apunkt/PageIndex
1
0
Fork 0
mirror of https://github.com/VectifyAI/PageIndex.git synced 2026-06-24 20:28:12 +02:00
Code Issues Projects Releases Packages Wiki Activity

Move pdf_parser off doc dict, pass via call args

Browse source
This commit is contained in:
Ray 2026-05-11 16:40:32 +08:00
parent ec1aaca4c9
commit 108cb28518
2 changed files with 5 additions and 9 deletions
Download patch file Download diff file Expand all files Collapse all files

5
pageindex/client.py
View file

@ -88,7 +88,6 @@ class PageIndexClient:
'doc_name': result.get('doc_name', ''), 'doc_name': result.get('doc_name', ''),
'doc_description': result.get('doc_description', ''), 'doc_description': result.get('doc_description', ''),
'page_count': len(pages), 'page_count': len(pages),
'pdf_parser': self.pdf_parser,
'structure': result['structure'], 'structure': result['structure'],
'pages': pages, 'pages': pages,
} }
@ -139,8 +138,6 @@ class PageIndexClient:
} }
if doc.get('type') == 'pdf': if doc.get('type') == 'pdf':
entry['page_count'] = doc.get('page_count') entry['page_count'] = doc.get('page_count')
if doc.get('pdf_parser'):
entry['pdf_parser'] = doc['pdf_parser']
elif doc.get('type') == 'md': elif doc.get('type') == 'md':
entry['line_count'] = doc.get('line_count') entry['line_count'] = doc.get('line_count')
return entry return entry
@ -232,4 +229,4 @@ class PageIndexClient:
"""Return page content for the given pages string (e.g. '5-7', '3,8', '12').""" """Return page content for the given pages string (e.g. '5-7', '3,8', '12')."""
if self.workspace: if self.workspace:
self._ensure_doc_loaded(doc_id) self._ensure_doc_loaded(doc_id)
return get_page_content(self.documents, doc_id, pages) return get_page_content(self.documents, doc_id, pages, pdf_parser=self.pdf_parser)

9
pageindex/retrieve.py
View file

@ -32,7 +32,7 @@ def _count_pages(doc_info: dict) -> int:
return get_number_of_pages(doc_info['path']) return get_number_of_pages(doc_info['path'])
def _get_pdf_page_content(doc_info: dict, page_nums: list[int]) -> list[dict]: def _get_pdf_page_content(doc_info: dict, page_nums: list[int], pdf_parser: str = DEFAULT_PDF_PARSER) -> list[dict]:
"""Extract text for specific PDF pages (1-indexed). Prefer cached pages, fallback to PDF.""" """Extract text for specific PDF pages (1-indexed). Prefer cached pages, fallback to PDF."""
cached_pages = doc_info.get('pages') cached_pages = doc_info.get('pages')
if cached_pages: if cached_pages:
@ -41,8 +41,7 @@ def _get_pdf_page_content(doc_info: dict, page_nums: list[int]) -> list[dict]:
{'page': p, 'content': page_map[p]} {'page': p, 'content': page_map[p]}
for p in page_nums if p in page_map for p in page_nums if p in page_map
] ]
parser = doc_info.get('pdf_parser') or DEFAULT_PDF_PARSER all_pages = read_pdf_pages(doc_info['path'], pdf_parser=pdf_parser)
all_pages = read_pdf_pages(doc_info['path'], pdf_parser=parser)
total = len(all_pages) total = len(all_pages)
valid_pages = [p for p in page_nums if 1 <= p <= total] valid_pages = [p for p in page_nums if 1 <= p <= total]
return [ return [
@ -105,7 +104,7 @@ def get_document_structure(documents: dict, doc_id: str) -> str:
return json.dumps(structure_no_text, ensure_ascii=False) return json.dumps(structure_no_text, ensure_ascii=False)
def get_page_content(documents: dict, doc_id: str, pages: str) -> str: def get_page_content(documents: dict, doc_id: str, pages: str, pdf_parser: str = DEFAULT_PDF_PARSER) -> str:
""" """
Retrieve page content for a document. Retrieve page content for a document.
@ -126,7 +125,7 @@ def get_page_content(documents: dict, doc_id: str, pages: str) -> str:
try: try:
if doc_info.get('type') == 'pdf': if doc_info.get('type') == 'pdf':
content = _get_pdf_page_content(doc_info, page_nums) content = _get_pdf_page_content(doc_info, page_nums, pdf_parser=pdf_parser)
else: else:
content = _get_md_page_content(doc_info, page_nums) content = _get_md_page_content(doc_info, page_nums)
except Exception as e: except Exception as e: