security-and-privacy/mat2
security-and-privacy/mat2
1
0
Fork 0
mirror of synced 2024-11-22 09:14:23 +01:00
Code Releases Activity

Improve a bit get_meta for libreoffice files

Browse Source
This commit is contained in:
jvoisin 2019-02-08 23:23:56 +01:00
parent 6cc034e81b
commit 6ef6aaa222
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
libmat2/office.py
View File

@ -384,7 +384,7 @@ class LibreOfficeParser(ArchiveBasedAbstractParser):
return {} return {}
with open(full_path, encoding='utf-8') as f: with open(full_path, encoding='utf-8') as f:
try: try:
results = re.findall(r"<((?:meta|dc|cp).+?)>(.+)</\1>", f.read(), re.I|re.M) results = re.findall(r"<((?:meta|dc|cp).+?)[^>]*>(.+)</\1>", f.read(), re.I|re.M)
return {k:v for (k, v) in results} return {k:v for (k, v) in results}
except (TypeError, UnicodeDecodeError): # We didn't manage to parse the xml file except (TypeError, UnicodeDecodeError): # We didn't manage to parse the xml file
# We didn't manage to parse the xml file # We didn't manage to parse the xml file