pengjunjie/ragflow
1
0
Fork 1
mirror of https://github.com/infiniflow/ragflow.git synced 2025-12-24 07:26:47 +08:00
Code Issues Packages Projects Releases Wiki Activity

Fix: Tika server upgrades. (#12073)

Browse Source 
### What problem does this PR solve?

#12037

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
This commit is contained in:
Kevin Hu
2025-12-23 09:35:52 +08:00
committed by GitHub
parent a95f22fa88
commit bd76b8ff1a
10 changed files with 52 additions and 19 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
rag/app/book.py
View File

@ -91,7 +91,7 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
filename, binary=binary, from_page=from_page, to_page=to_page)
remove_contents_table(sections, eng=is_english(
random_choices([t for t, _ in sections], k=200)))
tbls=vision_figure_parser_docx_wrapper(sections=sections,tbls=tbls,callback=callback,**kwargs)
tbls = vision_figure_parser_docx_wrapper(sections=sections,tbls=tbls,callback=callback,**kwargs)
# tbls = [((None, lns), None) for lns in tbls]
sections=[(item[0],item[1] if item[1] is not None else "") for item in sections if not isinstance(item[1], Image.Image)]
callback(0.8, "Finish parsing.")
@ -147,9 +147,16 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
elif re.search(r"\.doc$", filename, re.IGNORECASE):
callback(0.1, "Start to parse.")
with BytesIO(binary) as binary:
binary = BytesIO(binary)
doc_parsed = parser.from_buffer(binary)
try:
from tika import parser as tika_parser
except Exception as e:
callback(0.8, f"tika not available: {e}. Unsupported .doc parsing.")
logging.warning(f"tika not available: {e}. Unsupported .doc parsing for {filename}.")
return []
binary = BytesIO(binary)
doc_parsed = tika_parser.from_buffer(binary)
if doc_parsed.get('content', None) is not None:
sections = doc_parsed['content'].split('\n')
sections = [(line, "") for line in sections if line]
remove_contents_table(sections, eng=is_english(