ilia
2c28a623fb
- ocr/: Tesseract-based vendor/date/total extraction. PSM 6 (single uniform text block) instead of the default fixes receipts where item-name/price columns were otherwise split into separate blocks and dropped. Vendor line picked by median (not max) word height within the top fraction of the crop, breaking ties by topmost line - max() was fooled by single descender/ascender glyphs (commas, parens) inflating one word's bounding box. - naming/: merge OCR metadata into YYYY-MM-DD_vendor.pdf filenames, degrading gracefully to UNSORTED_<timestamp>.pdf; per-run dedup. - pdf/: img2pdf-based multi-page-capable assembly (images_to_pdf). - pipeline.run_export(): OCR + name + PDF each detected crop from a detect() report, writes pdf/ and export_summary.csv. - New `paperpod export <video>` CLI command. - Verified against synthetic Home Depot/Metro/Petro-Canada receipts: 3/3 correct vendor, date, and total after tuning. Known limitation (documented in README): no page-flip/multi-page grouping yet (that's events/, still unbuilt) - every detected document becomes its own single-page PDF.
52 lines
1.3 KiB
Python
52 lines
1.3 KiB
Python
"""End-to-end OCR tests against the synthetic receipt renderer.
|
|
|
|
Skipped automatically if the tesseract binary isn't installed.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import shutil
|
|
import sys
|
|
from pathlib import Path
|
|
|
|
import pytest
|
|
|
|
pytestmark = pytest.mark.skipif(
|
|
shutil.which("tesseract") is None, reason="tesseract binary not installed"
|
|
)
|
|
|
|
sys.path.insert(0, str(Path(__file__).parent.parent / "sample_data"))
|
|
|
|
|
|
def _receipt_image(index: int):
|
|
from make_receipt_video import RECEIPTS, make_receipt_image
|
|
|
|
return make_receipt_image(RECEIPTS[index])
|
|
|
|
|
|
def test_home_depot_receipt_fields():
|
|
from paperpod.ocr.extract import run_ocr
|
|
|
|
result = run_ocr(_receipt_image(0))
|
|
assert result.date == "2023-03-14"
|
|
assert result.total == "81.52"
|
|
assert "HOME DEPOT" in (result.vendor or "")
|
|
|
|
|
|
def test_metro_receipt_fields():
|
|
from paperpod.ocr.extract import run_ocr
|
|
|
|
result = run_ocr(_receipt_image(1))
|
|
assert result.date == "2023-06-02"
|
|
assert result.total == "30.63"
|
|
assert "METRO" in (result.vendor or "")
|
|
|
|
|
|
def test_petro_canada_receipt_fields():
|
|
from paperpod.ocr.extract import run_ocr
|
|
|
|
result = run_ocr(_receipt_image(2))
|
|
assert result.date == "2023-08-19"
|
|
assert result.total == "65.10"
|
|
assert "PETRO" in (result.vendor or "")
|