mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-07-26 20:14:47 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fixes for cell indexing

Browse Source 
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
This commit is contained in:
Christoph Auer 2025-07-25 11:55:48 +02:00
parent 7bc1c1ac3d
commit 7c3f9b7ab1
1 changed files with 18 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
docling/backend/mets_gbs_backend.py
View File

@ -326,7 +326,9 @@ class MetsGbsDocumentBackend(PaginatedDocumentBackend):
im = im.convert("RGB")
# Extract all ocrx_word spans
for word in ocr_root.xpath("//x:span[@class='ocrx_word']", namespaces=ns):
for ix, word in enumerate(
ocr_root.xpath("//x:span[@class='ocrx_word']", namespaces=ns)
):
text = "".join(word.itertext()).strip()
title = word.attrib.get("title", "")
rect = _extract_rect(title)
@ -334,13 +336,20 @@ class MetsGbsDocumentBackend(PaginatedDocumentBackend):
if rect:
word_cells.append(
TextCell(
text=text, orig=text, rect=rect, from_ocr=True, confidence=conf
index=ix,
text=text,
orig=text,
rect=rect,
from_ocr=True,
confidence=conf,
)
)
# Extract all ocr_line spans
# line: etree._Element
for line in ocr_root.xpath("//x:span[@class='ocr_line']", namespaces=ns):
for ix, line in enumerate(
ocr_root.xpath("//x:span[@class='ocr_line']", namespaces=ns)
):
text = "".join(line.itertext()).strip()
title = line.attrib.get("title", "")
rect = _extract_rect(title)
@ -348,7 +357,12 @@ class MetsGbsDocumentBackend(PaginatedDocumentBackend):
if rect:
line_cells.append(
TextCell(
text=text, orig=text, rect=rect, from_ocr=True, confidence=conf
index=ix,
text=text,
orig=text,
rect=rect,
from_ocr=True,
confidence=conf,
)
)