Attempt to fix #432

TeamMsgExtractor · Oct 2, 2024 · 16f3b9d · 16f3b9d
1 parent 30a28d8
commit 16f3b9d
Show file tree

Hide file tree

Showing 2 changed files with 4 additions and 1 deletion.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -1,3 +1,6 @@
+**v0.50.0**
+* [[TeamMsgExtractor #432](https://github.com/TeamMsgExtractor/msg-extractor/issues/432)] Adjust html header code to replace non-ascii characters with escaped versions.
+
 **v0.49.0**
 * [[TeamMsgExtractor #427](https://github.com/TeamMsgExtractor/msg-extractor/issues/427)] Adjusted code for converting time stamps to create null dates for any time stamp beyond a certain point. The point was determined to be close to the existing null dates.
 * [[TeamMsgExtractor #425](https://github.com/TeamMsgExtractor/msg-extractor/issues/425)] Added basic support for custom attachments that are Windows Metafiles.

diff --git a/extract_msg/msg_classes/message_base.py b/extract_msg/msg_classes/message_base.py
@@ -1213,7 +1213,7 @@ def htmlInjectableHeader(self) -> str:
         prefix = '<div id="injectedHeader"><div><p class="MsoNormal">'
         suffix = '<o:p></o:p></p></div></div>'
         joinStr = '<br/>'
-        formatter = (lambda name, value: f'<b>{name}:</b>&nbsp;{inputToString(htmlSanitize(value), self.stringEncoding)}')
+        formatter = (lambda name, value: f'<b>{name}:</b>&nbsp;{inputToString(htmlSanitize(value), self.stringEncoding).encode("ascii", "xmlcharrefreplace").decode()}')
 
         return self.getInjectableHeader(prefix, joinStr, suffix, formatter)