44 lines
1.5 KiB
Python
44 lines
1.5 KiB
Python
"""Debug PyMuPDF table.cells structure"""
|
|
import sys
|
|
from pathlib import Path
|
|
sys.path.insert(0, str(Path(__file__).parent.parent))
|
|
|
|
import fitz
|
|
|
|
pdf_path = Path(__file__).parent.parent.parent / "demo_docs" / "edit3.pdf"
|
|
doc = fitz.open(str(pdf_path))
|
|
page = doc[0]
|
|
|
|
tables = page.find_tables()
|
|
for idx, table in enumerate(tables.tables):
|
|
data = table.extract()
|
|
num_rows = len(data)
|
|
num_cols = max(len(row) for row in data) if data else 0
|
|
|
|
print(f"Table {idx}:")
|
|
print(f" table.extract() dimensions: {num_rows} rows x {num_cols} cols")
|
|
print(f" Expected positions: {num_rows * num_cols}")
|
|
|
|
cell_rects = getattr(table, 'cells', None)
|
|
if cell_rects:
|
|
print(f" table.cells length: {len(cell_rects)}")
|
|
none_count = sum(1 for c in cell_rects if c is None)
|
|
actual_count = sum(1 for c in cell_rects if c is not None)
|
|
print(f" None cells: {none_count}")
|
|
print(f" Actual cells: {actual_count}")
|
|
|
|
# Check if cell_rects matches grid size
|
|
if len(cell_rects) != num_rows * num_cols:
|
|
print(f" WARNING: cell_rects length ({len(cell_rects)}) != grid size ({num_rows * num_cols})")
|
|
|
|
# Show first few cells
|
|
print(f" First 5 cells: {cell_rects[:5]}")
|
|
else:
|
|
print(f" table.cells: NOT AVAILABLE")
|
|
|
|
# Check row_count and col_count
|
|
print(f" table.row_count: {getattr(table, 'row_count', 'N/A')}")
|
|
print(f" table.col_count: {getattr(table, 'col_count', 'N/A')}")
|
|
|
|
doc.close()
|