Version 0.33.0

CHANGELOG.md

@@ -1,3 +1,14 @@
+**v0.33.0**
+* [[TeamMsgExtractor #212](https://github.com/TeamMsgExtractor/msg-extractor/issues/212)] Added support for Task objects.
+* Added additional parameter `overrideClass` to all `_ensureSetX` type functions. This parameter is a class to initialize using the data, if provided. The data will be provided as the first argument to the `__init__` function of the class *if* the data is not `None`. If the data is done, the value set and returned from `_ensureSetX` will be `None`. This can be overriden using the second added parameter, which defaults to this behavior. Simply set `preserveNone` to `False` to force the data to be passed to the class. Keep in mind that this means the class will receive `None` as it's first parameter.
+* Updated `Named` class to make it more like the dictionary it is build on top of. Specifically, added `keys`, `values`, and `items` as functions.
+* Fixed issue in `Named` where old code wasn't deleted, causing some named properties to be completely omitted.
+* Improved efficiency of `Named` by making it so `get` no longer copied the entire dictionary repeatedly while looking for the property.
+* Fixed typo in `Attachment` that caused embedded msg files to still regenerate the `Named` instance even though they should have been using the parent's.
+* Updated fields in `MSGFile` to use enums.
+* Added additional properties to `MSGFile`. 
+* Significant cleanup. 
+
 **v0.32.0**
 * [[TeamMsgExtractor #217](https://github.com/TeamMsgExtractor/msg-extractor/issues/217)] Redesigned named properties to be much more efficient. All in all, load times for MSG files are significantly improved all around.
     * Named properties load dynamically.

README.rst

@@ -209,11 +209,20 @@ Credits
 
 And thank you to everyone who has opened an issue and helped us track down those pesky bugs.
 
+Extra
+-----
+
+Check out the new project `msg-explorer`_ that allows you to open MSG files and
+explore their contents in a GUI. It is usually updated within a few days of a
+major release to ensure continued support. Because of this, it is recommended to
+install it to a separate environment (like a vitural env) to not interfere with
+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-0.32.0-blue.svg
-   :target: https://pypi.org/project/extract-msg/0.32.0/
+.. |PyPI3| image:: https://img.shields.io/badge/pypi-0.33.0-blue.svg
+   :target: https://pypi.org/project/extract-msg/0.33.0/
 
 .. |PyPI2| image:: https://img.shields.io/badge/python-3.6+-brightgreen.svg
    :target: https://www.python.org/downloads/release/python-367/
@@ -227,3 +236,4 @@ And thank you to everyone who has opened an issue and helped us track down those
 .. _Seamus Tuohy: https://github.com/seamustuohy
 .. _Discord: https://discord.com/invite/B77McRmzdc
 .. _Buy Me a Coffee: https://www.buymeacoffee.com/DestructionE
+.. _msg-explorer: https://pypi.org/project/msg-explorer/

extract_msg/__init__.py

@@ -9,7 +9,7 @@
 https://github.com/TeamMsgExtractor/msg-extractor
 """
 
-# --- LICENSE.txt -----------------------------------------------------------------
+# --- LICENSE.txt --------------------------------------------------------------
 #
 #    Copyright 2013-2022 Matthew Walker and Destiny Peterson
 #
@@ -27,8 +27,8 @@
 #    along with this program.  If not, see <http://www.gnu.org/licenses/>.
 
 __author__ = 'Destiny Peterson & Matthew Walker'
-__date__ = '2022-06-07'
-__version__ = '0.32.0'
+__date__ = '2022-06-08'
+__version__ = '0.33.0'
 
 import logging
 
@@ -45,4 +45,5 @@
 from .prop import createProp
 from .properties import Properties
 from .recipient import Recipient
+from .task import Task
 from .utils import openMsg, properHex

extract_msg/__main__.py

@@ -4,7 +4,6 @@
 import traceback
 
 from extract_msg import __doc__, utils
-from extract_msg.message import Message
 
 
 def main() -> None:
@@ -14,7 +13,7 @@ def main() -> None:
     level = logging.INFO if args.verbose else logging.WARNING
 
     # Determine where to save the files to.
-    currentDir = os.getcwd() # Store this incase the path changes.
+    currentDir = os.getcwd() # Store this in case the path changes.
     if not args.zip:
         if args.out_path:
             if not os.path.exists(args.out_path):

extract_msg/appointment.py

@@ -1,5 +1,3 @@
-from . import constants
-from .attachment import Attachment
 from .message_base import MessageBase
 
 
@@ -33,8 +31,7 @@ def location(self):
         try:
             return self.__location
         except AttributeError:
-            self.__location = self.named.getNamedValue('8208')
-            self.__location = self.named.getNamedValue('0002') if self.__location is None else self.__location
+            self.__location = self.named.getNamedValue('8208') or self.named.getNamedValue('0002')
             return self.__location
 
     @property

extract_msg/attachment.py

@@ -8,9 +8,8 @@
 from . import constants
 from .attachment_base import AttachmentBase
 from .enums import AttachmentType
-from .prop import FixedLengthProp, VariableLengthProp
-from .properties import Properties
-from .utils import createZipOpen, inputToString, openMsg, prepareFilename, verifyPropertyId, verifyType
+from .utils import createZipOpen, inputToString, openMsg, prepareFilename
+
 
 logger = logging.getLogger(__name__)
 logger.addHandler(logging.NullHandler())
@@ -44,7 +43,7 @@ def __init__(self, msg, dir_):
             else:
                 self.__prefix = msg.prefixList + [dir_, '__substg1.0_3701000D']
                 self.__type = AttachmentType.MSG
-                self.__data = openMsg(self.msg.path, prefix = self.__prefix, parent = self.msg, **self.msg.kwargs)
+                self.__data = openMsg(self.msg.path, prefix = self.__prefix, parentMsg = self.msg, **self.msg.kwargs)
         elif (self.props['37050003'].value & 0x7) == 0x7:
             # TODO Handling for special attacment type 0x7
             self.__type = AttachmentType.WEB

extract_msg/attachment_base.py

@@ -1,12 +1,12 @@
 import logging
 
-from . import constants
 from .enums import PropertiesType
 from .named import NamedProperties
 from .prop import FixedLengthProp
 from .properties import Properties
 from .utils import verifyPropertyId, verifyType
 
+
 logger = logging.getLogger(__name__)
 logger.addHandler(logging.NullHandler())
 
@@ -30,13 +30,21 @@ def __init__(self, msg, dir_):
         self.__namedProperties = NamedProperties(msg.named, self)
 
 
-    def _ensureSet(self, variable, streamID, stringStream = True):
+    def _ensureSet(self, variable, streamID, stringStream = True, **kwargs):
         """
         Ensures that the variable exists, otherwise will set it using the
         specified stream. After that, return said variable.
 
         If the specified stream is not a string stream, make sure to set
         :param stringStream: to False.
+
+        :param overrideClass: Class/function to use to morph the data that was
+            read. The data will be the first argument to the class's __init__
+            function or the function itself, if that is what is provided. By
+            default, this will be completely ignored if the value was not found.
+        :param preserveNone: If true (default), causes the function to ignore
+            :param overrideClass: when the value could not be found (is None).
+            If this is changed to False, then the value will be used regardless.
         """
         try:
             return getattr(self, variable)
@@ -45,25 +53,51 @@ def _ensureSet(self, variable, streamID, stringStream = True):
                 value = self._getStringStream(streamID)
             else:
                 value = self._getStream(streamID)
+            # Check if we should be overriding the data type for this instance.
+            if kwargs:
+                overrideClass = kwargs.get('overrideClass')
+                if overrideClass is not None and (value is not None or not kwargs.get('preserveNone', True)):
+                    value = overrideClass(value)
             setattr(self, variable, value)
             return value
 
-    def _ensureSetNamed(self, variable, propertyName):
+    def _ensureSetNamed(self, variable, propertyName, **kwargs):
         """
         Ensures that the variable exists, otherwise will set it using the named
         property. After that, return said variable.
+
+        :param overrideClass: Class/function to use to morph the data that was
+            read. The data will be the first argument to the class's __init__
+            function or the function itself, if that is what is provided. By
+            default, this will be completely ignored if the value was not found.
+        :param preserveNone: If true (default), causes the function to ignore
+            :param overrideClass: when the value could not be found (is None).
+            If this is changed to False, then the value will be used regardless.
         """
         try:
             return getattr(self, variable)
         except AttributeError:
             value = self.namedProperties.get(propertyName)
+            # Check if we should be overriding the data type for this instance.
+            if kwargs:
+                overrideClass = kwargs.get('overrideClass')
+                if overrideClass is not None and (value is not None or not kwargs.get('preserveNone', True)):
+                    value = overrideClass(value)
             setattr(self, variable, value)
             return value
 
-    def _ensureSetProperty(self, variable, propertyName):
+    def _ensureSetProperty(self, variable, propertyName, **kwargs):
         """
         Ensures that the variable exists, otherwise will set it using the
         property. After that, return said variable.
+
+        :param overrideClass: Class/function to use to morph the data that was
+            read. The data will be the first argument to the class's __init__
+            function or the function itself, if that is what is provided. By
+            default, this will be completely ignored if the value was not found.
+        :param preserveNone: If true (default), causes the function to ignore
+            :param overrideClass: when the value could not be found (is None).
+            If this is changed to False, then the value will be used regardless.
         """
         try:
             return getattr(self, variable)
@@ -72,19 +106,37 @@ def _ensureSetProperty(self, variable, propertyName):
                 value = self.props[propertyName].value
             except (KeyError, AttributeError):
                 value = None
+            # Check if we should be overriding the data type for this instance.
+            if kwargs:
+                overrideClass = kwargs.get('overrideClass')
+                if overrideClass is not None and (value is not None or not kwargs.get('preserveNone', True)):
+                    value = overrideClass(value)
             setattr(self, variable, value)
             return value
 
-    def _ensureSetTyped(self, variable, _id):
+    def _ensureSetTyped(self, variable, _id, **kwargs):
         """
         Like the other ensure set functions, but designed for when something
         could be multiple types (where only one will be present). This way you
         have no need to set the type, it will be handled for you.
+
+        :param overrideClass: Class/function to use to morph the data that was
+            read. The data will be the first argument to the class's __init__
+            function or the function itself, if that is what is provided. By
+            default, this will be completely ignored if the value was not found.
+        :param preserveNone: If true (default), causes the function to ignore
+            :param overrideClass: when the value could not be found (is None).
+            If this is changed to False, then the value will be used regardless.
         """
         try:
             return getattr(self, variable)
         except AttributeError:
             value = self._getTypedData(_id)
+            # Check if we should be overriding the data type for this instance.
+            if kwargs:
+                overrideClass = kwargs.get('overrideClass')
+                if overrideClass is not None and (value is not None or not kwargs.get('preserveNone', True)):
+                    value = overrideClass(value)
             setattr(self, variable, value)
             return value
 

extract_msg/contact.py

@@ -1,5 +1,3 @@
-from . import constants
-from .attachment import Attachment
 from .msg import MSGFile
 
 
@@ -113,7 +111,7 @@ def country(self):
     @property
     def departmentName(self):
         """
-        The name of the dapartment the contact works in.
+        The name of the department the contact works in.
         """
         return self._ensureSet('_departmentName', '__substg1.0_3A18')
 

extract_msg/data.py

@@ -17,7 +17,7 @@ def __init__(self, data : bytes):
     @property
     def globalCounter(self) -> int:
         """
-        An unsigned ineger identifying the folder within its Store object.
+        An unsigned integer identifying the folder within its Store object.
         """
         return self.__globalCounter
 
@@ -42,7 +42,7 @@ def __init__(self, data):
     @property
     def globalCounter(self) -> int:
         """
-        An unsigned ineger identifying the folder within its Store object.
+        An unsigned integer identifying the folder within its Store object.
         """
         return self.__globalCounter
 

extract_msg/dev.py

@@ -21,7 +21,7 @@
 logger.addHandler(logging.NullHandler())
 
 
-def setupDevLogger(defaultPath=None, logfile = None, envKey='EXTRACT_MSG_LOG_CFG'):
+def setupDevLogger(defaultPath = None, logfile = None, envKey = 'EXTRACT_MSG_LOG_CFG'):
     utils.setupLogging(defaultPath, 5, logfile, True, envKey)
 
 
@@ -64,4 +64,4 @@ def main(args, argv):
                 logpath = x.baseFilename
             except AttributeError:
                 pass;
-        print(g'Logging complete. Log has been saved to {logpath}')
+        print(f'Logging complete. Log has been saved to {logpath}')

extract_msg/dev_classes/attachment.py

@@ -1,6 +1,5 @@
 import logging
 
-from .. import constants
 from ..enums import PropertiesType
 from ..properties import Properties
 from ..utils import properHex