Skip to content

armgit / papra

Public Imported from GitHub
0

The minimalistic document archiving platform.

feat(lecture): added global pdf ocr log (#630)

Corentin Thomasset1d20c0cfe39d
diff --git a/packages/lecture/src/extractors/pdf.extractor.ts b/packages/lecture/src/extractors/pdf.extractor.ts
index f55e2a0f..17b09cc9 100644
--- a/packages/lecture/src/extractors/pdf.extractor.ts
+++ b/packages/lecture/src/extractors/pdf.extractor.ts
@@ -23,6 +23,7 @@ export const pdfExtractorDefinition = defineTextExtractor({
const { extract, extractorType } = await createTesseractExtractor(config.tesseract);
const imageTexts = [];
+ const startOcrTime = Date.now();
for (let pageIndex = 1; pageIndex <= pageCount; pageIndex++) {
const images = await extractImages(pdf, pageIndex);
@@ -53,6 +54,10 @@ export const pdfExtractorDefinition = defineTextExtractor({
}
}
+ const totalOcrDuration = Date.now() - startOcrTime;
+
+ logger?.info({ pageCount, imagesProcessedCount: imageTexts.length, durationMs: totalOcrDuration }, 'Completed OCR on PDF images.');
+
return {
content: imageTexts.join('\n'),
subExtractorsUsed: [extractorType],