Merge pull request #468 from TeamMsgExtractor/next-release

Version 0.55.0

Author: TheElementalOfDestruction

CHANGELOG.md

@@ -1,3 +1,10 @@
+**v0.55.0**
+* [[TeamMsgExtractor #465](https://github.com/TeamMsgExtractor/msg-extractor/issues/465)] Added missing `msg.close()` to `openMsg()`. If the MSG file was actually just a plain OLE file, it would be left open.
+* Adjusted the default value of `maxNameLength` for `MessageBase.save()` to 40 instead of 256.
+* Adjusted exception handling for `MessageBase.save()` to properly report the reason a folder fails to be created.
+* Simplified some of the code for `MessageBase.save()`.
+* Fixed some typing information.
+
 **v0.54.1**
 * [[TeamMsgExtractor #462](https://github.com/TeamMsgExtractor/msg-extractor/issues/462)] Fix potential issue where child MSG might have incompatible encoding to parent MSG when trying to grab a stream from the parent.
 * Added code to attempt to significantly improve RTF deencapsulation times. This tries to strip away unneeded data before passing it to `RTFDE`. This shows improvements on all files that take more than one second. Currently, this actually fixes some files previously outputting wrong from `RTFDE` when deencapsulating the HTML body, specifically around non breaking spaces sometimes not transferring over.

README.rst

@@ -260,8 +260,8 @@ your access to the newest major version of extract-msg.
 .. |License: GPL v3| image:: https://img.shields.io/badge/License-GPLv3-blue.svg
    :target: LICENSE.txt
 
-.. |PyPI3| image:: https://img.shields.io/badge/pypi-0.54.1-blue.svg
-   :target: https://pypi.org/project/extract-msg/0.54.1/
+.. |PyPI3| image:: https://img.shields.io/badge/pypi-0.55.0-blue.svg
+   :target: https://pypi.org/project/extract-msg/0.55.0/
 
 .. |PyPI2| image:: https://img.shields.io/badge/python-3.8+-brightgreen.svg
    :target: https://www.python.org/downloads/release/python-3810/

extract_msg/__init__.py

@@ -27,8 +27,8 @@
 #    along with this program.  If not, see <http://www.gnu.org/licenses/>.
 
 __author__ = 'Destiny Peterson & Matthew Walker'
-__date__ = '2025-04-10'
-__version__ = '0.54.1'
+__date__ = '2025-08-12'
+__version__ = '0.55.0'
 
 __all__ = [
     # Modules:

extract_msg/attachments/attachment.py

@@ -13,7 +13,7 @@
 import string
 import zipfile
 
-from typing import TYPE_CHECKING
+from typing import Optional, TYPE_CHECKING
 
 from .. import constants
 from .attachment_base import AttachmentBase
@@ -72,7 +72,7 @@ def getFilename(self, **kwargs) -> str:
 
         return filename
 
-    def regenerateRandomName(self) -> str:
+    def regenerateRandomName(self) -> None:
         """
         Used to regenerate the random filename used if the attachment cannot
         find a usable filename.
@@ -166,9 +166,11 @@ def save(self, **kwargs) -> constants.SAVE_TYPE:
                 _zip.close()
 
     @property
-    def data(self) -> bytes:
+    def data(self) -> Optional[bytes]:
         """
         The bytes making up the attachment data.
+
+        If the attachment data stream does not exist, returns None.
         """
         return self.__data
 

extract_msg/msg_classes/message_base.py

@@ -726,12 +726,12 @@ def save(self, **kwargs) -> constants.SAVE_TYPE:
         pdf = kwargs.get('pdf', False)
         allowFallback = kwargs.get('allowFallback', False)
         _zip = kwargs.get('zip')
-        maxNameLength = kwargs.get('maxNameLength', 256)
+        maxNameLength = kwargs.get('maxNameLength', 40)
 
         # Variables involved in the save location.
         customFilename = kwargs.get('customFilename')
         useMsgFilename = kwargs.get('useMsgFilename', False)
-        #maxPathLength = kwargs.get('maxPathLength', 255)
+        #maxPathLength = kwargs.get('maxPathLength', 255) # TODO
 
         # Track if we are only saving the attachments.
         attachOnly = kwargs.get('attachmentsOnly', False)
@@ -742,6 +742,8 @@ def save(self, **kwargs) -> constants.SAVE_TYPE:
         # raising an exception.
         skipBodyNotFound = kwargs.get('skipBodyNotFound', False)
 
+        fext = None
+
         if pdf:
             kwargs['preparedHtml'] = True
 
@@ -758,30 +760,22 @@ def save(self, **kwargs) -> constants.SAVE_TYPE:
                 if self.htmlBody:
                     useHtml = True
                     fext = 'html'
-                elif not allowFallback:
-                    if skipBodyNotFound:
-                        fext = None
-                    else:
-                        raise DataNotFoundError('Could not find the htmlBody.')
+                elif not allowFallback and not skipBodyNotFound:
+                    raise DataNotFoundError('Could not find the htmlBody.')
 
             if pdf:
                 if self.htmlBody:
                     usePdf = True
                     fext = 'pdf'
-                elif not allowFallback:
-                    if skipBodyNotFound:
-                        fext = None
-                    else:
-                        raise DataNotFoundError('Count not find the htmlBody to convert to pdf.')
+                elif not allowFallback and not skipBodyNotFound:
+                    raise DataNotFoundError('Count not find the htmlBody to convert to pdf.')
 
             if rtf or (html and not useHtml) or (pdf and not usePdf):
                 if self.rtfBody:
                     useRtf = True
                     fext = 'rtf'
                 elif not allowFallback:
-                    if skipBodyNotFound:
-                        fext = None
-                    else:
+                    if not skipBodyNotFound:
                         raise DataNotFoundError('Could not find the rtfBody.')
                 else:
                     # This was the last resort before plain text, so fall
@@ -794,10 +788,7 @@ def save(self, **kwargs) -> constants.SAVE_TYPE:
                 # We need to check if the plain text body was found. If it
                 # was found but was empty that is considered valid, so we
                 # specifically check against None.
-                if self.body is None:
-                    if skipBodyNotFound:
-                        fext = None
-                    else:
+                if self.body is None and not skipBodyNotFound:
                         if allowFallback:
                             raise DataNotFoundError('Could not find a valid body using current options.')
                         else:
@@ -872,12 +863,12 @@ def save(self, **kwargs) -> constants.SAVE_TYPE:
             if not _zip:
                 try:
                     os.makedirs(path)
-                except Exception:
+                except Exception as e:
                     newDirName = addNumToDir(path)
                     if newDirName:
                         path = newDirName
                     else:
-                        raise OSError(f'Failed to create directory "{path}". Does it already exist?')
+                        raise OSError(f'Failed to create directory "{path}". Reason: {e}')
             else:
                 # In my testing I ended up with multiple files in a zip at the
                 # same location so let's try to handle that.

extract_msg/open_msg.py

@@ -109,6 +109,7 @@ def openMsg(path, **kwargs) -> MSGFile:
     # lower function. So let's make sure we got a good return first.
     if not ct:
         if kwargs.get('strict', True):
+            msg.close()
             raise InvalidFileFormatError('File was confirmed to be an olefile, but was not an MSG file.')
         else:
             # If strict mode is off, we'll just return an MSGFile anyways.