raiot
/
KeywordRetriever
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Compare commits

base: raiot:e5deab6fa2433d10958f88feb27e6b4b12f6479a
Branches Tags
raiot:master
raiot:main
..
compare: raiot:1ddb4e83ddb5c9121460f7ce5d0734831a0fe874
Branches Tags
raiot:master
raiot:main

No commits in common. "e5deab6fa2433d10958f88feb27e6b4b12f6479a" and "1ddb4e83ddb5c9121460f7ce5d0734831a0fe874" have entirely different histories.
e5deab6fa2 ... 1ddb4e83dd

2 changed files with 1 additions and 2 deletions
Show Stats Expand all files Collapse all files

2
retriever/forms.py
View File

@ -12,4 +12,4 @@ class SpaceSeparatedField(forms.CharField):
class UploadForm(forms.Form): class UploadForm(forms.Form):
attachments = MultiFileField(min_num=1, max_num=10, max_file_size=1024 * 1024 * 64, attachments = MultiFileField(min_num=1, max_num=10, max_file_size=1024 * 1024 * 64,
attrs={'class': 'file-input is-primary', 'accept': '.docx, .doc, .dot, .pptx, .ppt, .pdf, .xls'}) attrs={'class': 'file-input is-primary'})

1
retriever/tools/keyword_find.py
View File

@ -29,7 +29,6 @@ def docx_find(file_path: str, keyword_list: list) -> dict:
paragraph_keyword = [] paragraph_keyword = []
for para in doc_text.split('\n'): for para in doc_text.split('\n'):
para = re.sub(r'\s+', '', para) # 删除段落中空格
this_para_keyword = [keyword for keyword in keyword_list if keyword in para] # 查找该段落中的敏感词 this_para_keyword = [keyword for keyword in keyword_list if keyword in para] # 查找该段落中的敏感词
if this_para_keyword: if this_para_keyword: