#!/usr/bin/perl # # Robin Whittle 15 July 2001. Copyright Public Domain. Tab = 4 columns. # # Reads a directory full of Mbox format mailboxes and creates a set of # Maildir format mailboxes. Some details of this are to suit Courier # IMAP's naming conventions for Maildir mailboxes. # # http://www.inter7.com/courierimap/ # # This is intended to automate the conversion of the old # /var/spool/mail/blah file - with one call of this script - and to # convert one or more mailboxes in a specifed directory with separate # calls with other command line arguments. # # Run this as the user - in these examples "blah". # # Tested on RedHat 7.1 Perl 5.6.0 # # This script's web abode is http://www.firstpr.com.au/web-mail/ . # # I knew nothing of Perl before I wrote this. I used the man and FAQ pages # at http://www.perldoc.com and a chapter preview from http://www.cgi-perl.com. # # The Mbox -> Maildir inner loop is from qmail's script mbox2maildir, which # was kludged by Ivan Kohler in 1997 from convertandcreate (public domain) # by Russel Nelson. Both these convert a single mailspool file. # # The qmail distribution has a maildir2mbox.c program. # # # ----------------------------------------------------------------------------- # # # mb2md MBROOT MBDIR [DEST] # # # MBROOT Directory, relative to the user's home directory, # which is where the the MBDIR directory is located. # # # MBDIR Directory, relative to MBROOT where the Mbox files # are. There are two special cases: # # 1 - "None" # # 2 - "Inbox" # # If it is set to "None" then mailboxes in the MBROOT # directory will be converted and placed in the # DEST directory. (Typically the Inbox directory # which in this instance is also functioning as a # folder for other mailboxes.) # # If this is set to "Inbox" then the source will # be the single mailbox at /var/spool/mail/blah for # user blah and the destination mailbox will be the # DEST mailbox itself. # # Except in this "Inbox" case, the MBDIR directory # name will be encoded into the new mailboxes' names. # See the examples below. # # This script will not work with maibox files which # contain spaces in their names. # # Expect trouble if an files in MBDIR directory # are not proper Mbox mailbox files. # # This does not save an UW IMAP dummy message file # at the start of the Mbox file. Small changes # in the code could adapt it for looking for # other distinctive patterns of dummy messages too. # # Don't let the source directory you give as MBDIR # contain any "."s in its name, unless you want to # create subfolders from the IMAP user's point of # view. See the example below. # # # DEST Directory relative to user's home directory where the # Maildir format directories will be created. # If not given, then the destination will be ~/Maildir . # Typically, this is what the IMAP server sees as the # Inbox and the folder for all user mailboxes. # # # # Example # ======= # # We have a bunch of directories of Mbox mailboxes located at # /home/blah/oldmail/ # # /home/blah/oldmail/fffff # /home/blah/oldmail/ggggg # /home/blah/oldmail/xxx/aaaa # /home/blah/oldmail/xxx/bbbb # /home/blah/oldmail/xxx/cccc # /home/blah/oldmail/xxx/dddd # /home/blah/oldmail/yyyy/huey # /home/blah/oldmail/yyyy/duey # /home/blah/oldmail/yyyy/louie # # With the UW IMAP server, fffff and ggggg would have appeared in the root # of this mail server, along with the Inbox. aaaa, bbbb etc, would have # appeared in a folder called xxx from that root, and xxx was just a folder # not a mailbox for storing messages. # # We also have the mailspool Inbox at: # # /var/spool/mail/blah # # # To convert these, as user blah, we give the first command: # # mb2md xyz Inbox # # In this case, the first argument is irrelevant - "xyz" is ignored. # # The main Maildir directory will be created if it does not exist. # (This is true of any argument options, not just MBDIR = "Inbox".) # # /home/blah/Maildir/ # # It has the following subdirectories: # # /home/blah/Maildir/tmp/ # /home/blah/Maildir/new/ # /home/blah/Maildir/cur/ # # Then /var/spool/blah file is read, split into individual files and # written into /home/blah/Maildir/new/ . # # Now we give the second command: # # mb2md oldmail None # # This reads the fffff and ggggg Mbox mailboxes and creates: # # /home/blah/Maildir/.fffff/ # /home/blah/Maildir/.ggggg/ # # Now we give the third command: # # mb2md oldmail xxx # # Then all the mailboxes: # # /home/blah/oldmail/xxx/aaaa # /home/blah/oldmail/xxx/bbbb # /home/blah/oldmail/xxx/cccc # /home/blah/oldmail/xxx/dddd # # are converted into Maildir format mailboxes in the following # directories: # # /home/blah/Maildir/.xxx.aaaa/ # /home/blah/Maildir/.xxx.bbbb/ # /home/blah/Maildir/.xxx.cccc/ # /home/blah/Maildir/.xxx.aaaa/ # # This suits Courier IMAP fine, and these will appear to the IMAP # client as four mailboxes in the folder "xxx" within the Inbox # folder. # # The final command: # # mb2md oldmail yyyy # # does the rest. The result, from the IMAP client's point of view is: # # Inbox ----------------- # | # | fffff ----------- # | ggggg ----------- # | # - xxx # | | aaaa -------- # | | bbbb -------- # | | cccc -------- # | | dddd -------- # | # - yyyy # | huey ------- # | duey ------- # | louie ------ # # Note that although ~/Maildir/.xxx/ and ~/Maildir/.yyyy may appear # as folders to the IMAP client the above commands to not generate # any Maildir folders of these names. These are simply elements # of the names of other Maildir directories. # # With a separate run of this script, using the MBDIR = "None" # approach, it would be possible to create mailboxes which # appear at the same location as far as the IMAP client is # concerned. By having Mbox mailboxes in some directory: # ~/oldmail/nnn/ of the form: # # /home/blah/oldmail/nn/xxxx # /home/blah/oldmail/nn/yyyyy # # then the command: # # mb2md oldmail/nn None # # will create two new Maildirs: # # /home/blah/Maildir/.xxx/ # /home/blah/Maildir/.yyyy/ # # Then what used to be the xxx and yyyy folders now function as # mailboxes too. Netscape 4.77 needed to be put to sleep and given ECT # to recognise this - deleting the contents of (Win2k example): # # C:\Program Files\Netscape\Users\uu\ImapMail\aaa.bbb.ccc\ # # where "uu" is the user and "aaa.bbb.ccc" is the IMAP server # # I often find that deleting all this directory's contents, except # "rules.dat", forces Netscape back to reality after its IMAP innards # have become twisted. Then maybe use File > Subscribe - but this # seems incapable of subscribing to folders. # # For Outlook Express, select the mail server, then click the # "IMAP Folders" button and use "Reset list". In the "All" # window, select the mailboxes you want to see in normal # usage. # # # This script does not recurse subdirectories or delete old mailboxes. # # Be sure not to be accessing the Mbox mailboxes while running this # script. It does not attempt to lock them. Likewise, don't run two # copies of this script either. # # # Trickier usage . . . # ==================== # # If you have a bunch of mailboxes in a directory ~/oldmail/doors/ # and you want them to appear in folders such as: # # ~/Maildir/.music.bands.doors.Jim # ~/Maildir/.music.bands.doors.John # # etc. so they appear in an IMAP folder: # # Inbox ----------------- # | music # | bands # | doors # | Jim # | John # | Robbie # | Ray # # Then you should rename the source directory to: # # ~/oldmail/music.bands.doors/ # # then you can use: # # mb2md oldmail music.bands.doors # #------------------------------------------------------------------------------ require 'stat.pl'; # Get user ID and check home dir # exists. ($name, $passwd, $uid, $gid, $quota, $comment, $gcos, $dir, $shell) = getpwuid($<); -e $dir or die("Fatal: home dir $dir doesn't exist.\n") ; &Stat($dir); if ($uid != $st_uid) {die("Fatal: $name is $uid, but $dir is owned by $st_uid.\n");} # Dead wood, since we are not using # the current directory setting. chdir($dir) or die "Fatal: unable to chdir to $dir.\n"; # Get arguments and determine source # and target directories. # # Spit dummy if we don't have 2 or 3 # arguments. Perl args start at 0. if ( !($ARGV[1]) || ($ARGV[3]) ) { die("There should be 2 or 3 args. Read the script for full doco!\n"); } # Get the 2 or 3 arguments #------------------------- # eg. mbroot = oldmail # # Spit dummy if this directory does not # exist, except for if MBDIR is "Inbox", # in which case MBROOT is ignored. # So get the MBDIR argument, before # testing whether MBROOT exists. $mbroot = $ARGV[0]; # eg. mbdir = xxx # # Check the directory we want exists # after we have done the substitions # for "None" and "Inbox". $mbdir = $ARGV[1]; # Handle the third argument, if any. if ($ARGV[2]) {$dest = $ARGV[2];} else {$dest = "Maildir";} printf("MBROOT: $mbroot MBDIR: $mbdir DEST: $dest \n"); # Handle the arguments #--------------------- # # First, we set the $target string - # the mailspool directory where the # mails or mailboxes will be written. # We make sure it exists, or we # create it. # # Create the full path name of # the target directory, eg.: # /home/blah/Maildir/ $target = "$dir/$dest" ; # A debug line - we report this later. # printf("Target directory is $target/\n"); # If the directory doesn't exist, # make it. -d $target or mkdir $target,0700 or die("Fatal: Directory $target doesn't exist and can't be created.\n"); -d "$target/tmp" or mkdir("$target/tmp",0700) or die("Fatal: Unable to make $target/tmp/ subdirectory.\n"); -d "$target/new" or mkdir("$target/new",0700) or die("Fatal: Unable to make $target/new/ subdirectory.\n"); -d "$target/cur" or mkdir("$target/cur",0700) or die("Fatal: Unable to make $target/cur/ subdirectory.\n"); # Except for the MBDIR == "Inbox" case # check to see that the directory # specifed in MBDIR exists. if ($mbdir ne "Inbox") { -d "$dir/$mbroot" or die("Fatal: MBROOT directory $dir/$mbroot/ does not exist.\n"); -d "$dir/$mbroot" or die("Fatal: MBROOT $dir/$mbroot is not a directory.\n"); } # Depending on the three possible # modes of setting MBDIR, check that # the input directories (or mailspool # file) exists. # # Also set the $tfile variable. This # will form part of the name of # the mailbox we create (except for # when MBDIR is "Inbox". # # Create the full path source # directory. This is where we will # find the Mbox mailbox files. # We will add the trailing / when # we use it. # # Normally it will be, for example, # # /home/blah/oldmail/xxx # # but if mbdir == None, then it # will be: # # /home/blah/oldmail # # and if mbdir == Inbox, then it # will be: # # /var/spool/mail if ($mbdir eq "None") { $sourcedir = "$dir/$mbroot"; # No check needed - we have already # checked this exists. # # $tfile will be "." because there # is no directory component in the # names of the new mailboxes - their # names will come from the names # of the Mbox files. eg. # # .fffff/ $tfile = "."; } elsif ($mbdir eq "Inbox") { $sourcedir = "/var/spool/mail"; # Check the mailspool directory exists # and then check this user's file # exists. -e "$sourcedir" or die("Fatal: MBDIR = Inbox but directory $sourcedir/ does not exist.\n"); -d "$sourcedir" or die("Fatal: MBDIR = Inbox but $sourcedir is not a directory.\n"); -e "$sourcedir/$name" or die("Fatal: MBDIR = Inbox but $sourcedir/$name mailspool file does not exist.\n"); if (-d "$sourcedir/$name") {die("Fatal: MBDIR = Inbox but $sourcedir/$name is a directory.\n");} # $tfile will be "", because we are # putting it straight in # /home/blah/Maildir/ $tfile = ""; } else { $sourcedir = "$dir/$mbroot/$mbdir"; # This is the usual case, for instance # /home/blah/oldmail/xxx -e "$sourcedir" or die("Fatal: MBDIR directory $sourcedir/ does not exist.\n"); -d "$sourcedir" or die("Fatal: MBDIR $sourcedir is not a directory.\n"); # $tfile will be ".$mbdir". eg. # # .xxx. # # and we will add the rest of the # mailbox name as convert each # mailbox. eg. # # .xxx.aaa/ $tfile = ".$mbdir."; } # More debug lines. printf("\nSource directory: $sourcedir/ \n"); if ($mbdir eq "Inbox") { printf("Target mailbox: $target/ \n\n\n"); } else { printf("Target mailboxes: $target/$tfile??????? \n\n\n"); } # Outer Loop #----------- # # Now we have a loop which looks for # any file in the $sourcedir directory # and turns it into a Maildir mailbox. # We assume all files are Mbox # mailboxes. # # In one case, when $mbdir is "Inbox" # then the loop must work only once, # to find the user's mailspool file. # # readir() gets file/directory names # from a directory previously opened # with opendir(). We should close it # afterwards too. # # SDIR is a file handle. # # We ignore what we find if it is a # directory. There will be # directories, such as "." and ".." # at least. # # This test must be done inside the # while loop, not part of the # condition of the loop. # # I use -d to test for it being # a directory. # # All these -d and -T thingos are # in /func/X.html at perldoc.com. opendir(SDIR, $sourcedir) or die("Fatal: Cannot open source directory $sourcedir/ \n"); # Count the number of mailboxes, or # at least files, we found. $mailboxcount = 0; while ($sfile = readdir(SDIR)) { # Test firstly that this is a file, # and secondly, if $mbdir is "Inbox" # that it is the user's mailspool # file. if ( (!-d "$sourcedir/$sfile") && ( !($mbdir eq "Inbox") || ($sfile eq $name) ) ) { printf("Found $sourcedir/$sfile\n"); $mailboxcount++; # We have located the file to convert. # # In most cases, we need to create # a new Maildir format mailbox, with # its directory and three # subdirectories and then chdir to # the mailbox directory before # entering the conversion loop. # # But if MBDIR is "Inbox" then # we don't need to make any new # mailboxes, since we are going # to write, for instance, into # # /home/blah/Maildir/new/ # # If MBDIR is "None" then we will # convert into, for instance: # # /home/blah/Maildir/.fffff/new/ # /home/blah/Maildir/.ggggg/new/ # # Any other value for mdir, such as # "xxx" will make the destination # $target/.$mbroot/$tfile$mbdir/new/ # # /home/blah/Maildir/.xxx.aaaa/new/ # /home/blah/Maildir/.xxx.bbbb/new/ if ($mbdir eq "Inbox") { # No mailbox to create, but set # $targetmb appropriately. $targetmb = "$target" ; printf("Target Maildir is $targetmb \n\n") ; } else { # Set the target mailbox and create it. $targetmb = "$target/$tfile$sfile" ; printf("Target Maildir is $targetmb \n") ; -d $targetmb or mkdir $targetmb,0700 or die("Fatal: Directory $targetmb doesn't exist and can't be created.\n"); -d "$targetmb/tmp" or mkdir("$targetmb/tmp",0700) or die("Fatal: Unable to make $targetmb/tmp/ subdirectory.\n"); -d "$targetmb/new" or mkdir("$targetmb/new",0700) or die("Fatal: Unable to make $targetmb/new/ subdirectory.\n"); -d "$targetmb/cur" or mkdir("$targetmb/cur",0700) or die("Fatal: Unable to make $targetmb/cur/ subdirectory.\n"); } # Change to the target mailbox directory. chdir "$targetmb" ; # Inner loop #----------- # # Converts a Mbox to multiple files # in a Maildir. # This is adapted from mbox2maildir. # # Open the Mbox mailbox file. if (open(MBOX, "$sourcedir/$sfile")) { printf("Converting mailbox $sourcedir/$sfile . . . \n"); } else { die("Fatal: unable to open input mailbox file: $sourcedir/sfile ! \n"); } # This loop scans the input mailbox for # a line starting with "From ". The # "^" before it is pattern-matching # lingo for it being at the start of a # line. # # Each email in Mbox mailbox starts # with such a line, which is why any # such line in the body of the email # has to have a ">" put in front of it. # # This is not required in a Maildir # mailbox, and some majik below # finds any such quoted "From"s and # gets rid of the quote. # # Each email is put in a file # in the new/ subdirectory with a # name of the form: # # nnnnnnnnn.mbox # # where nnnnnnnnn is the Unix time # since 1970, incremented by 1 # for every email. # This is sort-of compliant with # the Maildir naming conventions # specified at: # # http://www.qmail.org/man/man5/maildir.html # # There are various IMAP flags which # could be added, and this approach # does not involve the process ID or # the host, but it is probably good # enough. # # When the IMAP server looks at this # mailbox, it will move the files to # the cur/ directory and change their # names as it pleases. In the case # of Courier IMAP, the names will # become like: # # 995096541.25351.mbox:2,S # # with 25351 being Courier IMAP's # process ID. The :2, is the start # of the flags, and the "S" means # that this one has been seen by # the user. # # This contrasts with a message # created by Courier IMAP, say with # a message copy, which is like: # # 995096541.25351.zair,S=14285:2,S # # where ",S=14285" is the size of the # message in bytes. # # Courier Maildrop's names are similar # but lack the ":2,xxx" flags . . . # except for my modified Maildrop # which can deliver them with a # ":2,T" - flagged for deletion. # # I have extened the logic of the # per-message inner loop to stop # saving a file for a message with: # # Subject: DON'T DELETE THIS MESSAGE -- FOLDER INTERNAL DATA # # This is the dummy message, always # at the start of an Mbox format # mailbox file - and is put there # by UW IMAPD. Since quite a few # people will use this for # converting from a UW system, # I figure it is worth it. # # As I am a bit sus about when each # message file is closed, I will have # a bit of a kludge to remember the # first file name we write, if # we determine it was a dummy so # we can delete it at the end of # converting the 1 or more messages # in the mailbox. $deletedummy = ""; $messagecount = 0; $unique = time; while() { if (/^From /) { $messagefn = sprintf("new/%d.$$.mbox", $unique); open(OUT, ">$messagefn") or die("Fatal: unable to create new message"); $unique++; # Count the messages. $messagecount++; next; } # Only for the first message, # check to see if it is a dummy. # # Add search terms as required. # The last 2 lines are for rent. if ( ($messagecount == 1) && ( (m/^Subject: DON'T DELETE THIS MESSAGE -- FOLDER INTERNAL DATA/) || (m/^Subject: Bulwinkle next Pope/) || (m/^Subject: Buy US War Bonds!/) ) ) { $deletedummy = "$messagefn"; } # Pattern matching Perl majik to # get rid of a Mbox quoted From. s/^>From /From /; print OUT or die("Fatal: unable to write to new message"); # So where do the bytes get written # to the file?? } # After all the messages have been # converted, check to see if the # first one was a dummy. # if so, delete it and make # the message count one less. if ($deletedummy ne "") { printf("Dummy mail system first message detected and not saved.\n"); unlink $deletedummy; $messagecount--; } close(MBOX); close(OUT); print(" $messagecount messages.\n\n"); } } closedir(SDIR); #die("So far so good.\n\n"); printf("$mailboxcount files processed.\n"); exit 0;