Skip to content
This repository was archived by the owner on Jun 30, 2025. It is now read-only.
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
10 changes: 5 additions & 5 deletions src/config.ts
Original file line number Diff line number Diff line change
@@ -1,20 +1,20 @@
import type { ExtractorConfig, PartialExtractorConfig } from './types';
import { languages as tesseractLanguages } from 'tesseract.js';

const languages = Object.values(tesseractLanguages);
export const ocrLanguages = Object.values(tesseractLanguages);

export function parseConfig({ rawConfig = {} }: { rawConfig?: PartialExtractorConfig } = {}): { config: ExtractorConfig } {
const ocrLanguages = rawConfig.tesseract?.languages ?? [];
const invalidLanguages = ocrLanguages.filter(language => !languages.includes(language));
const languages = rawConfig.tesseract?.languages ?? [];
const invalidLanguages = languages.filter(language => !ocrLanguages.includes(language));

if (invalidLanguages.length > 0) {
throw new Error(`Invalid languages for tesseract: ${invalidLanguages.join(', ')}. Valid languages are: ${languages.join(', ')}`);
throw new Error(`Invalid languages for tesseract: ${invalidLanguages.join(', ')}. Valid languages are: ${ocrLanguages.join(', ')}`);
}

return {
config: {
tesseract: {
languages: ocrLanguages.length > 0 ? ocrLanguages : ['eng'],
languages: languages.length > 0 ? languages : ['eng'],
},
},
};
Expand Down
2 changes: 2 additions & 0 deletions src/index.ts
Original file line number Diff line number Diff line change
@@ -1,3 +1,5 @@
export { ocrLanguages } from './config';

export {
extractText,
extractTextFromBlob,
Expand Down