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 errors detected by Ruff (#3918)

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

Fix errors detected by Ruff

### Type of change

- [x] Refactoring
This commit is contained in:
Zhichang Yu
2024-12-08 14:21:12 +08:00
committed by GitHub
parent e267a026f3
commit 0d68a6cd1b
97 changed files with 2558 additions and 1976 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
rag/app/book.py
View File

@ -94,7 +94,7 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
callback(0.1, "Start to parse.")
txt = get_text(filename, binary)
sections = txt.split("\n")
sections = [(l, "") for l in sections if l]
sections = [(line, "") for line in sections if line]
remove_contents_table(sections, eng=is_english(
random_choices([t for t, _ in sections], k=200)))
callback(0.8, "Finish parsing.")
@ -102,7 +102,7 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
elif re.search(r"\.(htm|html)$", filename, re.IGNORECASE):
callback(0.1, "Start to parse.")
sections = HtmlParser()(filename, binary)
sections = [(l, "") for l in sections if l]
sections = [(line, "") for line in sections if line]
remove_contents_table(sections, eng=is_english(
random_choices([t for t, _ in sections], k=200)))
callback(0.8, "Finish parsing.")
@ -112,7 +112,7 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
binary = BytesIO(binary)
doc_parsed = parser.from_buffer(binary)
sections = doc_parsed['content'].split('\n')
sections = [(l, "") for l in sections if l]
sections = [(line, "") for line in sections if line]
remove_contents_table(sections, eng=is_english(
random_choices([t for t, _ in sections], k=200)))
callback(0.8, "Finish parsing.")