "confidence": 0, "language": "uk", - "byteLogLikelihood": -4.252383775789, + "confidence": 0, + "byteLogLikelihood": -3.629332579687, "hits": 0, - "total": 228, + "total": 216, "hitRate": 0 } ] }, { "expected": { - "encoding": "ISO-8859-1", - "language": "it" + "encoding": "ISO-8859-15", + "language": "es" }, "predicted": { "encoding": "ISO-8859-1", - "confidence": 58, - "language": "it", - "byteLogLikelihood": -3.533686564708, - "hits": 31, - "total": 159, - "hitRate": 0.1949685534591195 + "language": "es", + "confidence": 61, + "byteLogLikelihood": -3.834657935767, + "hits": 41, + "total": 200, + "hitRate": 0.205 }, - "encodingExact": true, - "encodingEquivalent": false, + "encodingExact": false, + "encodingEquivalent": true, "encodingCorrect": true, "languageCorrect": true, - "tiedAtTop": 2, + "tiedAtTop": 3, "candidates": [ { "encoding": "ISO-8859-1", - "confidence": 58, - "language": "it", - "byteLogLikelihood": -3.533686564708, - "hits": 31, - "total": 159, - "hitRate": 0.1949685534591195 - }, - { - "encoding": "windows-1252", - "confidence": 58, - "language": "it", - "byteLogLikelihood": -3.533686564708, - "hits": 31, - "total": 159, - "hitRate": 0.1949685534591195 - }, - { - "encoding": "macintosh", - "confidence": 24, - "language": "fr", - "byteLogLikelihood": -5.010635294096, - "hits": 13, - "total": 158, - "hitRate": 0.08227848101265822 + "language": "es", + "confidence": 61, + "byteLogLikelihood": -3.834657935767, + "hits": 41, + "total": 200, + "hitRate": 0.205 }, { "encoding": "ISO-8859-15", - "confidence": 24, - "language": "fr", - "byteLogLikelihood": -5.010635294096, - "hits": 13, - "total": 159, - "hitRate": 0.08176100628930817 - }, - { - "encoding": "CP850", - "confidence": 24, - "language": "fr", - "byteLogLikelihood": -5.010635294096, - "hits": 13, - "total": 159, - "hitRate": 0.08176100628930817 - }, - { - "encoding": "windows-1258", - "confidence": 16, - "language": "vi", - "byteLogLikelihood": -3.012261575505, - "hits": 9, - "total": 159, - "hitRate": 0.05660377358490566 + "language": "es", + "confidence": 61, + "byteLogLikelihood": -3.834657935767, + "hits": 41, + "total": 200, + "hitRate": 0.205 }, { - "encoding": "ISO-8859-16", - "confidence": 16, - "language": "ro", - "byteLogLikelihood": -5.220355825078, - "hits": 9, - "total": 159, - "hitRate": 0.05660377358490566 + "encoding": "windows-1252", + "language": "es", + "confidence": 61, + "byteLogLikelihood": -3.834657935767, + "hits": 41, + "total": 200, + "hitRate": 0.205 }, { "encoding": "ISO-8859-2", - "confidence": 15, "language": "ro", + "confidence": 15, "byteLogLikelihood": -5.176149732574, - "hits": 8, - "total": 159, - "hitRate": 0.050314465408805034 + "hits": 10, + "total": 200, + "hitRate": 0.05 }, { "encoding": "windows-1250", - "confidence": 15, "language": "ro", - "byteLogLikelihood": -5.176149732574, - "hits": 8, - "total": 159, - "hitRate": 0.050314465408805034 - }, - { - "encoding": "windows-1257", - "confidence": 15, - "language": "lv", - "byteLogLikelihood": -5.19295685089, - "hits": 8, - "total": 159, - "hitRate": 0.050314465408805034 - }, - { - "encoding": "ISO-8859-4", "confidence": 15, - "language": "lv", - "byteLogLikelihood": -1.974081026022, - "hits": 8, - "total": 159, - "hitRate": 0.050314465408805034 - }, - { - "encoding": "ISO-8859-14", - "confidence": 9, - "language": "cy", - "byteLogLikelihood": -4.912654885736, - "hits": 5, - "total": 159, - "hitRate": 0.031446540880503145 - }, - { - "encoding": "CP852", - "confidence": 7, - "language": "pl", - "byteLogLikelihood": -5.087596335232, - "hits": 4, - "total": 159, - "hitRate": 0.025157232704402517 - }, - { - "encoding": "ISO-8859-9", - "confidence": 5, - "language": "tr", - "byteLogLikelihood": -5.075173815234, - "hits": 3, - "total": 159, - "hitRate": 0.018867924528301886 - }, - { - "encoding": "windows-1254", - "confidence": 5, - "language": "tr", - "byteLogLikelihood": -5.075173815234, - "hits": 3, - "total": 159, - "hitRate": 0.018867924528301886 - }, - { - "encoding": "ISO-8859-3", - "confidence": 5, - "language": "mt", - "byteLogLikelihood": -5.105945473901, - "hits": 3, - "total": 159, - "hitRate": 0.018867924528301886 - }, - { - "encoding": "ISO-8859-10", - "confidence": 3, - "language": "is", - "byteLogLikelihood": -5.204006687077, - "hits": 2, - "total": 159, - "hitRate": 0.012578616352201259 - }, - { - "encoding": "ISO-8859-13", - "confidence": 3, - "language": "lt", - "byteLogLikelihood": -3.332204510175, - "hits": 2, - "total": 159, - "hitRate": 0.012578616352201259 - }, - { - "encoding": "ISO-8859-5", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -2.954414124223, - "hits": 0, - "total": 159, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-6", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -6.113682179832, - "hits": 0, - "total": 159, - "hitRate": 0 + "byteLogLikelihood": -5.176149732574, + "hits": 10, + "total": 200, + "hitRate": 0.05 }, { "encoding": "ISO-8859-7", - "confidence": 0, "language": "el", - "byteLogLikelihood": -6.120297418951, + "confidence": 0, + "byteLogLikelihood": -3.106555532888, "hits": 0, - "total": 159, + "total": 200, "hitRate": 0 }, { "encoding": "ISO-8859-8", - "confidence": 0, "language": "he", - "byteLogLikelihood": -3.629660094454, + "confidence": 0, + "byteLogLikelihood": -3.411159813207, "hits": 0, - "total": 159, + "total": 200, "hitRate": 0 }, { "encoding": "windows-1251", - "confidence": 0, "language": "ru", - "byteLogLikelihood": -2.533200659147, + "confidence": 0, + "byteLogLikelihood": -3.336328204376, "hits": 0, - "total": 159, + "total": 200, "hitRate": 0 }, { "encoding": "windows-1253", - "confidence": 0, "language": "el", - "byteLogLikelihood": -6.120297418951, + "confidence": 0, + "byteLogLikelihood": -3.106555532888, "hits": 0, - "total": 159, + "total": 200, "hitRate": 0 }, { "encoding": "windows-1255", - "confidence": 0, "language": "he", - "byteLogLikelihood": -3.629660094454, + "confidence": 0, + "byteLogLikelihood": -3.411159813207, "hits": 0, - "total": 159, + "total": 200, "hitRate": 0 }, { "encoding": "windows-1256", - "confidence": 0, "language": "ar", - "byteLogLikelihood": -6.113682179832, - "hits": 0, - "total": 159, - "hitRate": 0 - }, - { - "encoding": "windows-874", - "confidence": 0, - "language": "th", - "byteLogLikelihood": -3.496507561466, - "hits": 0, - "total": 159, - "hitRate": 0 - }, - { - "encoding": "KOI8-R", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.692083742507, - "hits": 0, - "total": 159, - "hitRate": 0 - }, - { - "encoding": "KOI8-U", - "confidence": 0, - "language": "uk", - "byteLogLikelihood": -6.650279048587, - "hits": 0, - "total": 159, - "hitRate": 0 - }, - { - "encoding": "IBM866", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -2.954414124223, - "hits": 0, - "total": 159, - "hitRate": 0 - }, - { - "encoding": "IBM855", "confidence": 0, - "language": "sr", - "byteLogLikelihood": -6.520621127559, + "byteLogLikelihood": -3.300604963183, "hits": 0, - "total": 159, + "total": 200, "hitRate": 0 }, { "encoding": "x-mac-cyrillic", - "confidence": 0, "language": "ru", - "byteLogLikelihood": -2.533200659147, + "confidence": 0, + "byteLogLikelihood": -3.336328204376, "hits": 0, - "total": 159, + "total": 200, "hitRate": 0 } ] }, { "expected": { - "encoding": "ISO-8859-1", - "language": "nl" + "encoding": "ISO-8859-15", + "language": "fr" }, "predicted": { "encoding": "ISO-8859-1", - "confidence": 83, - "language": "nl", - "byteLogLikelihood": -3.295836866004, - "hits": 42, - "total": 151, - "hitRate": 0.2781456953642384 + "language": "fr", + "confidence": 77, + "byteLogLikelihood": -2.06619631493, + "hits": 59, + "total": 228, + "hitRate": 0.25877192982456143 }, - "encodingExact": true, - "encodingEquivalent": false, + "encodingExact": false, + "encodingEquivalent": true, "encodingCorrect": true, "languageCorrect": true, - "tiedAtTop": 2, + "tiedAtTop": 3, "candidates": [ { "encoding": "ISO-8859-1", - "confidence": 83, - "language": "nl", - "byteLogLikelihood": -3.295836866004, - "hits": 42, - "total": 151, - "hitRate": 0.2781456953642384 - }, - { - "encoding": "windows-1252", - "confidence": 83, - "language": "nl", - "byteLogLikelihood": -3.295836866004, - "hits": 42, - "total": 151, - "hitRate": 0.2781456953642384 - }, - { - "encoding": "macintosh", - "confidence": 63, - "language": "de", - "byteLogLikelihood": -5.003946305945, - "hits": 32, - "total": 151, - "hitRate": 0.2119205298013245 + "language": "fr", + "confidence": 77, + "byteLogLikelihood": -2.06619631493, + "hits": 59, + "total": 228, + "hitRate": 0.25877192982456143 }, { "encoding": "ISO-8859-15", - "confidence": 63, - "language": "de", - "byteLogLikelihood": -5.003946305945, - "hits": 32, - "total": 151, - "hitRate": 0.2119205298013245 - }, - { - "encoding": "CP850", - "confidence": 63, - "language": "de", - "byteLogLikelihood": -5.003946305945, - "hits": 32, - "total": 151, - "hitRate": 0.2119205298013245 + "language": "fr", + "confidence": 77, + "byteLogLikelihood": -2.06619631493, + "hits": 59, + "total": 228, + "hitRate": 0.25877192982456143 }, { - "encoding": "ISO-8859-14", - "confidence": 33, - "language": "cy", - "byteLogLikelihood": -4.912654885736, - "hits": 17, - "total": 151, - "hitRate": 0.11258278145695365 + "encoding": "windows-1252", + "language": "fr", + "confidence": 77, + "byteLogLikelihood": -2.06619631493, + "hits": 59, + "total": 228, + "hitRate": 0.25877192982456143 }, { "encoding": "ISO-8859-2", - "confidence": 13, "language": "ro", + "confidence": 11, "byteLogLikelihood": -5.176149732574, - "hits": 7, - "total": 151, - "hitRate": 0.046357615894039736 - }, - { - "encoding": "ISO-8859-9", - "confidence": 13, - "language": "tr", - "byteLogLikelihood": -5.075173815234, - "hits": 7, - "total": 151, - "hitRate": 0.046357615894039736 + "hits": 9, + "total": 228, + "hitRate": 0.039473684210526314 }, { "encoding": "windows-1250", - "confidence": 13, "language": "ro", + "confidence": 11, "byteLogLikelihood": -5.176149732574, - "hits": 7, - "total": 151, - "hitRate": 0.046357615894039736 - }, - { - "encoding": "windows-1254", - "confidence": 13, - "language": "tr", - "byteLogLikelihood": -5.075173815234, - "hits": 7, - "total": 151, - "hitRate": 0.046357615894039736 + "hits": 9, + "total": 228, + "hitRate": 0.039473684210526314 }, { "encoding": "ISO-8859-10", - "confidence": 11, "language": "is", + "confidence": 10, "byteLogLikelihood": -4.510859506517, - "hits": 6, - "total": 151, - "hitRate": 0.039735099337748346 - }, - { - "encoding": "ISO-8859-16", - "confidence": 11, - "language": "ro", - "byteLogLikelihood": -5.220355825078, - "hits": 6, - "total": 151, - "hitRate": 0.039735099337748346 - }, - { - "encoding": "windows-1257", - "confidence": 9, - "language": "et", - "byteLogLikelihood": -4.934473933131, - "hits": 5, - "total": 151, - "hitRate": 0.033112582781456956 - }, - { - "encoding": "windows-1258", - "confidence": 3, - "language": "vi", - "byteLogLikelihood": -5.497168225293, - "hits": 2, - "total": 151, - "hitRate": 0.013245033112582781 - }, - { - "encoding": "ISO-8859-13", - "confidence": 3, - "language": "lt", - "byteLogLikelihood": -5.123963979403, - "hits": 2, - "total": 151, - "hitRate": 0.013245033112582781 - }, - { - "encoding": "ISO-8859-3", - "confidence": 1, - "language": "mt", - "byteLogLikelihood": -5.105945473901, - "hits": 1, - "total": 151, - "hitRate": 0.006622516556291391 - }, - { - "encoding": "ISO-8859-4", - "confidence": 1, - "language": "lv", - "byteLogLikelihood": -5.19295685089, - "hits": 1, - "total": 151, - "hitRate": 0.006622516556291391 - }, - { - "encoding": "CP852", - "confidence": 1, - "language": "pl", - "byteLogLikelihood": -5.087596335232, - "hits": 1, - "total": 151, - "hitRate": 0.006622516556291391 - }, - { - "encoding": "ISO-8859-5", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.593471453839, - "hits": 0, - "total": 151, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-6", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -6.113682179832, - "hits": 0, - "total": 151, - "hitRate": 0 + "hits": 8, + "total": 228, + "hitRate": 0.03508771929824561 }, { "encoding": "ISO-8859-7", - "confidence": 0, "language": "el", + "confidence": 0, "byteLogLikelihood": -2.654561516151, "hits": 0, - "total": 151, + "total": 228, "hitRate": 0 }, { "encoding": "ISO-8859-8", - "confidence": 0, "language": "he", - "byteLogLikelihood": -2.405884662832, - "hits": 0, - "total": 151, - "hitRate": 0 - }, - { - "encoding": "windows-1251", "confidence": 0, - "language": "ru", - "byteLogLikelihood": -4.612642200827, + "byteLogLikelihood": -2.405884662832, "hits": 0, - "total": 151, + "total": 228, "hitRate": 0 }, { "encoding": "windows-1253", - "confidence": 0, "language": "el", + "confidence": 0, "byteLogLikelihood": -2.654561516151, "hits": 0, - "total": 151, + "total": 228, "hitRate": 0 }, { "encoding": "windows-1255", - "confidence": 0, "language": "he", - "byteLogLikelihood": -2.405884662832, - "hits": 0, - "total": 151, - "hitRate": 0 - }, - { - "encoding": "windows-1256", "confidence": 0, - "language": "ar", - "byteLogLikelihood": -6.113682179832, + "byteLogLikelihood": -2.405884662832, "hits": 0, - "total": 151, + "total": 228, "hitRate": 0 }, { "encoding": "windows-874", - "confidence": 0, "language": "th", - "byteLogLikelihood": -3.57655026914, - "hits": 0, - "total": 150, - "hitRate": 0 - }, - { - "encoding": "KOI8-R", "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.692083742507, + "byteLogLikelihood": -3.57655026914, "hits": 0, - "total": 151, + "total": 224, "hitRate": 0 }, { - "encoding": "KOI8-U", - "confidence": 0, + "encoding": "x-mac-cyrillic", "language": "uk", - "byteLogLikelihood": -6.650279048587, - "hits": 0, - "total": 151, - "hitRate": 0 - }, - { - "encoding": "IBM866", "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.593471453839, + "byteLogLikelihood": -4.252383775789, "hits": 0, - "total": 151, - "hitRate": 0 - }, - { - "encoding": "IBM855", - "confidence": 0, - "language": "sr", - "byteLogLikelihood": -4.728861658331, - "hits": 0, - "total": 151, - "hitRate": 0 - }, - { - "encoding": "x-mac-cyrillic", - "confidence": 0, - "language": "uk", - "byteLogLikelihood": -4.252383775789, - "hits": 0, - "total": 151, + "total": 228, "hitRate": 0 } ] }, { "expected": { - "encoding": "ISO-8859-1", - "language": "no" + "encoding": "ISO-8859-16", + "language": "ro" }, "predicted": { - "encoding": "ISO-8859-1", - "confidence": 47, - "language": "no", - "byteLogLikelihood": -3.052495812716, - "hits": 18, - "total": 114, - "hitRate": 0.15789473684210525 + "encoding": "ISO-8859-16", + "language": "ro", + "confidence": 53, + "byteLogLikelihood": -2.758152644716, + "hits": 38, + "total": 214, + "hitRate": 0.17757009345794392 }, "encodingExact": true, "encodingEquivalent": false, "encodingCorrect": true, "languageCorrect": true, - "tiedAtTop": 2, + "tiedAtTop": 1, "candidates": [ - { - "encoding": "ISO-8859-1", - "confidence": 47, - "language": "no", - "byteLogLikelihood": -3.052495812716, - "hits": 18, - "total": 114, - "hitRate": 0.15789473684210525 - }, - { - "encoding": "windows-1252", - "confidence": 47, - "language": "no", - "byteLogLikelihood": -3.052495812716, - "hits": 18, - "total": 114, - "hitRate": 0.15789473684210525 - }, - { - "encoding": "macintosh", - "confidence": 18, - "language": "de", - "byteLogLikelihood": -5.003946305945, - "hits": 7, - "total": 114, - "hitRate": 0.06140350877192982 - }, - { - "encoding": "ISO-8859-14", - "confidence": 18, - "language": "cy", - "byteLogLikelihood": -4.912654885736, - "hits": 7, - "total": 114, - "hitRate": 0.06140350877192982 - }, - { - "encoding": "ISO-8859-15", - "confidence": 18, - "language": "de", - "byteLogLikelihood": -5.003946305945, - "hits": 7, - "total": 114, - "hitRate": 0.06140350877192982 - }, - { - "encoding": "CP850", - "confidence": 18, - "language": "de", - "byteLogLikelihood": -5.003946305945, - "hits": 7, - "total": 114, - "hitRate": 0.06140350877192982 - }, - { - "encoding": "ISO-8859-10", - "confidence": 13, - "language": "is", - "byteLogLikelihood": -5.204006687077, - "hits": 5, - "total": 114, - "hitRate": 0.043859649122807015 - }, - { - "encoding": "windows-1258", - "confidence": 10, - "language": "vi", - "byteLogLikelihood": -5.497168225293, - "hits": 4, - "total": 114, - "hitRate": 0.03508771929824561 - }, { "encoding": "ISO-8859-16", - "confidence": 10, "language": "ro", - "byteLogLikelihood": -5.220355825078, - "hits": 4, - "total": 114, - "hitRate": 0.03508771929824561 + "confidence": 53, + "byteLogLikelihood": -2.758152644716, + "hits": 38, + "total": 214, + "hitRate": 0.17757009345794392 }, { "encoding": "ISO-8859-2", - "confidence": 7, - "language": "cs", - "byteLogLikelihood": -4.354336342997, - "hits": 3, - "total": 114, - "hitRate": 0.02631578947368421 - }, - { - "encoding": "ISO-8859-9", - "confidence": 7, - "language": "tr", - "byteLogLikelihood": -5.075173815234, - "hits": 3, - "total": 114, - "hitRate": 0.02631578947368421 + "language": "ro", + "confidence": 44, + "byteLogLikelihood": -2.870272383724, + "hits": 32, + "total": 214, + "hitRate": 0.14953271028037382 }, { "encoding": "windows-1250", - "confidence": 7, - "language": "cs", - "byteLogLikelihood": -4.354336342997, - "hits": 3, - "total": 114, - "hitRate": 0.02631578947368421 - }, - { - "encoding": "windows-1254", - "confidence": 7, - "language": "tr", - "byteLogLikelihood": -5.075173815234, - "hits": 3, - "total": 114, - "hitRate": 0.02631578947368421 + "language": "ro", + "confidence": 44, + "byteLogLikelihood": -2.870272383724, + "hits": 32, + "total": 214, + "hitRate": 0.14953271028037382 }, { - "encoding": "windows-1257", - "confidence": 7, - "language": "et", - "byteLogLikelihood": -4.934473933131, - "hits": 3, - "total": 114, - "hitRate": 0.02631578947368421 + "encoding": "ISO-8859-1", + "language": "it", + "confidence": 26, + "byteLogLikelihood": -4.919980925828, + "hits": 19, + "total": 214, + "hitRate": 0.08878504672897196 }, { - "encoding": "ISO-8859-3", - "confidence": 2, - "language": "mt", - "byteLogLikelihood": -4.210065739287, - "hits": 1, - "total": 114, - "hitRate": 0.008771929824561403 + "encoding": "windows-1252", + "language": "it", + "confidence": 26, + "byteLogLikelihood": -4.919980925828, + "hits": 19, + "total": 214, + "hitRate": 0.08878504672897196 }, { - "encoding": "ISO-8859-4", - "confidence": 2, + "encoding": "windows-1257", "language": "lv", - "byteLogLikelihood": -5.19295685089, - "hits": 1, - "total": 114, - "hitRate": 0.008771929824561403 - }, - { - "encoding": "ISO-8859-13", - "confidence": 2, - "language": "lt", - "byteLogLikelihood": -4.319245023186, - "hits": 1, - "total": 114, - "hitRate": 0.008771929824561403 - }, - { - "encoding": "CP852", - "confidence": 2, - "language": "pl", - "byteLogLikelihood": -5.087596335232, - "hits": 1, - "total": 114, - "hitRate": 0.008771929824561403 - }, - { - "encoding": "ISO-8859-5", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.652362971667, - "hits": 0, - "total": 114, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-6", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -4.641462690249, - "hits": 0, - "total": 114, - "hitRate": 0 + "confidence": 8, + "byteLogLikelihood": -4.456762061842, + "hits": 6, + "total": 214, + "hitRate": 0.028037383177570093 }, { "encoding": "ISO-8859-7", - "confidence": 0, "language": "el", - "byteLogLikelihood": -4.154384602589, + "confidence": 0, + "byteLogLikelihood": -4.499845100591, "hits": 0, - "total": 114, + "total": 214, "hitRate": 0 }, { "encoding": "ISO-8859-8", - "confidence": 0, "language": "he", - "byteLogLikelihood": -2.647504477241, + "confidence": 0, + "byteLogLikelihood": -4.429071192897, "hits": 0, - "total": 114, + "total": 213, "hitRate": 0 }, { "encoding": "windows-1251", - "confidence": 0, "language": "ru", - "byteLogLikelihood": -3.753215851617, - "hits": 0, - "total": 114, - "hitRate": 0 - }, - { - "encoding": "windows-1253", "confidence": 0, - "language": "el", - "byteLogLikelihood": -4.154384602589, + "byteLogLikelihood": -4.382241948417, "hits": 0, - "total": 114, + "total": 214, "hitRate": 0 }, { "encoding": "windows-1255", - "confidence": 0, "language": "he", - "byteLogLikelihood": -2.647504477241, + "confidence": 0, + "byteLogLikelihood": -4.429071192897, "hits": 0, - "total": 114, + "total": 213, "hitRate": 0 }, { - "encoding": "windows-1256", + "encoding": "IBM866", + "language": "ru", "confidence": 0, - "language": "ar", - "byteLogLikelihood": -5.217802445218, + "byteLogLikelihood": -4.333669615722, "hits": 0, - "total": 114, + "total": 215, "hitRate": 0 }, { - "encoding": "windows-874", + "encoding": "x-mac-cyrillic", + "language": "ru", "confidence": 0, - "language": "th", - "byteLogLikelihood": -6.061456918928, + "byteLogLikelihood": -4.382241948417, "hits": 0, - "total": 114, + "total": 214, "hitRate": 0 + } + ] + }, + { + "expected": { + "encoding": "ISO-8859-2", + "language": "cs" + }, + "predicted": { + "encoding": "ISO-8859-2", + "language": "cs", + "confidence": 30, + "byteLogLikelihood": -3.429159108442, + "hits": 13, + "total": 126, + "hitRate": 0.10317460317460317 + }, + "encodingExact": true, + "encodingEquivalent": false, + "encodingCorrect": true, + "languageCorrect": true, + "tiedAtTop": 2, + "candidates": [ + { + "encoding": "ISO-8859-2", + "language": "cs", + "confidence": 30, + "byteLogLikelihood": -3.429159108442, + "hits": 13, + "total": 126, + "hitRate": 0.10317460317460317 }, { - "encoding": "KOI8-R", + "encoding": "windows-1250", + "language": "cs", + "confidence": 30, + "byteLogLikelihood": -3.429159108442, + "hits": 13, + "total": 126, + "hitRate": 0.10317460317460317 + }, + { + "encoding": "ISO-8859-1", + "language": "pt", + "confidence": 11, + "byteLogLikelihood": -4.5670392286, + "hits": 5, + "total": 126, + "hitRate": 0.03968253968253968 + }, + { + "encoding": "windows-1252", + "language": "pt", + "confidence": 11, + "byteLogLikelihood": -4.5670392286, + "hits": 5, + "total": 126, + "hitRate": 0.03968253968253968 + }, + { + "encoding": "ISO-8859-15", + "language": "fr", + "confidence": 7, + "byteLogLikelihood": -4.081579721495, + "hits": 3, + "total": 126, + "hitRate": 0.023809523809523808 + }, + { + "encoding": "ISO-8859-7", + "language": "el", "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.692083742507, + "byteLogLikelihood": -3.401446196881, "hits": 0, - "total": 114, + "total": 126, "hitRate": 0 }, { - "encoding": "KOI8-U", + "encoding": "ISO-8859-8", + "language": "he", "confidence": 0, - "language": "uk", - "byteLogLikelihood": -6.650279048587, + "byteLogLikelihood": -3.467509652199, "hits": 0, - "total": 114, + "total": 125, "hitRate": 0 }, { - "encoding": "IBM866", - "confidence": 0, + "encoding": "windows-1251", "language": "ru", - "byteLogLikelihood": -5.652362971667, + "confidence": 0, + "byteLogLikelihood": -4.249199684222, "hits": 0, - "total": 114, + "total": 126, "hitRate": 0 }, { - "encoding": "IBM855", + "encoding": "windows-1253", + "language": "el", "confidence": 0, - "language": "ru", - "byteLogLikelihood": -4.679407897139, + "byteLogLikelihood": -3.401446196881, "hits": 0, - "total": 114, + "total": 126, + "hitRate": 0 + }, + { + "encoding": "windows-1255", + "language": "he", + "confidence": 0, + "byteLogLikelihood": -3.467509652199, + "hits": 0, + "total": 125, "hitRate": 0 }, { "encoding": "x-mac-cyrillic", + "language": "uk", "confidence": 0, - "language": "ru", - "byteLogLikelihood": -3.753215851617, + "byteLogLikelihood": -4.226561011787, "hits": 0, - "total": 114, + "total": 126, + "hitRate": 0 + }, + { + "encoding": "ISO-8859-10", + "language": "is", + "confidence": 0, + "byteLogLikelihood": -4.43713857777, + "hits": 0, + "total": 126, "hitRate": 0 } ] }, { "expected": { - "encoding": "ISO-8859-1", - "language": "pt" + "encoding": "ISO-8859-2", + "language": "hu" }, "predicted": { - "encoding": "ISO-8859-15", - "confidence": 33, - "language": "pt", - "byteLogLikelihood": -3.970754139021, - "hits": 16, - "total": 143, - "hitRate": 0.11188811188811189 + "encoding": "ISO-8859-2", + "language": "hu", + "confidence": 46, + "byteLogLikelihood": -3.161205902203, + "hits": 21, + "total": 136, + "hitRate": 0.15441176470588236 }, - "encodingExact": false, - "encodingEquivalent": true, + "encodingExact": true, + "encodingEquivalent": false, "encodingCorrect": true, "languageCorrect": true, - "tiedAtTop": 1, + "tiedAtTop": 2, "candidates": [ { - "encoding": "ISO-8859-15", - "confidence": 33, - "language": "es", - "byteLogLikelihood": -3.970754139021, - "hits": 16, - "total": 143, - "hitRate": 0.11188811188811189 + "encoding": "ISO-8859-2", + "language": "hu", + "confidence": 46, + "byteLogLikelihood": -3.161205902203, + "hits": 21, + "total": 136, + "hitRate": 0.15441176470588236 + }, + { + "encoding": "windows-1250", + "language": "hu", + "confidence": 46, + "byteLogLikelihood": -3.161205902203, + "hits": 21, + "total": 136, + "hitRate": 0.15441176470588236 }, { "encoding": "ISO-8859-1", - "confidence": 50, "language": "pt", - "byteLogLikelihood": -4.059947322987, - "hits": 24, - "total": 143, - "hitRate": 0.16783216783216784 + "confidence": 17, + "byteLogLikelihood": -4.507887190294, + "hits": 8, + "total": 136, + "hitRate": 0.058823529411764705 }, { "encoding": "windows-1252", - "confidence": 50, "language": "pt", - "byteLogLikelihood": -4.059947322987, - "hits": 24, - "total": 143, - "hitRate": 0.16783216783216784 + "confidence": 17, + "byteLogLikelihood": -4.507887190294, + "hits": 8, + "total": 136, + "hitRate": 0.058823529411764705 + }, + { + "encoding": "ISO-8859-15", + "language": "fr", + "confidence": 4, + "byteLogLikelihood": -4.274525549305, + "hits": 2, + "total": 136, + "hitRate": 0.014705882352941176 }, { "encoding": "windows-1257", - "confidence": 29, - "language": "lt", - "byteLogLikelihood": -4.777390389123, - "hits": 14, - "total": 143, - "hitRate": 0.0979020979020979 + "language": "et", + "confidence": 2, + "byteLogLikelihood": -4.453831056838, + "hits": 1, + "total": 136, + "hitRate": 0.007352941176470588 }, { - "encoding": "ISO-8859-13", - "confidence": 29, - "language": "lt", - "byteLogLikelihood": -4.777390389123, - "hits": 14, - "total": 143, - "hitRate": 0.0979020979020979 + "encoding": "ISO-8859-10", + "language": "is", + "confidence": 2, + "byteLogLikelihood": -3.90025153387, + "hits": 1, + "total": 136, + "hitRate": 0.007352941176470588 }, { - "encoding": "macintosh", - "confidence": 31, - "language": "es", - "byteLogLikelihood": -4.948759890378, - "hits": 15, - "total": 143, - "hitRate": 0.1048951048951049 + "encoding": "ISO-8859-7", + "language": "el", + "confidence": 0, + "byteLogLikelihood": -3.430247904624, + "hits": 0, + "total": 136, + "hitRate": 0 }, { - "encoding": "CP850", - "confidence": 31, - "language": "es", - "byteLogLikelihood": -4.948759890378, - "hits": 15, - "total": 143, - "hitRate": 0.1048951048951049 + "encoding": "ISO-8859-8", + "language": "he", + "confidence": 0, + "byteLogLikelihood": -3.984546441118, + "hits": 0, + "total": 135, + "hitRate": 0 }, { - "encoding": "ISO-8859-4", - "confidence": 23, - "language": "lv", - "byteLogLikelihood": -5.19295685089, - "hits": 11, - "total": 143, - "hitRate": 0.07692307692307693 + "encoding": "windows-1253", + "language": "el", + "confidence": 0, + "byteLogLikelihood": -3.430247904624, + "hits": 0, + "total": 136, + "hitRate": 0 }, { - "encoding": "ISO-8859-2", - "confidence": 10, - "language": "hu", - "byteLogLikelihood": -3.361609233757, - "hits": 5, - "total": 143, - "hitRate": 0.03496503496503497 + "encoding": "windows-1255", + "language": "he", + "confidence": 0, + "byteLogLikelihood": -3.984546441118, + "hits": 0, + "total": 135, + "hitRate": 0 + }, + { + "encoding": "x-mac-cyrillic", + "language": "uk", + "confidence": 0, + "byteLogLikelihood": -4.187765411941, + "hits": 0, + "total": 136, + "hitRate": 0 + } + ] + }, + { + "expected": { + "encoding": "ISO-8859-2", + "language": "pl" + }, + "predicted": { + "encoding": "ISO-8859-2", + "language": "pl", + "confidence": 40, + "byteLogLikelihood": -3.52910527172, + "hits": 25, + "total": 184, + "hitRate": 0.1358695652173913 + }, + "encodingExact": true, + "encodingEquivalent": false, + "encodingCorrect": true, + "languageCorrect": true, + "tiedAtTop": 1, + "candidates": [ + { + "encoding": "ISO-8859-2", + "language": "pl", + "confidence": 40, + "byteLogLikelihood": -3.52910527172, + "hits": 25, + "total": 184, + "hitRate": 0.1358695652173913 }, { "encoding": "windows-1250", - "confidence": 10, - "language": "hu", - "byteLogLikelihood": -3.361609233757, + "language": "pl", + "confidence": 37, + "byteLogLikelihood": -4.297518988235, + "hits": 23, + "total": 183, + "hitRate": 0.12568306010928962 + }, + { + "encoding": "ISO-8859-1", + "language": "it", + "confidence": 8, + "byteLogLikelihood": -4.919980925828, "hits": 5, - "total": 143, - "hitRate": 0.03496503496503497 + "total": 183, + "hitRate": 0.0273224043715847 }, { - "encoding": "ISO-8859-14", - "confidence": 10, - "language": "cy", - "byteLogLikelihood": -4.912654885736, + "encoding": "windows-1252", + "language": "it", + "confidence": 8, + "byteLogLikelihood": -4.919980925828, "hits": 5, - "total": 143, - "hitRate": 0.03496503496503497 + "total": 183, + "hitRate": 0.0273224043715847 }, { - "encoding": "windows-1258", + "encoding": "windows-1257", + "language": "et", "confidence": 6, - "language": "vi", - "byteLogLikelihood": -4.524213150766, - "hits": 3, - "total": 143, - "hitRate": 0.02097902097902098 + "byteLogLikelihood": -4.934473933131, + "hits": 4, + "total": 183, + "hitRate": 0.02185792349726776 }, { - "encoding": "ISO-8859-10", + "encoding": "macintosh", + "language": "es", "confidence": 6, - "language": "is", - "byteLogLikelihood": -4.06291963921, + "byteLogLikelihood": -4.948759890378, + "hits": 4, + "total": 183, + "hitRate": 0.02185792349726776 + }, + { + "encoding": "ISO-8859-15", + "language": "es", + "confidence": 6, + "byteLogLikelihood": -4.396558412648, + "hits": 4, + "total": 183, + "hitRate": 0.02185792349726776 + }, + { + "encoding": "CP850", + "language": "fr", + "confidence": 6, + "byteLogLikelihood": -5.010635294096, + "hits": 4, + "total": 182, + "hitRate": 0.02197802197802198 + }, + { + "encoding": "ISO-8859-4", + "language": "lv", + "confidence": 4, + "byteLogLikelihood": -4.794788079951, "hits": 3, - "total": 143, - "hitRate": 0.02097902097902098 + "total": 184, + "hitRate": 0.016304347826086956 }, { - "encoding": "ISO-8859-9", - "confidence": 2, - "language": "tr", - "byteLogLikelihood": -4.58869627797, + "encoding": "ISO-8859-3", + "language": "mt", + "confidence": 1, + "byteLogLikelihood": -4.476342508555, "hits": 1, - "total": 143, - "hitRate": 0.006993006993006993 + "total": 184, + "hitRate": 0.005434782608695652 }, { - "encoding": "windows-1254", - "confidence": 2, - "language": "tr", - "byteLogLikelihood": -4.58869627797, + "encoding": "ISO-8859-10", + "language": "is", + "confidence": 1, + "byteLogLikelihood": -4.71573455878, "hits": 1, - "total": 143, - "hitRate": 0.006993006993006993 + "total": 184, + "hitRate": 0.005434782608695652 + }, + { + "encoding": "ISO-8859-14", + "language": "cy", + "confidence": 1, + "byteLogLikelihood": -4.912654885736, + "hits": 1, + "total": 184, + "hitRate": 0.005434782608695652 + } + ] + }, + { + "expected": { + "encoding": "ISO-8859-2", + "language": "ro" + }, + "predicted": { + "encoding": "ISO-8859-2", + "language": "ro", + "confidence": 41, + "byteLogLikelihood": -2.684539297542, + "hits": 28, + "total": 202, + "hitRate": 0.13861386138613863 + }, + "encodingExact": true, + "encodingEquivalent": false, + "encodingCorrect": true, + "languageCorrect": true, + "tiedAtTop": 2, + "candidates": [ + { + "encoding": "ISO-8859-2", + "language": "ro", + "confidence": 41, + "byteLogLikelihood": -2.684539297542, + "hits": 28, + "total": 202, + "hitRate": 0.13861386138613863 + }, + { + "encoding": "windows-1250", + "language": "ro", + "confidence": 41, + "byteLogLikelihood": -2.684539297542, + "hits": 28, + "total": 202, + "hitRate": 0.13861386138613863 }, { "encoding": "ISO-8859-16", - "confidence": 2, "language": "ro", - "byteLogLikelihood": -5.220355825078, - "hits": 1, - "total": 143, - "hitRate": 0.006993006993006993 + "confidence": 38, + "byteLogLikelihood": -2.700458868498, + "hits": 26, + "total": 202, + "hitRate": 0.12871287128712872 }, { - "encoding": "CP852", - "confidence": 2, - "language": "pl", - "byteLogLikelihood": -5.087596335232, - "hits": 1, - "total": 143, - "hitRate": 0.006993006993006993 + "encoding": "ISO-8859-1", + "language": "it", + "confidence": 26, + "byteLogLikelihood": -4.919980925828, + "hits": 18, + "total": 202, + "hitRate": 0.0891089108910891 }, { - "encoding": "ISO-8859-5", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -4.338763438513, - "hits": 0, - "total": 143, - "hitRate": 0 + "encoding": "windows-1252", + "language": "it", + "confidence": 26, + "byteLogLikelihood": -4.919980925828, + "hits": 18, + "total": 202, + "hitRate": 0.0891089108910891 }, { - "encoding": "ISO-8859-6", + "encoding": "ISO-8859-5", + "language": "ru", "confidence": 0, - "language": "ar", - "byteLogLikelihood": -4.514449766028, + "byteLogLikelihood": -4.208609169552, "hits": 0, - "total": 143, + "total": 202, "hitRate": 0 }, { "encoding": "ISO-8859-7", - "confidence": 0, "language": "el", - "byteLogLikelihood": -3.017269736716, + "confidence": 0, + "byteLogLikelihood": -4.33505338151, "hits": 0, - "total": 143, + "total": 202, "hitRate": 0 }, { "encoding": "ISO-8859-8", - "confidence": 0, "language": "he", - "byteLogLikelihood": -3.50352863905, + "confidence": 0, + "byteLogLikelihood": -4.197813655274, "hits": 0, - "total": 143, + "total": 201, "hitRate": 0 }, { "encoding": "windows-1251", - "confidence": 0, "language": "ru", - "byteLogLikelihood": -3.846220145127, + "confidence": 0, + "byteLogLikelihood": -4.229886082374, "hits": 0, - "total": 143, + "total": 202, "hitRate": 0 }, { - "encoding": "windows-1253", + "encoding": "windows-1255", + "language": "he", "confidence": 0, - "language": "el", - "byteLogLikelihood": -3.017269736716, - "hits": 0, - "total": 143, - "hitRate": 0 - }, - { - "encoding": "windows-1255", - "confidence": 0, - "language": "he", - "byteLogLikelihood": -3.50352863905, - "hits": 0, - "total": 143, - "hitRate": 0 - }, - { - "encoding": "windows-1256", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -3.503504267293, - "hits": 0, - "total": 143, - "hitRate": 0 - }, - { - "encoding": "windows-874", - "confidence": 0, - "language": "th", - "byteLogLikelihood": -4.91521504926, - "hits": 0, - "total": 143, - "hitRate": 0 - }, - { - "encoding": "KOI8-R", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.518796947367, - "hits": 0, - "total": 143, - "hitRate": 0 - }, - { - "encoding": "KOI8-U", - "confidence": 0, - "language": "uk", - "byteLogLikelihood": -6.476992253447, + "byteLogLikelihood": -4.197813655274, "hits": 0, - "total": 143, + "total": 201, "hitRate": 0 }, { "encoding": "IBM866", - "confidence": 0, "language": "ru", - "byteLogLikelihood": -4.338763438513, - "hits": 0, - "total": 143, - "hitRate": 0 - }, - { - "encoding": "IBM855", "confidence": 0, - "language": "sr", - "byteLogLikelihood": -3.774998078834, + "byteLogLikelihood": -4.208609169552, "hits": 0, - "total": 143, + "total": 201, "hitRate": 0 }, { "encoding": "x-mac-cyrillic", + "language": "ru", "confidence": 0, - "language": "uk", - "byteLogLikelihood": -3.766179593299, - "hits": 0, - "total": 143, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-3", - "confidence": 0, - "language": "mt", - "byteLogLikelihood": -5.105945473901, + "byteLogLikelihood": -4.229886082374, "hits": 0, - "total": 143, + "total": 202, "hitRate": 0 } ] }, { "expected": { - "encoding": "ISO-8859-1", - "language": "sv" + "encoding": "ISO-8859-3", + "language": "mt" }, "predicted": { - "encoding": "ISO-8859-1", - "confidence": 50, - "language": "sv", - "byteLogLikelihood": -3.23645137845, - "hits": 23, - "total": 136, - "hitRate": 0.16911764705882354 + "encoding": "ISO-8859-3", + "language": "mt", + "confidence": 52, + "byteLogLikelihood": -2.738213481781, + "hits": 32, + "total": 183, + "hitRate": 0.17486338797814208 }, "encodingExact": true, "encodingEquivalent": false, "encodingCorrect": true, "languageCorrect": true, - "tiedAtTop": 2, + "tiedAtTop": 1, "candidates": [ { - "encoding": "ISO-8859-1", - "confidence": 50, - "language": "sv", - "byteLogLikelihood": -3.23645137845, - "hits": 23, - "total": 136, - "hitRate": 0.16911764705882354 - }, - { - "encoding": "windows-1252", - "confidence": 50, - "language": "sv", - "byteLogLikelihood": -3.23645137845, - "hits": 23, - "total": 136, - "hitRate": 0.16911764705882354 + "encoding": "ISO-8859-3", + "language": "mt", + "confidence": 52, + "byteLogLikelihood": -2.738213481781, + "hits": 32, + "total": 183, + "hitRate": 0.17486338797814208 }, { - "encoding": "windows-1258", - "confidence": 19, - "language": "vi", - "byteLogLikelihood": -5.497168225293, + "encoding": "ISO-8859-1", + "language": "it", + "confidence": 14, + "byteLogLikelihood": -4.81334289805, "hits": 9, - "total": 136, - "hitRate": 0.0661764705882353 + "total": 181, + "hitRate": 0.049723756906077346 }, { - "encoding": "ISO-8859-10", - "confidence": 19, - "language": "is", - "byteLogLikelihood": -4.980036753423, + "encoding": "windows-1252", + "language": "it", + "confidence": 14, + "byteLogLikelihood": -4.81334289805, "hits": 9, - "total": 136, - "hitRate": 0.0661764705882353 + "total": 181, + "hitRate": 0.049723756906077346 }, { - "encoding": "macintosh", - "confidence": 17, - "language": "de", - "byteLogLikelihood": -5.003946305945, + "encoding": "windows-1250", + "language": "pl", + "confidence": 13, + "byteLogLikelihood": -4.980958307454, "hits": 8, - "total": 136, - "hitRate": 0.058823529411764705 + "total": 182, + "hitRate": 0.04395604395604396 }, { - "encoding": "ISO-8859-15", - "confidence": 17, - "language": "de", - "byteLogLikelihood": -4.137512330246, + "encoding": "windows-1258", + "language": "vi", + "confidence": 13, + "byteLogLikelihood": -4.506236351586, "hits": 8, - "total": 136, - "hitRate": 0.058823529411764705 + "total": 181, + "hitRate": 0.04419889502762431 }, { - "encoding": "CP850", - "confidence": 17, - "language": "de", - "byteLogLikelihood": -5.003946305945, - "hits": 8, - "total": 136, - "hitRate": 0.058823529411764705 + "encoding": "macintosh", + "language": "es", + "confidence": 11, + "byteLogLikelihood": -4.948759890378, + "hits": 7, + "total": 181, + "hitRate": 0.03867403314917127 }, { - "encoding": "ISO-8859-2", - "confidence": 15, - "language": "cs", - "byteLogLikelihood": -5.159055299215, + "encoding": "ISO-8859-4", + "language": "lv", + "confidence": 11, + "byteLogLikelihood": -4.945351018208, "hits": 7, - "total": 136, - "hitRate": 0.051470588235294115 + "total": 183, + "hitRate": 0.03825136612021858 }, { - "encoding": "windows-1250", - "confidence": 15, - "language": "cs", - "byteLogLikelihood": -5.159055299215, + "encoding": "ISO-8859-15", + "language": "es", + "confidence": 11, + "byteLogLikelihood": -4.948759890378, "hits": 7, - "total": 136, - "hitRate": 0.051470588235294115 + "total": 181, + "hitRate": 0.03867403314917127 }, { - "encoding": "ISO-8859-9", + "encoding": "CP850", + "language": "es", "confidence": 11, - "language": "tr", - "byteLogLikelihood": -4.93784727915, - "hits": 5, - "total": 136, - "hitRate": 0.03676470588235294 + "byteLogLikelihood": -4.948759890378, + "hits": 7, + "total": 177, + "hitRate": 0.03954802259887006 }, { - "encoding": "windows-1254", - "confidence": 11, - "language": "tr", - "byteLogLikelihood": -4.93784727915, - "hits": 5, - "total": 136, - "hitRate": 0.03676470588235294 + "encoding": "ISO-8859-2", + "language": "pl", + "confidence": 9, + "byteLogLikelihood": -3.834078315244, + "hits": 6, + "total": 183, + "hitRate": 0.03278688524590164 + }, + { + "encoding": "windows-1257", + "language": "lv", + "confidence": 9, + "byteLogLikelihood": -5.19295685089, + "hits": 6, + "total": 182, + "hitRate": 0.03296703296703297 }, { "encoding": "ISO-8859-14", - "confidence": 8, "language": "cy", + "confidence": 6, "byteLogLikelihood": -4.912654885736, "hits": 4, - "total": 136, - "hitRate": 0.029411764705882353 - }, + "total": 183, + "hitRate": 0.02185792349726776 + } + ] + }, + { + "expected": { + "encoding": "ISO-8859-4", + "language": "lv" + }, + "predicted": { + "encoding": "ISO-8859-4", + "language": "lv", + "confidence": 40, + "byteLogLikelihood": -3.1328616083, + "hits": 23, + "total": 170, + "hitRate": 0.13529411764705881 + }, + "encodingExact": true, + "encodingEquivalent": false, + "encodingCorrect": true, + "languageCorrect": true, + "tiedAtTop": 1, + "candidates": [ { - "encoding": "ISO-8859-16", - "confidence": 6, - "language": "ro", - "byteLogLikelihood": -5.220355825078, - "hits": 3, - "total": 136, - "hitRate": 0.022058823529411766 + "encoding": "ISO-8859-4", + "language": "lv", + "confidence": 40, + "byteLogLikelihood": -3.1328616083, + "hits": 23, + "total": 170, + "hitRate": 0.13529411764705881 }, { "encoding": "windows-1257", - "confidence": 4, - "language": "lt", - "byteLogLikelihood": -5.123963979403, - "hits": 2, - "total": 136, - "hitRate": 0.014705882352941176 + "language": "lv", + "confidence": 31, + "byteLogLikelihood": -5.111410123766, + "hits": 18, + "total": 169, + "hitRate": 0.10650887573964497 }, { - "encoding": "ISO-8859-3", - "confidence": 4, - "language": "mt", - "byteLogLikelihood": -4.210065739287, - "hits": 2, - "total": 136, - "hitRate": 0.014705882352941176 + "encoding": "ISO-8859-1", + "language": "es", + "confidence": 14, + "byteLogLikelihood": -4.721042183854, + "hits": 8, + "total": 169, + "hitRate": 0.047337278106508875 + }, + { + "encoding": "windows-1252", + "language": "es", + "confidence": 14, + "byteLogLikelihood": -4.721042183854, + "hits": 8, + "total": 169, + "hitRate": 0.047337278106508875 + }, + { + "encoding": "ISO-8859-15", + "language": "es", + "confidence": 14, + "byteLogLikelihood": -4.721042183854, + "hits": 8, + "total": 169, + "hitRate": 0.047337278106508875 }, { "encoding": "ISO-8859-13", - "confidence": 4, "language": "lt", - "byteLogLikelihood": -5.123963979403, - "hits": 2, - "total": 136, - "hitRate": 0.014705882352941176 + "confidence": 10, + "byteLogLikelihood": -4.596975900219, + "hits": 6, + "total": 169, + "hitRate": 0.03550295857988166 }, { - "encoding": "CP852", - "confidence": 4, + "encoding": "ISO-8859-2", "language": "pl", - "byteLogLikelihood": -5.087596335232, - "hits": 2, - "total": 136, - "hitRate": 0.014705882352941176 + "confidence": 8, + "byteLogLikelihood": -4.763992911083, + "hits": 5, + "total": 170, + "hitRate": 0.029411764705882353 }, { - "encoding": "ISO-8859-5", - "confidence": 0, + "encoding": "windows-1250", + "language": "pl", + "confidence": 8, + "byteLogLikelihood": -4.846752537455, + "hits": 5, + "total": 169, + "hitRate": 0.029585798816568046 + }, + { + "encoding": "windows-1251", "language": "ru", - "byteLogLikelihood": -5.652362971667, + "confidence": 0, + "byteLogLikelihood": -4.704365179493, "hits": 0, - "total": 136, + "total": 169, "hitRate": 0 }, { - "encoding": "ISO-8859-6", + "encoding": "windows-874", + "language": "th", "confidence": 0, - "language": "ar", - "byteLogLikelihood": -3.287368473007, + "byteLogLikelihood": -4.578946937177, "hits": 0, - "total": 136, + "total": 170, "hitRate": 0 }, { - "encoding": "ISO-8859-7", + "encoding": "x-mac-cyrillic", + "language": "uk", "confidence": 0, - "language": "el", - "byteLogLikelihood": -3.876181596107, + "byteLogLikelihood": -4.65535318117, "hits": 0, - "total": 136, + "total": 170, "hitRate": 0 }, { - "encoding": "ISO-8859-8", + "encoding": "ISO-8859-16", + "language": "ro", "confidence": 0, - "language": "he", - "byteLogLikelihood": -3.066153183614, + "byteLogLikelihood": -4.616838329205, "hits": 0, - "total": 136, + "total": 169, "hitRate": 0 + } + ] + }, + { + "expected": { + "encoding": "ISO-8859-5", + "language": "ru" + }, + "predicted": { + "encoding": "ISO-8859-5", + "language": "ru", + "confidence": 41, + "byteLogLikelihood": -3.313760777855, + "hits": 25, + "total": 179, + "hitRate": 0.13966480446927373 + }, + "encodingExact": true, + "encodingEquivalent": false, + "encodingCorrect": true, + "languageCorrect": true, + "tiedAtTop": 1, + "candidates": [ + { + "encoding": "ISO-8859-5", + "language": "ru", + "confidence": 41, + "byteLogLikelihood": -3.313760777855, + "hits": 25, + "total": 179, + "hitRate": 0.13966480446927373 }, { - "encoding": "windows-1251", - "confidence": 0, + "encoding": "IBM855", "language": "ru", - "byteLogLikelihood": -3.393743210995, - "hits": 0, - "total": 136, - "hitRate": 0 + "confidence": 9, + "byteLogLikelihood": -4.826799236728, + "hits": 5, + "total": 166, + "hitRate": 0.030120481927710843 }, { - "encoding": "windows-1253", - "confidence": 0, - "language": "el", - "byteLogLikelihood": -3.876181596107, - "hits": 0, - "total": 136, - "hitRate": 0 + "encoding": "KOI8-U", + "language": "uk", + "confidence": 1, + "byteLogLikelihood": -4.816522715875, + "hits": 1, + "total": 179, + "hitRate": 0.00558659217877095 }, { - "encoding": "windows-1255", + "encoding": "ISO-8859-1", + "language": "it", "confidence": 0, - "language": "he", - "byteLogLikelihood": -3.066153183614, + "byteLogLikelihood": -4.841944488282, "hits": 0, - "total": 136, + "total": 176, "hitRate": 0 }, { - "encoding": "windows-1256", + "encoding": "ISO-8859-2", + "language": "hu", "confidence": 0, - "language": "ar", - "byteLogLikelihood": -4.25594643617, + "byteLogLikelihood": -4.941337938888, "hits": 0, - "total": 136, + "total": 177, "hitRate": 0 }, { - "encoding": "windows-874", + "encoding": "windows-1252", + "language": "it", "confidence": 0, - "language": "th", - "byteLogLikelihood": -5.801526726218, + "byteLogLikelihood": -4.841944488282, "hits": 0, - "total": 136, + "total": 176, "hitRate": 0 }, { - "encoding": "KOI8-R", + "encoding": "windows-1257", + "language": "lt", "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.432153549797, + "byteLogLikelihood": -4.847671496604, "hits": 0, - "total": 136, + "total": 176, "hitRate": 0 }, { - "encoding": "KOI8-U", + "encoding": "windows-1258", + "language": "vi", "confidence": 0, - "language": "uk", - "byteLogLikelihood": -6.390348855877, + "byteLogLikelihood": -4.755485363394, "hits": 0, - "total": 136, + "total": 166, "hitRate": 0 }, { - "encoding": "IBM866", + "encoding": "windows-874", + "language": "th", "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.652362971667, + "byteLogLikelihood": -4.810914106722, "hits": 0, - "total": 136, + "total": 84, "hitRate": 0 }, { - "encoding": "IBM855", + "encoding": "ISO-8859-13", + "language": "lt", "confidence": 0, - "language": "ru", - "byteLogLikelihood": -4.419477704429, + "byteLogLikelihood": -4.847671496604, "hits": 0, - "total": 136, + "total": 176, "hitRate": 0 }, { - "encoding": "x-mac-cyrillic", + "encoding": "ISO-8859-14", + "language": "cy", "confidence": 0, - "language": "ru", - "byteLogLikelihood": -3.393743210995, + "byteLogLikelihood": -4.83002806951, "hits": 0, - "total": 136, + "total": 178, "hitRate": 0 }, { - "encoding": "ISO-8859-4", + "encoding": "ISO-8859-15", + "language": "es", "confidence": 0, - "language": "lv", - "byteLogLikelihood": -5.19295685089, + "byteLogLikelihood": -4.848242748706, "hits": 0, - "total": 136, + "total": 177, "hitRate": 0 } ] }, { "expected": { - "encoding": "ISO-8859-10", - "language": "is" + "encoding": "ISO-8859-6", + "language": "ar" }, "predicted": { - "encoding": "ISO-8859-10", - "confidence": 38, - "language": "is", - "byteLogLikelihood": -3.025836278694, - "hits": 22, - "total": 171, - "hitRate": 0.1286549707602339 - }, - "encodingExact": true, - "encodingEquivalent": false, - "encodingCorrect": true, - "languageCorrect": true, + "encoding": "ISO-8859-6", + "language": "ar", + "confidence": 62, + "byteLogLikelihood": -3.306009422775, + "hits": 23, + "total": 110, + "hitRate": 0.20909090909090908 + }, + "encodingExact": true, + "encodingEquivalent": false, + "encodingCorrect": true, + "languageCorrect": true, "tiedAtTop": 1, "candidates": [ - { - "encoding": "ISO-8859-10", - "confidence": 38, - "language": "is", - "byteLogLikelihood": -3.025836278694, - "hits": 22, - "total": 171, - "hitRate": 0.1286549707602339 - }, - { - "encoding": "ISO-8859-1", - "confidence": 14, - "language": "sv", - "byteLogLikelihood": -4.633646206449, - "hits": 8, - "total": 171, - "hitRate": 0.04678362573099415 - }, - { - "encoding": "windows-1252", - "confidence": 14, - "language": "sv", - "byteLogLikelihood": -4.633646206449, - "hits": 8, - "total": 171, - "hitRate": 0.04678362573099415 - }, - { - "encoding": "ISO-8859-3", - "confidence": 12, - "language": "mt", - "byteLogLikelihood": -5.105945473901, - "hits": 7, - "total": 169, - "hitRate": 0.04142011834319527 - }, - { - "encoding": "windows-1257", - "confidence": 7, - "language": "lt", - "byteLogLikelihood": -3.989583472462, - "hits": 4, - "total": 171, - "hitRate": 0.023391812865497075 - }, - { - "encoding": "windows-1258", - "confidence": 7, - "language": "vi", - "byteLogLikelihood": -4.642697796053, - "hits": 4, - "total": 171, - "hitRate": 0.023391812865497075 - }, - { - "encoding": "ISO-8859-13", - "confidence": 7, - "language": "lt", - "byteLogLikelihood": -3.989583472462, - "hits": 4, - "total": 171, - "hitRate": 0.023391812865497075 - }, - { - "encoding": "macintosh", - "confidence": 5, - "language": "de", - "byteLogLikelihood": -5.003946305945, - "hits": 3, - "total": 169, - "hitRate": 0.01775147928994083 - }, - { - "encoding": "ISO-8859-4", - "confidence": 5, - "language": "lv", - "byteLogLikelihood": -5.19295685089, - "hits": 3, - "total": 171, - "hitRate": 0.017543859649122806 - }, - { - "encoding": "ISO-8859-15", - "confidence": 5, - "language": "de", - "byteLogLikelihood": -4.894502014278, - "hits": 3, - "total": 171, - "hitRate": 0.017543859649122806 - }, - { - "encoding": "CP850", - "confidence": 5, - "language": "de", - "byteLogLikelihood": -5.003946305945, - "hits": 3, - "total": 169, - "hitRate": 0.01775147928994083 - }, - { - "encoding": "CP852", - "confidence": 5, - "language": "pl", - "byteLogLikelihood": -5.087596335232, - "hits": 3, - "total": 169, - "hitRate": 0.01775147928994083 - }, - { - "encoding": "ISO-8859-2", - "confidence": 3, - "language": "cs", - "byteLogLikelihood": -4.497848163857, - "hits": 2, - "total": 171, - "hitRate": 0.011695906432748537 - }, - { - "encoding": "windows-1250", - "confidence": 3, - "language": "cs", - "byteLogLikelihood": -4.497848163857, - "hits": 2, - "total": 171, - "hitRate": 0.011695906432748537 - }, - { - "encoding": "ISO-8859-9", - "confidence": 1, - "language": "tr", - "byteLogLikelihood": -4.646338703133, - "hits": 1, - "total": 171, - "hitRate": 0.005847953216374269 - }, - { - "encoding": "windows-1254", - "confidence": 1, - "language": "tr", - "byteLogLikelihood": -4.646338703133, - "hits": 1, - "total": 171, - "hitRate": 0.005847953216374269 - }, - { - "encoding": "ISO-8859-5", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.838861551509, - "hits": 0, - "total": 169, - "hitRate": 0 - }, { "encoding": "ISO-8859-6", - "confidence": 0, "language": "ar", - "byteLogLikelihood": -5.345124108708, - "hits": 0, - "total": 167, - "hitRate": 0 + "confidence": 62, + "byteLogLikelihood": -3.306009422775, + "hits": 23, + "total": 110, + "hitRate": 0.20909090909090908 }, { - "encoding": "ISO-8859-7", - "confidence": 0, - "language": "el", - "byteLogLikelihood": -3.963723644165, - "hits": 0, - "total": 171, - "hitRate": 0 + "encoding": "windows-1256", + "language": "ar", + "confidence": 10, + "byteLogLikelihood": -3.968382111451, + "hits": 4, + "total": 110, + "hitRate": 0.03636363636363636 }, { - "encoding": "ISO-8859-8", + "encoding": "ISO-8859-1", + "language": "sv", "confidence": 0, - "language": "he", - "byteLogLikelihood": -4.249634019938, + "byteLogLikelihood": -4.69584393439, "hits": 0, - "total": 171, + "total": 110, "hitRate": 0 }, { - "encoding": "windows-1251", + "encoding": "ISO-8859-9", + "language": "tr", "confidence": 0, - "language": "ru", - "byteLogLikelihood": -3.84046735452, + "byteLogLikelihood": -4.933475282212, "hits": 0, - "total": 171, + "total": 110, "hitRate": 0 }, { - "encoding": "windows-1253", + "encoding": "windows-1252", + "language": "sv", "confidence": 0, - "language": "el", - "byteLogLikelihood": -3.963723644165, + "byteLogLikelihood": -4.69584393439, "hits": 0, - "total": 171, + "total": 110, "hitRate": 0 }, { - "encoding": "windows-1255", + "encoding": "windows-1254", + "language": "tr", "confidence": 0, - "language": "he", - "byteLogLikelihood": -4.249634019938, + "byteLogLikelihood": -4.933475282212, "hits": 0, - "total": 171, + "total": 110, "hitRate": 0 }, { - "encoding": "windows-1256", + "encoding": "windows-1257", + "language": "et", "confidence": 0, - "language": "ar", - "byteLogLikelihood": -4.696464660765, + "byteLogLikelihood": -4.72024182268, "hits": 0, - "total": 169, + "total": 110, "hitRate": 0 }, { "encoding": "windows-874", - "confidence": 0, "language": "th", - "byteLogLikelihood": -5.644763656357, - "hits": 0, - "total": 167, - "hitRate": 0 - }, - { - "encoding": "KOI8-R", "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.290788006393, + "byteLogLikelihood": -4.643135408712, "hits": 0, - "total": 171, + "total": 92, "hitRate": 0 }, { - "encoding": "KOI8-U", + "encoding": "macintosh", + "language": "es", "confidence": 0, - "language": "uk", - "byteLogLikelihood": -6.026638569428, + "byteLogLikelihood": -4.948759890378, "hits": 0, - "total": 171, + "total": 55, "hitRate": 0 }, { - "encoding": "IBM866", + "encoding": "ISO-8859-14", + "language": "cy", "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.838861551509, + "byteLogLikelihood": -4.799641758471, "hits": 0, - "total": 171, + "total": 111, "hitRate": 0 }, { - "encoding": "IBM855", + "encoding": "ISO-8859-15", + "language": "de", "confidence": 0, - "language": "sr", - "byteLogLikelihood": -5.795369889152, + "byteLogLikelihood": -4.755317425962, "hits": 0, - "total": 169, + "total": 110, "hitRate": 0 }, { - "encoding": "x-mac-cyrillic", + "encoding": "CP850", + "language": "es", "confidence": 0, - "language": "uk", - "byteLogLikelihood": -3.733983711968, + "byteLogLikelihood": -4.948759890378, "hits": 0, - "total": 171, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-14", - "confidence": 0, - "language": "cy", - "byteLogLikelihood": -4.657284871846, - "hits": 0, - "total": 171, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-16", - "confidence": 0, - "language": "ro", - "byteLogLikelihood": -5.220355825078, - "hits": 0, - "total": 171, + "total": 98, "hitRate": 0 } ] }, { "expected": { - "encoding": "ISO-8859-13", - "language": "lt" + "encoding": "ISO-8859-7", + "language": "el" }, "predicted": { - "encoding": "windows-1257", - "confidence": 34, - "language": "lt", - "byteLogLikelihood": -3.200530207132, - "hits": 20, - "total": 173, - "hitRate": 0.11560693641618497 + "encoding": "ISO-8859-7", + "language": "el", + "confidence": 51, + "byteLogLikelihood": -3.435199502, + "hits": 23, + "total": 134, + "hitRate": 0.17164179104477612 }, - "encodingExact": false, - "encodingEquivalent": true, + "encodingExact": true, + "encodingEquivalent": false, "encodingCorrect": true, "languageCorrect": true, "tiedAtTop": 2, "candidates": [ { - "encoding": "windows-1257", - "confidence": 34, - "language": "lt", - "byteLogLikelihood": -3.200530207132, - "hits": 20, - "total": 173, - "hitRate": 0.11560693641618497 - }, - { - "encoding": "ISO-8859-13", - "confidence": 34, - "language": "lt", - "byteLogLikelihood": -3.200530207132, - "hits": 20, - "total": 173, - "hitRate": 0.11560693641618497 - }, - { - "encoding": "ISO-8859-4", - "confidence": 22, - "language": "lv", - "byteLogLikelihood": -4.610398759565, - "hits": 13, - "total": 173, - "hitRate": 0.07514450867052024 - }, - { - "encoding": "ISO-8859-2", - "confidence": 15, - "language": "hu", - "byteLogLikelihood": -5.117993812417, - "hits": 9, - "total": 173, - "hitRate": 0.05202312138728324 - }, - { - "encoding": "windows-1250", - "confidence": 15, - "language": "hu", - "byteLogLikelihood": -5.117993812417, - "hits": 9, - "total": 173, - "hitRate": 0.05202312138728324 - }, - { - "encoding": "ISO-8859-1", - "confidence": 12, - "language": "es", - "byteLogLikelihood": -4.948759890378, - "hits": 7, - "total": 173, - "hitRate": 0.04046242774566474 - }, - { - "encoding": "windows-1252", - "confidence": 12, - "language": "es", - "byteLogLikelihood": -4.948759890378, - "hits": 7, - "total": 173, - "hitRate": 0.04046242774566474 - }, - { - "encoding": "macintosh", - "confidence": 12, - "language": "es", - "byteLogLikelihood": -4.948759890378, - "hits": 7, - "total": 168, - "hitRate": 0.041666666666666664 - }, - { - "encoding": "ISO-8859-15", - "confidence": 12, - "language": "es", - "byteLogLikelihood": -4.948759890378, - "hits": 7, - "total": 173, - "hitRate": 0.04046242774566474 - }, - { - "encoding": "CP850", - "confidence": 12, - "language": "es", - "byteLogLikelihood": -4.948759890378, - "hits": 7, - "total": 170, - "hitRate": 0.041176470588235294 - }, - { - "encoding": "ISO-8859-9", - "confidence": 8, - "language": "tr", - "byteLogLikelihood": -4.789760270297, - "hits": 5, - "total": 173, - "hitRate": 0.028901734104046242 - }, - { - "encoding": "windows-1254", - "confidence": 8, - "language": "tr", - "byteLogLikelihood": -4.789760270297, - "hits": 5, - "total": 173, - "hitRate": 0.028901734104046242 - }, - { - "encoding": "CP852", - "confidence": 7, - "language": "pl", - "byteLogLikelihood": -5.087596335232, - "hits": 4, - "total": 170, - "hitRate": 0.023529411764705882 - }, - { - "encoding": "ISO-8859-3", - "confidence": 5, - "language": "mt", - "byteLogLikelihood": -5.105945473901, - "hits": 3, - "total": 172, - "hitRate": 0.01744186046511628 + "encoding": "ISO-8859-7", + "language": "el", + "confidence": 51, + "byteLogLikelihood": -3.435199502, + "hits": 23, + "total": 134, + "hitRate": 0.17164179104477612 }, { - "encoding": "ISO-8859-14", - "confidence": 3, - "language": "cy", - "byteLogLikelihood": -4.6272413408, - "hits": 2, - "total": 173, - "hitRate": 0.011560693641618497 + "encoding": "windows-1253", + "language": "el", + "confidence": 51, + "byteLogLikelihood": -3.435199502, + "hits": 23, + "total": 134, + "hitRate": 0.17164179104477612 }, { - "encoding": "windows-1258", - "confidence": 1, - "language": "vi", - "byteLogLikelihood": -4.960186085121, + "encoding": "ISO-8859-8", + "language": "he", + "confidence": 2, + "byteLogLikelihood": -4.09495359507, "hits": 1, - "total": 171, - "hitRate": 0.005847953216374269 + "total": 127, + "hitRate": 0.007874015748031496 }, { - "encoding": "IBM855", - "confidence": 1, - "language": "ru", - "byteLogLikelihood": -5.488073838002, + "encoding": "windows-1255", + "language": "he", + "confidence": 2, + "byteLogLikelihood": -4.09495359507, "hits": 1, - "total": 170, - "hitRate": 0.0058823529411764705 + "total": 127, + "hitRate": 0.007874015748031496 }, { - "encoding": "ISO-8859-10", - "confidence": 1, - "language": "is", - "byteLogLikelihood": -4.416382325607, + "encoding": "x-mac-cyrillic", + "language": "uk", + "confidence": 2, + "byteLogLikelihood": -4.203232324163, "hits": 1, - "total": 173, - "hitRate": 0.005780346820809248 + "total": 131, + "hitRate": 0.007633587786259542 }, { - "encoding": "ISO-8859-5", + "encoding": "ISO-8859-1", + "language": "pt", "confidence": 0, - "language": "ru", - "byteLogLikelihood": -4.893109334109, + "byteLogLikelihood": -4.59932343766, "hits": 0, - "total": 172, + "total": 134, "hitRate": 0 }, { - "encoding": "ISO-8859-6", + "encoding": "ISO-8859-2", + "language": "hu", "confidence": 0, - "language": "ar", - "byteLogLikelihood": -5.773457169107, + "byteLogLikelihood": -4.358825259583, "hits": 0, - "total": 167, + "total": 134, "hitRate": 0 }, { - "encoding": "ISO-8859-7", + "encoding": "windows-1250", + "language": "hu", "confidence": 0, - "language": "el", - "byteLogLikelihood": -4.472500251122, + "byteLogLikelihood": -4.358825259583, "hits": 0, - "total": 173, + "total": 134, "hitRate": 0 }, { - "encoding": "ISO-8859-8", + "encoding": "windows-1251", + "language": "ru", "confidence": 0, - "language": "he", - "byteLogLikelihood": -4.444220754634, + "byteLogLikelihood": -4.288697198304, "hits": 0, - "total": 171, + "total": 134, "hitRate": 0 }, { - "encoding": "windows-1251", + "encoding": "windows-1252", + "language": "pt", "confidence": 0, - "language": "ru", - "byteLogLikelihood": -3.531827362419, + "byteLogLikelihood": -4.59932343766, "hits": 0, - "total": 173, + "total": 134, "hitRate": 0 }, { - "encoding": "windows-1253", + "encoding": "ISO-8859-10", + "language": "is", "confidence": 0, - "language": "el", - "byteLogLikelihood": -4.472500251122, + "byteLogLikelihood": -4.576407109739, "hits": 0, - "total": 173, + "total": 134, "hitRate": 0 }, { - "encoding": "windows-1255", + "encoding": "ISO-8859-15", + "language": "es", "confidence": 0, - "language": "he", - "byteLogLikelihood": -4.444220754634, + "byteLogLikelihood": -4.603974037796, "hits": 0, - "total": 171, + "total": 134, "hitRate": 0 - }, - { - "encoding": "windows-1256", + } + ] + }, + { + "expected": { + "encoding": "ISO-8859-8", + "language": "he" + }, + "predicted": { + "encoding": "ISO-8859-8", + "language": "he", + "confidence": 47, + "byteLogLikelihood": -3.320333973076, + "hits": 16, + "total": 102, + "hitRate": 0.1568627450980392 + }, + "encodingExact": true, + "encodingEquivalent": false, + "encodingCorrect": true, + "languageCorrect": true, + "tiedAtTop": 2, + "candidates": [ + { + "encoding": "ISO-8859-8", + "language": "he", + "confidence": 47, + "byteLogLikelihood": -3.320333973076, + "hits": 16, + "total": 102, + "hitRate": 0.1568627450980392 + }, + { + "encoding": "windows-1255", + "language": "he", + "confidence": 47, + "byteLogLikelihood": -3.320333973076, + "hits": 16, + "total": 102, + "hitRate": 0.1568627450980392 + }, + { + "encoding": "ISO-8859-7", + "language": "el", + "confidence": 2, + "byteLogLikelihood": -3.981926233577, + "hits": 1, + "total": 102, + "hitRate": 0.00980392156862745 + }, + { + "encoding": "windows-1253", + "language": "el", + "confidence": 2, + "byteLogLikelihood": -3.981926233577, + "hits": 1, + "total": 102, + "hitRate": 0.00980392156862745 + }, + { + "encoding": "ISO-8859-1", + "language": "sv", "confidence": 0, - "language": "ar", - "byteLogLikelihood": -5.924336543075, + "byteLogLikelihood": -4.395116706452, "hits": 0, - "total": 170, + "total": 102, "hitRate": 0 }, { - "encoding": "windows-874", + "encoding": "ISO-8859-2", + "language": "cs", "confidence": 0, - "language": "th", - "byteLogLikelihood": -5.58967630288, + "byteLogLikelihood": -4.461975046319, "hits": 0, - "total": 166, + "total": 102, "hitRate": 0 }, { - "encoding": "KOI8-R", + "encoding": "windows-1250", + "language": "cs", "confidence": 0, + "byteLogLikelihood": -4.461975046319, + "hits": 0, + "total": 102, + "hitRate": 0 + }, + { + "encoding": "windows-1251", "language": "ru", - "byteLogLikelihood": -6.365896834008, + "confidence": 0, + "byteLogLikelihood": -4.199203901043, "hits": 0, - "total": 173, + "total": 102, "hitRate": 0 }, { - "encoding": "KOI8-U", + "encoding": "windows-1252", + "language": "sv", "confidence": 0, - "language": "uk", - "byteLogLikelihood": -6.252539473952, + "byteLogLikelihood": -4.395116706452, "hits": 0, - "total": 173, + "total": 102, "hitRate": 0 }, { - "encoding": "IBM866", + "encoding": "windows-1257", + "language": "et", "confidence": 0, - "language": "ru", - "byteLogLikelihood": -4.893109334109, + "byteLogLikelihood": -4.639272141503, "hits": 0, - "total": 171, + "total": 102, "hitRate": 0 }, { "encoding": "x-mac-cyrillic", - "confidence": 0, "language": "uk", - "byteLogLikelihood": -3.441328843196, + "confidence": 0, + "byteLogLikelihood": -4.134202940863, "hits": 0, - "total": 173, + "total": 102, "hitRate": 0 }, { - "encoding": "ISO-8859-16", + "encoding": "ISO-8859-15", + "language": "fr", "confidence": 0, - "language": "ro", - "byteLogLikelihood": -4.616838329205, + "byteLogLikelihood": -4.521941300627, "hits": 0, - "total": 173, + "total": 102, "hitRate": 0 } ] }, { "expected": { - "encoding": "ISO-8859-14", - "language": "cy" + "encoding": "ISO-8859-9", + "language": "tr" }, "predicted": { - "encoding": "ISO-8859-14", - "confidence": 50, - "language": "cy", - "byteLogLikelihood": -3.988458644989, - "hits": 32, - "total": 189, - "hitRate": 0.1693121693121693 + "encoding": "ISO-8859-9", + "language": "tr", + "confidence": 55, + "byteLogLikelihood": -3.531675216773, + "hits": 25, + "total": 134, + "hitRate": 0.1865671641791045 }, "encodingExact": true, "encodingEquivalent": false, "encodingCorrect": true, "languageCorrect": true, - "tiedAtTop": 1, + "tiedAtTop": 2, "candidates": [ { - "encoding": "ISO-8859-14", - "confidence": 50, - "language": "cy", - "byteLogLikelihood": -3.988458644989, - "hits": 32, - "total": 189, - "hitRate": 0.1693121693121693 + "encoding": "ISO-8859-9", + "language": "tr", + "confidence": 55, + "byteLogLikelihood": -3.531675216773, + "hits": 25, + "total": 134, + "hitRate": 0.1865671641791045 + }, + { + "encoding": "windows-1254", + "language": "tr", + "confidence": 55, + "byteLogLikelihood": -3.531675216773, + "hits": 25, + "total": 134, + "hitRate": 0.1865671641791045 }, { "encoding": "ISO-8859-1", - "confidence": 14, - "language": "pt", - "byteLogLikelihood": -4.955827057601, - "hits": 9, - "total": 189, - "hitRate": 0.047619047619047616 + "language": "da", + "confidence": 17, + "byteLogLikelihood": -4.969813299576, + "hits": 8, + "total": 134, + "hitRate": 0.05970149253731343 }, { "encoding": "windows-1252", - "confidence": 14, - "language": "pt", - "byteLogLikelihood": -4.955827057601, - "hits": 9, - "total": 189, - "hitRate": 0.047619047619047616 + "language": "da", + "confidence": 17, + "byteLogLikelihood": -4.969813299576, + "hits": 8, + "total": 134, + "hitRate": 0.05970149253731343 }, { - "encoding": "windows-1258", - "confidence": 14, - "language": "vi", - "byteLogLikelihood": -4.34192292436, - "hits": 9, - "total": 188, - "hitRate": 0.047872340425531915 + "encoding": "ISO-8859-2", + "language": "ro", + "confidence": 13, + "byteLogLikelihood": -4.352190516073, + "hits": 6, + "total": 134, + "hitRate": 0.04477611940298507 }, { - "encoding": "macintosh", - "confidence": 11, - "language": "es", - "byteLogLikelihood": -4.948759890378, - "hits": 7, - "total": 188, - "hitRate": 0.03723404255319149 + "encoding": "windows-1250", + "language": "ro", + "confidence": 13, + "byteLogLikelihood": -4.352190516073, + "hits": 6, + "total": 134, + "hitRate": 0.04477611940298507 }, { - "encoding": "ISO-8859-15", + "encoding": "windows-1257", + "language": "lv", "confidence": 11, - "language": "es", - "byteLogLikelihood": -4.948759890378, - "hits": 7, - "total": 189, - "hitRate": 0.037037037037037035 + "byteLogLikelihood": -3.613497993373, + "hits": 5, + "total": 134, + "hitRate": 0.03731343283582089 }, { - "encoding": "CP850", + "encoding": "ISO-8859-13", + "language": "lt", "confidence": 11, - "language": "es", - "byteLogLikelihood": -4.948759890378, - "hits": 7, - "total": 188, - "hitRate": 0.03723404255319149 + "byteLogLikelihood": -4.394247673508, + "hits": 5, + "total": 134, + "hitRate": 0.03731343283582089 }, { - "encoding": "ISO-8859-2", - "confidence": 9, - "language": "cs", - "byteLogLikelihood": -5.159055299215, - "hits": 6, - "total": 189, - "hitRate": 0.031746031746031744 + "encoding": "ISO-8859-16", + "language": "ro", + "confidence": 11, + "byteLogLikelihood": -4.25849981603, + "hits": 5, + "total": 134, + "hitRate": 0.03731343283582089 }, { - "encoding": "windows-1250", - "confidence": 9, - "language": "cs", - "byteLogLikelihood": -5.159055299215, - "hits": 6, - "total": 189, - "hitRate": 0.031746031746031744 + "encoding": "ISO-8859-7", + "language": "el", + "confidence": 0, + "byteLogLikelihood": -4.216966174066, + "hits": 0, + "total": 134, + "hitRate": 0 }, { - "encoding": "windows-1257", - "confidence": 6, - "language": "et", - "byteLogLikelihood": -4.934473933131, - "hits": 4, - "total": 189, - "hitRate": 0.021164021164021163 - }, - { - "encoding": "ISO-8859-3", - "confidence": 4, - "language": "mt", - "byteLogLikelihood": -5.105945473901, - "hits": 3, - "total": 189, - "hitRate": 0.015873015873015872 - }, - { - "encoding": "ISO-8859-10", - "confidence": 4, - "language": "is", - "byteLogLikelihood": -4.009500374258, - "hits": 3, - "total": 189, - "hitRate": 0.015873015873015872 - }, - { - "encoding": "ISO-8859-9", - "confidence": 3, - "language": "tr", - "byteLogLikelihood": -4.613075694861, - "hits": 2, - "total": 189, - "hitRate": 0.010582010582010581 - }, - { - "encoding": "windows-1254", - "confidence": 3, - "language": "tr", - "byteLogLikelihood": -4.613075694861, - "hits": 2, - "total": 189, - "hitRate": 0.010582010582010581 - }, - { - "encoding": "CP852", - "confidence": 3, - "language": "pl", - "byteLogLikelihood": -5.087596335232, - "hits": 2, - "total": 188, - "hitRate": 0.010638297872340425 - }, - { - "encoding": "ISO-8859-4", - "confidence": 1, - "language": "lv", - "byteLogLikelihood": -4.961907790704, - "hits": 1, - "total": 189, - "hitRate": 0.005291005291005291 - }, - { - "encoding": "ISO-8859-13", - "confidence": 1, - "language": "lt", - "byteLogLikelihood": -3.647025046455, - "hits": 1, - "total": 189, - "hitRate": 0.005291005291005291 - }, - { - "encoding": "ISO-8859-5", + "encoding": "windows-1253", + "language": "el", "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.350299845595, + "byteLogLikelihood": -4.216966174066, "hits": 0, - "total": 189, + "total": 134, "hitRate": 0 }, { - "encoding": "ISO-8859-6", + "encoding": "x-mac-cyrillic", + "language": "uk", "confidence": 0, - "language": "ar", - "byteLogLikelihood": -5.420534999272, + "byteLogLikelihood": -4.22610845571, "hits": 0, - "total": 188, + "total": 134, "hitRate": 0 + } + ] + }, + { + "expected": { + "encoding": "KOI8-R", + "language": "ru" + }, + "predicted": { + "encoding": "KOI8-R", + "language": "ru", + "confidence": 43, + "byteLogLikelihood": -3.313760777855, + "hits": 26, + "total": 179, + "hitRate": 0.1452513966480447 + }, + "encodingExact": true, + "encodingEquivalent": false, + "encodingCorrect": true, + "languageCorrect": true, + "tiedAtTop": 1, + "candidates": [ + { + "encoding": "KOI8-R", + "language": "ru", + "confidence": 43, + "byteLogLikelihood": -3.313760777855, + "hits": 26, + "total": 179, + "hitRate": 0.1452513966480447 }, { - "encoding": "ISO-8859-7", - "confidence": 0, - "language": "el", - "byteLogLikelihood": -4.254156765951, - "hits": 0, - "total": 189, - "hitRate": 0 + "encoding": "KOI8-U", + "language": "uk", + "confidence": 28, + "byteLogLikelihood": -3.443215105753, + "hits": 17, + "total": 179, + "hitRate": 0.09497206703910614 }, { - "encoding": "ISO-8859-8", - "confidence": 0, - "language": "he", - "byteLogLikelihood": -4.917404374874, - "hits": 0, - "total": 188, - "hitRate": 0 + "encoding": "windows-874", + "language": "th", + "confidence": 12, + "byteLogLikelihood": -4.705552828452, + "hits": 7, + "total": 162, + "hitRate": 0.043209876543209874 }, { - "encoding": "windows-1251", + "encoding": "ISO-8859-1", + "language": "nl", "confidence": 0, - "language": "ru", - "byteLogLikelihood": -3.467895804539, + "byteLogLikelihood": -4.900684399759, "hits": 0, - "total": 189, + "total": 176, "hitRate": 0 }, { - "encoding": "windows-1253", + "encoding": "ISO-8859-6", + "language": "ar", "confidence": 0, - "language": "el", - "byteLogLikelihood": -4.254156765951, + "byteLogLikelihood": -4.759099059367, "hits": 0, - "total": 189, + "total": 176, "hitRate": 0 }, { - "encoding": "windows-1255", + "encoding": "windows-1252", + "language": "nl", "confidence": 0, - "language": "he", - "byteLogLikelihood": -4.917404374874, + "byteLogLikelihood": -4.900684399759, "hits": 0, - "total": 188, + "total": 176, "hitRate": 0 }, { "encoding": "windows-1256", - "confidence": 0, "language": "ar", - "byteLogLikelihood": -6.113682179832, - "hits": 0, - "total": 188, - "hitRate": 0 - }, - { - "encoding": "windows-874", - "confidence": 0, - "language": "th", - "byteLogLikelihood": -5.830407858741, - "hits": 0, - "total": 188, - "hitRate": 0 - }, - { - "encoding": "KOI8-R", "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.229985622133, + "byteLogLikelihood": -4.796335743252, "hits": 0, - "total": 189, + "total": 175, "hitRate": 0 }, { - "encoding": "KOI8-U", + "encoding": "windows-1257", + "language": "et", "confidence": 0, - "language": "uk", - "byteLogLikelihood": -5.821976831991, + "byteLogLikelihood": -4.91533239831, "hits": 0, - "total": 189, + "total": 176, "hitRate": 0 }, { - "encoding": "IBM866", + "encoding": "macintosh", + "language": "es", "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.350299845595, + "byteLogLikelihood": -4.948759890378, "hits": 0, - "total": 188, + "total": 94, "hitRate": 0 }, { - "encoding": "IBM855", + "encoding": "ISO-8859-14", + "language": "cy", "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.325879646284, + "byteLogLikelihood": -4.912654885736, "hits": 0, - "total": 188, + "total": 179, "hitRate": 0 }, { - "encoding": "x-mac-cyrillic", + "encoding": "ISO-8859-15", + "language": "de", "confidence": 0, - "language": "uk", - "byteLogLikelihood": -3.255815902698, + "byteLogLikelihood": -4.935090625757, "hits": 0, - "total": 189, + "total": 176, "hitRate": 0 }, { - "encoding": "ISO-8859-16", + "encoding": "CP850", + "language": "es", "confidence": 0, - "language": "ro", - "byteLogLikelihood": -3.903274585551, + "byteLogLikelihood": -4.948759890378, "hits": 0, - "total": 189, + "total": 92, "hitRate": 0 } ] }, { "expected": { - "encoding": "ISO-8859-15", - "language": "de" + "encoding": "KOI8-U", + "language": "uk" }, "predicted": { - "encoding": "ISO-8859-1", - "confidence": 73, - "language": "de", - "byteLogLikelihood": -3.169712077519, - "hits": 53, - "total": 216, - "hitRate": 0.24537037037037038 + "encoding": "KOI8-U", + "language": "uk", + "confidence": 32, + "byteLogLikelihood": -3.34369756932, + "hits": 19, + "total": 177, + "hitRate": 0.10734463276836158 }, - "encodingExact": false, - "encodingEquivalent": true, + "encodingExact": true, + "encodingEquivalent": false, "encodingCorrect": true, "languageCorrect": true, - "tiedAtTop": 3, + "tiedAtTop": 1, "candidates": [ { - "encoding": "ISO-8859-1", - "confidence": 73, - "language": "de", - "byteLogLikelihood": -3.169712077519, - "hits": 53, - "total": 216, - "hitRate": 0.24537037037037038 + "encoding": "KOI8-U", + "language": "uk", + "confidence": 32, + "byteLogLikelihood": -3.34369756932, + "hits": 19, + "total": 177, + "hitRate": 0.10734463276836158 }, { - "encoding": "windows-1252", - "confidence": 73, - "language": "de", - "byteLogLikelihood": -3.169712077519, - "hits": 53, - "total": 216, - "hitRate": 0.24537037037037038 + "encoding": "KOI8-R", + "language": "ru", + "confidence": 17, + "byteLogLikelihood": -3.510012695801, + "hits": 10, + "total": 172, + "hitRate": 0.05813953488372093 + }, + { + "encoding": "windows-874", + "language": "th", + "confidence": 11, + "byteLogLikelihood": -4.843281209678, + "hits": 6, + "total": 163, + "hitRate": 0.03680981595092025 + }, + { + "encoding": "ISO-8859-1", + "language": "en", + "confidence": 1, + "byteLogLikelihood": -4.915420747009, + "hits": 1, + "total": 168, + "hitRate": 0.005952380952380952 + }, + { + "encoding": "ISO-8859-6", + "language": "ar", + "confidence": 1, + "byteLogLikelihood": -4.726706027838, + "hits": 1, + "total": 170, + "hitRate": 0.0058823529411764705 + }, + { + "encoding": "windows-1252", + "language": "en", + "confidence": 1, + "byteLogLikelihood": -4.915420747009, + "hits": 1, + "total": 168, + "hitRate": 0.005952380952380952 + }, + { + "encoding": "windows-1256", + "language": "ar", + "confidence": 1, + "byteLogLikelihood": -4.693044688745, + "hits": 1, + "total": 168, + "hitRate": 0.005952380952380952 + }, + { + "encoding": "windows-1257", + "language": "et", + "confidence": 0, + "byteLogLikelihood": -4.922686041886, + "hits": 0, + "total": 168, + "hitRate": 0 + }, + { + "encoding": "macintosh", + "language": "es", + "confidence": 0, + "byteLogLikelihood": -4.948759890378, + "hits": 0, + "total": 89, + "hitRate": 0 + }, + { + "encoding": "ISO-8859-14", + "language": "cy", + "confidence": 0, + "byteLogLikelihood": -4.912654885736, + "hits": 0, + "total": 177, + "hitRate": 0 }, { "encoding": "ISO-8859-15", - "confidence": 73, + "language": "es", + "confidence": 0, + "byteLogLikelihood": -4.944199711559, + "hits": 0, + "total": 176, + "hitRate": 0 + }, + { + "encoding": "CP850", + "language": "es", + "confidence": 0, + "byteLogLikelihood": -4.948759890378, + "hits": 0, + "total": 92, + "hitRate": 0 + } + ] + }, + { + "expected": { + "encoding": "macintosh", + "language": "de" + }, + "predicted": { + "encoding": "macintosh", + "language": "de", + "confidence": 73, + "byteLogLikelihood": -3.169712077519, + "hits": 53, + "total": 216, + "hitRate": 0.24537037037037038 + }, + "encodingExact": true, + "encodingEquivalent": false, + "encodingCorrect": true, + "languageCorrect": true, + "tiedAtTop": 1, + "candidates": [ + { + "encoding": "macintosh", "language": "de", + "confidence": 73, "byteLogLikelihood": -3.169712077519, "hits": 53, "total": 216, "hitRate": 0.24537037037037038 }, { - "encoding": "macintosh", - "confidence": 72, + "encoding": "windows-1252", + "language": "de", + "confidence": 70, + "byteLogLikelihood": -5.003946305945, + "hits": 51, + "total": 216, + "hitRate": 0.2361111111111111 + }, + { + "encoding": "ISO-8859-15", "language": "de", + "confidence": 74, "byteLogLikelihood": -5.003946305945, - "hits": 52, - "total": 215, - "hitRate": 0.24186046511627907 + "hits": 53, + "total": 214, + "hitRate": 0.24766355140186916 + }, + { + "encoding": "ISO-8859-1", + "language": "de", + "confidence": 74, + "byteLogLikelihood": -5.003946305945, + "hits": 53, + "total": 214, + "hitRate": 0.24766355140186916 }, { "encoding": "CP850", - "confidence": 70, "language": "de", + "confidence": 69, "byteLogLikelihood": -5.003946305945, - "hits": 51, + "hits": 50, "total": 216, - "hitRate": 0.2361111111111111 + "hitRate": 0.23148148148148148 }, { "encoding": "ISO-8859-14", - "confidence": 20, "language": "cy", + "confidence": 22, "byteLogLikelihood": -4.912654885736, - "hits": 15, - "total": 216, - "hitRate": 0.06944444444444445 + "hits": 16, + "total": 214, + "hitRate": 0.07476635514018691 }, { "encoding": "ISO-8859-2", - "confidence": 13, "language": "ro", + "confidence": 15, "byteLogLikelihood": -5.176149732574, - "hits": 10, - "total": 216, - "hitRate": 0.046296296296296294 + "hits": 11, + "total": 214, + "hitRate": 0.0514018691588785 }, { "encoding": "windows-1250", - "confidence": 13, "language": "ro", + "confidence": 15, "byteLogLikelihood": -5.176149732574, - "hits": 10, + "hits": 11, "total": 216, - "hitRate": 0.046296296296296294 + "hitRate": 0.05092592592592592 }, { "encoding": "ISO-8859-9", - "confidence": 12, "language": "tr", - "byteLogLikelihood": -4.5258676709, - "hits": 9, - "total": 216, - "hitRate": 0.041666666666666664 + "confidence": 14, + "byteLogLikelihood": -5.075173815234, + "hits": 10, + "total": 214, + "hitRate": 0.04672897196261682 }, { "encoding": "windows-1254", - "confidence": 12, "language": "tr", - "byteLogLikelihood": -4.5258676709, + "confidence": 12, + "byteLogLikelihood": -5.075173815234, "hits": 9, "total": 216, "hitRate": 0.041666666666666664 }, - { - "encoding": "ISO-8859-16", - "confidence": 11, - "language": "ro", - "byteLogLikelihood": -5.220355825078, - "hits": 8, - "total": 216, - "hitRate": 0.037037037037037035 - }, { "encoding": "windows-1257", - "confidence": 9, - "language": "lv", - "byteLogLikelihood": -5.19295685089, - "hits": 7, - "total": 216, - "hitRate": 0.032407407407407406 - }, - { - "encoding": "ISO-8859-4", - "confidence": 9, "language": "lv", + "confidence": 11, "byteLogLikelihood": -5.19295685089, - "hits": 7, - "total": 216, - "hitRate": 0.032407407407407406 + "hits": 8, + "total": 214, + "hitRate": 0.037383177570093455 }, { "encoding": "CP852", - "confidence": 6, "language": "pl", - "byteLogLikelihood": -5.087596335232, - "hits": 5, - "total": 216, - "hitRate": 0.023148148148148147 - }, - { - "encoding": "windows-1258", "confidence": 5, - "language": "vi", - "byteLogLikelihood": -5.497168225293, + "byteLogLikelihood": -5.087596335232, "hits": 4, "total": 216, "hitRate": 0.018518518518518517 - }, - { - "encoding": "ISO-8859-3", - "confidence": 5, - "language": "mt", - "byteLogLikelihood": -5.105945473901, - "hits": 4, - "total": 216, - "hitRate": 0.018518518518518517 - }, - { - "encoding": "ISO-8859-13", - "confidence": 2, - "language": "lt", - "byteLogLikelihood": -5.123963979403, - "hits": 2, - "total": 216, - "hitRate": 0.009259259259259259 - }, - { - "encoding": "ISO-8859-10", - "confidence": 1, - "language": "is", - "byteLogLikelihood": -5.204006687077, - "hits": 1, - "total": 216, - "hitRate": 0.004629629629629629 - }, - { - "encoding": "ISO-8859-5", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.162408104115, - "hits": 0, - "total": 216, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-6", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -4.007313397456, - "hits": 0, - "total": 216, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-7", - "confidence": 0, - "language": "el", - "byteLogLikelihood": -4.349754587225, - "hits": 0, - "total": 216, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-8", - "confidence": 0, - "language": "he", - "byteLogLikelihood": -4.279537403415, - "hits": 0, - "total": 216, - "hitRate": 0 - }, - { - "encoding": "windows-1251", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -4.542402054434, - "hits": 0, - "total": 216, - "hitRate": 0 - }, - { - "encoding": "windows-1253", - "confidence": 0, - "language": "el", - "byteLogLikelihood": -4.349754587225, - "hits": 0, - "total": 216, - "hitRate": 0 - }, - { - "encoding": "windows-1255", - "confidence": 0, - "language": "he", - "byteLogLikelihood": -4.279537403415, - "hits": 0, - "total": 216, - "hitRate": 0 - }, - { - "encoding": "windows-1256", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -4.318835143108, - "hits": 0, - "total": 216, - "hitRate": 0 - }, - { - "encoding": "windows-874", - "confidence": 0, - "language": "th", - "byteLogLikelihood": -5.657121063601, - "hits": 0, - "total": 216, - "hitRate": 0 - }, - { - "encoding": "KOI8-R", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.28774788718, - "hits": 0, - "total": 216, - "hitRate": 0 - }, - { - "encoding": "KOI8-U", - "confidence": 0, - "language": "uk", - "byteLogLikelihood": -6.245943193261, - "hits": 0, - "total": 216, - "hitRate": 0 - }, - { - "encoding": "IBM866", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.692083742507, - "hits": 0, - "total": 216, - "hitRate": 0 - }, - { - "encoding": "IBM855", - "confidence": 0, - "language": "sr", - "byteLogLikelihood": -5.942998477092, - "hits": 0, - "total": 216, - "hitRate": 0 - }, - { - "encoding": "x-mac-cyrillic", - "confidence": 0, - "language": "uk", - "byteLogLikelihood": -3.629332579687, - "hits": 0, - "total": 216, - "hitRate": 0 - } - ] - }, - { - "expected": { - "encoding": "ISO-8859-15", - "language": "es" - }, - "predicted": { - "encoding": "ISO-8859-1", - "confidence": 61, - "language": "es", - "byteLogLikelihood": -3.834657935767, - "hits": 41, - "total": 200, - "hitRate": 0.205 - }, - "encodingExact": false, - "encodingEquivalent": true, - "encodingCorrect": true, - "languageCorrect": true, - "tiedAtTop": 3, - "candidates": [ - { - "encoding": "ISO-8859-1", - "confidence": 61, - "language": "es", - "byteLogLikelihood": -3.834657935767, - "hits": 41, - "total": 200, - "hitRate": 0.205 + } + ] + }, + { + "expected": { + "encoding": "macintosh", + "language": "es" + }, + "predicted": { + "encoding": "macintosh", + "language": "es", + "confidence": 61, + "byteLogLikelihood": -3.834657935767, + "hits": 41, + "total": 200, + "hitRate": 0.205 + }, + "encodingExact": true, + "encodingEquivalent": false, + "encodingCorrect": true, + "languageCorrect": true, + "tiedAtTop": 1, + "candidates": [ + { + "encoding": "macintosh", + "language": "es", + "confidence": 61, + "byteLogLikelihood": -3.834657935767, + "hits": 41, + "total": 200, + "hitRate": 0.205 }, { "encoding": "windows-1252", - "confidence": 61, "language": "es", - "byteLogLikelihood": -3.834657935767, - "hits": 41, - "total": 200, - "hitRate": 0.205 + "confidence": 58, + "byteLogLikelihood": -4.948759890378, + "hits": 39, + "total": 199, + "hitRate": 0.19597989949748743 }, { "encoding": "ISO-8859-15", - "confidence": 61, "language": "es", - "byteLogLikelihood": -3.834657935767, - "hits": 41, - "total": 200, - "hitRate": 0.205 + "confidence": 58, + "byteLogLikelihood": -4.948759890378, + "hits": 39, + "total": 199, + "hitRate": 0.19597989949748743 }, { - "encoding": "macintosh", - "confidence": 58, + "encoding": "ISO-8859-1", "language": "es", + "confidence": 58, "byteLogLikelihood": -4.948759890378, "hits": 39, "total": 199, @@ -6677,8 +5105,8 @@ }, { "encoding": "CP850", - "confidence": 58, "language": "es", + "confidence": 58, "byteLogLikelihood": -4.948759890378, "hits": 39, "total": 200, @@ -6686,10492 +5114,1122 @@ }, { "encoding": "windows-1257", - "confidence": 24, "language": "lv", + "confidence": 25, "byteLogLikelihood": -5.19295685089, - "hits": 16, - "total": 200, - "hitRate": 0.08 - }, - { - "encoding": "ISO-8859-4", - "confidence": 24, - "language": "lv", - "byteLogLikelihood": -5.009854802779, - "hits": 16, - "total": 200, - "hitRate": 0.08 - }, - { - "encoding": "ISO-8859-13", - "confidence": 19, - "language": "lt", - "byteLogLikelihood": -4.892914919217, - "hits": 13, - "total": 200, - "hitRate": 0.065 - }, - { - "encoding": "ISO-8859-14", - "confidence": 16, - "language": "cy", - "byteLogLikelihood": -4.912654885736, - "hits": 11, - "total": 200, - "hitRate": 0.055 - }, - { - "encoding": "ISO-8859-2", - "confidence": 15, - "language": "ro", - "byteLogLikelihood": -5.176149732574, - "hits": 10, - "total": 200, - "hitRate": 0.05 - }, - { - "encoding": "windows-1250", - "confidence": 15, - "language": "ro", - "byteLogLikelihood": -5.176149732574, - "hits": 10, - "total": 200, - "hitRate": 0.05 - }, - { - "encoding": "ISO-8859-16", - "confidence": 15, - "language": "ro", - "byteLogLikelihood": -5.220355825078, - "hits": 10, - "total": 200, - "hitRate": 0.05 - }, - { - "encoding": "ISO-8859-9", - "confidence": 7, - "language": "tr", - "byteLogLikelihood": -5.075173815234, - "hits": 5, - "total": 200, - "hitRate": 0.025 - }, - { - "encoding": "windows-1254", - "confidence": 7, - "language": "tr", - "byteLogLikelihood": -5.075173815234, - "hits": 5, - "total": 200, - "hitRate": 0.025 - }, - { - "encoding": "CP852", - "confidence": 7, - "language": "pl", - "byteLogLikelihood": -5.087596335232, - "hits": 5, - "total": 200, - "hitRate": 0.025 - }, - { - "encoding": "windows-1258", - "confidence": 4, - "language": "vi", - "byteLogLikelihood": -4.848531508941, - "hits": 3, - "total": 200, - "hitRate": 0.015 - }, - { - "encoding": "ISO-8859-10", - "confidence": 4, - "language": "is", - "byteLogLikelihood": -3.846028832089, - "hits": 3, - "total": 200, - "hitRate": 0.015 - }, - { - "encoding": "ISO-8859-5", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -4.977292083619, - "hits": 0, - "total": 200, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-6", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -5.346153815501, - "hits": 0, - "total": 200, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-7", - "confidence": 0, - "language": "el", - "byteLogLikelihood": -3.106555532888, - "hits": 0, - "total": 200, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-8", - "confidence": 0, - "language": "he", - "byteLogLikelihood": -3.411159813207, - "hits": 0, - "total": 200, - "hitRate": 0 - }, - { - "encoding": "windows-1251", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -3.336328204376, - "hits": 0, - "total": 200, - "hitRate": 0 - }, - { - "encoding": "windows-1253", - "confidence": 0, - "language": "el", - "byteLogLikelihood": -3.106555532888, - "hits": 0, - "total": 200, - "hitRate": 0 - }, - { - "encoding": "windows-1255", - "confidence": 0, - "language": "he", - "byteLogLikelihood": -3.411159813207, - "hits": 0, - "total": 200, - "hitRate": 0 - }, - { - "encoding": "windows-1256", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -3.300604963183, - "hits": 0, - "total": 200, - "hitRate": 0 - }, - { - "encoding": "windows-874", - "confidence": 0, - "language": "th", - "byteLogLikelihood": -5.412820202576, - "hits": 0, - "total": 200, - "hitRate": 0 - }, - { - "encoding": "KOI8-R", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.692083742507, - "hits": 0, - "total": 200, - "hitRate": 0 - }, - { - "encoding": "KOI8-U", - "confidence": 0, - "language": "uk", - "byteLogLikelihood": -6.303705458307, - "hits": 0, - "total": 200, - "hitRate": 0 - }, - { - "encoding": "IBM866", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -4.977292083619, - "hits": 0, - "total": 200, - "hitRate": 0 - }, - { - "encoding": "IBM855", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -4.203740544852, - "hits": 0, - "total": 200, - "hitRate": 0 - }, - { - "encoding": "x-mac-cyrillic", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -3.336328204376, - "hits": 0, - "total": 200, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-3", - "confidence": 0, - "language": "mt", - "byteLogLikelihood": -5.105945473901, - "hits": 0, - "total": 200, - "hitRate": 0 - } - ] - }, - { - "expected": { - "encoding": "ISO-8859-15", - "language": "fr" - }, - "predicted": { - "encoding": "ISO-8859-1", - "confidence": 77, - "language": "fr", - "byteLogLikelihood": -2.06619631493, - "hits": 59, - "total": 228, - "hitRate": 0.25877192982456143 - }, - "encodingExact": false, - "encodingEquivalent": true, - "encodingCorrect": true, - "languageCorrect": true, - "tiedAtTop": 3, - "candidates": [ - { - "encoding": "ISO-8859-1", - "confidence": 77, - "language": "fr", - "byteLogLikelihood": -2.06619631493, - "hits": 59, - "total": 228, - "hitRate": 0.25877192982456143 - }, - { - "encoding": "windows-1252", - "confidence": 77, - "language": "fr", - "byteLogLikelihood": -2.06619631493, - "hits": 59, - "total": 228, - "hitRate": 0.25877192982456143 - }, - { - "encoding": "ISO-8859-15", - "confidence": 77, - "language": "fr", - "byteLogLikelihood": -2.06619631493, - "hits": 59, - "total": 228, - "hitRate": 0.25877192982456143 - }, - { - "encoding": "macintosh", - "confidence": 71, - "language": "fr", - "byteLogLikelihood": -5.010635294096, - "hits": 54, - "total": 228, - "hitRate": 0.23684210526315788 - }, - { - "encoding": "CP850", - "confidence": 71, - "language": "fr", - "byteLogLikelihood": -5.010635294096, - "hits": 54, - "total": 228, - "hitRate": 0.23684210526315788 - }, - { - "encoding": "ISO-8859-2", - "confidence": 11, - "language": "ro", - "byteLogLikelihood": -5.176149732574, - "hits": 9, - "total": 228, - "hitRate": 0.039473684210526314 - }, - { - "encoding": "windows-1250", - "confidence": 11, - "language": "ro", - "byteLogLikelihood": -5.176149732574, - "hits": 9, - "total": 228, - "hitRate": 0.039473684210526314 - }, - { - "encoding": "ISO-8859-10", - "confidence": 10, - "language": "is", - "byteLogLikelihood": -4.510859506517, - "hits": 8, - "total": 228, - "hitRate": 0.03508771929824561 - }, - { - "encoding": "ISO-8859-16", - "confidence": 10, - "language": "ro", - "byteLogLikelihood": -5.220355825078, - "hits": 8, - "total": 228, - "hitRate": 0.03508771929824561 - }, - { - "encoding": "windows-1257", - "confidence": 7, - "language": "lv", - "byteLogLikelihood": -5.19295685089, - "hits": 6, - "total": 228, - "hitRate": 0.02631578947368421 - }, - { - "encoding": "ISO-8859-4", - "confidence": 7, - "language": "lv", - "byteLogLikelihood": -5.19295685089, - "hits": 6, - "total": 228, - "hitRate": 0.02631578947368421 - }, - { - "encoding": "CP852", - "confidence": 7, - "language": "pl", - "byteLogLikelihood": -5.087596335232, - "hits": 6, - "total": 228, - "hitRate": 0.02631578947368421 - }, - { - "encoding": "ISO-8859-9", - "confidence": 5, - "language": "tr", - "byteLogLikelihood": -5.075173815234, - "hits": 4, - "total": 228, - "hitRate": 0.017543859649122806 - }, - { - "encoding": "windows-1254", - "confidence": 5, - "language": "tr", - "byteLogLikelihood": -5.075173815234, - "hits": 4, - "total": 228, - "hitRate": 0.017543859649122806 - }, - { - "encoding": "windows-1258", - "confidence": 5, - "language": "vi", - "byteLogLikelihood": -5.497168225293, - "hits": 4, - "total": 228, - "hitRate": 0.017543859649122806 - }, - { - "encoding": "ISO-8859-3", - "confidence": 5, - "language": "mt", - "byteLogLikelihood": -5.105945473901, - "hits": 4, - "total": 228, - "hitRate": 0.017543859649122806 - }, - { - "encoding": "ISO-8859-13", - "confidence": 5, - "language": "lt", - "byteLogLikelihood": -5.123963979403, - "hits": 4, - "total": 228, - "hitRate": 0.017543859649122806 - }, - { - "encoding": "ISO-8859-14", - "confidence": 3, - "language": "cy", - "byteLogLikelihood": -4.912654885736, - "hits": 3, - "total": 228, - "hitRate": 0.013157894736842105 - }, - { - "encoding": "ISO-8859-5", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.593471453839, - "hits": 0, - "total": 228, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-6", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -6.113682179832, - "hits": 0, - "total": 228, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-7", - "confidence": 0, - "language": "el", - "byteLogLikelihood": -2.654561516151, - "hits": 0, - "total": 228, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-8", - "confidence": 0, - "language": "he", - "byteLogLikelihood": -2.405884662832, - "hits": 0, - "total": 228, - "hitRate": 0 - }, - { - "encoding": "windows-1251", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -4.612642200827, - "hits": 0, - "total": 228, - "hitRate": 0 - }, - { - "encoding": "windows-1253", - "confidence": 0, - "language": "el", - "byteLogLikelihood": -2.654561516151, - "hits": 0, - "total": 228, - "hitRate": 0 - }, - { - "encoding": "windows-1255", - "confidence": 0, - "language": "he", - "byteLogLikelihood": -2.405884662832, - "hits": 0, - "total": 228, - "hitRate": 0 - }, - { - "encoding": "windows-1256", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -6.113682179832, - "hits": 0, - "total": 228, - "hitRate": 0 - }, - { - "encoding": "windows-874", - "confidence": 0, - "language": "th", - "byteLogLikelihood": -3.57655026914, - "hits": 0, - "total": 224, - "hitRate": 0 - }, - { - "encoding": "KOI8-R", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.692083742507, - "hits": 0, - "total": 228, - "hitRate": 0 - }, - { - "encoding": "KOI8-U", - "confidence": 0, - "language": "uk", - "byteLogLikelihood": -6.650279048587, - "hits": 0, - "total": 228, - "hitRate": 0 - }, - { - "encoding": "IBM866", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.593471453839, - "hits": 0, - "total": 228, - "hitRate": 0 - }, - { - "encoding": "IBM855", - "confidence": 0, - "language": "sr", - "byteLogLikelihood": -4.728861658331, - "hits": 0, - "total": 228, - "hitRate": 0 - }, - { - "encoding": "x-mac-cyrillic", - "confidence": 0, - "language": "uk", - "byteLogLikelihood": -4.252383775789, - "hits": 0, - "total": 228, - "hitRate": 0 - } - ] - }, - { - "expected": { - "encoding": "ISO-8859-16", - "language": "ro" - }, - "predicted": { - "encoding": "ISO-8859-16", - "confidence": 53, - "language": "ro", - "byteLogLikelihood": -2.758152644716, - "hits": 38, - "total": 214, - "hitRate": 0.17757009345794392 - }, - "encodingExact": true, - "encodingEquivalent": false, - "encodingCorrect": true, - "languageCorrect": true, - "tiedAtTop": 1, - "candidates": [ - { - "encoding": "ISO-8859-16", - "confidence": 53, - "language": "ro", - "byteLogLikelihood": -2.758152644716, - "hits": 38, - "total": 214, - "hitRate": 0.17757009345794392 - }, - { - "encoding": "ISO-8859-2", - "confidence": 44, - "language": "ro", - "byteLogLikelihood": -2.870272383724, - "hits": 32, - "total": 214, - "hitRate": 0.14953271028037382 - }, - { - "encoding": "windows-1250", - "confidence": 44, - "language": "ro", - "byteLogLikelihood": -2.870272383724, - "hits": 32, - "total": 214, - "hitRate": 0.14953271028037382 - }, - { - "encoding": "ISO-8859-1", - "confidence": 26, - "language": "it", - "byteLogLikelihood": -4.919980925828, - "hits": 19, - "total": 214, - "hitRate": 0.08878504672897196 - }, - { - "encoding": "windows-1252", - "confidence": 26, - "language": "it", - "byteLogLikelihood": -4.919980925828, - "hits": 19, - "total": 214, - "hitRate": 0.08878504672897196 - }, - { - "encoding": "macintosh", - "confidence": 22, - "language": "fr", - "byteLogLikelihood": -5.010635294096, - "hits": 16, - "total": 210, - "hitRate": 0.0761904761904762 - }, - { - "encoding": "CP850", - "confidence": 18, - "language": "fr", - "byteLogLikelihood": -5.010635294096, - "hits": 13, - "total": 213, - "hitRate": 0.06103286384976526 - }, - { - "encoding": "ISO-8859-15", - "confidence": 16, - "language": "fr", - "byteLogLikelihood": -4.918215670022, - "hits": 12, - "total": 214, - "hitRate": 0.056074766355140186 - }, - { - "encoding": "ISO-8859-3", - "confidence": 12, - "language": "mt", - "byteLogLikelihood": -5.105945473901, - "hits": 9, - "total": 212, - "hitRate": 0.04245283018867924 - }, - { - "encoding": "ISO-8859-9", - "confidence": 9, - "language": "tr", - "byteLogLikelihood": -4.982754191159, - "hits": 7, - "total": 214, - "hitRate": 0.03271028037383177 - }, - { - "encoding": "windows-1254", - "confidence": 9, - "language": "tr", - "byteLogLikelihood": -4.982754191159, - "hits": 7, - "total": 214, - "hitRate": 0.03271028037383177 - }, - { - "encoding": "CP852", - "confidence": 9, - "language": "pl", - "byteLogLikelihood": -5.087596335232, - "hits": 7, - "total": 215, - "hitRate": 0.03255813953488372 - }, - { - "encoding": "windows-1257", - "confidence": 8, - "language": "lv", - "byteLogLikelihood": -4.456762061842, - "hits": 6, - "total": 214, - "hitRate": 0.028037383177570093 - }, - { - "encoding": "ISO-8859-4", - "confidence": 7, - "language": "lv", - "byteLogLikelihood": -4.924600071508, - "hits": 5, - "total": 214, - "hitRate": 0.02336448598130841 - }, - { - "encoding": "windows-1258", - "confidence": 5, - "language": "vi", - "byteLogLikelihood": -5.219909353069, - "hits": 4, - "total": 214, - "hitRate": 0.018691588785046728 - }, - { - "encoding": "ISO-8859-10", - "confidence": 5, - "language": "is", - "byteLogLikelihood": -5.111587063002, - "hits": 4, - "total": 216, - "hitRate": 0.018518518518518517 - }, - { - "encoding": "ISO-8859-13", - "confidence": 5, - "language": "lt", - "byteLogLikelihood": -4.864509292863, - "hits": 4, - "total": 214, - "hitRate": 0.018691588785046728 - }, - { - "encoding": "ISO-8859-14", - "confidence": 4, - "language": "cy", - "byteLogLikelihood": -4.542976389437, - "hits": 3, - "total": 216, - "hitRate": 0.013888888888888888 - }, - { - "encoding": "windows-874", - "confidence": 1, - "language": "th", - "byteLogLikelihood": -5.210426263201, - "hits": 1, - "total": 214, - "hitRate": 0.004672897196261682 - }, - { - "encoding": "ISO-8859-5", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -4.539739112612, - "hits": 0, - "total": 216, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-6", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -5.000268888635, - "hits": 0, - "total": 211, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-7", - "confidence": 0, - "language": "el", - "byteLogLikelihood": -4.499845100591, - "hits": 0, - "total": 214, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-8", - "confidence": 0, - "language": "he", - "byteLogLikelihood": -4.429071192897, - "hits": 0, - "total": 213, - "hitRate": 0 - }, - { - "encoding": "windows-1251", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -4.382241948417, - "hits": 0, - "total": 214, - "hitRate": 0 - }, - { - "encoding": "windows-1253", - "confidence": 0, - "language": "el", - "byteLogLikelihood": -4.499845100591, - "hits": 0, - "total": 214, - "hitRate": 0 - }, - { - "encoding": "windows-1255", - "confidence": 0, - "language": "he", - "byteLogLikelihood": -4.429071192897, - "hits": 0, - "total": 213, - "hitRate": 0 - }, - { - "encoding": "windows-1256", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -4.739610656221, - "hits": 0, - "total": 213, - "hitRate": 0 - }, - { - "encoding": "KOI8-R", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.414824870283, - "hits": 0, - "total": 213, - "hitRate": 0 - }, - { - "encoding": "KOI8-U", - "confidence": 0, - "language": "uk", - "byteLogLikelihood": -6.199507530667, - "hits": 0, - "total": 215, - "hitRate": 0 - }, - { - "encoding": "IBM866", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -4.333669615722, - "hits": 0, - "total": 215, - "hitRate": 0 - }, - { - "encoding": "IBM855", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -4.794020051248, - "hits": 0, - "total": 215, - "hitRate": 0 - }, - { - "encoding": "x-mac-cyrillic", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -4.382241948417, - "hits": 0, - "total": 214, - "hitRate": 0 - } - ] - }, - { - "expected": { - "encoding": "ISO-8859-2", - "language": "cs" - }, - "predicted": { - "encoding": "ISO-8859-2", - "confidence": 30, - "language": "cs", - "byteLogLikelihood": -3.429159108442, - "hits": 13, - "total": 126, - "hitRate": 0.10317460317460317 - }, - "encodingExact": true, - "encodingEquivalent": false, - "encodingCorrect": true, - "languageCorrect": true, - "tiedAtTop": 2, - "candidates": [ - { - "encoding": "ISO-8859-2", - "confidence": 30, - "language": "cs", - "byteLogLikelihood": -3.429159108442, - "hits": 13, - "total": 126, - "hitRate": 0.10317460317460317 - }, - { - "encoding": "windows-1250", - "confidence": 30, - "language": "cs", - "byteLogLikelihood": -3.429159108442, - "hits": 13, - "total": 126, - "hitRate": 0.10317460317460317 - }, - { - "encoding": "ISO-8859-1", - "confidence": 11, - "language": "pt", - "byteLogLikelihood": -4.5670392286, - "hits": 5, - "total": 126, - "hitRate": 0.03968253968253968 - }, - { - "encoding": "windows-1252", - "confidence": 11, - "language": "pt", - "byteLogLikelihood": -4.5670392286, - "hits": 5, - "total": 126, - "hitRate": 0.03968253968253968 - }, - { - "encoding": "CP852", - "confidence": 11, - "language": "pl", - "byteLogLikelihood": -5.087596335232, - "hits": 5, - "total": 126, - "hitRate": 0.03968253968253968 - }, - { - "encoding": "windows-1257", - "confidence": 7, - "language": "lt", - "byteLogLikelihood": -4.997937219301, - "hits": 3, - "total": 126, - "hitRate": 0.023809523809523808 - }, - { - "encoding": "windows-1258", - "confidence": 7, - "language": "vi", - "byteLogLikelihood": -4.506724065575, - "hits": 3, - "total": 126, - "hitRate": 0.023809523809523808 - }, - { - "encoding": "macintosh", - "confidence": 7, - "language": "fr", - "byteLogLikelihood": -5.010635294096, - "hits": 3, - "total": 124, - "hitRate": 0.024193548387096774 - }, - { - "encoding": "ISO-8859-13", - "confidence": 7, - "language": "lt", - "byteLogLikelihood": -4.997937219301, - "hits": 3, - "total": 126, - "hitRate": 0.023809523809523808 - }, - { - "encoding": "ISO-8859-15", - "confidence": 7, - "language": "fr", - "byteLogLikelihood": -4.081579721495, - "hits": 3, - "total": 126, - "hitRate": 0.023809523809523808 - }, - { - "encoding": "ISO-8859-16", - "confidence": 7, - "language": "ro", - "byteLogLikelihood": -5.220355825078, - "hits": 3, - "total": 126, - "hitRate": 0.023809523809523808 - }, - { - "encoding": "CP850", - "confidence": 7, - "language": "fr", - "byteLogLikelihood": -5.010635294096, - "hits": 3, - "total": 125, - "hitRate": 0.024 - }, - { - "encoding": "ISO-8859-9", - "confidence": 4, - "language": "tr", - "byteLogLikelihood": -4.849273210708, - "hits": 2, - "total": 126, - "hitRate": 0.015873015873015872 - }, - { - "encoding": "windows-1254", - "confidence": 4, - "language": "tr", - "byteLogLikelihood": -4.849273210708, - "hits": 2, - "total": 126, - "hitRate": 0.015873015873015872 - }, - { - "encoding": "ISO-8859-4", - "confidence": 4, - "language": "lv", - "byteLogLikelihood": -5.129943470839, - "hits": 2, - "total": 126, - "hitRate": 0.015873015873015872 - }, - { - "encoding": "ISO-8859-14", - "confidence": 4, - "language": "cy", - "byteLogLikelihood": -4.912654885736, - "hits": 2, - "total": 126, - "hitRate": 0.015873015873015872 - }, - { - "encoding": "ISO-8859-5", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.254067466067, - "hits": 0, - "total": 125, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-6", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -5.402405269754, - "hits": 0, - "total": 124, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-7", - "confidence": 0, - "language": "el", - "byteLogLikelihood": -3.401446196881, - "hits": 0, - "total": 126, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-8", - "confidence": 0, - "language": "he", - "byteLogLikelihood": -3.467509652199, - "hits": 0, - "total": 125, - "hitRate": 0 - }, - { - "encoding": "windows-1251", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -4.249199684222, - "hits": 0, - "total": 126, - "hitRate": 0 - }, - { - "encoding": "windows-1253", - "confidence": 0, - "language": "el", - "byteLogLikelihood": -3.401446196881, - "hits": 0, - "total": 126, - "hitRate": 0 - }, - { - "encoding": "windows-1255", - "confidence": 0, - "language": "he", - "byteLogLikelihood": -3.467509652199, - "hits": 0, - "total": 125, - "hitRate": 0 - }, - { - "encoding": "windows-1256", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -5.164526575273, - "hits": 0, - "total": 125, - "hitRate": 0 - }, - { - "encoding": "windows-874", - "confidence": 0, - "language": "th", - "byteLogLikelihood": -4.504431122267, - "hits": 0, - "total": 122, - "hitRate": 0 - }, - { - "encoding": "KOI8-R", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.566056982405, - "hits": 0, - "total": 126, - "hitRate": 0 - }, - { - "encoding": "KOI8-U", - "confidence": 0, - "language": "uk", - "byteLogLikelihood": -6.524252288486, - "hits": 0, - "total": 126, - "hitRate": 0 - }, - { - "encoding": "IBM866", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.254067466067, - "hits": 0, - "total": 125, - "hitRate": 0 - }, - { - "encoding": "IBM855", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.108905030169, - "hits": 0, - "total": 125, - "hitRate": 0 - }, - { - "encoding": "x-mac-cyrillic", - "confidence": 0, - "language": "uk", - "byteLogLikelihood": -4.226561011787, - "hits": 0, - "total": 126, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-3", - "confidence": 0, - "language": "mt", - "byteLogLikelihood": -5.105945473901, - "hits": 0, - "total": 126, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-10", - "confidence": 0, - "language": "is", - "byteLogLikelihood": -4.43713857777, - "hits": 0, - "total": 126, - "hitRate": 0 - } - ] - }, - { - "expected": { - "encoding": "ISO-8859-2", - "language": "hu" - }, - "predicted": { - "encoding": "ISO-8859-2", - "confidence": 46, - "language": "hu", - "byteLogLikelihood": -3.161205902203, - "hits": 21, - "total": 136, - "hitRate": 0.15441176470588236 - }, - "encodingExact": true, - "encodingEquivalent": false, - "encodingCorrect": true, - "languageCorrect": true, - "tiedAtTop": 2, - "candidates": [ - { - "encoding": "ISO-8859-2", - "confidence": 46, - "language": "hu", - "byteLogLikelihood": -3.161205902203, - "hits": 21, - "total": 136, - "hitRate": 0.15441176470588236 - }, - { - "encoding": "windows-1250", - "confidence": 46, - "language": "hu", - "byteLogLikelihood": -3.161205902203, - "hits": 21, - "total": 136, - "hitRate": 0.15441176470588236 - }, - { - "encoding": "ISO-8859-1", - "confidence": 17, - "language": "pt", - "byteLogLikelihood": -4.507887190294, - "hits": 8, - "total": 136, - "hitRate": 0.058823529411764705 - }, - { - "encoding": "windows-1252", - "confidence": 17, - "language": "pt", - "byteLogLikelihood": -4.507887190294, - "hits": 8, - "total": 136, - "hitRate": 0.058823529411764705 - }, - { - "encoding": "CP852", - "confidence": 15, - "language": "pl", - "byteLogLikelihood": -5.087596335232, - "hits": 7, - "total": 135, - "hitRate": 0.05185185185185185 - }, - { - "encoding": "ISO-8859-14", - "confidence": 8, - "language": "cy", - "byteLogLikelihood": -4.912654885736, - "hits": 4, - "total": 136, - "hitRate": 0.029411764705882353 - }, - { - "encoding": "macintosh", - "confidence": 6, - "language": "es", - "byteLogLikelihood": -4.948759890378, - "hits": 3, - "total": 135, - "hitRate": 0.022222222222222223 - }, - { - "encoding": "CP850", - "confidence": 6, - "language": "es", - "byteLogLikelihood": -4.948759890378, - "hits": 3, - "total": 134, - "hitRate": 0.022388059701492536 - }, - { - "encoding": "ISO-8859-15", - "confidence": 4, - "language": "fr", - "byteLogLikelihood": -4.274525549305, - "hits": 2, - "total": 136, - "hitRate": 0.014705882352941176 - }, - { - "encoding": "ISO-8859-16", - "confidence": 4, - "language": "ro", - "byteLogLikelihood": -5.220355825078, - "hits": 2, - "total": 136, - "hitRate": 0.014705882352941176 - }, - { - "encoding": "ISO-8859-9", - "confidence": 2, - "language": "tr", - "byteLogLikelihood": -4.5258676709, - "hits": 1, - "total": 136, - "hitRate": 0.007352941176470588 - }, - { - "encoding": "windows-1254", - "confidence": 2, - "language": "tr", - "byteLogLikelihood": -4.5258676709, - "hits": 1, - "total": 136, - "hitRate": 0.007352941176470588 - }, - { - "encoding": "windows-1257", - "confidence": 2, - "language": "et", - "byteLogLikelihood": -4.453831056838, - "hits": 1, - "total": 136, - "hitRate": 0.007352941176470588 - }, - { - "encoding": "ISO-8859-4", - "confidence": 2, - "language": "lv", - "byteLogLikelihood": -5.19295685089, - "hits": 1, - "total": 136, - "hitRate": 0.007352941176470588 - }, - { - "encoding": "ISO-8859-10", - "confidence": 2, - "language": "is", - "byteLogLikelihood": -3.90025153387, - "hits": 1, - "total": 136, - "hitRate": 0.007352941176470588 - }, - { - "encoding": "ISO-8859-13", - "confidence": 2, - "language": "lt", - "byteLogLikelihood": -4.950677184263, - "hits": 1, - "total": 136, - "hitRate": 0.007352941176470588 - }, - { - "encoding": "ISO-8859-5", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.485271956182, - "hits": 0, - "total": 136, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-6", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -5.538035906584, - "hits": 0, - "total": 134, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-7", - "confidence": 0, - "language": "el", - "byteLogLikelihood": -3.430247904624, - "hits": 0, - "total": 136, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-8", - "confidence": 0, - "language": "he", - "byteLogLikelihood": -3.984546441118, - "hits": 0, - "total": 135, - "hitRate": 0 - }, - { - "encoding": "windows-1251", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -4.6300671031, - "hits": 0, - "total": 136, - "hitRate": 0 - }, - { - "encoding": "windows-1253", - "confidence": 0, - "language": "el", - "byteLogLikelihood": -3.430247904624, - "hits": 0, - "total": 136, - "hitRate": 0 - }, - { - "encoding": "windows-1255", - "confidence": 0, - "language": "he", - "byteLogLikelihood": -3.984546441118, - "hits": 0, - "total": 135, - "hitRate": 0 - }, - { - "encoding": "windows-1256", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -5.009772962617, - "hits": 0, - "total": 135, - "hitRate": 0 - }, - { - "encoding": "windows-1258", - "confidence": 0, - "language": "vi", - "byteLogLikelihood": -5.010690688029, - "hits": 0, - "total": 136, - "hitRate": 0 - }, - { - "encoding": "windows-874", - "confidence": 0, - "language": "th", - "byteLogLikelihood": -4.953752719217, - "hits": 0, - "total": 133, - "hitRate": 0 - }, - { - "encoding": "KOI8-R", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.692083742507, - "hits": 0, - "total": 136, - "hitRate": 0 - }, - { - "encoding": "KOI8-U", - "confidence": 0, - "language": "uk", - "byteLogLikelihood": -6.606957349802, - "hits": 0, - "total": 136, - "hitRate": 0 - }, - { - "encoding": "IBM866", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.485271956182, - "hits": 0, - "total": 135, - "hitRate": 0 - }, - { - "encoding": "IBM855", - "confidence": 0, - "language": "sr", - "byteLogLikelihood": -5.100966544791, - "hits": 0, - "total": 136, - "hitRate": 0 - }, - { - "encoding": "x-mac-cyrillic", - "confidence": 0, - "language": "uk", - "byteLogLikelihood": -4.187765411941, - "hits": 0, - "total": 136, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-3", - "confidence": 0, - "language": "mt", - "byteLogLikelihood": -5.105945473901, - "hits": 0, - "total": 136, - "hitRate": 0 - } - ] - }, - { - "expected": { - "encoding": "ISO-8859-2", - "language": "pl" - }, - "predicted": { - "encoding": "ISO-8859-2", - "confidence": 40, - "language": "pl", - "byteLogLikelihood": -3.52910527172, - "hits": 25, - "total": 184, - "hitRate": 0.1358695652173913 - }, - "encodingExact": true, - "encodingEquivalent": false, - "encodingCorrect": true, - "languageCorrect": true, - "tiedAtTop": 1, - "candidates": [ - { - "encoding": "ISO-8859-2", - "confidence": 40, - "language": "pl", - "byteLogLikelihood": -3.52910527172, - "hits": 25, - "total": 184, - "hitRate": 0.1358695652173913 - }, - { - "encoding": "windows-1250", - "confidence": 37, - "language": "pl", - "byteLogLikelihood": -4.297518988235, - "hits": 23, - "total": 183, - "hitRate": 0.12568306010928962 - }, - { - "encoding": "CP852", - "confidence": 41, - "language": "pl", - "byteLogLikelihood": -5.087596335232, - "hits": 25, - "total": 182, - "hitRate": 0.13736263736263737 - }, - { - "encoding": "ISO-8859-1", - "confidence": 8, - "language": "it", - "byteLogLikelihood": -4.919980925828, - "hits": 5, - "total": 183, - "hitRate": 0.0273224043715847 - }, - { - "encoding": "windows-1252", - "confidence": 8, - "language": "it", - "byteLogLikelihood": -4.919980925828, - "hits": 5, - "total": 183, - "hitRate": 0.0273224043715847 - }, - { - "encoding": "windows-1258", - "confidence": 8, - "language": "vi", - "byteLogLikelihood": -5.343135518502, - "hits": 5, - "total": 183, - "hitRate": 0.0273224043715847 - }, - { - "encoding": "windows-1257", - "confidence": 6, - "language": "et", - "byteLogLikelihood": -4.934473933131, - "hits": 4, - "total": 183, - "hitRate": 0.02185792349726776 - }, - { - "encoding": "macintosh", - "confidence": 6, - "language": "es", - "byteLogLikelihood": -4.948759890378, - "hits": 4, - "total": 183, - "hitRate": 0.02185792349726776 - }, - { - "encoding": "ISO-8859-13", - "confidence": 6, - "language": "lt", - "byteLogLikelihood": -5.123963979403, - "hits": 4, - "total": 183, - "hitRate": 0.02185792349726776 - }, - { - "encoding": "ISO-8859-15", - "confidence": 6, - "language": "es", - "byteLogLikelihood": -4.396558412648, - "hits": 4, - "total": 183, - "hitRate": 0.02185792349726776 - }, - { - "encoding": "CP850", - "confidence": 6, - "language": "fr", - "byteLogLikelihood": -5.010635294096, - "hits": 4, - "total": 182, - "hitRate": 0.02197802197802198 - }, - { - "encoding": "ISO-8859-4", - "confidence": 4, - "language": "lv", - "byteLogLikelihood": -4.794788079951, - "hits": 3, - "total": 184, - "hitRate": 0.016304347826086956 - }, - { - "encoding": "ISO-8859-16", - "confidence": 3, - "language": "ro", - "byteLogLikelihood": -5.220355825078, - "hits": 2, - "total": 183, - "hitRate": 0.01092896174863388 - }, - { - "encoding": "ISO-8859-9", - "confidence": 1, - "language": "tr", - "byteLogLikelihood": -5.075173815234, - "hits": 1, - "total": 183, - "hitRate": 0.00546448087431694 - }, - { - "encoding": "windows-1254", - "confidence": 1, - "language": "tr", - "byteLogLikelihood": -5.075173815234, - "hits": 1, - "total": 183, - "hitRate": 0.00546448087431694 - }, - { - "encoding": "ISO-8859-3", - "confidence": 1, - "language": "mt", - "byteLogLikelihood": -4.476342508555, - "hits": 1, - "total": 184, - "hitRate": 0.005434782608695652 - }, - { - "encoding": "ISO-8859-10", - "confidence": 1, - "language": "is", - "byteLogLikelihood": -4.71573455878, - "hits": 1, - "total": 184, - "hitRate": 0.005434782608695652 - }, - { - "encoding": "ISO-8859-14", - "confidence": 1, - "language": "cy", - "byteLogLikelihood": -4.912654885736, - "hits": 1, - "total": 184, - "hitRate": 0.005434782608695652 - }, - { - "encoding": "ISO-8859-5", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.293914971567, - "hits": 0, - "total": 184, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-6", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -6.113682179832, - "hits": 0, - "total": 182, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-7", - "confidence": 0, - "language": "el", - "byteLogLikelihood": -5.002422325308, - "hits": 0, - "total": 183, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-8", - "confidence": 0, - "language": "he", - "byteLogLikelihood": -5.470147067075, - "hits": 0, - "total": 183, - "hitRate": 0 - }, - { - "encoding": "windows-1251", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.300217461931, - "hits": 0, - "total": 183, - "hitRate": 0 - }, - { - "encoding": "windows-1253", - "confidence": 0, - "language": "el", - "byteLogLikelihood": -5.002422325308, - "hits": 0, - "total": 183, - "hitRate": 0 - }, - { - "encoding": "windows-1255", - "confidence": 0, - "language": "he", - "byteLogLikelihood": -5.470147067075, - "hits": 0, - "total": 183, - "hitRate": 0 - }, - { - "encoding": "windows-1256", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -6.113682179832, - "hits": 0, - "total": 182, - "hitRate": 0 - }, - { - "encoding": "windows-874", - "confidence": 0, - "language": "th", - "byteLogLikelihood": -5.586271794593, - "hits": 0, - "total": 183, - "hitRate": 0 - }, - { - "encoding": "KOI8-R", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.538051035716, - "hits": 0, - "total": 183, - "hitRate": 0 - }, - { - "encoding": "KOI8-U", - "confidence": 0, - "language": "uk", - "byteLogLikelihood": -6.496246341796, - "hits": 0, - "total": 183, - "hitRate": 0 - }, - { - "encoding": "IBM866", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.447947678358, - "hits": 0, - "total": 183, - "hitRate": 0 - }, - { - "encoding": "IBM855", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.497577429688, - "hits": 0, - "total": 183, - "hitRate": 0 - }, - { - "encoding": "x-mac-cyrillic", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.300217461931, - "hits": 0, - "total": 183, - "hitRate": 0 - } - ] - }, - { - "expected": { - "encoding": "ISO-8859-2", - "language": "ro" - }, - "predicted": { - "encoding": "ISO-8859-2", - "confidence": 41, - "language": "ro", - "byteLogLikelihood": -2.684539297542, - "hits": 28, - "total": 202, - "hitRate": 0.13861386138613863 - }, - "encodingExact": true, - "encodingEquivalent": false, - "encodingCorrect": true, - "languageCorrect": true, - "tiedAtTop": 2, - "candidates": [ - { - "encoding": "ISO-8859-2", - "confidence": 41, - "language": "ro", - "byteLogLikelihood": -2.684539297542, - "hits": 28, - "total": 202, - "hitRate": 0.13861386138613863 - }, - { - "encoding": "windows-1250", - "confidence": 41, - "language": "ro", - "byteLogLikelihood": -2.684539297542, - "hits": 28, - "total": 202, - "hitRate": 0.13861386138613863 - }, - { - "encoding": "ISO-8859-16", - "confidence": 38, - "language": "ro", - "byteLogLikelihood": -2.700458868498, - "hits": 26, - "total": 202, - "hitRate": 0.12871287128712872 - }, - { - "encoding": "ISO-8859-1", - "confidence": 26, - "language": "it", - "byteLogLikelihood": -4.919980925828, - "hits": 18, - "total": 202, - "hitRate": 0.0891089108910891 - }, - { - "encoding": "windows-1252", - "confidence": 26, - "language": "it", - "byteLogLikelihood": -4.919980925828, - "hits": 18, - "total": 202, - "hitRate": 0.0891089108910891 - }, - { - "encoding": "macintosh", - "confidence": 19, - "language": "fr", - "byteLogLikelihood": -5.010635294096, - "hits": 13, - "total": 198, - "hitRate": 0.06565656565656566 - }, - { - "encoding": "CP850", - "confidence": 15, - "language": "fr", - "byteLogLikelihood": -5.010635294096, - "hits": 10, - "total": 199, - "hitRate": 0.05025125628140704 - }, - { - "encoding": "ISO-8859-15", - "confidence": 14, - "language": "fr", - "byteLogLikelihood": -4.903997266318, - "hits": 10, - "total": 202, - "hitRate": 0.04950495049504951 - }, - { - "encoding": "ISO-8859-3", - "confidence": 13, - "language": "mt", - "byteLogLikelihood": -5.105945473901, - "hits": 9, - "total": 200, - "hitRate": 0.045 - }, - { - "encoding": "ISO-8859-9", - "confidence": 10, - "language": "tr", - "byteLogLikelihood": -5.021854801345, - "hits": 7, - "total": 202, - "hitRate": 0.034653465346534656 - }, - { - "encoding": "windows-1254", - "confidence": 10, - "language": "tr", - "byteLogLikelihood": -5.021854801345, - "hits": 7, - "total": 202, - "hitRate": 0.034653465346534656 - }, - { - "encoding": "windows-1257", - "confidence": 8, - "language": "lv", - "byteLogLikelihood": -4.396820338954, - "hits": 6, - "total": 202, - "hitRate": 0.0297029702970297 - }, - { - "encoding": "CP852", - "confidence": 8, - "language": "pl", - "byteLogLikelihood": -5.087596335232, - "hits": 6, - "total": 201, - "hitRate": 0.029850746268656716 - }, - { - "encoding": "ISO-8859-4", - "confidence": 7, - "language": "lv", - "byteLogLikelihood": -4.936633427031, - "hits": 5, - "total": 202, - "hitRate": 0.024752475247524754 - }, - { - "encoding": "windows-1258", - "confidence": 5, - "language": "vi", - "byteLogLikelihood": -5.177254141958, - "hits": 4, - "total": 202, - "hitRate": 0.019801980198019802 - }, - { - "encoding": "ISO-8859-10", - "confidence": 5, - "language": "is", - "byteLogLikelihood": -5.150687673188, - "hits": 4, - "total": 202, - "hitRate": 0.019801980198019802 - }, - { - "encoding": "ISO-8859-13", - "confidence": 4, - "language": "lt", - "byteLogLikelihood": -4.974278583322, - "hits": 3, - "total": 202, - "hitRate": 0.01485148514851485 - }, - { - "encoding": "ISO-8859-14", - "confidence": 4, - "language": "cy", - "byteLogLikelihood": -4.539421788511, - "hits": 3, - "total": 202, - "hitRate": 0.01485148514851485 - }, - { - "encoding": "ISO-8859-5", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -4.208609169552, - "hits": 0, - "total": 202, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-6", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -4.828974536143, - "hits": 0, - "total": 199, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-7", - "confidence": 0, - "language": "el", - "byteLogLikelihood": -4.33505338151, - "hits": 0, - "total": 202, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-8", - "confidence": 0, - "language": "he", - "byteLogLikelihood": -4.197813655274, - "hits": 0, - "total": 201, - "hitRate": 0 - }, - { - "encoding": "windows-1251", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -4.229886082374, - "hits": 0, - "total": 202, - "hitRate": 0 - }, - { - "encoding": "windows-1253", - "confidence": 0, - "language": "el", - "byteLogLikelihood": -4.33505338151, - "hits": 0, - "total": 202, - "hitRate": 0 - }, - { - "encoding": "windows-1255", - "confidence": 0, - "language": "he", - "byteLogLikelihood": -4.197813655274, - "hits": 0, - "total": 201, - "hitRate": 0 - }, - { - "encoding": "windows-1256", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -4.528215037204, - "hits": 0, - "total": 201, - "hitRate": 0 - }, - { - "encoding": "windows-874", - "confidence": 0, - "language": "th", - "byteLogLikelihood": -5.239455511679, - "hits": 0, - "total": 200, - "hitRate": 0 - }, - { - "encoding": "KOI8-R", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.42548867306, - "hits": 0, - "total": 201, - "hitRate": 0 - }, - { - "encoding": "KOI8-U", - "confidence": 0, - "language": "uk", - "byteLogLikelihood": -6.32130473174, - "hits": 0, - "total": 201, - "hitRate": 0 - }, - { - "encoding": "IBM866", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -4.208609169552, - "hits": 0, - "total": 201, - "hitRate": 0 - }, - { - "encoding": "IBM855", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -4.608648280371, - "hits": 0, - "total": 201, - "hitRate": 0 - }, - { - "encoding": "x-mac-cyrillic", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -4.229886082374, - "hits": 0, - "total": 202, - "hitRate": 0 - } - ] - }, - { - "expected": { - "encoding": "ISO-8859-3", - "language": "mt" - }, - "predicted": { - "encoding": "ISO-8859-3", - "confidence": 52, - "language": "mt", - "byteLogLikelihood": -2.738213481781, - "hits": 32, - "total": 183, - "hitRate": 0.17486338797814208 - }, - "encodingExact": true, - "encodingEquivalent": false, - "encodingCorrect": true, - "languageCorrect": true, - "tiedAtTop": 1, - "candidates": [ - { - "encoding": "ISO-8859-3", - "confidence": 52, - "language": "mt", - "byteLogLikelihood": -2.738213481781, - "hits": 32, - "total": 183, - "hitRate": 0.17486338797814208 - }, - { - "encoding": "ISO-8859-9", - "confidence": 16, - "language": "tr", - "byteLogLikelihood": -5.075173815234, - "hits": 10, - "total": 181, - "hitRate": 0.055248618784530384 - }, - { - "encoding": "windows-1254", - "confidence": 16, - "language": "tr", - "byteLogLikelihood": -5.075173815234, - "hits": 10, - "total": 181, - "hitRate": 0.055248618784530384 - }, - { - "encoding": "ISO-8859-1", - "confidence": 14, - "language": "it", - "byteLogLikelihood": -4.81334289805, - "hits": 9, - "total": 181, - "hitRate": 0.049723756906077346 - }, - { - "encoding": "windows-1252", - "confidence": 14, - "language": "it", - "byteLogLikelihood": -4.81334289805, - "hits": 9, - "total": 181, - "hitRate": 0.049723756906077346 - }, - { - "encoding": "windows-1250", - "confidence": 13, - "language": "pl", - "byteLogLikelihood": -4.980958307454, - "hits": 8, - "total": 182, - "hitRate": 0.04395604395604396 - }, - { - "encoding": "windows-1258", - "confidence": 13, - "language": "vi", - "byteLogLikelihood": -4.506236351586, - "hits": 8, - "total": 181, - "hitRate": 0.04419889502762431 - }, - { - "encoding": "CP852", - "confidence": 13, - "language": "pl", - "byteLogLikelihood": -5.087596335232, - "hits": 8, - "total": 177, - "hitRate": 0.04519774011299435 - }, - { - "encoding": "macintosh", - "confidence": 11, - "language": "es", - "byteLogLikelihood": -4.948759890378, - "hits": 7, - "total": 181, - "hitRate": 0.03867403314917127 - }, - { - "encoding": "ISO-8859-4", - "confidence": 11, - "language": "lv", - "byteLogLikelihood": -4.945351018208, - "hits": 7, - "total": 183, - "hitRate": 0.03825136612021858 - }, - { - "encoding": "ISO-8859-15", - "confidence": 11, - "language": "es", - "byteLogLikelihood": -4.948759890378, - "hits": 7, - "total": 181, - "hitRate": 0.03867403314917127 - }, - { - "encoding": "CP850", - "confidence": 11, - "language": "es", - "byteLogLikelihood": -4.948759890378, - "hits": 7, - "total": 177, - "hitRate": 0.03954802259887006 - }, - { - "encoding": "ISO-8859-2", - "confidence": 9, - "language": "pl", - "byteLogLikelihood": -3.834078315244, - "hits": 6, - "total": 183, - "hitRate": 0.03278688524590164 - }, - { - "encoding": "windows-1257", - "confidence": 9, - "language": "lv", - "byteLogLikelihood": -5.19295685089, - "hits": 6, - "total": 182, - "hitRate": 0.03296703296703297 - }, - { - "encoding": "ISO-8859-14", - "confidence": 6, - "language": "cy", - "byteLogLikelihood": -4.912654885736, - "hits": 4, - "total": 183, - "hitRate": 0.02185792349726776 - }, - { - "encoding": "ISO-8859-13", - "confidence": 4, - "language": "lt", - "byteLogLikelihood": -4.986136327924, - "hits": 3, - "total": 182, - "hitRate": 0.016483516483516484 - }, - { - "encoding": "ISO-8859-16", - "confidence": 4, - "language": "ro", - "byteLogLikelihood": -5.220355825078, - "hits": 3, - "total": 182, - "hitRate": 0.016483516483516484 - }, - { - "encoding": "ISO-8859-10", - "confidence": 3, - "language": "is", - "byteLogLikelihood": -5.204006687077, - "hits": 2, - "total": 183, - "hitRate": 0.01092896174863388 - }, - { - "encoding": "ISO-8859-5", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.351251681057, - "hits": 0, - "total": 183, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-6", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -6.113682179832, - "hits": 0, - "total": 177, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-7", - "confidence": 0, - "language": "el", - "byteLogLikelihood": -5.198030006336, - "hits": 0, - "total": 182, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-8", - "confidence": 0, - "language": "he", - "byteLogLikelihood": -5.755123257218, - "hits": 0, - "total": 181, - "hitRate": 0 - }, - { - "encoding": "windows-1251", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.572384450833, - "hits": 0, - "total": 182, - "hitRate": 0 - }, - { - "encoding": "windows-1253", - "confidence": 0, - "language": "el", - "byteLogLikelihood": -5.198030006336, - "hits": 0, - "total": 182, - "hitRate": 0 - }, - { - "encoding": "windows-1255", - "confidence": 0, - "language": "he", - "byteLogLikelihood": -5.755123257218, - "hits": 0, - "total": 181, - "hitRate": 0 - }, - { - "encoding": "windows-1256", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -6.113682179832, - "hits": 0, - "total": 177, - "hitRate": 0 - }, - { - "encoding": "windows-874", - "confidence": 0, - "language": "th", - "byteLogLikelihood": -5.490920024976, - "hits": 0, - "total": 179, - "hitRate": 0 - }, - { - "encoding": "KOI8-R", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.42548867306, - "hits": 0, - "total": 181, - "hitRate": 0 - }, - { - "encoding": "KOI8-U", - "confidence": 0, - "language": "uk", - "byteLogLikelihood": -6.383683979141, - "hits": 0, - "total": 181, - "hitRate": 0 - }, - { - "encoding": "IBM866", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.404570694946, - "hits": 0, - "total": 181, - "hitRate": 0 - }, - { - "encoding": "IBM855", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.943656762101, - "hits": 0, - "total": 181, - "hitRate": 0 - }, - { - "encoding": "x-mac-cyrillic", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.572384450833, - "hits": 0, - "total": 182, - "hitRate": 0 - } - ] - }, - { - "expected": { - "encoding": "ISO-8859-4", - "language": "lv" - }, - "predicted": { - "encoding": "ISO-8859-4", - "confidence": 40, - "language": "lv", - "byteLogLikelihood": -3.1328616083, - "hits": 23, - "total": 170, - "hitRate": 0.13529411764705881 - }, - "encodingExact": true, - "encodingEquivalent": false, - "encodingCorrect": true, - "languageCorrect": true, - "tiedAtTop": 1, - "candidates": [ - { - "encoding": "ISO-8859-4", - "confidence": 40, - "language": "lv", - "byteLogLikelihood": -3.1328616083, - "hits": 23, - "total": 170, - "hitRate": 0.13529411764705881 - }, - { - "encoding": "windows-1257", - "confidence": 31, - "language": "lv", - "byteLogLikelihood": -5.111410123766, - "hits": 18, - "total": 169, - "hitRate": 0.10650887573964497 - }, - { - "encoding": "CP850", - "confidence": 16, - "language": "es", - "byteLogLikelihood": -4.948759890378, - "hits": 9, - "total": 168, - "hitRate": 0.05357142857142857 - }, - { - "encoding": "ISO-8859-1", - "confidence": 14, - "language": "es", - "byteLogLikelihood": -4.721042183854, - "hits": 8, - "total": 169, - "hitRate": 0.047337278106508875 - }, - { - "encoding": "windows-1252", - "confidence": 14, - "language": "es", - "byteLogLikelihood": -4.721042183854, - "hits": 8, - "total": 169, - "hitRate": 0.047337278106508875 - }, - { - "encoding": "macintosh", - "confidence": 14, - "language": "es", - "byteLogLikelihood": -4.948759890378, - "hits": 8, - "total": 169, - "hitRate": 0.047337278106508875 - }, - { - "encoding": "ISO-8859-15", - "confidence": 14, - "language": "es", - "byteLogLikelihood": -4.721042183854, - "hits": 8, - "total": 169, - "hitRate": 0.047337278106508875 - }, - { - "encoding": "CP852", - "confidence": 12, - "language": "pl", - "byteLogLikelihood": -5.087596335232, - "hits": 7, - "total": 169, - "hitRate": 0.04142011834319527 - }, - { - "encoding": "ISO-8859-13", - "confidence": 10, - "language": "lt", - "byteLogLikelihood": -4.596975900219, - "hits": 6, - "total": 169, - "hitRate": 0.03550295857988166 - }, - { - "encoding": "ISO-8859-2", - "confidence": 8, - "language": "pl", - "byteLogLikelihood": -4.763992911083, - "hits": 5, - "total": 170, - "hitRate": 0.029411764705882353 - }, - { - "encoding": "windows-1250", - "confidence": 8, - "language": "pl", - "byteLogLikelihood": -4.846752537455, - "hits": 5, - "total": 169, - "hitRate": 0.029585798816568046 - }, - { - "encoding": "ISO-8859-3", - "confidence": 8, - "language": "mt", - "byteLogLikelihood": -5.105945473901, - "hits": 5, - "total": 170, - "hitRate": 0.029411764705882353 - }, - { - "encoding": "ISO-8859-9", - "confidence": 7, - "language": "tr", - "byteLogLikelihood": -5.075173815234, - "hits": 4, - "total": 169, - "hitRate": 0.023668639053254437 - }, - { - "encoding": "windows-1254", - "confidence": 7, - "language": "tr", - "byteLogLikelihood": -5.075173815234, - "hits": 4, - "total": 169, - "hitRate": 0.023668639053254437 - }, - { - "encoding": "ISO-8859-10", - "confidence": 7, - "language": "is", - "byteLogLikelihood": -5.074758182528, - "hits": 4, - "total": 170, - "hitRate": 0.023529411764705882 - }, - { - "encoding": "windows-1258", - "confidence": 5, - "language": "vi", - "byteLogLikelihood": -4.725539964734, - "hits": 3, - "total": 169, - "hitRate": 0.01775147928994083 - }, - { - "encoding": "ISO-8859-5", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.226735250772, - "hits": 0, - "total": 170, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-6", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -6.113682179832, - "hits": 0, - "total": 167, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-7", - "confidence": 0, - "language": "el", - "byteLogLikelihood": -5.427610697135, - "hits": 0, - "total": 169, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-8", - "confidence": 0, - "language": "he", - "byteLogLikelihood": -4.928827369245, - "hits": 0, - "total": 168, - "hitRate": 0 - }, - { - "encoding": "windows-1251", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -4.704365179493, - "hits": 0, - "total": 169, - "hitRate": 0 - }, - { - "encoding": "windows-1253", - "confidence": 0, - "language": "el", - "byteLogLikelihood": -5.427610697135, - "hits": 0, - "total": 169, - "hitRate": 0 - }, - { - "encoding": "windows-1255", - "confidence": 0, - "language": "he", - "byteLogLikelihood": -4.928827369245, - "hits": 0, - "total": 168, - "hitRate": 0 - }, - { - "encoding": "windows-1256", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -6.113682179832, - "hits": 0, - "total": 167, - "hitRate": 0 - }, - { - "encoding": "windows-874", - "confidence": 0, - "language": "th", - "byteLogLikelihood": -4.578946937177, - "hits": 0, - "total": 170, - "hitRate": 0 - }, - { - "encoding": "KOI8-R", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.610537015382, - "hits": 0, - "total": 168, - "hitRate": 0 - }, - { - "encoding": "KOI8-U", - "confidence": 0, - "language": "uk", - "byteLogLikelihood": -6.609505685025, - "hits": 0, - "total": 169, - "hitRate": 0 - }, - { - "encoding": "IBM866", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.267508614334, - "hits": 0, - "total": 168, - "hitRate": 0 - }, - { - "encoding": "IBM855", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.182018138172, - "hits": 0, - "total": 169, - "hitRate": 0 - }, - { - "encoding": "x-mac-cyrillic", - "confidence": 0, - "language": "uk", - "byteLogLikelihood": -4.65535318117, - "hits": 0, - "total": 170, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-14", - "confidence": 0, - "language": "cy", - "byteLogLikelihood": -4.912654885736, - "hits": 0, - "total": 170, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-16", - "confidence": 0, - "language": "ro", - "byteLogLikelihood": -4.616838329205, - "hits": 0, - "total": 169, - "hitRate": 0 - } - ] - }, - { - "expected": { - "encoding": "ISO-8859-5", - "language": "ru" - }, - "predicted": { - "encoding": "ISO-8859-5", - "confidence": 41, - "language": "ru", - "byteLogLikelihood": -3.313760777855, - "hits": 25, - "total": 179, - "hitRate": 0.13966480446927373 - }, - "encodingExact": true, - "encodingEquivalent": false, - "encodingCorrect": true, - "languageCorrect": true, - "tiedAtTop": 1, - "candidates": [ - { - "encoding": "ISO-8859-5", - "confidence": 41, - "language": "ru", - "byteLogLikelihood": -3.313760777855, - "hits": 25, - "total": 179, - "hitRate": 0.13966480446927373 - }, - { - "encoding": "IBM866", - "confidence": 20, - "language": "ru", - "byteLogLikelihood": -5.798412758856, - "hits": 5, - "total": 75, - "hitRate": 0.06666666666666667 - }, - { - "encoding": "x-mac-cyrillic", - "confidence": 12, - "language": "uk", - "byteLogLikelihood": -5.66890403251, - "hits": 6, - "total": 147, - "hitRate": 0.04081632653061224 - }, - { - "encoding": "IBM855", - "confidence": 9, - "language": "ru", - "byteLogLikelihood": -4.826799236728, - "hits": 5, - "total": 166, - "hitRate": 0.030120481927710843 - }, - { - "encoding": "windows-1256", - "confidence": 1, - "language": "ar", - "byteLogLikelihood": -4.986561094704, - "hits": 1, - "total": 176, - "hitRate": 0.005681818181818182 - }, - { - "encoding": "KOI8-U", - "confidence": 1, - "language": "uk", - "byteLogLikelihood": -4.816522715875, - "hits": 1, - "total": 179, - "hitRate": 0.00558659217877095 - }, - { - "encoding": "ISO-8859-1", - "confidence": 0, - "language": "it", - "byteLogLikelihood": -4.841944488282, - "hits": 0, - "total": 176, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-2", - "confidence": 0, - "language": "hu", - "byteLogLikelihood": -4.941337938888, - "hits": 0, - "total": 177, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-6", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -5.219340428659, - "hits": 0, - "total": 152, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-7", - "confidence": 0, - "language": "el", - "byteLogLikelihood": -5.141186484933, - "hits": 0, - "total": 175, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-8", - "confidence": 0, - "language": "he", - "byteLogLikelihood": -5.371812787625, - "hits": 0, - "total": 75, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-9", - "confidence": 0, - "language": "tr", - "byteLogLikelihood": -4.982255634278, - "hits": 0, - "total": 175, - "hitRate": 0 - }, - { - "encoding": "windows-1250", - "confidence": 0, - "language": "hu", - "byteLogLikelihood": -4.941337938888, - "hits": 0, - "total": 176, - "hitRate": 0 - }, - { - "encoding": "windows-1251", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.667544038277, - "hits": 0, - "total": 178, - "hitRate": 0 - }, - { - "encoding": "windows-1252", - "confidence": 0, - "language": "it", - "byteLogLikelihood": -4.841944488282, - "hits": 0, - "total": 176, - "hitRate": 0 - }, - { - "encoding": "windows-1253", - "confidence": 0, - "language": "el", - "byteLogLikelihood": -5.141186484933, - "hits": 0, - "total": 174, - "hitRate": 0 - }, - { - "encoding": "windows-1254", - "confidence": 0, - "language": "tr", - "byteLogLikelihood": -4.982255634278, - "hits": 0, - "total": 175, - "hitRate": 0 - }, - { - "encoding": "windows-1255", - "confidence": 0, - "language": "he", - "byteLogLikelihood": -5.371812787625, - "hits": 0, - "total": 113, - "hitRate": 0 - }, - { - "encoding": "windows-1257", - "confidence": 0, - "language": "lt", - "byteLogLikelihood": -4.847671496604, - "hits": 0, - "total": 176, - "hitRate": 0 - }, - { - "encoding": "windows-1258", - "confidence": 0, - "language": "vi", - "byteLogLikelihood": -4.755485363394, - "hits": 0, - "total": 166, - "hitRate": 0 - }, - { - "encoding": "windows-874", - "confidence": 0, - "language": "th", - "byteLogLikelihood": -4.810914106722, - "hits": 0, - "total": 84, - "hitRate": 0 - }, - { - "encoding": "KOI8-R", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -4.977706457443, - "hits": 0, - "total": 177, - "hitRate": 0 - }, - { - "encoding": "macintosh", - "confidence": 0, - "language": "es", - "byteLogLikelihood": -4.948759890378, - "hits": 0, - "total": 98, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-3", - "confidence": 0, - "language": "mt", - "byteLogLikelihood": -5.105945473901, - "hits": 0, - "total": 175, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-4", - "confidence": 0, - "language": "lv", - "byteLogLikelihood": -4.966015130424, - "hits": 0, - "total": 177, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-10", - "confidence": 0, - "language": "is", - "byteLogLikelihood": -5.103902669993, - "hits": 0, - "total": 179, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-13", - "confidence": 0, - "language": "lt", - "byteLogLikelihood": -4.847671496604, - "hits": 0, - "total": 176, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-14", - "confidence": 0, - "language": "cy", - "byteLogLikelihood": -4.83002806951, - "hits": 0, - "total": 178, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-15", - "confidence": 0, - "language": "es", - "byteLogLikelihood": -4.848242748706, - "hits": 0, - "total": 177, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-16", - "confidence": 0, - "language": "ro", - "byteLogLikelihood": -5.105122227945, - "hits": 0, - "total": 178, - "hitRate": 0 - }, - { - "encoding": "CP850", - "confidence": 0, - "language": "es", - "byteLogLikelihood": -4.948759890378, - "hits": 0, - "total": 162, - "hitRate": 0 - }, - { - "encoding": "CP852", - "confidence": 0, - "language": "pl", - "byteLogLikelihood": -5.078415577874, - "hits": 0, - "total": 166, - "hitRate": 0 - } - ] - }, - { - "expected": { - "encoding": "ISO-8859-6", - "language": "ar" - }, - "predicted": { - "encoding": "ISO-8859-6", - "confidence": 62, - "language": "ar", - "byteLogLikelihood": -3.306009422775, - "hits": 23, - "total": 110, - "hitRate": 0.20909090909090908 - }, - "encodingExact": true, - "encodingEquivalent": false, - "encodingCorrect": true, - "languageCorrect": true, - "tiedAtTop": 1, - "candidates": [ - { - "encoding": "ISO-8859-6", - "confidence": 62, - "language": "ar", - "byteLogLikelihood": -3.306009422775, - "hits": 23, - "total": 110, - "hitRate": 0.20909090909090908 - }, - { - "encoding": "windows-1256", - "confidence": 10, - "language": "ar", - "byteLogLikelihood": -3.968382111451, - "hits": 4, - "total": 110, - "hitRate": 0.03636363636363636 - }, - { - "encoding": "x-mac-cyrillic", - "confidence": 10, - "language": "ru", - "byteLogLikelihood": -5.359123221706, - "hits": 3, - "total": 82, - "hitRate": 0.036585365853658534 - }, - { - "encoding": "ISO-8859-8", - "confidence": 8, - "language": "he", - "byteLogLikelihood": -5.049228744152, - "hits": 2, - "total": 70, - "hitRate": 0.02857142857142857 - }, - { - "encoding": "windows-1255", - "confidence": 8, - "language": "he", - "byteLogLikelihood": -5.049228744152, - "hits": 2, - "total": 72, - "hitRate": 0.027777777777777776 - }, - { - "encoding": "ISO-8859-7", - "confidence": 5, - "language": "el", - "byteLogLikelihood": -4.984009642853, - "hits": 2, - "total": 109, - "hitRate": 0.01834862385321101 - }, - { - "encoding": "windows-1253", - "confidence": 5, - "language": "el", - "byteLogLikelihood": -4.984009642853, - "hits": 2, - "total": 109, - "hitRate": 0.01834862385321101 - }, - { - "encoding": "KOI8-R", - "confidence": 2, - "language": "ru", - "byteLogLikelihood": -5.040654549299, - "hits": 1, - "total": 110, - "hitRate": 0.00909090909090909 - }, - { - "encoding": "KOI8-U", - "confidence": 2, - "language": "uk", - "byteLogLikelihood": -5.174167309306, - "hits": 1, - "total": 110, - "hitRate": 0.00909090909090909 - }, - { - "encoding": "ISO-8859-1", - "confidence": 0, - "language": "sv", - "byteLogLikelihood": -4.69584393439, - "hits": 0, - "total": 110, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-2", - "confidence": 0, - "language": "pl", - "byteLogLikelihood": -4.951980582514, - "hits": 0, - "total": 111, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-5", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.534213772279, - "hits": 0, - "total": 111, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-9", - "confidence": 0, - "language": "tr", - "byteLogLikelihood": -4.933475282212, - "hits": 0, - "total": 110, - "hitRate": 0 - }, - { - "encoding": "windows-1250", - "confidence": 0, - "language": "pl", - "byteLogLikelihood": -4.951980582514, - "hits": 0, - "total": 110, - "hitRate": 0 - }, - { - "encoding": "windows-1251", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.223507468988, - "hits": 0, - "total": 110, - "hitRate": 0 - }, - { - "encoding": "windows-1252", - "confidence": 0, - "language": "sv", - "byteLogLikelihood": -4.69584393439, - "hits": 0, - "total": 110, - "hitRate": 0 - }, - { - "encoding": "windows-1254", - "confidence": 0, - "language": "tr", - "byteLogLikelihood": -4.933475282212, - "hits": 0, - "total": 110, - "hitRate": 0 - }, - { - "encoding": "windows-1257", - "confidence": 0, - "language": "et", - "byteLogLikelihood": -4.72024182268, - "hits": 0, - "total": 110, - "hitRate": 0 - }, - { - "encoding": "windows-1258", - "confidence": 0, - "language": "vi", - "byteLogLikelihood": -5.029794115635, - "hits": 0, - "total": 109, - "hitRate": 0 - }, - { - "encoding": "windows-874", - "confidence": 0, - "language": "th", - "byteLogLikelihood": -4.643135408712, - "hits": 0, - "total": 92, - "hitRate": 0 - }, - { - "encoding": "IBM866", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.068419445019, - "hits": 0, - "total": 72, - "hitRate": 0 - }, - { - "encoding": "IBM855", - "confidence": 0, - "language": "sr", - "byteLogLikelihood": -5.811360688713, - "hits": 0, - "total": 100, - "hitRate": 0 - }, - { - "encoding": "macintosh", - "confidence": 0, - "language": "es", - "byteLogLikelihood": -4.948759890378, - "hits": 0, - "total": 55, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-3", - "confidence": 0, - "language": "mt", - "byteLogLikelihood": -5.047518534687, - "hits": 0, - "total": 110, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-4", - "confidence": 0, - "language": "lv", - "byteLogLikelihood": -5.155285808468, - "hits": 0, - "total": 111, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-10", - "confidence": 0, - "language": "is", - "byteLogLikelihood": -5.051594021628, - "hits": 0, - "total": 111, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-13", - "confidence": 0, - "language": "lt", - "byteLogLikelihood": -5.063690311528, - "hits": 0, - "total": 110, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-14", - "confidence": 0, - "language": "cy", - "byteLogLikelihood": -4.799641758471, - "hits": 0, - "total": 111, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-15", - "confidence": 0, - "language": "de", - "byteLogLikelihood": -4.755317425962, - "hits": 0, - "total": 110, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-16", - "confidence": 0, - "language": "ro", - "byteLogLikelihood": -5.160082157204, - "hits": 0, - "total": 111, - "hitRate": 0 - }, - { - "encoding": "CP850", - "confidence": 0, - "language": "es", - "byteLogLikelihood": -4.948759890378, - "hits": 0, - "total": 98, - "hitRate": 0 - }, - { - "encoding": "CP852", - "confidence": 0, - "language": "pl", - "byteLogLikelihood": -5.087596335232, - "hits": 0, - "total": 100, - "hitRate": 0 - } - ] - }, - { - "expected": { - "encoding": "ISO-8859-7", - "language": "el" - }, - "predicted": { - "encoding": "ISO-8859-7", - "confidence": 51, - "language": "el", - "byteLogLikelihood": -3.435199502, - "hits": 23, - "total": 134, - "hitRate": 0.17164179104477612 - }, - "encodingExact": true, - "encodingEquivalent": false, - "encodingCorrect": true, - "languageCorrect": true, - "tiedAtTop": 2, - "candidates": [ - { - "encoding": "ISO-8859-7", - "confidence": 51, - "language": "el", - "byteLogLikelihood": -3.435199502, - "hits": 23, - "total": 134, - "hitRate": 0.17164179104477612 - }, - { - "encoding": "windows-1253", - "confidence": 51, - "language": "el", - "byteLogLikelihood": -3.435199502, - "hits": 23, - "total": 134, - "hitRate": 0.17164179104477612 - }, - { - "encoding": "KOI8-U", - "confidence": 8, - "language": "uk", - "byteLogLikelihood": -6.254780178237, - "hits": 4, - "total": 134, - "hitRate": 0.029850746268656716 - }, - { - "encoding": "IBM855", - "confidence": 7, - "language": "ru", - "byteLogLikelihood": -5.358823187498, - "hits": 3, - "total": 118, - "hitRate": 0.025423728813559324 - }, - { - "encoding": "KOI8-R", - "confidence": 4, - "language": "ru", - "byteLogLikelihood": -6.302671202821, - "hits": 2, - "total": 134, - "hitRate": 0.014925373134328358 - }, - { - "encoding": "ISO-8859-6", - "confidence": 3, - "language": "ar", - "byteLogLikelihood": -5.268243094623, - "hits": 1, - "total": 81, - "hitRate": 0.012345679012345678 - }, - { - "encoding": "ISO-8859-8", - "confidence": 2, - "language": "he", - "byteLogLikelihood": -4.09495359507, - "hits": 1, - "total": 127, - "hitRate": 0.007874015748031496 - }, - { - "encoding": "windows-1255", - "confidence": 2, - "language": "he", - "byteLogLikelihood": -4.09495359507, - "hits": 1, - "total": 127, - "hitRate": 0.007874015748031496 - }, - { - "encoding": "x-mac-cyrillic", - "confidence": 2, - "language": "uk", - "byteLogLikelihood": -4.203232324163, - "hits": 1, - "total": 131, - "hitRate": 0.007633587786259542 - }, - { - "encoding": "ISO-8859-1", - "confidence": 0, - "language": "pt", - "byteLogLikelihood": -4.59932343766, - "hits": 0, - "total": 134, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-2", - "confidence": 0, - "language": "hu", - "byteLogLikelihood": -4.358825259583, - "hits": 0, - "total": 134, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-5", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.165809265202, - "hits": 0, - "total": 130, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-9", - "confidence": 0, - "language": "tr", - "byteLogLikelihood": -4.969377662519, - "hits": 0, - "total": 133, - "hitRate": 0 - }, - { - "encoding": "windows-1250", - "confidence": 0, - "language": "hu", - "byteLogLikelihood": -4.358825259583, - "hits": 0, - "total": 134, - "hitRate": 0 - }, - { - "encoding": "windows-1251", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -4.288697198304, - "hits": 0, - "total": 134, - "hitRate": 0 - }, - { - "encoding": "windows-1252", - "confidence": 0, - "language": "pt", - "byteLogLikelihood": -4.59932343766, - "hits": 0, - "total": 134, - "hitRate": 0 - }, - { - "encoding": "windows-1254", - "confidence": 0, - "language": "tr", - "byteLogLikelihood": -4.969377662519, - "hits": 0, - "total": 133, - "hitRate": 0 - }, - { - "encoding": "windows-1256", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -5.013410783916, - "hits": 0, - "total": 122, - "hitRate": 0 - }, - { - "encoding": "windows-1257", - "confidence": 0, - "language": "et", - "byteLogLikelihood": -4.827626146169, - "hits": 0, - "total": 134, - "hitRate": 0 - }, - { - "encoding": "windows-1258", - "confidence": 0, - "language": "vi", - "byteLogLikelihood": -4.681848366371, - "hits": 0, - "total": 127, - "hitRate": 0 - }, - { - "encoding": "windows-874", - "confidence": 0, - "language": "th", - "byteLogLikelihood": -5.483358374511, - "hits": 0, - "total": 52, - "hitRate": 0 - }, - { - "encoding": "IBM866", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.55248803416, - "hits": 0, - "total": 127, - "hitRate": 0 - }, - { - "encoding": "macintosh", - "confidence": 0, - "language": "es", - "byteLogLikelihood": -4.948759890378, - "hits": 0, - "total": 116, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-3", - "confidence": 0, - "language": "mt", - "byteLogLikelihood": -4.945729021813, - "hits": 0, - "total": 129, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-4", - "confidence": 0, - "language": "lv", - "byteLogLikelihood": -5.015268979336, - "hits": 0, - "total": 134, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-10", - "confidence": 0, - "language": "is", - "byteLogLikelihood": -4.576407109739, - "hits": 0, - "total": 134, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-13", - "confidence": 0, - "language": "lt", - "byteLogLikelihood": -4.890771320266, - "hits": 0, - "total": 134, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-14", - "confidence": 0, - "language": "cy", - "byteLogLikelihood": -4.788878603493, - "hits": 0, - "total": 134, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-15", - "confidence": 0, - "language": "es", - "byteLogLikelihood": -4.603974037796, - "hits": 0, - "total": 134, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-16", - "confidence": 0, - "language": "ro", - "byteLogLikelihood": -5.137560045078, - "hits": 0, - "total": 134, - "hitRate": 0 - }, - { - "encoding": "CP850", - "confidence": 0, - "language": "es", - "byteLogLikelihood": -4.948759890378, - "hits": 0, - "total": 93, - "hitRate": 0 - }, - { - "encoding": "CP852", - "confidence": 0, - "language": "pl", - "byteLogLikelihood": -5.087596335232, - "hits": 0, - "total": 96, - "hitRate": 0 - } - ] - }, - { - "expected": { - "encoding": "ISO-8859-8", - "language": "he" - }, - "predicted": { - "encoding": "ISO-8859-8", - "confidence": 47, - "language": "he", - "byteLogLikelihood": -3.320333973076, - "hits": 16, - "total": 102, - "hitRate": 0.1568627450980392 - }, - "encodingExact": true, - "encodingEquivalent": false, - "encodingCorrect": true, - "languageCorrect": true, - "tiedAtTop": 2, - "candidates": [ - { - "encoding": "ISO-8859-8", - "confidence": 47, - "language": "he", - "byteLogLikelihood": -3.320333973076, - "hits": 16, - "total": 102, - "hitRate": 0.1568627450980392 - }, - { - "encoding": "windows-1255", - "confidence": 47, - "language": "he", - "byteLogLikelihood": -3.320333973076, - "hits": 16, - "total": 102, - "hitRate": 0.1568627450980392 - }, - { - "encoding": "ISO-8859-7", - "confidence": 2, - "language": "el", - "byteLogLikelihood": -3.981926233577, - "hits": 1, - "total": 102, - "hitRate": 0.00980392156862745 - }, - { - "encoding": "windows-1253", - "confidence": 2, - "language": "el", - "byteLogLikelihood": -3.981926233577, - "hits": 1, - "total": 102, - "hitRate": 0.00980392156862745 - }, - { - "encoding": "IBM855", - "confidence": 2, - "language": "ru", - "byteLogLikelihood": -5.394495827364, - "hits": 1, - "total": 102, - "hitRate": 0.00980392156862745 - }, - { - "encoding": "ISO-8859-1", - "confidence": 0, - "language": "sv", - "byteLogLikelihood": -4.395116706452, - "hits": 0, - "total": 102, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-2", - "confidence": 0, - "language": "cs", - "byteLogLikelihood": -4.461975046319, - "hits": 0, - "total": 102, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-5", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.683415446443, - "hits": 0, - "total": 102, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-6", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -5.124491051534, - "hits": 0, - "total": 73, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-9", - "confidence": 0, - "language": "tr", - "byteLogLikelihood": -4.941685614581, - "hits": 0, - "total": 102, - "hitRate": 0 - }, - { - "encoding": "windows-1250", - "confidence": 0, - "language": "cs", - "byteLogLikelihood": -4.461975046319, - "hits": 0, - "total": 102, - "hitRate": 0 - }, - { - "encoding": "windows-1251", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -4.199203901043, - "hits": 0, - "total": 102, - "hitRate": 0 - }, - { - "encoding": "windows-1252", - "confidence": 0, - "language": "sv", - "byteLogLikelihood": -4.395116706452, - "hits": 0, - "total": 102, - "hitRate": 0 - }, - { - "encoding": "windows-1254", - "confidence": 0, - "language": "tr", - "byteLogLikelihood": -4.941685614581, - "hits": 0, - "total": 102, - "hitRate": 0 - }, - { - "encoding": "windows-1256", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -5.32364067176, - "hits": 0, - "total": 93, - "hitRate": 0 - }, - { - "encoding": "windows-1257", - "confidence": 0, - "language": "et", - "byteLogLikelihood": -4.639272141503, - "hits": 0, - "total": 102, - "hitRate": 0 - }, - { - "encoding": "windows-1258", - "confidence": 0, - "language": "vi", - "byteLogLikelihood": -5.029681805165, - "hits": 0, - "total": 99, - "hitRate": 0 - }, - { - "encoding": "windows-874", - "confidence": 0, - "language": "th", - "byteLogLikelihood": -5.31385343816, - "hits": 0, - "total": 48, - "hitRate": 0 - }, - { - "encoding": "KOI8-R", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.40669720385, - "hits": 0, - "total": 102, - "hitRate": 0 - }, - { - "encoding": "KOI8-U", - "confidence": 0, - "language": "uk", - "byteLogLikelihood": -6.393692981541, - "hits": 0, - "total": 102, - "hitRate": 0 - }, - { - "encoding": "IBM866", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.683415446443, - "hits": 0, - "total": 94, - "hitRate": 0 - }, - { - "encoding": "macintosh", - "confidence": 0, - "language": "es", - "byteLogLikelihood": -4.948759890378, - "hits": 0, - "total": 72, - "hitRate": 0 - }, - { - "encoding": "x-mac-cyrillic", - "confidence": 0, - "language": "uk", - "byteLogLikelihood": -4.134202940863, - "hits": 0, - "total": 102, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-3", - "confidence": 0, - "language": "mt", - "byteLogLikelihood": -4.956632184798, - "hits": 0, - "total": 102, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-4", - "confidence": 0, - "language": "lv", - "byteLogLikelihood": -5.146385148445, - "hits": 0, - "total": 102, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-10", - "confidence": 0, - "language": "is", - "byteLogLikelihood": -4.745792460039, - "hits": 0, - "total": 102, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-13", - "confidence": 0, - "language": "lt", - "byteLogLikelihood": -4.842271132243, - "hits": 0, - "total": 102, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-14", - "confidence": 0, - "language": "cy", - "byteLogLikelihood": -4.813633859942, - "hits": 0, - "total": 102, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-15", - "confidence": 0, - "language": "fr", - "byteLogLikelihood": -4.521941300627, - "hits": 0, - "total": 102, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-16", - "confidence": 0, - "language": "ro", - "byteLogLikelihood": -5.093070766591, - "hits": 0, - "total": 102, - "hitRate": 0 - }, - { - "encoding": "CP850", - "confidence": 0, - "language": "es", - "byteLogLikelihood": -4.948759890378, - "hits": 0, - "total": 85, - "hitRate": 0 - }, - { - "encoding": "CP852", - "confidence": 0, - "language": "pl", - "byteLogLikelihood": -5.087596335232, - "hits": 0, - "total": 89, - "hitRate": 0 - } - ] - }, - { - "expected": { - "encoding": "ISO-8859-9", - "language": "tr" - }, - "predicted": { - "encoding": "ISO-8859-9", - "confidence": 55, - "language": "tr", - "byteLogLikelihood": -3.531675216773, - "hits": 25, - "total": 134, - "hitRate": 0.1865671641791045 - }, - "encodingExact": true, - "encodingEquivalent": false, - "encodingCorrect": true, - "languageCorrect": true, - "tiedAtTop": 2, - "candidates": [ - { - "encoding": "ISO-8859-9", - "confidence": 55, - "language": "tr", - "byteLogLikelihood": -3.531675216773, - "hits": 25, - "total": 134, - "hitRate": 0.1865671641791045 - }, - { - "encoding": "windows-1254", - "confidence": 55, - "language": "tr", - "byteLogLikelihood": -3.531675216773, - "hits": 25, - "total": 134, - "hitRate": 0.1865671641791045 - }, - { - "encoding": "ISO-8859-3", - "confidence": 22, - "language": "mt", - "byteLogLikelihood": -5.105945473901, - "hits": 10, - "total": 134, - "hitRate": 0.07462686567164178 - }, - { - "encoding": "ISO-8859-1", - "confidence": 17, - "language": "da", - "byteLogLikelihood": -4.969813299576, - "hits": 8, - "total": 134, - "hitRate": 0.05970149253731343 - }, - { - "encoding": "windows-1252", - "confidence": 17, - "language": "da", - "byteLogLikelihood": -4.969813299576, - "hits": 8, - "total": 134, - "hitRate": 0.05970149253731343 - }, - { - "encoding": "ISO-8859-10", - "confidence": 17, - "language": "is", - "byteLogLikelihood": -4.720106560713, - "hits": 8, - "total": 134, - "hitRate": 0.05970149253731343 - }, - { - "encoding": "ISO-8859-2", - "confidence": 13, - "language": "ro", - "byteLogLikelihood": -4.352190516073, - "hits": 6, - "total": 134, - "hitRate": 0.04477611940298507 - }, - { - "encoding": "windows-1250", - "confidence": 13, - "language": "ro", - "byteLogLikelihood": -4.352190516073, - "hits": 6, - "total": 134, - "hitRate": 0.04477611940298507 - }, - { - "encoding": "windows-1257", - "confidence": 11, - "language": "lv", - "byteLogLikelihood": -3.613497993373, - "hits": 5, - "total": 134, - "hitRate": 0.03731343283582089 - }, - { - "encoding": "macintosh", - "confidence": 11, - "language": "es", - "byteLogLikelihood": -4.948759890378, - "hits": 5, - "total": 132, - "hitRate": 0.03787878787878788 - }, - { - "encoding": "ISO-8859-4", - "confidence": 11, - "language": "lv", - "byteLogLikelihood": -4.93302665818, - "hits": 5, - "total": 134, - "hitRate": 0.03731343283582089 - }, - { - "encoding": "ISO-8859-13", - "confidence": 11, - "language": "lt", - "byteLogLikelihood": -4.394247673508, - "hits": 5, - "total": 134, - "hitRate": 0.03731343283582089 - }, - { - "encoding": "ISO-8859-15", - "confidence": 11, - "language": "es", - "byteLogLikelihood": -4.948759890378, - "hits": 5, - "total": 134, - "hitRate": 0.03731343283582089 - }, - { - "encoding": "ISO-8859-16", - "confidence": 11, - "language": "ro", - "byteLogLikelihood": -4.25849981603, - "hits": 5, - "total": 134, - "hitRate": 0.03731343283582089 - }, - { - "encoding": "CP850", - "confidence": 11, - "language": "es", - "byteLogLikelihood": -4.948759890378, - "hits": 5, - "total": 132, - "hitRate": 0.03787878787878788 - }, - { - "encoding": "ISO-8859-14", - "confidence": 8, - "language": "cy", - "byteLogLikelihood": -4.652724693026, - "hits": 4, - "total": 134, - "hitRate": 0.029850746268656716 - }, - { - "encoding": "windows-1258", - "confidence": 6, - "language": "vi", - "byteLogLikelihood": -5.197431316193, - "hits": 3, - "total": 133, - "hitRate": 0.022556390977443608 - }, - { - "encoding": "CP852", - "confidence": 6, - "language": "pl", - "byteLogLikelihood": -5.087596335232, - "hits": 3, - "total": 133, - "hitRate": 0.022556390977443608 - }, - { - "encoding": "ISO-8859-5", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.88736478629, - "hits": 0, - "total": 133, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-6", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -5.217802445218, - "hits": 0, - "total": 132, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-7", - "confidence": 0, - "language": "el", - "byteLogLikelihood": -4.216966174066, - "hits": 0, - "total": 134, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-8", - "confidence": 0, - "language": "he", - "byteLogLikelihood": -4.95929011292, - "hits": 0, - "total": 132, - "hitRate": 0 - }, - { - "encoding": "windows-1251", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -4.576073075491, - "hits": 0, - "total": 134, - "hitRate": 0 - }, - { - "encoding": "windows-1253", - "confidence": 0, - "language": "el", - "byteLogLikelihood": -4.216966174066, - "hits": 0, - "total": 134, - "hitRate": 0 - }, - { - "encoding": "windows-1255", - "confidence": 0, - "language": "he", - "byteLogLikelihood": -4.95929011292, - "hits": 0, - "total": 132, - "hitRate": 0 - }, - { - "encoding": "windows-1256", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -6.113682179832, - "hits": 0, - "total": 132, - "hitRate": 0 - }, - { - "encoding": "windows-874", - "confidence": 0, - "language": "th", - "byteLogLikelihood": -5.714883328648, - "hits": 0, - "total": 130, - "hitRate": 0 - }, - { - "encoding": "KOI8-R", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.085579959517, - "hits": 0, - "total": 134, - "hitRate": 0 - }, - { - "encoding": "KOI8-U", - "confidence": 0, - "language": "uk", - "byteLogLikelihood": -6.303705458307, - "hits": 0, - "total": 134, - "hitRate": 0 - }, - { - "encoding": "IBM866", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.88736478629, - "hits": 0, - "total": 132, - "hitRate": 0 - }, - { - "encoding": "IBM855", - "confidence": 0, - "language": "sr", - "byteLogLikelihood": -4.742947096814, - "hits": 0, - "total": 132, - "hitRate": 0 - }, - { - "encoding": "x-mac-cyrillic", - "confidence": 0, - "language": "uk", - "byteLogLikelihood": -4.22610845571, - "hits": 0, - "total": 134, - "hitRate": 0 - } - ] - }, - { - "expected": { - "encoding": "KOI8-R", - "language": "ru" - }, - "predicted": { - "encoding": "KOI8-R", - "confidence": 43, - "language": "ru", - "byteLogLikelihood": -3.313760777855, - "hits": 26, - "total": 179, - "hitRate": 0.1452513966480447 - }, - "encodingExact": true, - "encodingEquivalent": false, - "encodingCorrect": true, - "languageCorrect": true, - "tiedAtTop": 1, - "candidates": [ - { - "encoding": "KOI8-R", - "confidence": 43, - "language": "ru", - "byteLogLikelihood": -3.313760777855, - "hits": 26, - "total": 179, - "hitRate": 0.1452513966480447 - }, - { - "encoding": "KOI8-U", - "confidence": 28, - "language": "uk", - "byteLogLikelihood": -3.443215105753, - "hits": 17, - "total": 179, - "hitRate": 0.09497206703910614 - }, - { - "encoding": "windows-874", - "confidence": 12, - "language": "th", - "byteLogLikelihood": -4.705552828452, - "hits": 7, - "total": 162, - "hitRate": 0.043209876543209874 - }, - { - "encoding": "ISO-8859-7", - "confidence": 6, - "language": "el", - "byteLogLikelihood": -5.840779048091, - "hits": 4, - "total": 177, - "hitRate": 0.022598870056497175 - }, - { - "encoding": "windows-1253", - "confidence": 6, - "language": "el", - "byteLogLikelihood": -5.840779048091, - "hits": 4, - "total": 177, - "hitRate": 0.022598870056497175 - }, - { - "encoding": "ISO-8859-5", - "confidence": 1, - "language": "ru", - "byteLogLikelihood": -5.543217452567, - "hits": 1, - "total": 179, - "hitRate": 0.00558659217877095 - }, - { - "encoding": "ISO-8859-10", - "confidence": 1, - "language": "is", - "byteLogLikelihood": -5.150827322214, - "hits": 1, - "total": 179, - "hitRate": 0.00558659217877095 - }, - { - "encoding": "ISO-8859-1", - "confidence": 0, - "language": "nl", - "byteLogLikelihood": -4.900684399759, - "hits": 0, - "total": 176, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-2", - "confidence": 0, - "language": "pl", - "byteLogLikelihood": -5.087596335232, - "hits": 0, - "total": 176, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-6", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -4.759099059366, - "hits": 0, - "total": 176, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-8", - "confidence": 0, - "language": "he", - "byteLogLikelihood": -5.899711049132, - "hits": 0, - "total": 7, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-9", - "confidence": 0, - "language": "tr", - "byteLogLikelihood": -5.056032280413, - "hits": 0, - "total": 176, - "hitRate": 0 - }, - { - "encoding": "windows-1250", - "confidence": 0, - "language": "pl", - "byteLogLikelihood": -5.087596335232, - "hits": 0, - "total": 176, - "hitRate": 0 - }, - { - "encoding": "windows-1251", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.313908864785, - "hits": 0, - "total": 179, - "hitRate": 0 - }, - { - "encoding": "windows-1252", - "confidence": 0, - "language": "nl", - "byteLogLikelihood": -4.900684399759, - "hits": 0, - "total": 176, - "hitRate": 0 - }, - { - "encoding": "windows-1254", - "confidence": 0, - "language": "tr", - "byteLogLikelihood": -5.056032280413, - "hits": 0, - "total": 176, - "hitRate": 0 - }, - { - "encoding": "windows-1255", - "confidence": 0, - "language": "he", - "byteLogLikelihood": -5.899711049132, - "hits": 0, - "total": 27, - "hitRate": 0 - }, - { - "encoding": "windows-1256", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -4.796335743252, - "hits": 0, - "total": 175, - "hitRate": 0 - }, - { - "encoding": "windows-1257", - "confidence": 0, - "language": "et", - "byteLogLikelihood": -4.91533239831, - "hits": 0, - "total": 176, - "hitRate": 0 - }, - { - "encoding": "windows-1258", - "confidence": 0, - "language": "vi", - "byteLogLikelihood": -5.174619785116, - "hits": 0, - "total": 174, - "hitRate": 0 - }, - { - "encoding": "IBM866", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.670016162969, - "hits": 0, - "total": 7, - "hitRate": 0 - }, - { - "encoding": "IBM855", - "confidence": 0, - "language": "sr", - "byteLogLikelihood": -5.983474020054, - "hits": 0, - "total": 96, - "hitRate": 0 - }, - { - "encoding": "macintosh", - "confidence": 0, - "language": "es", - "byteLogLikelihood": -4.948759890378, - "hits": 0, - "total": 94, - "hitRate": 0 - }, - { - "encoding": "x-mac-cyrillic", - "confidence": 0, - "language": "uk", - "byteLogLikelihood": -6.595875032476, - "hits": 0, - "total": 116, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-3", - "confidence": 0, - "language": "mt", - "byteLogLikelihood": -5.105945473901, - "hits": 0, - "total": 170, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-4", - "confidence": 0, - "language": "lv", - "byteLogLikelihood": -5.182298321669, - "hits": 0, - "total": 176, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-13", - "confidence": 0, - "language": "lt", - "byteLogLikelihood": -5.105602464686, - "hits": 0, - "total": 176, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-14", - "confidence": 0, - "language": "cy", - "byteLogLikelihood": -4.912654885736, - "hits": 0, - "total": 179, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-15", - "confidence": 0, - "language": "de", - "byteLogLikelihood": -4.935090625757, - "hits": 0, - "total": 176, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-16", - "confidence": 0, - "language": "ro", - "byteLogLikelihood": -5.206584689041, - "hits": 0, - "total": 179, - "hitRate": 0 - }, - { - "encoding": "CP850", - "confidence": 0, - "language": "es", - "byteLogLikelihood": -4.948759890378, - "hits": 0, - "total": 92, - "hitRate": 0 - }, - { - "encoding": "CP852", - "confidence": 0, - "language": "pl", - "byteLogLikelihood": -5.087596335232, - "hits": 0, - "total": 94, - "hitRate": 0 - } - ] - }, - { - "expected": { - "encoding": "KOI8-U", - "language": "uk" - }, - "predicted": { - "encoding": "KOI8-U", - "confidence": 32, - "language": "uk", - "byteLogLikelihood": -3.34369756932, - "hits": 19, - "total": 177, - "hitRate": 0.10734463276836158 - }, - "encodingExact": true, - "encodingEquivalent": false, - "encodingCorrect": true, - "languageCorrect": true, - "tiedAtTop": 1, - "candidates": [ - { - "encoding": "KOI8-U", - "confidence": 32, - "language": "uk", - "byteLogLikelihood": -3.34369756932, - "hits": 19, - "total": 177, - "hitRate": 0.10734463276836158 - }, - { - "encoding": "KOI8-R", - "confidence": 17, - "language": "ru", - "byteLogLikelihood": -3.510012695801, - "hits": 10, - "total": 172, - "hitRate": 0.05813953488372093 - }, - { - "encoding": "windows-874", - "confidence": 11, - "language": "th", - "byteLogLikelihood": -4.843281209678, - "hits": 6, - "total": 163, - "hitRate": 0.03680981595092025 - }, - { - "encoding": "ISO-8859-7", - "confidence": 8, - "language": "el", - "byteLogLikelihood": -5.876007286158, - "hits": 5, - "total": 168, - "hitRate": 0.02976190476190476 - }, - { - "encoding": "windows-1253", - "confidence": 8, - "language": "el", - "byteLogLikelihood": -5.876007286158, - "hits": 5, - "total": 168, - "hitRate": 0.02976190476190476 - }, - { - "encoding": "ISO-8859-1", - "confidence": 1, - "language": "en", - "byteLogLikelihood": -4.915420747009, - "hits": 1, - "total": 168, - "hitRate": 0.005952380952380952 - }, - { - "encoding": "ISO-8859-5", - "confidence": 1, - "language": "ru", - "byteLogLikelihood": -5.626926512473, - "hits": 1, - "total": 177, - "hitRate": 0.005649717514124294 - }, - { - "encoding": "ISO-8859-6", - "confidence": 1, - "language": "ar", - "byteLogLikelihood": -4.726706027838, - "hits": 1, - "total": 170, - "hitRate": 0.0058823529411764705 - }, - { - "encoding": "windows-1252", - "confidence": 1, - "language": "en", - "byteLogLikelihood": -4.915420747009, - "hits": 1, - "total": 168, - "hitRate": 0.005952380952380952 - }, - { - "encoding": "windows-1256", - "confidence": 1, - "language": "ar", - "byteLogLikelihood": -4.693044688745, - "hits": 1, - "total": 168, - "hitRate": 0.005952380952380952 - }, - { - "encoding": "ISO-8859-10", - "confidence": 1, - "language": "is", - "byteLogLikelihood": -5.128376292359, - "hits": 1, - "total": 177, - "hitRate": 0.005649717514124294 - }, - { - "encoding": "ISO-8859-2", - "confidence": 0, - "language": "pl", - "byteLogLikelihood": -5.087596335232, - "hits": 0, - "total": 176, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-8", - "confidence": 0, - "language": "he", - "byteLogLikelihood": -5.883441366246, - "hits": 0, - "total": 7, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-9", - "confidence": 0, - "language": "tr", - "byteLogLikelihood": -5.055144062354, - "hits": 0, - "total": 167, - "hitRate": 0 - }, - { - "encoding": "windows-1250", - "confidence": 0, - "language": "pl", - "byteLogLikelihood": -5.087596335232, - "hits": 0, - "total": 168, - "hitRate": 0 - }, - { - "encoding": "windows-1251", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.295907791508, - "hits": 0, - "total": 172, - "hitRate": 0 - }, - { - "encoding": "windows-1254", - "confidence": 0, - "language": "tr", - "byteLogLikelihood": -5.055144062354, - "hits": 0, - "total": 167, - "hitRate": 0 - }, - { - "encoding": "windows-1255", - "confidence": 0, - "language": "he", - "byteLogLikelihood": -5.883441366246, - "hits": 0, - "total": 27, - "hitRate": 0 - }, - { - "encoding": "windows-1257", - "confidence": 0, - "language": "et", - "byteLogLikelihood": -4.922686041886, - "hits": 0, - "total": 168, - "hitRate": 0 - }, - { - "encoding": "windows-1258", - "confidence": 0, - "language": "vi", - "byteLogLikelihood": -5.213223244884, - "hits": 0, - "total": 164, - "hitRate": 0 - }, - { - "encoding": "IBM866", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.582632026409, - "hits": 0, - "total": 22, - "hitRate": 0 - }, - { - "encoding": "IBM855", - "confidence": 0, - "language": "sr", - "byteLogLikelihood": -5.922515418323, - "hits": 0, - "total": 94, - "hitRate": 0 - }, - { - "encoding": "macintosh", - "confidence": 0, - "language": "es", - "byteLogLikelihood": -4.948759890378, - "hits": 0, - "total": 89, - "hitRate": 0 - }, - { - "encoding": "x-mac-cyrillic", - "confidence": 0, - "language": "uk", - "byteLogLikelihood": -6.589678128375, - "hits": 0, - "total": 117, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-3", - "confidence": 0, - "language": "mt", - "byteLogLikelihood": -5.105945473901, - "hits": 0, - "total": 175, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-4", - "confidence": 0, - "language": "lv", - "byteLogLikelihood": -5.19295685089, - "hits": 0, - "total": 176, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-13", - "confidence": 0, - "language": "lt", - "byteLogLikelihood": -5.110283442945, - "hits": 0, - "total": 168, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-14", - "confidence": 0, - "language": "cy", - "byteLogLikelihood": -4.912654885736, - "hits": 0, - "total": 177, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-15", - "confidence": 0, - "language": "es", - "byteLogLikelihood": -4.944199711559, - "hits": 0, - "total": 176, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-16", - "confidence": 0, - "language": "ro", - "byteLogLikelihood": -5.192994752161, - "hits": 0, - "total": 177, - "hitRate": 0 - }, - { - "encoding": "CP850", - "confidence": 0, - "language": "es", - "byteLogLikelihood": -4.948759890378, - "hits": 0, - "total": 92, - "hitRate": 0 - }, - { - "encoding": "CP852", - "confidence": 0, - "language": "pl", - "byteLogLikelihood": -5.087596335232, - "hits": 0, - "total": 94, - "hitRate": 0 - } - ] - }, - { - "expected": { - "encoding": "macintosh", - "language": "de" - }, - "predicted": { - "encoding": "macintosh", - "confidence": 73, - "language": "de", - "byteLogLikelihood": -3.169712077519, - "hits": 53, - "total": 216, - "hitRate": 0.24537037037037038 - }, - "encodingExact": true, - "encodingEquivalent": false, - "encodingCorrect": true, - "languageCorrect": true, - "tiedAtTop": 1, - "candidates": [ - { - "encoding": "macintosh", - "confidence": 73, - "language": "de", - "byteLogLikelihood": -3.169712077519, - "hits": 53, - "total": 216, - "hitRate": 0.24537037037037038 - }, - { - "encoding": "ISO-8859-1", - "confidence": 74, - "language": "de", - "byteLogLikelihood": -5.003946305945, - "hits": 53, - "total": 214, - "hitRate": 0.24766355140186916 - }, - { - "encoding": "ISO-8859-15", - "confidence": 74, - "language": "de", - "byteLogLikelihood": -5.003946305945, - "hits": 53, - "total": 214, - "hitRate": 0.24766355140186916 - }, - { - "encoding": "windows-1252", - "confidence": 70, - "language": "de", - "byteLogLikelihood": -5.003946305945, - "hits": 51, - "total": 216, - "hitRate": 0.2361111111111111 - }, - { - "encoding": "CP850", - "confidence": 69, - "language": "de", - "byteLogLikelihood": -5.003946305945, - "hits": 50, - "total": 216, - "hitRate": 0.23148148148148148 - }, - { - "encoding": "ISO-8859-14", - "confidence": 22, - "language": "cy", - "byteLogLikelihood": -4.912654885736, - "hits": 16, - "total": 214, - "hitRate": 0.07476635514018691 - }, - { - "encoding": "ISO-8859-2", - "confidence": 15, - "language": "ro", - "byteLogLikelihood": -5.176149732574, - "hits": 11, - "total": 214, - "hitRate": 0.0514018691588785 - }, - { - "encoding": "windows-1250", - "confidence": 15, - "language": "ro", - "byteLogLikelihood": -5.176149732574, - "hits": 11, - "total": 216, - "hitRate": 0.05092592592592592 - }, - { - "encoding": "ISO-8859-9", - "confidence": 14, - "language": "tr", - "byteLogLikelihood": -5.075173815234, - "hits": 10, - "total": 214, - "hitRate": 0.04672897196261682 - }, - { - "encoding": "windows-1254", - "confidence": 12, - "language": "tr", - "byteLogLikelihood": -5.075173815234, - "hits": 9, - "total": 216, - "hitRate": 0.041666666666666664 - }, - { - "encoding": "ISO-8859-16", - "confidence": 12, - "language": "ro", - "byteLogLikelihood": -5.220355825078, - "hits": 9, - "total": 214, - "hitRate": 0.04205607476635514 - }, - { - "encoding": "windows-1257", - "confidence": 11, - "language": "lv", - "byteLogLikelihood": -5.19295685089, - "hits": 8, - "total": 214, - "hitRate": 0.037383177570093455 - }, - { - "encoding": "ISO-8859-4", - "confidence": 11, - "language": "lv", - "byteLogLikelihood": -5.19295685089, - "hits": 8, - "total": 214, - "hitRate": 0.037383177570093455 - }, - { - "encoding": "windows-1258", - "confidence": 5, - "language": "vi", - "byteLogLikelihood": -5.497168225293, - "hits": 4, - "total": 214, - "hitRate": 0.018691588785046728 - }, - { - "encoding": "ISO-8859-3", - "confidence": 5, - "language": "mt", - "byteLogLikelihood": -5.105945473901, - "hits": 4, - "total": 214, - "hitRate": 0.018691588785046728 - }, - { - "encoding": "CP852", - "confidence": 5, - "language": "pl", - "byteLogLikelihood": -5.087596335232, - "hits": 4, - "total": 216, - "hitRate": 0.018518518518518517 - }, - { - "encoding": "ISO-8859-10", - "confidence": 4, - "language": "is", - "byteLogLikelihood": -5.204006687077, - "hits": 3, - "total": 214, - "hitRate": 0.014018691588785047 - }, - { - "encoding": "ISO-8859-13", - "confidence": 2, - "language": "lt", - "byteLogLikelihood": -5.123963979403, - "hits": 2, - "total": 214, - "hitRate": 0.009345794392523364 - }, - { - "encoding": "ISO-8859-5", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.692083742507, - "hits": 0, - "total": 215, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-6", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -6.113682179832, - "hits": 0, - "total": 214, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-7", - "confidence": 0, - "language": "el", - "byteLogLikelihood": -6.120297418951, - "hits": 0, - "total": 214, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-8", - "confidence": 0, - "language": "he", - "byteLogLikelihood": -5.932245187448, - "hits": 0, - "total": 214, - "hitRate": 0 - }, - { - "encoding": "windows-1251", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.692083742507, - "hits": 0, - "total": 216, - "hitRate": 0 - }, - { - "encoding": "windows-1253", - "confidence": 0, - "language": "el", - "byteLogLikelihood": -6.120297418951, - "hits": 0, - "total": 214, - "hitRate": 0 - }, - { - "encoding": "windows-1255", - "confidence": 0, - "language": "he", - "byteLogLikelihood": -5.932245187448, - "hits": 0, - "total": 214, - "hitRate": 0 - }, - { - "encoding": "windows-1256", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -6.113682179832, - "hits": 0, - "total": 216, - "hitRate": 0 - }, - { - "encoding": "windows-874", - "confidence": 0, - "language": "th", - "byteLogLikelihood": -5.661807706795, - "hits": 0, - "total": 215, - "hitRate": 0 - }, - { - "encoding": "KOI8-R", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.692083742507, - "hits": 0, - "total": 214, - "hitRate": 0 - }, - { - "encoding": "KOI8-U", - "confidence": 0, - "language": "uk", - "byteLogLikelihood": -6.534754518494, - "hits": 0, - "total": 215, - "hitRate": 0 - }, - { - "encoding": "IBM866", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.345510152227, - "hits": 0, - "total": 216, - "hitRate": 0 - }, - { - "encoding": "IBM855", - "confidence": 0, - "language": "sr", - "byteLogLikelihood": -6.337519079447, - "hits": 0, - "total": 216, - "hitRate": 0 - }, - { - "encoding": "x-mac-cyrillic", - "confidence": 0, - "language": "uk", - "byteLogLikelihood": -6.650279048587, - "hits": 0, - "total": 216, - "hitRate": 0 - } - ] - }, - { - "expected": { - "encoding": "macintosh", - "language": "es" - }, - "predicted": { - "encoding": "macintosh", - "confidence": 61, - "language": "es", - "byteLogLikelihood": -3.834657935767, - "hits": 41, - "total": 200, - "hitRate": 0.205 - }, - "encodingExact": true, - "encodingEquivalent": false, - "encodingCorrect": true, - "languageCorrect": true, - "tiedAtTop": 1, - "candidates": [ - { - "encoding": "macintosh", - "confidence": 61, - "language": "es", - "byteLogLikelihood": -3.834657935767, - "hits": 41, - "total": 200, - "hitRate": 0.205 - }, - { - "encoding": "ISO-8859-1", - "confidence": 58, - "language": "es", - "byteLogLikelihood": -4.948759890378, - "hits": 39, - "total": 199, - "hitRate": 0.19597989949748743 - }, - { - "encoding": "windows-1252", - "confidence": 58, - "language": "es", - "byteLogLikelihood": -4.948759890378, - "hits": 39, - "total": 199, - "hitRate": 0.19597989949748743 - }, - { - "encoding": "ISO-8859-15", - "confidence": 58, - "language": "es", - "byteLogLikelihood": -4.948759890378, - "hits": 39, - "total": 199, - "hitRate": 0.19597989949748743 - }, - { - "encoding": "CP850", - "confidence": 58, - "language": "es", - "byteLogLikelihood": -4.948759890378, - "hits": 39, - "total": 200, - "hitRate": 0.195 - }, - { - "encoding": "windows-1257", - "confidence": 25, - "language": "lv", - "byteLogLikelihood": -5.19295685089, - "hits": 17, - "total": 199, - "hitRate": 0.08542713567839195 - }, - { - "encoding": "ISO-8859-4", - "confidence": 25, - "language": "lv", - "byteLogLikelihood": -5.19295685089, - "hits": 17, - "total": 199, - "hitRate": 0.08542713567839195 - }, - { - "encoding": "ISO-8859-13", - "confidence": 19, - "language": "lt", - "byteLogLikelihood": -5.123963979403, - "hits": 13, - "total": 199, - "hitRate": 0.06532663316582915 - }, - { - "encoding": "ISO-8859-14", - "confidence": 16, - "language": "cy", - "byteLogLikelihood": -4.912654885736, - "hits": 11, - "total": 199, - "hitRate": 0.05527638190954774 - }, - { - "encoding": "ISO-8859-2", - "confidence": 15, - "language": "ro", - "byteLogLikelihood": -5.176149732574, - "hits": 10, - "total": 199, - "hitRate": 0.05025125628140704 - }, - { - "encoding": "windows-1250", - "confidence": 15, - "language": "ro", - "byteLogLikelihood": -5.176149732574, - "hits": 10, - "total": 199, - "hitRate": 0.05025125628140704 - }, - { - "encoding": "ISO-8859-16", - "confidence": 15, - "language": "ro", - "byteLogLikelihood": -5.220355825078, - "hits": 10, - "total": 199, - "hitRate": 0.05025125628140704 - }, - { - "encoding": "ISO-8859-9", - "confidence": 7, - "language": "tr", - "byteLogLikelihood": -5.075173815234, - "hits": 5, - "total": 199, - "hitRate": 0.02512562814070352 - }, - { - "encoding": "windows-1254", - "confidence": 7, - "language": "tr", - "byteLogLikelihood": -5.075173815234, - "hits": 5, - "total": 199, - "hitRate": 0.02512562814070352 - }, - { - "encoding": "windows-1258", - "confidence": 7, - "language": "vi", - "byteLogLikelihood": -5.497168225293, - "hits": 5, - "total": 199, - "hitRate": 0.02512562814070352 - }, - { - "encoding": "CP852", - "confidence": 7, - "language": "pl", - "byteLogLikelihood": -5.087596335232, - "hits": 5, - "total": 200, - "hitRate": 0.025 - }, - { - "encoding": "ISO-8859-10", - "confidence": 4, - "language": "is", - "byteLogLikelihood": -5.204006687077, - "hits": 3, - "total": 199, - "hitRate": 0.01507537688442211 - }, - { - "encoding": "ISO-8859-5", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.692083742507, - "hits": 0, - "total": 199, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-6", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -6.113682179832, - "hits": 0, - "total": 199, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-7", - "confidence": 0, - "language": "el", - "byteLogLikelihood": -6.120297418951, - "hits": 0, - "total": 199, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-8", - "confidence": 0, - "language": "he", - "byteLogLikelihood": -5.932245187448, - "hits": 0, - "total": 199, - "hitRate": 0 - }, - { - "encoding": "windows-1251", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.692083742507, - "hits": 0, - "total": 199, - "hitRate": 0 - }, - { - "encoding": "windows-1253", - "confidence": 0, - "language": "el", - "byteLogLikelihood": -6.120297418951, - "hits": 0, - "total": 199, - "hitRate": 0 - }, - { - "encoding": "windows-1255", - "confidence": 0, - "language": "he", - "byteLogLikelihood": -5.932245187448, - "hits": 0, - "total": 199, - "hitRate": 0 - }, - { - "encoding": "windows-1256", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -6.113682179832, - "hits": 0, - "total": 199, - "hitRate": 0 - }, - { - "encoding": "windows-874", - "confidence": 0, - "language": "th", - "byteLogLikelihood": -6.061456918928, - "hits": 0, - "total": 199, - "hitRate": 0 - }, - { - "encoding": "KOI8-R", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.692083742507, - "hits": 0, - "total": 199, - "hitRate": 0 - }, - { - "encoding": "KOI8-U", - "confidence": 0, - "language": "uk", - "byteLogLikelihood": -6.650279048587, - "hits": 0, - "total": 199, - "hitRate": 0 - }, - { - "encoding": "IBM866", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.692083742507, - "hits": 0, - "total": 200, - "hitRate": 0 - }, - { - "encoding": "IBM855", - "confidence": 0, - "language": "sr", - "byteLogLikelihood": -5.624741392945, - "hits": 0, - "total": 200, - "hitRate": 0 - }, - { - "encoding": "x-mac-cyrillic", - "confidence": 0, - "language": "uk", - "byteLogLikelihood": -6.303705458307, - "hits": 0, - "total": 200, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-3", - "confidence": 0, - "language": "mt", - "byteLogLikelihood": -5.105945473901, - "hits": 0, - "total": 199, - "hitRate": 0 - } - ] - }, - { - "expected": { - "encoding": "macintosh", - "language": "fr" - }, - "predicted": { - "encoding": "macintosh", - "confidence": 77, - "language": "fr", - "byteLogLikelihood": -2.06619631493, - "hits": 59, - "total": 228, - "hitRate": 0.25877192982456143 - }, - "encodingExact": true, - "encodingEquivalent": false, - "encodingCorrect": true, - "languageCorrect": true, - "tiedAtTop": 1, - "candidates": [ - { - "encoding": "macintosh", - "confidence": 77, - "language": "fr", - "byteLogLikelihood": -2.06619631493, - "hits": 59, - "total": 228, - "hitRate": 0.25877192982456143 - }, - { - "encoding": "ISO-8859-1", - "confidence": 75, - "language": "fr", - "byteLogLikelihood": -5.010635294096, - "hits": 56, - "total": 224, - "hitRate": 0.25 - }, - { - "encoding": "ISO-8859-15", - "confidence": 75, - "language": "fr", - "byteLogLikelihood": -5.010635294096, - "hits": 56, - "total": 224, - "hitRate": 0.25 - }, - { - "encoding": "windows-1252", - "confidence": 71, - "language": "fr", - "byteLogLikelihood": -5.010635294096, - "hits": 54, - "total": 228, - "hitRate": 0.23684210526315788 - }, - { - "encoding": "CP850", - "confidence": 71, - "language": "fr", - "byteLogLikelihood": -5.010635294096, - "hits": 54, - "total": 228, - "hitRate": 0.23684210526315788 - }, - { - "encoding": "ISO-8859-2", - "confidence": 12, - "language": "ro", - "byteLogLikelihood": -5.176149732574, - "hits": 9, - "total": 224, - "hitRate": 0.04017857142857143 - }, - { - "encoding": "ISO-8859-10", - "confidence": 12, - "language": "is", - "byteLogLikelihood": -5.204006687077, - "hits": 9, - "total": 224, - "hitRate": 0.04017857142857143 - }, - { - "encoding": "ISO-8859-16", - "confidence": 12, - "language": "ro", - "byteLogLikelihood": -5.220355825078, - "hits": 9, - "total": 224, - "hitRate": 0.04017857142857143 - }, - { - "encoding": "windows-1250", - "confidence": 11, - "language": "ro", - "byteLogLikelihood": -5.176149732574, - "hits": 9, - "total": 228, - "hitRate": 0.039473684210526314 - }, - { - "encoding": "ISO-8859-4", - "confidence": 9, - "language": "lv", - "byteLogLikelihood": -5.19295685089, - "hits": 7, - "total": 224, - "hitRate": 0.03125 - }, - { - "encoding": "ISO-8859-3", - "confidence": 8, - "language": "mt", - "byteLogLikelihood": -5.105945473901, - "hits": 6, - "total": 224, - "hitRate": 0.026785714285714284 - }, - { - "encoding": "windows-1257", - "confidence": 7, - "language": "lv", - "byteLogLikelihood": -5.19295685089, - "hits": 6, - "total": 228, - "hitRate": 0.02631578947368421 - }, - { - "encoding": "CP852", - "confidence": 7, - "language": "pl", - "byteLogLikelihood": -5.087596335232, - "hits": 6, - "total": 228, - "hitRate": 0.02631578947368421 - }, - { - "encoding": "ISO-8859-9", - "confidence": 6, - "language": "tr", - "byteLogLikelihood": -5.075173815234, - "hits": 5, - "total": 224, - "hitRate": 0.022321428571428572 - }, - { - "encoding": "windows-1254", - "confidence": 6, - "language": "tr", - "byteLogLikelihood": -5.075173815234, - "hits": 5, - "total": 224, - "hitRate": 0.022321428571428572 - }, - { - "encoding": "windows-1258", - "confidence": 6, - "language": "vi", - "byteLogLikelihood": -5.497168225293, - "hits": 5, - "total": 224, - "hitRate": 0.022321428571428572 - }, - { - "encoding": "ISO-8859-13", - "confidence": 5, - "language": "lt", - "byteLogLikelihood": -5.123963979403, - "hits": 4, - "total": 224, - "hitRate": 0.017857142857142856 - }, - { - "encoding": "ISO-8859-14", - "confidence": 4, - "language": "cy", - "byteLogLikelihood": -4.912654885736, - "hits": 3, - "total": 224, - "hitRate": 0.013392857142857142 - }, - { - "encoding": "ISO-8859-5", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.692083742507, - "hits": 0, - "total": 224, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-6", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -6.113682179832, - "hits": 0, - "total": 224, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-7", - "confidence": 0, - "language": "el", - "byteLogLikelihood": -6.120297418951, - "hits": 0, - "total": 224, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-8", - "confidence": 0, - "language": "he", - "byteLogLikelihood": -5.932245187448, - "hits": 0, - "total": 224, - "hitRate": 0 - }, - { - "encoding": "windows-1251", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.692083742507, - "hits": 0, - "total": 228, - "hitRate": 0 - }, - { - "encoding": "windows-1253", - "confidence": 0, - "language": "el", - "byteLogLikelihood": -6.120297418951, - "hits": 0, - "total": 224, - "hitRate": 0 - }, - { - "encoding": "windows-1255", - "confidence": 0, - "language": "he", - "byteLogLikelihood": -5.932245187448, - "hits": 0, - "total": 224, - "hitRate": 0 - }, - { - "encoding": "windows-1256", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -6.113682179832, - "hits": 0, - "total": 228, - "hitRate": 0 - }, - { - "encoding": "windows-874", - "confidence": 0, - "language": "th", - "byteLogLikelihood": -6.061456918928, - "hits": 0, - "total": 224, - "hitRate": 0 - }, - { - "encoding": "KOI8-R", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.692083742507, - "hits": 0, - "total": 224, - "hitRate": 0 - }, - { - "encoding": "KOI8-U", - "confidence": 0, - "language": "uk", - "byteLogLikelihood": -6.650279048587, - "hits": 0, - "total": 224, - "hitRate": 0 - }, - { - "encoding": "IBM866", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.998936561947, - "hits": 0, - "total": 228, - "hitRate": 0 - }, - { - "encoding": "IBM855", - "confidence": 0, - "language": "sr", - "byteLogLikelihood": -3.576182148392, - "hits": 0, - "total": 228, - "hitRate": 0 - }, - { - "encoding": "x-mac-cyrillic", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.998936561947, - "hits": 0, - "total": 228, - "hitRate": 0 - } - ] - }, - { - "expected": { - "encoding": "windows-1250", - "language": "cs" - }, - "predicted": { - "encoding": "ISO-8859-2", - "confidence": 30, - "language": "cs", - "byteLogLikelihood": -3.429159108442, - "hits": 13, - "total": 126, - "hitRate": 0.10317460317460317 - }, - "encodingExact": false, - "encodingEquivalent": true, - "encodingCorrect": true, - "languageCorrect": true, - "tiedAtTop": 2, - "candidates": [ - { - "encoding": "ISO-8859-2", - "confidence": 30, - "language": "cs", - "byteLogLikelihood": -3.429159108442, - "hits": 13, - "total": 126, - "hitRate": 0.10317460317460317 - }, - { - "encoding": "windows-1250", - "confidence": 30, - "language": "cs", - "byteLogLikelihood": -3.429159108442, - "hits": 13, - "total": 126, - "hitRate": 0.10317460317460317 - }, - { - "encoding": "ISO-8859-1", - "confidence": 11, - "language": "pt", - "byteLogLikelihood": -4.5670392286, - "hits": 5, - "total": 126, - "hitRate": 0.03968253968253968 - }, - { - "encoding": "windows-1252", - "confidence": 11, - "language": "pt", - "byteLogLikelihood": -4.5670392286, - "hits": 5, - "total": 126, - "hitRate": 0.03968253968253968 - }, - { - "encoding": "CP852", - "confidence": 11, - "language": "pl", - "byteLogLikelihood": -5.087596335232, - "hits": 5, - "total": 126, - "hitRate": 0.03968253968253968 - }, - { - "encoding": "windows-1257", - "confidence": 7, - "language": "lt", - "byteLogLikelihood": -4.997937219301, - "hits": 3, - "total": 126, - "hitRate": 0.023809523809523808 - }, - { - "encoding": "windows-1258", - "confidence": 7, - "language": "vi", - "byteLogLikelihood": -4.506724065575, - "hits": 3, - "total": 126, - "hitRate": 0.023809523809523808 - }, - { - "encoding": "macintosh", - "confidence": 7, - "language": "fr", - "byteLogLikelihood": -5.010635294096, - "hits": 3, - "total": 124, - "hitRate": 0.024193548387096774 - }, - { - "encoding": "ISO-8859-13", - "confidence": 7, - "language": "lt", - "byteLogLikelihood": -4.997937219301, - "hits": 3, - "total": 126, - "hitRate": 0.023809523809523808 - }, - { - "encoding": "ISO-8859-15", - "confidence": 7, - "language": "fr", - "byteLogLikelihood": -4.081579721495, - "hits": 3, - "total": 126, - "hitRate": 0.023809523809523808 - }, - { - "encoding": "ISO-8859-16", - "confidence": 7, - "language": "ro", - "byteLogLikelihood": -5.220355825078, - "hits": 3, - "total": 126, - "hitRate": 0.023809523809523808 - }, - { - "encoding": "CP850", - "confidence": 7, - "language": "fr", - "byteLogLikelihood": -5.010635294096, - "hits": 3, - "total": 125, - "hitRate": 0.024 - }, - { - "encoding": "ISO-8859-9", - "confidence": 4, - "language": "tr", - "byteLogLikelihood": -4.849273210708, - "hits": 2, - "total": 126, - "hitRate": 0.015873015873015872 - }, - { - "encoding": "windows-1254", - "confidence": 4, - "language": "tr", - "byteLogLikelihood": -4.849273210708, - "hits": 2, - "total": 126, - "hitRate": 0.015873015873015872 - }, - { - "encoding": "ISO-8859-4", - "confidence": 4, - "language": "lv", - "byteLogLikelihood": -5.129943470839, - "hits": 2, - "total": 126, - "hitRate": 0.015873015873015872 - }, - { - "encoding": "ISO-8859-14", - "confidence": 4, - "language": "cy", - "byteLogLikelihood": -4.912654885736, - "hits": 2, - "total": 126, - "hitRate": 0.015873015873015872 - }, - { - "encoding": "ISO-8859-5", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.254067466067, - "hits": 0, - "total": 125, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-6", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -5.402405269754, - "hits": 0, - "total": 124, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-7", - "confidence": 0, - "language": "el", - "byteLogLikelihood": -3.401446196881, - "hits": 0, - "total": 126, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-8", - "confidence": 0, - "language": "he", - "byteLogLikelihood": -3.467509652199, - "hits": 0, - "total": 125, - "hitRate": 0 - }, - { - "encoding": "windows-1251", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -4.249199684222, - "hits": 0, - "total": 126, - "hitRate": 0 - }, - { - "encoding": "windows-1253", - "confidence": 0, - "language": "el", - "byteLogLikelihood": -3.401446196881, - "hits": 0, - "total": 126, - "hitRate": 0 - }, - { - "encoding": "windows-1255", - "confidence": 0, - "language": "he", - "byteLogLikelihood": -3.467509652199, - "hits": 0, - "total": 125, - "hitRate": 0 - }, - { - "encoding": "windows-1256", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -5.164526575273, - "hits": 0, - "total": 125, - "hitRate": 0 - }, - { - "encoding": "windows-874", - "confidence": 0, - "language": "th", - "byteLogLikelihood": -4.504431122267, - "hits": 0, - "total": 122, - "hitRate": 0 - }, - { - "encoding": "KOI8-R", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.566056982405, - "hits": 0, - "total": 126, - "hitRate": 0 - }, - { - "encoding": "KOI8-U", - "confidence": 0, - "language": "uk", - "byteLogLikelihood": -6.524252288486, - "hits": 0, - "total": 126, - "hitRate": 0 - }, - { - "encoding": "IBM866", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.254067466067, - "hits": 0, - "total": 125, - "hitRate": 0 - }, - { - "encoding": "IBM855", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.108905030169, - "hits": 0, - "total": 125, - "hitRate": 0 - }, - { - "encoding": "x-mac-cyrillic", - "confidence": 0, - "language": "uk", - "byteLogLikelihood": -4.226561011787, - "hits": 0, - "total": 126, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-3", - "confidence": 0, - "language": "mt", - "byteLogLikelihood": -5.105945473901, - "hits": 0, - "total": 126, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-10", - "confidence": 0, - "language": "is", - "byteLogLikelihood": -4.43713857777, - "hits": 0, - "total": 126, - "hitRate": 0 - } - ] - }, - { - "expected": { - "encoding": "windows-1250", - "language": "hu" - }, - "predicted": { - "encoding": "ISO-8859-2", - "confidence": 46, - "language": "hu", - "byteLogLikelihood": -3.161205902203, - "hits": 21, - "total": 136, - "hitRate": 0.15441176470588236 - }, - "encodingExact": false, - "encodingEquivalent": true, - "encodingCorrect": true, - "languageCorrect": true, - "tiedAtTop": 2, - "candidates": [ - { - "encoding": "ISO-8859-2", - "confidence": 46, - "language": "hu", - "byteLogLikelihood": -3.161205902203, - "hits": 21, - "total": 136, - "hitRate": 0.15441176470588236 - }, - { - "encoding": "windows-1250", - "confidence": 46, - "language": "hu", - "byteLogLikelihood": -3.161205902203, - "hits": 21, - "total": 136, - "hitRate": 0.15441176470588236 - }, - { - "encoding": "ISO-8859-1", - "confidence": 17, - "language": "pt", - "byteLogLikelihood": -4.507887190294, - "hits": 8, - "total": 136, - "hitRate": 0.058823529411764705 - }, - { - "encoding": "windows-1252", - "confidence": 17, - "language": "pt", - "byteLogLikelihood": -4.507887190294, - "hits": 8, - "total": 136, - "hitRate": 0.058823529411764705 - }, - { - "encoding": "CP852", - "confidence": 15, - "language": "pl", - "byteLogLikelihood": -5.087596335232, - "hits": 7, - "total": 135, - "hitRate": 0.05185185185185185 - }, - { - "encoding": "ISO-8859-14", - "confidence": 8, - "language": "cy", - "byteLogLikelihood": -4.912654885736, - "hits": 4, - "total": 136, - "hitRate": 0.029411764705882353 - }, - { - "encoding": "macintosh", - "confidence": 6, - "language": "es", - "byteLogLikelihood": -4.948759890378, - "hits": 3, - "total": 135, - "hitRate": 0.022222222222222223 - }, - { - "encoding": "CP850", - "confidence": 6, - "language": "es", - "byteLogLikelihood": -4.948759890378, - "hits": 3, - "total": 134, - "hitRate": 0.022388059701492536 - }, - { - "encoding": "ISO-8859-15", - "confidence": 4, - "language": "fr", - "byteLogLikelihood": -4.274525549305, - "hits": 2, - "total": 136, - "hitRate": 0.014705882352941176 - }, - { - "encoding": "ISO-8859-16", - "confidence": 4, - "language": "ro", - "byteLogLikelihood": -5.220355825078, - "hits": 2, - "total": 136, - "hitRate": 0.014705882352941176 - }, - { - "encoding": "ISO-8859-9", - "confidence": 2, - "language": "tr", - "byteLogLikelihood": -4.5258676709, - "hits": 1, - "total": 136, - "hitRate": 0.007352941176470588 - }, - { - "encoding": "windows-1254", - "confidence": 2, - "language": "tr", - "byteLogLikelihood": -4.5258676709, - "hits": 1, - "total": 136, - "hitRate": 0.007352941176470588 - }, - { - "encoding": "windows-1257", - "confidence": 2, - "language": "et", - "byteLogLikelihood": -4.453831056838, - "hits": 1, - "total": 136, - "hitRate": 0.007352941176470588 - }, - { - "encoding": "ISO-8859-4", - "confidence": 2, - "language": "lv", - "byteLogLikelihood": -5.19295685089, - "hits": 1, - "total": 136, - "hitRate": 0.007352941176470588 - }, - { - "encoding": "ISO-8859-10", - "confidence": 2, - "language": "is", - "byteLogLikelihood": -3.90025153387, - "hits": 1, - "total": 136, - "hitRate": 0.007352941176470588 - }, - { - "encoding": "ISO-8859-13", - "confidence": 2, - "language": "lt", - "byteLogLikelihood": -4.950677184263, - "hits": 1, - "total": 136, - "hitRate": 0.007352941176470588 - }, - { - "encoding": "ISO-8859-5", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.485271956182, - "hits": 0, - "total": 136, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-6", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -5.538035906584, - "hits": 0, - "total": 134, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-7", - "confidence": 0, - "language": "el", - "byteLogLikelihood": -3.430247904624, - "hits": 0, - "total": 136, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-8", - "confidence": 0, - "language": "he", - "byteLogLikelihood": -3.984546441118, - "hits": 0, - "total": 135, - "hitRate": 0 - }, - { - "encoding": "windows-1251", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -4.6300671031, - "hits": 0, - "total": 136, - "hitRate": 0 - }, - { - "encoding": "windows-1253", - "confidence": 0, - "language": "el", - "byteLogLikelihood": -3.430247904624, - "hits": 0, - "total": 136, - "hitRate": 0 - }, - { - "encoding": "windows-1255", - "confidence": 0, - "language": "he", - "byteLogLikelihood": -3.984546441118, - "hits": 0, - "total": 135, - "hitRate": 0 - }, - { - "encoding": "windows-1256", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -5.009772962617, - "hits": 0, - "total": 135, - "hitRate": 0 - }, - { - "encoding": "windows-1258", - "confidence": 0, - "language": "vi", - "byteLogLikelihood": -5.010690688029, - "hits": 0, - "total": 136, - "hitRate": 0 - }, - { - "encoding": "windows-874", - "confidence": 0, - "language": "th", - "byteLogLikelihood": -4.953752719217, - "hits": 0, - "total": 133, - "hitRate": 0 - }, - { - "encoding": "KOI8-R", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.692083742507, - "hits": 0, - "total": 136, - "hitRate": 0 - }, - { - "encoding": "KOI8-U", - "confidence": 0, - "language": "uk", - "byteLogLikelihood": -6.606957349802, - "hits": 0, - "total": 136, - "hitRate": 0 - }, - { - "encoding": "IBM866", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.485271956182, - "hits": 0, - "total": 135, - "hitRate": 0 - }, - { - "encoding": "IBM855", - "confidence": 0, - "language": "sr", - "byteLogLikelihood": -5.100966544791, - "hits": 0, - "total": 136, - "hitRate": 0 - }, - { - "encoding": "x-mac-cyrillic", - "confidence": 0, - "language": "uk", - "byteLogLikelihood": -4.187765411941, - "hits": 0, - "total": 136, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-3", - "confidence": 0, - "language": "mt", - "byteLogLikelihood": -5.105945473901, - "hits": 0, - "total": 136, - "hitRate": 0 - } - ] - }, - { - "expected": { - "encoding": "windows-1250", - "language": "pl" - }, - "predicted": { - "encoding": "windows-1250", - "confidence": 40, - "language": "pl", - "byteLogLikelihood": -3.52910527172, - "hits": 25, - "total": 184, - "hitRate": 0.1358695652173913 - }, - "encodingExact": true, - "encodingEquivalent": false, - "encodingCorrect": true, - "languageCorrect": true, - "tiedAtTop": 1, - "candidates": [ - { - "encoding": "windows-1250", - "confidence": 40, - "language": "pl", - "byteLogLikelihood": -3.52910527172, - "hits": 25, - "total": 184, - "hitRate": 0.1358695652173913 - }, - { - "encoding": "ISO-8859-2", - "confidence": 37, - "language": "pl", - "byteLogLikelihood": -4.297518988235, - "hits": 23, - "total": 184, - "hitRate": 0.125 - }, - { - "encoding": "CP852", - "confidence": 41, - "language": "pl", - "byteLogLikelihood": -5.087596335232, - "hits": 25, - "total": 182, - "hitRate": 0.13736263736263737 - }, - { - "encoding": "ISO-8859-1", - "confidence": 8, - "language": "it", - "byteLogLikelihood": -4.919980925828, - "hits": 5, - "total": 183, - "hitRate": 0.0273224043715847 - }, - { - "encoding": "windows-1252", - "confidence": 8, - "language": "it", - "byteLogLikelihood": -4.919980925828, - "hits": 5, - "total": 183, - "hitRate": 0.0273224043715847 - }, - { - "encoding": "windows-1257", - "confidence": 6, - "language": "et", - "byteLogLikelihood": -4.934473933131, - "hits": 4, - "total": 183, - "hitRate": 0.02185792349726776 - }, - { - "encoding": "windows-1258", - "confidence": 6, - "language": "vi", - "byteLogLikelihood": -5.343135518502, - "hits": 4, - "total": 183, - "hitRate": 0.02185792349726776 - }, - { - "encoding": "ISO-8859-13", - "confidence": 6, - "language": "lt", - "byteLogLikelihood": -5.123963979403, - "hits": 4, - "total": 183, - "hitRate": 0.02185792349726776 - }, - { - "encoding": "ISO-8859-15", - "confidence": 6, - "language": "es", - "byteLogLikelihood": -4.396558412648, - "hits": 4, - "total": 183, - "hitRate": 0.02185792349726776 - }, - { - "encoding": "CP850", - "confidence": 6, - "language": "es", - "byteLogLikelihood": -4.948759890378, - "hits": 4, - "total": 182, - "hitRate": 0.02197802197802198 - }, - { - "encoding": "macintosh", - "confidence": 4, - "language": "es", - "byteLogLikelihood": -4.826691858304, - "hits": 3, - "total": 184, - "hitRate": 0.016304347826086956 - }, - { - "encoding": "ISO-8859-4", - "confidence": 4, - "language": "lv", - "byteLogLikelihood": -4.704684722593, - "hits": 3, - "total": 184, - "hitRate": 0.016304347826086956 - }, - { - "encoding": "ISO-8859-3", - "confidence": 3, - "language": "mt", - "byteLogLikelihood": -5.105945473901, - "hits": 2, - "total": 184, - "hitRate": 0.010869565217391304 - }, - { - "encoding": "ISO-8859-10", - "confidence": 3, - "language": "is", - "byteLogLikelihood": -4.71573455878, - "hits": 2, - "total": 184, - "hitRate": 0.010869565217391304 - }, - { - "encoding": "ISO-8859-16", - "confidence": 3, - "language": "ro", - "byteLogLikelihood": -5.220355825078, - "hits": 2, - "total": 184, - "hitRate": 0.010869565217391304 - }, - { - "encoding": "ISO-8859-9", - "confidence": 1, - "language": "tr", - "byteLogLikelihood": -5.075173815234, - "hits": 1, - "total": 183, - "hitRate": 0.00546448087431694 - }, - { - "encoding": "windows-1254", - "confidence": 1, - "language": "tr", - "byteLogLikelihood": -5.075173815234, - "hits": 1, - "total": 183, - "hitRate": 0.00546448087431694 - }, - { - "encoding": "ISO-8859-14", - "confidence": 1, - "language": "cy", - "byteLogLikelihood": -4.912654885736, - "hits": 1, - "total": 184, - "hitRate": 0.005434782608695652 - }, - { - "encoding": "ISO-8859-5", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.293914971567, - "hits": 0, - "total": 184, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-6", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -6.113682179832, - "hits": 0, - "total": 182, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-7", - "confidence": 0, - "language": "el", - "byteLogLikelihood": -4.848389618517, - "hits": 0, - "total": 184, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-8", - "confidence": 0, - "language": "he", - "byteLogLikelihood": -5.470147067075, - "hits": 0, - "total": 183, - "hitRate": 0 - }, - { - "encoding": "windows-1251", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.300217461931, - "hits": 0, - "total": 183, - "hitRate": 0 - }, - { - "encoding": "windows-1253", - "confidence": 0, - "language": "el", - "byteLogLikelihood": -4.848389618517, - "hits": 0, - "total": 184, - "hitRate": 0 - }, - { - "encoding": "windows-1255", - "confidence": 0, - "language": "he", - "byteLogLikelihood": -5.470147067075, - "hits": 0, - "total": 183, - "hitRate": 0 - }, - { - "encoding": "windows-1256", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -6.113682179832, - "hits": 0, - "total": 182, - "hitRate": 0 - }, - { - "encoding": "windows-874", - "confidence": 0, - "language": "th", - "byteLogLikelihood": -5.163001081631, - "hits": 0, - "total": 183, - "hitRate": 0 - }, - { - "encoding": "KOI8-R", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.538051035716, - "hits": 0, - "total": 183, - "hitRate": 0 - }, - { - "encoding": "KOI8-U", - "confidence": 0, - "language": "uk", - "byteLogLikelihood": -6.496246341796, - "hits": 0, - "total": 183, - "hitRate": 0 - }, - { - "encoding": "IBM866", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.447947678358, - "hits": 0, - "total": 183, - "hitRate": 0 - }, - { - "encoding": "IBM855", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.204348837508, - "hits": 0, - "total": 183, - "hitRate": 0 - }, - { - "encoding": "x-mac-cyrillic", - "confidence": 0, - "language": "uk", - "byteLogLikelihood": -4.955485669412, - "hits": 0, - "total": 184, - "hitRate": 0 - } - ] - }, - { - "expected": { - "encoding": "windows-1250", - "language": "ro" - }, - "predicted": { - "encoding": "ISO-8859-2", - "confidence": 41, - "language": "ro", - "byteLogLikelihood": -2.684539297542, - "hits": 28, - "total": 202, - "hitRate": 0.13861386138613863 - }, - "encodingExact": false, - "encodingEquivalent": true, - "encodingCorrect": true, - "languageCorrect": true, - "tiedAtTop": 2, - "candidates": [ - { - "encoding": "ISO-8859-2", - "confidence": 41, - "language": "ro", - "byteLogLikelihood": -2.684539297542, - "hits": 28, - "total": 202, - "hitRate": 0.13861386138613863 - }, - { - "encoding": "windows-1250", - "confidence": 41, - "language": "ro", - "byteLogLikelihood": -2.684539297542, - "hits": 28, - "total": 202, - "hitRate": 0.13861386138613863 - }, - { - "encoding": "ISO-8859-16", - "confidence": 38, - "language": "ro", - "byteLogLikelihood": -2.700458868498, - "hits": 26, - "total": 202, - "hitRate": 0.12871287128712872 - }, - { - "encoding": "ISO-8859-1", - "confidence": 26, - "language": "it", - "byteLogLikelihood": -4.919980925828, - "hits": 18, - "total": 202, - "hitRate": 0.0891089108910891 - }, - { - "encoding": "windows-1252", - "confidence": 26, - "language": "it", - "byteLogLikelihood": -4.919980925828, - "hits": 18, - "total": 202, - "hitRate": 0.0891089108910891 - }, - { - "encoding": "macintosh", - "confidence": 19, - "language": "fr", - "byteLogLikelihood": -5.010635294096, - "hits": 13, - "total": 198, - "hitRate": 0.06565656565656566 - }, - { - "encoding": "CP850", - "confidence": 15, - "language": "fr", - "byteLogLikelihood": -5.010635294096, - "hits": 10, - "total": 199, - "hitRate": 0.05025125628140704 - }, - { - "encoding": "ISO-8859-15", - "confidence": 14, - "language": "fr", - "byteLogLikelihood": -4.903997266318, - "hits": 10, - "total": 202, - "hitRate": 0.04950495049504951 - }, - { - "encoding": "ISO-8859-3", - "confidence": 13, - "language": "mt", - "byteLogLikelihood": -5.105945473901, - "hits": 9, - "total": 200, - "hitRate": 0.045 - }, - { - "encoding": "ISO-8859-9", - "confidence": 10, - "language": "tr", - "byteLogLikelihood": -5.021854801345, - "hits": 7, - "total": 202, - "hitRate": 0.034653465346534656 - }, - { - "encoding": "windows-1254", - "confidence": 10, - "language": "tr", - "byteLogLikelihood": -5.021854801345, - "hits": 7, - "total": 202, - "hitRate": 0.034653465346534656 - }, - { - "encoding": "windows-1257", - "confidence": 8, - "language": "lv", - "byteLogLikelihood": -4.396820338954, - "hits": 6, - "total": 202, - "hitRate": 0.0297029702970297 - }, - { - "encoding": "CP852", - "confidence": 8, - "language": "pl", - "byteLogLikelihood": -5.087596335232, - "hits": 6, - "total": 201, - "hitRate": 0.029850746268656716 - }, - { - "encoding": "ISO-8859-4", - "confidence": 7, - "language": "lv", - "byteLogLikelihood": -4.936633427031, - "hits": 5, - "total": 202, - "hitRate": 0.024752475247524754 - }, - { - "encoding": "windows-1258", - "confidence": 5, - "language": "vi", - "byteLogLikelihood": -5.177254141958, - "hits": 4, - "total": 202, - "hitRate": 0.019801980198019802 - }, - { - "encoding": "ISO-8859-10", - "confidence": 5, - "language": "is", - "byteLogLikelihood": -5.150687673188, - "hits": 4, - "total": 202, - "hitRate": 0.019801980198019802 - }, - { - "encoding": "ISO-8859-13", - "confidence": 4, - "language": "lt", - "byteLogLikelihood": -4.974278583322, - "hits": 3, - "total": 202, - "hitRate": 0.01485148514851485 - }, - { - "encoding": "ISO-8859-14", - "confidence": 4, - "language": "cy", - "byteLogLikelihood": -4.539421788511, - "hits": 3, - "total": 202, - "hitRate": 0.01485148514851485 - }, - { - "encoding": "ISO-8859-5", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -4.208609169552, - "hits": 0, - "total": 202, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-6", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -4.828974536143, - "hits": 0, - "total": 199, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-7", - "confidence": 0, - "language": "el", - "byteLogLikelihood": -4.33505338151, - "hits": 0, - "total": 202, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-8", - "confidence": 0, - "language": "he", - "byteLogLikelihood": -4.197813655274, - "hits": 0, - "total": 201, - "hitRate": 0 - }, - { - "encoding": "windows-1251", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -4.229886082374, - "hits": 0, - "total": 202, - "hitRate": 0 - }, - { - "encoding": "windows-1253", - "confidence": 0, - "language": "el", - "byteLogLikelihood": -4.33505338151, - "hits": 0, - "total": 202, - "hitRate": 0 - }, - { - "encoding": "windows-1255", - "confidence": 0, - "language": "he", - "byteLogLikelihood": -4.197813655274, - "hits": 0, - "total": 201, - "hitRate": 0 - }, - { - "encoding": "windows-1256", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -4.528215037204, - "hits": 0, - "total": 201, - "hitRate": 0 - }, - { - "encoding": "windows-874", - "confidence": 0, - "language": "th", - "byteLogLikelihood": -5.239455511679, - "hits": 0, - "total": 200, - "hitRate": 0 - }, - { - "encoding": "KOI8-R", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.42548867306, - "hits": 0, - "total": 201, - "hitRate": 0 - }, - { - "encoding": "KOI8-U", - "confidence": 0, - "language": "uk", - "byteLogLikelihood": -6.32130473174, - "hits": 0, - "total": 201, - "hitRate": 0 - }, - { - "encoding": "IBM866", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -4.208609169552, - "hits": 0, - "total": 201, - "hitRate": 0 - }, - { - "encoding": "IBM855", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -4.608648280371, - "hits": 0, - "total": 201, - "hitRate": 0 - }, - { - "encoding": "x-mac-cyrillic", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -4.229886082374, - "hits": 0, - "total": 202, - "hitRate": 0 - } - ] - }, - { - "expected": { - "encoding": "windows-1251", - "language": "ru" - }, - "predicted": { - "encoding": "windows-1251", - "confidence": 41, - "language": "ru", - "byteLogLikelihood": -3.313760777855, - "hits": 25, - "total": 179, - "hitRate": 0.13966480446927373 - }, - "encodingExact": true, - "encodingEquivalent": false, - "encodingCorrect": true, - "languageCorrect": true, - "tiedAtTop": 1, - "candidates": [ - { - "encoding": "windows-1251", - "confidence": 41, - "language": "ru", - "byteLogLikelihood": -3.313760777855, - "hits": 25, - "total": 179, - "hitRate": 0.13966480446927373 - }, - { - "encoding": "x-mac-cyrillic", - "confidence": 34, - "language": "ru", - "byteLogLikelihood": -3.411211853364, - "hits": 20, - "total": 175, - "hitRate": 0.11428571428571428 - }, - { - "encoding": "IBM855", - "confidence": 9, - "language": "sr", - "byteLogLikelihood": -5.604243216214, - "hits": 5, - "total": 164, - "hitRate": 0.03048780487804878 - }, - { - "encoding": "KOI8-U", - "confidence": 5, - "language": "uk", - "byteLogLikelihood": -6.290472763796, - "hits": 3, - "total": 179, - "hitRate": 0.01675977653631285 - }, - { - "encoding": "ISO-8859-8", - "confidence": 3, - "language": "he", - "byteLogLikelihood": -3.941595102268, - "hits": 2, - "total": 167, - "hitRate": 0.011976047904191617 - }, - { - "encoding": "windows-1255", - "confidence": 3, - "language": "he", - "byteLogLikelihood": -3.941595102268, - "hits": 2, - "total": 167, - "hitRate": 0.011976047904191617 - }, - { - "encoding": "windows-1256", - "confidence": 1, - "language": "ar", - "byteLogLikelihood": -5.552676456081, - "hits": 1, - "total": 165, - "hitRate": 0.006060606060606061 - }, - { - "encoding": "KOI8-R", - "confidence": 1, - "language": "ru", - "byteLogLikelihood": -6.346028593552, - "hits": 1, - "total": 179, - "hitRate": 0.00558659217877095 - }, - { - "encoding": "ISO-8859-14", - "confidence": 1, - "language": "cy", - "byteLogLikelihood": -4.724449359889, - "hits": 1, - "total": 179, - "hitRate": 0.00558659217877095 - }, - { - "encoding": "ISO-8859-1", - "confidence": 0, - "language": "sv", - "byteLogLikelihood": -4.665227236998, - "hits": 0, - "total": 179, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-2", - "confidence": 0, - "language": "cs", - "byteLogLikelihood": -4.845647442888, - "hits": 0, - "total": 176, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-5", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.054854043559, - "hits": 0, - "total": 177, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-6", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -4.827625181516, - "hits": 0, - "total": 129, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-7", - "confidence": 0, - "language": "el", - "byteLogLikelihood": -4.209243802684, - "hits": 0, - "total": 176, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-9", - "confidence": 0, - "language": "tr", - "byteLogLikelihood": -4.950903003627, - "hits": 0, - "total": 179, - "hitRate": 0 - }, - { - "encoding": "windows-1250", - "confidence": 0, - "language": "cs", - "byteLogLikelihood": -4.845647442888, - "hits": 0, - "total": 176, - "hitRate": 0 - }, - { - "encoding": "windows-1252", - "confidence": 0, - "language": "sv", - "byteLogLikelihood": -4.665227236998, - "hits": 0, - "total": 179, - "hitRate": 0 - }, - { - "encoding": "windows-1253", - "confidence": 0, - "language": "el", - "byteLogLikelihood": -4.209243802684, - "hits": 0, - "total": 176, - "hitRate": 0 - }, - { - "encoding": "windows-1254", - "confidence": 0, - "language": "tr", - "byteLogLikelihood": -4.950903003627, - "hits": 0, - "total": 179, - "hitRate": 0 - }, - { - "encoding": "windows-1257", - "confidence": 0, - "language": "lv", - "byteLogLikelihood": -4.61521723683, - "hits": 0, - "total": 176, - "hitRate": 0 - }, - { - "encoding": "windows-1258", - "confidence": 0, - "language": "vi", - "byteLogLikelihood": -4.899487478125, - "hits": 0, - "total": 175, - "hitRate": 0 - }, - { - "encoding": "windows-874", - "confidence": 0, - "language": "th", - "byteLogLikelihood": -5.446015416921, - "hits": 0, - "total": 88, - "hitRate": 0 - }, - { - "encoding": "IBM866", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.059444422239, - "hits": 0, - "total": 167, - "hitRate": 0 - }, - { - "encoding": "macintosh", - "confidence": 0, - "language": "es", - "byteLogLikelihood": -4.948759890378, - "hits": 0, - "total": 150, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-3", - "confidence": 0, - "language": "mt", - "byteLogLikelihood": -4.904224209153, - "hits": 0, - "total": 172, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-4", - "confidence": 0, - "language": "lv", - "byteLogLikelihood": -4.79659105312, - "hits": 0, - "total": 176, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-10", - "confidence": 0, - "language": "is", - "byteLogLikelihood": -4.939249573759, - "hits": 0, - "total": 179, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-13", - "confidence": 0, - "language": "lt", - "byteLogLikelihood": -4.66408545306, - "hits": 0, - "total": 176, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-15", - "confidence": 0, - "language": "fr", - "byteLogLikelihood": -4.760478683076, - "hits": 0, - "total": 179, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-16", - "confidence": 0, - "language": "ro", - "byteLogLikelihood": -4.970632247101, - "hits": 0, - "total": 179, - "hitRate": 0 - }, - { - "encoding": "CP850", - "confidence": 0, - "language": "es", - "byteLogLikelihood": -4.948759890378, - "hits": 0, - "total": 136, - "hitRate": 0 - }, - { - "encoding": "CP852", - "confidence": 0, - "language": "pl", - "byteLogLikelihood": -5.087596335232, - "hits": 0, - "total": 155, - "hitRate": 0 - } - ] - }, - { - "expected": { - "encoding": "windows-1252", - "language": "da" - }, - "predicted": { - "encoding": "ISO-8859-1", - "confidence": 52, - "language": "da", - "byteLogLikelihood": -3.146558879633, - "hits": 21, - "total": 120, - "hitRate": 0.175 - }, - "encodingExact": false, - "encodingEquivalent": true, - "encodingCorrect": true, - "languageCorrect": true, - "tiedAtTop": 2, - "candidates": [ - { - "encoding": "ISO-8859-1", - "confidence": 52, - "language": "da", - "byteLogLikelihood": -3.146558879633, - "hits": 21, - "total": 120, - "hitRate": 0.175 - }, - { - "encoding": "windows-1252", - "confidence": 52, - "language": "da", - "byteLogLikelihood": -3.146558879633, - "hits": 21, - "total": 120, - "hitRate": 0.175 - }, - { - "encoding": "macintosh", - "confidence": 30, - "language": "de", - "byteLogLikelihood": -5.003946305945, - "hits": 12, - "total": 120, - "hitRate": 0.1 - }, - { - "encoding": "ISO-8859-15", - "confidence": 30, - "language": "de", - "byteLogLikelihood": -5.003946305945, - "hits": 12, - "total": 120, - "hitRate": 0.1 - }, - { - "encoding": "CP850", - "confidence": 30, - "language": "de", - "byteLogLikelihood": -5.003946305945, - "hits": 12, - "total": 120, - "hitRate": 0.1 - }, - { - "encoding": "ISO-8859-14", - "confidence": 15, - "language": "cy", - "byteLogLikelihood": -4.912654885736, - "hits": 6, - "total": 120, - "hitRate": 0.05 - }, - { - "encoding": "ISO-8859-16", - "confidence": 15, - "language": "ro", - "byteLogLikelihood": -5.220355825078, - "hits": 6, - "total": 120, - "hitRate": 0.05 - }, - { - "encoding": "ISO-8859-2", - "confidence": 10, - "language": "ro", - "byteLogLikelihood": -5.176149732574, - "hits": 4, - "total": 120, - "hitRate": 0.03333333333333333 - }, - { - "encoding": "ISO-8859-9", - "confidence": 10, - "language": "tr", - "byteLogLikelihood": -5.075173815234, - "hits": 4, - "total": 120, - "hitRate": 0.03333333333333333 - }, - { - "encoding": "windows-1250", - "confidence": 10, - "language": "ro", - "byteLogLikelihood": -5.176149732574, - "hits": 4, - "total": 120, - "hitRate": 0.03333333333333333 - }, - { - "encoding": "windows-1254", - "confidence": 10, - "language": "tr", - "byteLogLikelihood": -5.075173815234, - "hits": 4, - "total": 120, - "hitRate": 0.03333333333333333 - }, - { - "encoding": "windows-1257", - "confidence": 10, - "language": "et", - "byteLogLikelihood": -4.934473933131, - "hits": 4, - "total": 120, - "hitRate": 0.03333333333333333 - }, - { - "encoding": "windows-1258", - "confidence": 7, - "language": "vi", - "byteLogLikelihood": -5.497168225293, - "hits": 3, - "total": 120, - "hitRate": 0.025 - }, - { - "encoding": "ISO-8859-10", - "confidence": 7, - "language": "is", - "byteLogLikelihood": -4.717529149813, - "hits": 3, - "total": 120, - "hitRate": 0.025 - }, - { - "encoding": "CP852", - "confidence": 5, - "language": "pl", - "byteLogLikelihood": -5.087596335232, - "hits": 2, - "total": 120, - "hitRate": 0.016666666666666666 - }, - { - "encoding": "ISO-8859-3", - "confidence": 2, - "language": "mt", - "byteLogLikelihood": -4.658005606594, - "hits": 1, - "total": 120, - "hitRate": 0.008333333333333333 - }, - { - "encoding": "ISO-8859-4", - "confidence": 2, - "language": "lv", - "byteLogLikelihood": -5.19295685089, - "hits": 1, - "total": 120, - "hitRate": 0.008333333333333333 - }, - { - "encoding": "ISO-8859-13", - "confidence": 2, - "language": "lt", - "byteLogLikelihood": -4.145958228046, - "hits": 1, - "total": 120, - "hitRate": 0.008333333333333333 - }, - { - "encoding": "ISO-8859-5", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.825649766807, - "hits": 0, - "total": 120, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-6", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -4.736335095675, - "hits": 0, - "total": 120, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-7", - "confidence": 0, - "language": "el", - "byteLogLikelihood": -4.689401143463, - "hits": 0, - "total": 120, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-8", - "confidence": 0, - "language": "he", - "byteLogLikelihood": -3.231348206195, - "hits": 0, - "total": 120, - "hitRate": 0 - }, - { - "encoding": "windows-1251", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -4.288232392491, - "hits": 0, - "total": 120, - "hitRate": 0 - }, - { - "encoding": "windows-1253", - "confidence": 0, - "language": "el", - "byteLogLikelihood": -4.689401143463, - "hits": 0, - "total": 120, - "hitRate": 0 - }, - { - "encoding": "windows-1255", - "confidence": 0, - "language": "he", - "byteLogLikelihood": -3.231348206195, - "hits": 0, - "total": 120, - "hitRate": 0 - }, - { - "encoding": "windows-1256", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -4.861023356308, - "hits": 0, - "total": 120, - "hitRate": 0 - }, - { - "encoding": "windows-874", - "confidence": 0, - "language": "th", - "byteLogLikelihood": -5.888170123788, - "hits": 0, - "total": 120, - "hitRate": 0 - }, - { - "encoding": "KOI8-R", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.518796947367, - "hits": 0, - "total": 120, - "hitRate": 0 - }, - { - "encoding": "KOI8-U", - "confidence": 0, - "language": "uk", - "byteLogLikelihood": -6.476992253447, - "hits": 0, - "total": 120, - "hitRate": 0 - }, - { - "encoding": "IBM866", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.825649766807, - "hits": 0, - "total": 120, - "hitRate": 0 - }, - { - "encoding": "IBM855", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.685745819823, - "hits": 0, - "total": 120, - "hitRate": 0 - }, - { - "encoding": "x-mac-cyrillic", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -4.288232392491, - "hits": 0, - "total": 120, - "hitRate": 0 - } - ] - }, - { - "expected": { - "encoding": "windows-1252", - "language": "de" - }, - "predicted": { - "encoding": "ISO-8859-1", - "confidence": 73, - "language": "de", - "byteLogLikelihood": -3.169712077519, - "hits": 53, - "total": 216, - "hitRate": 0.24537037037037038 - }, - "encodingExact": false, - "encodingEquivalent": true, - "encodingCorrect": true, - "languageCorrect": true, - "tiedAtTop": 3, - "candidates": [ - { - "encoding": "ISO-8859-1", - "confidence": 73, - "language": "de", - "byteLogLikelihood": -3.169712077519, - "hits": 53, - "total": 216, - "hitRate": 0.24537037037037038 - }, - { - "encoding": "windows-1252", - "confidence": 73, - "language": "de", - "byteLogLikelihood": -3.169712077519, - "hits": 53, - "total": 216, - "hitRate": 0.24537037037037038 - }, - { - "encoding": "ISO-8859-15", - "confidence": 73, - "language": "de", - "byteLogLikelihood": -3.169712077519, - "hits": 53, - "total": 216, - "hitRate": 0.24537037037037038 - }, - { - "encoding": "macintosh", - "confidence": 72, - "language": "de", - "byteLogLikelihood": -5.003946305945, - "hits": 52, - "total": 215, - "hitRate": 0.24186046511627907 - }, - { - "encoding": "CP850", - "confidence": 70, - "language": "de", - "byteLogLikelihood": -5.003946305945, - "hits": 51, - "total": 216, - "hitRate": 0.2361111111111111 - }, - { - "encoding": "ISO-8859-14", - "confidence": 20, - "language": "cy", - "byteLogLikelihood": -4.912654885736, - "hits": 15, - "total": 216, - "hitRate": 0.06944444444444445 - }, - { - "encoding": "ISO-8859-2", - "confidence": 13, - "language": "ro", - "byteLogLikelihood": -5.176149732574, - "hits": 10, - "total": 216, - "hitRate": 0.046296296296296294 - }, - { - "encoding": "windows-1250", - "confidence": 13, - "language": "ro", - "byteLogLikelihood": -5.176149732574, - "hits": 10, - "total": 216, - "hitRate": 0.046296296296296294 - }, - { - "encoding": "ISO-8859-9", - "confidence": 12, - "language": "tr", - "byteLogLikelihood": -4.5258676709, - "hits": 9, - "total": 216, - "hitRate": 0.041666666666666664 - }, - { - "encoding": "windows-1254", - "confidence": 12, - "language": "tr", - "byteLogLikelihood": -4.5258676709, - "hits": 9, - "total": 216, - "hitRate": 0.041666666666666664 - }, - { - "encoding": "ISO-8859-16", - "confidence": 11, - "language": "ro", - "byteLogLikelihood": -5.220355825078, - "hits": 8, - "total": 216, - "hitRate": 0.037037037037037035 - }, - { - "encoding": "windows-1257", - "confidence": 9, - "language": "lv", - "byteLogLikelihood": -5.19295685089, - "hits": 7, - "total": 216, - "hitRate": 0.032407407407407406 - }, - { - "encoding": "ISO-8859-4", - "confidence": 9, - "language": "lv", - "byteLogLikelihood": -5.19295685089, - "hits": 7, - "total": 216, - "hitRate": 0.032407407407407406 - }, - { - "encoding": "CP852", - "confidence": 6, - "language": "pl", - "byteLogLikelihood": -5.087596335232, - "hits": 5, - "total": 216, - "hitRate": 0.023148148148148147 - }, - { - "encoding": "windows-1258", - "confidence": 5, - "language": "vi", - "byteLogLikelihood": -5.497168225293, - "hits": 4, - "total": 216, - "hitRate": 0.018518518518518517 - }, - { - "encoding": "ISO-8859-3", - "confidence": 5, - "language": "mt", - "byteLogLikelihood": -5.105945473901, - "hits": 4, - "total": 216, - "hitRate": 0.018518518518518517 - }, - { - "encoding": "ISO-8859-13", - "confidence": 2, - "language": "lt", - "byteLogLikelihood": -5.123963979403, - "hits": 2, - "total": 216, - "hitRate": 0.009259259259259259 - }, - { - "encoding": "ISO-8859-10", - "confidence": 1, - "language": "is", - "byteLogLikelihood": -5.204006687077, - "hits": 1, - "total": 216, - "hitRate": 0.004629629629629629 - }, - { - "encoding": "ISO-8859-5", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.162408104115, - "hits": 0, - "total": 216, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-6", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -4.007313397456, - "hits": 0, - "total": 216, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-7", - "confidence": 0, - "language": "el", - "byteLogLikelihood": -4.349754587225, - "hits": 0, - "total": 216, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-8", - "confidence": 0, - "language": "he", - "byteLogLikelihood": -4.279537403415, - "hits": 0, - "total": 216, - "hitRate": 0 - }, - { - "encoding": "windows-1251", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -4.542402054434, - "hits": 0, - "total": 216, - "hitRate": 0 - }, - { - "encoding": "windows-1253", - "confidence": 0, - "language": "el", - "byteLogLikelihood": -4.349754587225, - "hits": 0, - "total": 216, - "hitRate": 0 - }, - { - "encoding": "windows-1255", - "confidence": 0, - "language": "he", - "byteLogLikelihood": -4.279537403415, - "hits": 0, - "total": 216, - "hitRate": 0 - }, - { - "encoding": "windows-1256", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -4.318835143108, - "hits": 0, - "total": 216, - "hitRate": 0 - }, - { - "encoding": "windows-874", - "confidence": 0, - "language": "th", - "byteLogLikelihood": -5.657121063601, - "hits": 0, - "total": 216, - "hitRate": 0 - }, - { - "encoding": "KOI8-R", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.28774788718, - "hits": 0, - "total": 216, - "hitRate": 0 - }, - { - "encoding": "KOI8-U", - "confidence": 0, - "language": "uk", - "byteLogLikelihood": -6.245943193261, - "hits": 0, - "total": 216, - "hitRate": 0 - }, - { - "encoding": "IBM866", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.692083742507, - "hits": 0, - "total": 216, - "hitRate": 0 - }, - { - "encoding": "IBM855", - "confidence": 0, - "language": "sr", - "byteLogLikelihood": -5.942998477092, - "hits": 0, - "total": 216, - "hitRate": 0 - }, - { - "encoding": "x-mac-cyrillic", - "confidence": 0, - "language": "uk", - "byteLogLikelihood": -3.629332579687, - "hits": 0, - "total": 216, - "hitRate": 0 - } - ] - }, - { - "expected": { - "encoding": "windows-1252", - "language": "en" - }, - "predicted": { - "encoding": "ISO-8859-15", - "confidence": 29, - "language": "en", - "byteLogLikelihood": -2.06619631493, - "hits": 13, - "total": 132, - "hitRate": 0.09848484848484848 - }, - "encodingExact": false, - "encodingEquivalent": true, - "encodingCorrect": true, - "languageCorrect": true, - "tiedAtTop": 1, - "candidates": [ - { - "encoding": "ISO-8859-15", - "confidence": 29, - "language": "fr", - "byteLogLikelihood": -2.06619631493, - "hits": 13, - "total": 132, - "hitRate": 0.09848484848484848 - }, - { - "encoding": "ISO-8859-1", - "confidence": 47, - "language": "en", - "byteLogLikelihood": -3.310543013394, - "hits": 21, - "total": 132, - "hitRate": 0.1590909090909091 - }, - { - "encoding": "windows-1252", - "confidence": 47, - "language": "en", - "byteLogLikelihood": -3.310543013394, - "hits": 21, - "total": 132, - "hitRate": 0.1590909090909091 - }, - { - "encoding": "macintosh", - "confidence": 27, - "language": "fr", - "byteLogLikelihood": -5.010635294096, - "hits": 12, - "total": 132, - "hitRate": 0.09090909090909091 - }, - { - "encoding": "CP850", - "confidence": 27, - "language": "fr", - "byteLogLikelihood": -5.010635294096, - "hits": 12, - "total": 132, - "hitRate": 0.09090909090909091 - }, - { - "encoding": "windows-1257", - "confidence": 11, - "language": "et", - "byteLogLikelihood": -4.934473933131, - "hits": 5, - "total": 132, - "hitRate": 0.03787878787878788 - }, - { - "encoding": "ISO-8859-14", - "confidence": 11, - "language": "cy", - "byteLogLikelihood": -4.912654885736, - "hits": 5, - "total": 132, - "hitRate": 0.03787878787878788 - }, - { - "encoding": "ISO-8859-2", - "confidence": 9, - "language": "cs", - "byteLogLikelihood": -3.54961738678, - "hits": 4, - "total": 132, - "hitRate": 0.030303030303030304 - }, - { - "encoding": "windows-1250", - "confidence": 9, - "language": "cs", - "byteLogLikelihood": -3.54961738678, - "hits": 4, - "total": 132, - "hitRate": 0.030303030303030304 - }, - { - "encoding": "windows-1258", - "confidence": 9, - "language": "vi", - "byteLogLikelihood": -5.497168225293, - "hits": 4, - "total": 132, - "hitRate": 0.030303030303030304 - }, - { - "encoding": "ISO-8859-16", - "confidence": 9, - "language": "ro", - "byteLogLikelihood": -5.220355825078, - "hits": 4, - "total": 132, - "hitRate": 0.030303030303030304 - }, - { - "encoding": "ISO-8859-4", - "confidence": 6, - "language": "lv", - "byteLogLikelihood": -5.19295685089, - "hits": 3, - "total": 132, - "hitRate": 0.022727272727272728 - }, - { - "encoding": "ISO-8859-9", - "confidence": 4, - "language": "tr", - "byteLogLikelihood": -5.075173815234, - "hits": 2, - "total": 132, - "hitRate": 0.015151515151515152 - }, - { - "encoding": "windows-1254", - "confidence": 4, - "language": "tr", - "byteLogLikelihood": -5.075173815234, - "hits": 2, - "total": 132, - "hitRate": 0.015151515151515152 - }, - { - "encoding": "ISO-8859-3", - "confidence": 4, - "language": "mt", - "byteLogLikelihood": -5.105945473901, - "hits": 2, - "total": 132, - "hitRate": 0.015151515151515152 - }, - { - "encoding": "CP852", - "confidence": 4, - "language": "pl", - "byteLogLikelihood": -5.087596335232, - "hits": 2, - "total": 132, - "hitRate": 0.015151515151515152 - }, - { - "encoding": "ISO-8859-13", - "confidence": 2, - "language": "lt", - "byteLogLikelihood": -5.123963979403, - "hits": 1, - "total": 132, - "hitRate": 0.007575757575757576 - }, - { - "encoding": "ISO-8859-5", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.593471453839, - "hits": 0, - "total": 132, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-6", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -6.113682179832, - "hits": 0, - "total": 132, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-7", - "confidence": 0, - "language": "el", - "byteLogLikelihood": -2.654561516151, - "hits": 0, - "total": 132, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-8", - "confidence": 0, - "language": "he", - "byteLogLikelihood": -2.405884662832, - "hits": 0, - "total": 132, - "hitRate": 0 - }, - { - "encoding": "windows-1251", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -4.612642200827, - "hits": 0, - "total": 132, - "hitRate": 0 - }, - { - "encoding": "windows-1253", - "confidence": 0, - "language": "el", - "byteLogLikelihood": -2.654561516151, - "hits": 0, - "total": 132, - "hitRate": 0 - }, - { - "encoding": "windows-1255", - "confidence": 0, - "language": "he", - "byteLogLikelihood": -2.405884662832, - "hits": 0, - "total": 132, - "hitRate": 0 - }, - { - "encoding": "windows-1256", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -6.113682179832, - "hits": 0, - "total": 132, - "hitRate": 0 - }, - { - "encoding": "windows-874", - "confidence": 0, - "language": "th", - "byteLogLikelihood": -3.57655026914, - "hits": 0, - "total": 131, - "hitRate": 0 - }, - { - "encoding": "KOI8-R", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.692083742507, - "hits": 0, - "total": 132, - "hitRate": 0 - }, - { - "encoding": "KOI8-U", - "confidence": 0, - "language": "uk", - "byteLogLikelihood": -6.650279048587, - "hits": 0, - "total": 132, - "hitRate": 0 - }, - { - "encoding": "IBM866", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.593471453839, - "hits": 0, - "total": 132, - "hitRate": 0 - }, - { - "encoding": "IBM855", - "confidence": 0, - "language": "sr", - "byteLogLikelihood": -4.728861658331, - "hits": 0, - "total": 132, - "hitRate": 0 - }, - { - "encoding": "x-mac-cyrillic", - "confidence": 0, - "language": "uk", - "byteLogLikelihood": -4.252383775789, - "hits": 0, - "total": 132, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-10", - "confidence": 0, - "language": "is", - "byteLogLikelihood": -4.510859506517, - "hits": 0, - "total": 132, - "hitRate": 0 - } - ] - }, - { - "expected": { - "encoding": "windows-1252", - "language": "es" - }, - "predicted": { - "encoding": "ISO-8859-1", - "confidence": 61, - "language": "es", - "byteLogLikelihood": -3.834657935767, - "hits": 41, - "total": 200, - "hitRate": 0.205 - }, - "encodingExact": false, - "encodingEquivalent": true, - "encodingCorrect": true, - "languageCorrect": true, - "tiedAtTop": 3, - "candidates": [ - { - "encoding": "ISO-8859-1", - "confidence": 61, - "language": "es", - "byteLogLikelihood": -3.834657935767, - "hits": 41, - "total": 200, - "hitRate": 0.205 - }, - { - "encoding": "windows-1252", - "confidence": 61, - "language": "es", - "byteLogLikelihood": -3.834657935767, - "hits": 41, - "total": 200, - "hitRate": 0.205 - }, - { - "encoding": "ISO-8859-15", - "confidence": 61, - "language": "es", - "byteLogLikelihood": -3.834657935767, - "hits": 41, - "total": 200, - "hitRate": 0.205 - }, - { - "encoding": "macintosh", - "confidence": 58, - "language": "es", - "byteLogLikelihood": -4.948759890378, - "hits": 39, - "total": 199, - "hitRate": 0.19597989949748743 - }, - { - "encoding": "CP850", - "confidence": 58, - "language": "es", - "byteLogLikelihood": -4.948759890378, - "hits": 39, - "total": 200, - "hitRate": 0.195 - }, - { - "encoding": "windows-1257", - "confidence": 24, - "language": "lv", - "byteLogLikelihood": -5.19295685089, - "hits": 16, - "total": 200, - "hitRate": 0.08 - }, - { - "encoding": "ISO-8859-4", - "confidence": 24, - "language": "lv", - "byteLogLikelihood": -5.009854802779, - "hits": 16, - "total": 200, - "hitRate": 0.08 - }, - { - "encoding": "ISO-8859-13", - "confidence": 19, - "language": "lt", - "byteLogLikelihood": -4.892914919217, - "hits": 13, - "total": 200, - "hitRate": 0.065 - }, - { - "encoding": "ISO-8859-14", - "confidence": 16, - "language": "cy", - "byteLogLikelihood": -4.912654885736, - "hits": 11, - "total": 200, - "hitRate": 0.055 - }, - { - "encoding": "ISO-8859-2", - "confidence": 15, - "language": "ro", - "byteLogLikelihood": -5.176149732574, - "hits": 10, - "total": 200, - "hitRate": 0.05 - }, - { - "encoding": "windows-1250", - "confidence": 15, - "language": "ro", - "byteLogLikelihood": -5.176149732574, - "hits": 10, - "total": 200, - "hitRate": 0.05 - }, - { - "encoding": "ISO-8859-16", - "confidence": 15, - "language": "ro", - "byteLogLikelihood": -5.220355825078, - "hits": 10, - "total": 200, - "hitRate": 0.05 - }, - { - "encoding": "ISO-8859-9", - "confidence": 7, - "language": "tr", - "byteLogLikelihood": -5.075173815234, - "hits": 5, - "total": 200, - "hitRate": 0.025 - }, - { - "encoding": "windows-1254", - "confidence": 7, - "language": "tr", - "byteLogLikelihood": -5.075173815234, - "hits": 5, - "total": 200, - "hitRate": 0.025 - }, - { - "encoding": "CP852", - "confidence": 7, - "language": "pl", - "byteLogLikelihood": -5.087596335232, - "hits": 5, - "total": 200, - "hitRate": 0.025 - }, - { - "encoding": "windows-1258", - "confidence": 4, - "language": "vi", - "byteLogLikelihood": -4.848531508941, - "hits": 3, - "total": 200, - "hitRate": 0.015 - }, - { - "encoding": "ISO-8859-10", - "confidence": 4, - "language": "is", - "byteLogLikelihood": -3.846028832089, - "hits": 3, - "total": 200, - "hitRate": 0.015 - }, - { - "encoding": "ISO-8859-5", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -4.977292083619, - "hits": 0, - "total": 200, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-6", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -5.346153815501, - "hits": 0, - "total": 200, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-7", - "confidence": 0, - "language": "el", - "byteLogLikelihood": -3.106555532888, - "hits": 0, - "total": 200, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-8", - "confidence": 0, - "language": "he", - "byteLogLikelihood": -3.411159813207, - "hits": 0, - "total": 200, - "hitRate": 0 - }, - { - "encoding": "windows-1251", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -3.336328204376, - "hits": 0, - "total": 200, - "hitRate": 0 - }, - { - "encoding": "windows-1253", - "confidence": 0, - "language": "el", - "byteLogLikelihood": -3.106555532888, - "hits": 0, - "total": 200, - "hitRate": 0 - }, - { - "encoding": "windows-1255", - "confidence": 0, - "language": "he", - "byteLogLikelihood": -3.411159813207, - "hits": 0, - "total": 200, - "hitRate": 0 - }, - { - "encoding": "windows-1256", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -3.300604963183, - "hits": 0, - "total": 200, - "hitRate": 0 - }, - { - "encoding": "windows-874", - "confidence": 0, - "language": "th", - "byteLogLikelihood": -5.412820202576, - "hits": 0, - "total": 200, - "hitRate": 0 - }, - { - "encoding": "KOI8-R", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.692083742507, - "hits": 0, - "total": 200, - "hitRate": 0 - }, - { - "encoding": "KOI8-U", - "confidence": 0, - "language": "uk", - "byteLogLikelihood": -6.303705458307, - "hits": 0, - "total": 200, - "hitRate": 0 - }, - { - "encoding": "IBM866", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -4.977292083619, - "hits": 0, - "total": 200, - "hitRate": 0 - }, - { - "encoding": "IBM855", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -4.203740544852, - "hits": 0, - "total": 200, - "hitRate": 0 - }, - { - "encoding": "x-mac-cyrillic", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -3.336328204376, - "hits": 0, - "total": 200, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-3", - "confidence": 0, - "language": "mt", - "byteLogLikelihood": -5.105945473901, - "hits": 0, - "total": 200, - "hitRate": 0 - } - ] - }, - { - "expected": { - "encoding": "windows-1252", - "language": "fr" - }, - "predicted": { - "encoding": "ISO-8859-1", - "confidence": 77, - "language": "fr", - "byteLogLikelihood": -2.06619631493, - "hits": 59, - "total": 228, - "hitRate": 0.25877192982456143 - }, - "encodingExact": false, - "encodingEquivalent": true, - "encodingCorrect": true, - "languageCorrect": true, - "tiedAtTop": 3, - "candidates": [ - { - "encoding": "ISO-8859-1", - "confidence": 77, - "language": "fr", - "byteLogLikelihood": -2.06619631493, - "hits": 59, - "total": 228, - "hitRate": 0.25877192982456143 - }, - { - "encoding": "windows-1252", - "confidence": 77, - "language": "fr", - "byteLogLikelihood": -2.06619631493, - "hits": 59, - "total": 228, - "hitRate": 0.25877192982456143 - }, - { - "encoding": "ISO-8859-15", - "confidence": 77, - "language": "fr", - "byteLogLikelihood": -2.06619631493, - "hits": 59, - "total": 228, - "hitRate": 0.25877192982456143 - }, - { - "encoding": "macintosh", - "confidence": 71, - "language": "fr", - "byteLogLikelihood": -5.010635294096, - "hits": 54, - "total": 228, - "hitRate": 0.23684210526315788 - }, - { - "encoding": "CP850", - "confidence": 71, - "language": "fr", - "byteLogLikelihood": -5.010635294096, - "hits": 54, - "total": 228, - "hitRate": 0.23684210526315788 - }, - { - "encoding": "ISO-8859-2", - "confidence": 11, - "language": "ro", - "byteLogLikelihood": -5.176149732574, - "hits": 9, - "total": 228, - "hitRate": 0.039473684210526314 - }, - { - "encoding": "windows-1250", - "confidence": 11, - "language": "ro", - "byteLogLikelihood": -5.176149732574, - "hits": 9, - "total": 228, - "hitRate": 0.039473684210526314 - }, - { - "encoding": "ISO-8859-10", - "confidence": 10, - "language": "is", - "byteLogLikelihood": -4.510859506517, - "hits": 8, - "total": 228, - "hitRate": 0.03508771929824561 - }, - { - "encoding": "ISO-8859-16", - "confidence": 10, - "language": "ro", - "byteLogLikelihood": -5.220355825078, - "hits": 8, - "total": 228, - "hitRate": 0.03508771929824561 - }, - { - "encoding": "windows-1257", - "confidence": 7, - "language": "lv", - "byteLogLikelihood": -5.19295685089, - "hits": 6, - "total": 228, - "hitRate": 0.02631578947368421 - }, - { - "encoding": "ISO-8859-4", - "confidence": 7, - "language": "lv", - "byteLogLikelihood": -5.19295685089, - "hits": 6, - "total": 228, - "hitRate": 0.02631578947368421 - }, - { - "encoding": "CP852", - "confidence": 7, - "language": "pl", - "byteLogLikelihood": -5.087596335232, - "hits": 6, - "total": 228, - "hitRate": 0.02631578947368421 - }, - { - "encoding": "ISO-8859-9", - "confidence": 5, - "language": "tr", - "byteLogLikelihood": -5.075173815234, - "hits": 4, - "total": 228, - "hitRate": 0.017543859649122806 - }, - { - "encoding": "windows-1254", - "confidence": 5, - "language": "tr", - "byteLogLikelihood": -5.075173815234, - "hits": 4, - "total": 228, - "hitRate": 0.017543859649122806 - }, - { - "encoding": "windows-1258", - "confidence": 5, - "language": "vi", - "byteLogLikelihood": -5.497168225293, - "hits": 4, - "total": 228, - "hitRate": 0.017543859649122806 - }, - { - "encoding": "ISO-8859-3", - "confidence": 5, - "language": "mt", - "byteLogLikelihood": -5.105945473901, - "hits": 4, - "total": 228, - "hitRate": 0.017543859649122806 - }, - { - "encoding": "ISO-8859-13", - "confidence": 5, - "language": "lt", - "byteLogLikelihood": -5.123963979403, - "hits": 4, - "total": 228, - "hitRate": 0.017543859649122806 - }, - { - "encoding": "ISO-8859-14", - "confidence": 3, - "language": "cy", - "byteLogLikelihood": -4.912654885736, - "hits": 3, - "total": 228, - "hitRate": 0.013157894736842105 - }, - { - "encoding": "ISO-8859-5", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.593471453839, - "hits": 0, - "total": 228, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-6", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -6.113682179832, - "hits": 0, - "total": 228, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-7", - "confidence": 0, - "language": "el", - "byteLogLikelihood": -2.654561516151, - "hits": 0, - "total": 228, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-8", - "confidence": 0, - "language": "he", - "byteLogLikelihood": -2.405884662832, - "hits": 0, - "total": 228, - "hitRate": 0 - }, - { - "encoding": "windows-1251", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -4.612642200827, - "hits": 0, - "total": 228, - "hitRate": 0 - }, - { - "encoding": "windows-1253", - "confidence": 0, - "language": "el", - "byteLogLikelihood": -2.654561516151, - "hits": 0, - "total": 228, - "hitRate": 0 - }, - { - "encoding": "windows-1255", - "confidence": 0, - "language": "he", - "byteLogLikelihood": -2.405884662832, - "hits": 0, - "total": 228, - "hitRate": 0 - }, - { - "encoding": "windows-1256", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -6.113682179832, - "hits": 0, - "total": 228, - "hitRate": 0 - }, - { - "encoding": "windows-874", - "confidence": 0, - "language": "th", - "byteLogLikelihood": -3.57655026914, - "hits": 0, - "total": 224, - "hitRate": 0 - }, - { - "encoding": "KOI8-R", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.692083742507, - "hits": 0, - "total": 228, - "hitRate": 0 - }, - { - "encoding": "KOI8-U", - "confidence": 0, - "language": "uk", - "byteLogLikelihood": -6.650279048587, - "hits": 0, - "total": 228, - "hitRate": 0 - }, - { - "encoding": "IBM866", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.593471453839, - "hits": 0, - "total": 228, - "hitRate": 0 - }, - { - "encoding": "IBM855", - "confidence": 0, - "language": "sr", - "byteLogLikelihood": -4.728861658331, - "hits": 0, - "total": 228, - "hitRate": 0 - }, - { - "encoding": "x-mac-cyrillic", - "confidence": 0, - "language": "uk", - "byteLogLikelihood": -4.252383775789, - "hits": 0, - "total": 228, - "hitRate": 0 - } - ] - }, - { - "expected": { - "encoding": "windows-1252", - "language": "it" - }, - "predicted": { - "encoding": "ISO-8859-1", - "confidence": 58, - "language": "it", - "byteLogLikelihood": -3.533686564708, - "hits": 31, - "total": 159, - "hitRate": 0.1949685534591195 - }, - "encodingExact": false, - "encodingEquivalent": true, - "encodingCorrect": true, - "languageCorrect": true, - "tiedAtTop": 2, - "candidates": [ - { - "encoding": "ISO-8859-1", - "confidence": 58, - "language": "it", - "byteLogLikelihood": -3.533686564708, - "hits": 31, - "total": 159, - "hitRate": 0.1949685534591195 - }, - { - "encoding": "windows-1252", - "confidence": 58, - "language": "it", - "byteLogLikelihood": -3.533686564708, - "hits": 31, - "total": 159, - "hitRate": 0.1949685534591195 - }, - { - "encoding": "macintosh", - "confidence": 24, - "language": "fr", - "byteLogLikelihood": -5.010635294096, - "hits": 13, - "total": 158, - "hitRate": 0.08227848101265822 - }, - { - "encoding": "ISO-8859-15", - "confidence": 24, - "language": "fr", - "byteLogLikelihood": -5.010635294096, - "hits": 13, - "total": 159, - "hitRate": 0.08176100628930817 - }, - { - "encoding": "CP850", - "confidence": 24, - "language": "fr", - "byteLogLikelihood": -5.010635294096, - "hits": 13, - "total": 159, - "hitRate": 0.08176100628930817 - }, - { - "encoding": "windows-1258", - "confidence": 16, - "language": "vi", - "byteLogLikelihood": -3.012261575505, - "hits": 9, - "total": 159, - "hitRate": 0.05660377358490566 - }, - { - "encoding": "ISO-8859-16", - "confidence": 16, - "language": "ro", - "byteLogLikelihood": -5.220355825078, - "hits": 9, - "total": 159, - "hitRate": 0.05660377358490566 - }, - { - "encoding": "ISO-8859-2", - "confidence": 15, - "language": "ro", - "byteLogLikelihood": -5.176149732574, - "hits": 8, - "total": 159, - "hitRate": 0.050314465408805034 - }, - { - "encoding": "windows-1250", - "confidence": 15, - "language": "ro", - "byteLogLikelihood": -5.176149732574, - "hits": 8, - "total": 159, - "hitRate": 0.050314465408805034 - }, - { - "encoding": "windows-1257", - "confidence": 15, - "language": "lv", - "byteLogLikelihood": -5.19295685089, - "hits": 8, - "total": 159, - "hitRate": 0.050314465408805034 - }, - { - "encoding": "ISO-8859-4", - "confidence": 15, - "language": "lv", - "byteLogLikelihood": -1.974081026022, - "hits": 8, - "total": 159, - "hitRate": 0.050314465408805034 - }, - { - "encoding": "ISO-8859-14", - "confidence": 9, - "language": "cy", - "byteLogLikelihood": -4.912654885736, - "hits": 5, - "total": 159, - "hitRate": 0.031446540880503145 - }, - { - "encoding": "CP852", - "confidence": 7, - "language": "pl", - "byteLogLikelihood": -5.087596335232, - "hits": 4, - "total": 159, - "hitRate": 0.025157232704402517 - }, - { - "encoding": "ISO-8859-9", - "confidence": 5, - "language": "tr", - "byteLogLikelihood": -5.075173815234, - "hits": 3, - "total": 159, - "hitRate": 0.018867924528301886 - }, - { - "encoding": "windows-1254", - "confidence": 5, - "language": "tr", - "byteLogLikelihood": -5.075173815234, - "hits": 3, - "total": 159, - "hitRate": 0.018867924528301886 - }, - { - "encoding": "ISO-8859-3", - "confidence": 5, - "language": "mt", - "byteLogLikelihood": -5.105945473901, - "hits": 3, - "total": 159, - "hitRate": 0.018867924528301886 - }, - { - "encoding": "ISO-8859-10", - "confidence": 3, - "language": "is", - "byteLogLikelihood": -5.204006687077, - "hits": 2, - "total": 159, - "hitRate": 0.012578616352201259 - }, - { - "encoding": "ISO-8859-13", - "confidence": 3, - "language": "lt", - "byteLogLikelihood": -3.332204510175, - "hits": 2, - "total": 159, - "hitRate": 0.012578616352201259 - }, - { - "encoding": "ISO-8859-5", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -2.954414124223, - "hits": 0, - "total": 159, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-6", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -6.113682179832, - "hits": 0, - "total": 159, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-7", - "confidence": 0, - "language": "el", - "byteLogLikelihood": -6.120297418951, - "hits": 0, - "total": 159, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-8", - "confidence": 0, - "language": "he", - "byteLogLikelihood": -3.629660094454, - "hits": 0, - "total": 159, - "hitRate": 0 - }, - { - "encoding": "windows-1251", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -2.533200659147, - "hits": 0, - "total": 159, - "hitRate": 0 - }, - { - "encoding": "windows-1253", - "confidence": 0, - "language": "el", - "byteLogLikelihood": -6.120297418951, - "hits": 0, - "total": 159, - "hitRate": 0 - }, - { - "encoding": "windows-1255", - "confidence": 0, - "language": "he", - "byteLogLikelihood": -3.629660094454, - "hits": 0, - "total": 159, - "hitRate": 0 - }, - { - "encoding": "windows-1256", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -6.113682179832, - "hits": 0, - "total": 159, - "hitRate": 0 - }, - { - "encoding": "windows-874", - "confidence": 0, - "language": "th", - "byteLogLikelihood": -3.496507561466, - "hits": 0, - "total": 159, - "hitRate": 0 - }, - { - "encoding": "KOI8-R", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.692083742507, - "hits": 0, - "total": 159, - "hitRate": 0 - }, - { - "encoding": "KOI8-U", - "confidence": 0, - "language": "uk", - "byteLogLikelihood": -6.650279048587, - "hits": 0, - "total": 159, - "hitRate": 0 - }, - { - "encoding": "IBM866", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -2.954414124223, - "hits": 0, - "total": 159, - "hitRate": 0 - }, - { - "encoding": "IBM855", - "confidence": 0, - "language": "sr", - "byteLogLikelihood": -6.520621127559, - "hits": 0, - "total": 159, - "hitRate": 0 - }, - { - "encoding": "x-mac-cyrillic", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -2.533200659147, - "hits": 0, - "total": 159, - "hitRate": 0 - } - ] - }, - { - "expected": { - "encoding": "windows-1252", - "language": "nl" - }, - "predicted": { - "encoding": "ISO-8859-1", - "confidence": 83, - "language": "nl", - "byteLogLikelihood": -3.295836866004, - "hits": 42, - "total": 151, - "hitRate": 0.2781456953642384 - }, - "encodingExact": false, - "encodingEquivalent": true, - "encodingCorrect": true, - "languageCorrect": true, - "tiedAtTop": 2, - "candidates": [ - { - "encoding": "ISO-8859-1", - "confidence": 83, - "language": "nl", - "byteLogLikelihood": -3.295836866004, - "hits": 42, - "total": 151, - "hitRate": 0.2781456953642384 - }, - { - "encoding": "windows-1252", - "confidence": 83, - "language": "nl", - "byteLogLikelihood": -3.295836866004, - "hits": 42, - "total": 151, - "hitRate": 0.2781456953642384 - }, - { - "encoding": "macintosh", - "confidence": 63, - "language": "de", - "byteLogLikelihood": -5.003946305945, - "hits": 32, - "total": 151, - "hitRate": 0.2119205298013245 - }, - { - "encoding": "ISO-8859-15", - "confidence": 63, - "language": "de", - "byteLogLikelihood": -5.003946305945, - "hits": 32, - "total": 151, - "hitRate": 0.2119205298013245 - }, - { - "encoding": "CP850", - "confidence": 63, - "language": "de", - "byteLogLikelihood": -5.003946305945, - "hits": 32, - "total": 151, - "hitRate": 0.2119205298013245 - }, - { - "encoding": "ISO-8859-14", - "confidence": 33, - "language": "cy", - "byteLogLikelihood": -4.912654885736, - "hits": 17, - "total": 151, - "hitRate": 0.11258278145695365 - }, - { - "encoding": "ISO-8859-2", - "confidence": 13, - "language": "ro", - "byteLogLikelihood": -5.176149732574, - "hits": 7, - "total": 151, - "hitRate": 0.046357615894039736 - }, - { - "encoding": "ISO-8859-9", - "confidence": 13, - "language": "tr", - "byteLogLikelihood": -5.075173815234, - "hits": 7, - "total": 151, - "hitRate": 0.046357615894039736 - }, - { - "encoding": "windows-1250", - "confidence": 13, - "language": "ro", - "byteLogLikelihood": -5.176149732574, - "hits": 7, - "total": 151, - "hitRate": 0.046357615894039736 - }, - { - "encoding": "windows-1254", - "confidence": 13, - "language": "tr", - "byteLogLikelihood": -5.075173815234, - "hits": 7, - "total": 151, - "hitRate": 0.046357615894039736 - }, - { - "encoding": "ISO-8859-10", - "confidence": 11, - "language": "is", - "byteLogLikelihood": -4.510859506517, - "hits": 6, - "total": 151, - "hitRate": 0.039735099337748346 - }, - { - "encoding": "ISO-8859-16", - "confidence": 11, - "language": "ro", - "byteLogLikelihood": -5.220355825078, - "hits": 6, - "total": 151, - "hitRate": 0.039735099337748346 - }, - { - "encoding": "windows-1257", - "confidence": 9, - "language": "et", - "byteLogLikelihood": -4.934473933131, - "hits": 5, - "total": 151, - "hitRate": 0.033112582781456956 - }, - { - "encoding": "windows-1258", - "confidence": 3, - "language": "vi", - "byteLogLikelihood": -5.497168225293, - "hits": 2, - "total": 151, - "hitRate": 0.013245033112582781 - }, - { - "encoding": "ISO-8859-13", - "confidence": 3, - "language": "lt", - "byteLogLikelihood": -5.123963979403, - "hits": 2, - "total": 151, - "hitRate": 0.013245033112582781 - }, - { - "encoding": "ISO-8859-3", - "confidence": 1, - "language": "mt", - "byteLogLikelihood": -5.105945473901, - "hits": 1, - "total": 151, - "hitRate": 0.006622516556291391 - }, - { - "encoding": "ISO-8859-4", - "confidence": 1, - "language": "lv", - "byteLogLikelihood": -5.19295685089, - "hits": 1, - "total": 151, - "hitRate": 0.006622516556291391 - }, - { - "encoding": "CP852", - "confidence": 1, - "language": "pl", - "byteLogLikelihood": -5.087596335232, - "hits": 1, - "total": 151, - "hitRate": 0.006622516556291391 - }, - { - "encoding": "ISO-8859-5", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.593471453839, - "hits": 0, - "total": 151, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-6", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -6.113682179832, - "hits": 0, - "total": 151, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-7", - "confidence": 0, - "language": "el", - "byteLogLikelihood": -2.654561516151, - "hits": 0, - "total": 151, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-8", - "confidence": 0, - "language": "he", - "byteLogLikelihood": -2.405884662832, - "hits": 0, - "total": 151, - "hitRate": 0 - }, - { - "encoding": "windows-1251", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -4.612642200827, - "hits": 0, - "total": 151, - "hitRate": 0 - }, - { - "encoding": "windows-1253", - "confidence": 0, - "language": "el", - "byteLogLikelihood": -2.654561516151, - "hits": 0, - "total": 151, - "hitRate": 0 - }, - { - "encoding": "windows-1255", - "confidence": 0, - "language": "he", - "byteLogLikelihood": -2.405884662832, - "hits": 0, - "total": 151, - "hitRate": 0 - }, - { - "encoding": "windows-1256", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -6.113682179832, - "hits": 0, - "total": 151, - "hitRate": 0 - }, - { - "encoding": "windows-874", - "confidence": 0, - "language": "th", - "byteLogLikelihood": -3.57655026914, - "hits": 0, - "total": 150, - "hitRate": 0 + "hits": 17, + "total": 199, + "hitRate": 0.08542713567839195 }, { - "encoding": "KOI8-R", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.692083742507, - "hits": 0, - "total": 151, - "hitRate": 0 + "encoding": "ISO-8859-14", + "language": "cy", + "confidence": 16, + "byteLogLikelihood": -4.912654885736, + "hits": 11, + "total": 199, + "hitRate": 0.05527638190954774 }, { - "encoding": "KOI8-U", - "confidence": 0, - "language": "uk", - "byteLogLikelihood": -6.650279048587, - "hits": 0, - "total": 151, - "hitRate": 0 + "encoding": "ISO-8859-2", + "language": "ro", + "confidence": 15, + "byteLogLikelihood": -5.176149732574, + "hits": 10, + "total": 199, + "hitRate": 0.05025125628140704 }, { - "encoding": "IBM866", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.593471453839, - "hits": 0, - "total": 151, - "hitRate": 0 + "encoding": "windows-1250", + "language": "ro", + "confidence": 15, + "byteLogLikelihood": -5.176149732574, + "hits": 10, + "total": 199, + "hitRate": 0.05025125628140704 }, { - "encoding": "IBM855", - "confidence": 0, - "language": "sr", - "byteLogLikelihood": -4.728861658331, - "hits": 0, - "total": 151, - "hitRate": 0 + "encoding": "ISO-8859-9", + "language": "tr", + "confidence": 7, + "byteLogLikelihood": -5.075173815234, + "hits": 5, + "total": 199, + "hitRate": 0.02512562814070352 }, { - "encoding": "x-mac-cyrillic", - "confidence": 0, - "language": "uk", - "byteLogLikelihood": -4.252383775789, - "hits": 0, - "total": 151, - "hitRate": 0 + "encoding": "windows-1254", + "language": "tr", + "confidence": 7, + "byteLogLikelihood": -5.075173815234, + "hits": 5, + "total": 199, + "hitRate": 0.02512562814070352 + }, + { + "encoding": "CP852", + "language": "pl", + "confidence": 7, + "byteLogLikelihood": -5.087596335232, + "hits": 5, + "total": 200, + "hitRate": 0.025 } ] }, { "expected": { - "encoding": "windows-1252", - "language": "no" + "encoding": "macintosh", + "language": "fr" }, "predicted": { - "encoding": "ISO-8859-1", - "confidence": 47, - "language": "no", - "byteLogLikelihood": -3.052495812716, - "hits": 18, - "total": 114, - "hitRate": 0.15789473684210525 + "encoding": "macintosh", + "language": "fr", + "confidence": 77, + "byteLogLikelihood": -2.06619631493, + "hits": 59, + "total": 228, + "hitRate": 0.25877192982456143 }, - "encodingExact": false, - "encodingEquivalent": true, + "encodingExact": true, + "encodingEquivalent": false, "encodingCorrect": true, "languageCorrect": true, - "tiedAtTop": 2, + "tiedAtTop": 1, "candidates": [ - { - "encoding": "ISO-8859-1", - "confidence": 47, - "language": "no", - "byteLogLikelihood": -3.052495812716, - "hits": 18, - "total": 114, - "hitRate": 0.15789473684210525 - }, - { - "encoding": "windows-1252", - "confidence": 47, - "language": "no", - "byteLogLikelihood": -3.052495812716, - "hits": 18, - "total": 114, - "hitRate": 0.15789473684210525 - }, { "encoding": "macintosh", - "confidence": 18, - "language": "de", - "byteLogLikelihood": -5.003946305945, - "hits": 7, - "total": 114, - "hitRate": 0.06140350877192982 + "language": "fr", + "confidence": 77, + "byteLogLikelihood": -2.06619631493, + "hits": 59, + "total": 228, + "hitRate": 0.25877192982456143 }, { - "encoding": "ISO-8859-14", - "confidence": 18, - "language": "cy", - "byteLogLikelihood": -4.912654885736, - "hits": 7, - "total": 114, - "hitRate": 0.06140350877192982 + "encoding": "windows-1252", + "language": "fr", + "confidence": 71, + "byteLogLikelihood": -5.010635294096, + "hits": 54, + "total": 228, + "hitRate": 0.23684210526315788 }, { "encoding": "ISO-8859-15", - "confidence": 18, - "language": "de", - "byteLogLikelihood": -5.003946305945, - "hits": 7, - "total": 114, - "hitRate": 0.06140350877192982 + "language": "fr", + "confidence": 75, + "byteLogLikelihood": -5.010635294096, + "hits": 56, + "total": 224, + "hitRate": 0.25 }, { - "encoding": "CP850", - "confidence": 18, - "language": "de", - "byteLogLikelihood": -5.003946305945, - "hits": 7, - "total": 114, - "hitRate": 0.06140350877192982 + "encoding": "ISO-8859-1", + "language": "fr", + "confidence": 75, + "byteLogLikelihood": -5.010635294096, + "hits": 56, + "total": 224, + "hitRate": 0.25 }, { - "encoding": "ISO-8859-10", - "confidence": 13, - "language": "is", - "byteLogLikelihood": -5.204006687077, - "hits": 5, - "total": 114, - "hitRate": 0.043859649122807015 + "encoding": "CP850", + "language": "fr", + "confidence": 71, + "byteLogLikelihood": -5.010635294096, + "hits": 54, + "total": 228, + "hitRate": 0.23684210526315788 }, { - "encoding": "windows-1258", - "confidence": 10, - "language": "vi", - "byteLogLikelihood": -5.497168225293, - "hits": 4, - "total": 114, - "hitRate": 0.03508771929824561 + "encoding": "ISO-8859-2", + "language": "ro", + "confidence": 12, + "byteLogLikelihood": -5.176149732574, + "hits": 9, + "total": 224, + "hitRate": 0.04017857142857143 }, { - "encoding": "ISO-8859-16", - "confidence": 10, + "encoding": "windows-1250", "language": "ro", - "byteLogLikelihood": -5.220355825078, - "hits": 4, - "total": 114, - "hitRate": 0.03508771929824561 + "confidence": 11, + "byteLogLikelihood": -5.176149732574, + "hits": 9, + "total": 228, + "hitRate": 0.039473684210526314 }, { - "encoding": "ISO-8859-2", + "encoding": "windows-1257", + "language": "lv", "confidence": 7, - "language": "cs", - "byteLogLikelihood": -4.354336342997, - "hits": 3, - "total": 114, + "byteLogLikelihood": -5.19295685089, + "hits": 6, + "total": 228, "hitRate": 0.02631578947368421 }, { "encoding": "ISO-8859-9", - "confidence": 7, "language": "tr", + "confidence": 6, "byteLogLikelihood": -5.075173815234, - "hits": 3, - "total": 114, - "hitRate": 0.02631578947368421 - }, - { - "encoding": "windows-1250", - "confidence": 7, - "language": "cs", - "byteLogLikelihood": -4.354336342997, - "hits": 3, - "total": 114, - "hitRate": 0.02631578947368421 + "hits": 5, + "total": 224, + "hitRate": 0.022321428571428572 }, { "encoding": "windows-1254", - "confidence": 7, "language": "tr", + "confidence": 6, "byteLogLikelihood": -5.075173815234, - "hits": 3, - "total": 114, - "hitRate": 0.02631578947368421 + "hits": 5, + "total": 224, + "hitRate": 0.022321428571428572 }, { - "encoding": "windows-1257", - "confidence": 7, - "language": "et", - "byteLogLikelihood": -4.934473933131, + "encoding": "ISO-8859-14", + "language": "cy", + "confidence": 4, + "byteLogLikelihood": -4.912654885736, "hits": 3, - "total": 114, - "hitRate": 0.02631578947368421 - }, - { - "encoding": "ISO-8859-3", - "confidence": 2, - "language": "mt", - "byteLogLikelihood": -4.210065739287, - "hits": 1, - "total": 114, - "hitRate": 0.008771929824561403 + "total": 224, + "hitRate": 0.013392857142857142 }, { - "encoding": "ISO-8859-4", - "confidence": 2, - "language": "lv", - "byteLogLikelihood": -5.19295685089, - "hits": 1, - "total": 114, - "hitRate": 0.008771929824561403 + "encoding": "IBM855", + "language": "sr", + "confidence": 0, + "byteLogLikelihood": -3.576182148392, + "hits": 0, + "total": 228, + "hitRate": 0 + } + ] + }, + { + "expected": { + "encoding": "windows-1250", + "language": "cs" + }, + "predicted": { + "encoding": "ISO-8859-2", + "language": "cs", + "confidence": 30, + "byteLogLikelihood": -3.429159108442, + "hits": 13, + "total": 126, + "hitRate": 0.10317460317460317 + }, + "encodingExact": false, + "encodingEquivalent": true, + "encodingCorrect": true, + "languageCorrect": true, + "tiedAtTop": 2, + "candidates": [ + { + "encoding": "ISO-8859-2", + "language": "cs", + "confidence": 30, + "byteLogLikelihood": -3.429159108442, + "hits": 13, + "total": 126, + "hitRate": 0.10317460317460317 }, { - "encoding": "ISO-8859-13", - "confidence": 2, - "language": "lt", - "byteLogLikelihood": -4.319245023186, - "hits": 1, - "total": 114, - "hitRate": 0.008771929824561403 + "encoding": "windows-1250", + "language": "cs", + "confidence": 30, + "byteLogLikelihood": -3.429159108442, + "hits": 13, + "total": 126, + "hitRate": 0.10317460317460317 }, { - "encoding": "CP852", - "confidence": 2, - "language": "pl", - "byteLogLikelihood": -5.087596335232, - "hits": 1, - "total": 114, - "hitRate": 0.008771929824561403 + "encoding": "ISO-8859-1", + "language": "pt", + "confidence": 11, + "byteLogLikelihood": -4.5670392286, + "hits": 5, + "total": 126, + "hitRate": 0.03968253968253968 }, { - "encoding": "ISO-8859-5", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.652362971667, - "hits": 0, - "total": 114, - "hitRate": 0 + "encoding": "windows-1252", + "language": "pt", + "confidence": 11, + "byteLogLikelihood": -4.5670392286, + "hits": 5, + "total": 126, + "hitRate": 0.03968253968253968 }, { - "encoding": "ISO-8859-6", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -4.641462690249, - "hits": 0, - "total": 114, - "hitRate": 0 + "encoding": "ISO-8859-15", + "language": "fr", + "confidence": 7, + "byteLogLikelihood": -4.081579721495, + "hits": 3, + "total": 126, + "hitRate": 0.023809523809523808 }, { "encoding": "ISO-8859-7", - "confidence": 0, "language": "el", - "byteLogLikelihood": -4.154384602589, + "confidence": 0, + "byteLogLikelihood": -3.401446196881, "hits": 0, - "total": 114, + "total": 126, "hitRate": 0 }, { "encoding": "ISO-8859-8", - "confidence": 0, "language": "he", - "byteLogLikelihood": -2.647504477241, + "confidence": 0, + "byteLogLikelihood": -3.467509652199, "hits": 0, - "total": 114, + "total": 125, "hitRate": 0 }, { "encoding": "windows-1251", - "confidence": 0, "language": "ru", - "byteLogLikelihood": -3.753215851617, + "confidence": 0, + "byteLogLikelihood": -4.249199684222, "hits": 0, - "total": 114, + "total": 126, "hitRate": 0 }, { "encoding": "windows-1253", - "confidence": 0, "language": "el", - "byteLogLikelihood": -4.154384602589, + "confidence": 0, + "byteLogLikelihood": -3.401446196881, "hits": 0, - "total": 114, + "total": 126, "hitRate": 0 }, { "encoding": "windows-1255", - "confidence": 0, "language": "he", - "byteLogLikelihood": -2.647504477241, + "confidence": 0, + "byteLogLikelihood": -3.467509652199, "hits": 0, - "total": 114, + "total": 125, "hitRate": 0 }, { - "encoding": "windows-1256", + "encoding": "x-mac-cyrillic", + "language": "uk", "confidence": 0, - "language": "ar", - "byteLogLikelihood": -5.217802445218, + "byteLogLikelihood": -4.226561011787, "hits": 0, - "total": 114, + "total": 126, "hitRate": 0 }, { - "encoding": "windows-874", + "encoding": "ISO-8859-10", + "language": "is", "confidence": 0, - "language": "th", - "byteLogLikelihood": -6.061456918928, + "byteLogLikelihood": -4.43713857777, "hits": 0, - "total": 114, + "total": 126, "hitRate": 0 + } + ] + }, + { + "expected": { + "encoding": "windows-1250", + "language": "hu" + }, + "predicted": { + "encoding": "ISO-8859-2", + "language": "hu", + "confidence": 46, + "byteLogLikelihood": -3.161205902203, + "hits": 21, + "total": 136, + "hitRate": 0.15441176470588236 + }, + "encodingExact": false, + "encodingEquivalent": true, + "encodingCorrect": true, + "languageCorrect": true, + "tiedAtTop": 2, + "candidates": [ + { + "encoding": "ISO-8859-2", + "language": "hu", + "confidence": 46, + "byteLogLikelihood": -3.161205902203, + "hits": 21, + "total": 136, + "hitRate": 0.15441176470588236 }, { - "encoding": "KOI8-R", + "encoding": "windows-1250", + "language": "hu", + "confidence": 46, + "byteLogLikelihood": -3.161205902203, + "hits": 21, + "total": 136, + "hitRate": 0.15441176470588236 + }, + { + "encoding": "ISO-8859-1", + "language": "pt", + "confidence": 17, + "byteLogLikelihood": -4.507887190294, + "hits": 8, + "total": 136, + "hitRate": 0.058823529411764705 + }, + { + "encoding": "windows-1252", + "language": "pt", + "confidence": 17, + "byteLogLikelihood": -4.507887190294, + "hits": 8, + "total": 136, + "hitRate": 0.058823529411764705 + }, + { + "encoding": "ISO-8859-15", + "language": "fr", + "confidence": 4, + "byteLogLikelihood": -4.274525549305, + "hits": 2, + "total": 136, + "hitRate": 0.014705882352941176 + }, + { + "encoding": "windows-1257", + "language": "et", + "confidence": 2, + "byteLogLikelihood": -4.453831056838, + "hits": 1, + "total": 136, + "hitRate": 0.007352941176470588 + }, + { + "encoding": "ISO-8859-10", + "language": "is", + "confidence": 2, + "byteLogLikelihood": -3.90025153387, + "hits": 1, + "total": 136, + "hitRate": 0.007352941176470588 + }, + { + "encoding": "ISO-8859-7", + "language": "el", "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.692083742507, + "byteLogLikelihood": -3.430247904624, "hits": 0, - "total": 114, + "total": 136, "hitRate": 0 }, { - "encoding": "KOI8-U", + "encoding": "ISO-8859-8", + "language": "he", "confidence": 0, - "language": "uk", - "byteLogLikelihood": -6.650279048587, + "byteLogLikelihood": -3.984546441118, "hits": 0, - "total": 114, + "total": 135, "hitRate": 0 }, { - "encoding": "IBM866", + "encoding": "windows-1253", + "language": "el", "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.652362971667, + "byteLogLikelihood": -3.430247904624, "hits": 0, - "total": 114, + "total": 136, "hitRate": 0 }, { - "encoding": "IBM855", + "encoding": "windows-1255", + "language": "he", "confidence": 0, - "language": "ru", - "byteLogLikelihood": -4.679407897139, + "byteLogLikelihood": -3.984546441118, "hits": 0, - "total": 114, + "total": 135, "hitRate": 0 }, { "encoding": "x-mac-cyrillic", + "language": "uk", "confidence": 0, - "language": "ru", - "byteLogLikelihood": -3.753215851617, + "byteLogLikelihood": -4.187765411941, "hits": 0, - "total": 114, + "total": 136, "hitRate": 0 } ] }, { "expected": { - "encoding": "windows-1252", - "language": "pt" + "encoding": "windows-1250", + "language": "pl" }, "predicted": { - "encoding": "ISO-8859-15", - "confidence": 33, - "language": "pt", - "byteLogLikelihood": -3.970754139021, - "hits": 16, - "total": 143, - "hitRate": 0.11188811188811189 + "encoding": "windows-1250", + "language": "pl", + "confidence": 40, + "byteLogLikelihood": -3.52910527172, + "hits": 25, + "total": 184, + "hitRate": 0.1358695652173913 }, - "encodingExact": false, - "encodingEquivalent": true, + "encodingExact": true, + "encodingEquivalent": false, "encodingCorrect": true, "languageCorrect": true, "tiedAtTop": 1, "candidates": [ { - "encoding": "ISO-8859-15", - "confidence": 33, - "language": "es", - "byteLogLikelihood": -3.970754139021, - "hits": 16, - "total": 143, - "hitRate": 0.11188811188811189 + "encoding": "windows-1250", + "language": "pl", + "confidence": 40, + "byteLogLikelihood": -3.52910527172, + "hits": 25, + "total": 184, + "hitRate": 0.1358695652173913 + }, + { + "encoding": "ISO-8859-2", + "language": "pl", + "confidence": 37, + "byteLogLikelihood": -4.297518988235, + "hits": 23, + "total": 184, + "hitRate": 0.125 }, { "encoding": "ISO-8859-1", - "confidence": 50, - "language": "pt", - "byteLogLikelihood": -4.059947322987, - "hits": 24, - "total": 143, - "hitRate": 0.16783216783216784 + "language": "it", + "confidence": 8, + "byteLogLikelihood": -4.919980925828, + "hits": 5, + "total": 183, + "hitRate": 0.0273224043715847 }, { "encoding": "windows-1252", - "confidence": 50, - "language": "pt", - "byteLogLikelihood": -4.059947322987, - "hits": 24, - "total": 143, - "hitRate": 0.16783216783216784 + "language": "it", + "confidence": 8, + "byteLogLikelihood": -4.919980925828, + "hits": 5, + "total": 183, + "hitRate": 0.0273224043715847 }, { "encoding": "windows-1257", - "confidence": 29, - "language": "lt", - "byteLogLikelihood": -4.777390389123, - "hits": 14, - "total": 143, - "hitRate": 0.0979020979020979 - }, - { - "encoding": "ISO-8859-13", - "confidence": 29, - "language": "lt", - "byteLogLikelihood": -4.777390389123, - "hits": 14, - "total": 143, - "hitRate": 0.0979020979020979 + "language": "et", + "confidence": 6, + "byteLogLikelihood": -4.934473933131, + "hits": 4, + "total": 183, + "hitRate": 0.02185792349726776 }, { - "encoding": "macintosh", - "confidence": 31, + "encoding": "ISO-8859-15", "language": "es", - "byteLogLikelihood": -4.948759890378, - "hits": 15, - "total": 143, - "hitRate": 0.1048951048951049 + "confidence": 6, + "byteLogLikelihood": -4.396558412648, + "hits": 4, + "total": 183, + "hitRate": 0.02185792349726776 }, { - "encoding": "CP850", - "confidence": 31, + "encoding": "macintosh", "language": "es", - "byteLogLikelihood": -4.948759890378, - "hits": 15, - "total": 143, - "hitRate": 0.1048951048951049 + "confidence": 4, + "byteLogLikelihood": -4.826691858304, + "hits": 3, + "total": 184, + "hitRate": 0.016304347826086956 }, { "encoding": "ISO-8859-4", - "confidence": 23, "language": "lv", - "byteLogLikelihood": -5.19295685089, - "hits": 11, - "total": 143, - "hitRate": 0.07692307692307693 - }, - { - "encoding": "ISO-8859-2", - "confidence": 10, - "language": "hu", - "byteLogLikelihood": -3.361609233757, - "hits": 5, - "total": 143, - "hitRate": 0.03496503496503497 - }, - { - "encoding": "windows-1250", - "confidence": 10, - "language": "hu", - "byteLogLikelihood": -3.361609233757, - "hits": 5, - "total": 143, - "hitRate": 0.03496503496503497 - }, - { - "encoding": "ISO-8859-14", - "confidence": 10, - "language": "cy", - "byteLogLikelihood": -4.912654885736, - "hits": 5, - "total": 143, - "hitRate": 0.03496503496503497 - }, - { - "encoding": "windows-1258", - "confidence": 6, - "language": "vi", - "byteLogLikelihood": -4.524213150766, + "confidence": 4, + "byteLogLikelihood": -4.704684722593, "hits": 3, - "total": 143, - "hitRate": 0.02097902097902098 + "total": 184, + "hitRate": 0.016304347826086956 }, { "encoding": "ISO-8859-10", - "confidence": 6, "language": "is", - "byteLogLikelihood": -4.06291963921, - "hits": 3, - "total": 143, - "hitRate": 0.02097902097902098 - }, - { - "encoding": "ISO-8859-9", - "confidence": 2, - "language": "tr", - "byteLogLikelihood": -4.58869627797, - "hits": 1, - "total": 143, - "hitRate": 0.006993006993006993 - }, - { - "encoding": "windows-1254", - "confidence": 2, - "language": "tr", - "byteLogLikelihood": -4.58869627797, - "hits": 1, - "total": 143, - "hitRate": 0.006993006993006993 - }, - { - "encoding": "ISO-8859-16", - "confidence": 2, - "language": "ro", - "byteLogLikelihood": -5.220355825078, - "hits": 1, - "total": 143, - "hitRate": 0.006993006993006993 + "confidence": 3, + "byteLogLikelihood": -4.71573455878, + "hits": 2, + "total": 184, + "hitRate": 0.010869565217391304 }, { - "encoding": "CP852", - "confidence": 2, - "language": "pl", - "byteLogLikelihood": -5.087596335232, + "encoding": "ISO-8859-14", + "language": "cy", + "confidence": 1, + "byteLogLikelihood": -4.912654885736, "hits": 1, - "total": 143, - "hitRate": 0.006993006993006993 + "total": 184, + "hitRate": 0.005434782608695652 }, { - "encoding": "ISO-8859-5", + "encoding": "ISO-8859-7", + "language": "el", "confidence": 0, - "language": "ru", - "byteLogLikelihood": -4.338763438513, + "byteLogLikelihood": -4.848389618517, "hits": 0, - "total": 143, + "total": 184, "hitRate": 0 }, { - "encoding": "ISO-8859-6", + "encoding": "windows-1253", + "language": "el", "confidence": 0, - "language": "ar", - "byteLogLikelihood": -4.514449766028, + "byteLogLikelihood": -4.848389618517, "hits": 0, - "total": 143, + "total": 184, "hitRate": 0 + } + ] + }, + { + "expected": { + "encoding": "windows-1250", + "language": "ro" + }, + "predicted": { + "encoding": "ISO-8859-2", + "language": "ro", + "confidence": 41, + "byteLogLikelihood": -2.684539297542, + "hits": 28, + "total": 202, + "hitRate": 0.13861386138613863 + }, + "encodingExact": false, + "encodingEquivalent": true, + "encodingCorrect": true, + "languageCorrect": true, + "tiedAtTop": 2, + "candidates": [ + { + "encoding": "ISO-8859-2", + "language": "ro", + "confidence": 41, + "byteLogLikelihood": -2.684539297542, + "hits": 28, + "total": 202, + "hitRate": 0.13861386138613863 }, { - "encoding": "ISO-8859-7", - "confidence": 0, - "language": "el", - "byteLogLikelihood": -3.017269736716, - "hits": 0, - "total": 143, - "hitRate": 0 + "encoding": "windows-1250", + "language": "ro", + "confidence": 41, + "byteLogLikelihood": -2.684539297542, + "hits": 28, + "total": 202, + "hitRate": 0.13861386138613863 }, { - "encoding": "ISO-8859-8", - "confidence": 0, - "language": "he", - "byteLogLikelihood": -3.50352863905, - "hits": 0, - "total": 143, - "hitRate": 0 + "encoding": "ISO-8859-16", + "language": "ro", + "confidence": 38, + "byteLogLikelihood": -2.700458868498, + "hits": 26, + "total": 202, + "hitRate": 0.12871287128712872 }, { - "encoding": "windows-1251", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -3.846220145127, - "hits": 0, - "total": 143, - "hitRate": 0 + "encoding": "ISO-8859-1", + "language": "it", + "confidence": 26, + "byteLogLikelihood": -4.919980925828, + "hits": 18, + "total": 202, + "hitRate": 0.0891089108910891 }, { - "encoding": "windows-1253", - "confidence": 0, - "language": "el", - "byteLogLikelihood": -3.017269736716, - "hits": 0, - "total": 143, - "hitRate": 0 + "encoding": "windows-1252", + "language": "it", + "confidence": 26, + "byteLogLikelihood": -4.919980925828, + "hits": 18, + "total": 202, + "hitRate": 0.0891089108910891 }, { - "encoding": "windows-1255", + "encoding": "ISO-8859-5", + "language": "ru", "confidence": 0, - "language": "he", - "byteLogLikelihood": -3.50352863905, + "byteLogLikelihood": -4.208609169552, "hits": 0, - "total": 143, + "total": 202, "hitRate": 0 }, { - "encoding": "windows-1256", + "encoding": "ISO-8859-7", + "language": "el", "confidence": 0, - "language": "ar", - "byteLogLikelihood": -3.503504267293, + "byteLogLikelihood": -4.33505338151, "hits": 0, - "total": 143, + "total": 202, "hitRate": 0 }, { - "encoding": "windows-874", + "encoding": "ISO-8859-8", + "language": "he", "confidence": 0, - "language": "th", - "byteLogLikelihood": -4.91521504926, + "byteLogLikelihood": -4.197813655274, "hits": 0, - "total": 143, + "total": 201, "hitRate": 0 }, { - "encoding": "KOI8-R", - "confidence": 0, + "encoding": "windows-1251", "language": "ru", - "byteLogLikelihood": -6.518796947367, + "confidence": 0, + "byteLogLikelihood": -4.229886082374, "hits": 0, - "total": 143, + "total": 202, "hitRate": 0 }, { - "encoding": "KOI8-U", + "encoding": "windows-1255", + "language": "he", "confidence": 0, - "language": "uk", - "byteLogLikelihood": -6.476992253447, + "byteLogLikelihood": -4.197813655274, "hits": 0, - "total": 143, + "total": 201, "hitRate": 0 }, { "encoding": "IBM866", - "confidence": 0, "language": "ru", - "byteLogLikelihood": -4.338763438513, - "hits": 0, - "total": 143, - "hitRate": 0 - }, - { - "encoding": "IBM855", "confidence": 0, - "language": "sr", - "byteLogLikelihood": -3.774998078834, + "byteLogLikelihood": -4.208609169552, "hits": 0, - "total": 143, + "total": 201, "hitRate": 0 }, { "encoding": "x-mac-cyrillic", + "language": "ru", "confidence": 0, - "language": "uk", - "byteLogLikelihood": -3.766179593299, - "hits": 0, - "total": 143, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-3", - "confidence": 0, - "language": "mt", - "byteLogLikelihood": -5.105945473901, + "byteLogLikelihood": -4.229886082374, "hits": 0, - "total": 143, + "total": 202, "hitRate": 0 } ] }, { "expected": { - "encoding": "windows-1252", - "language": "sv" + "encoding": "windows-1251", + "language": "ru" }, "predicted": { - "encoding": "ISO-8859-1", - "confidence": 50, - "language": "sv", - "byteLogLikelihood": -3.23645137845, - "hits": 23, - "total": 136, - "hitRate": 0.16911764705882354 + "encoding": "windows-1251", + "language": "ru", + "confidence": 41, + "byteLogLikelihood": -3.313760777855, + "hits": 25, + "total": 179, + "hitRate": 0.13966480446927373 }, - "encodingExact": false, - "encodingEquivalent": true, + "encodingExact": true, + "encodingEquivalent": false, "encodingCorrect": true, "languageCorrect": true, - "tiedAtTop": 2, + "tiedAtTop": 1, "candidates": [ { - "encoding": "ISO-8859-1", - "confidence": 50, - "language": "sv", - "byteLogLikelihood": -3.23645137845, - "hits": 23, - "total": 136, - "hitRate": 0.16911764705882354 + "encoding": "windows-1251", + "language": "ru", + "confidence": 41, + "byteLogLikelihood": -3.313760777855, + "hits": 25, + "total": 179, + "hitRate": 0.13966480446927373 }, { - "encoding": "windows-1252", - "confidence": 50, - "language": "sv", - "byteLogLikelihood": -3.23645137845, - "hits": 23, - "total": 136, - "hitRate": 0.16911764705882354 + "encoding": "x-mac-cyrillic", + "language": "ru", + "confidence": 34, + "byteLogLikelihood": -3.411211853364, + "hits": 20, + "total": 175, + "hitRate": 0.11428571428571428 }, { - "encoding": "windows-1258", - "confidence": 19, - "language": "vi", - "byteLogLikelihood": -5.497168225293, - "hits": 9, - "total": 136, - "hitRate": 0.0661764705882353 + "encoding": "ISO-8859-8", + "language": "he", + "confidence": 3, + "byteLogLikelihood": -3.941595102268, + "hits": 2, + "total": 167, + "hitRate": 0.011976047904191617 }, { - "encoding": "ISO-8859-10", - "confidence": 19, - "language": "is", - "byteLogLikelihood": -4.980036753423, - "hits": 9, - "total": 136, - "hitRate": 0.0661764705882353 + "encoding": "windows-1255", + "language": "he", + "confidence": 3, + "byteLogLikelihood": -3.941595102268, + "hits": 2, + "total": 167, + "hitRate": 0.011976047904191617 }, { - "encoding": "macintosh", - "confidence": 17, - "language": "de", - "byteLogLikelihood": -5.003946305945, - "hits": 8, - "total": 136, - "hitRate": 0.058823529411764705 + "encoding": "ISO-8859-14", + "language": "cy", + "confidence": 1, + "byteLogLikelihood": -4.724449359889, + "hits": 1, + "total": 179, + "hitRate": 0.00558659217877095 }, { - "encoding": "ISO-8859-15", - "confidence": 17, - "language": "de", - "byteLogLikelihood": -4.137512330246, - "hits": 8, - "total": 136, - "hitRate": 0.058823529411764705 + "encoding": "ISO-8859-1", + "language": "sv", + "confidence": 0, + "byteLogLikelihood": -4.665227236998, + "hits": 0, + "total": 179, + "hitRate": 0 }, { - "encoding": "CP850", - "confidence": 17, - "language": "de", - "byteLogLikelihood": -5.003946305945, - "hits": 8, - "total": 136, - "hitRate": 0.058823529411764705 + "encoding": "ISO-8859-7", + "language": "el", + "confidence": 0, + "byteLogLikelihood": -4.209243802684, + "hits": 0, + "total": 176, + "hitRate": 0 }, { - "encoding": "ISO-8859-2", - "confidence": 15, - "language": "cs", - "byteLogLikelihood": -5.159055299215, - "hits": 7, - "total": 136, - "hitRate": 0.051470588235294115 + "encoding": "windows-1252", + "language": "sv", + "confidence": 0, + "byteLogLikelihood": -4.665227236998, + "hits": 0, + "total": 179, + "hitRate": 0 }, { - "encoding": "windows-1250", - "confidence": 15, - "language": "cs", - "byteLogLikelihood": -5.159055299215, - "hits": 7, - "total": 136, - "hitRate": 0.051470588235294115 + "encoding": "windows-1253", + "language": "el", + "confidence": 0, + "byteLogLikelihood": -4.209243802684, + "hits": 0, + "total": 176, + "hitRate": 0 + }, + { + "encoding": "windows-1257", + "language": "lv", + "confidence": 0, + "byteLogLikelihood": -4.61521723683, + "hits": 0, + "total": 176, + "hitRate": 0 + }, + { + "encoding": "ISO-8859-13", + "language": "lt", + "confidence": 0, + "byteLogLikelihood": -4.66408545306, + "hits": 0, + "total": 176, + "hitRate": 0 }, { - "encoding": "ISO-8859-9", - "confidence": 11, - "language": "tr", - "byteLogLikelihood": -4.93784727915, - "hits": 5, - "total": 136, - "hitRate": 0.03676470588235294 + "encoding": "ISO-8859-15", + "language": "fr", + "confidence": 0, + "byteLogLikelihood": -4.760478683076, + "hits": 0, + "total": 179, + "hitRate": 0 + } + ] + }, + { + "expected": { + "encoding": "windows-1252", + "language": "da" + }, + "predicted": { + "encoding": "ISO-8859-1", + "language": "da", + "confidence": 52, + "byteLogLikelihood": -3.146558879633, + "hits": 21, + "total": 120, + "hitRate": 0.175 + }, + "encodingExact": false, + "encodingEquivalent": true, + "encodingCorrect": true, + "languageCorrect": true, + "tiedAtTop": 2, + "candidates": [ + { + "encoding": "ISO-8859-1", + "language": "da", + "confidence": 52, + "byteLogLikelihood": -3.146558879633, + "hits": 21, + "total": 120, + "hitRate": 0.175 }, { - "encoding": "windows-1254", - "confidence": 11, - "language": "tr", - "byteLogLikelihood": -4.93784727915, - "hits": 5, - "total": 136, - "hitRate": 0.03676470588235294 + "encoding": "windows-1252", + "language": "da", + "confidence": 52, + "byteLogLikelihood": -3.146558879633, + "hits": 21, + "total": 120, + "hitRate": 0.175 }, { - "encoding": "ISO-8859-14", - "confidence": 8, - "language": "cy", - "byteLogLikelihood": -4.912654885736, + "encoding": "ISO-8859-2", + "language": "ro", + "confidence": 10, + "byteLogLikelihood": -5.176149732574, "hits": 4, - "total": 136, - "hitRate": 0.029411764705882353 + "total": 120, + "hitRate": 0.03333333333333333 }, { - "encoding": "ISO-8859-16", - "confidence": 6, + "encoding": "windows-1250", "language": "ro", - "byteLogLikelihood": -5.220355825078, - "hits": 3, - "total": 136, - "hitRate": 0.022058823529411766 + "confidence": 10, + "byteLogLikelihood": -5.176149732574, + "hits": 4, + "total": 120, + "hitRate": 0.03333333333333333 }, { "encoding": "windows-1257", - "confidence": 4, - "language": "lt", - "byteLogLikelihood": -5.123963979403, - "hits": 2, - "total": 136, - "hitRate": 0.014705882352941176 + "language": "et", + "confidence": 10, + "byteLogLikelihood": -4.934473933131, + "hits": 4, + "total": 120, + "hitRate": 0.03333333333333333 }, { "encoding": "ISO-8859-3", - "confidence": 4, "language": "mt", - "byteLogLikelihood": -4.210065739287, - "hits": 2, - "total": 136, - "hitRate": 0.014705882352941176 + "confidence": 2, + "byteLogLikelihood": -4.658005606594, + "hits": 1, + "total": 120, + "hitRate": 0.008333333333333333 }, { "encoding": "ISO-8859-13", - "confidence": 4, "language": "lt", - "byteLogLikelihood": -5.123963979403, - "hits": 2, - "total": 136, - "hitRate": 0.014705882352941176 - }, - { - "encoding": "CP852", - "confidence": 4, - "language": "pl", - "byteLogLikelihood": -5.087596335232, - "hits": 2, - "total": 136, - "hitRate": 0.014705882352941176 + "confidence": 2, + "byteLogLikelihood": -4.145958228046, + "hits": 1, + "total": 120, + "hitRate": 0.008333333333333333 }, { - "encoding": "ISO-8859-5", + "encoding": "ISO-8859-7", + "language": "el", "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.652362971667, + "byteLogLikelihood": -4.689401143463, "hits": 0, - "total": 136, + "total": 120, "hitRate": 0 }, { - "encoding": "ISO-8859-6", + "encoding": "ISO-8859-8", + "language": "he", "confidence": 0, - "language": "ar", - "byteLogLikelihood": -3.287368473007, + "byteLogLikelihood": -3.231348206195, "hits": 0, - "total": 136, + "total": 120, "hitRate": 0 }, { - "encoding": "ISO-8859-7", + "encoding": "windows-1251", + "language": "ru", "confidence": 0, - "language": "el", - "byteLogLikelihood": -3.876181596107, + "byteLogLikelihood": -4.288232392491, "hits": 0, - "total": 136, + "total": 120, "hitRate": 0 }, { - "encoding": "ISO-8859-8", - "confidence": 0, + "encoding": "windows-1255", "language": "he", - "byteLogLikelihood": -3.066153183614, + "confidence": 0, + "byteLogLikelihood": -3.231348206195, "hits": 0, - "total": 136, + "total": 120, "hitRate": 0 }, { - "encoding": "windows-1251", - "confidence": 0, + "encoding": "x-mac-cyrillic", "language": "ru", - "byteLogLikelihood": -3.393743210995, + "confidence": 0, + "byteLogLikelihood": -4.288232392491, "hits": 0, - "total": 136, + "total": 120, "hitRate": 0 + } + ] + }, + { + "expected": { + "encoding": "windows-1252", + "language": "de" + }, + "predicted": { + "encoding": "ISO-8859-1", + "language": "de", + "confidence": 73, + "byteLogLikelihood": -3.169712077519, + "hits": 53, + "total": 216, + "hitRate": 0.24537037037037038 + }, + "encodingExact": false, + "encodingEquivalent": true, + "encodingCorrect": true, + "languageCorrect": true, + "tiedAtTop": 3, + "candidates": [ + { + "encoding": "ISO-8859-1", + "language": "de", + "confidence": 73, + "byteLogLikelihood": -3.169712077519, + "hits": 53, + "total": 216, + "hitRate": 0.24537037037037038 }, { - "encoding": "windows-1253", - "confidence": 0, - "language": "el", - "byteLogLikelihood": -3.876181596107, - "hits": 0, - "total": 136, - "hitRate": 0 + "encoding": "ISO-8859-15", + "language": "de", + "confidence": 73, + "byteLogLikelihood": -3.169712077519, + "hits": 53, + "total": 216, + "hitRate": 0.24537037037037038 }, { - "encoding": "windows-1255", - "confidence": 0, - "language": "he", - "byteLogLikelihood": -3.066153183614, - "hits": 0, - "total": 136, - "hitRate": 0 + "encoding": "windows-1252", + "language": "de", + "confidence": 73, + "byteLogLikelihood": -3.169712077519, + "hits": 53, + "total": 216, + "hitRate": 0.24537037037037038 }, { - "encoding": "windows-1256", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -4.25594643617, - "hits": 0, - "total": 136, - "hitRate": 0 + "encoding": "ISO-8859-9", + "language": "tr", + "confidence": 12, + "byteLogLikelihood": -4.5258676709, + "hits": 9, + "total": 216, + "hitRate": 0.041666666666666664 }, { - "encoding": "windows-874", + "encoding": "windows-1257", + "language": "lv", + "confidence": 9, + "byteLogLikelihood": -5.19295685089, + "hits": 7, + "total": 216, + "hitRate": 0.032407407407407406 + }, + { + "encoding": "ISO-8859-6", + "language": "ar", "confidence": 0, - "language": "th", - "byteLogLikelihood": -5.801526726218, + "byteLogLikelihood": -4.007313397456, "hits": 0, - "total": 136, + "total": 216, "hitRate": 0 }, { - "encoding": "KOI8-R", + "encoding": "ISO-8859-7", + "language": "el", "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.432153549797, + "byteLogLikelihood": -4.349754587225, "hits": 0, - "total": 136, + "total": 216, "hitRate": 0 }, { - "encoding": "KOI8-U", + "encoding": "ISO-8859-8", + "language": "he", "confidence": 0, - "language": "uk", - "byteLogLikelihood": -6.390348855877, + "byteLogLikelihood": -4.279537403415, "hits": 0, - "total": 136, + "total": 216, "hitRate": 0 }, { - "encoding": "IBM866", + "encoding": "windows-1253", + "language": "el", "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.652362971667, + "byteLogLikelihood": -4.349754587225, "hits": 0, - "total": 136, + "total": 216, "hitRate": 0 }, { - "encoding": "IBM855", + "encoding": "windows-1255", + "language": "he", "confidence": 0, - "language": "ru", - "byteLogLikelihood": -4.419477704429, + "byteLogLikelihood": -4.279537403415, "hits": 0, - "total": 136, + "total": 216, "hitRate": 0 }, { - "encoding": "x-mac-cyrillic", + "encoding": "windows-1256", + "language": "ar", "confidence": 0, - "language": "ru", - "byteLogLikelihood": -3.393743210995, + "byteLogLikelihood": -4.318835143108, "hits": 0, - "total": 136, + "total": 216, "hitRate": 0 }, { - "encoding": "ISO-8859-4", + "encoding": "x-mac-cyrillic", + "language": "uk", "confidence": 0, - "language": "lv", - "byteLogLikelihood": -5.19295685089, + "byteLogLikelihood": -3.629332579687, "hits": 0, - "total": 136, + "total": 216, "hitRate": 0 } ] }, { "expected": { - "encoding": "windows-1253", - "language": "el" + "encoding": "windows-1252", + "language": "en" }, "predicted": { - "encoding": "ISO-8859-7", - "confidence": 51, - "language": "el", - "byteLogLikelihood": -3.435199502, - "hits": 23, - "total": 134, - "hitRate": 0.17164179104477612 + "encoding": "ISO-8859-1", + "language": "en", + "confidence": 47, + "byteLogLikelihood": -3.310543013394, + "hits": 21, + "total": 132, + "hitRate": 0.1590909090909091 }, "encodingExact": false, "encodingEquivalent": true, @@ -17180,308 +6238,388 @@ "tiedAtTop": 2, "candidates": [ { - "encoding": "ISO-8859-7", - "confidence": 51, - "language": "el", - "byteLogLikelihood": -3.435199502, - "hits": 23, - "total": 134, - "hitRate": 0.17164179104477612 + "encoding": "ISO-8859-1", + "language": "en", + "confidence": 47, + "byteLogLikelihood": -3.310543013394, + "hits": 21, + "total": 132, + "hitRate": 0.1590909090909091 }, { - "encoding": "windows-1253", - "confidence": 51, - "language": "el", - "byteLogLikelihood": -3.435199502, - "hits": 23, - "total": 134, - "hitRate": 0.17164179104477612 + "encoding": "ISO-8859-15", + "language": "fr", + "confidence": 29, + "byteLogLikelihood": -2.06619631493, + "hits": 13, + "total": 132, + "hitRate": 0.09848484848484848 }, { - "encoding": "KOI8-U", - "confidence": 8, - "language": "uk", - "byteLogLikelihood": -6.254780178237, - "hits": 4, - "total": 134, - "hitRate": 0.029850746268656716 + "encoding": "windows-1252", + "language": "en", + "confidence": 47, + "byteLogLikelihood": -3.310543013394, + "hits": 21, + "total": 132, + "hitRate": 0.1590909090909091 }, { - "encoding": "IBM855", - "confidence": 7, - "language": "ru", - "byteLogLikelihood": -5.358823187498, - "hits": 3, - "total": 118, - "hitRate": 0.025423728813559324 + "encoding": "ISO-8859-2", + "language": "cs", + "confidence": 9, + "byteLogLikelihood": -3.54961738678, + "hits": 4, + "total": 132, + "hitRate": 0.030303030303030304 }, { - "encoding": "KOI8-R", - "confidence": 4, - "language": "ru", - "byteLogLikelihood": -6.302671202821, - "hits": 2, - "total": 134, - "hitRate": 0.014925373134328358 + "encoding": "windows-1250", + "language": "cs", + "confidence": 9, + "byteLogLikelihood": -3.54961738678, + "hits": 4, + "total": 132, + "hitRate": 0.030303030303030304 }, { - "encoding": "ISO-8859-6", - "confidence": 3, - "language": "ar", - "byteLogLikelihood": -5.268243094623, - "hits": 1, - "total": 81, - "hitRate": 0.012345679012345678 + "encoding": "ISO-8859-7", + "language": "el", + "confidence": 0, + "byteLogLikelihood": -2.654561516151, + "hits": 0, + "total": 132, + "hitRate": 0 }, { "encoding": "ISO-8859-8", - "confidence": 2, - "language": "he", - "byteLogLikelihood": -4.09495359507, - "hits": 1, - "total": 127, - "hitRate": 0.007874015748031496 - }, - { - "encoding": "windows-1255", - "confidence": 2, "language": "he", - "byteLogLikelihood": -4.09495359507, - "hits": 1, - "total": 127, - "hitRate": 0.007874015748031496 - }, - { - "encoding": "x-mac-cyrillic", - "confidence": 2, - "language": "uk", - "byteLogLikelihood": -4.203232324163, - "hits": 1, - "total": 131, - "hitRate": 0.007633587786259542 - }, - { - "encoding": "ISO-8859-1", "confidence": 0, - "language": "pt", - "byteLogLikelihood": -4.59932343766, + "byteLogLikelihood": -2.405884662832, "hits": 0, - "total": 134, + "total": 132, "hitRate": 0 }, { - "encoding": "ISO-8859-2", + "encoding": "windows-1253", + "language": "el", "confidence": 0, - "language": "hu", - "byteLogLikelihood": -4.358825259583, + "byteLogLikelihood": -2.654561516151, "hits": 0, - "total": 134, + "total": 132, "hitRate": 0 }, { - "encoding": "ISO-8859-5", + "encoding": "windows-1255", + "language": "he", "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.165809265202, + "byteLogLikelihood": -2.405884662832, "hits": 0, - "total": 130, + "total": 132, "hitRate": 0 }, { - "encoding": "ISO-8859-9", + "encoding": "windows-874", + "language": "th", "confidence": 0, - "language": "tr", - "byteLogLikelihood": -4.969377662519, + "byteLogLikelihood": -3.57655026914, "hits": 0, - "total": 133, + "total": 131, "hitRate": 0 }, { - "encoding": "windows-1250", + "encoding": "x-mac-cyrillic", + "language": "uk", "confidence": 0, - "language": "hu", - "byteLogLikelihood": -4.358825259583, + "byteLogLikelihood": -4.252383775789, "hits": 0, - "total": 134, + "total": 132, "hitRate": 0 }, { - "encoding": "windows-1251", + "encoding": "ISO-8859-10", + "language": "is", "confidence": 0, - "language": "ru", - "byteLogLikelihood": -4.288697198304, + "byteLogLikelihood": -4.510859506517, "hits": 0, - "total": 134, + "total": 132, "hitRate": 0 + } + ] + }, + { + "expected": { + "encoding": "windows-1252", + "language": "es" + }, + "predicted": { + "encoding": "ISO-8859-1", + "language": "es", + "confidence": 61, + "byteLogLikelihood": -3.834657935767, + "hits": 41, + "total": 200, + "hitRate": 0.205 + }, + "encodingExact": false, + "encodingEquivalent": true, + "encodingCorrect": true, + "languageCorrect": true, + "tiedAtTop": 3, + "candidates": [ + { + "encoding": "ISO-8859-1", + "language": "es", + "confidence": 61, + "byteLogLikelihood": -3.834657935767, + "hits": 41, + "total": 200, + "hitRate": 0.205 + }, + { + "encoding": "ISO-8859-15", + "language": "es", + "confidence": 61, + "byteLogLikelihood": -3.834657935767, + "hits": 41, + "total": 200, + "hitRate": 0.205 }, { "encoding": "windows-1252", - "confidence": 0, - "language": "pt", - "byteLogLikelihood": -4.59932343766, - "hits": 0, - "total": 134, - "hitRate": 0 + "language": "es", + "confidence": 61, + "byteLogLikelihood": -3.834657935767, + "hits": 41, + "total": 200, + "hitRate": 0.205 + }, + { + "encoding": "ISO-8859-2", + "language": "ro", + "confidence": 15, + "byteLogLikelihood": -5.176149732574, + "hits": 10, + "total": 200, + "hitRate": 0.05 + }, + { + "encoding": "windows-1250", + "language": "ro", + "confidence": 15, + "byteLogLikelihood": -5.176149732574, + "hits": 10, + "total": 200, + "hitRate": 0.05 }, { - "encoding": "windows-1254", + "encoding": "ISO-8859-7", + "language": "el", "confidence": 0, - "language": "tr", - "byteLogLikelihood": -4.969377662519, + "byteLogLikelihood": -3.106555532888, "hits": 0, - "total": 133, + "total": 200, "hitRate": 0 }, { - "encoding": "windows-1256", + "encoding": "ISO-8859-8", + "language": "he", "confidence": 0, - "language": "ar", - "byteLogLikelihood": -5.013410783916, + "byteLogLikelihood": -3.411159813207, "hits": 0, - "total": 122, + "total": 200, "hitRate": 0 }, { - "encoding": "windows-1257", + "encoding": "windows-1251", + "language": "ru", "confidence": 0, - "language": "et", - "byteLogLikelihood": -4.827626146169, + "byteLogLikelihood": -3.336328204376, "hits": 0, - "total": 134, + "total": 200, "hitRate": 0 }, { - "encoding": "windows-1258", + "encoding": "windows-1253", + "language": "el", "confidence": 0, - "language": "vi", - "byteLogLikelihood": -4.681848366371, + "byteLogLikelihood": -3.106555532888, "hits": 0, - "total": 127, + "total": 200, "hitRate": 0 }, { - "encoding": "windows-874", + "encoding": "windows-1255", + "language": "he", "confidence": 0, - "language": "th", - "byteLogLikelihood": -5.483358374511, + "byteLogLikelihood": -3.411159813207, "hits": 0, - "total": 52, + "total": 200, "hitRate": 0 }, { - "encoding": "IBM866", + "encoding": "windows-1256", + "language": "ar", "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.55248803416, + "byteLogLikelihood": -3.300604963183, "hits": 0, - "total": 127, + "total": 200, "hitRate": 0 }, { - "encoding": "macintosh", + "encoding": "x-mac-cyrillic", + "language": "ru", "confidence": 0, - "language": "es", - "byteLogLikelihood": -4.948759890378, + "byteLogLikelihood": -3.336328204376, "hits": 0, - "total": 116, + "total": 200, "hitRate": 0 + } + ] + }, + { + "expected": { + "encoding": "windows-1252", + "language": "fr" + }, + "predicted": { + "encoding": "ISO-8859-1", + "language": "fr", + "confidence": 77, + "byteLogLikelihood": -2.06619631493, + "hits": 59, + "total": 228, + "hitRate": 0.25877192982456143 + }, + "encodingExact": false, + "encodingEquivalent": true, + "encodingCorrect": true, + "languageCorrect": true, + "tiedAtTop": 3, + "candidates": [ + { + "encoding": "ISO-8859-1", + "language": "fr", + "confidence": 77, + "byteLogLikelihood": -2.06619631493, + "hits": 59, + "total": 228, + "hitRate": 0.25877192982456143 }, { - "encoding": "ISO-8859-3", - "confidence": 0, - "language": "mt", - "byteLogLikelihood": -4.945729021813, - "hits": 0, - "total": 129, - "hitRate": 0 + "encoding": "ISO-8859-15", + "language": "fr", + "confidence": 77, + "byteLogLikelihood": -2.06619631493, + "hits": 59, + "total": 228, + "hitRate": 0.25877192982456143 }, { - "encoding": "ISO-8859-4", - "confidence": 0, - "language": "lv", - "byteLogLikelihood": -5.015268979336, - "hits": 0, - "total": 134, - "hitRate": 0 + "encoding": "windows-1252", + "language": "fr", + "confidence": 77, + "byteLogLikelihood": -2.06619631493, + "hits": 59, + "total": 228, + "hitRate": 0.25877192982456143 + }, + { + "encoding": "ISO-8859-2", + "language": "ro", + "confidence": 11, + "byteLogLikelihood": -5.176149732574, + "hits": 9, + "total": 228, + "hitRate": 0.039473684210526314 + }, + { + "encoding": "windows-1250", + "language": "ro", + "confidence": 11, + "byteLogLikelihood": -5.176149732574, + "hits": 9, + "total": 228, + "hitRate": 0.039473684210526314 }, { "encoding": "ISO-8859-10", - "confidence": 0, "language": "is", - "byteLogLikelihood": -4.576407109739, - "hits": 0, - "total": 134, - "hitRate": 0 + "confidence": 10, + "byteLogLikelihood": -4.510859506517, + "hits": 8, + "total": 228, + "hitRate": 0.03508771929824561 }, { - "encoding": "ISO-8859-13", + "encoding": "ISO-8859-7", + "language": "el", "confidence": 0, - "language": "lt", - "byteLogLikelihood": -4.890771320266, + "byteLogLikelihood": -2.654561516151, "hits": 0, - "total": 134, + "total": 228, "hitRate": 0 }, { - "encoding": "ISO-8859-14", + "encoding": "ISO-8859-8", + "language": "he", "confidence": 0, - "language": "cy", - "byteLogLikelihood": -4.788878603493, + "byteLogLikelihood": -2.405884662832, "hits": 0, - "total": 134, + "total": 228, "hitRate": 0 }, { - "encoding": "ISO-8859-15", + "encoding": "windows-1253", + "language": "el", "confidence": 0, - "language": "es", - "byteLogLikelihood": -4.603974037796, + "byteLogLikelihood": -2.654561516151, "hits": 0, - "total": 134, + "total": 228, "hitRate": 0 }, { - "encoding": "ISO-8859-16", + "encoding": "windows-1255", + "language": "he", "confidence": 0, - "language": "ro", - "byteLogLikelihood": -5.137560045078, + "byteLogLikelihood": -2.405884662832, "hits": 0, - "total": 134, + "total": 228, "hitRate": 0 }, { - "encoding": "CP850", + "encoding": "windows-874", + "language": "th", "confidence": 0, - "language": "es", - "byteLogLikelihood": -4.948759890378, + "byteLogLikelihood": -3.57655026914, "hits": 0, - "total": 93, + "total": 224, "hitRate": 0 }, { - "encoding": "CP852", + "encoding": "x-mac-cyrillic", + "language": "uk", "confidence": 0, - "language": "pl", - "byteLogLikelihood": -5.087596335232, + "byteLogLikelihood": -4.252383775789, "hits": 0, - "total": 96, + "total": 228, "hitRate": 0 } ] }, { "expected": { - "encoding": "windows-1254", - "language": "tr" + "encoding": "windows-1252", + "language": "it" }, "predicted": { - "encoding": "ISO-8859-9", - "confidence": 55, - "language": "tr", - "byteLogLikelihood": -3.531675216773, - "hits": 25, - "total": 134, - "hitRate": 0.1865671641791045 + "encoding": "ISO-8859-1", + "language": "it", + "confidence": 58, + "byteLogLikelihood": -3.533686564708, + "hits": 31, + "total": 159, + "hitRate": 0.1949685534591195 }, "encodingExact": false, "encodingEquivalent": true, @@ -17489,309 +6627,259 @@ "languageCorrect": true, "tiedAtTop": 2, "candidates": [ - { - "encoding": "ISO-8859-9", - "confidence": 55, - "language": "tr", - "byteLogLikelihood": -3.531675216773, - "hits": 25, - "total": 134, - "hitRate": 0.1865671641791045 - }, - { - "encoding": "windows-1254", - "confidence": 55, - "language": "tr", - "byteLogLikelihood": -3.531675216773, - "hits": 25, - "total": 134, - "hitRate": 0.1865671641791045 - }, - { - "encoding": "ISO-8859-3", - "confidence": 22, - "language": "mt", - "byteLogLikelihood": -5.105945473901, - "hits": 10, - "total": 134, - "hitRate": 0.07462686567164178 - }, { "encoding": "ISO-8859-1", - "confidence": 17, - "language": "da", - "byteLogLikelihood": -4.969813299576, - "hits": 8, - "total": 134, - "hitRate": 0.05970149253731343 - }, - { - "encoding": "windows-1252", - "confidence": 17, - "language": "da", - "byteLogLikelihood": -4.969813299576, - "hits": 8, - "total": 134, - "hitRate": 0.05970149253731343 - }, - { - "encoding": "ISO-8859-10", - "confidence": 17, - "language": "is", - "byteLogLikelihood": -4.720106560713, - "hits": 8, - "total": 134, - "hitRate": 0.05970149253731343 + "language": "it", + "confidence": 58, + "byteLogLikelihood": -3.533686564708, + "hits": 31, + "total": 159, + "hitRate": 0.1949685534591195 }, - { - "encoding": "ISO-8859-2", - "confidence": 13, - "language": "ro", - "byteLogLikelihood": -4.352190516073, - "hits": 6, - "total": 134, - "hitRate": 0.04477611940298507 + { + "encoding": "windows-1252", + "language": "it", + "confidence": 58, + "byteLogLikelihood": -3.533686564708, + "hits": 31, + "total": 159, + "hitRate": 0.1949685534591195 }, { - "encoding": "windows-1250", - "confidence": 13, - "language": "ro", - "byteLogLikelihood": -4.352190516073, - "hits": 6, - "total": 134, - "hitRate": 0.04477611940298507 + "encoding": "windows-1258", + "language": "vi", + "confidence": 16, + "byteLogLikelihood": -3.012261575505, + "hits": 9, + "total": 159, + "hitRate": 0.05660377358490566 }, { "encoding": "windows-1257", - "confidence": 11, "language": "lv", - "byteLogLikelihood": -3.613497993373, - "hits": 5, - "total": 134, - "hitRate": 0.03731343283582089 - }, - { - "encoding": "macintosh", - "confidence": 11, - "language": "es", - "byteLogLikelihood": -4.948759890378, - "hits": 5, - "total": 132, - "hitRate": 0.03787878787878788 + "confidence": 15, + "byteLogLikelihood": -5.19295685089, + "hits": 8, + "total": 159, + "hitRate": 0.050314465408805034 }, { "encoding": "ISO-8859-4", - "confidence": 11, "language": "lv", - "byteLogLikelihood": -4.93302665818, - "hits": 5, - "total": 134, - "hitRate": 0.03731343283582089 + "confidence": 15, + "byteLogLikelihood": -1.974081026022, + "hits": 8, + "total": 159, + "hitRate": 0.050314465408805034 }, { "encoding": "ISO-8859-13", - "confidence": 11, "language": "lt", - "byteLogLikelihood": -4.394247673508, - "hits": 5, - "total": 134, - "hitRate": 0.03731343283582089 - }, - { - "encoding": "ISO-8859-15", - "confidence": 11, - "language": "es", - "byteLogLikelihood": -4.948759890378, - "hits": 5, - "total": 134, - "hitRate": 0.03731343283582089 - }, - { - "encoding": "ISO-8859-16", - "confidence": 11, - "language": "ro", - "byteLogLikelihood": -4.25849981603, - "hits": 5, - "total": 134, - "hitRate": 0.03731343283582089 - }, - { - "encoding": "CP850", - "confidence": 11, - "language": "es", - "byteLogLikelihood": -4.948759890378, - "hits": 5, - "total": 132, - "hitRate": 0.03787878787878788 - }, - { - "encoding": "ISO-8859-14", - "confidence": 8, - "language": "cy", - "byteLogLikelihood": -4.652724693026, - "hits": 4, - "total": 134, - "hitRate": 0.029850746268656716 - }, - { - "encoding": "windows-1258", - "confidence": 6, - "language": "vi", - "byteLogLikelihood": -5.197431316193, - "hits": 3, - "total": 133, - "hitRate": 0.022556390977443608 - }, - { - "encoding": "CP852", - "confidence": 6, - "language": "pl", - "byteLogLikelihood": -5.087596335232, - "hits": 3, - "total": 133, - "hitRate": 0.022556390977443608 + "confidence": 3, + "byteLogLikelihood": -3.332204510175, + "hits": 2, + "total": 159, + "hitRate": 0.012578616352201259 }, { "encoding": "ISO-8859-5", - "confidence": 0, "language": "ru", - "byteLogLikelihood": -5.88736478629, + "confidence": 0, + "byteLogLikelihood": -2.954414124223, "hits": 0, - "total": 133, + "total": 159, "hitRate": 0 }, { - "encoding": "ISO-8859-6", + "encoding": "ISO-8859-8", + "language": "he", "confidence": 0, - "language": "ar", - "byteLogLikelihood": -5.217802445218, + "byteLogLikelihood": -3.629660094454, "hits": 0, - "total": 132, + "total": 159, "hitRate": 0 }, { - "encoding": "ISO-8859-7", + "encoding": "windows-1251", + "language": "ru", "confidence": 0, - "language": "el", - "byteLogLikelihood": -4.216966174066, + "byteLogLikelihood": -2.533200659147, "hits": 0, - "total": 134, + "total": 159, "hitRate": 0 }, { - "encoding": "ISO-8859-8", + "encoding": "windows-874", + "language": "th", "confidence": 0, - "language": "he", - "byteLogLikelihood": -4.95929011292, + "byteLogLikelihood": -3.496507561466, "hits": 0, - "total": 132, + "total": 159, "hitRate": 0 }, { - "encoding": "windows-1251", - "confidence": 0, + "encoding": "IBM866", "language": "ru", - "byteLogLikelihood": -4.576073075491, + "confidence": 0, + "byteLogLikelihood": -2.954414124223, "hits": 0, - "total": 134, + "total": 159, "hitRate": 0 }, { - "encoding": "windows-1253", + "encoding": "x-mac-cyrillic", + "language": "ru", "confidence": 0, - "language": "el", - "byteLogLikelihood": -4.216966174066, + "byteLogLikelihood": -2.533200659147, "hits": 0, - "total": 134, + "total": 159, "hitRate": 0 + } + ] + }, + { + "expected": { + "encoding": "windows-1252", + "language": "nl" + }, + "predicted": { + "encoding": "ISO-8859-1", + "language": "nl", + "confidence": 83, + "byteLogLikelihood": -3.295836866004, + "hits": 42, + "total": 151, + "hitRate": 0.2781456953642384 + }, + "encodingExact": false, + "encodingEquivalent": true, + "encodingCorrect": true, + "languageCorrect": true, + "tiedAtTop": 2, + "candidates": [ + { + "encoding": "ISO-8859-1", + "language": "nl", + "confidence": 83, + "byteLogLikelihood": -3.295836866004, + "hits": 42, + "total": 151, + "hitRate": 0.2781456953642384 }, { - "encoding": "windows-1255", - "confidence": 0, - "language": "he", - "byteLogLikelihood": -4.95929011292, - "hits": 0, - "total": 132, - "hitRate": 0 + "encoding": "ISO-8859-15", + "language": "de", + "confidence": 63, + "byteLogLikelihood": -5.003946305945, + "hits": 32, + "total": 151, + "hitRate": 0.2119205298013245 }, { - "encoding": "windows-1256", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -6.113682179832, - "hits": 0, - "total": 132, - "hitRate": 0 + "encoding": "windows-1252", + "language": "nl", + "confidence": 83, + "byteLogLikelihood": -3.295836866004, + "hits": 42, + "total": 151, + "hitRate": 0.2781456953642384 }, { - "encoding": "windows-874", + "encoding": "ISO-8859-2", + "language": "ro", + "confidence": 13, + "byteLogLikelihood": -5.176149732574, + "hits": 7, + "total": 151, + "hitRate": 0.046357615894039736 + }, + { + "encoding": "windows-1250", + "language": "ro", + "confidence": 13, + "byteLogLikelihood": -5.176149732574, + "hits": 7, + "total": 151, + "hitRate": 0.046357615894039736 + }, + { + "encoding": "ISO-8859-10", + "language": "is", + "confidence": 11, + "byteLogLikelihood": -4.510859506517, + "hits": 6, + "total": 151, + "hitRate": 0.039735099337748346 + }, + { + "encoding": "ISO-8859-7", + "language": "el", "confidence": 0, - "language": "th", - "byteLogLikelihood": -5.714883328648, + "byteLogLikelihood": -2.654561516151, "hits": 0, - "total": 130, + "total": 151, "hitRate": 0 }, { - "encoding": "KOI8-R", + "encoding": "ISO-8859-8", + "language": "he", "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.085579959517, + "byteLogLikelihood": -2.405884662832, "hits": 0, - "total": 134, + "total": 151, "hitRate": 0 }, { - "encoding": "KOI8-U", + "encoding": "windows-1253", + "language": "el", "confidence": 0, - "language": "uk", - "byteLogLikelihood": -6.303705458307, + "byteLogLikelihood": -2.654561516151, "hits": 0, - "total": 134, + "total": 151, "hitRate": 0 }, { - "encoding": "IBM866", + "encoding": "windows-1255", + "language": "he", "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.88736478629, + "byteLogLikelihood": -2.405884662832, "hits": 0, - "total": 132, + "total": 151, "hitRate": 0 }, { - "encoding": "IBM855", + "encoding": "windows-874", + "language": "th", "confidence": 0, - "language": "sr", - "byteLogLikelihood": -4.742947096814, + "byteLogLikelihood": -3.57655026914, "hits": 0, - "total": 132, + "total": 150, "hitRate": 0 }, { "encoding": "x-mac-cyrillic", - "confidence": 0, "language": "uk", - "byteLogLikelihood": -4.22610845571, + "confidence": 0, + "byteLogLikelihood": -4.252383775789, "hits": 0, - "total": 134, + "total": 151, "hitRate": 0 } ] }, { "expected": { - "encoding": "windows-1255", - "language": "he" + "encoding": "windows-1252", + "language": "no" }, "predicted": { - "encoding": "ISO-8859-8", + "encoding": "ISO-8859-1", + "language": "no", "confidence": 47, - "language": "he", - "byteLogLikelihood": -3.320333973076, - "hits": 16, - "total": 102, - "hitRate": 0.1568627450980392 + "byteLogLikelihood": -3.052495812716, + "hits": 18, + "total": 114, + "hitRate": 0.15789473684210525 }, "encodingExact": false, "encodingEquivalent": true, @@ -17800,618 +6888,778 @@ "tiedAtTop": 2, "candidates": [ { - "encoding": "ISO-8859-8", + "encoding": "ISO-8859-1", + "language": "no", "confidence": 47, - "language": "he", - "byteLogLikelihood": -3.320333973076, - "hits": 16, - "total": 102, - "hitRate": 0.1568627450980392 + "byteLogLikelihood": -3.052495812716, + "hits": 18, + "total": 114, + "hitRate": 0.15789473684210525 }, { - "encoding": "windows-1255", + "encoding": "windows-1252", + "language": "no", "confidence": 47, - "language": "he", - "byteLogLikelihood": -3.320333973076, - "hits": 16, - "total": 102, - "hitRate": 0.1568627450980392 + "byteLogLikelihood": -3.052495812716, + "hits": 18, + "total": 114, + "hitRate": 0.15789473684210525 }, { - "encoding": "ISO-8859-7", - "confidence": 2, - "language": "el", - "byteLogLikelihood": -3.981926233577, - "hits": 1, - "total": 102, - "hitRate": 0.00980392156862745 + "encoding": "ISO-8859-2", + "language": "cs", + "confidence": 7, + "byteLogLikelihood": -4.354336342997, + "hits": 3, + "total": 114, + "hitRate": 0.02631578947368421 }, { - "encoding": "windows-1253", + "encoding": "windows-1257", + "language": "et", + "confidence": 7, + "byteLogLikelihood": -4.934473933131, + "hits": 3, + "total": 114, + "hitRate": 0.02631578947368421 + }, + { + "encoding": "ISO-8859-3", + "language": "mt", "confidence": 2, - "language": "el", - "byteLogLikelihood": -3.981926233577, + "byteLogLikelihood": -4.210065739287, "hits": 1, - "total": 102, - "hitRate": 0.00980392156862745 + "total": 114, + "hitRate": 0.008771929824561403 }, { - "encoding": "IBM855", + "encoding": "ISO-8859-13", + "language": "lt", "confidence": 2, - "language": "ru", - "byteLogLikelihood": -5.394495827364, + "byteLogLikelihood": -4.319245023186, "hits": 1, - "total": 102, - "hitRate": 0.00980392156862745 + "total": 114, + "hitRate": 0.008771929824561403 }, { - "encoding": "ISO-8859-1", + "encoding": "ISO-8859-7", + "language": "el", "confidence": 0, - "language": "sv", - "byteLogLikelihood": -4.395116706452, + "byteLogLikelihood": -4.154384602589, "hits": 0, - "total": 102, + "total": 114, "hitRate": 0 }, { - "encoding": "ISO-8859-2", + "encoding": "ISO-8859-8", + "language": "he", "confidence": 0, - "language": "cs", - "byteLogLikelihood": -4.461975046319, + "byteLogLikelihood": -2.647504477241, "hits": 0, - "total": 102, + "total": 114, "hitRate": 0 }, { - "encoding": "ISO-8859-5", - "confidence": 0, + "encoding": "windows-1251", "language": "ru", - "byteLogLikelihood": -5.683415446443, - "hits": 0, - "total": 102, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-6", "confidence": 0, - "language": "ar", - "byteLogLikelihood": -5.124491051534, + "byteLogLikelihood": -3.753215851617, "hits": 0, - "total": 73, + "total": 114, "hitRate": 0 }, { - "encoding": "ISO-8859-9", + "encoding": "windows-1253", + "language": "el", "confidence": 0, - "language": "tr", - "byteLogLikelihood": -4.941685614581, + "byteLogLikelihood": -4.154384602589, "hits": 0, - "total": 102, + "total": 114, "hitRate": 0 }, { - "encoding": "windows-1250", + "encoding": "windows-1255", + "language": "he", "confidence": 0, - "language": "cs", - "byteLogLikelihood": -4.461975046319, + "byteLogLikelihood": -2.647504477241, "hits": 0, - "total": 102, + "total": 114, "hitRate": 0 }, { - "encoding": "windows-1251", - "confidence": 0, + "encoding": "x-mac-cyrillic", "language": "ru", - "byteLogLikelihood": -4.199203901043, - "hits": 0, - "total": 102, - "hitRate": 0 - }, - { - "encoding": "windows-1252", "confidence": 0, - "language": "sv", - "byteLogLikelihood": -4.395116706452, + "byteLogLikelihood": -3.753215851617, "hits": 0, - "total": 102, + "total": 114, "hitRate": 0 - }, + } + ] + }, + { + "expected": { + "encoding": "windows-1252", + "language": "pt" + }, + "predicted": { + "encoding": "ISO-8859-1", + "language": "pt", + "confidence": 50, + "byteLogLikelihood": -4.059947322987, + "hits": 24, + "total": 143, + "hitRate": 0.16783216783216784 + }, + "encodingExact": false, + "encodingEquivalent": true, + "encodingCorrect": true, + "languageCorrect": true, + "tiedAtTop": 2, + "candidates": [ { - "encoding": "windows-1254", - "confidence": 0, - "language": "tr", - "byteLogLikelihood": -4.941685614581, - "hits": 0, - "total": 102, - "hitRate": 0 + "encoding": "ISO-8859-1", + "language": "pt", + "confidence": 50, + "byteLogLikelihood": -4.059947322987, + "hits": 24, + "total": 143, + "hitRate": 0.16783216783216784 }, { - "encoding": "windows-1256", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -5.32364067176, - "hits": 0, - "total": 93, - "hitRate": 0 + "encoding": "windows-1252", + "language": "pt", + "confidence": 50, + "byteLogLikelihood": -4.059947322987, + "hits": 24, + "total": 143, + "hitRate": 0.16783216783216784 }, { - "encoding": "windows-1257", - "confidence": 0, - "language": "et", - "byteLogLikelihood": -4.639272141503, - "hits": 0, - "total": 102, - "hitRate": 0 + "encoding": "ISO-8859-2", + "language": "hu", + "confidence": 10, + "byteLogLikelihood": -3.361609233757, + "hits": 5, + "total": 143, + "hitRate": 0.03496503496503497 }, { - "encoding": "windows-1258", - "confidence": 0, - "language": "vi", - "byteLogLikelihood": -5.029681805165, - "hits": 0, - "total": 99, - "hitRate": 0 + "encoding": "windows-1250", + "language": "hu", + "confidence": 10, + "byteLogLikelihood": -3.361609233757, + "hits": 5, + "total": 143, + "hitRate": 0.03496503496503497 }, { - "encoding": "windows-874", + "encoding": "ISO-8859-7", + "language": "el", "confidence": 0, - "language": "th", - "byteLogLikelihood": -5.31385343816, + "byteLogLikelihood": -3.017269736716, "hits": 0, - "total": 48, + "total": 143, "hitRate": 0 }, { - "encoding": "KOI8-R", + "encoding": "ISO-8859-8", + "language": "he", "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.40669720385, + "byteLogLikelihood": -3.50352863905, "hits": 0, - "total": 102, + "total": 143, "hitRate": 0 }, { - "encoding": "KOI8-U", + "encoding": "windows-1251", + "language": "ru", "confidence": 0, - "language": "uk", - "byteLogLikelihood": -6.393692981541, + "byteLogLikelihood": -3.846220145127, "hits": 0, - "total": 102, + "total": 143, "hitRate": 0 }, { - "encoding": "IBM866", + "encoding": "windows-1253", + "language": "el", "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.683415446443, + "byteLogLikelihood": -3.017269736716, "hits": 0, - "total": 94, + "total": 143, "hitRate": 0 }, { - "encoding": "macintosh", + "encoding": "windows-1255", + "language": "he", "confidence": 0, - "language": "es", - "byteLogLikelihood": -4.948759890378, + "byteLogLikelihood": -3.50352863905, "hits": 0, - "total": 72, + "total": 143, "hitRate": 0 }, { - "encoding": "x-mac-cyrillic", + "encoding": "windows-1256", + "language": "ar", "confidence": 0, - "language": "uk", - "byteLogLikelihood": -4.134202940863, + "byteLogLikelihood": -3.503504267293, "hits": 0, - "total": 102, + "total": 143, "hitRate": 0 }, { - "encoding": "ISO-8859-3", + "encoding": "IBM855", + "language": "sr", "confidence": 0, - "language": "mt", - "byteLogLikelihood": -4.956632184798, + "byteLogLikelihood": -3.774998078834, "hits": 0, - "total": 102, + "total": 143, "hitRate": 0 }, { - "encoding": "ISO-8859-4", + "encoding": "x-mac-cyrillic", + "language": "uk", "confidence": 0, - "language": "lv", - "byteLogLikelihood": -5.146385148445, + "byteLogLikelihood": -3.766179593299, "hits": 0, - "total": 102, + "total": 143, "hitRate": 0 + } + ] + }, + { + "expected": { + "encoding": "windows-1252", + "language": "sv" + }, + "predicted": { + "encoding": "ISO-8859-1", + "language": "sv", + "confidence": 50, + "byteLogLikelihood": -3.23645137845, + "hits": 23, + "total": 136, + "hitRate": 0.16911764705882354 + }, + "encodingExact": false, + "encodingEquivalent": true, + "encodingCorrect": true, + "languageCorrect": true, + "tiedAtTop": 2, + "candidates": [ + { + "encoding": "ISO-8859-1", + "language": "sv", + "confidence": 50, + "byteLogLikelihood": -3.23645137845, + "hits": 23, + "total": 136, + "hitRate": 0.16911764705882354 }, { - "encoding": "ISO-8859-10", + "encoding": "windows-1252", + "language": "sv", + "confidence": 50, + "byteLogLikelihood": -3.23645137845, + "hits": 23, + "total": 136, + "hitRate": 0.16911764705882354 + }, + { + "encoding": "ISO-8859-15", + "language": "de", + "confidence": 17, + "byteLogLikelihood": -4.137512330246, + "hits": 8, + "total": 136, + "hitRate": 0.058823529411764705 + }, + { + "encoding": "windows-1257", + "language": "lt", + "confidence": 4, + "byteLogLikelihood": -5.123963979403, + "hits": 2, + "total": 136, + "hitRate": 0.014705882352941176 + }, + { + "encoding": "ISO-8859-3", + "language": "mt", + "confidence": 4, + "byteLogLikelihood": -4.210065739287, + "hits": 2, + "total": 136, + "hitRate": 0.014705882352941176 + }, + { + "encoding": "ISO-8859-6", + "language": "ar", "confidence": 0, - "language": "is", - "byteLogLikelihood": -4.745792460039, + "byteLogLikelihood": -3.287368473007, "hits": 0, - "total": 102, + "total": 136, "hitRate": 0 }, { - "encoding": "ISO-8859-13", + "encoding": "ISO-8859-7", + "language": "el", "confidence": 0, - "language": "lt", - "byteLogLikelihood": -4.842271132243, + "byteLogLikelihood": -3.876181596107, "hits": 0, - "total": 102, + "total": 136, "hitRate": 0 }, { - "encoding": "ISO-8859-14", + "encoding": "ISO-8859-8", + "language": "he", "confidence": 0, - "language": "cy", - "byteLogLikelihood": -4.813633859942, + "byteLogLikelihood": -3.066153183614, "hits": 0, - "total": 102, + "total": 136, "hitRate": 0 }, { - "encoding": "ISO-8859-15", + "encoding": "windows-1251", + "language": "ru", "confidence": 0, - "language": "fr", - "byteLogLikelihood": -4.521941300627, + "byteLogLikelihood": -3.393743210995, "hits": 0, - "total": 102, + "total": 136, "hitRate": 0 }, { - "encoding": "ISO-8859-16", + "encoding": "windows-1253", + "language": "el", "confidence": 0, - "language": "ro", - "byteLogLikelihood": -5.093070766591, + "byteLogLikelihood": -3.876181596107, "hits": 0, - "total": 102, + "total": 136, "hitRate": 0 }, { - "encoding": "CP850", + "encoding": "windows-1255", + "language": "he", "confidence": 0, - "language": "es", - "byteLogLikelihood": -4.948759890378, + "byteLogLikelihood": -3.066153183614, "hits": 0, - "total": 85, + "total": 136, "hitRate": 0 }, { - "encoding": "CP852", + "encoding": "x-mac-cyrillic", + "language": "ru", "confidence": 0, - "language": "pl", - "byteLogLikelihood": -5.087596335232, + "byteLogLikelihood": -3.393743210995, "hits": 0, - "total": 89, + "total": 136, "hitRate": 0 } ] }, { "expected": { - "encoding": "windows-1256", - "language": "ar" + "encoding": "windows-1253", + "language": "el" }, "predicted": { - "encoding": "windows-1256", - "confidence": 62, - "language": "ar", - "byteLogLikelihood": -3.306009422775, + "encoding": "ISO-8859-7", + "language": "el", + "confidence": 51, + "byteLogLikelihood": -3.435199502, "hits": 23, - "total": 110, - "hitRate": 0.20909090909090908 + "total": 134, + "hitRate": 0.17164179104477612 }, - "encodingExact": true, - "encodingEquivalent": false, + "encodingExact": false, + "encodingEquivalent": true, "encodingCorrect": true, "languageCorrect": true, - "tiedAtTop": 1, + "tiedAtTop": 2, "candidates": [ { - "encoding": "windows-1256", - "confidence": 62, - "language": "ar", - "byteLogLikelihood": -3.306009422775, + "encoding": "ISO-8859-7", + "language": "el", + "confidence": 51, + "byteLogLikelihood": -3.435199502, "hits": 23, - "total": 110, - "hitRate": 0.20909090909090908 - }, - { - "encoding": "IBM855", - "confidence": 21, - "language": "sr", - "byteLogLikelihood": -5.640676681359, - "hits": 7, - "total": 100, - "hitRate": 0.07 + "total": 134, + "hitRate": 0.17164179104477612 }, { - "encoding": "ISO-8859-6", - "confidence": 15, - "language": "ar", - "byteLogLikelihood": -3.973986161297, - "hits": 5, - "total": 99, - "hitRate": 0.050505050505050504 + "encoding": "windows-1253", + "language": "el", + "confidence": 51, + "byteLogLikelihood": -3.435199502, + "hits": 23, + "total": 134, + "hitRate": 0.17164179104477612 }, { "encoding": "ISO-8859-8", - "confidence": 5, "language": "he", - "byteLogLikelihood": -5.107875566922, + "confidence": 2, + "byteLogLikelihood": -4.09495359507, "hits": 1, - "total": 58, - "hitRate": 0.017241379310344827 + "total": 127, + "hitRate": 0.007874015748031496 }, { "encoding": "windows-1255", - "confidence": 5, "language": "he", - "byteLogLikelihood": -5.107875566922, - "hits": 1, - "total": 60, - "hitRate": 0.016666666666666666 - }, - { - "encoding": "ISO-8859-5", - "confidence": 2, - "language": "ru", - "byteLogLikelihood": -5.047579876205, - "hits": 1, - "total": 111, - "hitRate": 0.009009009009009009 - }, - { - "encoding": "KOI8-R", "confidence": 2, - "language": "ru", - "byteLogLikelihood": -5.041761137138, + "byteLogLikelihood": -4.09495359507, "hits": 1, - "total": 110, - "hitRate": 0.00909090909090909 + "total": 127, + "hitRate": 0.007874015748031496 }, { - "encoding": "KOI8-U", - "confidence": 2, + "encoding": "x-mac-cyrillic", "language": "uk", - "byteLogLikelihood": -4.982175743167, + "confidence": 2, + "byteLogLikelihood": -4.203232324163, "hits": 1, - "total": 110, - "hitRate": 0.00909090909090909 + "total": 131, + "hitRate": 0.007633587786259542 }, { "encoding": "ISO-8859-1", + "language": "pt", "confidence": 0, - "language": "es", - "byteLogLikelihood": -4.70358763711, - "hits": 0, - "total": 110, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-2", - "confidence": 0, - "language": "cs", - "byteLogLikelihood": -4.668535969782, - "hits": 0, - "total": 111, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-7", - "confidence": 0, - "language": "el", - "byteLogLikelihood": -4.916907952775, + "byteLogLikelihood": -4.59932343766, "hits": 0, - "total": 109, + "total": 134, "hitRate": 0 }, { - "encoding": "ISO-8859-9", + "encoding": "ISO-8859-2", + "language": "hu", "confidence": 0, - "language": "tr", - "byteLogLikelihood": -4.906860727803, + "byteLogLikelihood": -4.358825259583, "hits": 0, - "total": 109, + "total": 134, "hitRate": 0 }, { "encoding": "windows-1250", + "language": "hu", "confidence": 0, - "language": "cs", - "byteLogLikelihood": -4.668535969782, + "byteLogLikelihood": -4.358825259583, "hits": 0, - "total": 111, + "total": 134, "hitRate": 0 }, { "encoding": "windows-1251", - "confidence": 0, "language": "ru", - "byteLogLikelihood": -5.575363278011, + "confidence": 0, + "byteLogLikelihood": -4.288697198304, "hits": 0, - "total": 111, + "total": 134, "hitRate": 0 }, { "encoding": "windows-1252", + "language": "pt", "confidence": 0, - "language": "es", - "byteLogLikelihood": -4.70358763711, + "byteLogLikelihood": -4.59932343766, "hits": 0, - "total": 110, + "total": 134, "hitRate": 0 }, { - "encoding": "windows-1253", + "encoding": "ISO-8859-10", + "language": "is", "confidence": 0, - "language": "el", - "byteLogLikelihood": -4.916907952775, + "byteLogLikelihood": -4.576407109739, "hits": 0, - "total": 109, + "total": 134, "hitRate": 0 }, { - "encoding": "windows-1254", + "encoding": "ISO-8859-15", + "language": "es", "confidence": 0, - "language": "tr", - "byteLogLikelihood": -4.906860727803, + "byteLogLikelihood": -4.603974037796, "hits": 0, - "total": 109, + "total": 134, "hitRate": 0 + } + ] + }, + { + "expected": { + "encoding": "windows-1254", + "language": "tr" + }, + "predicted": { + "encoding": "ISO-8859-9", + "language": "tr", + "confidence": 55, + "byteLogLikelihood": -3.531675216773, + "hits": 25, + "total": 134, + "hitRate": 0.1865671641791045 + }, + "encodingExact": false, + "encodingEquivalent": true, + "encodingCorrect": true, + "languageCorrect": true, + "tiedAtTop": 2, + "candidates": [ + { + "encoding": "ISO-8859-9", + "language": "tr", + "confidence": 55, + "byteLogLikelihood": -3.531675216773, + "hits": 25, + "total": 134, + "hitRate": 0.1865671641791045 + }, + { + "encoding": "windows-1254", + "language": "tr", + "confidence": 55, + "byteLogLikelihood": -3.531675216773, + "hits": 25, + "total": 134, + "hitRate": 0.1865671641791045 + }, + { + "encoding": "ISO-8859-1", + "language": "da", + "confidence": 17, + "byteLogLikelihood": -4.969813299576, + "hits": 8, + "total": 134, + "hitRate": 0.05970149253731343 + }, + { + "encoding": "windows-1252", + "language": "da", + "confidence": 17, + "byteLogLikelihood": -4.969813299576, + "hits": 8, + "total": 134, + "hitRate": 0.05970149253731343 + }, + { + "encoding": "ISO-8859-2", + "language": "ro", + "confidence": 13, + "byteLogLikelihood": -4.352190516073, + "hits": 6, + "total": 134, + "hitRate": 0.04477611940298507 + }, + { + "encoding": "windows-1250", + "language": "ro", + "confidence": 13, + "byteLogLikelihood": -4.352190516073, + "hits": 6, + "total": 134, + "hitRate": 0.04477611940298507 }, { "encoding": "windows-1257", - "confidence": 0, - "language": "et", - "byteLogLikelihood": -4.856571347512, - "hits": 0, - "total": 110, - "hitRate": 0 + "language": "lv", + "confidence": 11, + "byteLogLikelihood": -3.613497993373, + "hits": 5, + "total": 134, + "hitRate": 0.03731343283582089 }, { - "encoding": "windows-1258", - "confidence": 0, - "language": "vi", - "byteLogLikelihood": -5.029693479499, - "hits": 0, - "total": 106, - "hitRate": 0 + "encoding": "ISO-8859-13", + "language": "lt", + "confidence": 11, + "byteLogLikelihood": -4.394247673508, + "hits": 5, + "total": 134, + "hitRate": 0.03731343283582089 }, { - "encoding": "windows-874", - "confidence": 0, - "language": "th", - "byteLogLikelihood": -4.736714293626, - "hits": 0, - "total": 90, - "hitRate": 0 + "encoding": "ISO-8859-16", + "language": "ro", + "confidence": 11, + "byteLogLikelihood": -4.25849981603, + "hits": 5, + "total": 134, + "hitRate": 0.03731343283582089 }, { - "encoding": "IBM866", + "encoding": "ISO-8859-7", + "language": "el", "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.982133409941, + "byteLogLikelihood": -4.216966174066, "hits": 0, - "total": 60, + "total": 134, "hitRate": 0 }, { - "encoding": "macintosh", + "encoding": "windows-1253", + "language": "el", "confidence": 0, - "language": "es", - "byteLogLikelihood": -4.948759890378, + "byteLogLikelihood": -4.216966174066, "hits": 0, - "total": 46, + "total": 134, "hitRate": 0 }, { "encoding": "x-mac-cyrillic", + "language": "uk", "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.655679070563, + "byteLogLikelihood": -4.22610845571, "hits": 0, - "total": 81, + "total": 134, "hitRate": 0 + } + ] + }, + { + "expected": { + "encoding": "windows-1255", + "language": "he" + }, + "predicted": { + "encoding": "ISO-8859-8", + "language": "he", + "confidence": 47, + "byteLogLikelihood": -3.320333973076, + "hits": 16, + "total": 102, + "hitRate": 0.1568627450980392 + }, + "encodingExact": false, + "encodingEquivalent": true, + "encodingCorrect": true, + "languageCorrect": true, + "tiedAtTop": 2, + "candidates": [ + { + "encoding": "ISO-8859-8", + "language": "he", + "confidence": 47, + "byteLogLikelihood": -3.320333973076, + "hits": 16, + "total": 102, + "hitRate": 0.1568627450980392 }, { - "encoding": "ISO-8859-3", - "confidence": 0, - "language": "mt", - "byteLogLikelihood": -5.078935619012, - "hits": 0, - "total": 110, - "hitRate": 0 + "encoding": "windows-1255", + "language": "he", + "confidence": 47, + "byteLogLikelihood": -3.320333973076, + "hits": 16, + "total": 102, + "hitRate": 0.1568627450980392 }, { - "encoding": "ISO-8859-4", + "encoding": "ISO-8859-7", + "language": "el", + "confidence": 2, + "byteLogLikelihood": -3.981926233577, + "hits": 1, + "total": 102, + "hitRate": 0.00980392156862745 + }, + { + "encoding": "windows-1253", + "language": "el", + "confidence": 2, + "byteLogLikelihood": -3.981926233577, + "hits": 1, + "total": 102, + "hitRate": 0.00980392156862745 + }, + { + "encoding": "ISO-8859-1", + "language": "sv", "confidence": 0, - "language": "lv", - "byteLogLikelihood": -5.19295685089, + "byteLogLikelihood": -4.395116706452, "hits": 0, - "total": 111, + "total": 102, "hitRate": 0 }, { - "encoding": "ISO-8859-10", + "encoding": "ISO-8859-2", + "language": "cs", "confidence": 0, - "language": "is", - "byteLogLikelihood": -4.796168589227, + "byteLogLikelihood": -4.461975046319, "hits": 0, - "total": 111, + "total": 102, "hitRate": 0 }, { - "encoding": "ISO-8859-13", + "encoding": "windows-1250", + "language": "cs", "confidence": 0, - "language": "lt", - "byteLogLikelihood": -5.003416643654, + "byteLogLikelihood": -4.461975046319, "hits": 0, - "total": 110, + "total": 102, "hitRate": 0 }, { - "encoding": "ISO-8859-14", + "encoding": "windows-1251", + "language": "ru", "confidence": 0, - "language": "cy", - "byteLogLikelihood": -4.912654885736, + "byteLogLikelihood": -4.199203901043, "hits": 0, - "total": 111, + "total": 102, "hitRate": 0 }, { - "encoding": "ISO-8859-15", + "encoding": "windows-1252", + "language": "sv", "confidence": 0, - "language": "es", - "byteLogLikelihood": -4.70358763711, + "byteLogLikelihood": -4.395116706452, "hits": 0, - "total": 110, + "total": 102, "hitRate": 0 }, { - "encoding": "ISO-8859-16", + "encoding": "windows-1257", + "language": "et", "confidence": 0, - "language": "ro", - "byteLogLikelihood": -5.119560962469, + "byteLogLikelihood": -4.639272141503, "hits": 0, - "total": 111, + "total": 102, "hitRate": 0 }, { - "encoding": "CP850", + "encoding": "x-mac-cyrillic", + "language": "uk", "confidence": 0, - "language": "es", - "byteLogLikelihood": -4.941225681894, + "byteLogLikelihood": -4.134202940863, "hits": 0, - "total": 97, + "total": 102, "hitRate": 0 }, { - "encoding": "CP852", + "encoding": "ISO-8859-15", + "language": "fr", "confidence": 0, - "language": "pl", - "byteLogLikelihood": -5.087596335232, + "byteLogLikelihood": -4.521941300627, "hits": 0, - "total": 100, + "total": 102, "hitRate": 0 } ] }, { "expected": { - "encoding": "windows-1257", - "language": "et" + "encoding": "windows-1256", + "language": "ar" }, "predicted": { - "encoding": "windows-1257", - "confidence": 40, - "language": "et", - "byteLogLikelihood": -3.489288054183, - "hits": 16, - "total": 120, - "hitRate": 0.13333333333333333 + "encoding": "windows-1256", + "language": "ar", + "confidence": 62, + "byteLogLikelihood": -3.306009422775, + "hits": 23, + "total": 110, + "hitRate": 0.20909090909090908 }, "encodingExact": true, "encodingEquivalent": false, @@ -18420,288 +7668,238 @@ "tiedAtTop": 1, "candidates": [ { - "encoding": "windows-1257", - "confidence": 40, - "language": "et", - "byteLogLikelihood": -3.489288054183, - "hits": 16, - "total": 120, - "hitRate": 0.13333333333333333 - }, - { - "encoding": "ISO-8859-1", - "confidence": 12, - "language": "es", - "byteLogLikelihood": -4.948759890378, - "hits": 5, - "total": 120, - "hitRate": 0.041666666666666664 - }, - { - "encoding": "ISO-8859-9", - "confidence": 12, - "language": "tr", - "byteLogLikelihood": -3.976561526566, - "hits": 5, - "total": 120, - "hitRate": 0.041666666666666664 - }, - { - "encoding": "windows-1252", - "confidence": 12, - "language": "es", - "byteLogLikelihood": -4.948759890378, - "hits": 5, - "total": 120, - "hitRate": 0.041666666666666664 - }, - { - "encoding": "windows-1254", - "confidence": 12, - "language": "tr", - "byteLogLikelihood": -3.976561526566, - "hits": 5, - "total": 120, - "hitRate": 0.041666666666666664 - }, - { - "encoding": "macintosh", - "confidence": 12, - "language": "es", - "byteLogLikelihood": -4.948759890378, - "hits": 5, - "total": 120, - "hitRate": 0.041666666666666664 - }, - { - "encoding": "ISO-8859-3", - "confidence": 12, - "language": "mt", - "byteLogLikelihood": -5.105945473901, - "hits": 5, - "total": 120, - "hitRate": 0.041666666666666664 + "encoding": "windows-1256", + "language": "ar", + "confidence": 62, + "byteLogLikelihood": -3.306009422775, + "hits": 23, + "total": 110, + "hitRate": 0.20909090909090908 }, { - "encoding": "ISO-8859-15", - "confidence": 12, - "language": "es", - "byteLogLikelihood": -4.948759890378, + "encoding": "ISO-8859-6", + "language": "ar", + "confidence": 15, + "byteLogLikelihood": -3.973986161297, "hits": 5, - "total": 120, - "hitRate": 0.041666666666666664 + "total": 99, + "hitRate": 0.050505050505050504 }, { - "encoding": "CP850", - "confidence": 12, + "encoding": "ISO-8859-1", "language": "es", - "byteLogLikelihood": -4.948759890378, - "hits": 5, - "total": 120, - "hitRate": 0.041666666666666664 + "confidence": 0, + "byteLogLikelihood": -4.70358763711, + "hits": 0, + "total": 110, + "hitRate": 0 }, { "encoding": "ISO-8859-2", - "confidence": 10, - "language": "pl", - "byteLogLikelihood": -5.087596335232, - "hits": 4, - "total": 120, - "hitRate": 0.03333333333333333 - }, - { - "encoding": "windows-1250", - "confidence": 10, - "language": "pl", - "byteLogLikelihood": -5.087596335232, - "hits": 4, - "total": 120, - "hitRate": 0.03333333333333333 - }, - { - "encoding": "ISO-8859-4", - "confidence": 10, - "language": "lv", - "byteLogLikelihood": -5.19295685089, - "hits": 4, - "total": 120, - "hitRate": 0.03333333333333333 - }, - { - "encoding": "ISO-8859-10", - "confidence": 10, - "language": "is", - "byteLogLikelihood": -5.204006687077, - "hits": 4, - "total": 120, - "hitRate": 0.03333333333333333 - }, - { - "encoding": "ISO-8859-13", - "confidence": 10, - "language": "lt", - "byteLogLikelihood": -5.123963979403, - "hits": 4, - "total": 120, - "hitRate": 0.03333333333333333 + "language": "cs", + "confidence": 0, + "byteLogLikelihood": -4.668535969782, + "hits": 0, + "total": 111, + "hitRate": 0 }, { - "encoding": "CP852", - "confidence": 10, - "language": "pl", - "byteLogLikelihood": -5.087596335232, - "hits": 4, - "total": 120, - "hitRate": 0.03333333333333333 + "encoding": "ISO-8859-9", + "language": "tr", + "confidence": 0, + "byteLogLikelihood": -4.906860727803, + "hits": 0, + "total": 109, + "hitRate": 0 }, { - "encoding": "windows-1258", - "confidence": 7, - "language": "vi", - "byteLogLikelihood": -5.497168225293, - "hits": 3, - "total": 120, - "hitRate": 0.025 + "encoding": "windows-1250", + "language": "cs", + "confidence": 0, + "byteLogLikelihood": -4.668535969782, + "hits": 0, + "total": 111, + "hitRate": 0 }, { - "encoding": "ISO-8859-16", - "confidence": 5, - "language": "ro", - "byteLogLikelihood": -5.220355825078, - "hits": 2, - "total": 120, - "hitRate": 0.016666666666666666 + "encoding": "windows-1252", + "language": "es", + "confidence": 0, + "byteLogLikelihood": -4.70358763711, + "hits": 0, + "total": 110, + "hitRate": 0 }, { - "encoding": "ISO-8859-14", - "confidence": 2, - "language": "cy", - "byteLogLikelihood": -4.912654885736, - "hits": 1, - "total": 120, - "hitRate": 0.008333333333333333 + "encoding": "windows-1254", + "language": "tr", + "confidence": 0, + "byteLogLikelihood": -4.906860727803, + "hits": 0, + "total": 109, + "hitRate": 0 }, { - "encoding": "ISO-8859-5", + "encoding": "windows-1257", + "language": "et", "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.692083742507, + "byteLogLikelihood": -4.856571347512, "hits": 0, - "total": 120, + "total": 110, "hitRate": 0 }, { - "encoding": "ISO-8859-6", + "encoding": "windows-874", + "language": "th", "confidence": 0, - "language": "ar", - "byteLogLikelihood": -4.30822322351, + "byteLogLikelihood": -4.736714293626, "hits": 0, - "total": 120, + "total": 90, "hitRate": 0 }, { - "encoding": "ISO-8859-7", + "encoding": "ISO-8859-10", + "language": "is", "confidence": 0, - "language": "el", - "byteLogLikelihood": -4.41969872812, + "byteLogLikelihood": -4.796168589227, "hits": 0, - "total": 120, + "total": 111, "hitRate": 0 }, { - "encoding": "ISO-8859-8", + "encoding": "ISO-8859-15", + "language": "es", "confidence": 0, - "language": "he", - "byteLogLikelihood": -4.51563851542, + "byteLogLikelihood": -4.70358763711, "hits": 0, - "total": 120, + "total": 110, "hitRate": 0 + } + ] + }, + { + "expected": { + "encoding": "windows-1257", + "language": "et" + }, + "predicted": { + "encoding": "windows-1257", + "language": "et", + "confidence": 40, + "byteLogLikelihood": -3.489288054183, + "hits": 16, + "total": 120, + "hitRate": 0.13333333333333333 + }, + "encodingExact": true, + "encodingEquivalent": false, + "encodingCorrect": true, + "languageCorrect": true, + "tiedAtTop": 1, + "candidates": [ + { + "encoding": "windows-1257", + "language": "et", + "confidence": 40, + "byteLogLikelihood": -3.489288054183, + "hits": 16, + "total": 120, + "hitRate": 0.13333333333333333 }, { - "encoding": "windows-1251", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -4.453415335268, - "hits": 0, + "encoding": "ISO-8859-1", + "language": "es", + "confidence": 12, + "byteLogLikelihood": -4.948759890378, + "hits": 5, "total": 120, - "hitRate": 0 + "hitRate": 0.041666666666666664 }, { - "encoding": "windows-1253", - "confidence": 0, - "language": "el", - "byteLogLikelihood": -4.41969872812, - "hits": 0, + "encoding": "ISO-8859-9", + "language": "tr", + "confidence": 12, + "byteLogLikelihood": -3.976561526566, + "hits": 5, "total": 120, - "hitRate": 0 + "hitRate": 0.041666666666666664 }, { - "encoding": "windows-1255", - "confidence": 0, - "language": "he", - "byteLogLikelihood": -4.51563851542, - "hits": 0, + "encoding": "windows-1252", + "language": "es", + "confidence": 12, + "byteLogLikelihood": -4.948759890378, + "hits": 5, "total": 120, - "hitRate": 0 + "hitRate": 0.041666666666666664 }, { - "encoding": "windows-1256", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -4.831207501101, - "hits": 0, + "encoding": "windows-1254", + "language": "tr", + "confidence": 12, + "byteLogLikelihood": -3.976561526566, + "hits": 5, "total": 120, - "hitRate": 0 + "hitRate": 0.041666666666666664 }, { - "encoding": "windows-874", + "encoding": "ISO-8859-15", + "language": "es", + "confidence": 12, + "byteLogLikelihood": -4.948759890378, + "hits": 5, + "total": 120, + "hitRate": 0.041666666666666664 + }, + { + "encoding": "ISO-8859-6", + "language": "ar", "confidence": 0, - "language": "th", - "byteLogLikelihood": -5.714883328648, + "byteLogLikelihood": -4.30822322351, "hits": 0, "total": 120, "hitRate": 0 }, { - "encoding": "KOI8-R", + "encoding": "ISO-8859-7", + "language": "el", "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.345510152227, + "byteLogLikelihood": -4.41969872812, "hits": 0, "total": 120, "hitRate": 0 }, { - "encoding": "KOI8-U", + "encoding": "ISO-8859-8", + "language": "he", "confidence": 0, - "language": "uk", - "byteLogLikelihood": -6.303705458307, + "byteLogLikelihood": -4.51563851542, "hits": 0, "total": 120, "hitRate": 0 }, { - "encoding": "IBM866", - "confidence": 0, + "encoding": "windows-1251", "language": "ru", - "byteLogLikelihood": -6.692083742507, + "confidence": 0, + "byteLogLikelihood": -4.453415335268, "hits": 0, "total": 120, "hitRate": 0 }, { - "encoding": "IBM855", + "encoding": "windows-1253", + "language": "el", "confidence": 0, - "language": "sr", - "byteLogLikelihood": -5.827473946999, + "byteLogLikelihood": -4.41969872812, "hits": 0, "total": 120, "hitRate": 0 }, { "encoding": "x-mac-cyrillic", - "confidence": 0, "language": "uk", + "confidence": 0, "byteLogLikelihood": -3.632538332325, "hits": 0, "total": 120, @@ -18716,8 +7914,8 @@ }, "predicted": { "encoding": "windows-1257", - "confidence": 34, "language": "lt", + "confidence": 34, "byteLogLikelihood": -3.200530207132, "hits": 20, "total": 173, @@ -18731,8 +7929,8 @@ "candidates": [ { "encoding": "windows-1257", - "confidence": 34, "language": "lt", + "confidence": 34, "byteLogLikelihood": -3.200530207132, "hits": 20, "total": 173, @@ -18740,8 +7938,8 @@ }, { "encoding": "ISO-8859-13", - "confidence": 34, "language": "lt", + "confidence": 34, "byteLogLikelihood": -3.200530207132, "hits": 20, "total": 173, @@ -18749,170 +7947,44 @@ }, { "encoding": "ISO-8859-4", - "confidence": 22, "language": "lv", + "confidence": 22, "byteLogLikelihood": -4.610398759565, "hits": 13, "total": 173, "hitRate": 0.07514450867052024 }, - { - "encoding": "ISO-8859-2", - "confidence": 15, - "language": "hu", - "byteLogLikelihood": -5.117993812417, - "hits": 9, - "total": 173, - "hitRate": 0.05202312138728324 - }, - { - "encoding": "windows-1250", - "confidence": 15, - "language": "hu", - "byteLogLikelihood": -5.117993812417, - "hits": 9, - "total": 173, - "hitRate": 0.05202312138728324 - }, { "encoding": "ISO-8859-1", - "confidence": 12, "language": "es", - "byteLogLikelihood": -4.948759890378, - "hits": 7, - "total": 173, - "hitRate": 0.04046242774566474 - }, - { - "encoding": "windows-1252", "confidence": 12, - "language": "es", "byteLogLikelihood": -4.948759890378, "hits": 7, "total": 173, "hitRate": 0.04046242774566474 }, { - "encoding": "macintosh", - "confidence": 12, + "encoding": "windows-1252", "language": "es", - "byteLogLikelihood": -4.948759890378, - "hits": 7, - "total": 168, - "hitRate": 0.041666666666666664 - }, - { - "encoding": "ISO-8859-15", "confidence": 12, - "language": "es", "byteLogLikelihood": -4.948759890378, "hits": 7, "total": 173, "hitRate": 0.04046242774566474 }, { - "encoding": "CP850", - "confidence": 12, - "language": "es", - "byteLogLikelihood": -4.948759890378, - "hits": 7, - "total": 170, - "hitRate": 0.041176470588235294 - }, - { - "encoding": "ISO-8859-9", - "confidence": 8, - "language": "tr", - "byteLogLikelihood": -4.789760270297, - "hits": 5, - "total": 173, - "hitRate": 0.028901734104046242 - }, - { - "encoding": "windows-1254", - "confidence": 8, - "language": "tr", - "byteLogLikelihood": -4.789760270297, - "hits": 5, - "total": 173, - "hitRate": 0.028901734104046242 - }, - { - "encoding": "CP852", - "confidence": 7, - "language": "pl", - "byteLogLikelihood": -5.087596335232, - "hits": 4, - "total": 170, - "hitRate": 0.023529411764705882 - }, - { - "encoding": "ISO-8859-3", - "confidence": 5, - "language": "mt", - "byteLogLikelihood": -5.105945473901, - "hits": 3, - "total": 172, - "hitRate": 0.01744186046511628 - }, - { - "encoding": "ISO-8859-14", - "confidence": 3, - "language": "cy", - "byteLogLikelihood": -4.6272413408, - "hits": 2, - "total": 173, - "hitRate": 0.011560693641618497 - }, - { - "encoding": "windows-1258", - "confidence": 1, - "language": "vi", - "byteLogLikelihood": -4.960186085121, - "hits": 1, - "total": 171, - "hitRate": 0.005847953216374269 - }, - { - "encoding": "IBM855", - "confidence": 1, - "language": "ru", - "byteLogLikelihood": -5.488073838002, - "hits": 1, - "total": 170, - "hitRate": 0.0058823529411764705 - }, - { - "encoding": "ISO-8859-10", - "confidence": 1, - "language": "is", - "byteLogLikelihood": -4.416382325607, - "hits": 1, - "total": 173, - "hitRate": 0.005780346820809248 - }, - { - "encoding": "ISO-8859-5", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -4.893109334109, - "hits": 0, - "total": 172, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-6", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -5.773457169107, - "hits": 0, - "total": 167, - "hitRate": 0 + "encoding": "ISO-8859-10", + "language": "is", + "confidence": 1, + "byteLogLikelihood": -4.416382325607, + "hits": 1, + "total": 173, + "hitRate": 0.005780346820809248 }, { "encoding": "ISO-8859-7", - "confidence": 0, "language": "el", + "confidence": 0, "byteLogLikelihood": -4.472500251122, "hits": 0, "total": 173, @@ -18920,8 +7992,8 @@ }, { "encoding": "ISO-8859-8", - "confidence": 0, "language": "he", + "confidence": 0, "byteLogLikelihood": -4.444220754634, "hits": 0, "total": 171, @@ -18929,8 +8001,8 @@ }, { "encoding": "windows-1251", - "confidence": 0, "language": "ru", + "confidence": 0, "byteLogLikelihood": -3.531827362419, "hits": 0, "total": 173, @@ -18938,8 +8010,8 @@ }, { "encoding": "windows-1253", - "confidence": 0, "language": "el", + "confidence": 0, "byteLogLikelihood": -4.472500251122, "hits": 0, "total": 173, @@ -18947,72 +8019,18 @@ }, { "encoding": "windows-1255", - "confidence": 0, "language": "he", - "byteLogLikelihood": -4.444220754634, - "hits": 0, - "total": 171, - "hitRate": 0 - }, - { - "encoding": "windows-1256", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -5.924336543075, - "hits": 0, - "total": 170, - "hitRate": 0 - }, - { - "encoding": "windows-874", - "confidence": 0, - "language": "th", - "byteLogLikelihood": -5.58967630288, - "hits": 0, - "total": 166, - "hitRate": 0 - }, - { - "encoding": "KOI8-R", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.365896834008, - "hits": 0, - "total": 173, - "hitRate": 0 - }, - { - "encoding": "KOI8-U", - "confidence": 0, - "language": "uk", - "byteLogLikelihood": -6.252539473952, - "hits": 0, - "total": 173, - "hitRate": 0 - }, - { - "encoding": "IBM866", "confidence": 0, - "language": "ru", - "byteLogLikelihood": -4.893109334109, + "byteLogLikelihood": -4.444220754634, "hits": 0, "total": 171, "hitRate": 0 }, { "encoding": "x-mac-cyrillic", - "confidence": 0, "language": "uk", - "byteLogLikelihood": -3.441328843196, - "hits": 0, - "total": 173, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-16", "confidence": 0, - "language": "ro", - "byteLogLikelihood": -4.616838329205, + "byteLogLikelihood": -3.441328843196, "hits": 0, "total": 173, "hitRate": 0 @@ -19026,8 +8044,8 @@ }, "predicted": { "encoding": "windows-1257", - "confidence": 40, "language": "lv", + "confidence": 40, "byteLogLikelihood": -3.1328616083, "hits": 23, "total": 170, @@ -19041,170 +8059,44 @@ "candidates": [ { "encoding": "windows-1257", - "confidence": 40, "language": "lv", + "confidence": 40, "byteLogLikelihood": -3.1328616083, "hits": 23, "total": 170, "hitRate": 0.13529411764705881 }, - { - "encoding": "ISO-8859-4", - "confidence": 31, - "language": "lv", - "byteLogLikelihood": -5.003611214133, - "hits": 18, - "total": 170, - "hitRate": 0.10588235294117647 - }, - { - "encoding": "CP850", - "confidence": 15, - "language": "es", - "byteLogLikelihood": -4.948759890378, - "hits": 9, - "total": 170, - "hitRate": 0.052941176470588235 - }, { "encoding": "ISO-8859-1", - "confidence": 14, - "language": "fr", - "byteLogLikelihood": -4.806768476285, - "hits": 8, - "total": 170, - "hitRate": 0.047058823529411764 - }, - { - "encoding": "windows-1252", - "confidence": 14, "language": "fr", - "byteLogLikelihood": -4.806768476285, - "hits": 8, - "total": 170, - "hitRate": 0.047058823529411764 - }, - { - "encoding": "macintosh", - "confidence": 14, - "language": "es", - "byteLogLikelihood": -4.948759890378, - "hits": 8, - "total": 170, - "hitRate": 0.047058823529411764 - }, - { - "encoding": "ISO-8859-15", "confidence": 14, - "language": "fr", "byteLogLikelihood": -4.806768476285, "hits": 8, "total": 170, "hitRate": 0.047058823529411764 }, - { - "encoding": "CP852", - "confidence": 12, - "language": "pl", - "byteLogLikelihood": -5.087596335232, - "hits": 7, - "total": 170, - "hitRate": 0.041176470588235294 - }, - { - "encoding": "ISO-8859-3", - "confidence": 10, - "language": "mt", - "byteLogLikelihood": -5.105945473901, - "hits": 6, - "total": 170, - "hitRate": 0.03529411764705882 - }, - { - "encoding": "ISO-8859-13", - "confidence": 10, - "language": "lt", - "byteLogLikelihood": -4.977793000004, - "hits": 6, - "total": 170, - "hitRate": 0.03529411764705882 - }, - { - "encoding": "ISO-8859-2", - "confidence": 8, - "language": "pl", - "byteLogLikelihood": -5.087596335232, - "hits": 5, - "total": 170, - "hitRate": 0.029411764705882353 - }, - { - "encoding": "windows-1250", - "confidence": 8, - "language": "pl", - "byteLogLikelihood": -5.087596335232, - "hits": 5, - "total": 170, - "hitRate": 0.029411764705882353 - }, - { - "encoding": "ISO-8859-9", - "confidence": 7, - "language": "tr", - "byteLogLikelihood": -4.576539240129, - "hits": 4, - "total": 170, - "hitRate": 0.023529411764705882 - }, - { - "encoding": "windows-1254", - "confidence": 7, - "language": "tr", - "byteLogLikelihood": -4.576539240129, - "hits": 4, - "total": 170, - "hitRate": 0.023529411764705882 - }, { "encoding": "windows-1258", - "confidence": 7, "language": "vi", + "confidence": 7, "byteLogLikelihood": -4.342387954294, "hits": 4, "total": 169, "hitRate": 0.023668639053254437 }, - { - "encoding": "ISO-8859-10", - "confidence": 7, - "language": "is", - "byteLogLikelihood": -4.928587203128, - "hits": 4, - "total": 170, - "hitRate": 0.023529411764705882 - }, { "encoding": "ISO-8859-5", - "confidence": 0, "language": "ru", + "confidence": 0, "byteLogLikelihood": -4.459882683974, "hits": 0, "total": 170, "hitRate": 0 }, - { - "encoding": "ISO-8859-6", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -5.080491263049, - "hits": 0, - "total": 169, - "hitRate": 0 - }, { "encoding": "ISO-8859-7", - "confidence": 0, "language": "el", + "confidence": 0, "byteLogLikelihood": -3.703260469986, "hits": 0, "total": 170, @@ -19212,8 +8104,8 @@ }, { "encoding": "ISO-8859-8", - "confidence": 0, "language": "he", + "confidence": 0, "byteLogLikelihood": -4.207917523838, "hits": 0, "total": 170, @@ -19221,8 +8113,8 @@ }, { "encoding": "windows-1251", - "confidence": 0, "language": "ru", + "confidence": 0, "byteLogLikelihood": -3.543665829263, "hits": 0, "total": 170, @@ -19230,8 +8122,8 @@ }, { "encoding": "windows-1253", - "confidence": 0, "language": "el", + "confidence": 0, "byteLogLikelihood": -3.703260469986, "hits": 0, "total": 170, @@ -19239,71 +8131,26 @@ }, { "encoding": "windows-1255", - "confidence": 0, "language": "he", - "byteLogLikelihood": -4.207917523838, - "hits": 0, - "total": 170, - "hitRate": 0 - }, - { - "encoding": "windows-1256", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -5.924336543075, - "hits": 0, - "total": 170, - "hitRate": 0 - }, - { - "encoding": "windows-874", - "confidence": 0, - "language": "th", - "byteLogLikelihood": -5.58909903103, - "hits": 0, - "total": 167, - "hitRate": 0 - }, - { - "encoding": "KOI8-R", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -6.155101602334, - "hits": 0, - "total": 170, - "hitRate": 0 - }, - { - "encoding": "KOI8-U", "confidence": 0, - "language": "uk", - "byteLogLikelihood": -6.147141858115, + "byteLogLikelihood": -4.207917523838, "hits": 0, "total": 170, "hitRate": 0 }, { "encoding": "IBM866", - "confidence": 0, "language": "ru", - "byteLogLikelihood": -4.459882683974, - "hits": 0, - "total": 170, - "hitRate": 0 - }, - { - "encoding": "IBM855", "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.609454107834, + "byteLogLikelihood": -4.459882683974, "hits": 0, "total": 170, "hitRate": 0 }, { "encoding": "x-mac-cyrillic", - "confidence": 0, "language": "uk", + "confidence": 0, "byteLogLikelihood": -3.416476215238, "hits": 0, "total": 170, @@ -19311,18 +8158,9 @@ }, { "encoding": "ISO-8859-14", + "language": "cy", "confidence": 0, - "language": "cy", - "byteLogLikelihood": -4.423374522988, - "hits": 0, - "total": 170, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-16", - "confidence": 0, - "language": "ro", - "byteLogLikelihood": -4.717949371076, + "byteLogLikelihood": -4.423374522988, "hits": 0, "total": 170, "hitRate": 0 @@ -19336,8 +8174,8 @@ }, "predicted": { "encoding": "windows-1258", - "confidence": 98, "language": "vi", + "confidence": 98, "byteLogLikelihood": -3.323414763285, "hits": 42, "total": 124, @@ -19351,8 +8189,8 @@ "candidates": [ { "encoding": "windows-1258", - "confidence": 98, "language": "vi", + "confidence": 98, "byteLogLikelihood": -3.323414763285, "hits": 42, "total": 124, @@ -19360,8 +8198,8 @@ }, { "encoding": "ISO-8859-1", - "confidence": 9, "language": "pt", + "confidence": 9, "byteLogLikelihood": -4.721506246424, "hits": 4, "total": 126, @@ -19369,8 +8207,8 @@ }, { "encoding": "windows-1252", - "confidence": 9, "language": "pt", + "confidence": 9, "byteLogLikelihood": -4.721506246424, "hits": 4, "total": 126, @@ -19378,35 +8216,17 @@ }, { "encoding": "windows-1257", - "confidence": 9, "language": "lt", - "byteLogLikelihood": -4.767575136152, - "hits": 4, - "total": 126, - "hitRate": 0.031746031746031744 - }, - { - "encoding": "macintosh", - "confidence": 9, - "language": "es", - "byteLogLikelihood": -4.948759890378, - "hits": 4, - "total": 122, - "hitRate": 0.03278688524590164 - }, - { - "encoding": "ISO-8859-4", "confidence": 9, - "language": "lv", - "byteLogLikelihood": -4.83530398146, + "byteLogLikelihood": -4.767575136152, "hits": 4, "total": 126, "hitRate": 0.031746031746031744 }, { "encoding": "ISO-8859-13", - "confidence": 9, "language": "lt", + "confidence": 9, "byteLogLikelihood": -4.767575136152, "hits": 4, "total": 126, @@ -19414,215 +8234,53 @@ }, { "encoding": "ISO-8859-14", - "confidence": 9, "language": "cy", + "confidence": 9, "byteLogLikelihood": -4.643097648852, "hits": 4, "total": 126, "hitRate": 0.031746031746031744 }, - { - "encoding": "ISO-8859-2", - "confidence": 7, - "language": "ro", - "byteLogLikelihood": -5.060625202481, - "hits": 3, - "total": 126, - "hitRate": 0.023809523809523808 - }, { "encoding": "ISO-8859-9", - "confidence": 7, "language": "tr", - "byteLogLikelihood": -4.76855606835, - "hits": 3, - "total": 126, - "hitRate": 0.023809523809523808 - }, - { - "encoding": "windows-1250", "confidence": 7, - "language": "ro", - "byteLogLikelihood": -5.060625202481, + "byteLogLikelihood": -4.76855606835, "hits": 3, "total": 126, "hitRate": 0.023809523809523808 }, { "encoding": "windows-1254", - "confidence": 7, "language": "tr", - "byteLogLikelihood": -4.76855606835, - "hits": 3, - "total": 126, - "hitRate": 0.023809523809523808 - }, - { - "encoding": "ISO-8859-3", - "confidence": 7, - "language": "mt", - "byteLogLikelihood": -4.906120867834, - "hits": 3, - "total": 124, - "hitRate": 0.024193548387096774 - }, - { - "encoding": "ISO-8859-15", "confidence": 7, - "language": "es", - "byteLogLikelihood": -4.873536273681, + "byteLogLikelihood": -4.76855606835, "hits": 3, "total": 126, "hitRate": 0.023809523809523808 }, - { - "encoding": "CP850", - "confidence": 7, - "language": "es", - "byteLogLikelihood": -4.948759890378, - "hits": 3, - "total": 116, - "hitRate": 0.02586206896551724 - }, - { - "encoding": "CP852", - "confidence": 7, - "language": "pl", - "byteLogLikelihood": -5.087596335232, - "hits": 3, - "total": 119, - "hitRate": 0.025210084033613446 - }, - { - "encoding": "ISO-8859-16", - "confidence": 2, - "language": "ro", - "byteLogLikelihood": -5.104831294985, - "hits": 1, - "total": 126, - "hitRate": 0.007936507936507936 - }, - { - "encoding": "ISO-8859-5", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.315573016103, - "hits": 0, - "total": 124, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-6", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -5.428051016065, - "hits": 0, - "total": 115, - "hitRate": 0 - }, { "encoding": "ISO-8859-7", - "confidence": 0, "language": "el", + "confidence": 0, "byteLogLikelihood": -4.428592570712, "hits": 0, "total": 125, "hitRate": 0 }, - { - "encoding": "ISO-8859-8", - "confidence": 0, - "language": "he", - "byteLogLikelihood": -4.890004274964, - "hits": 0, - "total": 124, - "hitRate": 0 - }, - { - "encoding": "windows-1251", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -4.843070172798, - "hits": 0, - "total": 126, - "hitRate": 0 - }, { "encoding": "windows-1253", - "confidence": 0, "language": "el", + "confidence": 0, "byteLogLikelihood": -4.428592570712, "hits": 0, "total": 125, "hitRate": 0 }, - { - "encoding": "windows-1255", - "confidence": 0, - "language": "he", - "byteLogLikelihood": -4.890004274964, - "hits": 0, - "total": 124, - "hitRate": 0 - }, - { - "encoding": "windows-1256", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -5.628297137503, - "hits": 0, - "total": 121, - "hitRate": 0 - }, - { - "encoding": "windows-874", - "confidence": 0, - "language": "th", - "byteLogLikelihood": -5.351753988745, - "hits": 0, - "total": 114, - "hitRate": 0 - }, - { - "encoding": "KOI8-R", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.775144482981, - "hits": 0, - "total": 126, - "hitRate": 0 - }, - { - "encoding": "KOI8-U", - "confidence": 0, - "language": "uk", - "byteLogLikelihood": -5.565906355903, - "hits": 0, - "total": 126, - "hitRate": 0 - }, - { - "encoding": "IBM866", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.727056945557, - "hits": 0, - "total": 124, - "hitRate": 0 - }, - { - "encoding": "IBM855", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.876501639082, - "hits": 0, - "total": 124, - "hitRate": 0 - }, { "encoding": "x-mac-cyrillic", - "confidence": 0, "language": "ru", + "confidence": 0, "byteLogLikelihood": -4.782036156761, "hits": 0, "total": 125, @@ -19630,8 +8288,8 @@ }, { "encoding": "ISO-8859-10", - "confidence": 0, "language": "is", + "confidence": 0, "byteLogLikelihood": -4.794574996468, "hits": 0, "total": 126, @@ -19646,8 +8304,8 @@ }, "predicted": { "encoding": "windows-874", - "confidence": 21, "language": "th", + "confidence": 21, "byteLogLikelihood": -3.827006747769, "hits": 7, "total": 100, @@ -19661,125 +8319,35 @@ "candidates": [ { "encoding": "windows-874", - "confidence": 21, "language": "th", + "confidence": 21, "byteLogLikelihood": -3.827006747769, "hits": 7, "total": 100, "hitRate": 0.07 }, - { - "encoding": "ISO-8859-6", - "confidence": 6, - "language": "ar", - "byteLogLikelihood": -5.033884846794, - "hits": 2, - "total": 93, - "hitRate": 0.021505376344086023 - }, - { - "encoding": "ISO-8859-8", - "confidence": 6, - "language": "he", - "byteLogLikelihood": -5.415196995324, - "hits": 1, - "total": 43, - "hitRate": 0.023255813953488372 - }, - { - "encoding": "windows-1255", - "confidence": 6, - "language": "he", - "byteLogLikelihood": -5.415196995324, - "hits": 1, - "total": 47, - "hitRate": 0.02127659574468085 - }, - { - "encoding": "ISO-8859-7", - "confidence": 12, - "language": "el", - "byteLogLikelihood": -5.563277974308, - "hits": 4, - "total": 97, - "hitRate": 0.041237113402061855 - }, - { - "encoding": "windows-1253", - "confidence": 12, - "language": "el", - "byteLogLikelihood": -5.563277974308, - "hits": 4, - "total": 97, - "hitRate": 0.041237113402061855 - }, - { - "encoding": "windows-1251", - "confidence": 5, - "language": "ru", - "byteLogLikelihood": -5.926448142289, - "hits": 2, - "total": 102, - "hitRate": 0.0196078431372549 - }, - { - "encoding": "x-mac-cyrillic", - "confidence": 11, - "language": "ru", - "byteLogLikelihood": -6.059253444951, - "hits": 3, - "total": 79, - "hitRate": 0.0379746835443038 - }, - { - "encoding": "KOI8-R", - "confidence": 3, - "language": "ru", - "byteLogLikelihood": -5.413211053323, - "hits": 1, - "total": 94, - "hitRate": 0.010638297872340425 - }, - { - "encoding": "IBM855", - "confidence": 3, - "language": "sr", - "byteLogLikelihood": -5.781484174666, - "hits": 1, - "total": 88, - "hitRate": 0.011363636363636364 - }, { "encoding": "ISO-8859-1", - "confidence": 0, "language": "it", - "byteLogLikelihood": -4.767489617961, - "hits": 0, - "total": 97, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-2", "confidence": 0, - "language": "cs", - "byteLogLikelihood": -4.903917269007, + "byteLogLikelihood": -4.767489617961, "hits": 0, - "total": 103, + "total": 97, "hitRate": 0 }, { - "encoding": "ISO-8859-5", + "encoding": "ISO-8859-2", + "language": "cs", "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.535400651308, + "byteLogLikelihood": -4.903917269007, "hits": 0, "total": 103, "hitRate": 0 }, { "encoding": "ISO-8859-9", - "confidence": 0, "language": "tr", + "confidence": 0, "byteLogLikelihood": -4.985031025935, "hits": 0, "total": 97, @@ -19787,8 +8355,8 @@ }, { "encoding": "windows-1250", - "confidence": 0, "language": "pl", + "confidence": 0, "byteLogLikelihood": -4.798656950405, "hits": 0, "total": 101, @@ -19796,116 +8364,44 @@ }, { "encoding": "windows-1252", - "confidence": 0, "language": "it", - "byteLogLikelihood": -4.767489617961, - "hits": 0, - "total": 97, - "hitRate": 0 - }, - { - "encoding": "windows-1254", "confidence": 0, - "language": "tr", - "byteLogLikelihood": -4.985031025935, + "byteLogLikelihood": -4.767489617961, "hits": 0, "total": 97, "hitRate": 0 }, - { - "encoding": "windows-1256", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -5.209625144761, - "hits": 0, - "total": 95, - "hitRate": 0 - }, { "encoding": "windows-1257", - "confidence": 0, "language": "et", + "confidence": 0, "byteLogLikelihood": -4.916002186025, "hits": 0, "total": 97, "hitRate": 0 }, - { - "encoding": "windows-1258", - "confidence": 0, - "language": "vi", - "byteLogLikelihood": -5.154894826847, - "hits": 0, - "total": 91, - "hitRate": 0 - }, - { - "encoding": "KOI8-U", - "confidence": 0, - "language": "uk", - "byteLogLikelihood": -5.334497573029, - "hits": 0, - "total": 98, - "hitRate": 0 - }, - { - "encoding": "IBM866", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.961753913164, - "hits": 0, - "total": 58, - "hitRate": 0 - }, { "encoding": "macintosh", - "confidence": 0, "language": "es", + "confidence": 0, "byteLogLikelihood": -4.948759890378, "hits": 0, "total": 65, "hitRate": 0 }, - { - "encoding": "ISO-8859-3", - "confidence": 0, - "language": "mt", - "byteLogLikelihood": -5.084507932234, - "hits": 0, - "total": 98, - "hitRate": 0 - }, { "encoding": "ISO-8859-4", - "confidence": 0, "language": "lv", - "byteLogLikelihood": -4.783724339715, - "hits": 0, - "total": 103, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-10", "confidence": 0, - "language": "is", - "byteLogLikelihood": -5.119633132705, + "byteLogLikelihood": -4.783724339715, "hits": 0, "total": 103, "hitRate": 0 }, - { - "encoding": "ISO-8859-13", - "confidence": 0, - "language": "lt", - "byteLogLikelihood": -5.010167702209, - "hits": 0, - "total": 97, - "hitRate": 0 - }, { "encoding": "ISO-8859-14", - "confidence": 0, "language": "cy", + "confidence": 0, "byteLogLikelihood": -4.912654885736, "hits": 0, "total": 103, @@ -19913,36 +8409,18 @@ }, { "encoding": "ISO-8859-15", - "confidence": 0, "language": "fr", + "confidence": 0, "byteLogLikelihood": -4.801693311206, "hits": 0, "total": 101, "hitRate": 0 }, - { - "encoding": "ISO-8859-16", - "confidence": 0, - "language": "ro", - "byteLogLikelihood": -5.134285984462, - "hits": 0, - "total": 103, - "hitRate": 0 - }, { "encoding": "CP850", - "confidence": 0, "language": "es", - "byteLogLikelihood": -4.887413059939, - "hits": 0, - "total": 85, - "hitRate": 0 - }, - { - "encoding": "CP852", "confidence": 0, - "language": "pl", - "byteLogLikelihood": -5.056712497361, + "byteLogLikelihood": -4.887413059939, "hits": 0, "total": 85, "hitRate": 0 @@ -19956,8 +8434,8 @@ }, "predicted": { "encoding": "x-mac-cyrillic", - "confidence": 36, "language": "ru", + "confidence": 36, "byteLogLikelihood": -3.313760777855, "hits": 22, "total": 179, @@ -19971,8 +8449,8 @@ "candidates": [ { "encoding": "x-mac-cyrillic", - "confidence": 36, "language": "ru", + "confidence": 36, "byteLogLikelihood": -3.313760777855, "hits": 22, "total": 179, @@ -19980,26 +8458,17 @@ }, { "encoding": "windows-1251", - "confidence": 42, "language": "ru", + "confidence": 42, "byteLogLikelihood": -3.411211853364, "hits": 25, "total": 177, "hitRate": 0.14124293785310735 }, - { - "encoding": "IBM855", - "confidence": 9, - "language": "sr", - "byteLogLikelihood": -5.603105135042, - "hits": 5, - "total": 165, - "hitRate": 0.030303030303030304 - }, { "encoding": "ISO-8859-8", - "confidence": 3, "language": "he", + "confidence": 3, "byteLogLikelihood": -3.941595102268, "hits": 2, "total": 167, @@ -20007,215 +8476,71 @@ }, { "encoding": "windows-1255", - "confidence": 3, "language": "he", - "byteLogLikelihood": -3.941595102268, - "hits": 2, - "total": 167, - "hitRate": 0.011976047904191617 - }, - { - "encoding": "KOI8-U", "confidence": 3, - "language": "uk", - "byteLogLikelihood": -6.334488595021, - "hits": 2, - "total": 177, - "hitRate": 0.011299435028248588 - }, - { - "encoding": "windows-1256", - "confidence": 1, - "language": "ar", - "byteLogLikelihood": -5.525051915661, - "hits": 1, - "total": 163, - "hitRate": 0.006134969325153374 - }, - { - "encoding": "KOI8-R", - "confidence": 1, - "language": "ru", - "byteLogLikelihood": -6.390589047944, - "hits": 1, - "total": 177, - "hitRate": 0.005649717514124294 - }, - { - "encoding": "ISO-8859-14", - "confidence": 1, - "language": "cy", - "byteLogLikelihood": -4.724449359889, - "hits": 1, - "total": 177, - "hitRate": 0.005649717514124294 - }, - { - "encoding": "ISO-8859-1", - "confidence": 0, - "language": "sv", - "byteLogLikelihood": -4.665227236998, - "hits": 0, - "total": 177, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-2", - "confidence": 0, - "language": "cs", - "byteLogLikelihood": -4.845647442888, - "hits": 0, - "total": 177, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-5", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -4.975257565806, - "hits": 0, - "total": 175, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-6", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -4.847464468096, - "hits": 0, - "total": 127, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-7", - "confidence": 0, - "language": "el", - "byteLogLikelihood": -4.148248171081, - "hits": 0, - "total": 177, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-9", - "confidence": 0, - "language": "tr", - "byteLogLikelihood": -4.950903003627, - "hits": 0, - "total": 177, - "hitRate": 0 - }, - { - "encoding": "windows-1250", - "confidence": 0, - "language": "cs", - "byteLogLikelihood": -4.845647442888, - "hits": 0, - "total": 177, - "hitRate": 0 - }, - { - "encoding": "windows-1252", - "confidence": 0, - "language": "sv", - "byteLogLikelihood": -4.665227236998, - "hits": 0, - "total": 177, - "hitRate": 0 - }, - { - "encoding": "windows-1253", - "confidence": 0, - "language": "el", - "byteLogLikelihood": -4.148248171081, - "hits": 0, - "total": 177, - "hitRate": 0 - }, - { - "encoding": "windows-1254", - "confidence": 0, - "language": "tr", - "byteLogLikelihood": -4.950903003627, - "hits": 0, - "total": 177, - "hitRate": 0 - }, - { - "encoding": "windows-1257", - "confidence": 0, - "language": "lv", - "byteLogLikelihood": -4.61521723683, - "hits": 0, - "total": 177, - "hitRate": 0 - }, - { - "encoding": "windows-1258", - "confidence": 0, - "language": "vi", - "byteLogLikelihood": -4.899487478125, - "hits": 0, - "total": 173, - "hitRate": 0 + "byteLogLikelihood": -3.941595102268, + "hits": 2, + "total": 167, + "hitRate": 0.011976047904191617 }, { - "encoding": "windows-874", - "confidence": 0, - "language": "th", - "byteLogLikelihood": -5.446015416921, - "hits": 0, - "total": 85, - "hitRate": 0 + "encoding": "ISO-8859-14", + "language": "cy", + "confidence": 1, + "byteLogLikelihood": -4.724449359889, + "hits": 1, + "total": 177, + "hitRate": 0.005649717514124294 }, { - "encoding": "IBM866", + "encoding": "ISO-8859-1", + "language": "sv", "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.05026366488, + "byteLogLikelihood": -4.665227236998, "hits": 0, - "total": 169, + "total": 177, "hitRate": 0 }, { - "encoding": "macintosh", + "encoding": "ISO-8859-7", + "language": "el", "confidence": 0, - "language": "es", - "byteLogLikelihood": -4.944169511699, + "byteLogLikelihood": -4.148248171081, "hits": 0, - "total": 151, + "total": 177, "hitRate": 0 }, { - "encoding": "ISO-8859-3", + "encoding": "windows-1252", + "language": "sv", "confidence": 0, - "language": "mt", - "byteLogLikelihood": -4.904224209153, + "byteLogLikelihood": -4.665227236998, "hits": 0, - "total": 175, + "total": 177, "hitRate": 0 }, { - "encoding": "ISO-8859-4", + "encoding": "windows-1253", + "language": "el", "confidence": 0, - "language": "lv", - "byteLogLikelihood": -4.79659105312, + "byteLogLikelihood": -4.148248171081, "hits": 0, "total": 177, "hitRate": 0 }, { - "encoding": "ISO-8859-10", + "encoding": "windows-1257", + "language": "lv", "confidence": 0, - "language": "is", - "byteLogLikelihood": -4.939249573759, + "byteLogLikelihood": -4.61521723683, "hits": 0, "total": 177, "hitRate": 0 }, { "encoding": "ISO-8859-13", - "confidence": 0, "language": "lt", + "confidence": 0, "byteLogLikelihood": -4.66408545306, "hits": 0, "total": 177, @@ -20223,39 +8548,12 @@ }, { "encoding": "ISO-8859-15", - "confidence": 0, "language": "fr", - "byteLogLikelihood": -4.760478683076, - "hits": 0, - "total": 177, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-16", "confidence": 0, - "language": "ro", - "byteLogLikelihood": -4.97522262578, + "byteLogLikelihood": -4.760478683076, "hits": 0, "total": 177, "hitRate": 0 - }, - { - "encoding": "CP850", - "confidence": 0, - "language": "es", - "byteLogLikelihood": -4.948759890378, - "hits": 0, - "total": 137, - "hitRate": 0 - }, - { - "encoding": "CP852", - "confidence": 0, - "language": "pl", - "byteLogLikelihood": -5.083005956553, - "hits": 0, - "total": 156, - "hitRate": 0 } ] }, @@ -20266,8 +8564,8 @@ }, "predicted": { "encoding": "x-mac-cyrillic", - "confidence": 32, "language": "uk", + "confidence": 32, "byteLogLikelihood": -3.34369756932, "hits": 19, "total": 177, @@ -20281,8 +8579,8 @@ "candidates": [ { "encoding": "x-mac-cyrillic", - "confidence": 32, "language": "uk", + "confidence": 32, "byteLogLikelihood": -3.34369756932, "hits": 19, "total": 177, @@ -20290,26 +8588,17 @@ }, { "encoding": "windows-1251", - "confidence": 17, "language": "ru", + "confidence": 17, "byteLogLikelihood": -3.606822645813, "hits": 10, "total": 176, "hitRate": 0.056818181818181816 }, - { - "encoding": "IBM855", - "confidence": 5, - "language": "sr", - "byteLogLikelihood": -5.830774318921, - "hits": 3, - "total": 163, - "hitRate": 0.018404907975460124 - }, { "encoding": "ISO-8859-8", - "confidence": 3, "language": "he", + "confidence": 3, "byteLogLikelihood": -4.062591421695, "hits": 2, "total": 165, @@ -20317,98 +8606,35 @@ }, { "encoding": "windows-1255", - "confidence": 3, "language": "he", + "confidence": 3, "byteLogLikelihood": -4.062591421695, "hits": 2, "total": 165, "hitRate": 0.012121212121212121 }, - { - "encoding": "KOI8-R", - "confidence": 3, - "language": "ru", - "byteLogLikelihood": -6.397907632883, - "hits": 2, - "total": 169, - "hitRate": 0.011834319526627219 - }, - { - "encoding": "ISO-8859-6", - "confidence": 2, - "language": "ar", - "byteLogLikelihood": -4.990380473945, - "hits": 1, - "total": 119, - "hitRate": 0.008403361344537815 - }, - { - "encoding": "KOI8-U", - "confidence": 1, - "language": "uk", - "byteLogLikelihood": -6.341901231006, - "hits": 1, - "total": 175, - "hitRate": 0.005714285714285714 - }, { "encoding": "ISO-8859-1", - "confidence": 0, "language": "it", - "byteLogLikelihood": -4.629500955096, - "hits": 0, - "total": 169, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-2", "confidence": 0, - "language": "cs", - "byteLogLikelihood": -4.739775351774, + "byteLogLikelihood": -4.629500955096, "hits": 0, "total": 169, "hitRate": 0 }, - { - "encoding": "ISO-8859-5", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -4.989983227843, - "hits": 0, - "total": 171, - "hitRate": 0 - }, { "encoding": "ISO-8859-7", - "confidence": 0, "language": "el", - "byteLogLikelihood": -4.300043808736, - "hits": 0, - "total": 169, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-9", "confidence": 0, - "language": "tr", - "byteLogLikelihood": -4.951345660734, + "byteLogLikelihood": -4.300043808736, "hits": 0, "total": 169, "hitRate": 0 }, - { - "encoding": "windows-1250", - "confidence": 0, - "language": "cs", - "byteLogLikelihood": -4.739775351774, - "hits": 0, - "total": 170, - "hitRate": 0 - }, { "encoding": "windows-1252", - "confidence": 0, "language": "it", + "confidence": 0, "byteLogLikelihood": -4.629500955096, "hits": 0, "total": 170, @@ -20416,107 +8642,35 @@ }, { "encoding": "windows-1253", - "confidence": 0, "language": "el", + "confidence": 0, "byteLogLikelihood": -4.300043808736, "hits": 0, "total": 169, "hitRate": 0 }, - { - "encoding": "windows-1254", - "confidence": 0, - "language": "tr", - "byteLogLikelihood": -4.951345660734, - "hits": 0, - "total": 170, - "hitRate": 0 - }, - { - "encoding": "windows-1256", - "confidence": 0, - "language": "ar", - "byteLogLikelihood": -5.607550779971, - "hits": 0, - "total": 155, - "hitRate": 0 - }, { "encoding": "windows-1257", - "confidence": 0, "language": "lv", + "confidence": 0, "byteLogLikelihood": -4.60874799529, "hits": 0, "total": 169, "hitRate": 0 }, - { - "encoding": "windows-1258", - "confidence": 0, - "language": "vi", - "byteLogLikelihood": -4.777030248466, - "hits": 0, - "total": 164, - "hitRate": 0 - }, - { - "encoding": "windows-874", - "confidence": 0, - "language": "th", - "byteLogLikelihood": -5.197321748228, - "hits": 0, - "total": 83, - "hitRate": 0 - }, - { - "encoding": "IBM866", - "confidence": 0, - "language": "ru", - "byteLogLikelihood": -5.100977296295, - "hits": 0, - "total": 167, - "hitRate": 0 - }, - { - "encoding": "macintosh", - "confidence": 0, - "language": "es", - "byteLogLikelihood": -4.948759890378, - "hits": 0, - "total": 139, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-3", - "confidence": 0, - "language": "mt", - "byteLogLikelihood": -5.035218126431, - "hits": 0, - "total": 164, - "hitRate": 0 - }, { "encoding": "ISO-8859-4", - "confidence": 0, "language": "lv", + "confidence": 0, "byteLogLikelihood": -4.726279355538, "hits": 0, "total": 169, "hitRate": 0 }, - { - "encoding": "ISO-8859-10", - "confidence": 0, - "language": "is", - "byteLogLikelihood": -4.876716873437, - "hits": 0, - "total": 175, - "hitRate": 0 - }, { "encoding": "ISO-8859-13", - "confidence": 0, "language": "lt", + "confidence": 0, "byteLogLikelihood": -4.669220995205, "hits": 0, "total": 169, @@ -20524,48 +8678,12 @@ }, { "encoding": "ISO-8859-14", - "confidence": 0, "language": "cy", - "byteLogLikelihood": -4.725687554138, - "hits": 0, - "total": 175, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-15", - "confidence": 0, - "language": "fr", - "byteLogLikelihood": -4.753004092615, - "hits": 0, - "total": 175, - "hitRate": 0 - }, - { - "encoding": "ISO-8859-16", "confidence": 0, - "language": "ro", - "byteLogLikelihood": -5.030920483462, + "byteLogLikelihood": -4.725687554138, "hits": 0, "total": 175, "hitRate": 0 - }, - { - "encoding": "CP850", - "confidence": 0, - "language": "es", - "byteLogLikelihood": -4.948759890378, - "hits": 0, - "total": 137, - "hitRate": 0 - }, - { - "encoding": "CP852", - "confidence": 0, - "language": "pl", - "byteLogLikelihood": -5.087596335232, - "hits": 0, - "total": 152, - "hitRate": 0 } ] } diff --git a/package.json b/package.json index a3e54c5..1cb77cb 100644 --- a/package.json +++ b/package.json @@ -16,9 +16,9 @@ "build": "rm -rf lib/* && tsc -p tsconfig.build.json", "corpus:build": "node scripts/build-corpus.mjs", "corpus:verify": "node scripts/verify-corpus.mjs", - "models:build": "node scripts/build-models.mjs", - "models:evaluate": "node scripts/evaluate-models.mjs", - "models:verify": "node scripts/verify-models.mjs", + "models:build": "tsx scripts/build-models.mjs", + "models:evaluate": "tsx scripts/evaluate-models.mjs", + "models:verify": "tsx scripts/verify-models.mjs", "benchmark": "tsx scripts/benchmark.mjs", "validate": "tsx scripts/validate.mjs", "format": "prettier --write \"**/*.{ts,json,md,mjs}\"", diff --git a/scripts/model-utils.mjs b/scripts/model-utils.mjs index f9e9f15..e068aa9 100644 --- a/scripts/model-utils.mjs +++ b/scripts/model-utils.mjs @@ -2,6 +2,11 @@ import { spawnSync } from 'node:child_process'; import { mkdirSync, readFileSync, writeFileSync } from 'node:fs'; import { dirname, join, resolve } from 'node:path'; import { fileURLToPath } from 'node:url'; +import { + prepareSBCSModels, + scoreSBCS, + trigrams, +} from '../src/encoding/sbcs-scoring.ts'; const root = resolve(dirname(fileURLToPath(import.meta.url)), '..'); const corpus = join(root, 'corpus'); @@ -90,30 +95,6 @@ function byteMapFor(encoding) { return byteMap; } -function normalizedBytes(buffer, byteMap) { - const normalized = []; - let ignoreSpace = false; - for (const byte of buffer) { - const mapped = byteMap[byte]; - if (mapped !== 0) { - if (!(mapped === 0x20 && ignoreSpace)) normalized.push(mapped); - ignoreSpace = mapped === 0x20; - } - } - normalized.push(0x20); - return normalized; -} - -function trigrams(buffer, byteMap) { - const values = []; - let trigram = 0; - for (const byte of normalizedBytes(buffer, byteMap)) { - trigram = ((trigram << 8) + byte) & 0xffffff; - values.push(trigram); - } - return values; -} - function detectorNgrams(buffers, byteMap) { const counts = new Map(); for (const buffer of buffers) { @@ -160,43 +141,6 @@ function highByteDistribution(buffers) { }; } -function byteLogLikelihood(buffer, distribution) { - const counts = new Map(distribution.counts); - const denominator = distribution.total + 128; - let highBytes = 0; - let likelihood = 0; - for (const byte of buffer) { - if (byte >= 0x80) { - likelihood += Math.log(((counts.get(byte) ?? 0) + 1) / denominator); - highBytes += 1; - } - } - return highBytes === 0 - ? Number.NEGATIVE_INFINITY - : Number((likelihood / highBytes).toFixed(12)); -} - -function ngramScore(buffer, byteMap, modelNgrams) { - const known = new Set(modelNgrams); - const values = trigrams(buffer, byteMap); - const hits = values.filter((trigram) => known.has(trigram)).length; - const rawPercent = hits / values.length; - return { - confidence: rawPercent > 0.33 ? 98 : Math.floor(rawPercent * 300), - hits, - total: values.length, - hitRate: rawPercent, - }; -} - -function statisticallyCompetitive(best, candidate) { - const variance = - (best.hitRate * (1 - best.hitRate)) / best.total + - (candidate.hitRate * (1 - candidate.hitRate)) / candidate.total; - const margin = 1.96 * Math.sqrt(variance); - return best.hitRate - candidate.hitRate <= margin; -} - function decodedText(buffer, encodingName) { const encoding = manifest.encodings.find( (candidate) => candidate.name === encodingName, @@ -215,21 +159,6 @@ function byteEquivalent(buffer, leftEncoding, rightEncoding) { } } -const equivalentEncodingFamilies = [ - ['ISO-8859-1', 'ISO-8859-15', 'windows-1252'], - ['ISO-8859-2', 'windows-1250'], - ['ISO-8859-7', 'windows-1253'], - ['ISO-8859-8', 'windows-1255'], - ['ISO-8859-9', 'windows-1254'], - ['ISO-8859-13', 'windows-1257'], -]; - -function encodingFamily(name) { - return ( - equivalentEncodingFamilies.find((family) => family.includes(name)) ?? [name] - ); -} - function compileSingleByteModels() { const models = []; for (const encoding of manifest.encodings) { @@ -262,78 +191,14 @@ function compileSingleByteModels() { } function evaluate(models) { + const preparedModels = prepareSBCSModels(models); const tests = corpusIndex.filter( (row) => row.split === 'test' && row.encoding !== 'CP949', ); const results = tests.map((test) => { const buffer = readFileSync(join(generatedCorpus, test.path)); - const candidates = models.map((model) => { - const languageScores = model.languages.map((language) => ({ - language: language.language, - ...ngramScore(buffer, model.byteMap, language.ngrams), - byteLogLikelihood: byteLogLikelihood(buffer, language.highBytes), - })); - const confidenceScore = Math.max( - ...languageScores.map((score) => score.confidence), - ); - const confidenceLanguages = languageScores.filter( - (score) => score.confidence === confidenceScore, - ); - confidenceLanguages.sort( - (left, right) => right.byteLogLikelihood - left.byteLogLikelihood, - ); - const confidenceLanguage = confidenceLanguages[0]; - return { - encoding: model.encoding, - confidence: confidenceScore, - language: confidenceLanguage.language, - byteLogLikelihood: confidenceLanguage.byteLogLikelihood, - hits: confidenceLanguage.hits, - total: confidenceLanguage.total, - hitRate: confidenceLanguage.hitRate, - }; - }); - candidates.sort((left, right) => right.confidence - left.confidence); - const strongest = candidates[0]; - const competitive = candidates.filter((candidate) => - statisticallyCompetitive(strongest, candidate), - ); - const competitiveEncodings = new Set( - competitive.map((candidate) => candidate.encoding), - ); - competitive.sort( - (left, right) => - right.byteLogLikelihood - left.byteLogLikelihood || - right.confidence - left.confidence, - ); - const remaining = candidates.filter( - (candidate) => !competitiveEncodings.has(candidate.encoding), - ); - candidates.splice(0, candidates.length, ...competitive, ...remaining); - const strongestPrediction = candidates[0]; - const strongestFamily = encodingFamily(strongestPrediction.encoding); - const equivalentLanguageCandidates = candidates.filter( - (candidate) => - strongestFamily.includes(candidate.encoding) && - byteEquivalent( - buffer, - strongestPrediction.encoding, - candidate.encoding, - ), - ); - equivalentLanguageCandidates.sort( - (left, right) => - manifest.encodings.findIndex( - (encoding) => encoding.name === left.encoding, - ) - - manifest.encodings.findIndex( - (encoding) => encoding.name === right.encoding, - ), - ); - const predicted = { - ...strongestPrediction, - language: equivalentLanguageCandidates[0].language, - }; + const candidates = scoreSBCS(buffer, preparedModels); + const predicted = candidates[0]; const encodingExact = predicted.encoding === test.encoding; const encodingEquivalent = !encodingExact && diff --git a/src/encoding/sbcs-scoring.test.ts b/src/encoding/sbcs-scoring.test.ts new file mode 100644 index 0000000..a509527 --- /dev/null +++ b/src/encoding/sbcs-scoring.test.ts @@ -0,0 +1,78 @@ +import fs from 'fs'; +import path from 'path'; +import { describe, expect, it } from 'vitest'; +import type { Context } from '.'; +import { generatedSBCSModels } from './models/generated'; +import type { GeneratedSBCSModel } from './models/types'; +import { analyseGeneratedSBCS } from './sbcs'; +import { prepareSBCSModels, scoreSBCS, trigrams } from './sbcs-scoring'; + +const preparedModels = prepareSBCSModels( + generatedSBCSModels as readonly GeneratedSBCSModel[], +); + +function context(input: Uint8Array): Context { + const byteStats = Array(256).fill(0); + for (const byte of input) byteStats[byte] += 1; + return { + byteStats, + c1Bytes: input.some((byte) => byte >= 0x80 && byte <= 0x9f), + rawInput: input, + rawLen: input.length, + inputBytes: input, + inputLen: input.length, + }; +} + +describe('shared SBCS scoring', () => { + it('normalizes ignored bytes and repeated spaces before scoring trigrams', () => { + const byteMap = Array.from({ length: 256 }, (_, byte) => byte); + byteMap[0x27] = 0; + + expect( + trigrams(new Uint8Array([0x41, 0x20, 0x20, 0x27, 0x42]), byteMap), + ).toEqual([0x41, 0x4120, 0x412042, 0x204220]); + }); + + it.each([ + new Uint8Array(), + new Uint8Array([0x41]), + new Uint8Array([0xff]), + new Uint8Array([0xc3]), + new Uint8Array([0x00, 0xff, 0x80, 0x00]), + ])('returns deterministic finite confidence scores for %j', (input) => { + const first = scoreSBCS(input, preparedModels); + const second = scoreSBCS(input, preparedModels); + + expect(second).toEqual(first); + expect(first.length).toBeGreaterThan(0); + expect( + first.every( + ({ confidence }) => + Number.isFinite(confidence) && confidence >= 0 && confidence <= 100, + ), + ).toBe(true); + }); + + it('keeps the runtime wrapper aligned with the shared scorer on the corpus', () => { + const corpusRoot = path.join(__dirname, '../../corpus/generated'); + const corpusIndex = JSON.parse( + fs.readFileSync(path.join(corpusRoot, 'index.json'), 'utf8'), + ) as { encoding: string; path: string }[]; + const rows = corpusIndex.filter(({ encoding }) => encoding !== 'CP949'); + + for (const row of rows) { + const input = fs.readFileSync(path.join(corpusRoot, row.path)); + const raw = scoreSBCS(input, preparedModels).find( + ({ confidence }) => confidence > 0, + ); + const runtime = analyseGeneratedSBCS(context(input))[0]; + + expect(runtime, row.path).toEqual({ + name: raw?.encoding, + lang: raw?.language, + confidence: raw ? raw.confidence / 100 : undefined, + }); + } + }); +}); diff --git a/src/encoding/sbcs-scoring.ts b/src/encoding/sbcs-scoring.ts new file mode 100644 index 0000000..d192928 --- /dev/null +++ b/src/encoding/sbcs-scoring.ts @@ -0,0 +1,304 @@ +import type { EncodingName } from '../match'; +import type { + GeneratedSBCSLanguage, + GeneratedSBCSModel, + HighByteDistribution, +} from './models/types'; + +const N_GRAM_MASK = 0xffffff; +// Byte distributions are cheap and sufficiently discriminative to exclude +// most encodings before the more expensive n-gram pass. The corpus needs 11 +// candidates to preserve full-result accuracy; keep one additional candidate +// as headroom for unseen inputs. +const MAX_SBCS_CANDIDATES = 12; + +export interface SBCSScore { + readonly confidence: number; + readonly hitRate: number; + readonly hits: number; + readonly total: number; +} + +export interface SBCSCandidate extends SBCSScore { + readonly encoding: EncodingName; + readonly language: string; + readonly byteLogLikelihood: number; +} + +interface RankedSBCSCandidate extends SBCSCandidate { + readonly modelIndex: number; +} + +interface PreparedSBCSLanguage { + readonly model: GeneratedSBCSLanguage; + readonly highByteLogProbabilities: Float64Array; +} + +export interface PreparedSBCSModel { + readonly model: GeneratedSBCSModel; + readonly modelIndex: number; + readonly languages: readonly PreparedSBCSLanguage[]; + readonly ngramLanguageIndexes: ReadonlyMap; +} + +type HighByteCounts = readonly (readonly [number, number])[]; + +const equivalentEncodingFamilies = [ + ['ISO-8859-1', 'ISO-8859-15', 'windows-1252'], + ['ISO-8859-2', 'windows-1250'], + ['ISO-8859-7', 'windows-1253'], + ['ISO-8859-8', 'windows-1255'], + ['ISO-8859-9', 'windows-1254'], + ['ISO-8859-13', 'windows-1257'], +] as const; + +function scanTrigrams( + input: Uint8Array, + byteMap: readonly number[], + record: (value: number) => void, +): number { + let ignoreSpace = false; + let ngram = 0; + let total = 0; + + const append = (mapped: number) => { + ngram = ((ngram << 8) + mapped) & N_GRAM_MASK; + total += 1; + record(ngram); + }; + + for (const byte of input) { + const mapped = byteMap[byte]; + if (mapped !== 0) { + if (!(mapped === 0x20 && ignoreSpace)) append(mapped); + ignoreSpace = mapped === 0x20; + } + } + + append(0x20); + return total; +} + +export function trigrams( + input: Uint8Array, + byteMap: readonly number[], +): number[] { + const values: number[] = []; + scanTrigrams(input, byteMap, (value) => values.push(value)); + return values; +} + +export function statisticallyCompetitive( + best: SBCSScore, + candidate: SBCSScore, +): boolean { + const variance = + (best.hitRate * (1 - best.hitRate)) / best.total + + (candidate.hitRate * (1 - candidate.hitRate)) / candidate.total; + return best.hitRate - candidate.hitRate <= 1.96 * Math.sqrt(variance); +} + +function highByteCounts(input: Uint8Array): HighByteCounts { + const counts = new Uint32Array(128); + for (const byte of input) { + if (byte >= 0x80) counts[byte - 0x80] += 1; + } + + const result: [number, number][] = []; + counts.forEach((count, index) => { + if (count > 0) result.push([index + 0x80, count]); + }); + return result; +} + +function highByteLogProbabilities(distribution: HighByteDistribution) { + const counts = new Map(distribution.counts); + const denominator = distribution.total + 128; + return Float64Array.from({ length: 128 }, (_, index) => + Math.log(((counts.get(index + 0x80) ?? 0) + 1) / denominator), + ); +} + +function ngramLanguageIndexes(model: GeneratedSBCSModel) { + const indexes = new Map(); + model.languages.forEach((language, languageIndex) => { + for (const ngram of new Set(language.ngrams)) { + const languageIndexes = indexes.get(ngram) ?? []; + languageIndexes.push(languageIndex); + indexes.set(ngram, languageIndexes); + } + }); + return indexes; +} + +export function prepareSBCSModels( + models: readonly GeneratedSBCSModel[], +): readonly PreparedSBCSModel[] { + return models.map((model, modelIndex) => ({ + model, + modelIndex, + languages: model.languages.map((language) => ({ + model: language, + highByteLogProbabilities: highByteLogProbabilities(language.highBytes), + })), + ngramLanguageIndexes: ngramLanguageIndexes(model), + })); +} + +function byteLogLikelihood( + counts: HighByteCounts, + logProbabilities: Float64Array, +) { + let highBytes = 0; + let likelihood = 0; + + for (const [byte, count] of counts) { + likelihood += logProbabilities[byte - 0x80] * count; + highBytes += count; + } + + return highBytes === 0 + ? Number.NEGATIVE_INFINITY + : Number((likelihood / highBytes).toFixed(12)); +} + +function modelByteLogLikelihood( + counts: HighByteCounts, + prepared: PreparedSBCSModel, +) { + let best = Number.NEGATIVE_INFINITY; + for (const language of prepared.languages) { + best = Math.max( + best, + byteLogLikelihood(counts, language.highByteLogProbabilities), + ); + } + return best; +} + +function candidate( + input: Uint8Array, + counts: HighByteCounts, + prepared: PreparedSBCSModel, + hits: Uint32Array, +): RankedSBCSCandidate { + hits.fill(0, 0, prepared.languages.length); + const total = scanTrigrams(input, prepared.model.byteMap, (value) => { + for (const languageIndex of prepared.ngramLanguageIndexes.get(value) ?? + []) { + hits[languageIndex] += 1; + } + }); + + let bestIndex = 0; + let bestConfidence = -1; + let bestByteLogLikelihood = Number.NEGATIVE_INFINITY; + let bestHitRate = 0; + + for (let index = 0; index < prepared.languages.length; index += 1) { + const hitRate = hits[index] / total; + const confidence = hitRate > 0.33 ? 98 : Math.floor(hitRate * 300); + const likelihood = byteLogLikelihood( + counts, + prepared.languages[index].highByteLogProbabilities, + ); + if ( + confidence > bestConfidence || + (confidence === bestConfidence && likelihood > bestByteLogLikelihood) + ) { + bestIndex = index; + bestConfidence = confidence; + bestByteLogLikelihood = likelihood; + bestHitRate = hitRate; + } + } + + return { + encoding: prepared.model.encoding, + language: prepared.languages[bestIndex].model.language, + confidence: bestConfidence, + byteLogLikelihood: bestByteLogLikelihood, + hits: hits[bestIndex], + total, + hitRate: bestHitRate, + modelIndex: prepared.modelIndex, + }; +} + +function family(name: EncodingName) { + return equivalentEncodingFamilies.find((value) => + value.includes(name as never), + ); +} + +function familyPreference( + left: SBCSCandidate, + right: SBCSCandidate, + c1Bytes: boolean, +) { + const leftFamily = family(left.encoding); + if (!leftFamily || leftFamily !== family(right.encoding)) return 0; + const preferred = + leftFamily[0] === 'ISO-8859-13' || c1Bytes + ? [...leftFamily].reverse() + : [...leftFamily]; + return ( + preferred.indexOf(left.encoding as never) - + preferred.indexOf(right.encoding as never) + ); +} + +export function scoreSBCS( + input: Uint8Array, + preparedModels: readonly PreparedSBCSModel[], + c1Bytes = input.some((byte) => byte >= 0x80 && byte <= 0x9f), +): SBCSCandidate[] { + if (preparedModels.length === 0) return []; + + const counts = highByteCounts(input); + const hits = new Uint32Array( + Math.max(...preparedModels.map((model) => model.languages.length)), + ); + const models = + counts.length === 0 + ? preparedModels + : preparedModels + .map((model) => ({ + model, + likelihood: modelByteLogLikelihood(counts, model), + })) + .sort( + (left, right) => + right.likelihood - left.likelihood || + left.model.modelIndex - right.model.modelIndex, + ) + .slice(0, MAX_SBCS_CANDIDATES) + .map(({ model }) => model); + const candidates = models.map((model) => + candidate(input, counts, model, hits), + ); + candidates.sort( + (left, right) => + right.confidence - left.confidence || left.modelIndex - right.modelIndex, + ); + + const strongest = candidates[0]; + const competitive = candidates.filter((value) => + statisticallyCompetitive(strongest, value), + ); + const competitiveNames = new Set(competitive.map((value) => value.encoding)); + competitive.sort( + (left, right) => + familyPreference(left, right, c1Bytes) || + right.byteLogLikelihood - left.byteLogLikelihood || + right.confidence - left.confidence || + left.modelIndex - right.modelIndex, + ); + const remaining = candidates.filter( + (value) => !competitiveNames.has(value.encoding), + ); + + return [...competitive, ...remaining].map( + ({ modelIndex: _modelIndex, ...value }) => value, + ); +} diff --git a/src/encoding/sbcs.ts b/src/encoding/sbcs.ts index 3e79e99..bc45362 100644 --- a/src/encoding/sbcs.ts +++ b/src/encoding/sbcs.ts @@ -1,267 +1,23 @@ import type { Match } from '../match'; import type { Context } from '.'; import { generatedSBCSModels } from './models/generated'; -import type { - GeneratedSBCSLanguage, - GeneratedSBCSModel, - HighByteDistribution, -} from './models/types'; +import type { GeneratedSBCSModel } from './models/types'; +import { prepareSBCSModels, scoreSBCS } from './sbcs-scoring'; -const N_GRAM_MASK = 0xffffff; -// Byte distributions are cheap and sufficiently discriminative to exclude -// most encodings before the more expensive n-gram pass. The corpus needs 11 -// candidates to preserve full-result accuracy; keep one additional candidate -// as headroom for unseen inputs. -const MAX_SBCS_CANDIDATES = 12; - -interface Score { - confidence: number; - hitRate: number; - hits: number; - total: number; -} - -interface Candidate extends Match, Score { - byteLogLikelihood: number; -} - -interface PreparedSBCSLanguage { - readonly model: GeneratedSBCSLanguage; - readonly highByteLogProbabilities: Float64Array; -} - -interface PreparedSBCSModel { - readonly model: GeneratedSBCSModel; - readonly languages: readonly PreparedSBCSLanguage[]; - readonly ngramLanguageMasks: ReadonlyMap; -} - -type HighByteCounts = readonly (readonly [number, number])[]; - -function highByteLogProbabilities(distribution: HighByteDistribution) { - const counts = new Map(distribution.counts); - const denominator = distribution.total + 128; - return Float64Array.from({ length: 128 }, (_, index) => - Math.log(((counts.get(index + 0x80) ?? 0) + 1) / denominator), - ); -} - -function ngramLanguageMasks(model: GeneratedSBCSModel) { - const masks = new Map(); - model.languages.forEach((language, languageIndex) => { - for (const ngram of new Set(language.ngrams)) { - masks.set(ngram, (masks.get(ngram) ?? 0) | (1 << languageIndex)); - } - }); - return masks; -} - -const preparedSBCSModels: readonly PreparedSBCSModel[] = ( - generatedSBCSModels as readonly GeneratedSBCSModel[] -).map((model) => ({ - model, - languages: model.languages.map((language) => ({ - model: language, - highByteLogProbabilities: highByteLogProbabilities(language.highBytes), - })), - ngramLanguageMasks: ngramLanguageMasks(model), -})); -const maxLanguagesPerModel = Math.max( - ...preparedSBCSModels.map((model) => model.languages.length), +const preparedSBCSModels = prepareSBCSModels( + generatedSBCSModels as readonly GeneratedSBCSModel[], ); -const equivalentEncodingFamilies = [ - ['ISO-8859-1', 'ISO-8859-15', 'windows-1252'], - ['ISO-8859-2', 'windows-1250'], - ['ISO-8859-7', 'windows-1253'], - ['ISO-8859-8', 'windows-1255'], - ['ISO-8859-9', 'windows-1254'], - ['ISO-8859-13', 'windows-1257'], -] as const; - -function family(name: Match['name']) { - return equivalentEncodingFamilies.find((value) => - value.includes(name as never), - ); -} - -function familyPreference(left: Candidate, right: Candidate, c1Bytes: boolean) { - const leftFamily = family(left.name); - if (!leftFamily || leftFamily !== family(right.name)) return 0; - const preferred = - leftFamily[0] === 'ISO-8859-13' || c1Bytes - ? [...leftFamily].reverse() - : [...leftFamily]; - return ( - preferred.indexOf(left.name as never) - - preferred.indexOf(right.name as never) - ); -} - -function ngramHits( - input: Uint8Array, - prepared: PreparedSBCSModel, - hits: Uint32Array, -): number { - hits.fill(0, 0, prepared.languages.length); - const byteMap = prepared.model.byteMap; - let ignoreSpace = false; - let ngram = 0; - let total = 0; - - const record = (value: number) => { - let languageMask = prepared.ngramLanguageMasks.get(value) ?? 0; - while (languageMask !== 0) { - const languageBit = languageMask & -languageMask; - hits[31 - Math.clz32(languageBit)] += 1; - languageMask ^= languageBit; - } - }; - - for (let inputIndex = 0; inputIndex < input.length; inputIndex += 1) { - const byte = input[inputIndex]; - const mapped = byteMap[byte]; - if (mapped !== 0) { - if (!(mapped === 0x20 && ignoreSpace)) { - ngram = ((ngram << 8) + mapped) & N_GRAM_MASK; - total += 1; - record(ngram); - } - ignoreSpace = mapped === 0x20; - } - } - - ngram = ((ngram << 8) + 0x20) & N_GRAM_MASK; - total += 1; - record(ngram); - return total; -} - -function byteLogLikelihood( - highByteCounts: HighByteCounts, - logProbabilities: Float64Array, -) { - let highBytes = 0; - let likelihood = 0; - - for (const [byte, count] of highByteCounts) { - likelihood += logProbabilities[byte - 0x80] * count; - highBytes += count; - } - - return highBytes === 0 ? Number.NEGATIVE_INFINITY : likelihood / highBytes; -} - -function modelByteLogLikelihood( - highByteCounts: HighByteCounts, - prepared: PreparedSBCSModel, -) { - let best = Number.NEGATIVE_INFINITY; - for (const language of prepared.languages) { - best = Math.max( - best, - byteLogLikelihood(highByteCounts, language.highByteLogProbabilities), - ); - } - return best; -} - -function candidate( - input: Uint8Array, - highByteCounts: HighByteCounts, - prepared: PreparedSBCSModel, - hits: Uint32Array, -): Candidate { - const { model, languages: preparedLanguages } = prepared; - const total = ngramHits(input, prepared, hits); - let bestIndex = 0; - let bestConfidence = -1; - let bestByteLogLikelihood = Number.NEGATIVE_INFINITY; - let bestHitRate = 0; - - for (let index = 0; index < preparedLanguages.length; index += 1) { - const hitRate = hits[index] / total; - const confidence = hitRate > 0.33 ? 98 : Math.floor(hitRate * 300); - const likelihood = byteLogLikelihood( - highByteCounts, - preparedLanguages[index].highByteLogProbabilities, - ); - if ( - confidence > bestConfidence || - (confidence === bestConfidence && likelihood > bestByteLogLikelihood) - ) { - bestIndex = index; - bestConfidence = confidence; - bestByteLogLikelihood = likelihood; - bestHitRate = hitRate; - } - } - - return { - name: model.encoding, - lang: preparedLanguages[bestIndex].model.language, - confidence: bestConfidence, - byteLogLikelihood: bestByteLogLikelihood, - hits: hits[bestIndex], - total, - hitRate: bestHitRate, - }; -} - -function statisticallyCompetitive(best: Score, value: Score) { - const variance = - (best.hitRate * (1 - best.hitRate)) / best.total + - (value.hitRate * (1 - value.hitRate)) / value.total; - return best.hitRate - value.hitRate <= 1.96 * Math.sqrt(variance); -} - export function analyseGeneratedSBCS(context: Context): Match[] { - const highByteCounts: [number, number][] = []; - for (let byte = 0x80; byte <= 0xff; byte += 1) { - const count = context.byteStats[byte]; - if (count > 0) highByteCounts.push([byte, count]); - } - const hits = new Uint32Array(maxLanguagesPerModel); - const models = - highByteCounts.length === 0 - ? preparedSBCSModels - : preparedSBCSModels - .map((model, index) => ({ - model, - index, - likelihood: modelByteLogLikelihood(highByteCounts, model), - })) - .sort( - (left, right) => - right.likelihood - left.likelihood || left.index - right.index, - ) - .slice(0, MAX_SBCS_CANDIDATES) - .map(({ model }) => model); - const candidates = models.map((model) => - candidate(context.inputBytes, highByteCounts, model, hits), - ); - candidates.sort((left, right) => right.confidence - left.confidence); - - const strongest = candidates[0]; - const competitive = candidates.filter((value) => - statisticallyCompetitive(strongest, value), - ); - const competitiveNames = new Set(competitive.map((value) => value.name)); - competitive.sort( - (left, right) => - familyPreference(left, right, context.c1Bytes) || - right.byteLogLikelihood - left.byteLogLikelihood || - right.confidence - left.confidence, - ); - const remaining = candidates.filter( - (value) => !competitiveNames.has(value.name), - ); - let confidenceCeiling = 1; - return [...competitive, ...remaining] + return scoreSBCS(context.inputBytes, preparedSBCSModels, context.c1Bytes) .filter((value) => value.confidence > 0) - .map(({ name, lang, confidence }) => { + .map(({ encoding, language, confidence }) => { confidenceCeiling = Math.min(confidenceCeiling, confidence / 100); - return { name, lang, confidence: confidenceCeiling }; + return { + name: encoding, + lang: language, + confidence: confidenceCeiling, + }; }); }