Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
17 changes: 15 additions & 2 deletions .github/workflows/test-build.js
Original file line number Diff line number Diff line change
Expand Up @@ -9,8 +9,21 @@ assert(typeof chardet.detectFileSync, 'function');

assert.deepStrictEqual(chardet.analyse(Buffer.from('This is a test')), [
{ confidence: 1, name: 'ASCII', lang: undefined },
{ confidence: 0.98, name: 'ISO-8859-1', lang: 'en' },
{ confidence: 0.98, name: 'ISO-8859-2', lang: 'hu' },
{ name: 'ISO-8859-2', lang: 'hu', confidence: 0.6 },
{ name: 'windows-1250', lang: 'hu', confidence: 0.6 },
{ name: 'ISO-8859-1', lang: 'en', confidence: 0.4 },
{ name: 'windows-1252', lang: 'en', confidence: 0.4 },
{ name: 'ISO-8859-10', lang: 'is', confidence: 0.4 },
{ name: 'windows-1257', lang: 'lv', confidence: 0.2 },
{ name: 'macintosh', lang: 'de', confidence: 0.2 },
{ name: 'ISO-8859-3', lang: 'mt', confidence: 0.2 },
{ name: 'ISO-8859-4', lang: 'lv', confidence: 0.2 },
{ name: 'ISO-8859-13', lang: 'lt', confidence: 0.2 },
{ name: 'ISO-8859-14', lang: 'cy', confidence: 0.2 },
{ name: 'ISO-8859-15', lang: 'de', confidence: 0.2 },
{ name: 'ISO-8859-16', lang: 'ro', confidence: 0.2 },
{ name: 'CP850', lang: 'de', confidence: 0.2 },
{ name: 'CP852', lang: 'pl', confidence: 0.2 },
{ confidence: 0.1, name: 'UTF-8', lang: undefined },
{ confidence: 0.1, name: 'Shift_JIS', lang: 'ja' },
{ confidence: 0.1, name: 'Big5', lang: 'zh' },
Expand Down
17 changes: 15 additions & 2 deletions .github/workflows/test-build.ts
Original file line number Diff line number Diff line change
Expand Up @@ -12,8 +12,21 @@ const main = async () => {

assert.deepStrictEqual(chardet.analyse(Buffer.from('This is a test')), [
{ confidence: 1, name: 'ASCII', lang: undefined },
{ confidence: 0.98, name: 'ISO-8859-1', lang: 'en' },
{ confidence: 0.98, name: 'ISO-8859-2', lang: 'hu' },
{ name: 'ISO-8859-2', lang: 'hu', confidence: 0.6 },
{ name: 'windows-1250', lang: 'hu', confidence: 0.6 },
{ name: 'ISO-8859-1', lang: 'en', confidence: 0.4 },
{ name: 'windows-1252', lang: 'en', confidence: 0.4 },
{ name: 'ISO-8859-10', lang: 'is', confidence: 0.4 },
{ name: 'windows-1257', lang: 'lv', confidence: 0.2 },
{ name: 'macintosh', lang: 'de', confidence: 0.2 },
{ name: 'ISO-8859-3', lang: 'mt', confidence: 0.2 },
{ name: 'ISO-8859-4', lang: 'lv', confidence: 0.2 },
{ name: 'ISO-8859-13', lang: 'lt', confidence: 0.2 },
{ name: 'ISO-8859-14', lang: 'cy', confidence: 0.2 },
{ name: 'ISO-8859-15', lang: 'de', confidence: 0.2 },
{ name: 'ISO-8859-16', lang: 'ro', confidence: 0.2 },
{ name: 'CP850', lang: 'de', confidence: 0.2 },
{ name: 'CP852', lang: 'pl', confidence: 0.2 },
{ confidence: 0.1, name: 'UTF-8', lang: undefined },
{ confidence: 0.1, name: 'Shift_JIS', lang: 'ja' },
{ confidence: 0.1, name: 'Big5', lang: 'zh' },
Expand Down
18 changes: 18 additions & 0 deletions src/encoding/models/types.ts
Original file line number Diff line number Diff line change
@@ -0,0 +1,18 @@
import type { EncodingName } from '../../match';

export interface HighByteDistribution {
readonly total: number;
readonly counts: readonly (readonly [number, number])[];
}

export interface GeneratedSBCSLanguage {
readonly language: string;
readonly ngrams: readonly number[];
readonly highBytes: HighByteDistribution;
}

export interface GeneratedSBCSModel {
readonly encoding: EncodingName;
readonly byteMap: readonly number[];
readonly languages: readonly GeneratedSBCSLanguage[];
}
8 changes: 8 additions & 0 deletions src/encoding/sbcs.test.ts
Original file line number Diff line number Diff line change
Expand Up @@ -18,6 +18,14 @@ describe('Singlebyte Character Sets', () => {
expect(detect('iso88591_en')).toBe('ISO-8859-1');
});

it('should retain a weak ISO-8859-1 candidate after byte prefiltering', () => {
const fixture = path.join(
__dirname,
'../../corpus/generated/ISO-8859-1/es/validation/river-trip.bin',
);
expect(chardet.detectFileSync(fixture)).toBe('ISO-8859-1');
});

it('should return ISO-8859-2 (Czech)', () => {
expect(detect('iso88592_cs')).toBe('ISO-8859-2');
});
Expand Down
Loading