egg/OCR
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

test: add covering images to preprocessing test output

Browse Source 
Updates test script to display covering images count in quality report.

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

Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
egg
2025-12-04 07:43:19 +08:00
parent d6387adbd1
commit 1c3c37bce0
1 changed files with 2 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
scripts/run_preprocessing_tests.py
View File

@@ -65,7 +65,8 @@ def test_preprocessing_pipeline():
print(f"\n[Quality Report]")
print(f" Total pages: {report['total_pages']}")
print(f" Pages sanitized: {report['preprocessing_stats']['pages_sanitized']}")
print(f" Whiteout regions detected: {report['preprocessing_stats']['total_whiteout_regions']}")
print(f" Whiteout regions (vector): {report['preprocessing_stats']['total_whiteout_regions']}")
print(f" Covering images (black/white): {report['preprocessing_stats'].get('total_covering_images', 0)}")
print(f" Average garble rate: {report['average_garble_rate']:.2%}")
print(f" Needs OCR fallback: {report['needs_ocr_fallback']}")