From d00ca800b2d4ba7f72db7c77cefe8da43e42f735 Mon Sep 17 00:00:00 2001
From: jvoisin <julien.voisin@dustri.org>
Date: Sun, 14 Mar 2021 14:41:40 +0100
Subject: [PATCH] Keep sharedStrings.xml when processing MSOffice sheets

---
 libmat2/office.py | 1 +
 1 file changed, 1 insertion(+)

diff --git a/libmat2/office.py b/libmat2/office.py
index 7e8c60c..4cd9da2 100644
--- a/libmat2/office.py
+++ b/libmat2/office.py
@@ -87,6 +87,7 @@ class MSOfficeParser(ZipParser):
         self.files_to_keep = set(map(re.compile, {  # type: ignore
             r'^\[Content_Types\]\.xml$',
             r'^_rels/\.rels$',
+            r'^xl/sharedStrings\.xml$',  # https://docs.microsoft.com/en-us/office/open-xml/working-with-the-shared-string-table
             r'^(?:word|ppt|xl)/_rels/document\.xml\.rels$',
             r'^(?:word|ppt|xl)/_rels/footer[0-9]*\.xml\.rels$',
             r'^(?:word|ppt|xl)/_rels/header[0-9]*\.xml\.rels$',