Merge pull request #376 from TeamMsgExtractor/next-release

Fix issue with variable names

Author: TheElementalOfDestruction

CHANGELOG.md

@@ -1,3 +1,7 @@
+**v0.42.1**
+* Fixed some constants being accessed with the wrong name (names were changed in reorganization).
+* Removed unused regular expression.
+
 **v0.42.0**
 * [[TeamMsgExtractor #372](https://github.com/TeamMsgExtractor/msg-extractor/issues/372)] Changed the way that the save functions return a value. This makes the return value from all save functions much more informative, allowing a user to separate if a file or folder (or if more than one) was saved from the function. It also guarantees that all classes from this module will return the relevant path(s) if data is actually saved.
 * [[TeamMsgExtractor #288](https://github.com/TeamMsgExtractor/msg-extractor/issues/288)] Added feature to allow attachment save functions to simply overwrite existing files of the same name. This can be done with the `overwriteExisting` keyword argument from code or the `--overwrite-existing` option from the command line.

README.rst

@@ -242,8 +242,8 @@ 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-0.42.0-blue.svg
-   :target: https://pypi.org/project/extract-msg/0.42.0/
+.. |PyPI3| image:: https://img.shields.io/badge/pypi-0.42.1-blue.svg
+   :target: https://pypi.org/project/extract-msg/0.42.1/
 
 .. |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__ = '2023-07-29'
-__version__ = '0.42.0'
+__date__ = '2023-07-31'
+__version__ = '0.42.1'
 
 __all__ = [
     # Modules:

extract_msg/attachments/attachment.py

@@ -62,7 +62,7 @@ def getFilename(self, **kwargs) -> str:
             customFilename = str(customFilename)
             # First we need to validate it. If there are invalid characters,
             # this will detect it.
-            if constants.re.INVALID_FILENAME_CHARACTERS.search(customFilename):
+            if constants.re.INVALID_FILENAME_CHARS.search(customFilename):
                 raise ValueError('Invalid character found in customFilename. Must not contain any of the following characters: \\/:*?"<>|')
             filename = customFilename
         else:

extract_msg/attachments/custom_att.py

@@ -57,7 +57,7 @@ def getFilename(self, **kwargs) -> str:
             customFilename = str(customFilename)
             # First we need to validate it. If there are invalid characters,
             # this will detect it.
-            if constants.re.INVALID_FILENAME_CHARACTERS.search(customFilename):
+            if constants.re.INVALID_FILENAME_CHARS.search(customFilename):
                 raise ValueError('Invalid character found in customFilename. Must not contain any of the following characters: \\/:*?"<>|')
             filename = customFilename
         else:

extract_msg/attachments/emb_msg_att.py

@@ -52,7 +52,7 @@ def getFilename(self, **kwargs) -> str:
             customFilename = str(customFilename)
             # First we need to validate it. If there are invalid characters,
             # this will detect it.
-            if constants.re.INVALID_FILENAME_CHARACTERS.search(customFilename):
+            if constants.re.INVALID_FILENAME_CHARS.search(customFilename):
                 raise ValueError('Invalid character found in customFilename. Must not contain any of the following characters: \\/:*?"<>|')
             return customFilename
         else:

extract_msg/constants/re.py

@@ -3,10 +3,9 @@
 """
 
 __all__ = [
-    'BIN',
     'HTML_BODY_START',
     'HTML_SAN_SPACE',
-    'INVALID_FILENAME_CHARACTERS',
+    'INVALID_FILENAME_CHARS',
     'INVALID_OLE_PATH',
     'RTF_ENC_BODY_START',
 ]
@@ -24,9 +23,6 @@
 # Regular expression to find the start of the html body in encapsulated RTF.
 # This is used for one of the pattern types that makes life easy.
 RTF_ENC_BODY_START = re.compile(br'\{\\\*\\htmltag[0-9]* ?<body[^>]*>\}')
-# This is used in the workaround for decoding issues in RTFDE. We find `\bin`
-# sections and try to remove all of them to help with the decoding.
-BIN = re.compile(br'\\bin([0-9]+) ?')
 # Used in the vaildation of OLE paths. Any of these characters in a name make it
 # invalid.
 INVALID_OLE_PATH = re.compile(r'[:/\\!]')