[code/myrepos.git] / mr

#!/usr/bin/perl

=head1 NAME

mr - a Multiple Repository management tool

=head1 SYNOPSIS

B<mr> [options] checkout

B<mr> [options] update

B<mr> [options] status

B<mr> [options] commit [-m "message"]

B<mr> [options] record [-m "message"]

B<mr> [options] diff

B<mr> [options] log

B<mr> [options] bootstrap url [directory]

B<mr> [options] register [repository]

B<mr> [options] config section ["parameter=[value]" ...]

B<mr> [options] action [params ...]

B<mr> [options] [online|offline]

B<mr> [options] remember action [params ...]

=head1 DESCRIPTION

B<mr> is a Multiple Repository management tool. It can checkout, update, or
perform other actions on a set of repositories as if they were one combined
repository. It supports any combination of subversion, git, cvs, mercurial,
bzr and darcs repositories, and support for other revision control systems can
easily be added.

B<mr> cds into and operates on all registered repositories at or below your
working directory. Or, if you are in a subdirectory of a repository that
contains no other registered repositories, it will stay in that directory,
and work on only that repository,

B<mr> is configured by .mrconfig files, which list the repositories. It
starts by reading the .mrconfig file in your home directory, and this can
in turn chain load .mrconfig files from repositories.

These predefined commands should be fairly familiar to users of any revision
control system:

=over 4

=item checkout (or co)

Checks out any repositories that are not already checked out.

=item update

Updates each repository from its configured remote repository.

If a repository isn't checked out yet, it will first check it out.

=item status

Displays a status report for each repository, showing what
uncommitted changes are present in the repository.

=item commit (or ci)

Commits changes to each repository. (By default, changes are pushed to the
remote repository too, when using distributed systems like git. If you
don't like this default, you can change it in your .mrconfig, or use record
instead.)

The optional -m parameter allows specifying a commit message.

=item record

Records changes to the local repository, but does not push them to the
remote repository. Only supported for distributed revision control systems.

The optional -m parameter allows specifying a commit message.

=item push

Pushes committed local changes to the remote repository. A no-op for
centralized revision control systems.

=item diff

Show a diff of uncommitted changes.

=item log

Show the commit log.

=back

These commands are also available:

=over 4

=item bootstrap url [directory]

Causes mr to download the url, and use it as a .mrconfig file
to checkout the repositories listed in it, into the specified directory.

The directory will be created if it does not exist. If no directory is
specified, the current directory will be used.

If the .mrconfig file includes a repository named ".", that
is checked out into the top of the specified directory.

=item list (or ls)

List the repositories that mr will act on.

=item register

Register an existing repository in a mrconfig file. By default, the
repository in the current directory is registered, or you can specify a
directory to register.

The mrconfig file that is modified is chosen by either the -c option, or by
looking for the closest known one at or below the current directory.

=item config

Adds, modifies, removes, or prints a value from a mrconfig file. The next
parameter is the name of the section the value is in. To add or modify
values, use one or more instances of "parameter=value". Use "parameter=" to
remove a parameter. Use just "parameter" to get the value of a parameter.

For example, to add (or edit) a repository in src/foo:

  mr config src/foo checkout="svn co svn://example.com/foo/trunk foo"

To show the command that mr uses to update the repository in src/foo:

  mr config src/foo update

To see the built-in library of shell functions contained in mr:

  mr config DEFAULT lib

The ~/.mrconfig file is used by default. To use a different config file,
use the -c option.

=item offline

Advises mr that it is in offline mode. Any commands that fail in
offline mode will be remembered, and retried when mr is told it's online.

=item online

Advices mr that it is in online mode again. Commands that failed while in
offline mode will be re-run.

=item remember

Remember a command, to be run later when mr re-enters online mode. This
implicitly puts mr into offline mode. The command can be any regular mr
command. This is useful when you know that a command will fail due to being
offline, and so don't want to run it right now at all, but just remember
to run it when you go back online.

=item help

Displays this help.

=back

Actions can be abbreviated to any unambiguous substring, so
"mr st" is equivalent to "mr status", and "mr up" is equivalent to "mr
update"

Additional parameters can be passed to most commands, and are passed on
unchanged to the underlying revision control system. This is mostly useful
if the repositories mr will act on all use the same revision control
system.

=head1 OPTIONS

=over 4

=item -d directory

=item --directory directory

Specifies the topmost directory that B<mr> should work in. The default is
the current working directory.

=item -c mrconfig

=item --config mrconfig

Use the specified mrconfig file. The default is B<~/.mrconfig>

=item -p

=item --path

Search in the current directory, and its parent directories and use
the first B<.mrconfig> found, instead of the default B<~/.mrconfig>.

=item -v

=item --verbose

Be verbose.

=item -q

=item --quiet

Be quiet.

=item -s

=item --stats

Expand the statistics line displayed at the end to include information
about exactly which repositories failed and were skipped, if any.

=item -i

=item --interactive

Interactive mode. If a repository fails to be processed, a subshell will be
started which you can use to resolve or investigate the problem. Exit the
subshell to continue the mr run.

=item -n [number]

=item --no-recurse [number]

If no number if specified, just operate on the repository for the current
directory, do not recurse into deeper repositories.

If a number is specified, will recurse into repositories at most that many
subdirectories deep. For example, with -n 2 it would recurse into ./src/foo,
but not ./src/packages/bar.

=item -j [number]

=item --jobs [number]

Run the specified number of jobs in parallel, or an unlimited number of jobs
with no number specified. This can greatly speed up operations such as updates.
It is not recommended for interactive operations.

Note that running more than 10 jobs at a time is likely to run afoul of
ssh connection limits. Running between 3 and 5 jobs at a time will yield
a good speedup in updates without loading the machine too much.

=item -t

=item --trust-all

Trust all mrconfig files even if they are not listed in ~/.mrtrust.
Use with caution.

=back

=head1 "MRCONFIG FILES"

Here is an example .mrconfig file:

  [src]
  checkout = svn co svn://svn.example.com/src/trunk src
  chain = true

  [src/linux-2.6]
  checkout = git clone git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6.git &&
        cd linux-2.6 &&
        git checkout -b mybranch origin/master

The .mrconfig file uses a variant of the INI file format. Lines starting with
"#" are comments. Values can be continued to the following line by
indenting the line with whitespace.

The "DEFAULT" section allows setting default values for the sections that
come after it.

The "ALIAS" section allows adding aliases for actions. Each parameter
is an alias, and its value is the action to use.

All other sections add repositories. The section header specifies the
directory where the repository is located. This is relative to the directory
that contains the mrconfig file, but you can also choose to use absolute
paths. (Note that you can use environment variables in section names; they
will be passed through the shell for expansion. For example, 
"[$HOSTNAME]", or "[${HOSTNAME}foo]")

Within a section, each parameter defines a shell command to run to handle a
given action. mr contains default handlers for "update", "status",
"commit", and other standard actions. Normally you only need to specify what
to do for "checkout".

Note that these shell commands are run in a "set -e" shell
environment, where any additional parameters you pass are available in
"$@". The "checkout" command is run in the parent of the repository
directory, since the repository isn't checked out yet. All other commands
are run inside the repository, though not necessarily at the top of it.

The "MR_REPO" environment variable is set to the path to the top of the
repository. (For the "register" action, "MR_REPO" is instead set to the 
basename of the directory that should be created when checking the
repository out.)

The "MR_CONFIG" environment variable is set to the .mrconfig file
that defines the repo being acted on, or, if the repo is not yet in a config
file, the .mrconfig file that should be modified to register the repo.

A few parameters have special meanings:

=over 4

=item skip

If the "skip" parameter is set and its command returns true, then B<mr>
will skip acting on that repository. The command is passed the action
name in $1.

Here are two examples. The first skips the repo unless
mr is run by joey. The second uses the hours_since function
(included in mr's built-in library) to skip updating the repo unless it's
been at least 12 hours since the last update.

  skip = test `whoami` != joey
  skip = [ "$1" = update ] && ! hours_since "$1" 12

=item order

The "order" parameter can be used to override the default ordering of
repositories. The default order value is 10. Use smaller values to make
repositories be processed earlier, and larger values to make repositories
be processed later.

Note that if a repository is located in a subdirectory of another
repository, ordering it to be processed earlier is not recommended.

=item chain

If the "chain" parameter is set and its command returns true, then B<mr>
will try to load a .mrconfig file from the root of the repository.

=item include

If the "include" parameter is set, its command is ran, and should output
additional mrconfig file content. The content is included as if it were
part of the including file.

Unlike all other parameters, this parameter does not need to be placed
within a section.

=item lib

The "lib" parameter can specify some shell code that will be run before each
command, this can be a useful way to define shell functions for other commands
to use.

=back

When looking for a command to run for a given action, mr first looks for
a parameter with the same name as the action. If that is not found, it
looks for a parameter named "rcs_action" (substituting in the name of the
revision control system and the action). The name of the revision control
system is itself determined by running each defined "rcs_test" action,
until one succeeds.

Internally, mr has settings for "git_update", "svn_update", etc. To change
the action that is performed for a given revision control system, you can
override these rcs specific actions. To add a new revision control system,
you can just add rcs specific actions for it.

The ~/.mrlog file contains commands that mr has remembered to run later,
due to being offline. You can delete or edit this file to remove commands,
or even to add other commands for 'mr online' to run. If the file is
present, mr assumes it is in offline mode.

=head "UNTRUSTED MRCONFIG FILES"

Since mrconfig files can contain arbitrary shell commands, they can do
anything. This flexability is good, but it also allows a malicious mrconfig
file to delete your whole home directory. Such a file might be contained
inside a repository that your main ~/.mrconfig checks out and chains to. To
avoid worries about evil commands in a mrconfig file, mr
has the ability to read mrconfig files in untrusted mode. Such files are
limited to running only known safe commands (like "git clone") in a
carefully checked manner.

By default, mr trusts all mrconfig files. (This default will change in a
future release!) But if you have a ~/.mrtrust file, mr will only trust
mrconfig files that are listed within it. (One file per line.) All other
files will be treated as untrusted.

=head1 EXTENSIONS

mr can be extended to support things such as unison and git-svn. Some
files providing such extensions are available in /usr/share/mr/. See
the documentation in the files for details about using them.

=head1 AUTHOR

Copyright 2007-2009 Joey Hess <joey@kitenet.net>

Licensed under the GNU GPL version 2 or higher.

http://kitenet.net/~joey/code/mr/

=cut

use warnings;
use strict;
use Getopt::Long;
use Cwd qw(getcwd abs_path);

# things that can happen when mr runs a command
use constant {
        OK => 0,
        FAILED => 1,
        SKIPPED => 2,
        ABORT => 3,
};

# configurables
my $config_overridden=0;
my $verbose=0;
my $quiet=0;
my $stats=0;
my $interactive=0;
my $max_depth;
my $no_chdir=0;
my $jobs=1;
my $trust_all=0;
my $directory=getcwd();
$ENV{MR_CONFIG}="$ENV{HOME}/.mrconfig";

# globals :-(
my %config;
my %configfiles;
my %knownactions;
my %alias;
my (@ok, @failed, @skipped);

main();

my %rcs;
sub rcs_test {
        my ($action, $dir, $topdir, $subdir) = @_;

        if (exists $rcs{$dir}) {
                return $rcs{$dir};
        }

        my $test="set -e\n";
        foreach my $rcs_test (
                        sort {
                                length $a <=> length $b 
                                          ||
                                       $a cmp $b
                        } grep { /_test$/ } keys %{$config{$topdir}{$subdir}}) {
                my ($rcs)=$rcs_test=~/(.*)_test/;
                $test="my_$rcs_test() {\n$config{$topdir}{$subdir}{$rcs_test}\n}\n".$test;
                $test.="if my_$rcs_test; then echo $rcs; fi\n";
        }
        $test=$config{$topdir}{$subdir}{lib}."\n".$test
                if exists $config{$topdir}{$subdir}{lib};
        
        print "mr $action: running rcs test >>$test<<\n" if $verbose;
        my $rcs=`$test`;
        chomp $rcs;
        if ($rcs=~/\n/s) {
                $rcs=~s/\n/, /g;
                print STDERR "mr $action: found multiple possible repository types ($rcs) for $topdir$subdir\n";
                return undef;
        }
        if (! length $rcs) {
                return $rcs{$dir}=undef;
        }
        else {
                return $rcs{$dir}=$rcs;
        }
}
        
sub findcommand {
        my ($action, $dir, $topdir, $subdir, $is_checkout) = @_;
        
        if (exists $config{$topdir}{$subdir}{$action}) {
                return $config{$topdir}{$subdir}{$action};
        }

        if ($is_checkout) {
                return undef;
        }

        my $rcs=rcs_test(@_);

        if (defined $rcs && 
            exists $config{$topdir}{$subdir}{$rcs."_".$action}) {
                return $config{$topdir}{$subdir}{$rcs."_".$action};
        }
        else {
                return undef;
        }
}

sub action {
        my ($action, $dir, $topdir, $subdir, $force_checkout) = @_;
        
        $ENV{MR_CONFIG}=$configfiles{$topdir};
        my $lib=exists $config{$topdir}{$subdir}{lib} ?
                       $config{$topdir}{$subdir}{lib}."\n" : "";
        my $is_checkout=($action eq 'checkout');

        $ENV{MR_REPO}=$dir;

        if ($is_checkout) {
                if (! $force_checkout) {
                        if (-d $dir) {
                                print "mr $action: $dir already exists, skipping checkout\n" if $verbose;
                                return SKIPPED;
                        }
        
                        $dir=~s/^(.*)\/[^\/]+\/?$/$1/;
                }
        }
        elsif ($action =~ /update/) {
                if (! -d $dir) {
                        return action("checkout", $dir, $topdir, $subdir);
                }
        }

        my $skiptest=findcommand("skip", $dir, $topdir, $subdir, $is_checkout);
        my $command=findcommand($action, $dir, $topdir, $subdir, $is_checkout);

        if (defined $skiptest) {
                my $test="set -e;".$lib.
                        "my_action(){ $skiptest\n }; my_action '$action'";
                print "mr $action: running skip test >>$test<<\n" if $verbose;
                my $ret=system($test);
                if ($ret != 0) {
                        if (($? & 127) == 2) {
                                print STDERR "mr $action: interrupted\n";
                                return ABORT;
                        }
                        elsif ($? & 127) {
                                print STDERR "mr $action: skip test received signal ".($? & 127)."\n";
                                return ABORT;
                        }
                }
                if ($ret >> 8 == 0) {
                        print "mr $action: $dir skipped per config file\n" if $verbose;
                        return SKIPPED;
                }
        }

        if ($is_checkout && ! -d $dir) {
                print "mr $action: creating parent directory $dir\n" if $verbose;
                system("mkdir", "-p", $dir);
        }

        if (! $no_chdir && ! chdir($dir)) {
                print STDERR "mr $action: failed to chdir to $dir: $!\n";
                return FAILED;
        }
        elsif (! defined $command) {
                my $rcs=rcs_test(@_);
                if (! defined $rcs) {
                        print STDERR "mr $action: unknown repository type and no defined $action command for $topdir$subdir\n";
                        return FAILED;
                }
                else {
                        print STDERR "mr $action: no defined action for $rcs repository $topdir$subdir, skipping\n";
                        return SKIPPED;
                }
        }
        else {
                if (! $no_chdir) {
                        print "mr $action: $topdir$subdir\n" unless $quiet;
                }
                else {
                        my $s=$directory;
                        $s=~s/^\Q$topdir$subdir\E\/?//;
                        print "mr $action: $topdir$subdir (in subdir $s)\n" unless $quiet;
                }
                $command="set -e; ".$lib.
                        "my_action(){ $command\n }; my_action ".
                        join(" ", map { s/\//\/\//g; s/"/\"/g; '"'.$_.'"' } @ARGV);
                print "mr $action: running >>$command<<\n" if $verbose;
                my $ret=system($command);
                if ($ret != 0) {
                        if (($? & 127) == 2) {
                                print STDERR "mr $action: interrupted\n";
                                return ABORT;
                        }
                        elsif ($? & 127) {
                                print STDERR "mr $action: received signal ".($? & 127)."\n";
                                return ABORT;
                        }
                        print STDERR "mr $action: failed ($ret)\n" if $verbose;
                        if ($ret >> 8 != 0) {
                                print STDERR "mr $action: command failed\n";
                                if (-e "$ENV{HOME}/.mrlog" && $action ne 'remember') {
                                        # recreate original command line to
                                        # remember, and avoid recursing
                                        my @orig=@ARGV;
                                        @ARGV=('-n', $action, @orig);
                                        action("remember", $dir, $topdir, $subdir);
                                        @ARGV=@orig;
                                }
                        }
                        elsif ($ret != 0) {
                                print STDERR "mr $action: command died ($ret)\n";
                        }
                        return FAILED;
                }
                else {
                        if ($action eq 'checkout' && ! -d $dir) {
                                print STDERR "mr $action: $dir missing after checkout\n";;
                                return FAILED;
                        }

                        return OK;
                }
        }
}

# run actions on multiple repos, in parallel
sub mrs {
        my $action=shift;
        my @repos=@_;

        $| = 1;
        my @active;
        my @fhs;
        my @out;
        my $running=0;
        while (@fhs or @repos) {
                while ((!$jobs || $running < $jobs) && @repos) {
                        $running++;
                        my $repo = shift @repos;
                        pipe(my $outfh, CHILD_STDOUT);
                        pipe(my $errfh, CHILD_STDERR);
                        my $pid;
                        unless ($pid = fork) {
                                die "mr $action: cannot fork: $!" unless defined $pid;
                                open(STDOUT, ">&CHILD_STDOUT") || die "mr $action cannot reopen stdout: $!";
                                open(STDERR, ">&CHILD_STDERR") || die "mr $action cannot reopen stderr: $!";
                                close CHILD_STDOUT;
                                close CHILD_STDERR;
                                close $outfh;
                                close $errfh;
                                exit action($action, @$repo);
                        }
                        close CHILD_STDOUT;
                        close CHILD_STDERR;
                        push @active, [$pid, $repo];
                        push @fhs, [$outfh, $errfh];
                        push @out, ['',     ''];
                }
                my ($rin, $rout) = ('','');
                my $nfound;
                foreach my $fh (@fhs) {
                        next unless defined $fh;
                        vec($rin, fileno($fh->[0]), 1) = 1 if defined $fh->[0];
                        vec($rin, fileno($fh->[1]), 1) = 1 if defined $fh->[1];
                }
                $nfound = select($rout=$rin, undef, undef, 1);
                foreach my $channel (0, 1) {
                        foreach my $i (0..$#fhs) {
                                next unless defined $fhs[$i];
                                my $fh = $fhs[$i][$channel];
                                next unless defined $fh;
                                if (vec($rout, fileno($fh), 1) == 1) {
                                        my $r = '';
                                        if (sysread($fh, $r, 1024) == 0) {
                                                close($fh);
                                                $fhs[$i][$channel] = undef;
                                                if (! defined $fhs[$i][0] &&
                                                    ! defined $fhs[$i][1]) {
                                                        waitpid($active[$i][0], 0);
                                                        print STDOUT $out[$i][0];
                                                        print STDERR $out[$i][1];
                                                        record($active[$i][1], $? >> 8);
                                                        splice(@fhs, $i, 1);
                                                        splice(@active, $i, 1);
                                                        splice(@out, $i, 1);
                                                        $running--;
                                                }
                                        }
                                        $out[$i][$channel] .= $r;
                                }
                        }
                }
        }
}

sub record {
        my $dir=shift()->[0];
        my $ret=shift;

        if ($ret == OK) {
                push @ok, $dir;
                print "\n";
        }
        elsif ($ret == FAILED) {
                if ($interactive) {
                        chdir($dir) unless $no_chdir;
                        print STDERR "mr: Starting interactive shell. Exit shell to continue.\n";
                        system((getpwuid($<))[8], "-i");
                }
                push @failed, $dir;
                print "\n";
        }
        elsif ($ret == SKIPPED) {
                push @skipped, $dir;
        }
        elsif ($ret == ABORT) {
                exit 1;
        }
        else {
                die "unknown exit status $ret";
        }
}

sub showstats {
        my $action=shift;
        if (! @ok && ! @failed && ! @skipped) {
                die "mr $action: no repositories found to work on\n";
        }
        print "mr $action: finished (".join("; ",
                showstat($#ok+1, "ok", "ok"),
                showstat($#failed+1, "failed", "failed"),
                showstat($#skipped+1, "skipped", "skipped"),
        ).")\n" unless $quiet;
        if ($stats) {
                if (@skipped) {
                        print "mr $action: (skipped: ".join(" ", @skipped).")\n" unless $quiet;
                }
                if (@failed) {
                        print STDERR "mr $action: (failed: ".join(" ", @failed).")\n";
                }
        }
}

sub showstat {
        my $count=shift;
        my $singular=shift;
        my $plural=shift;
        if ($count) {
                return "$count ".($count > 1 ? $plural : $singular);
        }
        return;
}

# an ordered list of repos
sub repolist {
        my @list;
        foreach my $topdir (sort keys %config) {
                foreach my $subdir (sort keys %{$config{$topdir}}) {
                        push @list, {
                                topdir => $topdir,
                                subdir => $subdir,
                                order => $config{$topdir}{$subdir}{order},
                        };
                }
        }
        return sort {
                $a->{order}  <=> $b->{order}
                             ||
                $a->{topdir} cmp $b->{topdir}
                             ||
                $a->{subdir} cmp $b->{subdir}
        } @list;
}

# figure out which repos to act on
sub selectrepos {
        my @repos;
        foreach my $repo (repolist()) {
                my $topdir=$repo->{topdir};
                my $subdir=$repo->{subdir};

                next if $subdir eq 'DEFAULT';
                my $dir=($subdir =~/^\//) ? $subdir : $topdir.$subdir;
                my $d=$directory;
                $dir.="/" unless $dir=~/\/$/;
                $d.="/" unless $d=~/\/$/;
                next if $dir ne $d && $dir !~ /^\Q$d\E/;
                if (defined $max_depth) {
                        my @a=split('/', $dir);
                        my @b=split('/', $d);
                        do { } while (@a && @b && shift(@a) eq shift(@b));
                        next if @a > $max_depth || @b > $max_depth;
                }
                push @repos, [$dir, $topdir, $subdir];
        }
        if (! @repos) {
                # fallback to find a leaf repo
                foreach my $repo (reverse repolist()) {
                        my $topdir=$repo->{topdir};
                        my $subdir=$repo->{subdir};
                        
                        next if $subdir eq 'DEFAULT';
                        my $dir=($subdir =~/^\//) ? $subdir : $topdir.$subdir;
                        my $d=$directory;
                        $dir.="/" unless $dir=~/\/$/;
                        $d.="/" unless $d=~/\/$/;
                        if ($d=~/^\Q$dir\E/) {
                                push @repos, [$dir, $topdir, $subdir];
                                last;
                        }
                }
                $no_chdir=1;
        }
        return @repos;
}

sub expandenv {
        my $val=shift;
        

        if ($val=~/\$/) {
                $val=`echo "$val"`;
                chomp $val;
        }
        
        return $val;
}

my %trusted;
sub is_trusted_config {
        my $config=shift; # must be abs_pathed already

        # We always trust ~/.mrconfig.
        return 1 if $config eq abs_path("$ENV{HOME}/.mrconfig");

        return 1 if $trust_all;

        my $trustfile=$ENV{HOME}."/.mrtrust";

        if (! -e $trustfile) {
                print "mr: Assuming $config is trusted.\n";
                print "mr: For better security, you are encouraged to create ~/.mrtrust\n";
                print "mr: and list all trusted mrconfig files in it.\n";
                return 1;
        }

        if (! %trusted) {
                $trusted{"$ENV{HOME}/.mrconfig"}=1;
                open (TRUST, "<", $trustfile) || die "$trustfile: $!";
                while (<TRUST>) {
                        chomp;
                        s/^~\//$ENV{HOME}\//;
                        $trusted{abs_path($_)}=1;
                }
                close TRUST;
        }

        return $trusted{$config};
}


sub is_trusted_repo {
        my $repo=shift;
        
        # Tightly limit what is allowed in a repo name.
        # No ../, no absolute paths, and no unusual filenames
        # that might try to escape to the shell.
        return $repo =~ /^[-_.+\/A-Za-z0-9]+$/ &&
               $repo !~ /\.\./ && $repo !~ /^\//;
}

sub is_trusted_checkout {
        my $command=shift;
        
        # To determine if the command is safe, compare it with the
        # *_trusted_checkout config settings. Those settings are
        # templates for allowed commands, so make sure that each word
        # of the command matches the corresponding word of the template.
        
        my @words;
        foreach my $word (split(' ', $command)) {
                # strip quoting
                if ($word=~/^'(.*)'$/) {
                        $word=$1;
                }
                elsif ($word=~/^"(.*)"$/) {
                        $word=$1;
                }

                push @words, $word;
        }

        foreach my $key (grep { /_trusted_checkout$/ }
                         keys %{$config{''}{DEFAULT}}) {
                my @twords=split(' ', $config{''}{DEFAULT}{$key});
                next if @words > @twords;

                my $match=1;
                my $url;
                for (my $c=0; $c < @twords && $match; $c++) {
                        if ($twords[$c] eq '$url') {
                                # Match all the typical characters found in
                                # urls, plus @ which svn can use. Note
                                # that the "url" might also be a local
                                # directory.
                                $match=(
                                        defined $words[$c] &&
                                        $words[$c] =~ /^[-_.+:@\/A-Za-z0-9]+$/
                                );
                                $url=$words[$c];
                        }
                        elsif ($twords[$c] eq '$repo') {
                                # If a repo is not specified, assume it
                                # will be the last path component of the
                                # url, or something derived from it, and
                                # check that.
                                if (! defined $words[$c] && defined $url) {
                                        ($words[$c])=$url=~/\/([^\/]+)\/?$/;
                                }

                                $match=(
                                        defined $words[$c] &&
                                        is_trusted_repo($words[$c])
                                );
                        }
                        elsif (defined $words[$c] && $twords[$c] eq $words[$c]) {
                                $match=1;
                        }
                        else {
                                $match=0;
                        }
                }
                return 1 if $match;
        }

        return 0;
}

my %loaded;
sub loadconfig {
        my $f=shift;
        my $dir=shift;

        my @toload;

        my $in;
        my $trusted;
        if (ref $f eq 'GLOB') {
                $dir="";
                $in=$f;
                $trusted=1;
        }
        else {
                if (! -e $f) {
                        return;
                }

                my $absf=abs_path($f);
                if ($loaded{$absf}) {
                        return;
                }
                $loaded{$absf}=1;

                $trusted=is_trusted_config($absf);

                if (! defined $dir) {
                        ($dir)=$f=~/^(.*\/)[^\/]+$/;
                        if (! defined $dir) {
                                $dir=".";
                        }
                }

                $dir=abs_path($dir)."/";
                
                if (! exists $configfiles{$dir}) {
                        $configfiles{$dir}=$f;
                }

                # copy in defaults from first parent
                my $parent=$dir;
                while ($parent=~s/^(.*\/)[^\/]+\/?$/$1/) {
                        if ($parent eq '/') {
                                $parent="";
                        }
                        if (exists $config{$parent} &&
                            exists $config{$parent}{DEFAULT}) {
                                $config{$dir}{DEFAULT}={ %{$config{$parent}{DEFAULT}} };
                                last;
                        }
                }
                
                print "mr: loading config $f\n" if $verbose;
                open($in, "<", $f) || die "mr: open $f: $!\n";
        }
        my @lines=<$in>;
        close $in;

        my $section;
        my $line=0;
        while (@lines) {
                $_=shift @lines;
                $line++;
                chomp;
                next if /^\s*\#/ || /^\s*$/;
                if (/^\[([^\]]*)\]\s*$/) {
                        $section=$1;

                        if (! $trusted) {
                                if (! is_trusted_repo($section) ||
                                    $section eq 'ALIAS' ||
                                    $section eq 'DEFAULT') {
                                        die "mr: illegal section \"[$section]\" in untrusted $f line $line\n";
                                }
                        }
                        $section=expandenv($section) if $trusted;
                }
                elsif (/^(\w+)\s*=\s*(.*)/) {
                        my $parameter=$1;
                        my $value=$2;

                        # continued value
                        while (@lines && $lines[0]=~/^\s(.+)/) {
                                shift(@lines);
                                $line++;
                                $value.="\n$1";
                                chomp $value;
                        }

                        if (! $trusted) {
                                # Untrusted files can only contain checkout
                                # parameters.
                                if ($parameter ne 'checkout') {
                                        die "mr: illegal setting \"$parameter=$value\" in untrusted $f line $line\n";
                                }
                                if (! is_trusted_checkout($value)) {
                                        die "mr: illegal checkout command \"$value\" in untrusted $f line $line\n";
                                }
                        }

                        if ($parameter eq "include") {
                                print "mr: including output of \"$value\"\n" if $verbose;
                                unshift @lines, `$value`;
                                if ($?) {
                                        print STDERR "mr: include command exited nonzero ($?)\n";
                                }
                                next;
                        }

                        if (! defined $section) {
                                die "$f line $.: parameter ($parameter) not in section\n";
                        }
                        if ($section ne 'ALIAS' &&
                            ! exists $config{$dir}{$section} &&
                            exists $config{$dir}{DEFAULT}) {
                                # copy in defaults
                                $config{$dir}{$section}={ %{$config{$dir}{DEFAULT}} };
                        }
                        if ($section eq 'ALIAS') {
                                $alias{$parameter}=$value;
                        }
                        elsif ($parameter eq 'lib') {
                                $config{$dir}{$section}{lib}.=$value."\n";
                        }
                        else {
                                $config{$dir}{$section}{$parameter}=$value;
                                if ($parameter =~ /.*_(.*)/) {
                                        $knownactions{$1}=1;
                                }
                                else {
                                        $knownactions{$parameter}=1;
                                }
                                if ($parameter eq 'chain' &&
                                    length $dir && $section ne "DEFAULT" &&
                                    -e $dir.$section."/.mrconfig") {
                                        my $ret=system($value);
                                        if ($ret != 0) {
                                                if (($? & 127) == 2) {
                                                        print STDERR "mr: chain test interrupted\n";
                                                        exit 2;
                                                }
                                                elsif ($? & 127) {
                                                        print STDERR "mr: chain test received signal ".($? & 127)."\n";
                                                }
                                        }
                                        else {
                                                push @toload, $dir.$section."/.mrconfig";
                                        }
                                }
                        }
                }
                else {
                        die "$f line $line: parse error\n";
                }
        }

        foreach (@toload) {
                loadconfig($_);
        }
}

sub modifyconfig {
        my $f=shift;
        # the section to modify or add
        my $targetsection=shift;
        # fields to change in the section
        # To remove a field, set its value to "".
        my %changefields=@_;

        my @lines;
        my @out;

        if (-e $f) {
                open(my $in, "<", $f) || die "mr: open $f: $!\n";
                @lines=<$in>;
                close $in;
        }

        my $formatfield=sub {
                my $field=shift;
                my @value=split(/\n/, shift);

                return "$field = ".shift(@value)."\n".
                        join("", map { "\t$_\n" } @value);
        };
        my $addfields=sub {
                my @blanks;
                while ($out[$#out] =~ /^\s*$/) {
                        unshift @blanks, pop @out;
                }
                foreach my $field (sort keys %changefields) {
                        if (length $changefields{$field}) {
                                push @out, "$field = $changefields{$field}\n";
                                delete $changefields{$field};
                        }
                }
                push @out, @blanks;
        };

        my $section;
        while (@lines) {
                $_=shift(@lines);

                if (/^\s*\#/ || /^\s*$/) {
                        push @out, $_;
                }
                elsif (/^\[([^\]]*)\]\s*$/) {
                        if (defined $section && 
                            $section eq $targetsection) {
                                $addfields->();
                        }

                        $section=expandenv($1);

                        push @out, $_;
                }
                elsif (/^(\w+)\s*=\s(.*)/) {
                        my $parameter=$1;
                        my $value=$2;

                        # continued value
                        while (@lines && $lines[0]=~/^\s(.+)/) {
                                shift(@lines);
                                $value.="\n$1";
                                chomp $value;
                        }

                        if ($section eq $targetsection) {
                                if (exists $changefields{$parameter}) {
                                        if (length $changefields{$parameter}) {
                                                $value=$changefields{$parameter};
                                        }
                                        delete $changefields{$parameter};
                                }
                        }

                        push @out, $formatfield->($parameter, $value);
                }
        }

        if (defined $section && 
            $section eq $targetsection) {
                $addfields->();
        }
        elsif (%changefields) {
                push @out, "\n[$targetsection]\n";
                foreach my $field (sort keys %changefields) {
                        if (length $changefields{$field}) {
                                push @out, $formatfield->($field, $changefields{$field});
                        }
                }
        }

        open(my $out, ">", $f) || die "mr: write $f: $!\n";
        print $out @out;
        close $out;     
}

sub dispatch {
        my $action=shift;

        # actions that do not operate on all repos
        if ($action eq 'help') {
                help(@ARGV);
        }
        elsif ($action eq 'config') {
                config(@ARGV);
        }
        elsif ($action eq 'register') {
                register(@ARGV);
        }
        elsif ($action eq 'bootstrap') {
                bootstrap();
        }
        elsif ($action eq 'remember' ||
               $action eq 'offline' ||
               $action eq 'online') {
                my @repos=selectrepos;
                action($action, @{$repos[0]}) if @repos;
                exit 0;
        }

        if (!$jobs || $jobs > 1) {
                mrs($action, selectrepos());
        }
        else {
                foreach my $repo (selectrepos()) {
                        record($repo, action($action, @$repo));
                }
        }
}

sub help {
        exec($config{''}{DEFAULT}{help}) || die "exec: $!";
}

sub config {
        if (@_ < 2) {
                die "mr config: not enough parameters\n";
        }
        my $section=shift;
        if ($section=~/^\//) {
                # try to convert to a path relative to the config file
                my ($dir)=$ENV{MR_CONFIG}=~/^(.*\/)[^\/]+$/;
                $dir=abs_path($dir);
                $dir.="/" unless $dir=~/\/$/;
                if ($section=~/^\Q$dir\E(.*)/) {
                        $section=$1;
                }
        }
        my %changefields;
        foreach (@_) {
                if (/^([^=]+)=(.*)$/) {
                        $changefields{$1}=$2;
                }
                else {
                        my $found=0;
                        foreach my $topdir (sort keys %config) {
                                if (exists $config{$topdir}{$section} &&
                                    exists $config{$topdir}{$section}{$_}) {
                                        print $config{$topdir}{$section}{$_}."\n";
                                        $found=1;
                                        last if $section eq 'DEFAULT';
                                }
                        }
                        if (! $found) {
                                die "mr config: $section $_ not set\n";
                        }
                }
        }
        modifyconfig($ENV{MR_CONFIG}, $section, %changefields) if %changefields;
        exit 0;
}

sub register {
        if ($config_overridden) {
                # Find the directory that the specified config file is
                # located in.
                ($directory)=abs_path($ENV{MR_CONFIG})=~/^(.*\/)[^\/]+$/;
        }
        else {
                # Find the closest known mrconfig file to the current
                # directory.
                $directory.="/" unless $directory=~/\/$/;
                my $foundconfig=0;
                foreach my $topdir (reverse sort keys %config) {
                        next unless length $topdir;
                        if ($directory=~/^\Q$topdir\E/) {
                                $ENV{MR_CONFIG}=$configfiles{$topdir};
                                $directory=$topdir;
                                $foundconfig=1;
                                last;
                        }
                }
                if (! $foundconfig) {
                        $directory=""; # no config file, use builtin
                }
        }
        if (@ARGV) {
                my $subdir=shift @ARGV;
                if (! chdir($subdir)) {
                        print STDERR "mr register: failed to chdir to $subdir: $!\n";
                }
        }

        $ENV{MR_REPO}=getcwd();
        my $command=findcommand("register", $ENV{MR_REPO}, $directory, 'DEFAULT', 0);
        if (! defined $command) {
                die "mr register: unknown repository type\n";
        }

        $ENV{MR_REPO}=~s/.*\/(.*)/$1/;
        $command="set -e; ".$config{$directory}{DEFAULT}{lib}."\n".
                "my_action(){ $command\n }; my_action ".
                join(" ", map { s/\//\/\//g; s/"/\"/g; '"'.$_.'"' } @ARGV);
        print "mr register: running >>$command<<\n" if $verbose;
        exec($command) || die "exec: $!";
}

sub bootstrap {
        my $url=shift @ARGV;
        my $dir=shift @ARGV || ".";
        
        if (! defined $url || ! length $url) {
                die "mr: bootstrap requires url\n";
        }
        
        # Download the config file to a temporary location.
        eval q{use File::Temp};
        die $@ if $@;
        my $tmpconfig=File::Temp->new();
        if (system("curl", "-A", "mr", "-s", $url, "-o", $tmpconfig) != 0) {
                die "mr: download of $url failed\n";
        }

        if (! -e $dir) {
                system("mkdir", "-p", $dir);
        }
        chdir($dir) || die "chdir $dir: $!";

        # Special case to handle checkout of the "." repo, which 
        # would normally be skipped.
        my $topdir=abs_path(".")."/";
        my @repo=($topdir, $topdir, ".");
        loadconfig($tmpconfig, $topdir);
        record(\@repo, action("checkout", @repo, 1))
                if exists $config{$topdir}{"."}{"checkout"};

        if (-e ".mrconfig") {
                print STDERR "mr: .mrconfig file already exists, not overwriting with $url\n";
        }
        else {
                rename($tmpconfig, ".mrconfig") || die "rename: $!";
        }

        exec("mr $ENV{MR_SWITCHES} -c .mrconfig checkout");
        die "failed to run mr checkout";
}

# alias expansion and command stemming
sub expandaction {
        my $action=shift;
        if (exists $alias{$action}) {
                $action=$alias{$action};
        }
        if (! exists $knownactions{$action}) {
                my @matches = grep { /^\Q$action\E/ }
                        keys %knownactions, keys %alias;
                if (@matches == 1) {
                        $action=$matches[0];
                }
                elsif (@matches == 0) {
                        die "mr: unknown action \"$action\" (known actions: ".
                                join(", ", sort keys %knownactions).")\n";
                }
                else {
                        die "mr: ambiguous action \"$action\" (matches: ".
                                join(", ", @matches).")\n";
                }
        }
        return $action;
}

sub find_nearest_mrconfig {
        my $dir=getcwd();
        while (length $dir) {
                if (-e "$dir/.mrconfig") {
                        return "$dir/.mrconfig";
                }
                $dir=~s/\/[^\/]*$//;
        }
        die "no .mrconfig found in path\n";
}

sub getopts {
        my @saved=@ARGV;
        Getopt::Long::Configure("bundling", "no_permute");
        my $result=GetOptions(
                "d|directory=s" => sub { $directory=abs_path($_[1]) },
                "c|config=s" => sub { $ENV{MR_CONFIG}=$_[1]; $config_overridden=1 },
                "p|path" => sub { $ENV{MR_CONFIG}=find_nearest_mrconfig(); $config_overridden=1 },
                "v|verbose" => \$verbose,
                "q|quiet" => \$quiet,
                "s|stats" => \$stats,
                "i|interactive" => \$interactive,
                "n|no-recurse:i" => \$max_depth,
                "j|jobs:i" => \$jobs,
                "t|trust-all" => \$trust_all,
        );
        if (! $result || @ARGV < 1) {
                die("Usage: mr [options] action [params ...]\n".
                    "(Use mr help for man page.)\n");
        }
        
        $ENV{MR_SWITCHES}="";
        foreach my $option (@saved) {
                last if $option eq $ARGV[0];
                $ENV{MR_SWITCHES}.="$option ";
        }
}

sub init {
        $SIG{INT}=sub {
                print STDERR "mr: interrupted\n";
                exit 2;
        };
        
        # This can happen if it's run in a directory that was removed
        # or other strangeness.
        if (! defined $directory) {
                die("mr: failed to determine working directory\n");
        }
        # Make sure MR_CONFIG is an absolute path, but don't use abs_path since
        # the config file might be a symlink to elsewhere, and the directory it's
        # in is significant.
        if ($ENV{MR_CONFIG} !~ /^\//) {
                $ENV{MR_CONFIG}=getcwd()."/".$ENV{MR_CONFIG};
        }
        # Try to set MR_PATH to the path to the program.
        eval {
                use FindBin qw($Bin $Script);
                $ENV{MR_PATH}=$Bin."/".$Script;
        };
}

sub main {
        getopts();
        init();

        loadconfig(\*DATA);
        loadconfig($ENV{MR_CONFIG});
        #use Data::Dumper; print Dumper(\%config);
        
        my $action=expandaction(shift @ARGV);
        dispatch($action);
        showstats($action);

        if (@failed) {
                exit 1;
        }
        elsif (! @ok && @skipped) {
                exit 1;
        }
        else {
                exit 0;
        }
}

# Finally, some useful actions that mr knows about by default.
# These can be overridden in ~/.mrconfig.
__DATA__
[ALIAS]
co = checkout
ci = commit
ls = list

[DEFAULT]
order = 10
lib =
        error() {
                echo "mr: $@" >&2
                exit 1
        }
        warning() {
                echo "mr (warning): $@" >&2
        }
        info() {
                echo "mr: $@" >&2
        }
        hours_since() {
                if [ -z "$1" ] || [ -z "$2" ]; then
                        error "mr: usage: hours_since action num"
                fi
                for dir in .git .svn .bzr CVS .hg _darcs; do
                        if [ -e "$MR_REPO/$dir" ]; then
                                flagfile="$MR_REPO/$dir/.mr_last$1"
                                break
                        fi
                done
                if [ -z "$flagfile" ]; then
                        error "cannot determine flag filename"
                fi
                delta=`perl -wle 'print -f shift() ? int((-M _) * 24) : 9999' "$flagfile"`
                if [ "$delta" -lt "$2" ]; then
                        exit 0
                else
                        touch "$flagfile"
                        exit 1
                fi
        }

svn_test = test -d "$MR_REPO"/.svn
git_test = test -d "$MR_REPO"/.git
bzr_test = test -d "$MR_REPO"/.bzr
cvs_test = test -d "$MR_REPO"/CVS
hg_test  = test -d "$MR_REPO"/.hg
darcs_test = test -d "$MR_REPO"/_darcs
git_bare_test =
        test -d "$MR_REPO"/refs/heads && test -d "$MR_REPO"/refs/tags &&
        test -d "$MR_REPO"/objects && test -f "$MR_REPO"/config &&
        test "`GIT_CONFIG="$MR_REPO"/config git config --get core.bare`" = true

svn_update = svn update "$@"
git_update = git pull "$@"
bzr_update = bzr merge --pull "$@"
cvs_update = cvs update "$@"
hg_update  = hg pull "$@" && hg update "$@"
darcs_update = darcs pull -a "$@"

svn_status = svn status "$@"
git_status = git status "$@" || true
bzr_status = bzr status "$@"
cvs_status = cvs status "$@"
hg_status  = hg status "$@"
darcs_status = darcs whatsnew -ls "$@" || true

svn_commit = svn commit "$@"
git_commit = git commit -a "$@" && git push --all
bzr_commit = bzr commit "$@" && bzr push
cvs_commit = cvs commit "$@"
hg_commit  = hg commit -m "$@" && hg push
darcs_commit = darcs record -a -m "$@" && darcs push -a

git_record = git commit -a "$@"
bzr_record = bzr commit "$@"
hg_record  = hg commit -m "$@"
darcs_record = darcs record -a -m "$@"

svn_push = :
git_push = git push "$@"
bzr_push = bzr push "$@"
cvs_push = :
hg_push = hg push "$@"
darcs_push = darcs push -a "$@"

svn_diff = svn diff "$@"
git_diff = git diff "$@"
bzr_diff = bzr diff "$@"
cvs_diff = cvs diff "$@"
hg_diff  = hg diff "$@"
darcs_diff = darcs diff -u "$@"

svn_log = svn log "$@"
git_log = git log "$@"
bzr_log = bzr log "$@"
cvs_log = cvs log "$@"
hg_log  = hg log "$@"
darcs_log = darcs changes "$@"
git_bare_log = git log "$@"

svn_register =
        url=`LC_ALL=C svn info . | grep -i '^URL:' | cut -d ' ' -f 2`
        if [ -z "$url" ]; then
                error "cannot determine svn url"
        fi
        echo "Registering svn url: $url in $MR_CONFIG"
        mr -c "$MR_CONFIG" config "`pwd`" checkout="svn co '$url' '$MR_REPO'"
git_register = 
        url="`LC_ALL=C git config --get remote.origin.url`" || true
        if [ -z "$url" ]; then
                error "cannot determine git url"
        fi
        echo "Registering git url: $url in $MR_CONFIG"
        mr -c "$MR_CONFIG" config "`pwd`" checkout="git clone '$url' '$MR_REPO'"
bzr_register =
        url="`LC_ALL=C bzr info . | egrep -i 'checkout of branch|parent branch' | awk '{print $NF}'`"
        if [ -z "$url" ]; then
                error "cannot determine bzr url"
        fi
        echo "Registering bzr url: $url in $MR_CONFIG"
        mr -c "$MR_CONFIG" config "`pwd`" checkout="bzr clone '$url' '$MR_REPO'"
cvs_register =
        repo=`cat CVS/Repository`
        root=`cat CVS/Root`
        if [ -z "$root" ]; then
                error "cannot determine cvs root"
                fi
        echo "Registering cvs repository $repo at root $root"
        mr -c "$MR_CONFIG" config "`pwd`" checkout="cvs -d '$root' co -d '$MR_REPO' '$repo'"
hg_register = 
        url=`hg showconfig paths.default`
        echo "Registering mercurial repo url: $url in $MR_CONFIG"
        mr -c "$MR_CONFIG" config "`pwd`" checkout="hg clone '$url' '$MR_REPO'"
darcs_register = 
        url=`cat _darcs/prefs/defaultrepo`
        echo "Registering darcs repository $url in $MR_CONFIG"
        mr -c "$MR_CONFIG" config "`pwd`" checkout="darcs get '$url' '$MR_REPO'"
git_bare_register = 
        url="`LC_ALL=C GIT_CONFIG=config git config --get remote.origin.url`" || true
        if [ -z "$url" ]; then
                error "cannot determine git url"
        fi
        echo "Registering git url: $url in $MR_CONFIG"
        mr -c "$MR_CONFIG" config "`pwd`" checkout="git clone --bare '$url' '$MR_REPO'"

svn_trusted_checkout = svn co $url $repo
svn_alt_trusted_checkout = svn checkout $url $repo
git_trusted_checkout = git clone $url $repo
bzr_trusted_checkout = bzr clone $url $repo
# cvs: too hard
hg_trusted_checkout = hg clone $url $repo
darcs_trusted_checkout = darcs get $url $repo
git_bare_trusted_checkout = git clone --bare $url $repo


help =
        case `uname -s` in
                SunOS)
                SHOWMANFILE="man -f"
                ;;
                Darwin)
                SHOWMANFILE="man"
                ;;
                *)
                SHOWMANFILE="man -l"
                ;;
        esac
        if [ ! -e "$MR_PATH" ]; then
                error "cannot find program path"
        fi
        tmp=$(mktemp -t mr.XXXXXXXXXX) || error "mktemp failed"
        trap "rm -f $tmp" exit
        pod2man -c mr "$MR_PATH" > "$tmp" || error "pod2man failed"
        $SHOWMANFILE "$tmp" || error "man failed"
list = true
config = 
bootstrap = 

online =
        if [ -s ~/.mrlog ]; then
                info "running offline commands"
                mv -f ~/.mrlog ~/.mrlog.old
                if ! sh -e ~/.mrlog.old; then
                        error "offline command failed; left in ~/.mrlog.old"
                fi
                rm -f ~/.mrlog.old
        else
                info "no offline commands to run"
        fi
offline =
        umask 077
        touch ~/.mrlog
        info "offline mode enabled"
remember =
        info "remembering command: 'mr $@'"
        command="mr -d '$(pwd)' $MR_SWITCHES"
        for w in "$@"; do
                command="$command '$w'"
        done
        if [ ! -e ~/.mrlog ] || ! grep -q -F "$command" ~/.mrlog; then
                echo "$command" >> ~/.mrlog
        fi

ed = echo "A horse is a horse, of course, of course.."
T = echo "I pity the fool."
right = echo "Not found."

# vim:sw=8:sts=0:ts=8:noet