From 6ef6aaa2221340f03c2571a3141c67ca027f5a4f Mon Sep 17 00:00:00 2001
From: jvoisin <julien.voisin@dustri.org>
Date: Fri, 8 Feb 2019 23:23:56 +0100
Subject: [PATCH] Improve a bit get_meta for libreoffice files
---
libmat2/office.py | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/libmat2/office.py b/libmat2/office.py
index 0c9caa8..f3a5b22 100644
--- a/libmat2/office.py
+++ b/libmat2/office.py
@@ -384,7 +384,7 @@ class LibreOfficeParser(ArchiveBasedAbstractParser):
return {}
with open(full_path, encoding='utf-8') as f:
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}
except (TypeError, UnicodeDecodeError): # We didn't manage to parse the xml file
# We didn't manage to parse the xml file
--
GitLab