Merge pull request #366 from TeamMsgExtractor/next-release

Fix for #365 (v0.41.3)

CHANGELOG.md

@@ -1,3 +1,8 @@
+**v0.41.3**
+* [[TeamMsgExtractor #365](https://github.com/TeamMsgExtractor/msg-extractor/issues/365)] Fixed an issue that would cause certain values retrieved from the header to not be decoded properly. It does this when retrieving the values, so nothing about the header has been changed.
+* Added new property `MessageBase.headerText` which is the text content of the header stream. Adjusted other things to use this instead of trying to retrieve the stream directly in multiple places.
+* Added typing to `MessageBase.header`.
+
 **v0.41.2**
 * Updated annotations on `MessageBase.save`.
 * Added new enum `BodyTypes`.

README.rst

@@ -250,8 +250,8 @@ 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-0.41.2-blue.svg
-   :target: https://pypi.org/project/extract-msg/0.41.2/
+.. |PyPI3| image:: https://img.shields.io/badge/pypi-0.41.3-blue.svg
+   :target: https://pypi.org/project/extract-msg/0.41.3/
 
 .. |PyPI2| image:: https://img.shields.io/badge/python-3.8+-brightgreen.svg
    :target: https://www.python.org/downloads/release/python-3816/

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__ = '2023-05-24'
-__version__ = '0.41.2'
+__date__ = '2023-06-10'
+__version__ = '0.41.3'
 
 __all__ = [
     # Modules:

extract_msg/message_base.py

@@ -39,9 +39,9 @@
 from .structures.report_tag import ReportTag
 from .recipient import Recipient
 from .utils import (
-        addNumToDir, addNumToZipDir, createZipOpen, findWk, htmlSanitize,
-        inputToBytes, inputToString, isEncapsulatedRtf, prepareFilename,
-        rtfSanitizeHtml, rtfSanitizePlain, validateHtml
+        addNumToDir, addNumToZipDir, createZipOpen, decodeRfc2047, findWk,
+        htmlSanitize, inputToBytes, inputToString, isEncapsulatedRtf,
+        prepareFilename, rtfSanitizeHtml, rtfSanitizePlain, validateHtml
     )
 
 from imapclient.imapclient import decode_utf7
@@ -135,6 +135,7 @@ def _genRecipient(self, recipientType, recipientInt : RecipientType) -> Optional
             if self.headerInit():
                 value = self.header[recipientType]
                 if value:
+                    value = decodeRfc2047(value)
                     value = value.replace(',', self.__recipientSeparator)
 
             # If the header had a blank field or didn't have the field, generate
@@ -792,7 +793,7 @@ def save(self, **kwargs) -> MessageBase:
 
         # If the user has requested the headers for this file, save it now.
         if kwargs.get('saveHeader', False):
-            headerText = self._getStringStream('__substg1.0_007D')
+            headerText = self.headerText
             if not headerText:
                 headerText = constants.HEADER_FORMAT.format(subject = self.subject, **self.header)
 
@@ -1047,15 +1048,15 @@ def detectedBodies(self) -> BodyTypes:
         return bodies
 
     @property
-    def header(self):
+    def header(self) -> email.message.Message:
         """
         Returns the message header, if it exists. Otherwise it will generate
         one.
         """
         try:
             return self._header
         except AttributeError:
-            headerText = self._getStringStream('__substg1.0_007D')
+            headerText = self.headerText
             if headerText:
                 self._header = EmailParser().parsestr(headerText)
                 self._header['date'] = self.date
@@ -1071,6 +1072,7 @@ def header(self):
                 # TODO find authentication results outside of header
                 header.add_header('Authentication-Results', None)
                 self._header = header
+
             return self._header
 
     @property
@@ -1130,6 +1132,13 @@ def headerFormatProperties(self) -> constants.HEADER_FORMAT_TYPE:
             },
         }
 
+    @functools.cached_property
+    def headerText(self) -> Optional[str]:
+        """
+        The raw text of the header stream, if it exists.
+        """
+        return self._getStringStream('__substg1.0_007D')
+
     @property
     def htmlBody(self) -> Optional[bytes]:
         """
@@ -1229,7 +1238,7 @@ def messageId(self) -> Optional[str]:
         except AttributeError:
             headerResult = None
             if self.headerInit():
-                headerResult = self._header['message-id']
+                headerResult = self.header['message-id']
             if headerResult is not None:
                 self._messageId = headerResult
             else:
@@ -1329,7 +1338,7 @@ def sender(self) -> Optional[str]:
         except AttributeError:
             # Check header first
             if self.headerInit():
-                headerResult = self.header['from']
+                headerResult = decodeRfc2047(self.header['from'])
                 if headerResult is not None:
                     self._sender = headerResult
                     return headerResult

extract_msg/utils.py

@@ -25,6 +25,7 @@
 import collections
 import copy
 import datetime
+import email.header
 import email.message
 import email.policy
 import glob
@@ -169,6 +170,21 @@ def _open(name, mode, *args, **kwargs):
     return _open
 
 
+def decodeRfc2047(encoded : str) -> str:
+    """
+    Decodes text encoded using the method specified in RFC 2047.
+    """
+    # This returns a list of tuples containing the bytes and the encoding they
+    # are using, so we decode each one and join them together.
+    #
+    # decode_header header will return a string instead of bytes for the first
+    # object if the input is not encoded, something that is frustrating.
+    return ''.join(
+        x[0].decode(x[1] or 'ascii') if isinstance(x[0], bytes) else x
+        for x in email.header.decode_header(encoded)
+    )
+
+
 def dictGetCasedKey(_dict : Dict, key : Any) -> Any:
     """
     Retrieves the key from the dictionary with the proper casing using a