Benjamin_Boenisch/breakpilot-lehrer
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix(ocr-pipeline): exclude header/footer/page_ref from cell grid columns

Browse Source 
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
Benjamin Admin
2026-03-01 17:33:48 +01:00
parent 27b895a848
commit a666e883da
1 changed files with 3 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
klausur-service/backend/cv_vocab_pipeline.py
View File

@@ -3057,8 +3057,9 @@ def build_cell_grid(
logger.warning("build_cell_grid: no content rows found") logger.warning("build_cell_grid: no content rows found")
return [], [] return [], []
# Use all columns except column_ignore # Use columns only — skip ignore, header, footer, page_ref
relevant_cols = [c for c in column_regions if c.type != 'column_ignore'] _skip_types = {'column_ignore', 'header', 'footer', 'page_ref'}
relevant_cols = [c for c in column_regions if c.type not in _skip_types]
if not relevant_cols: if not relevant_cols:
logger.warning("build_cell_grid: no usable columns found") logger.warning("build_cell_grid: no usable columns found")
return [], [] return [], []