AI/ragflow
1
0
Fork 0
mirror of https://git.mirrors.martin98.com/https://github.com/infiniflow/ragflow.git synced 2025-08-12 19:39:00 +08:00
Code Issues Packages Projects Releases Wiki Activity

remove doc from supported processing types (#488)

Browse Source 
### What problem does this PR solve?
#474 

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
This commit is contained in:
KevinHuSh 2024-04-22 15:46:09 +08:00 committed by GitHub
parent 3610e1e5b4
commit a38e163035
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
4 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
rag/app/book.py
View File

@ -67,7 +67,7 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
doc["title_sm_tks"] = huqie.qieqie(doc["title_tks"]) doc["title_sm_tks"] = huqie.qieqie(doc["title_tks"])
pdf_parser = None pdf_parser = None
sections, tbls = [], [] sections, tbls = [], []
if re.search(r"\.docx?$", filename, re.IGNORECASE): if re.search(r"\.docx$", filename, re.IGNORECASE):
callback(0.1, "Start to parse.") callback(0.1, "Start to parse.")
doc_parser = DocxParser() doc_parser = DocxParser()
# TODO: table of contents need to be removed # TODO: table of contents need to be removed

2
rag/app/laws.py
View File

@ -93,7 +93,7 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
doc["title_sm_tks"] = huqie.qieqie(doc["title_tks"]) doc["title_sm_tks"] = huqie.qieqie(doc["title_tks"])
pdf_parser = None pdf_parser = None
sections = [] sections = []
if re.search(r"\.docx?$", filename, re.IGNORECASE): if re.search(r"\.docx$", filename, re.IGNORECASE):
callback(0.1, "Start to parse.") callback(0.1, "Start to parse.")
for txt in Docx()(filename, binary): for txt in Docx()(filename, binary):
sections.append(txt) sections.append(txt)

2
rag/app/naive.py
View File

@ -119,7 +119,7 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
res = [] res = []
pdf_parser = None pdf_parser = None
sections = [] sections = []
if re.search(r"\.docx?$", filename, re.IGNORECASE): if re.search(r"\.docx$", filename, re.IGNORECASE):
callback(0.1, "Start to parse.") callback(0.1, "Start to parse.")
sections, tbls = Docx()(filename, binary) sections, tbls = Docx()(filename, binary)
res = tokenize_table(tbls, doc, eng) res = tokenize_table(tbls, doc, eng)

2
rag/app/one.py
View File

@ -60,7 +60,7 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
eng = lang.lower() == "english" # is_english(cks) eng = lang.lower() == "english" # is_english(cks)
if re.search(r"\.docx?$", filename, re.IGNORECASE): if re.search(r"\.docx$", filename, re.IGNORECASE):
callback(0.1, "Start to parse.") callback(0.1, "Start to parse.")
sections = [txt for txt in laws.Docx()(filename, binary) if txt] sections = [txt for txt in laws.Docx()(filename, binary) if txt]
callback(0.8, "Finish parsing.") callback(0.8, "Finish parsing.")