git-archimport.perl 23.3 KB
Newer Older
1 2 3 4 5 6 7 8
#!/usr/bin/perl -w
#
# This tool is copyright (c) 2005, Martin Langhoff.
# It is released under the Gnu Public License, version 2.
#
# The basic idea is to walk the output of tla abrowse, 
# fetch the changesets and apply them. 
#
9

10 11
=head1 Invocation

12
    git-archimport [ -h ] [ -v ] [ -T ] [ -t tempdir ] <archive>/<branch> [ <archive>/<branch> ]
13

14 15 16 17 18
Imports a project from one or more Arch repositories. It will follow branches
and repositories within the namespaces defined by the <archive/branch>
parameters suppplied. If it cannot find the remote branch a merge comes from
it will just import it as a regular commit. If it can find it, it will mark it 
as a merge whenever possible.
19

20
See man (1) git-archimport for more details.
21

22
=head1 TODO
23

24
 - create tag objects instead of ref tags
25
 - audit shell-escaping of filenames
26 27
 - hide our private tags somewhere smarter
 - find a way to make "cat *patches | patch" safe even when patchfiles are missing newlines  
28 29 30 31 32 33 34 35 36 37 38

=head1 Devel tricks

Add print in front of the shell commands invoked via backticks. 

=cut

use strict;
use warnings;
use Getopt::Std;
use File::Spec;
39
use File::Temp qw(tempfile tempdir);
40 41 42 43 44 45 46 47 48 49 50 51 52
use File::Path qw(mkpath);
use File::Basename qw(basename dirname);
use String::ShellQuote;
use Time::Local;
use IO::Socket;
use IO::Pipe;
use POSIX qw(strftime dup2);
use Data::Dumper qw/ Dumper /;
use IPC::Open2;

$SIG{'PIPE'}="IGNORE";
$ENV{'TZ'}="UTC";

53 54
my $git_dir = $ENV{"GIT_DIR"} || ".git";
$ENV{"GIT_DIR"} = $git_dir;
55
my $ptag_dir = "$git_dir/archimport/tags";
56

57
our($opt_h,$opt_v, $opt_T,
58
    $opt_C,$opt_t);
59 60 61 62

sub usage() {
    print STDERR <<END;
Usage: ${\basename $0}     # fetch/update GIT from Arch
63
       [ -h ] [ -v ] [ -T ] [ -t tempdir ] 
64 65 66 67 68
       repository/arch-branch [ repository/arch-branch] ...
END
    exit(1);
}

69
getopts("Thvt:") or usage();
70 71 72 73 74
usage if $opt_h;

@ARGV >= 1 or usage();
my @arch_roots = @ARGV;

75 76 77 78
my ($tmpdir, $tmpdirname) = tempdir('git-archimport-XXXXXX', TMPDIR => 1, CLEANUP => 1);
my $tmp = $opt_t || 1;
$tmp = tempdir('git-archimport-XXXXXX', TMPDIR => 1, CLEANUP => 1);
$opt_v && print "+ Using $tmp as temporary directory\n";
79 80

my @psets  = ();                # the collection
81 82 83 84
my %psets  = ();                # the collection, by name

my %rptags = ();                # my reverse private tags
                                # to map a SHA1 to a commitid
85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104

foreach my $root (@arch_roots) {
    my ($arepo, $abranch) = split(m!/!, $root);
    open ABROWSE, "tla abrowse -f -A $arepo --desc --merges $abranch |" 
        or die "Problems with tla abrowse: $!";
    
    my %ps        = ();         # the current one
    my $mode      = '';
    my $lastseen  = '';
    
    while (<ABROWSE>) {
        chomp;
        
        # first record padded w 8 spaces
        if (s/^\s{8}\b//) {
            
            # store the record we just captured
            if (%ps) {
                my %temp = %ps; # break references
                push (@psets, \%temp);
105
		$psets{$temp{id}} = \%temp;
106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167
                %ps = ();
            }
            
            my ($id, $type) = split(m/\s{3}/, $_);
            $ps{id}   = $id;
            $ps{repo} = $arepo;

            # deal with types
            if ($type =~ m/^\(simple changeset\)/) {
                $ps{type} = 's';
            } elsif ($type eq '(initial import)') {
                $ps{type} = 'i';
            } elsif ($type =~ m/^\(tag revision of (.+)\)/) {
                $ps{type} = 't';
                $ps{tag}  = $1;
            } else { 
                warn "Unknown type $type";
            }
            $lastseen = 'id';
        }
        
        if (s/^\s{10}//) { 
            # 10 leading spaces or more 
            # indicate commit metadata
            
            # date & author 
            if ($lastseen eq 'id' && m/^\d{4}-\d{2}-\d{2}/) {
                
                my ($date, $authoremail) = split(m/\s{2,}/, $_);
                $ps{date}   = $date;
                $ps{date}   =~ s/\bGMT$//; # strip off trailign GMT
                if ($ps{date} =~ m/\b\w+$/) {
                    warn 'Arch dates not in GMT?! - imported dates will be wrong';
                }
            
                $authoremail =~ m/^(.+)\s(\S+)$/;
                $ps{author} = $1;
                $ps{email}  = $2;
            
                $lastseen = 'date';
            
            } elsif ($lastseen eq 'date') {
                # the only hint is position
                # subject is after date
                $ps{subj} = $_;
                $lastseen = 'subj';
            
            } elsif ($lastseen eq 'subj' && $_ eq 'merges in:') {
                $ps{merges} = [];
                $lastseen = 'merges';
            
            } elsif ($lastseen eq 'merges' && s/^\s{2}//) {
                push (@{$ps{merges}}, $_);
            } else {
                warn 'more metadata after merges!?';
            }
            
        }
    }

    if (%ps) {
        my %temp = %ps;         # break references
168 169
        push (@psets, \%temp);  
	$psets{ $temp{id} } = \%temp;
170 171 172 173 174 175 176 177 178 179 180 181 182 183
        %ps = ();
    }    
    close ABROWSE;
}                               # end foreach $root

## Order patches by time
@psets = sort {$a->{date}.$b->{id} cmp $b->{date}.$b->{id}} @psets;

#print Dumper \@psets;

##
## TODO cleanup irrelevant patches
##      and put an initial import
##      or a full tag
184
my $import = 0;
185
unless (-d $git_dir) { # initial import
186 187
    if ($psets[0]{type} eq 'i' || $psets[0]{type} eq 't') {
        print "Starting import from $psets[0]{id}\n";
188 189 190
	`git-init-db`;
	die $! if $?;
	$import = 1;
191 192 193
    } else {
        die "Need to start from an import or a tag -- cannot use $psets[0]{id}";
    }
194 195
} else {    # progressing an import
    # load the rptags
196
    opendir(DIR, "$git_dir/archimport/tags")
197 198
	|| die "can't opendir: $!";
    while (my $file = readdir(DIR)) {
199 200 201 202 203 204 205 206 207 208 209
        # skip non-interesting-files
        next unless -f "$ptag_dir/$file";
   
        # convert first '--' to '/' from old git-archimport to use
        # as an archivename/c--b--v private tag
        if ($file !~ m!,!) {
            my $oldfile = $file;
            $file =~ s!--!,!;
            print STDERR "converting old tag $oldfile to $file\n";
            rename("$ptag_dir/$oldfile", "$ptag_dir/$file") or die $!;
        }
210 211 212 213 214
	my $sha = ptag($file);
	chomp $sha;
	$rptags{$sha} = $file;
    }
    closedir DIR;
215 216
}

217
# process patchsets
218 219 220 221 222 223 224 225 226 227 228 229 230
foreach my $ps (@psets) {

    $ps->{branch} =  branchname($ps->{id});

    #
    # ensure we have a clean state 
    # 
    if (`git diff-files`) {
        die "Unclean tree when about to process $ps->{id} " .
            " - did we fail to commit cleanly before?";
    }
    die $! if $?;

231 232 233 234
    #
    # skip commits already in repo
    #
    if (ptag($ps->{id})) {
235
      $opt_v && print " * Skipping already imported: $ps->{id}\n";
236 237 238
      next;
    }

239 240
    print " * Starting to work on $ps->{id}\n";

241 242 243
    # 
    # create the branch if needed
    #
244 245
    if ($ps->{type} eq 'i' && !$import) {
        die "Should not have more than one 'Initial import' per GIT import: $ps->{id}";
246 247
    }

248
    unless ($import) { # skip for import
249
        if ( -e "$git_dir/refs/heads/$ps->{branch}") {
250 251 252 253 254 255 256 257 258 259 260
            # we know about this branch
            `git checkout    $ps->{branch}`;
        } else {
            # new branch! we need to verify a few things
            die "Branch on a non-tag!" unless $ps->{type} eq 't';
            my $branchpoint = ptag($ps->{tag});
            die "Tagging from unknown id unsupported: $ps->{tag}" 
                unless $branchpoint;
            
            # find where we are supposed to branch from
            `git checkout -b $ps->{branch} $branchpoint`;
261 262 263 264 265 266 267 268

            # If we trust Arch with the fact that this is just 
            # a tag, and it does not affect the state of the tree
            # then we just tag and move on
            tag($ps->{id}, $branchpoint);
            ptag($ps->{id}, $branchpoint);
            print " * Tagged $ps->{id} at $branchpoint\n";
            next;
269 270 271 272 273 274 275 276 277
        } 
        die $! if $?;
    } 

    #
    # Apply the import/changeset/merge into the working tree
    # 
    if ($ps->{type} eq 'i' || $ps->{type} eq 't') {
        apply_import($ps) or die $!;
278
        $import=0;
279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301
    } elsif ($ps->{type} eq 's') {
        apply_cset($ps);
    }

    #
    # prepare update git's index, based on what arch knows
    # about the pset, resolve parents, etc
    #
    my $tree;
    
    my $commitlog = `tla cat-archive-log -A $ps->{repo} $ps->{id}`; 
    die "Error in cat-archive-log: $!" if $?;
        
    # parselog will git-add/rm files
    # and generally prepare things for the commit
    # NOTE: parselog will shell-quote filenames! 
    my ($sum, $msg, $add, $del, $mod, $ren) = parselog($commitlog);
    my $logmessage = "$sum\n$msg";


    # imports don't give us good info
    # on added files. Shame on them
    if ($ps->{type} eq 'i' || $ps->{type} eq 't') { 
302
        `find . -type f -print0 | grep -zv '^./$git_dir' | xargs -0 -l100 git-update-index --add`;
Junio C Hamano's avatar
Junio C Hamano committed
303
        `git-ls-files --deleted -z | xargs --no-run-if-empty -0 -l100 git-update-index --remove`;
304 305 306 307 308 309
    }

    if (@$add) {
        while (@$add) {
            my @slice = splice(@$add, 0, 100);
            my $slice = join(' ', @slice);          
Junio C Hamano's avatar
Junio C Hamano committed
310 311
            `git-update-index --add $slice`;
            die "Error in git-update-index --add: $!" if $?;
312 313 314 315 316 317 318 319 320
        }
    }
    if (@$del) {
        foreach my $file (@$del) {
            unlink $file or die "Problems deleting $file : $!";
        }
        while (@$del) {
            my @slice = splice(@$del, 0, 100);
            my $slice = join(' ', @slice);
Junio C Hamano's avatar
Junio C Hamano committed
321 322
            `git-update-index --remove $slice`;
            die "Error in git-update-index --remove: $!" if $?;
323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339
        }
    }
    if (@$ren) {                # renamed
        if (@$ren % 2) {
            die "Odd number of entries in rename!?";
        }
        ;
        while (@$ren) {
            my $from = pop @$ren;
            my $to   = pop @$ren;           

            unless (-d dirname($to)) {
                mkpath(dirname($to)); # will die on err
            }
            #print "moving $from $to";
            `mv $from $to`;
            die "Error renaming $from $to : $!" if $?;
Junio C Hamano's avatar
Junio C Hamano committed
340 341 342 343
            `git-update-index --remove $from`;
            die "Error in git-update-index --remove: $!" if $?;
            `git-update-index --add $to`;
            die "Error in git-update-index --add: $!" if $?;
344 345 346 347 348 349 350
        }

    }
    if (@$mod) {                # must be _after_ renames
        while (@$mod) {
            my @slice = splice(@$mod, 0, 100);
            my $slice = join(' ', @slice);
Junio C Hamano's avatar
Junio C Hamano committed
351 352
            `git-update-index $slice`;
            die "Error in git-update-index: $!" if $?;
353 354 355
        }
    }

Junio C Hamano's avatar
Junio C Hamano committed
356
    # warn "errors when running git-update-index! $!";
357 358 359 360 361 362 363 364 365
    $tree = `git-write-tree`;
    die "cannot write tree $!" if $?;
    chomp $tree;
        
    
    #
    # Who's your daddy?
    #
    my @par;
366 367
    if ( -e "$git_dir/refs/heads/$ps->{branch}") {
        if (open HEAD, "<$git_dir/refs/heads/$ps->{branch}") {
368 369 370 371 372 373 374 375 376 377 378
            my $p = <HEAD>;
            close HEAD;
            chomp $p;
            push @par, '-p', $p;
        } else { 
            if ($ps->{type} eq 's') {
                warn "Could not find the right head for the branch $ps->{branch}";
            }
        }
    }
    
379 380 381
    if ($ps->{merges}) {
        push @par, find_parents($ps);
    }
382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413
    my $par = join (' ', @par);

    #    
    # Commit, tag and clean state
    #
    $ENV{TZ}                  = 'GMT';
    $ENV{GIT_AUTHOR_NAME}     = $ps->{author};
    $ENV{GIT_AUTHOR_EMAIL}    = $ps->{email};
    $ENV{GIT_AUTHOR_DATE}     = $ps->{date};
    $ENV{GIT_COMMITTER_NAME}  = $ps->{author};
    $ENV{GIT_COMMITTER_EMAIL} = $ps->{email};
    $ENV{GIT_COMMITTER_DATE}  = $ps->{date};

    my ($pid, $commit_rh, $commit_wh);
    $commit_rh = 'commit_rh';
    $commit_wh = 'commit_wh';
    
    $pid = open2(*READER, *WRITER, "git-commit-tree $tree $par") 
        or die $!;
    print WRITER $logmessage;   # write
    close WRITER;
    my $commitid = <READER>;    # read
    chomp $commitid;
    close READER;
    waitpid $pid,0;             # close;

    if (length $commitid != 40) {
        die "Something went wrong with the commit! $! $commitid";
    }
    #
    # Update the branch
    # 
414
    open  HEAD, ">$git_dir/refs/heads/$ps->{branch}";
415 416
    print HEAD $commitid;
    close HEAD;
417
    system('git-update-ref', 'HEAD', "$ps->{branch}");
418 419 420 421 422 423 424 425 426

    # tag accordingly
    ptag($ps->{id}, $commitid); # private tag
    if ($opt_T || $ps->{type} eq 't' || $ps->{type} eq 'i') {
        tag($ps->{id}, $commitid);
    }
    print " * Committed $ps->{id}\n";
    print "   + tree   $tree\n";
    print "   + commit $commitid\n";
427 428
    $opt_v && print "   + commit date is  $ps->{date} \n";
    $opt_v && print "   + parents:  $par \n";
429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445
}

sub branchname {
    my $id = shift;
    $id =~ s#^.+?/##;
    my @parts = split(m/--/, $id);
    return join('--', @parts[0..1]);
}

sub apply_import {
    my $ps = shift;
    my $bname = branchname($ps->{id});

    `mkdir -p $tmp`;

    `tla get -s --no-pristine -A $ps->{repo} $ps->{id} $tmp/import`;
    die "Cannot get import: $!" if $?;    
446
    `rsync -v --archive --delete --exclude '$git_dir' --exclude '.arch-ids' --exclude '{arch}' $tmp/import/* ./`;
447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491
    die "Cannot rsync import:$!" if $?;
    
    `rm -fr $tmp/import`;
    die "Cannot remove tempdir: $!" if $?;
    

    return 1;
}

sub apply_cset {
    my $ps = shift;

    `mkdir -p $tmp`;

    # get the changeset
    `tla get-changeset  -A $ps->{repo} $ps->{id} $tmp/changeset`;
    die "Cannot get changeset: $!" if $?;
    
    # apply patches
    if (`find $tmp/changeset/patches -type f -name '*.patch'`) {
        # this can be sped up considerably by doing
        #    (find | xargs cat) | patch
        # but that cna get mucked up by patches
        # with missing trailing newlines or the standard 
        # 'missing newline' flag in the patch - possibly
        # produced with an old/buggy diff.
        # slow and safe, we invoke patch once per patchfile
        `find $tmp/changeset/patches -type f -name '*.patch' -print0 | grep -zv '{arch}' | xargs -iFILE -0 --no-run-if-empty patch -p1 --forward -iFILE`;
        die "Problem applying patches! $!" if $?;
    }

    # apply changed binary files
    if (my @modified = `find $tmp/changeset/patches -type f -name '*.modified'`) {
        foreach my $mod (@modified) {
            chomp $mod;
            my $orig = $mod;
            $orig =~ s/\.modified$//; # lazy
            $orig =~ s!^\Q$tmp\E/changeset/patches/!!;
            #print "rsync -p '$mod' '$orig'";
            `rsync -p $mod ./$orig`;
            die "Problem applying binary changes! $!" if $?;
        }
    }

    # bring in new files
492
    `rsync --archive --exclude '$git_dir' --exclude '.arch-ids' --exclude '{arch}' $tmp/changeset/new-files-archive/* ./`;
493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570

    # deleted files are hinted from the commitlog processing

    `rm -fr $tmp/changeset`;
}


# =for reference
# A log entry looks like 
# Revision: moodle-org--moodle--1.3.3--patch-15
# Archive: arch-eduforge@catalyst.net.nz--2004
# Creator: Penny Leach <penny@catalyst.net.nz>
# Date: Wed May 25 14:15:34 NZST 2005
# Standard-date: 2005-05-25 02:15:34 GMT
# New-files: lang/de/.arch-ids/block_glossary_random.php.id
#     lang/de/.arch-ids/block_html.php.id
# New-directories: lang/de/help/questionnaire
#     lang/de/help/questionnaire/.arch-ids
# Renamed-files: .arch-ids/db_sears.sql.id db/.arch-ids/db_sears.sql.id
#    db_sears.sql db/db_sears.sql
# Removed-files: lang/be/docs/.arch-ids/release.html.id
#     lang/be/docs/.arch-ids/releaseold.html.id
# Modified-files: admin/cron.php admin/delete.php
#     admin/editor.html backup/lib.php backup/restore.php
# New-patches: arch-eduforge@catalyst.net.nz--2004/moodle-org--moodle--1.3.3--patch-15
# Summary: Updating to latest from MOODLE_14_STABLE (1.4.5+)
# Keywords:
#
# Updating yadda tadda tadda madda
sub parselog {
    my $log = shift;
    #print $log;

    my (@add, @del, @mod, @ren, @kw, $sum, $msg );

    if ($log =~ m/(?:\n|^)New-files:(.*?)(?=\n\w)/s ) {
        my $files = $1;
        @add = split(m/\s+/s, $files);
    }
       
    if ($log =~ m/(?:\n|^)Removed-files:(.*?)(?=\n\w)/s ) {
        my $files = $1;
        @del = split(m/\s+/s, $files);
    }
    
    if ($log =~ m/(?:\n|^)Modified-files:(.*?)(?=\n\w)/s ) {
        my $files = $1;
        @mod = split(m/\s+/s, $files);
    }
    
    if ($log =~ m/(?:\n|^)Renamed-files:(.*?)(?=\n\w)/s ) {
        my $files = $1;
        @ren = split(m/\s+/s, $files);
    }

    $sum ='';
    if ($log =~ m/^Summary:(.+?)$/m ) {
        $sum = $1;
        $sum =~ s/^\s+//;
        $sum =~ s/\s+$//;
    }

    $msg = '';
    if ($log =~ m/\n\n(.+)$/s) {
        $msg = $1;
        $msg =~ s/^\s+//;
        $msg =~ s/\s+$//;
    }


    # cleanup the arrays
    foreach my $ref ( (\@add, \@del, \@mod, \@ren) ) {
        my @tmp = ();
        while (my $t = pop @$ref) {
            next unless length ($t);
            next if $t =~ m!\{arch\}/!;
            next if $t =~ m!\.arch-ids/!;
            next if $t =~ m!\.arch-inventory$!;
571 572 573 574 575
           # tla cat-archive-log will give us filenames with spaces as file\(sp)name - why?
           # we can assume that any filename with \ indicates some pika escaping that we want to get rid of.
           if  ($t =~ /\\/ ){
               $t = `tla escape --unescaped '$t'`;
           }
576 577 578 579 580 581 582 583 584 585 586 587
            push (@tmp, shell_quote($t));
        }
        @$ref = @tmp;
    }
    
    #print Dumper [$sum, $msg, \@add, \@del, \@mod, \@ren]; 
    return       ($sum, $msg, \@add, \@del, \@mod, \@ren); 
}

# write/read a tag
sub tag {
    my ($tag, $commit) = @_;
588 589 590
 
    # don't use subdirs for tags yet, it could screw up other porcelains
    $tag =~ s|/|,|;
591 592
    
    if ($commit) {
593
        open(C,">","$git_dir/refs/tags/$tag")
594 595 596 597 598
            or die "Cannot create tag $tag: $!\n";
        print C "$commit\n"
            or die "Cannot write tag $tag: $!\n";
        close(C)
            or die "Cannot write tag $tag: $!\n";
599
        print " * Created tag '$tag' on '$commit'\n" if $opt_v;
600
    } else {                    # read
601
        open(C,"<","$git_dir/refs/tags/$tag")
602 603 604 605 606 607 608 609 610 611 612 613 614 615
            or die "Cannot read tag $tag: $!\n";
        $commit = <C>;
        chomp $commit;
        die "Error reading tag $tag: $!\n" unless length $commit == 40;
        close(C)
            or die "Cannot read tag $tag: $!\n";
        return $commit;
    }
}

# write/read a private tag
# reads fail softly if the tag isn't there
sub ptag {
    my ($tag, $commit) = @_;
616 617 618

    # don't use subdirs for tags yet, it could screw up other porcelains
    $tag =~ s|/|,|g; 
619
    
620 621 622
    my $tag_file = "$ptag_dir/$tag";
    my $tag_branch_dir = dirname($tag_file);
    mkpath($tag_branch_dir) unless (-d $tag_branch_dir);
623 624

    if ($commit) {              # write
625
        open(C,">",$tag_file)
626 627 628 629 630
            or die "Cannot create tag $tag: $!\n";
        print C "$commit\n"
            or die "Cannot write tag $tag: $!\n";
        close(C)
            or die "Cannot write tag $tag: $!\n";
631 632
	$rptags{$commit} = $tag 
	    unless $tag =~ m/--base-0$/;
633 634
    } else {                    # read
        # if the tag isn't there, return 0
635
        unless ( -s $tag_file) {
636 637
            return 0;
        }
638
        open(C,"<",$tag_file)
639 640 641 642 643 644
            or die "Cannot read tag $tag: $!\n";
        $commit = <C>;
        chomp $commit;
        die "Error reading tag $tag: $!\n" unless length $commit == 40;
        close(C)
            or die "Cannot read tag $tag: $!\n";
645 646 647
	unless (defined $rptags{$commit}) {
	    $rptags{$commit} = $tag;
	}
648 649 650
        return $commit;
    }
}
651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689

sub find_parents {
    #
    # Identify what branches are merging into me
    # and whether we are fully merged
    # git-merge-base <headsha> <headsha> should tell
    # me what the base of the merge should be 
    #
    my $ps = shift;

    my %branches; # holds an arrayref per branch
                  # the arrayref contains a list of
                  # merged patches between the base
                  # of the merge and the current head

    my @parents;  # parents found for this commit

    # simple loop to split the merges
    # per branch
    foreach my $merge (@{$ps->{merges}}) {
	my $branch = branchname($merge);
	unless (defined $branches{$branch} ){
	    $branches{$branch} = [];
	}
	push @{$branches{$branch}}, $merge;
    }

    #
    # foreach branch find a merge base and walk it to the 
    # head where we are, collecting the merged patchsets that
    # Arch has recorded. Keep that in @have
    # Compare that with the commits on the other branch
    # between merge-base and the tip of the branch (@need)
    # and see if we have a series of consecutive patches
    # starting from the merge base. The tip of the series
    # of consecutive patches merged is our new parent for 
    # that branch.
    #
    foreach my $branch (keys %branches) {
690 691 692 693

	# check that we actually know about the branch
	next unless -e "$git_dir/refs/heads/$branch";

694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787
	my $mergebase = `git-merge-base $branch $ps->{branch}`;
	die "Cannot find merge base for $branch and $ps->{branch}" if $?;
	chomp $mergebase;

	# now walk up to the mergepoint collecting what patches we have
	my $branchtip = git_rev_parse($ps->{branch});
	my @ancestors = `git-rev-list --merge-order $branchtip ^$mergebase`;
	my %have; # collected merges this branch has
	foreach my $merge (@{$ps->{merges}}) {
	    $have{$merge} = 1;
	}
	my %ancestorshave;
	foreach my $par (@ancestors) {
	    $par = commitid2pset($par);
	    if (defined $par->{merges}) {
		foreach my $merge (@{$par->{merges}}) {
		    $ancestorshave{$merge}=1;
		}
	    }
	}
	# print "++++ Merges in $ps->{id} are....\n";
	# my @have = sort keys %have;	print Dumper(\@have);

	# merge what we have with what ancestors have
	%have = (%have, %ancestorshave);

	# see what the remote branch has - these are the merges we 
	# will want to have in a consecutive series from the mergebase
	my $otherbranchtip = git_rev_parse($branch);
	my @needraw = `git-rev-list --merge-order $otherbranchtip ^$mergebase`;
	my @need;
	foreach my $needps (@needraw) { 	# get the psets
	    $needps = commitid2pset($needps);
	    # git-rev-list will also
	    # list commits merged in via earlier 
	    # merges. we are only interested in commits
	    # from the branch we're looking at
	    if ($branch eq $needps->{branch}) {
		push @need, $needps->{id};
	    }
	}

	# print "++++ Merges from $branch we want are....\n";
	# print Dumper(\@need);

	my $newparent;
	while (my $needed_commit = pop @need) {
	    if ($have{$needed_commit}) {
		$newparent = $needed_commit;
	    } else {
		last; # break out of the while
	    }
	}
	if ($newparent) {
	    push @parents, $newparent;
	}


    } # end foreach branch

    # prune redundant parents
    my %parents;
    foreach my $p (@parents) {
	$parents{$p} = 1;
    }
    foreach my $p (@parents) {
	next unless exists $psets{$p}{merges};
	next unless ref    $psets{$p}{merges};
	my @merges = @{$psets{$p}{merges}};
	foreach my $merge (@merges) {
	    if ($parents{$merge}) { 
		delete $parents{$merge};
	    }
	}
    }
    @parents = keys %parents;
    @parents = map { " -p " . ptag($_) } @parents;
    return @parents;
}

sub git_rev_parse {
    my $name = shift;
    my $val  = `git-rev-parse $name`;
    die "Error: git-rev-parse $name" if $?;
    chomp $val;
    return $val;
}

# resolve a SHA1 to a known patchset
sub commitid2pset {
    my $commitid = shift;
    chomp $commitid;
    my $name = $rptags{$commitid} 
	|| die "Cannot find reverse tag mapping for $commitid";
788
    $name =~ s|,|/|;
789 790 791 792
    my $ps   = $psets{$name} 
	|| (print Dumper(sort keys %psets)) && die "Cannot find patchset for $name";
    return $ps;
}