Merge pull request #407 from TeamMsgExtractor/next-release

Version 0.48.2

Author: TheElementalOfDestruction

CHANGELOG.md

@@ -1,3 +1,6 @@
+**v0.48.2**
+* Fixed bugs with `MessageBase.asEmailMessage()`. Numerous improvements to how it handles the data.
+
 **v0.48.1**
 * Added an option (`-s`, `--stdin`) to the command line to take an MSG file from stdin. This allows the user to pipe the MSG data from another program directly instead of having to write a middleman that uses the `extract-msg` library directly or having to write the file to the disk first.
 * Changed main function to allow for manual argument list to be passed to it.

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-0.48.1-blue.svg
-   :target: https://pypi.org/project/extract-msg/0.48.1/
+.. |PyPI3| image:: https://img.shields.io/badge/pypi-0.48.2-blue.svg
+   :target: https://pypi.org/project/extract-msg/0.48.2/
 
 .. |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__ = '2024-03-08'
-__version__ = '0.48.1'
+__date__ = '2024-03-09'
+__version__ = '0.48.2'
 
 __all__ = [
     # Modules:

extract_msg/msg_classes/message_base.py

@@ -24,7 +24,10 @@
 import RTFDE.exceptions
 
 from email import policy
+from email.charset import Charset, QP
 from email.message import EmailMessage
+from email.mime.multipart import MIMEMultipart
+from email.mime.text import MIMEText
 from email.parser import HeaderParser
 from typing import Any, Callable, cast, Dict, List, Optional, Tuple, Type, Union
 
@@ -151,13 +154,24 @@ def asEmailMessage(self) -> EmailMessage:
 
         # Copy the headers.
         for key, value in self.header.items():
-            ret[key] = value
+            if key.lower() != 'content-type':
+                ret[key] = value.replace('\r\n', '').replace('\n', '')
+
+        ret['Content-Type'] = 'multipart/mixed'
 
         # Attach the body to the EmailMessage instance.
+        msgMain = MIMEMultipart('related')
+        ret.attach(msgMain)
+        bodyParts = MIMEMultipart('alternative')
+        msgMain.attach(bodyParts)
+
+        c = Charset('utf-8')
+        c.body_encoding = QP
+
+        if self.body:
+            bodyParts.attach(MIMEText(self.body, 'plain', c))
         if self.htmlBody:
-            ret.set_content(self.body, subtype = 'html', cte = 'quoted-printable')
-        elif self.body:
-            ret.set_content(self.body, cte = 'quoted-printable')
+            bodyParts.attach(MIMEText(self.htmlBody.decode('utf-8'), 'html', c))
 
         # Process attachments.
         for att in self.attachments:
@@ -167,7 +181,7 @@ def asEmailMessage(self) -> EmailMessage:
                     filename = att.getFilename()
                     if filename.lower().endswith('.msg'):
                         filename = filename[:-4] + '.eml'
-                    ret.add_attachment(
+                    msgMain.add_attachment(
                                         att.data.asEmailMessage(),
                                         filename = filename,
                                         cid = att.contentId)
@@ -183,11 +197,17 @@ def asEmailMessage(self) -> EmailMessage:
                         raise ConversionError(f'Could not find a suitable method to attach attachment data type "{att.dataType}".')
                     mime = att.mimetype or 'application/octet-stream'
                     mainType, subType = mime.split('/')[0], mime.split('/')[-1]
-                    ret.add_attachment(data,
-                                       maintype = mainType,
-                                       subtype = subType,
-                                       filename = att.getFilename(),
-                                       cid = att.contentId)
+                    # Need to do this manually instead of using add_attachment.
+                    attachment = EmailMessage()
+                    attachment.set_content(data,
+                                           maintype = mainType,
+                                           subtype = subType,
+                                           cid = att.contentId)
+                    # This is just a very basic check.
+                    attachment['Content-Disposition'] = f'{"inline" if att.hidden else "attachment"}; filename="{att.getFilename()}"'
+
+                    # Add the attachment.
+                    msgMain.attach(attachment)
 
         return ret
 

setup.cfg

@@ -1,5 +1,5 @@
 [bdist_wheel]
-universal=1
+python-tag=py3
 
 [options.extras_require]
 all =