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

Refactor section title handling and index validation

Browse source 
Updated section title logging to use secure document text formatting and improved physical index validation logic.
This commit is contained in:
Savio Dsouza 2026-07-02 08:33:17 +05:30 • committed by GitHub
parent abdca8efca
commit 6d75f96fdd
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 16 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

19
pageindex/page_index.py
View file

@ -90,7 +90,7 @@ async def check_title_appearance(item, page_list, start_index=1, model=None):
Note: do fuzzy matching, ignore any space inconsistency in the page_text.
The given section title is {title}.
The given section title is {_secure_doc_text(str(title))}.
The given page_text is:
{_secure_doc_text(page_text)}
@ -120,7 +120,7 @@ async def check_title_appearance_in_start(title, page_text, model=None, logger=N
Note: do fuzzy matching, ignore any space inconsistency in the page_text.
The given section title is {title}.
The given section title is {_secure_doc_text(str(title))}.
The given page_text is:
{_secure_doc_text(page_text)}
@ -755,8 +755,21 @@ 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:
had_index_before = {
i for i, e in enumerate(toc_with_page_number)
if e.get("physical_index") is not None
}
toc_with_page_number = add_page_number_to_toc(group_text, toc_with_page_number, model)
toc_with_page_number = _validate_chunk_physical_indices(toc_with_page_number, group_text)
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")
if raw is None:
continue
m = _PHYSICAL_INDEX_MARKER_RE.match(str(raw).strip())
if not m or int(m.group(1)) not in valid_indices:
entry["physical_index"] = None
logger.info(f'add_page_number_to_toc: {toc_with_page_number}')
toc_with_page_number = convert_physical_index_to_int(toc_with_page_number)