Merge pull request #148 from kyrias/nuke-learn

Rip out broken classification system
afewmail · Jun 12, 2017 · 2671bbe · 2671bbe
2 parents 9c8a4da + 86d881d
commit 2671bbe
Show file tree

Hide file tree

Showing 19 changed files with 18 additions and 579 deletions.
diff --git a/README.rst b/README.rst
@@ -16,10 +16,8 @@ Its basic task is to provide automatic tagging each time new mail is registered
 with notmuch. In a classic setup, you might call it after 'notmuch new' in an
 offlineimap post sync hook.
 
-In addition to more elementary features such as adding tags based on email
-headers or maildir folders, handling killed threads and spam, it can do some
-heavy magic in order to *learn* how to initially tag your mails based on their
-content.
+It can do basic thing such as adding tags based on email headers or maildir
+folders, handling killed threads and spam.
 
 In move mode, afew will move mails between maildir folders according to
 configurable rules that can contain arbitrary notmuch queries to match against
@@ -44,7 +42,6 @@ Please keep an eye on NEWS.md for important news.
 Features
 --------
 
-* text classification, magic tags aka the mailing list without server
 * spam handling (flush all tags, add spam)
 * killed thread handling
 * tags posts to lists with ``lists``, ``$list-id``
@@ -62,12 +59,6 @@ Features
 Installation
 ------------
 
-You'll need dbacl for the text classification:
-
-.. code:: bash
-
-  $ aptitude install dbacl
-
 And I'd like to suggest to install afew as your unprivileged user.
 If you do, make sure ``~/.local/bin`` is in your path.
 
@@ -94,7 +85,6 @@ Put a list of filters into ``~/.config/afew/config``:
 
   # This is the default filter chain
   [SpamFilter]
-  [ClassifyingFilter]
   [KillThreadsFilter]
   [ListMailsFilter]
   [ArchiveSentMailsFilter]
@@ -126,25 +116,13 @@ Commandline help
     -h, --help            show this help message and exit
 
     Actions:
-      Please specify exactly one action (both update actions can be
-      specified simultaniously).
+      Please specify exactly one action.
 
       -t, --tag           run the tag filters
-      -l LEARN, --learn=LEARN
-                          train the category with the messages matching the
-                          given query
-      -u, --update        update the categories [requires no query]
-      -U, --update-reference
-                          update the reference category (takes quite some time)
-                          [requires no query]
-      -c, --classify      classify each message matching the given query (to
-                          test the trained categories)
       -m, --move-mails    move mail files between maildir folders
 
     Query modifiers:
-      Please specify either --all or --new or a query string. The default
-      query for the update actions is a random selection of
-      REFERENCE_SET_SIZE mails from the last REFERENCE_SET_TIMEFRAME days.
+      Please specify either --all or --new or a query string.
 
       -a, --all           operate on all messages
       -n, --new           operate on all new messages
@@ -232,64 +210,6 @@ For information on how to configure rules for move mode, what you can
 do with it and what you can't, please refer to ``docs/move_mode``.
 
 
-
-The real deal
--------------
-
-Let's train on an existing tag ``spam``:
-
-.. code:: bash
-
-  $ afew --learn spam -- tag:spam
-
-Let's build the reference category. This is important to reduce the
-false positive rate. This may take a while...
-
-
-.. code:: bash
-
-  $ afew --update-reference
-
-And now let's create a new tag from an arbitrary query result:
-
-.. code:: bash
-
-  $ afew -vv --learn sourceforge -- sourceforge
-
-Let's see how good the classification is:
-
-.. code:: bash
-
-  $ afew --classify -- tag:inbox and not tag:killed
-  Sergio López <slpml@sinrega.org> (2011-10-08) (bug-hurd inbox lists unread) --> no match
-  Patrick Totzke <reply+i-1840934-9a702d09342dca2b120126b26b008d0deea1731e@reply.github.com> (2011-10-08) (alot inbox lists) --> alot
-  [...]
-
-As soon as you trained some categories, afew will automatically
-tag your new mails using the classifier. If you want to disable this
-feature, either use the ``--enable-filters`` option to override the default
-set of filters or remove the files in your afew state dir:
-
-.. code:: bash
-
-  $ ls ~/.local/share/afew/categories
-  alot juggling  reference_category  sourceforge  spam
-
-You need to update the category files periodically. I'd suggest to run
-
-.. code:: bash
-
-  $ afew --update
-
-on a weekly and
-
-.. code:: bash
-
-  $ afew --update-reference
-
-on a monthly basis.
-
-
 Have fun :)
 
 

diff --git a/afew/DBACL.py b/afew/DBACL.py
diff --git a/afew/Database.py b/afew/Database.py
@@ -23,7 +23,6 @@
 import notmuch
 
 from .NotmuchSettings import notmuch_settings, get_notmuch_new_tags
-from .utils import extract_mail_body
 
 class Database(object):
     '''
@@ -111,22 +110,6 @@ def get_messages(self, query, full_thread = False):
                 for message in self.walk_thread(thread):
                     yield message
 
-
-    def mail_bodies_matching(self, *args, **kwargs):
-        '''
-        Filters each message yielded from
-        :func:`Database.get_messages` through
-        :func:`afew.utils.extract_mail_body`.
-
-        This functions accepts the same arguments as
-        :func:`Database.get_messages`.
-
-        :returns: an iterator over :class:`list` of :class:`str`
-        '''
-        query = self.get_messages(*args, **kwargs)
-        for message in query:
-            yield extract_mail_body(message)
-
     def walk_replies(self, message):
         '''
         Returns all replies to the given message.

diff --git a/afew/commands.py b/afew/commands.py
@@ -39,8 +39,7 @@
 # the actions
 action_group = parser.add_argument_group(
     'Actions',
-    'Please specify exactly one action (both update actions can be specified '
-    'simultaneously).'
+    'Please specify exactly one action.'
 )
 action_group.add_argument(
     '-t', '--tag', action='store_true',
@@ -50,24 +49,6 @@
     '-w', '--watch', action='store_true',
     help='continuously monitor the mailbox for new files'
 )
-action_group.add_argument(
-    '-l', '--learn', action='store',
-    help='train the category with the messages matching the given query'
-)
-action_group.add_argument(
-    '-u', '--update', action='store_true',
-    help='update the categories [requires no query]'
-)
-action_group.add_argument(
-    '-U', '--update-reference', action='store_true',
-    help='update the reference category (takes quite some time) [requires no'
-    ' query]'
-)
-action_group.add_argument(
-    '-c', '--classify', action='store_true',
-    help='classify each message matching the given query (to test the trained'
-    ' categories)'
-)
 action_group.add_argument(
     '-m', '--move-mails', action='store_true',
     help='move mail files between maildir folders'
@@ -77,8 +58,6 @@
 query_modifier_group = parser.add_argument_group(
     'Query modifiers',
     'Please specify either --all or --new or a query string.'
-    ' The default query for the update actions is a random selection of'
-    ' REFERENCE_SET_SIZE mails from the last REFERENCE_SET_TIMEFRAME days.'
 )
 query_modifier_group.add_argument(
     '-a', '--all', action='store_true',
@@ -131,23 +110,17 @@ def main():
     no_actions = len(filter_compat(None, (
         args.tag,
         args.watch,
-        args.update or args.update_reference,
-        args.learn,
-        args.classify,
         args.move_mails
     )))
     if no_actions == 0:
         sys.exit('You need to specify an action')
     elif no_actions > 1:
-        sys.exit(
-            'Please specify exactly one action (both update actions can be'
-            ' given at once)')
+        sys.exit('Please specify exactly one action')
 
     no_query_modifiers = len(filter_compat(None, (args.all,
                                                   args.new, args.query)))
-    if no_query_modifiers == 0 and not \
-       (args.update or args.update_reference or args.watch) and not \
-       args.move_mails:
+    if no_query_modifiers == 0 and not args.watch \
+        and not args.move_mails:
         sys.exit('You need to specify one of --new, --all or a query string')
     elif no_query_modifiers > 1:
         sys.exit('Please specify either --all, --new or a query string')
@@ -158,14 +131,8 @@ def main():
         query_string = get_notmuch_new_query()
     elif args.all:
         query_string = ''
-    elif not (args.update or args.update_reference):
-        query_string = ' '.join(args.query)
-    elif args.update or args.update_reference:
-        query_string = '%i..%i' % (
-            time.time() - args.reference_set_timeframe * 24 * 60 * 60,
-            time.time())
     else:
-        sys.exit('Weird... please file a bug containing your command line.')
+        query_string = ' '.join(args.query)
 
     loglevel = {
         0: logging.WARNING,

diff --git a/afew/defaults/afew.config b/afew/defaults/afew.config
@@ -11,7 +11,6 @@
 
 # This is the default filter chain
 #[SpamFilter]
-#[ClassifyingFilter]
 #[KillThreadsFilter]
 #[ListMailsFilter]
 #[ArchiveSentMailsFilter]