Fix a few bugs and started working on #452

TheElementalOfDestruction · TheElementalOfDestruction · commit f1752de191d1 · 2025-03-13T07:51:31.000-07:00
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -1,3 +1,9 @@
+**v0.53.2**
+* [[TeamMsgExtractor #452](https://github.com/TeamMsgExtractor/msg-extractor/issues/452)]
+* Fixed a bug that would cause an error in task objects due to a lack of `enumerate`.
+* Fix `TOCEntry` not initializing `DVTargetDevice` correctly.
+* Add temporary properties for `ContentID` to `SignedAttachment`. AFAIK these can't ever be set, but this prevents errors in some places.
+
 **v0.53.1**
 * Expanded allowable range for `red-black-tree-mod`.
 * Fix issue with `MessageBase.asEmailMessage()` that prevented embedded MSG files from being attached.
diff --git a/extract_msg/attachments/signed_att.py b/extract_msg/attachments/signed_att.py
@@ -45,7 +45,7 @@ def __init__(self, msg, data: bytes, name: str, mimetype: str, node: email.messa
         self.__node = node
         self.__treePath = msg.treePath + [makeWeakRef(self)]
 
-        self.__data = None
+        self.__data = b''
         # To add support for embedded MSG files, we are going to completely
         # ignore the mimetype and just do a few simple checks to see if we can
         # use the bytes as am embedded file.
@@ -59,7 +59,7 @@ def __init__(self, msg, data: bytes, name: str, mimetype: str, node: email.messa
             except Exception:
                 logger.exception('Signed message was an OLE file, but could not be read as an MSG file due to an exception.')
 
-        if self.__data is None:
+        if not self.__data:
             self.__data = data
 
     def _handleFnc(self, _zip, filename, customPath: pathlib.Path, kwargs) -> pathlib.Path:
@@ -205,6 +205,12 @@ def saveEmbededMessage(self, **kwargs) -> constants.SAVE_TYPE:
     def asBytes(self) -> bytes:
         return self.__asBytes
 
+    @property
+    def contentID(self) -> None:
+        return None
+
+    cid = contentID
+
     @property
     def data(self) -> Union[bytes, MSGFile]:
         """
diff --git a/extract_msg/msg_classes/message_base.py b/extract_msg/msg_classes/message_base.py
@@ -96,6 +96,7 @@ def __init__(self, path, **kwargs):
             except Exception as e:
                 # Prevent an error in the body from preventing opening.
                 logger.exception('Critical error accessing the body. File opened but accessing the body will throw an exception.')
+            self._htmlEncoding = None
         except:
             try:
                 self.close()
@@ -380,7 +381,7 @@ def getSaveHtmlBody(self, preparedHtml: bool = False, charset: str = 'utf-8', **
 
             # If we are preparing the HTML, then we should
             if preparedHtml and charset:
-                bs = bs4.BeautifulSoup(data, features = 'html.parser')
+                bs = bs4.BeautifulSoup(data, features = 'html.parser', from_encoding=self._htmlEncoding)
                 if not bs.find('meta', {'http-equiv': 'Content-Type'}):
                     # Setup the attributes for the tag.
                     tagAttrs = {
@@ -405,7 +406,7 @@ def getSaveHtmlBody(self, preparedHtml: bool = False, charset: str = 'utf-8', **
 
             return data
         else:
-            return self.htmlBody
+            return self.htmlBody or b''
 
     def getSavePdfBody(self, wkPath = None, wkOptions = None, **kwargs) -> bytes:
         """
@@ -511,7 +512,7 @@ def injectHtmlHeader(self, prepared: bool = False) -> bytes:
             # the <html> and <body> tag are missing, we determine where to put
             # the body tag (around everything if there is no <head> tag,
             # otherwise at the end) and then wrap it all in the <html> tag.
-            parser = bs4.BeautifulSoup(body, features = 'html.parser')
+            parser = bs4.BeautifulSoup(body, features = 'html.parser', from_encoding=self._htmlEncoding)
             if not parser.find('html') and not parser.find('body'):
                 if parser.find('head') or parser.find('footer'):
                     # Create the parser we will be using for the corrections.
@@ -1186,7 +1187,7 @@ def htmlBodyPrepared(self) -> Optional[bytes]:
             return self.htmlBody
 
         # Create the BeautifulSoup instance to use.
-        soup = bs4.BeautifulSoup(self.htmlBody, 'html.parser')
+        soup = bs4.BeautifulSoup(self.htmlBody, 'html.parser', from_encoding=self._htmlEncoding)
 
         # Get a list of image tags to see if we can inject into. If the source
         # of an image starts with "cid:" that means it is one of the attachments
diff --git a/extract_msg/msg_classes/task_request.py b/extract_msg/msg_classes/task_request.py
@@ -63,7 +63,7 @@ def taskObject(self) -> Optional[Task]:
         # The task object MUST be the first attachment, but we will be
         # lenient and allow it to be in any position. It not existing,
         # however, will not be tolerated.
-        task = next(((index, att) for index, att in self.attachments if isinstance(att.data, Task)), None)
+        task = next(((index, att) for index, att in enumerate(self.attachments) if isinstance(att.data, Task)), None)
 
         if task is None:
             if ErrorBehavior.STANDARDS_VIOLATION in self.errorBehavior:
diff --git a/extract_msg/structures/toc_entry.py b/extract_msg/structures/toc_entry.py
@@ -20,7 +20,7 @@ def __init__(self, reader: Optional[Union[bytes, BytesReader]] = None):
             self.__lindex = 0
             self.__tymed = 0
             self.__advf = 0
-            self.__targetDevice = DVTargetDevice()
+            self.__targetDevice = DVTargetDevice(None)
             return
 
         if isinstance(reader, bytes):
