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 TOC entry update logic in page_index.py

Browse source
This commit is contained in:
Savio Dsouza 2026-07-15 19:18:09 +05:30 • committed by GitHub
parent 9470b63960
commit 9bcc7cff89
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 6 additions and 12 deletions
Download patch file Download diff file Expand all files Collapse all files

18
pageindex/page_index.py
View file

@ -755,22 +755,17 @@ 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:
current_entries = {
entry["structure"]: entry
for entry in toc_with_page_number
}
llm_result = add_page_number_to_toc(group_text, toc_with_page_number, model)
if len(llm_result) != len(toc_with_page_number):
raise ValueError(
"LLM returned a different number of TOC entries than expected."
)
valid_indices = _extract_chunk_marker_set(group_text)
for update in llm_result:
key = update.get("structure")
for idx, current in enumerate(toc_with_page_number):
update = llm_result[idx]
if key not in current_entries:
continue
current = current_entries[key]
if current.get("physical_index") is not None:
continue
@ -785,7 +780,6 @@ def process_toc_no_page_numbers(toc_content, toc_page_list, page_list, start_in
continue
current["physical_index"] = raw
toc_with_page_number = list(current_entries.values())
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)