docling-project/docling-parse
1
0
Fork 0
mirror of https://github.com/docling-project/docling-parse.git synced 2026-05-17 13:10:49 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: Build lines from word level cells

Browse Source 
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
This commit is contained in:
Christoph Auer
2025-03-25 10:58:55 +01:00
parent 514b6fe83d
commit 8076e30969
1 changed files with 4 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docling_parse/pdf_parser.py
+4 -1
View File
@@ -367,10 +367,13 @@ class PdfDocument:
if len(segmented_page.textline_cells) > 0:
return
self._create_word_cells(segmented_page, _loglevel)
sanitizer = pdf_sanitizer(level=_loglevel)
char_data = []
for item in segmented_page.char_cells:
# Note: We build the lines from the word level cells.
for item in segmented_page.word_cells:
item_dict = item.model_dump(mode="json", by_alias=True, exclude_none=True)
# TODO changing representation for the C++ parser, need to update on C++ code.