apunkt/PageIndex
1
0
Fork 0
mirror of https://github.com/VectifyAI/PageIndex.git synced 2026-07-24 21:41:04 +02:00
Code Issues Projects Releases Packages Wiki Activity

Preserve prior physical index values in TOC

Browse source 
Store prior physical index values to restore them later.
This commit is contained in:
Savio Dsouza 2026-07-05 16:33:54 +05:30 • committed by GitHub
parent 6d75f96fdd
commit 94a882b394
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 7 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

9
pageindex/page_index.py
View file

@ -755,6 +755,10 @@ def process_toc_no_page_numbers(toc_content, toc_page_list, page_list, start_in
toc_with_page_number=copy.deepcopy(toc_content)
for group_text in group_texts:
prior_values = {
i: e.get("physical_index")
for i, e in enumerate(toc_with_page_number)
}
had_index_before = {
i for i, e in enumerate(toc_with_page_number)
if e.get("physical_index") is not None
@ -763,8 +767,9 @@ def process_toc_no_page_numbers(toc_content, toc_page_list, page_list, start_in
valid_indices = _extract_chunk_marker_set(group_text)
for i, entry in enumerate(toc_with_page_number):
if i in had_index_before:
continue
raw = entry.get("physical_index")
entry["physical_index"] = prior_values[i]
else:
raw = entry.get("physical_index")
if raw is None:
continue
m = _PHYSICAL_INDEX_MARKER_RE.match(str(raw).strip())