Metadata-Version: 1.0
Name: rpatterson.mailsync
Version: 0.4
Summary: Integration between mswatch, OfflineIMAP, and Gnus for realtime mail
Home-page: http://pypi.python.org/pypi/rpatterson.mailsync
Author: Ross Patterson
Author-email: me@rpatterson.net
License: GPL
Description: ===================
        rpatterson.mailsync
        ===================
        
        Integration between mswatch, OfflineIMAP, and Gnus for realtime mail
        
        .. contents::
        
        This package provides some scripts that wrap parts of mswatch and
        OfflineIMAP and integrate with Gnus to provide a local maildir that
        is synchronized with a remote maildir as changes occur, instead of
        polling on a regular basis.  This provides for near instant delivery
        of new mail while also reducing resource utilization.  Integration
        with the Emacs mail and newsreader, Gnus, is also provided in such a
        way that your single threaded Emacs process is blocked much less as
        changes occur to the maildirs.
        
        Requirements
        ============
        
        * `mswatch <http://mswatch.sourceforge.net>`_
        * `OfflineIMAP <http://software.complete.org/software/projects/show/offlineimap>`_
        * `Gnus <http://gnus.org>`_
        
        Actually, they're all kinda optional.  The OfflineIMAP sync wrapper
        script can be used with mswatch without Gnus.  The Gnus checkers can
        be used without OfflineIMAP.  For that matter, the OfflineIMAP sync
        wrapper script can be used without mswatch, but why would you?  :)
        
        Installation
        ============
        
        All you need is easy_install_::
        
        $ easy_install rpatterson.mailsync
        
        The mailsync-gnus.el library will be installed in the site-lisp
        directory in the egg.  To use the library, you'll need to add this
        path to your emacs load-path.  It should be something like the
        following but be sure to substitute the question marks with the
        appropriate values for your version of Python, the version of
        rpatterson.mailsync, and your easy_install site-dirs::
        
        /usr/lib/python?.?/site-packages/rpatterson.mailsync-?-py?.?.egg/site-lisp/
        
        Alternatively, if you have a /usr/local/emacs/site-lisp directory, the
        mailsync-gnus.el library can be installed into that directory if you
        install rpatterson.mailsync from a source distribution.  You can still
        use easy_install to get the source distribution::
        
        $ easy_install --editable --build-directory=/usr/local/src rpatterson.mailsync
        $ cd /usr/local/src/rpatterson.mailsync/
        $ python setup.py install
        
        Once the library is on Emacs' load-path, to use the
        mailsync/gnus-check function, you'll need to make sure it's loaded in
        your Emacs.  You can do this by adding the following to your .gnus.el::
        
        (load-library "mailsync-gnus")
        
        If you'll be using mailsync_offlineimap to synchronize your mail,
        start by configuring OfflineIMAP as per the OfflineIMAP
        documentation.  Once OfflineIMAP is verified working, verify
        mailsync_offlineimap by running it from the console.
        
        On any machine where you'll be using the maildir watchers, either with
        or without mswatch, see the mswatch documentation and verify that
        watch_maildirs works.  Install rpatterson.mailsync wherever you want
        to use mailsync_gnus_watch.  Run it from the console to test it.  It
        should check all groups in Gnus and output a blank line when it's
        started up and then it should check any changed maildir folder groups
        in Gnus when changed and then omit the folder name. Use
        "mailsync_gnus_watch --help" to see what options are available to
        modifying the watcher behavior.
        
        To use mswatch, see the mswatch documentation but base your
        ~/.mswatchrc on the following and see the "MAILSYNC:" comments for
        what to change::
        
        # minimum time after first queued mailbox change to synchronization (default: 10s)
        #base_delay 10
        
        # minimum time between two syncs or failed attempts (default: 60s)
        #inter_delay 60
        
        # minimum time between two syncs or failed attempts for specific lists
        #inter_delay 30 important_list
        #inter_delay 600 high_volume_list another_list
        
        # maximum waiting time between failed attempts (default: 600s)
        #max_delay 600
        
        # program (and arguments) to run to sync the mail stores (required)
        # sync mswatch-sync
        
        # MAILSYNC: use the following to have mswatch use your OfflineIMAP
        # setup to sync folders on change.
        sync mailsync_offlineimap
        
        # prefix this string to sync's mailboxes;
        #     useful as mbsync channel or OfflineIMAP account.
        # the first string ("mydomain") is always prefixed
        # the second string (":") is prefixed only when syncing a particular mailbox
        mailbox_prefix foo :
        
        # a store to watch, call it "local" (required)
        store local
        {
        # program (and args) that will monitor this store for changes (required)
        # see 'man watch_maildirs' to tell watch_maildirs where to find mail
        # watch watch_maildirs
        
        # MAILSYNC: use the following to have your local Gnus check
        # folders as they change, otherwise, just use the above.
        watch mailsync_gnus_watch
        }
        
        # the other store to watch, call it "mydomain" (required)
        store foo.com
        {
        # program (and args) that will monitor this store for changes (required).
        #
        # Uses ssh private/public keys to login without password prompting.
        # Uses ssh BatchMode so that 'mswatch' promptly detects disconnects.
        # Uses 'inputkill' to run 'watch_maildirs' so that 'watch_maildirs'
        # promptly exits if the connection dies.
        # watch ssh -o BatchMode=yes foo.com inputkill watch_maildirs
        
        # MAILSYNC: use the following to have your remote Gnus check
        # folders as they change, otherwise, just use the above.
        watch ssh -o BatchMode=yes foo.com inputkill mailsync_gnus_watch
        }
        
        .. _easy_install: http://peak.telecommunity.com/DevCenter/EasyInstall#installing-easy-install
        
        
        TODO
        ====
        
        * Use optparse for syncers
        
        Add built-in help and clearer option and argument handling for the
        syncers using optparse.
        
        * Use delay in watchers/checkers
        
        Currently, the checkers run every time the watcher emits a folder
        name.  Most maildir changes emit the same folder multiple times
        resulting in the checker running reduntantly.  With mswatch, the
        logic for coalescing events using a delay is in the mswatch process.
        To address this problem, that logic would have to be extended to the
        watchers.  This is another reason among many for reimplementing
        mswatch.
        
        * Invoke OfflineIMAP in the same process
        
        Currently, mailsync invokes OfflineIMAP as a subprocess which is a
        little wasteful given how heavy launching a python app can be.  I
        briefly looked at the OfflineIMAP code to see if it could be easily
        done but was disappointed.
        
        It would be great if any OfflineIMAP people want to show me how I
        can do this.
        
        * Long running syncers
        
        Currently, mswatch invokes the sync process anew every time.  Pretty
        much any sync process establishes one or more network connections.
        There's no need to do this every time.  Better to have a long
        running sync process that mswatch can feed the folders to sync as
        they require syncing.  Implementing this would require modifying or
        reimplementing mswatch itself.  It would also require support in the
        sync process.  Perhaps OfflineIMAP could be used as a library to
        accomplish this.
        
        * Ignore duplicate maildir notifications
        
        As described_ on the mswatch page, every sync is redundantly issued
        twice.  To address this would require modifying or reimplementing
        mswatch itself.
        
        .. _described: http://mswatch.sourceforge.net/#limitations
        
        * maildrop and gnus splitting?
        
        Maybe have maildrop directly invoke Gnus splitting and feed
        incomming messages to be split at time of delivery.  This would
        eliminate redundant syncs on the INBOX where gnus would otherwise
        just immediately move the message into another folder.  This
        approach is, however, probably way to heavy for a maildrop pipeline.
        
        An alternative approach would be to use a maildir (~/Incomming)
        separate from the real INBOX maildir (~/Maildir) where mails would
        first be delivered.  This incomming maildir could be monitored using
        a checker/watcher whose only real purpose is to get gnus to check
        the incomming maildir and split messages.  The split would then move
        the message to the destination or fallback to the real INBOX maildir
        which would in turn trigger any real watchers/checkers used by
        mswatch.
        
        This approach requires no additional mailsync support.  It also
        keeps maildrop job small and light, decoupling the gnus splitting
        work from delivery.
        
        An advantage of either approach is that mail would be split on the
        server even when the local mswatch wasn't connected.  As it is now,
        mail is only split when mswatch is running or if the Gnus running on
        the server checks all mail periodically.
        
        * Use Gamin
        
        Use Gamin to provide compatibility across the file modification
        services available.
        
        
        Changelog
        =========
        
        0.4 - 2009-06-28
        ----------------
        
        * Propogate non-zero return codes from subprocesses so that mswatch
        can know to restart things.
        
        * Don't check if the sync fails, allows mswatch to keep trying to sync
        when offline without constantly making the checkers run
        
        * Add another syncer for offlineimap with a local-only gnus checker
        
        * Translate Gmail and Gnus IMAP folder separators
        
        
        0.3 - 2008-05-13
        ----------------
        
        * Clarify and correct documentation
        
        0.2 - 2008-05-07
        ----------------
        
        * Fix handling of site-lisp for easy_install
        
        0.1 - 2008-05-01
        ----------------
        
        * Initial release
        
        0.0 - Backstory
        ---------------
        
        It is amazing that `MUAs do indeed still suck`_.  In my case this is
        exacerbated by a strong preference to use Gnus as my MUA.  Thunderbird
        may be great, but since it lacks good integration with Emacs (and no,
        emacsclient external editor is not enoug), it really doesn't matter.
        
        I began by using nnimap to access dovecot on my server.  I was still a
        Gnus newbie at that time and I ran into many problems with nnimap.  I
        tried using the Gnus agent to address these but then my head and my
        Emacs exploded in unison.
        
        As many others have before, I moved on to sync the ~/Maildir on my
        server with a full local copy using OfflineIMAP.  Then I setup gnus on
        my laptop to use nnimap talking to Dovecot running locally on my
        laptop.  This worked fabulously with one exception, I had to choose
        between how quickly new mail would show up and how much bandwidth
        OfflineIMAP would use.  I'm pretty impatient about my email, so with a
        sync frequency of every minute, I found that OfflineIMAP could easily
        saturate what little bandwidth was available at a cafe or somesuch.
        Lengthening the frequency only improved things slightly since every 5
        minutes or what have you, my web browsing would still slow to a crawl.
        I assume I was also slowing down everyone else, please don't tell
        them.  Still I used this approach for a year or more since I could
        think of nothing better.
        
        Time went on and I used more and more of Gnus' features.  I have a
        beautiful BBDB fancy splitting setup.  I use automatic scoring which
        is just a delight.  I agree that Gnus is much too hard to learn and
        configure, but in all honesty, it could be even harder and I'd still
        use Gnus.
        
        Later, with much more Gnus experience under my belt, I blew away my
        .emacs and .gnus.el determined to use nnimap and the agent now that I
        was more proficient.  I set it all up and it all seemed to work but as
        time went on I kept running into more and more problems.  Over and
        over again, the Group buffer would show inaccurate counts of new
        messages or not show new messages at all.  I'd find that articles
        hadn't been downloaded after all so I wasn't able to read them
        offline.  I came to resemble a Skinarian pigeon, genuflecting before
        Gnus in the face of chaos with mysterious combinations of "C-u g" and
        "M-x gnus-agent-regenerate".  In addition to those and many other
        small annoyances, there was still the bandwidth vs check frequency
        issue, only this time every time the mail would be checked my emacs
        would block as well.
        
        Then I learned about IMAP IDLE and was beside myself with excitement.
        Then I learned that neither OfflineIMAP nor Gnus nnimap supported it
        and that Thunderbird did and I found myself seriously considering
        switching.  Reluctance to leave Gnus, however, kept me googling for
        some time and eventually I found mswatch.  Really a trio of three
        utilities, mswatch uses Linux's file modification notification system
        (inotify or dnotify) to synchronize maildirs as needed.
        
        Initially, I tried mswatch with its intended sync program, mbsync, but
        mbsync cannot sync nested IMAP folders.  The author of mswatch was
        kind enough to document clearly the interfaces used for the separate
        processes, so I set about writing a script that wraps OfflineIMAP to
        provide the mswatch interface.  For the first time, I finally had a
        mail setup that delivered new mail quickly and didn't consume obscene
        amounts of bandwidth.
        
        But wait, I use Gnus splitting with BBDB, so whenever mail arrived in
        the INBOX on my server, it would be synced to my laptop which Gnus
        would then split into its destination and then it would be synced back
        to the server.  This little dance doubles the bandwidth consumption.
        Furthermore, I've always wanted my BBDB splitting to be done on my
        server for those times when I use Gnus in an SSH session or when I
        access my mail from another IMAP client.  So I also wanted to notify
        my gnus runnong on my server when when mail arrived.
        
        So then I set about writing a checker script that wraps the mswatch's
        watcher processes and uses "emacsclient --eval" to tell Gnus to check
        the folder where a change has occurred.  On my server, this means the
        mail will be split before notifying the mswatch process that a change
        has occurred which means that mswatch will also synchronize the folder
        the message was moved to.  No more round trip.  This also has the
        added benefit of keeping Gnus up to date on all of my mail folders
        without having to use gnus-demon to periodically check all folders.
        All in all, *much* faster, very current information, and much less
        interruptions.
        
        There are many things about this solution that are hackish and
        inefficient so I'd say it's somewhere between %75 and %80 there, as it
        were.  Given, however, that no previous solution has even broken %50
        I'm happy as a clam for now.
        
        .. _`MUAs do indeed still suck`: http://groups.google.com/group/linux.debian.user/msg/7594165a2b6d1c49
        
Platform: UNKNOWN
Classifier: Programming Language :: Python
Classifier: Topic :: Software Development :: Libraries :: Python Modules
