pengjunjie/ragflow
1
0
Fork 1
mirror of https://github.com/infiniflow/ragflow.git synced 2025-12-08 20:42:30 +08:00
Code Issues Packages Projects Releases Wiki Activity

Fix: chunk method error. (#11807)

Browse Source 
### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
This commit is contained in:
Kevin Hu
2025-12-08 14:28:23 +08:00
committed by GitHub
parent 43f51baa96
commit 09a3854ed8
2 changed files with 18 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
deepdoc/parser/excel_parser.py
View File

@ -41,7 +41,7 @@ class RAGFlowExcelParser:
try:
file_like_object.seek(0)
df = pd.read_csv(file_like_object)
df = pd.read_csv(file_like_object, on_bad_lines='skip')
return RAGFlowExcelParser._dataframe_to_workbook(df)
except Exception as e_csv:
@ -164,7 +164,7 @@ class RAGFlowExcelParser:
except Exception as e:
logging.warning(f"Parse spreadsheet error: {e}, trying to interpret as CSV file")
file_like_object.seek(0)
df = pd.read_csv(file_like_object)
df = pd.read_csv(file_like_object, on_bad_lines='skip')
df = df.replace(r"^\s*$", "", regex=True)
return df.to_markdown(index=False)

21
rag/app/laws.py
View File

@ -201,12 +201,23 @@ 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.")
binary = BytesIO(binary)
doc_parsed = parser.from_buffer(binary)
sections = doc_parsed['content'].split('\n')
sections = [s for s in sections if s]
callback(0.8, "Finish parsing.")
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 = [s for s in sections if s]
callback(0.8, "Finish parsing.")
else:
callback(0.8, f"tika.parser got empty content from {filename}.")
logging.warning(f"tika.parser got empty content from {filename}.")
return []
else:
raise NotImplementedError(
"file type not supported yet(doc, docx, pdf, txt supported)")