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

Split Excel file into different chunks (#847)

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


Split Excel into different chunk
### Type of change

- [x] New Feature (non-breaking change which adds functionality)
This commit is contained in:
GYH
2024-05-20 18:35:15 +08:00
committed by GitHub
parent 71068895ae
commit c27c02ea67
3 changed files with 27 additions and 18 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
rag/app/naive.py
View File

@ -134,7 +134,7 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
elif re.search(r"\.xlsx?$", filename, re.IGNORECASE):
callback(0.1, "Start to parse.")
excel_parser = ExcelParser()
sections = [(excel_parser.html(binary), "")]
sections = [(l, "") for l in excel_parser.html(binary) if l]
elif re.search(r"\.(txt|md|py|js|java|c|cpp|h|php|go|ts|sh|cs|kt)$", filename, re.IGNORECASE):
callback(0.1, "Start to parse.")

2
rag/app/one.py
View File

@ -78,7 +78,7 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
elif re.search(r"\.xlsx?$", filename, re.IGNORECASE):
callback(0.1, "Start to parse.")
excel_parser = ExcelParser()
sections = [excel_parser.html(binary)]
sections = excel_parser.html(binary , 10000000)
elif re.search(r"\.txt$", filename, re.IGNORECASE):
callback(0.1, "Start to parse.")