feat(ocr): Add docTR OCR engine with metrics infrastructure

Browse Source

Add docTR as primary OCR engine with 2-tier sequential processing,
OCR metrics tracking, and simplified engine selection.

Features:
- docTR OCR engine with light+medium preprocessing tiers
- doctr_plus mode with early exit optimization (~65% fast path)
- OCR metrics dashboard with per-engine statistics
- User OCR preference persistence
- Parallel worker pool for OCR processing
- Cross-validation for extraction quality

Engine options: tesseract, doctr, doctr_plus (recommended), paddleocr

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

...

This commit is contained in:

Marius Mutu

2026-01-02 05:37:16 +02:00

parent 74f7aefc26

commit 495790411f

75 changed files with 23349 additions and 1311 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

BIN

docs/data-entry/Lidl papetarie 604 fara TVA. nu are cod fiscal.pdf Normal file

Binary file not shown.

BIN

docs/data-entry/benzina 07 aug. 2024.pdf Normal file

Binary file not shown.

BIN

docs/data-entry/benzina 10 mai 2025.pdf Normal file

Binary file not shown.

BIN

docs/data-entry/benzina 13 iulie.pdf Normal file

Binary file not shown.

BIN

docs/data-entry/benzina 13 septembrie .pdf Normal file

Binary file not shown.

BIN

docs/data-entry/benzina 20 dec.pdf Normal file

Binary file not shown.

BIN

docs/data-entry/best print stampila .pdf Normal file

Binary file not shown.

BIN

docs/data-entry/bon fiscal Dedeman - efactura.pdf Normal file

Binary file not shown.

BIN

docs/data-entry/brick consumabil 604 50% deductibil 22 dec.pdf Normal file

Binary file not shown.

BIN

docs/data-entry/brick consumabile 604 22 dec.pdf Normal file

Binary file not shown.

6740

docs/data-entry/brick igiena 1 sept.pdf Normal file

File diff suppressed because it is too large Load Diff

2552

docs/data-entry/brick igiena 604.pdf Normal file

File diff suppressed because it is too large Load Diff

2292

docs/data-entry/brick igiena 8 octombrie 98.95 lei card.pdf Normal file

File diff suppressed because it is too large Load Diff

2610

docs/data-entry/brick igiena, electrice consumabile 604.pdf Normal file

File diff suppressed because it is too large Load Diff

BIN

docs/data-entry/electrobering igiena iulie 604.pdf Normal file

Binary file not shown.

BIN

docs/data-entry/electrobering telecomanda.pdf Normal file

Binary file not shown.

1370

docs/data-entry/factura 70005116259 20.09.2025 Dedeman.pdf Normal file

File diff suppressed because it is too large Load Diff

BIN

docs/data-entry/gama ink refill toner imprimanta 17 sept 2024.pdf Normal file

Binary file not shown.

BIN

docs/data-entry/kineterra abonament terapie august 2024.pdf Normal file

Binary file not shown.

BIN

docs/data-entry/kineterra fizioterapie 9 sept.pdf Normal file

Binary file not shown.

BIN

docs/data-entry/stepout market carti tva 5%.pdf Normal file

Binary file not shown.

BIN

docs/data-entry/unlimited duplicat chei 23 mai.pdf Normal file

Binary file not shown.