From 0b094b594bd1db017ed3d063a10714f6b2a7b9f3 Mon Sep 17 00:00:00 2001
From: jvoisin <julien.voisin@dustri.org>
Date: Wed, 14 Jul 2021 23:34:02 +0200
Subject: [PATCH] Improve xlsx support
This should close #156
---
libmat2/office.py | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/libmat2/office.py b/libmat2/office.py
index 19e2ce5..f77c0f5 100644
--- a/libmat2/office.py
+++ b/libmat2/office.py
@@ -88,6 +88,7 @@ class MSOfficeParser(ZipParser):
r'^\[Content_Types\]\.xml$',
r'^_rels/\.rels$',
r'^xl/sharedStrings\.xml$', # https://docs.microsoft.com/en-us/office/open-xml/working-with-the-shared-string-table
+ r'^xl/calcChain\.xml$',
r'^(?:word|ppt|xl)/_rels/document\.xml\.rels$',
r'^(?:word|ppt|xl)/_rels/footer[0-9]*\.xml\.rels$',
r'^(?:word|ppt|xl)/_rels/header[0-9]*\.xml\.rels$',
@@ -108,6 +109,8 @@ class MSOfficeParser(ZipParser):
r'^ppt/slideMasters/slideMaster[0-9]+\.xml',
r'^ppt/slideMasters/_rels/slideMaster[0-9]+\.xml\.rels',
r'^xl/worksheets/_rels/sheet[0-9]+\.xml\.rels',
+ r'^xl/drawings/vmlDrawing[0-9]+\.vml',
+ r'^xl/drawings/drawing[0-9]+\.xml',
}))
self.files_to_omit = set(map(re.compile, { # type: ignore
r'^\[trash\]/',
@@ -124,6 +127,7 @@ class MSOfficeParser(ZipParser):
# Additional presentation-wide properties like printing properties,
# presentation show properties etc.
r'^(?:word|ppt|xl)/presProps\.xml$',
+ r'^(?:word|ppt|xl)/comments[0-9]+\.xml$',
# we have an allowlist in self.files_to_keep,
# so we can trash everything else
--
GitLab