git-svn.perl 86.5 KB
Newer Older
E
Eric Wong 已提交
1
#!/usr/bin/env perl
2 3
# Copyright (C) 2006, Eric Wong <normalperson@yhbt.net>
# License: GPL v2 or later
E
Eric Wong 已提交
4 5 6
use warnings;
use strict;
use vars qw/	$AUTHOR $VERSION
7
		$SVN_URL $SVN_INFO $SVN_WC $SVN_UUID
E
Eric Wong 已提交
8
		$GIT_SVN_INDEX $GIT_SVN
9
		$GIT_DIR $GIT_SVN_DIR $REVDB/;
E
Eric Wong 已提交
10
$AUTHOR = 'Eric Wong <normalperson@yhbt.net>';
E
Eric Wong 已提交
11
$VERSION = '@@GIT_VERSION@@';
12 13 14 15 16

use Cwd qw/abs_path/;
$GIT_DIR = abs_path($ENV{GIT_DIR} || '.git');
$ENV{GIT_DIR} = $GIT_DIR;

17
my $LC_ALL = $ENV{LC_ALL};
18
my $TZ = $ENV{TZ};
E
Eric Wong 已提交
19 20 21
# make sure the svn binary gives consistent output between locales and TZs:
$ENV{TZ} = 'UTC';
$ENV{LC_ALL} = 'C';
22
$| = 1; # unbuffer STDOUT
E
Eric Wong 已提交
23 24 25

# If SVN:: library support is added, please make the dependencies
# optional and preserve the capability to use the command-line client.
26
# use eval { require SVN::... } to make it lazy load
27
# We don't use any modules not in the standard Perl distribution:
E
Eric Wong 已提交
28 29 30 31
use Carp qw/croak/;
use IO::File qw//;
use File::Basename qw/dirname basename/;
use File::Path qw/mkpath/;
32
use Getopt::Long qw/:config gnu_getopt no_ignore_case auto_abbrev pass_through/;
E
Eric Wong 已提交
33
use File::Spec qw//;
34
use POSIX qw/strftime/;
35
use IPC::Open3;
36 37
use Memoize;
memoize('revisions_eq');
38 39
memoize('cmt_metadata');
memoize('get_commit_time');
40 41 42 43

my ($SVN_PATH, $SVN, $SVN_LOG, $_use_lib);
$_use_lib = 1 unless $ENV{GIT_SVN_NO_LIB};
libsvn_load();
44
my $_optimize_commits = 1 unless $ENV{GIT_SVN_NO_OPTIMIZE_COMMITS};
E
Eric Wong 已提交
45
my $sha1 = qr/[a-f\d]{40}/;
46
my $sha1_short = qr/[a-f\d]{4,40}/;
47
my ($_revision,$_stdin,$_no_ignore_ext,$_no_stop_copy,$_help,$_rmdir,$_edit,
48
	$_find_copies_harder, $_l, $_cp_similarity, $_cp_remote,
49
	$_repack, $_repack_nr, $_repack_flags, $_q,
50
	$_message, $_file, $_follow_parent, $_no_metadata,
51
	$_template, $_shared, $_no_default_regex, $_no_graft_copy,
52
	$_limit, $_verbose, $_incremental, $_oneline, $_l_fmt, $_show_commit,
53
	$_version, $_upgrade, $_authors, $_branch_all_refs, @_opt_m);
54
my (@_branch_from, %tree_map, %users, %rusers, %equiv);
55
my ($_svn_co_url_revs, $_svn_pg_peg_revs);
56
my @repo_path_split_cache;
E
Eric Wong 已提交
57

58
my %fc_opts = ( 'no-ignore-externals' => \$_no_ignore_ext,
59
		'branch|b=s' => \@_branch_from,
60
		'follow-parent|follow' => \$_follow_parent,
61
		'branch-all-refs|B' => \$_branch_all_refs,
62 63
		'authors-file|A=s' => \$_authors,
		'repack:i' => \$_repack,
64
		'no-metadata' => \$_no_metadata,
65
		'quiet|q' => \$_q,
66
		'repack-flags|repack-args|repack-opts=s' => \$_repack_flags);
67

68 69 70 71 72
my ($_trunk, $_tags, $_branches);
my %multi_opts = ( 'trunk|T=s' => \$_trunk,
		'tags|t=s' => \$_tags,
		'branches|b=s' => \$_branches );
my %init_opts = ( 'template=s' => \$_template, 'shared' => \$_shared );
E
Eric Wong 已提交
73 74 75 76 77 78
my %cmt_opts = ( 'edit|e' => \$_edit,
		'rmdir' => \$_rmdir,
		'find-copies-harder' => \$_find_copies_harder,
		'l=i' => \$_l,
		'copy-similarity|C=i'=> \$_cp_similarity
);
79

80 81 82
# yes, 'native' sets "\n".  Patches to fix this for non-*nix systems welcome:
my %EOL = ( CR => "\015", LF => "\012", CRLF => "\015\012", native => "\012" );

E
Eric Wong 已提交
83
my %cmd = (
84 85
	fetch => [ \&fetch, "Download new revisions from SVN",
			{ 'revision|r=s' => \$_revision, %fc_opts } ],
E
Eric Wong 已提交
86
	init => [ \&init, "Initialize a repo for tracking" .
87
			  " (requires URL argument)",
88
			  \%init_opts ],
89
	commit => [ \&commit, "Commit git revisions to SVN",
E
Eric Wong 已提交
90
			{	'stdin|' => \$_stdin, %cmt_opts, %fc_opts, } ],
91 92
	'show-ignore' => [ \&show_ignore, "Show svn:ignore listings",
			{ 'revision|r=i' => \$_revision } ],
93 94
	rebuild => [ \&rebuild, "Rebuild git-svn metadata (after git clone)",
			{ 'no-ignore-externals' => \$_no_ignore_ext,
95
			  'copy-remote|remote=s' => \$_cp_remote,
96
			  'upgrade' => \$_upgrade } ],
97 98 99
	'graft-branches' => [ \&graft_branches,
			'Detect merges/branches from already imported history',
			{ 'merge-rx|m' => \@_opt_m,
100 101
			  'branch|b=s' => \@_branch_from,
			  'branch-all-refs|B' => \$_branch_all_refs,
102 103 104 105 106 107 108 109
			  'no-default-regex' => \$_no_default_regex,
			  'no-graft-copy' => \$_no_graft_copy } ],
	'multi-init' => [ \&multi_init,
			'Initialize multiple trees (like git-svnimport)',
			{ %multi_opts, %fc_opts } ],
	'multi-fetch' => [ \&multi_fetch,
			'Fetch multiple trees (like git-svnimport)',
			\%fc_opts ],
110 111 112 113 114 115 116 117 118
	'log' => [ \&show_log, 'Show commit logs',
			{ 'limit=i' => \$_limit,
			  'revision|r=s' => \$_revision,
			  'verbose|v' => \$_verbose,
			  'incremental' => \$_incremental,
			  'oneline' => \$_oneline,
			  'show-commit' => \$_show_commit,
			  'authors-file|A=s' => \$_authors,
			} ],
E
Eric Wong 已提交
119 120 121 122
	'commit-diff' => [ \&commit_diff, 'Commit a diff between two trees',
			{ 'message|m=s' => \$_message,
			  'file|F=s' => \$_file,
			%cmt_opts } ],
E
Eric Wong 已提交
123
);
124

E
Eric Wong 已提交
125 126 127 128 129 130 131 132 133
my $cmd;
for (my $i = 0; $i < @ARGV; $i++) {
	if (defined $cmd{$ARGV[$i]}) {
		$cmd = $ARGV[$i];
		splice @ARGV, $i, 1;
		last;
	}
};

134
my %opts = %{$cmd{$cmd}->[2]} if (defined $cmd);
135

136
read_repo_config(\%opts);
137 138 139 140
my $rv = GetOptions(%opts, 'help|H|h' => \$_help,
				'version|V' => \$_version,
				'id|i=s' => \$GIT_SVN);
exit 1 if (!$rv && $cmd ne 'log');
141

142
set_default_vals();
E
Eric Wong 已提交
143
usage(0) if $_help;
144
version() if $_version;
145
usage(1) unless defined $cmd;
146
init_vars();
147
load_authors() if $_authors;
148
load_all_refs() if $_branch_all_refs;
149
svn_compat_check() unless $_use_lib;
150
migration_check() unless $cmd =~ /^(?:init|rebuild|multi-init)$/;
E
Eric Wong 已提交
151 152 153 154 155 156 157 158 159 160
$cmd{$cmd}->[0]->(@ARGV);
exit 0;

####################### primary functions ######################
sub usage {
	my $exit = shift || 0;
	my $fd = $exit ? \*STDERR : \*STDOUT;
	print $fd <<"";
git-svn - bidirectional operations between a single Subversion tree and git
Usage: $0 <command> [options] [arguments]\n
161 162

	print $fd "Available commands:\n" unless $cmd;
E
Eric Wong 已提交
163 164

	foreach (sort keys %cmd) {
165
		next if $cmd && $cmd ne $_;
166
		print $fd '  ',pack('A13',$_),$cmd{$_}->[1],"\n";
167 168
		foreach (keys %{$cmd{$_}->[2]}) {
			# prints out arguments as they should be passed:
169
			my $x = s#[:=]s$## ? '<arg>' : s#[:=]i$## ? '<num>' : '';
170 171 172 173
			print $fd ' ' x 17, join(', ', map { length $_ > 1 ?
							"--$_" : "-$_" }
						split /\|/,$_)," $x\n";
		}
E
Eric Wong 已提交
174 175
	}
	print $fd <<"";
176 177 178 179
\nGIT_SVN_ID may be set in the environment or via the --id/-i switch to an
arbitrary identifier if you're tracking multiple SVN branches/repositories in
one git repository and want to keep them separate.  See git-svn(1) for more
information.
E
Eric Wong 已提交
180 181 182 183

	exit $exit;
}

184 185 186 187 188
sub version {
	print "git-svn version $VERSION\n";
	exit 0;
}

E
Eric Wong 已提交
189
sub rebuild {
190 191 192
	if (quiet_run(qw/git-rev-parse --verify/,"refs/remotes/$GIT_SVN^0")) {
		copy_remote_ref();
	}
E
Eric Wong 已提交
193 194
	$SVN_URL = shift or undef;
	my $newest_rev = 0;
195 196 197 198 199
	if ($_upgrade) {
		sys('git-update-ref',"refs/remotes/$GIT_SVN","$GIT_SVN-HEAD");
	} else {
		check_upgrade_needed();
	}
E
Eric Wong 已提交
200 201 202 203

	my $pid = open(my $rev_list,'-|');
	defined $pid or croak $!;
	if ($pid == 0) {
204
		exec("git-rev-list","refs/remotes/$GIT_SVN") or croak $!;
E
Eric Wong 已提交
205
	}
206
	my $latest;
E
Eric Wong 已提交
207 208 209 210 211 212
	while (<$rev_list>) {
		chomp;
		my $c = $_;
		croak "Non-SHA1: $c\n" unless $c =~ /^$sha1$/o;
		my @commit = grep(/^git-svn-id: /,`git-cat-file commit $c`);
		next if (!@commit); # skip merges
213 214 215 216
		my ($url, $rev, $uuid) = extract_metadata($commit[$#commit]);
		if (!$rev || !$uuid) {
			croak "Unable to extract revision or UUID from ",
				"$c, $commit[$#commit]\n";
E
Eric Wong 已提交
217
		}
218 219 220

		# if we merged or otherwise started elsewhere, this is
		# how we break out of it
221
		next if (defined $SVN_UUID && ($uuid ne $SVN_UUID));
222
		next if (defined $SVN_URL && defined $url && ($url ne $SVN_URL));
223 224

		unless (defined $latest) {
E
Eric Wong 已提交
225 226 227 228
			if (!$SVN_URL && !$url) {
				croak "SVN repository location required: $url\n";
			}
			$SVN_URL ||= $url;
229 230
			$SVN_UUID ||= $uuid;
			setup_git_svn();
231
			$latest = $rev;
E
Eric Wong 已提交
232
		}
233 234
		revdb_set($REVDB, $rev, $c);
		print "r$rev = $c\n";
E
Eric Wong 已提交
235 236 237
		$newest_rev = $rev if ($rev > $newest_rev);
	}
	close $rev_list or croak $?;
238 239

	goto out if $_use_lib;
E
Eric Wong 已提交
240
	if (!chdir $SVN_WC) {
241
		svn_cmd_checkout($SVN_URL, $latest, $SVN_WC);
E
Eric Wong 已提交
242 243 244 245 246 247 248 249 250 251
		chdir $SVN_WC or croak $!;
	}

	$pid = fork;
	defined $pid or croak $!;
	if ($pid == 0) {
		my @svn_up = qw(svn up);
		push @svn_up, '--ignore-externals' unless $_no_ignore_ext;
		sys(@svn_up,"-r$newest_rev");
		$ENV{GIT_INDEX_FILE} = $GIT_SVN_INDEX;
252
		index_changes();
253
		exec('git-write-tree') or croak $!;
E
Eric Wong 已提交
254 255
	}
	waitpid $pid, 0;
256
	croak $? if $?;
257
out:
258 259 260 261 262 263
	if ($_upgrade) {
		print STDERR <<"";
Keeping deprecated refs/head/$GIT_SVN-HEAD for now.  Please remove it
when you have upgraded your tools and habits to use refs/remotes/$GIT_SVN

	}
E
Eric Wong 已提交
264 265 266
}

sub init {
267
	my $url = shift or die "SVN repository location required " .
E
Eric Wong 已提交
268
				"as a command-line argument\n";
269 270 271 272 273 274 275 276 277 278 279
	$url =~ s!/+$!!; # strip trailing slash

	if (my $repo_path = shift) {
		unless (-d $repo_path) {
			mkpath([$repo_path]);
		}
		$GIT_DIR = $ENV{GIT_DIR} = $repo_path . "/.git";
		init_vars();
	}

	$SVN_URL = $url;
E
Eric Wong 已提交
280
	unless (-d $GIT_DIR) {
281 282 283 284
		my @init_db = ('git-init-db');
		push @init_db, "--template=$_template" if defined $_template;
		push @init_db, "--shared" if defined $_shared;
		sys(@init_db);
E
Eric Wong 已提交
285 286 287 288 289
	}
	setup_git_svn();
}

sub fetch {
290
	check_upgrade_needed();
291
	$SVN_URL ||= file_to_s("$GIT_SVN_DIR/info/url");
292 293 294 295 296 297 298 299 300 301
	my $ret = $_use_lib ? fetch_lib(@_) : fetch_cmd(@_);
	if ($ret->{commit} && quiet_run(qw(git-rev-parse --verify
						refs/heads/master^0))) {
		sys(qw(git-update-ref refs/heads/master),$ret->{commit});
	}
	return $ret;
}

sub fetch_cmd {
	my (@parents) = @_;
E
Eric Wong 已提交
302
	my @log_args = -d $SVN_WC ? ($SVN_WC) : ($SVN_URL);
303 304
	unless ($_revision) {
		$_revision = -d $SVN_WC ? 'BASE:HEAD' : '0:HEAD';
E
Eric Wong 已提交
305
	}
306
	push @log_args, "-r$_revision";
E
Eric Wong 已提交
307 308
	push @log_args, '--stop-on-copy' unless $_no_stop_copy;

309
	my $svn_log = svn_log_raw(@log_args);
E
Eric Wong 已提交
310

311
	my $base = next_log_entry($svn_log) or croak "No base revision!\n";
312 313 314 315 316
	# don't need last_revision from grab_base_rev() because
	# user could've specified a different revision to skip (they
	# didn't want to import certain revisions into git for whatever
	# reason, so trust $base->{revision} instead.
	my (undef, $last_commit) = svn_grab_base_rev();
E
Eric Wong 已提交
317
	unless (-d $SVN_WC) {
318
		svn_cmd_checkout($SVN_URL,$base->{revision},$SVN_WC);
E
Eric Wong 已提交
319
		chdir $SVN_WC or croak $!;
320
		read_uuid();
E
Eric Wong 已提交
321
		$last_commit = git_commit($base, @parents);
322
		assert_tree($last_commit);
E
Eric Wong 已提交
323 324
	} else {
		chdir $SVN_WC or croak $!;
325
		read_uuid();
326 327 328 329 330 331 332
		# looks like a user manually cp'd and svn switch'ed
		unless ($last_commit) {
			sys(qw/svn revert -R ./);
			assert_svn_wc_clean($base->{revision});
			$last_commit = git_commit($base, @parents);
			assert_tree($last_commit);
		}
E
Eric Wong 已提交
333 334 335
	}
	my @svn_up = qw(svn up);
	push @svn_up, '--ignore-externals' unless $_no_ignore_ext;
336 337 338 339 340 341
	my $last = $base;
	while (my $log_msg = next_log_entry($svn_log)) {
		if ($last->{revision} >= $log_msg->{revision}) {
			croak "Out of order: last >= current: ",
				"$last->{revision} >= $log_msg->{revision}\n";
		}
342 343 344 345 346
		# Revert is needed for cases like:
		# https://svn.musicpd.org/Jamming/trunk (r166:167), but
		# I can't seem to reproduce something like that on a test...
		sys(qw/svn revert -R ./);
		assert_svn_wc_clean($last->{revision});
347
		sys(@svn_up,"-r$log_msg->{revision}");
E
Eric Wong 已提交
348
		$last_commit = git_commit($log_msg, $last_commit, @parents);
349
		$last = $log_msg;
E
Eric Wong 已提交
350
	}
351
	close $svn_log->{fh};
352
	$last->{commit} = $last_commit;
353
	return $last;
E
Eric Wong 已提交
354 355
}

356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403
sub fetch_lib {
	my (@parents) = @_;
	$SVN_URL ||= file_to_s("$GIT_SVN_DIR/info/url");
	my $repo;
	($repo, $SVN_PATH) = repo_path_split($SVN_URL);
	$SVN_LOG ||= libsvn_connect($repo);
	$SVN ||= libsvn_connect($repo);
	my ($last_rev, $last_commit) = svn_grab_base_rev();
	my ($base, $head) = libsvn_parse_revision($last_rev);
	if ($base > $head) {
		return { revision => $last_rev, commit => $last_commit }
	}
	my $index = set_index($GIT_SVN_INDEX);

	# limit ourselves and also fork() since get_log won't release memory
	# after processing a revision and SVN stuff seems to leak
	my $inc = 1000;
	my ($min, $max) = ($base, $head < $base+$inc ? $head : $base+$inc);
	read_uuid();
	if (defined $last_commit) {
		unless (-e $GIT_SVN_INDEX) {
			sys(qw/git-read-tree/, $last_commit);
		}
		chomp (my $x = `git-write-tree`);
		my ($y) = (`git-cat-file commit $last_commit`
							=~ /^tree ($sha1)/m);
		if ($y ne $x) {
			unlink $GIT_SVN_INDEX or croak $!;
			sys(qw/git-read-tree/, $last_commit);
		}
		chomp ($x = `git-write-tree`);
		if ($y ne $x) {
			print STDERR "trees ($last_commit) $y != $x\n",
				 "Something is seriously wrong...\n";
		}
	}
	while (1) {
		# fork, because using SVN::Pool with get_log() still doesn't
		# seem to help enough to keep memory usage down.
		defined(my $pid = fork) or croak $!;
		if (!$pid) {
			$SVN::Error::handler = \&libsvn_skip_unknown_revs;

			# Yes I'm perfectly aware that the fourth argument
			# below is the limit revisions number.  Unfortunately
			# performance sucks with it enabled, so it's much
			# faster to fetch revision ranges instead of relying
			# on the limiter.
404 405
			libsvn_get_log($SVN_LOG, '/'.$SVN_PATH,
					$min, $max, 0, 1, 1,
406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434
				sub {
					my $log_msg;
					if ($last_commit) {
						$log_msg = libsvn_fetch(
							$last_commit, @_);
						$last_commit = git_commit(
							$log_msg,
							$last_commit,
							@parents);
					} else {
						$log_msg = libsvn_new_tree(@_);
						$last_commit = git_commit(
							$log_msg, @parents);
					}
				});
			exit 0;
		}
		waitpid $pid, 0;
		croak $? if $?;
		($last_rev, $last_commit) = svn_grab_base_rev();
		last if ($max >= $head);
		$min = $max + 1;
		$max += $inc;
		$max = $head if ($max > $head);
	}
	restore_index($index);
	return { revision => $last_rev, commit => $last_commit };
}

E
Eric Wong 已提交
435 436
sub commit {
	my (@commits) = @_;
437
	check_upgrade_needed();
E
Eric Wong 已提交
438 439 440 441
	if ($_stdin || !@commits) {
		print "Reading from stdin...\n";
		@commits = ();
		while (<STDIN>) {
442
			if (/\b($sha1_short)\b/o) {
E
Eric Wong 已提交
443 444 445 446 447
				unshift @commits, $1;
			}
		}
	}
	my @revs;
448 449 450 451 452 453 454 455 456
	foreach my $c (@commits) {
		chomp(my @tmp = safe_qx('git-rev-parse',$c));
		if (scalar @tmp == 1) {
			push @revs, $tmp[0];
		} elsif (scalar @tmp > 1) {
			push @revs, reverse (safe_qx('git-rev-list',@tmp));
		} else {
			die "Failed to rev-parse $c\n";
		}
E
Eric Wong 已提交
457 458
	}
	chomp @revs;
459 460 461 462 463 464
	$_use_lib ? commit_lib(@revs) : commit_cmd(@revs);
	print "Done committing ",scalar @revs," revisions to SVN\n";
}

sub commit_cmd {
	my (@revs) = @_;
E
Eric Wong 已提交
465

466
	chdir $SVN_WC or croak "Unable to chdir $SVN_WC: $!\n";
467
	my $info = svn_info('.');
468 469 470 471 472 473 474 475
	my $fetched = fetch();
	if ($info->{Revision} != $fetched->{revision}) {
		print STDERR "There are new revisions that were fetched ",
				"and need to be merged (or acknowledged) ",
				"before committing.\n";
		exit 1;
	}
	$info = svn_info('.');
476
	read_uuid($info);
477
	my $last = $fetched;
E
Eric Wong 已提交
478
	foreach my $c (@revs) {
479
		my $mods = svn_checkout_tree($last, $c);
480 481 482 483
		if (scalar @$mods == 0) {
			print "Skipping, no changes detected\n";
			next;
		}
484
		$last = svn_commit_tree($last, $c);
E
Eric Wong 已提交
485 486 487
	}
}

488 489 490 491
sub commit_lib {
	my (@revs) = @_;
	my ($r_last, $cmt_last) = svn_grab_base_rev();
	defined $r_last or die "Must have an existing revision to commit\n";
492
	my $fetched = fetch();
493 494 495 496 497 498 499 500 501 502 503 504
	if ($r_last != $fetched->{revision}) {
		print STDERR "There are new revisions that were fetched ",
				"and need to be merged (or acknowledged) ",
				"before committing.\n",
				"last rev: $r_last\n",
				" current: $fetched->{revision}\n";
		exit 1;
	}
	read_uuid();
	my @lock = $SVN::Core::VERSION ge '1.2.0' ? (undef, 0) : ();
	my $commit_msg = "$GIT_SVN_DIR/.svn-commit.tmp.$$";

E
Eric Wong 已提交
505
	set_svn_commit_env();
506
	foreach my $c (@revs) {
507 508
		my $log_msg = get_commit_message($c, $commit_msg);

509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529
		# fork for each commit because there's a memory leak I
		# can't track down... (it's probably in the SVN code)
		defined(my $pid = open my $fh, '-|') or croak $!;
		if (!$pid) {
			my $ed = SVN::Git::Editor->new(
					{	r => $r_last,
						ra => $SVN,
						c => $c,
						svn_path => $SVN_PATH
					},
					$SVN->get_commit_editor(
						$log_msg->{msg},
						sub {
							libsvn_commit_cb(
								@_, $c,
								$log_msg->{msg},
								$r_last,
								$cmt_last)
						},
						@lock)
					);
530
			my $mods = libsvn_checkout_tree($cmt_last, $c, $ed);
531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548
			if (@$mods == 0) {
				print "No changes\nr$r_last = $cmt_last\n";
				$ed->abort_edit;
			} else {
				$ed->close_edit;
			}
			exit 0;
		}
		my ($r_new, $cmt_new, $no);
		while (<$fh>) {
			print $_;
			chomp;
			if (/^r(\d+) = ($sha1)$/o) {
				($r_new, $cmt_new) = ($1, $2);
			} elsif ($_ eq 'No changes') {
				$no = 1;
			}
		}
549
		close $fh or croak $?;
550 551 552 553 554 555 556 557
		if (! defined $r_new && ! defined $cmt_new) {
			unless ($no) {
				die "Failed to parse revision information\n";
			}
		} else {
			($r_last, $cmt_last) = ($r_new, $cmt_new);
		}
	}
558
	$ENV{LC_ALL} = 'C';
559 560
	unlink $commit_msg;
}
561

562
sub show_ignore {
563
	$SVN_URL ||= file_to_s("$GIT_SVN_DIR/info/url");
564 565 566 567 568 569 570 571 572
	$_use_lib ? show_ignore_lib() : show_ignore_cmd();
}

sub show_ignore_cmd {
	require File::Find or die $!;
	if (defined $_revision) {
		die "-r/--revision option doesn't work unless the Perl SVN ",
			"libraries are used\n";
	}
573 574 575 576
	chdir $SVN_WC or croak $!;
	my %ign;
	File::Find::find({wanted=>sub{if(lstat $_ && -d _ && -d "$_/.svn"){
		s#^\./##;
577
		@{$ign{$_}} = svn_propget_base('svn:ignore', $_);
578 579 580 581 582 583 584 585 586 587 588
		}}, no_chdir=>1},'.');

	print "\n# /\n";
	foreach (@{$ign{'.'}}) { print '/',$_ if /\S/ }
	delete $ign{'.'};
	foreach my $i (sort keys %ign) {
		print "\n# ",$i,"\n";
		foreach (@{$ign{$i}}) { print '/',$i,'/',$_ if /\S/ }
	}
}

589 590 591 592 593 594 595 596
sub show_ignore_lib {
	my $repo;
	($repo, $SVN_PATH) = repo_path_split($SVN_URL);
	$SVN ||= libsvn_connect($repo);
	my $r = defined $_revision ? $_revision : $SVN->get_latest_revnum;
	libsvn_traverse_ignore(\*STDOUT, $SVN_PATH, $r);
}

597 598 599 600 601 602 603 604 605 606 607 608 609 610
sub graft_branches {
	my $gr_file = "$GIT_DIR/info/grafts";
	my ($grafts, $comments) = read_grafts($gr_file);
	my $gr_sha1;

	if (%$grafts) {
		# temporarily disable our grafts file to make this idempotent
		chomp($gr_sha1 = safe_qx(qw/git-hash-object -w/,$gr_file));
		rename $gr_file, "$gr_file~$gr_sha1" or croak $!;
	}

	my $l_map = read_url_paths();
	my @re = map { qr/$_/is } @_opt_m if @_opt_m;
	unless ($_no_default_regex) {
611 612 613
		push @re, (qr/\b(?:merge|merging|merged)\s+with\s+([\w\.\-]+)/i,
			qr/\b(?:merge|merging|merged)\s+([\w\.\-]+)/i,
			qr/\b(?:from|of)\s+([\w\.\-]+)/i );
614 615 616 617
	}
	foreach my $u (keys %$l_map) {
		if (@re) {
			foreach my $p (keys %{$l_map->{$u}}) {
618
				graft_merge_msg($grafts,$l_map,$u,$p,@re);
619 620
			}
		}
621 622 623 624 625 626 627
		unless ($_no_graft_copy) {
			if ($_use_lib) {
				graft_file_copy_lib($grafts,$l_map,$u);
			} else {
				graft_file_copy_cmd($grafts,$l_map,$u);
			}
		}
628
	}
629
	graft_tree_joins($grafts);
630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661

	write_grafts($grafts, $comments, $gr_file);
	unlink "$gr_file~$gr_sha1" if $gr_sha1;
}

sub multi_init {
	my $url = shift;
	$_trunk ||= 'trunk';
	$_trunk =~ s#/+$##;
	$url =~ s#/+$## if $url;
	if ($_trunk !~ m#^[a-z\+]+://#) {
		$_trunk = '/' . $_trunk if ($_trunk !~ m#^/#);
		unless ($url) {
			print STDERR "E: '$_trunk' is not a complete URL ",
				"and a separate URL is not specified\n";
			exit 1;
		}
		$_trunk = $url . $_trunk;
	}
	if ($GIT_SVN eq 'git-svn') {
		print "GIT_SVN_ID set to 'trunk' for $_trunk\n";
		$GIT_SVN = $ENV{GIT_SVN_ID} = 'trunk';
	}
	init_vars();
	init($_trunk);
	complete_url_ls_init($url, $_branches, '--branches/-b', '');
	complete_url_ls_init($url, $_tags, '--tags/-t', 'tags/');
}

sub multi_fetch {
	# try to do trunk first, since branches/tags
	# may be descended from it.
662 663
	if (-e "$GIT_DIR/svn/trunk/info/url") {
		fetch_child_id('trunk', @_);
664 665 666 667
	}
	rec_fetch('', "$GIT_DIR/svn", @_);
}

668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692
sub show_log {
	my (@args) = @_;
	my ($r_min, $r_max);
	my $r_last = -1; # prevent dupes
	rload_authors() if $_authors;
	if (defined $TZ) {
		$ENV{TZ} = $TZ;
	} else {
		delete $ENV{TZ};
	}
	if (defined $_revision) {
		if ($_revision =~ /^(\d+):(\d+)$/) {
			($r_min, $r_max) = ($1, $2);
		} elsif ($_revision =~ /^\d+$/) {
			$r_min = $r_max = $_revision;
		} else {
			print STDERR "-r$_revision is not supported, use ",
				"standard \'git log\' arguments instead\n";
			exit 1;
		}
	}

	my $pid = open(my $log,'-|');
	defined $pid or croak $!;
	if (!$pid) {
693
		exec(git_svn_log_cmd($r_min,$r_max), @args) or croak $!;
694 695 696
	}
	setup_pager();
	my (@k, $c, $d);
697

698 699 700
	while (<$log>) {
		if (/^commit ($sha1_short)/o) {
			my $cmt = $1;
701
			if ($c && cmt_showable($c) && $c->{r} != $r_last) {
702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719
				$r_last = $c->{r};
				process_commit($c, $r_min, $r_max, \@k) or
								goto out;
			}
			$d = undef;
			$c = { c => $cmt };
		} elsif (/^author (.+) (\d+) ([\-\+]?\d+)$/) {
			get_author_info($c, $1, $2, $3);
		} elsif (/^(?:tree|parent|committer) /) {
			# ignore
		} elsif (/^:\d{6} \d{6} $sha1_short/o) {
			push @{$c->{raw}}, $_;
		} elsif (/^diff /) {
			$d = 1;
			push @{$c->{diff}}, $_;
		} elsif ($d) {
			push @{$c->{diff}}, $_;
		} elsif (/^    (git-svn-id:.+)$/) {
720
			(undef, $c->{r}, undef) = extract_metadata($1);
721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739
		} elsif (s/^    //) {
			push @{$c->{l}}, $_;
		}
	}
	if ($c && defined $c->{r} && $c->{r} != $r_last) {
		$r_last = $c->{r};
		process_commit($c, $r_min, $r_max, \@k);
	}
	if (@k) {
		my $swap = $r_max;
		$r_max = $r_min;
		$r_min = $swap;
		process_commit($_, $r_min, $r_max) foreach reverse @k;
	}
out:
	close $log;
	print '-' x72,"\n" unless $_incremental || $_oneline;
}

E
Eric Wong 已提交
740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788
sub commit_diff_usage {
	print STDERR "Usage: $0 commit-diff <tree-ish> <tree-ish> [<URL>]\n";
	exit 1
}

sub commit_diff {
	if (!$_use_lib) {
		print STDERR "commit-diff must be used with SVN libraries\n";
		exit 1;
	}
	my $ta = shift or commit_diff_usage();
	my $tb = shift or commit_diff_usage();
	if (!eval { $SVN_URL = shift || file_to_s("$GIT_SVN_DIR/info/url") }) {
		print STDERR "Needed URL or usable git-svn id command-line\n";
		commit_diff_usage();
	}
	if (defined $_message && defined $_file) {
		print STDERR "Both --message/-m and --file/-F specified ",
				"for the commit message.\n",
				"I have no idea what you mean\n";
		exit 1;
	}
	if (defined $_file) {
		$_message = file_to_s($_message);
	} else {
		$_message ||= get_commit_message($tb,
					"$GIT_DIR/.svn-commit.tmp.$$")->{msg};
	}
	my $repo;
	($repo, $SVN_PATH) = repo_path_split($SVN_URL);
	$SVN_LOG ||= libsvn_connect($repo);
	$SVN ||= libsvn_connect($repo);
	my @lock = $SVN::Core::VERSION ge '1.2.0' ? (undef, 0) : ();
	my $ed = SVN::Git::Editor->new({	r => $SVN->get_latest_revnum,
						ra => $SVN, c => $tb,
						svn_path => $SVN_PATH
					},
				$SVN->get_commit_editor($_message,
					sub {print "Committed $_[0]\n"},@lock)
				);
	my $mods = libsvn_checkout_tree($ta, $tb, $ed);
	if (@$mods == 0) {
		print "No changes\n$ta == $tb\n";
		$ed->abort_edit;
	} else {
		$ed->close_edit;
	}
}

E
Eric Wong 已提交
789 790
########################### utility functions #########################

791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836
sub cmt_showable {
	my ($c) = @_;
	return 1 if defined $c->{r};
	if ($c->{l} && $c->{l}->[-1] eq "...\n" &&
				$c->{a_raw} =~ /\@([a-f\d\-]+)>$/) {
		my @msg = safe_qx(qw/git-cat-file commit/, $c->{c});
		shift @msg while ($msg[0] ne "\n");
		shift @msg;
		@{$c->{l}} = grep !/^git-svn-id: /, @msg;

		(undef, $c->{r}, undef) = extract_metadata(
				(grep(/^git-svn-id: /, @msg))[-1]);
	}
	return defined $c->{r};
}

sub git_svn_log_cmd {
	my ($r_min, $r_max) = @_;
	my @cmd = (qw/git-log --abbrev-commit --pretty=raw
			--default/, "refs/remotes/$GIT_SVN");
	push @cmd, '--summary' if $_verbose;
	return @cmd unless defined $r_max;
	if ($r_max == $r_min) {
		push @cmd, '--max-count=1';
		if (my $c = revdb_get($REVDB, $r_max)) {
			push @cmd, $c;
		}
	} else {
		my ($c_min, $c_max);
		$c_max = revdb_get($REVDB, $r_max);
		$c_min = revdb_get($REVDB, $r_min);
		if ($c_min && $c_max) {
			if ($r_max > $r_max) {
				push @cmd, "$c_min..$c_max";
			} else {
				push @cmd, "$c_max..$c_min";
			}
		} elsif ($r_max > $r_min) {
			push @cmd, $c_max;
		} else {
			push @cmd, $c_min;
		}
	}
	return @cmd;
}

837 838 839 840
sub fetch_child_id {
	my $id = shift;
	print "Fetching $id\n";
	my $ref = "$GIT_DIR/refs/remotes/$id";
841
	defined(my $pid = open my $fh, '-|') or croak $!;
842
	if (!$pid) {
843
		$_repack = undef;
844 845 846 847 848 849
		$GIT_SVN = $ENV{GIT_SVN_ID} = $id;
		init_vars();
		fetch(@_);
		exit 0;
	}
	while (<$fh>) {
850 851
		print $_;
		check_repack() if (/^r\d+ = $sha1/);
852
	}
853
	close $fh or croak $?;
854 855
}

856 857 858 859 860 861 862 863
sub rec_fetch {
	my ($pfx, $p, @args) = @_;
	my @dir;
	foreach (sort <$p/*>) {
		if (-r "$_/info/url") {
			$pfx .= '/' if $pfx && $pfx !~ m!/$!;
			my $id = $pfx . basename $_;
			next if $id eq 'trunk';
864
			fetch_child_id($id, @args);
865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891
		} elsif (-d $_) {
			push @dir, $_;
		}
	}
	foreach (@dir) {
		my $x = $_;
		$x =~ s!^\Q$GIT_DIR\E/svn/!!;
		rec_fetch($x, $_);
	}
}

sub complete_url_ls_init {
	my ($url, $var, $switch, $pfx) = @_;
	unless ($var) {
		print STDERR "W: $switch not specified\n";
		return;
	}
	$var =~ s#/+$##;
	if ($var !~ m#^[a-z\+]+://#) {
		$var = '/' . $var if ($var !~ m#^/#);
		unless ($url) {
			print STDERR "E: '$var' is not a complete URL ",
				"and a separate URL is not specified\n";
			exit 1;
		}
		$var = $url . $var;
	}
892 893
	chomp(my @ls = $_use_lib ? libsvn_ls_fullurl($var)
				: safe_qx(qw/svn ls --non-interactive/, $var));
894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934
	my $old = $GIT_SVN;
	defined(my $pid = fork) or croak $!;
	if (!$pid) {
		foreach my $u (map { "$var/$_" } (grep m!/$!, @ls)) {
			$u =~ s#/+$##;
			if ($u !~ m!\Q$var\E/(.+)$!) {
				print STDERR "W: Unrecognized URL: $u\n";
				die "This should never happen\n";
			}
			my $id = $pfx.$1;
			print "init $u => $id\n";
			$GIT_SVN = $ENV{GIT_SVN_ID} = $id;
			init_vars();
			init($u);
		}
		exit 0;
	}
	waitpid $pid, 0;
	croak $? if $?;
}

sub common_prefix {
	my $paths = shift;
	my %common;
	foreach (@$paths) {
		my @tmp = split m#/#, $_;
		my $p = '';
		while (my $x = shift @tmp) {
			$p .= "/$x";
			$common{$p} ||= 0;
			$common{$p}++;
		}
	}
	foreach (sort {length $b <=> length $a} keys %common) {
		if ($common{$_} == @$paths) {
			return $_;
		}
	}
	return '';
}

935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005
# grafts set here are 'stronger' in that they're based on actual tree
# matches, and won't be deleted from merge-base checking in write_grafts()
sub graft_tree_joins {
	my $grafts = shift;
	map_tree_joins() if (@_branch_from && !%tree_map);
	return unless %tree_map;

	git_svn_each(sub {
		my $i = shift;
		defined(my $pid = open my $fh, '-|') or croak $!;
		if (!$pid) {
			exec qw/git-rev-list --pretty=raw/,
					"refs/remotes/$i" or croak $!;
		}
		while (<$fh>) {
			next unless /^commit ($sha1)$/o;
			my $c = $1;
			my ($t) = (<$fh> =~ /^tree ($sha1)$/o);
			next unless $tree_map{$t};

			my $l;
			do {
				$l = readline $fh;
			} until ($l =~ /^committer (?:.+) (\d+) ([\-\+]?\d+)$/);

			my ($s, $tz) = ($1, $2);
			if ($tz =~ s/^\+//) {
				$s += tz_to_s_offset($tz);
			} elsif ($tz =~ s/^\-//) {
				$s -= tz_to_s_offset($tz);
			}

			my ($url_a, $r_a, $uuid_a) = cmt_metadata($c);

			foreach my $p (@{$tree_map{$t}}) {
				next if $p eq $c;
				my $mb = eval {
					safe_qx('git-merge-base', $c, $p)
				};
				next unless ($@ || $?);
				if (defined $r_a) {
					# see if SVN says it's a relative
					my ($url_b, $r_b, $uuid_b) =
							cmt_metadata($p);
					next if (defined $url_b &&
							defined $url_a &&
							($url_a eq $url_b) &&
							($uuid_a eq $uuid_b));
					if ($uuid_a eq $uuid_b) {
						if ($r_b < $r_a) {
							$grafts->{$c}->{$p} = 2;
							next;
						} elsif ($r_b > $r_a) {
							$grafts->{$p}->{$c} = 2;
							next;
						}
					}
				}
				my $ct = get_commit_time($p);
				if ($ct < $s) {
					$grafts->{$c}->{$p} = 2;
				} elsif ($ct > $s) {
					$grafts->{$p}->{$c} = 2;
				}
				# what should we do when $ct == $s ?
			}
		}
		close $fh or croak $?;
	});
}

1006
# this isn't funky-filename safe, but good enough for now...
1007
sub graft_file_copy_cmd {
1008 1009 1010
	my ($grafts, $l_map, $u) = @_;
	my $paths = $l_map->{$u};
	my $pfx = common_prefix([keys %$paths]);
1011
	$SVN_URL ||= $u.$pfx;
1012 1013 1014
	my $pid = open my $fh, '-|';
	defined $pid or croak $!;
	unless ($pid) {
1015 1016 1017
		my @exec = qw/svn log -v/;
		push @exec, "-r$_revision" if defined $_revision;
		exec @exec, $u.$pfx or croak $!;
1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029
	}
	my ($r, $mp) = (undef, undef);
	while (<$fh>) {
		chomp;
		if (/^\-{72}$/) {
			$mp = $r = undef;
		} elsif (/^r(\d+) \| /) {
			$r = $1 unless defined $r;
		} elsif (/^Changed paths:/) {
			$mp = 1;
		} elsif ($mp && m#^   [AR] /(\S.*?) \(from /(\S+?):(\d+)\)$#) {
			my ($p1, $p0, $r0) = ($1, $2, $3);
1030
			my $c = find_graft_path_commit($paths, $p1, $r);
1031
			next unless $c;
1032
			find_graft_path_parents($grafts, $paths, $c, $p0, $r0);
1033 1034 1035 1036
		}
	}
}

1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047
sub graft_file_copy_lib {
	my ($grafts, $l_map, $u) = @_;
	my $tree_paths = $l_map->{$u};
	my $pfx = common_prefix([keys %$tree_paths]);
	my ($repo, $path) = repo_path_split($u.$pfx);
	$SVN_LOG ||= libsvn_connect($repo);
	$SVN ||= libsvn_connect($repo);

	my ($base, $head) = libsvn_parse_revision();
	my $inc = 1000;
	my ($min, $max) = ($base, $head < $base+$inc ? $head : $base+$inc);
1048 1049
	my $eh = $SVN::Error::handler;
	$SVN::Error::handler = \&libsvn_skip_unknown_revs;
1050 1051
	while (1) {
		my $pool = SVN::Pool->new;
1052
		libsvn_get_log($SVN_LOG, "/$path", $min, $max, 0, 1, 1,
1053 1054 1055 1056 1057 1058 1059 1060 1061 1062
			sub {
				libsvn_graft_file_copies($grafts, $tree_paths,
							$path, @_);
			}, $pool);
		$pool->clear;
		last if ($max >= $head);
		$min = $max + 1;
		$max += $inc;
		$max = $head if ($max > $head);
	}
1063
	$SVN::Error::handler = $eh;
1064 1065
}

1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083
sub process_merge_msg_matches {
	my ($grafts, $l_map, $u, $p, $c, @matches) = @_;
	my (@strong, @weak);
	foreach (@matches) {
		# merging with ourselves is not interesting
		next if $_ eq $p;
		if ($l_map->{$u}->{$_}) {
			push @strong, $_;
		} else {
			push @weak, $_;
		}
	}
	foreach my $w (@weak) {
		last if @strong;
		# no exact match, use branch name as regexp.
		my $re = qr/\Q$w\E/i;
		foreach (keys %{$l_map->{$u}}) {
			if (/$re/) {
1084
				push @strong, $l_map->{$u}->{$_};
1085 1086 1087 1088 1089 1090 1091 1092
				last;
			}
		}
		last if @strong;
		$w = basename($w);
		$re = qr/\Q$w\E/i;
		foreach (keys %{$l_map->{$u}}) {
			if (/$re/) {
1093
				push @strong, $l_map->{$u}->{$_};
1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105
				last;
			}
		}
	}
	my ($rev) = ($c->{m} =~ /^git-svn-id:\s(?:\S+?)\@(\d+)
					\s(?:[a-f\d\-]+)$/xsm);
	unless (defined $rev) {
		($rev) = ($c->{m} =~/^git-svn-id:\s(\d+)
					\@(?:[a-f\d\-]+)/xsm);
		return unless defined $rev;
	}
	foreach my $m (@strong) {
1106
		my ($r0, $s0) = find_rev_before($rev, $m, 1);
1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124
		$grafts->{$c->{c}}->{$s0} = 1 if defined $s0;
	}
}

sub graft_merge_msg {
	my ($grafts, $l_map, $u, $p, @re) = @_;

	my $x = $l_map->{$u}->{$p};
	my $rl = rev_list_raw($x);
	while (my $c = next_rev_list_entry($rl)) {
		foreach my $re (@re) {
			my (@br) = ($c->{m} =~ /$re/g);
			next unless @br;
			process_merge_msg_matches($grafts,$l_map,$u,$p,$c,@br);
		}
	}
}

1125 1126
sub read_uuid {
	return if $SVN_UUID;
1127 1128 1129 1130 1131 1132 1133
	if ($_use_lib) {
		my $pool = SVN::Pool->new;
		$SVN_UUID = $SVN->get_uuid($pool);
		$pool->clear;
	} else {
		my $info = shift || svn_info('.');
		$SVN_UUID = $info->{'Repository UUID'} or
1134
					croak "Repository UUID unreadable\n";
1135
	}
1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166
}

sub quiet_run {
	my $pid = fork;
	defined $pid or croak $!;
	if (!$pid) {
		open my $null, '>', '/dev/null' or croak $!;
		open STDERR, '>&', $null or croak $!;
		open STDOUT, '>&', $null or croak $!;
		exec @_ or croak $!;
	}
	waitpid $pid, 0;
	return $?;
}

sub repo_path_split {
	my $full_url = shift;
	$full_url =~ s#/+$##;

	foreach (@repo_path_split_cache) {
		if ($full_url =~ s#$_##) {
			my $u = $1;
			$full_url =~ s#^/+##;
			return ($u, $full_url);
		}
	}

	my ($url, $path) = ($full_url =~ m!^([a-z\+]+://[^/]*)(.*)$!i);
	$path =~ s#^/+##;
	my @paths = split(m#/+#, $path);

1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179
	if ($_use_lib) {
		while (1) {
			$SVN = libsvn_connect($url);
			last if (defined $SVN &&
				defined eval { $SVN->get_latest_revnum });
			my $n = shift @paths || last;
			$url .= "/$n";
		}
	} else {
		while (quiet_run(qw/svn ls --non-interactive/, $url)) {
			my $n = shift @paths || last;
			$url .= "/$n";
		}
1180 1181
	}
	push @repo_path_split_cache, qr/^(\Q$url\E)/;
1182
	$path = join('/',@paths);
1183
	return ($url, $path);
1184 1185
}

E
Eric Wong 已提交
1186 1187 1188 1189 1190
sub setup_git_svn {
	defined $SVN_URL or croak "SVN repository location required\n";
	unless (-d $GIT_DIR) {
		croak "GIT_DIR=$GIT_DIR does not exist!\n";
	}
1191 1192
	mkpath([$GIT_SVN_DIR]);
	mkpath(["$GIT_SVN_DIR/info"]);
1193 1194
	open my $fh, '>>',$REVDB or croak $!;
	close $fh;
1195
	s_to_file($SVN_URL,"$GIT_SVN_DIR/info/url");
E
Eric Wong 已提交
1196 1197 1198 1199

}

sub assert_svn_wc_clean {
1200
	return if $_use_lib;
1201
	my ($svn_rev) = @_;
E
Eric Wong 已提交
1202
	croak "$svn_rev is not an integer!\n" unless ($svn_rev =~ /^\d+$/);
1203 1204 1205 1206 1207 1208 1209 1210 1211 1212
	my $lcr = svn_info('.')->{'Last Changed Rev'};
	if ($svn_rev != $lcr) {
		print STDERR "Checking for copy-tree ... ";
		my @diff = grep(/^Index: /,(safe_qx(qw(svn diff),
						"-r$lcr:$svn_rev")));
		if (@diff) {
			croak "Nope!  Expected r$svn_rev, got r$lcr\n";
		} else {
			print STDERR "OK!\n";
		}
E
Eric Wong 已提交
1213 1214 1215 1216 1217 1218 1219 1220
	}
	my @status = grep(!/^Performing status on external/,(`svn status`));
	@status = grep(!/^\s*$/,@status);
	if (scalar @status) {
		print STDERR "Tree ($SVN_WC) is not clean:\n";
		print STDERR $_ foreach @status;
		croak;
	}
1221 1222
}

1223
sub get_tree_from_treeish {
1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239
	my ($treeish) = @_;
	croak "Not a sha1: $treeish\n" unless $treeish =~ /^$sha1$/o;
	chomp(my $type = `git-cat-file -t $treeish`);
	my $expected;
	while ($type eq 'tag') {
		chomp(($treeish, $type) = `git-cat-file tag $treeish`);
	}
	if ($type eq 'commit') {
		$expected = (grep /^tree /,`git-cat-file commit $treeish`)[0];
		($expected) = ($expected =~ /^tree ($sha1)$/);
		die "Unable to get tree from $treeish\n" unless $expected;
	} elsif ($type eq 'tree') {
		$expected = $treeish;
	} else {
		die "$treeish is a $type, expected tree, tag or commit\n";
	}
1240 1241 1242 1243 1244 1245 1246
	return $expected;
}

sub assert_tree {
	return if $_use_lib;
	my ($treeish) = @_;
	my $expected = get_tree_from_treeish($treeish);
1247 1248 1249 1250 1251

	my $tmpindex = $GIT_SVN_INDEX.'.assert-tmp';
	if (-e $tmpindex) {
		unlink $tmpindex or croak $!;
	}
1252
	my $old_index = set_index($tmpindex);
1253
	index_changes(1);
1254
	chomp(my $tree = `git-write-tree`);
1255
	restore_index($old_index);
1256 1257
	if ($tree ne $expected) {
		croak "Tree mismatch, Got: $tree, Expected: $expected\n";
E
Eric Wong 已提交
1258
	}
1259
	unlink $tmpindex;
E
Eric Wong 已提交
1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278
}

sub parse_diff_tree {
	my $diff_fh = shift;
	local $/ = "\0";
	my $state = 'meta';
	my @mods;
	while (<$diff_fh>) {
		chomp $_; # this gets rid of the trailing "\0"
		if ($state eq 'meta' && /^:(\d{6})\s(\d{6})\s
					$sha1\s($sha1)\s([MTCRAD])\d*$/xo) {
			push @mods, {	mode_a => $1, mode_b => $2,
					sha1_b => $3, chg => $4 };
			if ($4 =~ /^(?:C|R)$/) {
				$state = 'file_a';
			} else {
				$state = 'file_b';
			}
		} elsif ($state eq 'file_a') {
1279
			my $x = $mods[$#mods] or croak "Empty array\n";
E
Eric Wong 已提交
1280
			if ($x->{chg} !~ /^(?:C|R)$/) {
1281
				croak "Error parsing $_, $x->{chg}\n";
E
Eric Wong 已提交
1282 1283 1284 1285
			}
			$x->{file_a} = $_;
			$state = 'file_b';
		} elsif ($state eq 'file_b') {
1286
			my $x = $mods[$#mods] or croak "Empty array\n";
E
Eric Wong 已提交
1287
			if (exists $x->{file_a} && $x->{chg} !~ /^(?:C|R)$/) {
1288
				croak "Error parsing $_, $x->{chg}\n";
E
Eric Wong 已提交
1289 1290
			}
			if (!exists $x->{file_a} && $x->{chg} =~ /^(?:C|R)$/) {
1291
				croak "Error parsing $_, $x->{chg}\n";
E
Eric Wong 已提交
1292 1293 1294 1295
			}
			$x->{file_b} = $_;
			$state = 'meta';
		} else {
1296
			croak "Error parsing $_\n";
E
Eric Wong 已提交
1297 1298
		}
	}
1299
	close $diff_fh or croak $?;
1300

E
Eric Wong 已提交
1301 1302 1303 1304 1305
	return \@mods;
}

sub svn_check_prop_executable {
	my $m = shift;
1306 1307 1308 1309 1310 1311 1312
	return if -l $m->{file_b};
	if ($m->{mode_b} =~ /755$/) {
		chmod((0755 &~ umask),$m->{file_b}) or croak $!;
		if ($m->{mode_a} !~ /755$/) {
			sys(qw(svn propset svn:executable 1), $m->{file_b});
		}
		-x $m->{file_b} or croak "$m->{file_b} is not executable!\n";
E
Eric Wong 已提交
1313 1314
	} elsif ($m->{mode_b} !~ /755$/ && $m->{mode_a} =~ /755$/) {
		sys(qw(svn propdel svn:executable), $m->{file_b});
1315 1316
		chmod((0644 &~ umask),$m->{file_b}) or croak $!;
		-x $m->{file_b} and croak "$m->{file_b} is executable!\n";
E
Eric Wong 已提交
1317 1318 1319 1320 1321 1322 1323 1324 1325 1326
	}
}

sub svn_ensure_parent_path {
	my $dir_b = dirname(shift);
	svn_ensure_parent_path($dir_b) if ($dir_b ne File::Spec->curdir);
	mkpath([$dir_b]) unless (-d $dir_b);
	sys(qw(svn add -N), $dir_b) unless (-d "$dir_b/.svn");
}

1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392
sub precommit_check {
	my $mods = shift;
	my (%rm_file, %rmdir_check, %added_check);

	my %o = ( D => 0, R => 1, C => 2, A => 3, M => 3, T => 3 );
	foreach my $m (sort { $o{$a->{chg}} <=> $o{$b->{chg}} } @$mods) {
		if ($m->{chg} eq 'R') {
			if (-d $m->{file_b}) {
				err_dir_to_file("$m->{file_a} => $m->{file_b}");
			}
			# dir/$file => dir/file/$file
			my $dirname = dirname($m->{file_b});
			while ($dirname ne File::Spec->curdir) {
				if ($dirname ne $m->{file_a}) {
					$dirname = dirname($dirname);
					next;
				}
				err_file_to_dir("$m->{file_a} => $m->{file_b}");
			}
			# baz/zzz => baz (baz is a file)
			$dirname = dirname($m->{file_a});
			while ($dirname ne File::Spec->curdir) {
				if ($dirname ne $m->{file_b}) {
					$dirname = dirname($dirname);
					next;
				}
				err_dir_to_file("$m->{file_a} => $m->{file_b}");
			}
		}
		if ($m->{chg} =~ /^(D|R)$/) {
			my $t = $1 eq 'D' ? 'file_b' : 'file_a';
			$rm_file{ $m->{$t} } = 1;
			my $dirname = dirname( $m->{$t} );
			my $basename = basename( $m->{$t} );
			$rmdir_check{$dirname}->{$basename} = 1;
		} elsif ($m->{chg} =~ /^(?:A|C)$/) {
			if (-d $m->{file_b}) {
				err_dir_to_file($m->{file_b});
			}
			my $dirname = dirname( $m->{file_b} );
			my $basename = basename( $m->{file_b} );
			$added_check{$dirname}->{$basename} = 1;
			while ($dirname ne File::Spec->curdir) {
				if ($rm_file{$dirname}) {
					err_file_to_dir($m->{file_b});
				}
				$dirname = dirname $dirname;
			}
		}
	}
	return (\%rmdir_check, \%added_check);

	sub err_dir_to_file {
		my $file = shift;
		print STDERR "Node change from directory to file ",
				"is not supported by Subversion: ",$file,"\n";
		exit 1;
	}
	sub err_file_to_dir {
		my $file = shift;
		print STDERR "Node change from file to directory ",
				"is not supported by Subversion: ",$file,"\n";
		exit 1;
	}
}

1393 1394

sub get_diff {
1395
	my ($from, $treeish) = @_;
1396
	assert_tree($from);
1397
	print "diff-tree $from $treeish\n";
E
Eric Wong 已提交
1398 1399 1400
	my $pid = open my $diff_fh, '-|';
	defined $pid or croak $!;
	if ($pid == 0) {
1401 1402 1403 1404 1405 1406
		my @diff_tree = qw(git-diff-tree -z -r);
		if ($_cp_similarity) {
			push @diff_tree, "-C$_cp_similarity";
		} else {
			push @diff_tree, '-C';
		}
1407 1408
		push @diff_tree, '--find-copies-harder' if $_find_copies_harder;
		push @diff_tree, "-l$_l" if defined $_l;
1409
		exec(@diff_tree, $from, $treeish) or croak $!;
E
Eric Wong 已提交
1410
	}
1411 1412 1413 1414
	return parse_diff_tree($diff_fh);
}

sub svn_checkout_tree {
1415 1416
	my ($from, $treeish) = @_;
	my $mods = get_diff($from->{commit}, $treeish);
1417
	return $mods unless (scalar @$mods);
1418 1419 1420 1421
	my ($rm, $add) = precommit_check($mods);

	my %o = ( D => 1, R => 0, C => -1, A => 3, M => 3, T => 3 );
	foreach my $m (sort { $o{$a->{chg}} <=> $o{$b->{chg}} } @$mods) {
E
Eric Wong 已提交
1422 1423 1424
		if ($m->{chg} eq 'C') {
			svn_ensure_parent_path( $m->{file_b} );
			sys(qw(svn cp),		$m->{file_a}, $m->{file_b});
1425
			apply_mod_line_blob($m);
E
Eric Wong 已提交
1426 1427 1428 1429 1430 1431
			svn_check_prop_executable($m);
		} elsif ($m->{chg} eq 'D') {
			sys(qw(svn rm --force), $m->{file_b});
		} elsif ($m->{chg} eq 'R') {
			svn_ensure_parent_path( $m->{file_b} );
			sys(qw(svn mv --force), $m->{file_a}, $m->{file_b});
1432
			apply_mod_line_blob($m);
E
Eric Wong 已提交
1433 1434
			svn_check_prop_executable($m);
		} elsif ($m->{chg} eq 'M') {
1435
			apply_mod_line_blob($m);
E
Eric Wong 已提交
1436 1437 1438
			svn_check_prop_executable($m);
		} elsif ($m->{chg} eq 'T') {
			sys(qw(svn rm --force),$m->{file_b});
1439
			apply_mod_line_blob($m);
1440
			sys(qw(svn add), $m->{file_b});
1441
			svn_check_prop_executable($m);
E
Eric Wong 已提交
1442 1443
		} elsif ($m->{chg} eq 'A') {
			svn_ensure_parent_path( $m->{file_b} );
1444
			apply_mod_line_blob($m);
1445
			sys(qw(svn add), $m->{file_b});
1446
			svn_check_prop_executable($m);
E
Eric Wong 已提交
1447 1448 1449 1450
		} else {
			croak "Invalid chg: $m->{chg}\n";
		}
	}
1451 1452 1453 1454 1455 1456 1457 1458 1459

	assert_tree($treeish);
	if ($_rmdir) { # remove empty directories
		handle_rmdir($rm, $add);
	}
	assert_tree($treeish);
	return $mods;
}

1460
sub libsvn_checkout_tree {
1461 1462
	my ($from, $treeish, $ed) = @_;
	my $mods = get_diff($from, $treeish);
1463 1464 1465 1466 1467
	return $mods unless (scalar @$mods);
	my %o = ( D => 1, R => 0, C => -1, A => 3, M => 3, T => 3 );
	foreach my $m (sort { $o{$a->{chg}} <=> $o{$b->{chg}} } @$mods) {
		my $f = $m->{chg};
		if (defined $o{$f}) {
1468
			$ed->$f($m, $_q);
1469 1470 1471 1472
		} else {
			croak "Invalid change type: $f\n";
		}
	}
1473
	$ed->rmdirs($_q) if $_rmdir;
1474 1475 1476
	return $mods;
}

1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510
# svn ls doesn't work with respect to the current working tree, but what's
# in the repository.  There's not even an option for it... *sigh*
# (added files don't show up and removed files remain in the ls listing)
sub svn_ls_current {
	my ($dir, $rm, $add) = @_;
	chomp(my @ls = safe_qx('svn','ls',$dir));
	my @ret = ();
	foreach (@ls) {
		s#/$##; # trailing slashes are evil
		push @ret, $_ unless $rm->{$dir}->{$_};
	}
	if (exists $add->{$dir}) {
		push @ret, keys %{$add->{$dir}};
	}
	return \@ret;
}

sub handle_rmdir {
	my ($rm, $add) = @_;

	foreach my $dir (sort {length $b <=> length $a} keys %$rm) {
		my $ls = svn_ls_current($dir, $rm, $add);
		next if (scalar @$ls);
		sys(qw(svn rm --force),$dir);

		my $dn = dirname $dir;
		$rm->{ $dn }->{ basename $dir } = 1;
		$ls = svn_ls_current($dn, $rm, $add);
		while (scalar @$ls == 0 && $dn ne File::Spec->curdir) {
			sys(qw(svn rm --force),$dn);
			$dir = basename $dn;
			$dn = dirname $dn;
			$rm->{ $dn }->{ $dir } = 1;
			$ls = svn_ls_current($dn, $rm, $add);
E
Eric Wong 已提交
1511 1512 1513 1514
		}
	}
}

1515 1516
sub get_commit_message {
	my ($commit, $commit_msg) = (@_);
1517
	my %log_msg = ( msg => '' );
1518
	open my $msg, '>', $commit_msg or croak $!;
E
Eric Wong 已提交
1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531

	chomp(my $type = `git-cat-file -t $commit`);
	if ($type eq 'commit') {
		my $pid = open my $msg_fh, '-|';
		defined $pid or croak $!;

		if ($pid == 0) {
			exec(qw(git-cat-file commit), $commit) or croak $!;
		}
		my $in_msg = 0;
		while (<$msg_fh>) {
			if (!$in_msg) {
				$in_msg = 1 if (/^\s*$/);
1532 1533 1534
			} elsif (/^git-svn-id: /) {
				# skip this, we regenerate the correct one
				# on re-fetch anyways
E
Eric Wong 已提交
1535 1536 1537 1538
			} else {
				print $msg $_ or croak $!;
			}
		}
1539
		close $msg_fh or croak $?;
E
Eric Wong 已提交
1540 1541 1542 1543 1544 1545 1546
	}
	close $msg or croak $!;

	if ($_edit || ($type eq 'tree')) {
		my $editor = $ENV{VISUAL} || $ENV{EDITOR} || 'vi';
		system($editor, $commit_msg);
	}
1547 1548 1549 1550 1551 1552

	# file_to_s removes all trailing newlines, so just use chomp() here:
	open $msg, '<', $commit_msg or croak $!;
	{ local $/; chomp($log_msg{msg} = <$msg>); }
	close $msg or croak $!;

1553 1554 1555
	return \%log_msg;
}

E
Eric Wong 已提交
1556 1557 1558 1559 1560 1561 1562 1563
sub set_svn_commit_env {
	if (defined $LC_ALL) {
		$ENV{LC_ALL} = $LC_ALL;
	} else {
		delete $ENV{LC_ALL};
	}
}

1564
sub svn_commit_tree {
1565
	my ($last, $commit) = @_;
1566 1567 1568
	my $commit_msg = "$GIT_SVN_DIR/.svn-commit.tmp.$$";
	my $log_msg = get_commit_message($commit, $commit_msg);
	my ($oneline) = ($log_msg->{msg} =~ /([^\n\r]+)/);
1569 1570
	print "Committing $commit: $oneline\n";

E
Eric Wong 已提交
1571
	set_svn_commit_env();
E
Eric Wong 已提交
1572
	my @ci_output = safe_qx(qw(svn commit -F),$commit_msg);
1573
	$ENV{LC_ALL} = 'C';
E
Eric Wong 已提交
1574
	unlink $commit_msg;
1575 1576 1577 1578 1579 1580 1581
	my ($committed) = ($ci_output[$#ci_output] =~ /(\d+)/);
	if (!defined $committed) {
		my $out = join("\n",@ci_output);
		print STDERR "W: Trouble parsing \`svn commit' output:\n\n",
				$out, "\n\nAssuming English locale...";
		($committed) = ($out =~ /^Committed revision \d+\./sm);
		defined $committed or die " FAILED!\n",
E
Eric Wong 已提交
1582
			"Commit output failed to parse committed revision!\n",
1583 1584
		print STDERR " OK\n";
	}
E
Eric Wong 已提交
1585

1586
	my @svn_up = qw(svn up);
E
Eric Wong 已提交
1587
	push @svn_up, '--ignore-externals' unless $_no_ignore_ext;
1588
	if ($_optimize_commits && ($committed == ($last->{revision} + 1))) {
1589
		push @svn_up, "-r$committed";
1590 1591 1592
		sys(@svn_up);
		my $info = svn_info('.');
		my $date = $info->{'Last Changed Date'} or die "Missing date\n";
1593 1594
		if ($info->{'Last Changed Rev'} != $committed) {
			croak "$info->{'Last Changed Rev'} != $committed\n"
1595 1596 1597 1598 1599
		}
		my ($Y,$m,$d,$H,$M,$S,$tz) = ($date =~
					/(\d{4})\-(\d\d)\-(\d\d)\s
					 (\d\d)\:(\d\d)\:(\d\d)\s([\-\+]\d+)/x)
					 or croak "Failed to parse date: $date\n";
1600 1601 1602 1603
		$log_msg->{date} = "$tz $Y-$m-$d $H:$M:$S";
		$log_msg->{author} = $info->{'Last Changed Author'};
		$log_msg->{revision} = $committed;
		$log_msg->{msg} .= "\n";
1604 1605 1606
		$log_msg->{parents} = [ $last->{commit} ];
		$log_msg->{commit} = git_commit($log_msg, $commit);
		return $log_msg;
1607 1608
	}
	# resync immediately
1609
	push @svn_up, "-r$last->{revision}";
E
Eric Wong 已提交
1610
	sys(@svn_up);
1611
	return fetch("$committed=$commit");
E
Eric Wong 已提交
1612 1613
}

1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645
sub rev_list_raw {
	my (@args) = @_;
	my $pid = open my $fh, '-|';
	defined $pid or croak $!;
	if (!$pid) {
		exec(qw/git-rev-list --pretty=raw/, @args) or croak $!;
	}
	return { fh => $fh, t => { } };
}

sub next_rev_list_entry {
	my $rl = shift;
	my $fh = $rl->{fh};
	my $x = $rl->{t};
	while (<$fh>) {
		if (/^commit ($sha1)$/o) {
			if ($x->{c}) {
				$rl->{t} = { c => $1 };
				return $x;
			} else {
				$x->{c} = $1;
			}
		} elsif (/^parent ($sha1)$/o) {
			$x->{p}->{$1} = 1;
		} elsif (s/^    //) {
			$x->{m} ||= '';
			$x->{m} .= $_;
		}
	}
	return ($x != $rl->{t}) ? $x : undef;
}

1646 1647
# read the entire log into a temporary file (which is removed ASAP)
# and store the file handle + parser state
E
Eric Wong 已提交
1648 1649
sub svn_log_raw {
	my (@log_args) = @_;
1650 1651
	my $log_fh = IO::File->new_tmpfile or croak $!;
	my $pid = fork;
E
Eric Wong 已提交
1652
	defined $pid or croak $!;
1653 1654
	if (!$pid) {
		open STDOUT, '>&', $log_fh or croak $!;
E
Eric Wong 已提交
1655 1656
		exec (qw(svn log), @log_args) or croak $!
	}
1657
	waitpid $pid, 0;
1658
	croak $? if $?;
1659 1660 1661 1662 1663 1664 1665 1666
	seek $log_fh, 0, 0 or croak $!;
	return { state => 'sep', fh => $log_fh };
}

sub next_log_entry {
	my $log = shift; # retval of svn_log_raw()
	my $ret = undef;
	my $fh = $log->{fh};
E
Eric Wong 已提交
1667

1668
	while (<$fh>) {
E
Eric Wong 已提交
1669 1670
		chomp;
		if (/^\-{72}$/) {
1671 1672 1673 1674 1675
			if ($log->{state} eq 'msg') {
				if ($ret->{lines}) {
					$ret->{msg} .= $_."\n";
					unless(--$ret->{lines}) {
						$log->{state} = 'sep';
1676 1677 1678
					}
				} else {
					croak "Log parse error at: $_\n",
1679
						$ret->{revision},
1680 1681 1682 1683
						"\n";
				}
				next;
			}
1684
			if ($log->{state} ne 'sep') {
1685
				croak "Log parse error at: $_\n",
1686 1687
					"state: $log->{state}\n",
					$ret->{revision},
1688 1689
					"\n";
			}
1690
			$log->{state} = 'rev';
E
Eric Wong 已提交
1691 1692

			# if we have an empty log message, put something there:
1693 1694 1695 1696
			if ($ret) {
				$ret->{msg} ||= "\n";
				delete $ret->{lines};
				return $ret;
E
Eric Wong 已提交
1697 1698 1699
			}
			next;
		}
1700
		if ($log->{state} eq 'rev' && s/^r(\d+)\s*\|\s*//) {
E
Eric Wong 已提交
1701
			my $rev = $1;
1702 1703
			my ($author, $date, $lines) = split(/\s*\|\s*/, $_, 3);
			($lines) = ($lines =~ /(\d+)/);
E
Eric Wong 已提交
1704 1705 1706 1707
			my ($Y,$m,$d,$H,$M,$S,$tz) = ($date =~
					/(\d{4})\-(\d\d)\-(\d\d)\s
					 (\d\d)\:(\d\d)\:(\d\d)\s([\-\+]\d+)/x)
					 or croak "Failed to parse date: $date\n";
1708
			$ret = {	revision => $rev,
E
Eric Wong 已提交
1709 1710
					date => "$tz $Y-$m-$d $H:$M:$S",
					author => $author,
1711
					lines => $lines,
1712
					msg => '' };
1713 1714 1715 1716
			if (defined $_authors && ! defined $users{$author}) {
				die "Author: $author not defined in ",
						"$_authors file\n";
			}
1717
			$log->{state} = 'msg_start';
E
Eric Wong 已提交
1718 1719 1720
			next;
		}
		# skip the first blank line of the message:
1721 1722 1723 1724 1725 1726 1727
		if ($log->{state} eq 'msg_start' && /^$/) {
			$log->{state} = 'msg';
		} elsif ($log->{state} eq 'msg') {
			if ($ret->{lines}) {
				$ret->{msg} .= $_."\n";
				unless (--$ret->{lines}) {
					$log->{state} = 'sep';
1728 1729 1730
				}
			} else {
				croak "Log parse error at: $_\n",
1731
					$ret->{revision},"\n";
1732
			}
E
Eric Wong 已提交
1733 1734
		}
	}
1735
	return $ret;
E
Eric Wong 已提交
1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751
}

sub svn_info {
	my $url = shift || $SVN_URL;

	my $pid = open my $info_fh, '-|';
	defined $pid or croak $!;

	if ($pid == 0) {
		exec(qw(svn info),$url) or croak $!;
	}

	my $ret = {};
	# only single-lines seem to exist in svn info output
	while (<$info_fh>) {
		chomp $_;
1752
		if (m#^([^:]+)\s*:\s*(\S.*)$#) {
E
Eric Wong 已提交
1753 1754 1755 1756
			$ret->{$1} = $2;
			push @{$ret->{-order}}, $1;
		}
	}
1757
	close $info_fh or croak $?;
E
Eric Wong 已提交
1758 1759 1760 1761 1762
	return $ret;
}

sub sys { system(@_) == 0 or croak $? }

1763 1764
sub eol_cp {
	my ($from, $to) = @_;
1765
	my $es = svn_propget_base('svn:eol-style', $to);
1766 1767 1768 1769
	open my $rfd, '<', $from or croak $!;
	binmode $rfd or croak $!;
	open my $wfd, '>', $to or croak $!;
	binmode $wfd or croak $!;
1770 1771 1772 1773
	eol_cp_fd($rfd, $wfd, $es);
	close $rfd or croak $!;
	close $wfd or croak $!;
}
1774

1775 1776 1777
sub eol_cp_fd {
	my ($rfd, $wfd, $es) = @_;
	my $eol = defined $es ? $EOL{$es} : undef;
1778
	my $buf;
E
Eric Wong 已提交
1779
	use bytes;
1780 1781 1782 1783
	while (1) {
		my ($r, $w, $t);
		defined($r = sysread($rfd, $buf, 4096)) or croak $!;
		return unless $r;
E
Eric Wong 已提交
1784 1785 1786 1787 1788 1789 1790 1791 1792
		if ($eol) {
			if ($buf =~ /\015$/) {
				my $c;
				defined($r = sysread($rfd,$c,1)) or croak $!;
				$buf .= $c if $r > 0;
			}
			$buf =~ s/(?:\015\012|\015|\012)/$eol/gs;
			$r = length($buf);
		}
1793 1794 1795 1796
		for ($w = 0; $w < $r; $w += $t) {
			$t = syswrite($wfd, $buf, $r - $w, $w) or croak $!;
		}
	}
E
Eric Wong 已提交
1797
	no bytes;
1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815
}

sub do_update_index {
	my ($z_cmd, $cmd, $no_text_base) = @_;

	my $z = open my $p, '-|';
	defined $z or croak $!;
	unless ($z) { exec @$z_cmd or croak $! }

	my $pid = open my $ui, '|-';
	defined $pid or croak $!;
	unless ($pid) {
		exec('git-update-index',"--$cmd",'-z','--stdin') or croak $!;
	}
	local $/ = "\0";
	while (my $x = <$p>) {
		chomp $x;
		if (!$no_text_base && lstat $x && ! -l _ &&
1816
				svn_propget_base('svn:keywords', $x)) {
1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832
			my $mode = -x _ ? 0755 : 0644;
			my ($v,$d,$f) = File::Spec->splitpath($x);
			my $tb = File::Spec->catfile($d, '.svn', 'tmp',
						'text-base',"$f.svn-base");
			$tb =~ s#^/##;
			unless (-f $tb) {
				$tb = File::Spec->catfile($d, '.svn',
						'text-base',"$f.svn-base");
				$tb =~ s#^/##;
			}
			unlink $x or croak $!;
			eol_cp($tb, $x);
			chmod(($mode &~ umask), $x) or croak $!;
		}
		print $ui $x,"\0";
	}
1833
	close $ui or croak $?;
1834 1835 1836
}

sub index_changes {
1837
	return if $_use_lib;
1838 1839 1840 1841 1842 1843

	if (!-f "$GIT_SVN_DIR/info/exclude") {
		open my $fd, '>>', "$GIT_SVN_DIR/info/exclude" or croak $!;
		print $fd '.svn',"\n";
		close $fd or croak $!;
	}
1844 1845 1846 1847 1848
	my $no_text_base = shift;
	do_update_index([qw/git-diff-files --name-only -z/],
			'remove',
			$no_text_base);
	do_update_index([qw/git-ls-files -z --others/,
1849
				"--exclude-from=$GIT_SVN_DIR/info/exclude"],
1850 1851
			'add',
			$no_text_base);
E
Eric Wong 已提交
1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872
}

sub s_to_file {
	my ($str, $file, $mode) = @_;
	open my $fd,'>',$file or croak $!;
	print $fd $str,"\n" or croak $!;
	close $fd or croak $!;
	chmod ($mode &~ umask, $file) if (defined $mode);
}

sub file_to_s {
	my $file = shift;
	open my $fd,'<',$file or croak "$!: file: $file\n";
	local $/;
	my $ret = <$fd>;
	close $fd or croak $!;
	$ret =~ s/\s*$//s;
	return $ret;
}

sub assert_revision_unknown {
1873 1874 1875
	my $r = shift;
	if (my $c = revdb_get($REVDB, $r)) {
		croak "$r = $c already exists! Why are we refetching it?";
E
Eric Wong 已提交
1876 1877 1878
	}
}

1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890
sub trees_eq {
	my ($x, $y) = @_;
	my @x = safe_qx('git-cat-file','commit',$x);
	my @y = safe_qx('git-cat-file','commit',$y);
	if (($y[0] ne $x[0]) || $x[0] !~ /^tree $sha1\n$/
				|| $y[0] !~ /^tree $sha1\n$/) {
		print STDERR "Trees not equal: $y[0] != $x[0]\n";
		return 0
	}
	return 1;
}

E
Eric Wong 已提交
1891 1892 1893
sub git_commit {
	my ($log_msg, @parents) = @_;
	assert_revision_unknown($log_msg->{revision});
1894 1895
	map_tree_joins() if (@_branch_from && !%tree_map);

1896 1897 1898 1899
	my (@tmp_parents, @exec_parents, %seen_parent);
	if (my $lparents = $log_msg->{parents}) {
		@tmp_parents = @$lparents
	}
E
Eric Wong 已提交
1900 1901 1902 1903 1904 1905
	# commit parents can be conditionally bound to a particular
	# svn revision via: "svn_revno=commit_sha1", filter them out here:
	foreach my $p (@parents) {
		next unless defined $p;
		if ($p =~ /^(\d+)=($sha1_short)$/o) {
			if ($1 == $log_msg->{revision}) {
1906
				push @tmp_parents, $2;
E
Eric Wong 已提交
1907 1908
			}
		} else {
1909
			push @tmp_parents, $p if $p =~ /$sha1_short/o;
E
Eric Wong 已提交
1910 1911
		}
	}
1912 1913 1914
	my $tree = $log_msg->{tree};
	if (!defined $tree) {
		my $index = set_index($GIT_SVN_INDEX);
1915
		index_changes();
1916
		chomp($tree = `git-write-tree`);
1917
		croak $? if $?;
1918 1919
		restore_index($index);
	}
1920 1921 1922 1923 1924 1925 1926

	# just in case we clobber the existing ref, we still want that ref
	# as our parent:
	if (my $cur = eval { file_to_s("$GIT_DIR/refs/remotes/$GIT_SVN") }) {
		push @tmp_parents, $cur;
	}

1927
	if (exists $tree_map{$tree}) {
1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947
		foreach my $p (@{$tree_map{$tree}}) {
			my $skip;
			foreach (@tmp_parents) {
				# see if a common parent is found
				my $mb = eval {
					safe_qx('git-merge-base', $_, $p)
				};
				next if ($@ || $?);
				$skip = 1;
				last;
			}
			next if $skip;
			my ($url_p, $r_p, $uuid_p) = cmt_metadata($p);
			next if (($SVN_UUID eq $uuid_p) &&
						($log_msg->{revision} > $r_p));
			next if (defined $url_p && defined $SVN_URL &&
						($SVN_UUID eq $uuid_p) &&
						($url_p eq $SVN_URL));
			push @tmp_parents, $p;
		}
1948 1949 1950 1951 1952 1953 1954 1955 1956
	}
	foreach (@tmp_parents) {
		next if $seen_parent{$_};
		$seen_parent{$_} = 1;
		push @exec_parents, $_;
		# MAXPARENT is defined to 16 in commit-tree.c:
		last if @exec_parents > 16;
	}

1957 1958 1959 1960 1961 1962 1963 1964
	set_commit_env($log_msg);
	my @exec = ('git-commit-tree', $tree);
	push @exec, '-p', $_  foreach @exec_parents;
	defined(my $pid = open3(my $msg_fh, my $out_fh, '>&STDERR', @exec))
								or croak $!;
	print $msg_fh $log_msg->{msg} or croak $!;
	unless ($_no_metadata) {
		print $msg_fh "\ngit-svn-id: $SVN_URL\@$log_msg->{revision}",
1965
					" $SVN_UUID\n" or croak $!;
E
Eric Wong 已提交
1966
	}
1967 1968
	$msg_fh->flush == 0 or croak $!;
	close $msg_fh or croak $!;
E
Eric Wong 已提交
1969
	chomp(my $commit = do { local $/; <$out_fh> });
1970 1971 1972
	close $out_fh or croak $!;
	waitpid $pid, 0;
	croak $? if $?;
E
Eric Wong 已提交
1973
	if ($commit !~ /^$sha1$/o) {
1974
		die "Failed to commit, invalid sha1: $commit\n";
E
Eric Wong 已提交
1975
	}
1976
	sys('git-update-ref',"refs/remotes/$GIT_SVN",$commit);
1977 1978
	revdb_set($REVDB, $log_msg->{revision}, $commit);

1979
	# this output is read via pipe, do not change:
E
Eric Wong 已提交
1980
	print "r$log_msg->{revision} = $commit\n";
1981 1982 1983 1984 1985
	check_repack();
	return $commit;
}

sub check_repack {
1986 1987 1988 1989
	if ($_repack && (--$_repack_nr == 0)) {
		$_repack_nr = $_repack;
		sys("git repack $_repack_flags");
	}
E
Eric Wong 已提交
1990 1991
}

1992
sub set_commit_env {
1993
	my ($log_msg) = @_;
1994
	my $author = $log_msg->{author};
1995 1996 1997
	if (!defined $author || length $author == 0) {
		$author = '(no author)';
	}
1998
	my ($name,$email) = defined $users{$author} ?  @{$users{$author}}
1999
				: ($author,"$author\@$SVN_UUID");
2000 2001 2002 2003 2004
	$ENV{GIT_AUTHOR_NAME} = $ENV{GIT_COMMITTER_NAME} = $name;
	$ENV{GIT_AUTHOR_EMAIL} = $ENV{GIT_COMMITTER_EMAIL} = $email;
	$ENV{GIT_AUTHOR_DATE} = $ENV{GIT_COMMITTER_DATE} = $log_msg->{date};
}

2005 2006 2007 2008 2009 2010 2011 2012 2013
sub apply_mod_line_blob {
	my $m = shift;
	if ($m->{mode_b} =~ /^120/) {
		blob_to_symlink($m->{sha1_b}, $m->{file_b});
	} else {
		blob_to_file($m->{sha1_b}, $m->{file_b});
	}
}

E
Eric Wong 已提交
2014 2015 2016 2017
sub blob_to_symlink {
	my ($blob, $link) = @_;
	defined $link or croak "\$link not defined!\n";
	croak "Not a sha1: $blob\n" unless $blob =~ /^$sha1$/o;
2018 2019 2020 2021
	if (-l $link || -f _) {
		unlink $link or croak $!;
	}

E
Eric Wong 已提交
2022 2023 2024 2025 2026 2027 2028 2029
	my $dest = `git-cat-file blob $blob`; # no newline, so no chomp
	symlink $dest, $link or croak $!;
}

sub blob_to_file {
	my ($blob, $file) = @_;
	defined $file or croak "\$file not defined!\n";
	croak "Not a sha1: $blob\n" unless $blob =~ /^$sha1$/o;
2030 2031 2032 2033
	if (-l $file || -f _) {
		unlink $file or croak $!;
	}

E
Eric Wong 已提交
2034 2035 2036 2037 2038 2039
	open my $blob_fh, '>', $file or croak "$!: $file\n";
	my $pid = fork;
	defined $pid or croak $!;

	if ($pid == 0) {
		open STDOUT, '>&', $blob_fh or croak $!;
2040
		exec('git-cat-file','blob',$blob) or croak $!;
E
Eric Wong 已提交
2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051
	}
	waitpid $pid, 0;
	croak $? if $?;

	close $blob_fh or croak $!;
}

sub safe_qx {
	my $pid = open my $child, '-|';
	defined $pid or croak $!;
	if ($pid == 0) {
2052
		exec(@_) or croak $!;
E
Eric Wong 已提交
2053 2054 2055 2056 2057 2058 2059
	}
	my @ret = (<$child>);
	close $child or croak $?;
	die $? if $?; # just in case close didn't error out
	return wantarray ? @ret : join('',@ret);
}

2060
sub svn_compat_check {
2061 2062 2063 2064 2065
	if ($_follow_parent) {
		print STDERR 'E: --follow-parent functionality is only ',
				"available when SVN libraries are used\n";
		exit 1;
	}
2066 2067
	my @co_help = safe_qx(qw(svn co -h));
	unless (grep /ignore-externals/,@co_help) {
E
Eric Wong 已提交
2068 2069 2070 2071
		print STDERR "W: Installed svn version does not support ",
				"--ignore-externals\n";
		$_no_ignore_ext = 1;
	}
2072 2073 2074
	if (grep /usage: checkout URL\[\@REV\]/,@co_help) {
		$_svn_co_url_revs = 1;
	}
2075 2076 2077
	if (grep /\[TARGET\[\@REV\]\.\.\.\]/, `svn propget -h`) {
		$_svn_pg_peg_revs = 1;
	}
2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088

	# I really, really hope nobody hits this...
	unless (grep /stop-on-copy/, (safe_qx(qw(svn log -h)))) {
		print STDERR <<'';
W: The installed svn version does not support the --stop-on-copy flag in
   the log command.
   Lets hope the directory you're tracking is not a branch or tag
   and was never moved within the repository...

		$_no_stop_copy = 1;
	}
2089 2090 2091 2092 2093 2094 2095 2096 2097 2098
}

# *sigh*, new versions of svn won't honor -r<rev> without URL@<rev>,
# (and they won't honor URL@<rev> without -r<rev>, too!)
sub svn_cmd_checkout {
	my ($url, $rev, $dir) = @_;
	my @cmd = ('svn','co', "-r$rev");
	push @cmd, '--ignore-externals' unless $_no_ignore_ext;
	$url .= "\@$rev" if $_svn_co_url_revs;
	sys(@cmd, $url, $dir);
E
Eric Wong 已提交
2099
}
2100 2101

sub check_upgrade_needed {
2102
	if (!-r $REVDB) {
2103
		-d $GIT_SVN_DIR or mkpath([$GIT_SVN_DIR]);
2104 2105 2106
		open my $fh, '>>',$REVDB or croak $!;
		close $fh;
	}
2107 2108 2109 2110 2111
	my $old = eval {
		my $pid = open my $child, '-|';
		defined $pid or croak $!;
		if ($pid == 0) {
			close STDERR;
2112
			exec('git-rev-parse',"$GIT_SVN-HEAD") or croak $!;
2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126
		}
		my @ret = (<$child>);
		close $child or croak $?;
		die $? if $?; # just in case close didn't error out
		return wantarray ? @ret : join('',@ret);
	};
	return unless $old;
	my $head = eval { safe_qx('git-rev-parse',"refs/remotes/$GIT_SVN") };
	if ($@ || !$head) {
		print STDERR "Please run: $0 rebuild --upgrade\n";
		exit 1;
	}
}

2127 2128 2129
# fills %tree_map with a reverse mapping of trees to commits.  Useful
# for finding parents to commit on.
sub map_tree_joins {
2130
	my %seen;
2131 2132 2133 2134
	foreach my $br (@_branch_from) {
		my $pid = open my $pipe, '-|';
		defined $pid or croak $!;
		if ($pid == 0) {
2135
			exec(qw(git-rev-list --topo-order --pretty=raw), $br)
2136
								or croak $!;
2137 2138 2139 2140
		}
		while (<$pipe>) {
			if (/^commit ($sha1)$/o) {
				my $commit = $1;
2141 2142 2143 2144

				# if we've seen a commit,
				# we've seen its parents
				last if $seen{$commit};
2145 2146 2147 2148 2149
				my ($tree) = (<$pipe> =~ /^tree ($sha1)$/o);
				unless (defined $tree) {
					die "Failed to parse commit $commit\n";
				}
				push @{$tree_map{$tree}}, $commit;
2150
				$seen{$commit} = 1;
2151 2152
			}
		}
2153
		close $pipe; # we could be breaking the pipe early
2154 2155 2156
	}
}

2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167
sub load_all_refs {
	if (@_branch_from) {
		print STDERR '--branch|-b parameters are ignored when ',
			"--branch-all-refs|-B is passed\n";
	}

	# don't worry about rev-list on non-commit objects/tags,
	# it shouldn't blow up if a ref is a blob or tree...
	chomp(@_branch_from = `git-rev-parse --symbolic --all`);
}

2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179
# '<svn username> = real-name <email address>' mapping based on git-svnimport:
sub load_authors {
	open my $authors, '<', $_authors or die "Can't open $_authors $!\n";
	while (<$authors>) {
		chomp;
		next unless /^(\S+?)\s*=\s*(.+?)\s*<(.+)>\s*$/;
		my ($user, $name, $email) = ($1, $2, $3);
		$users{$user} = [$name, $email];
	}
	close $authors or croak $!;
}

2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190
sub rload_authors {
	open my $authors, '<', $_authors or die "Can't open $_authors $!\n";
	while (<$authors>) {
		chomp;
		next unless /^(\S+?)\s*=\s*(.+?)\s*<(.+)>\s*$/;
		my ($user, $name, $email) = ($1, $2, $3);
		$rusers{"$name <$email>"} = $user;
	}
	close $authors or croak $!;
}

2191 2192 2193 2194 2195 2196
sub svn_propget_base {
	my ($p, $f) = @_;
	$f .= '@BASE' if $_svn_pg_peg_revs;
	return safe_qx(qw/svn propget/, $p, $f);
}

2197 2198 2199 2200 2201 2202 2203 2204 2205 2206
sub git_svn_each {
	my $sub = shift;
	foreach (`git-rev-parse --symbolic --all`) {
		next unless s#^refs/remotes/##;
		chomp $_;
		next unless -f "$GIT_DIR/svn/$_/info/url";
		&$sub($_);
	}
}

2207 2208 2209 2210 2211 2212 2213 2214 2215
sub migrate_revdb {
	git_svn_each(sub {
		my $id = shift;
		defined(my $pid = fork) or croak $!;
		if (!$pid) {
			$GIT_SVN = $ENV{GIT_SVN_ID} = $id;
			init_vars();
			exit 0 if -r $REVDB;
			print "Upgrading svn => git mapping...\n";
2216
			-d $GIT_SVN_DIR or mkpath([$GIT_SVN_DIR]);
2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228
			open my $fh, '>>',$REVDB or croak $!;
			close $fh;
			rebuild();
			print "Done upgrading. You may now delete the ",
				"deprecated $GIT_SVN_DIR/revs directory\n";
			exit 0;
		}
		waitpid $pid, 0;
		croak $? if $?;
	});
}

2229
sub migration_check {
2230
	migrate_revdb() unless (-e $REVDB);
2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249
	return if (-d "$GIT_DIR/svn" || !-d $GIT_DIR);
	print "Upgrading repository...\n";
	unless (-d "$GIT_DIR/svn") {
		mkdir "$GIT_DIR/svn" or croak $!;
	}
	print "Data from a previous version of git-svn exists, but\n\t",
				"$GIT_SVN_DIR\n\t(required for this version ",
				"($VERSION) of git-svn) does not.\n";

	foreach my $x (`git-rev-parse --symbolic --all`) {
		next unless $x =~ s#^refs/remotes/##;
		chomp $x;
		next unless -f "$GIT_DIR/$x/info/url";
		my $u = eval { file_to_s("$GIT_DIR/$x/info/url") };
		next unless $u;
		my $dn = dirname("$GIT_DIR/svn/$x");
		mkpath([$dn]) unless -d $dn;
		rename "$GIT_DIR/$x", "$GIT_DIR/svn/$x" or croak "$!: $x";
	}
2250
	migrate_revdb() if (-d $GIT_SVN_DIR && !-w $REVDB);
2251 2252 2253
	print "Done upgrading.\n";
}

2254
sub find_rev_before {
2255 2256
	my ($r, $id, $eq_ok) = @_;
	my $f = "$GIT_DIR/svn/$id/.rev_db";
2257 2258
	return (undef,undef) unless -r $f;
	--$r unless $eq_ok;
2259 2260 2261 2262 2263
	while ($r > 0) {
		if (my $c = revdb_get($f, $r)) {
			return ($r, $c);
		}
		--$r;
2264 2265 2266 2267
	}
	return (undef, undef);
}

2268 2269 2270
sub init_vars {
	$GIT_SVN ||= $ENV{GIT_SVN_ID} || 'git-svn';
	$GIT_SVN_DIR = "$GIT_DIR/svn/$GIT_SVN";
2271
	$REVDB = "$GIT_SVN_DIR/.rev_db";
2272 2273 2274
	$GIT_SVN_INDEX = "$GIT_SVN_DIR/index";
	$SVN_URL = undef;
	$SVN_WC = "$GIT_SVN_DIR/tree";
2275
	%tree_map = ();
2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300
}

# convert GetOpt::Long specs for use by git-repo-config
sub read_repo_config {
	return unless -d $GIT_DIR;
	my $opts = shift;
	foreach my $o (keys %$opts) {
		my $v = $opts->{$o};
		my ($key) = ($o =~ /^([a-z\-]+)/);
		$key =~ s/-//g;
		my $arg = 'git-repo-config';
		$arg .= ' --int' if ($o =~ /[:=]i$/);
		$arg .= ' --bool' if ($o !~ /[:=][sfi]$/);
		if (ref $v eq 'ARRAY') {
			chomp(my @tmp = `$arg --get-all svn.$key`);
			@$v = @tmp if @tmp;
		} else {
			chomp(my $tmp = `$arg --get svn.$key`);
			if ($tmp && !($arg =~ / --bool / && $tmp eq 'false')) {
				$$v = $tmp;
			}
		}
	}
}

2301 2302 2303 2304
sub set_default_vals {
	if (defined $_repack) {
		$_repack = 1000 if ($_repack <= 0);
		$_repack_nr = $_repack;
2305
		$_repack_flags ||= '-d';
2306 2307 2308
	}
}

2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342
sub read_grafts {
	my $gr_file = shift;
	my ($grafts, $comments) = ({}, {});
	if (open my $fh, '<', $gr_file) {
		my @tmp;
		while (<$fh>) {
			if (/^($sha1)\s+/) {
				my $c = $1;
				if (@tmp) {
					@{$comments->{$c}} = @tmp;
					@tmp = ();
				}
				foreach my $p (split /\s+/, $_) {
					$grafts->{$c}->{$p} = 1;
				}
			} else {
				push @tmp, $_;
			}
		}
		close $fh or croak $!;
		@{$comments->{'END'}} = @tmp if @tmp;
	}
	return ($grafts, $comments);
}

sub write_grafts {
	my ($grafts, $comments, $gr_file) = @_;

	open my $fh, '>', $gr_file or croak $!;
	foreach my $c (sort keys %$grafts) {
		if ($comments->{$c}) {
			print $fh $_ foreach @{$comments->{$c}};
		}
		my $p = $grafts->{$c};
2343
		my %x; # real parents
2344 2345 2346 2347 2348 2349 2350
		delete $p->{$c}; # commits are not self-reproducing...
		my $pid = open my $ch, '-|';
		defined $pid or croak $!;
		if (!$pid) {
			exec(qw/git-cat-file commit/, $c) or croak $!;
		}
		while (<$ch>) {
2351 2352
			if (/^parent ($sha1)/) {
				$x{$1} = $p->{$1} = 1;
2353
			} else {
2354
				last unless /^\S/;
2355 2356 2357
			}
		}
		close $ch; # breaking the pipe
2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385

		# if real parents are the only ones in the grafts, drop it
		next if join(' ',sort keys %$p) eq join(' ',sort keys %x);

		my (@ip, @jp, $mb);
		my %del = %x;
		@ip = @jp = keys %$p;
		foreach my $i (@ip) {
			next if $del{$i} || $p->{$i} == 2;
			foreach my $j (@jp) {
				next if $i eq $j || $del{$j} || $p->{$j} == 2;
				$mb = eval { safe_qx('git-merge-base',$i,$j) };
				next unless $mb;
				chomp $mb;
				next if $x{$mb};
				if ($mb eq $j) {
					delete $p->{$i};
					$del{$i} = 1;
				} elsif ($mb eq $i) {
					delete $p->{$j};
					$del{$j} = 1;
				}
			}
		}

		# if real parents are the only ones in the grafts, drop it
		next if join(' ',sort keys %$p) eq join(' ',sort keys %x);

2386 2387 2388 2389 2390 2391 2392 2393
		print $fh $c, ' ', join(' ', sort keys %$p),"\n";
	}
	if ($comments->{'END'}) {
		print $fh $_ foreach @{$comments->{'END'}};
	}
	close $fh or croak $!;
}

2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415
sub read_url_paths_all {
	my ($l_map, $pfx, $p) = @_;
	my @dir;
	foreach (<$p/*>) {
		if (-r "$_/info/url") {
			$pfx .= '/' if $pfx && $pfx !~ m!/$!;
			my $id = $pfx . basename $_;
			my $url = file_to_s("$_/info/url");
			my ($u, $p) = repo_path_split($url);
			$l_map->{$u}->{$p} = $id;
		} elsif (-d $_) {
			push @dir, $_;
		}
	}
	foreach (@dir) {
		my $x = $_;
		$x =~ s!^\Q$GIT_DIR\E/svn/!!o;
		read_url_paths_all($l_map, $x, $_);
	}
}

# this one only gets ids that have been imported, not new ones
2416 2417 2418
sub read_url_paths {
	my $l_map = {};
	git_svn_each(sub { my $x = shift;
2419 2420
			my $url = file_to_s("$GIT_DIR/svn/$x/info/url");
			my ($u, $p) = repo_path_split($url);
2421 2422 2423 2424 2425
			$l_map->{$u}->{$p} = $x;
			});
	return $l_map;
}

2426
sub extract_metadata {
2427
	my $id = shift or return (undef, undef, undef);
2428 2429 2430 2431 2432 2433 2434 2435 2436 2437
	my ($url, $rev, $uuid) = ($id =~ /^git-svn-id:\s(\S+?)\@(\d+)
							\s([a-f\d\-]+)$/x);
	if (!$rev || !$uuid || !$url) {
		# some of the original repositories I made had
		# indentifiers like this:
		($rev, $uuid) = ($id =~/^git-svn-id:\s(\d+)\@([a-f\d\-]+)/);
	}
	return ($url, $rev, $uuid);
}

2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462
sub cmt_metadata {
	return extract_metadata((grep(/^git-svn-id: /,
		safe_qx(qw/git-cat-file commit/, shift)))[-1]);
}

sub get_commit_time {
	my $cmt = shift;
	defined(my $pid = open my $fh, '-|') or croak $!;
	if (!$pid) {
		exec qw/git-rev-list --pretty=raw -n1/, $cmt or croak $!;
	}
	while (<$fh>) {
		/^committer\s(?:.+) (\d+) ([\-\+]?\d+)$/ or next;
		my ($s, $tz) = ($1, $2);
		if ($tz =~ s/^\+//) {
			$s += tz_to_s_offset($tz);
		} elsif ($tz =~ s/^\-//) {
			$s -= tz_to_s_offset($tz);
		}
		close $fh;
		return $s;
	}
	die "Can't get commit time for commit: $cmt\n";
}

2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490
sub tz_to_s_offset {
	my ($tz) = @_;
	$tz =~ s/(\d\d)$//;
	return ($1 * 60) + ($tz * 3600);
}

sub setup_pager { # translated to Perl from pager.c
	return unless (-t *STDOUT);
	my $pager = $ENV{PAGER};
	if (!defined $pager) {
		$pager = 'less';
	} elsif (length $pager == 0 || $pager eq 'cat') {
		return;
	}
	pipe my $rfd, my $wfd or return;
	defined(my $pid = fork) or croak $!;
	if (!$pid) {
		open STDOUT, '>&', $wfd or croak $!;
		return;
	}
	open STDIN, '<&', $rfd or croak $!;
	$ENV{LESS} ||= '-S';
	exec $pager or croak "Can't run pager: $!\n";;
}

sub get_author_info {
	my ($dest, $author, $t, $tz) = @_;
	$author =~ s/(?:^\s*|\s*$)//g;
2491
	$dest->{a_raw} = $author;
2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587
	my $_a;
	if ($_authors) {
		$_a = $rusers{$author} || undef;
	}
	if (!$_a) {
		($_a) = ($author =~ /<([^>]+)\@[^>]+>$/);
	}
	$dest->{t} = $t;
	$dest->{tz} = $tz;
	$dest->{a} = $_a;
	# Date::Parse isn't in the standard Perl distro :(
	if ($tz =~ s/^\+//) {
		$t += tz_to_s_offset($tz);
	} elsif ($tz =~ s/^\-//) {
		$t -= tz_to_s_offset($tz);
	}
	$dest->{t_utc} = $t;
}

sub process_commit {
	my ($c, $r_min, $r_max, $defer) = @_;
	if (defined $r_min && defined $r_max) {
		if ($r_min == $c->{r} && $r_min == $r_max) {
			show_commit($c);
			return 0;
		}
		return 1 if $r_min == $r_max;
		if ($r_min < $r_max) {
			# we need to reverse the print order
			return 0 if (defined $_limit && --$_limit < 0);
			push @$defer, $c;
			return 1;
		}
		if ($r_min != $r_max) {
			return 1 if ($r_min < $c->{r});
			return 1 if ($r_max > $c->{r});
		}
	}
	return 0 if (defined $_limit && --$_limit < 0);
	show_commit($c);
	return 1;
}

sub show_commit {
	my $c = shift;
	if ($_oneline) {
		my $x = "\n";
		if (my $l = $c->{l}) {
			while ($l->[0] =~ /^\s*$/) { shift @$l }
			$x = $l->[0];
		}
		$_l_fmt ||= 'A' . length($c->{r});
		print 'r',pack($_l_fmt, $c->{r}),' | ';
		print "$c->{c} | " if $_show_commit;
		print $x;
	} else {
		show_commit_normal($c);
	}
}

sub show_commit_normal {
	my ($c) = @_;
	print '-' x72, "\nr$c->{r} | ";
	print "$c->{c} | " if $_show_commit;
	print "$c->{a} | ", strftime("%Y-%m-%d %H:%M:%S %z (%a, %d %b %Y)",
				 localtime($c->{t_utc})), ' | ';
	my $nr_line = 0;

	if (my $l = $c->{l}) {
		while ($l->[$#$l] eq "\n" && $l->[($#$l - 1)] eq "\n") {
			pop @$l;
		}
		$nr_line = scalar @$l;
		if (!$nr_line) {
			print "1 line\n\n\n";
		} else {
			if ($nr_line == 1) {
				$nr_line = '1 line';
			} else {
				$nr_line .= ' lines';
			}
			print $nr_line, "\n\n";
			print $_ foreach @$l;
		}
	} else {
		print "1 line\n\n";

	}
	foreach my $x (qw/raw diff/) {
		if ($c->{$x}) {
			print "\n";
			print $_ foreach @{$c->{$x}}
		}
	}
}

2588 2589 2590 2591
sub libsvn_load {
	return unless $_use_lib;
	$_use_lib = eval {
		require SVN::Core;
2592 2593
		if ($SVN::Core::VERSION lt '1.1.0') {
			die "Need SVN::Core 1.1.0 or better ",
2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619
					"(got $SVN::Core::VERSION) ",
					"Falling back to command-line svn\n";
		}
		require SVN::Ra;
		require SVN::Delta;
		push @SVN::Git::Editor::ISA, 'SVN::Delta::Editor';
		my $kill_stupid_warnings = $SVN::Node::none.$SVN::Node::file.
					$SVN::Node::dir.$SVN::Node::unknown.
					$SVN::Node::none.$SVN::Node::file.
					$SVN::Node::dir.$SVN::Node::unknown;
		1;
	};
}

sub libsvn_connect {
	my ($url) = @_;
	my $auth = SVN::Core::auth_open([SVN::Client::get_simple_provider(),
			  SVN::Client::get_ssl_server_trust_file_provider(),
			  SVN::Client::get_username_provider()]);
	my $s = eval { SVN::Ra->new(url => $url, auth => $auth) };
	return $s;
}

sub libsvn_get_file {
	my ($gui, $f, $rev) = @_;
	my $p = $f;
2620
	return unless ($p =~ s#^\Q$SVN_PATH\E/##);
2621

2622
	my ($hash, $pid, $in, $out);
2623
	my $pool = SVN::Pool->new;
2624 2625
	defined($pid = open3($in, $out, '>&STDERR',
				qw/git-hash-object -w --stdin/)) or croak $!;
2626 2627 2628 2629
	# redirect STDOUT for SVN 1.1.x compatibility
	open my $stdout, '>&', \*STDOUT or croak $!;
	open STDOUT, '>&', $in or croak $!;
	my ($r, $props) = $SVN->get_file($f, $rev, \*STDOUT, $pool);
2630
	$in->flush == 0 or croak $!;
2631
	open STDOUT, '>&', $stdout or croak $!;
2632
	close $in or croak $!;
2633
	close $stdout or croak $!;
2634
	$pool->clear;
2635 2636 2637 2638 2639 2640
	chomp($hash = do { local $/; <$out> });
	close $out or croak $!;
	waitpid $pid, 0;
	$hash =~ /^$sha1$/o or die "not a sha1: $hash\n";

	my $mode = exists $props->{'svn:executable'} ? '100755' : '100644';
2641 2642
	if (exists $props->{'svn:special'}) {
		$mode = '120000';
2643
		my $link = `git-cat-file blob $hash`;
2644 2645
		$link =~ s/^link // or die "svn:special file with contents: <",
						$link, "> is not understood\n";
2646 2647 2648 2649 2650 2651 2652 2653 2654
		defined($pid = open3($in, $out, '>&STDERR',
				qw/git-hash-object -w --stdin/)) or croak $!;
		print $in $link;
		$in->flush == 0 or croak $!;
		close $in or croak $!;
		chomp($hash = do { local $/; <$out> });
		close $out or croak $!;
		waitpid $pid, 0;
		$hash =~ /^$sha1$/o or die "not a sha1: $hash\n";
2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684
	}
	print $gui $mode,' ',$hash,"\t",$p,"\0" or croak $!;
}

sub libsvn_log_entry {
	my ($rev, $author, $date, $msg, $parents) = @_;
	my ($Y,$m,$d,$H,$M,$S) = ($date =~ /^(\d{4})\-(\d\d)\-(\d\d)T
					 (\d\d)\:(\d\d)\:(\d\d).\d+Z$/x)
				or die "Unable to parse date: $date\n";
	if (defined $_authors && ! defined $users{$author}) {
		die "Author: $author not defined in $_authors file\n";
	}
	return { revision => $rev, date => "+0000 $Y-$m-$d $H:$M:$S",
		author => $author, msg => $msg."\n", parents => $parents || [] }
}

sub process_rm {
	my ($gui, $last_commit, $f) = @_;
	$f =~ s#^\Q$SVN_PATH\E/?## or return;
	# remove entire directories.
	if (safe_qx('git-ls-tree',$last_commit,'--',$f) =~ /^040000 tree/) {
		defined(my $pid = open my $ls, '-|') or croak $!;
		if (!$pid) {
			exec(qw/git-ls-tree -r --name-only -z/,
				$last_commit,'--',$f) or croak $!;
		}
		local $/ = "\0";
		while (<$ls>) {
			print $gui '0 ',0 x 40,"\t",$_ or croak $!;
		}
2685
		close $ls or croak $?;
2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698
	} else {
		print $gui '0 ',0 x 40,"\t",$f,"\0" or croak $!;
	}
}

sub libsvn_fetch {
	my ($last_commit, $paths, $rev, $author, $date, $msg) = @_;
	open my $gui, '| git-update-index -z --index-info' or croak $!;
	my @amr;
	foreach my $f (keys %$paths) {
		my $m = $paths->{$f}->action();
		$f =~ s#^/+##;
		if ($m =~ /^[DR]$/) {
2699
			print "\t$m\t$f\n" unless $_q;
2700 2701 2702 2703 2704 2705 2706 2707
			process_rm($gui, $last_commit, $f);
			next if $m eq 'D';
			# 'R' can be file replacements, too, right?
		}
		my $pool = SVN::Pool->new;
		my $t = $SVN->check_path($f, $rev, $pool);
		if ($t == $SVN::Node::file) {
			if ($m =~ /^[AMR]$/) {
2708
				push @amr, [ $m, $f ];
2709 2710 2711 2712 2713 2714
			} else {
				die "Unrecognized action: $m, ($f r$rev)\n";
			}
		}
		$pool->clear;
	}
2715 2716 2717 2718
	foreach (@amr) {
		print "\t$_->[0]\t$_->[1]\n" unless $_q;
		libsvn_get_file($gui, $_->[1], $rev)
	}
2719
	close $gui or croak $?;
2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733
	return libsvn_log_entry($rev, $author, $date, $msg, [$last_commit]);
}

sub svn_grab_base_rev {
	defined(my $pid = open my $fh, '-|') or croak $!;
	if (!$pid) {
		open my $null, '>', '/dev/null' or croak $!;
		open STDERR, '>&', $null or croak $!;
		exec qw/git-rev-parse --verify/,"refs/remotes/$GIT_SVN^0"
								or croak $!;
	}
	chomp(my $c = do { local $/; <$fh> });
	close $fh;
	if (defined $c && length $c) {
2734
		my ($url, $rev, $uuid) = cmt_metadata($c);
2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756
		return ($rev, $c) if defined $rev;
	}
	if ($_no_metadata) {
		my $offset = -41; # from tail
		my $rl;
		open my $fh, '<', $REVDB or
			die "--no-metadata specified and $REVDB not readable\n";
		seek $fh, $offset, 2;
		$rl = readline $fh;
		defined $rl or return (undef, undef);
		chomp $rl;
		while ($c ne $rl && tell $fh != 0) {
			$offset -= 41;
			seek $fh, $offset, 2;
			$rl = readline $fh;
			defined $rl or return (undef, undef);
			chomp $rl;
		}
		my $rev = tell $fh;
		croak $! if ($rev < -1);
		$rev =  ($rev - 41) / 41;
		close $fh or croak $!;
2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790
		return ($rev, $c);
	}
	return (undef, undef);
}

sub libsvn_parse_revision {
	my $base = shift;
	my $head = $SVN->get_latest_revnum();
	if (!defined $_revision || $_revision eq 'BASE:HEAD') {
		return ($base + 1, $head) if (defined $base);
		return (0, $head);
	}
	return ($1, $2) if ($_revision =~ /^(\d+):(\d+)$/);
	return ($_revision, $_revision) if ($_revision =~ /^\d+$/);
	if ($_revision =~ /^BASE:(\d+)$/) {
		return ($base + 1, $1) if (defined $base);
		return (0, $head);
	}
	return ($1, $head) if ($_revision =~ /^(\d+):HEAD$/);
	die "revision argument: $_revision not understood by git-svn\n",
		"Try using the command-line svn client instead\n";
}

sub libsvn_traverse {
	my ($gui, $pfx, $path, $rev) = @_;
	my $cwd = "$pfx/$path";
	my $pool = SVN::Pool->new;
	$cwd =~ s#^/+##g;
	my ($dirent, $r, $props) = $SVN->get_dir($cwd, $rev, $pool);
	foreach my $d (keys %$dirent) {
		my $t = $dirent->{$d}->kind;
		if ($t == $SVN::Node::dir) {
			libsvn_traverse($gui, $cwd, $d, $rev);
		} elsif ($t == $SVN::Node::file) {
2791
			print "\tA\t$cwd/$d\n" unless $_q;
2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823
			libsvn_get_file($gui, "$cwd/$d", $rev);
		}
	}
	$pool->clear;
}

sub libsvn_traverse_ignore {
	my ($fh, $path, $r) = @_;
	$path =~ s#^/+##g;
	my $pool = SVN::Pool->new;
	my ($dirent, undef, $props) = $SVN->get_dir($path, $r, $pool);
	my $p = $path;
	$p =~ s#^\Q$SVN_PATH\E/?##;
	print $fh length $p ? "\n# $p\n" : "\n# /\n";
	if (my $s = $props->{'svn:ignore'}) {
		$s =~ s/[\r\n]+/\n/g;
		chomp $s;
		if (length $p == 0) {
			$s =~ s#\n#\n/$p#g;
			print $fh "/$s\n";
		} else {
			$s =~ s#\n#\n/$p/#g;
			print $fh "/$p/$s\n";
		}
	}
	foreach (sort keys %$dirent) {
		next if $dirent->{$_}->kind != $SVN::Node::dir;
		libsvn_traverse_ignore($fh, "$path/$_", $r);
	}
	$pool->clear;
}

2824 2825 2826 2827 2828 2829 2830
sub revisions_eq {
	my ($path, $r0, $r1) = @_;
	return 1 if $r0 == $r1;
	my $nr = 0;
	if ($_use_lib) {
		# should be OK to use Pool here (r1 - r0) should be small
		my $pool = SVN::Pool->new;
2831 2832
		libsvn_get_log($SVN, "/$path", $r0, $r1,
				0, 1, 1, sub {$nr++}, $pool);
2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844
		$pool->clear;
	} else {
		my ($url, undef) = repo_path_split($SVN_URL);
		my $svn_log = svn_log_raw("$url/$path","-r$r0:$r1");
		while (next_log_entry($svn_log)) { $nr++ }
		close $svn_log->{fh};
	}
	return 0 if ($nr > 1);
	return 1;
}

sub libsvn_find_parent_branch {
2845 2846 2847 2848
	my ($paths, $rev, $author, $date, $msg) = @_;
	my $svn_path = '/'.$SVN_PATH;

	# look for a parent from another branch:
2849 2850 2851 2852 2853 2854
	my $i = $paths->{$svn_path} or return;
	my $branch_from = $i->copyfrom_path or return;
	my $r = $i->copyfrom_rev;
	print STDERR  "Found possible branch point: ",
				"$branch_from => $svn_path, $r\n";
	$branch_from =~ s#^/##;
2855 2856
	my $l_map = {};
	read_url_paths_all($l_map, '', "$GIT_DIR/svn");
2857 2858
	my $url = $SVN->{url};
	defined $l_map->{$url} or return;
2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871
	my $id = $l_map->{$url}->{$branch_from};
	if (!defined $id && $_follow_parent) {
		print STDERR "Following parent: $branch_from\@$r\n";
		# auto create a new branch and follow it
		$id = basename($branch_from);
		$id .= '@'.$r if -r "$GIT_DIR/svn/$id";
		while (-r "$GIT_DIR/svn/$id") {
			# just grow a tail if we're not unique enough :x
			$id .= '-';
		}
	}
	return unless defined $id;

2872
	my ($r0, $parent) = find_rev_before($r,$id,1);
2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889
	if ($_follow_parent && (!defined $r0 || !defined $parent)) {
		defined(my $pid = fork) or croak $!;
		if (!$pid) {
			$GIT_SVN = $ENV{GIT_SVN_ID} = $id;
			init_vars();
			$SVN_URL = "$url/$branch_from";
			$SVN_LOG = $SVN = undef;
			setup_git_svn();
			# we can't assume SVN_URL exists at r+1:
			$_revision = "0:$r";
			fetch_lib();
			exit 0;
		}
		waitpid $pid, 0;
		croak $? if $?;
		($r0, $parent) = find_rev_before($r,$id,1);
	}
2890 2891 2892
	return unless (defined $r0 && defined $parent);
	if (revisions_eq($branch_from, $r0, $r)) {
		unlink $GIT_SVN_INDEX;
2893
		print STDERR "Found branch parent: ($GIT_SVN) $parent\n";
2894 2895 2896 2897 2898
		sys(qw/git-read-tree/, $parent);
		return libsvn_fetch($parent, $paths, $rev,
					$author, $date, $msg);
	}
	print STDERR "Nope, branch point not imported or unknown\n";
2899 2900 2901
	return undef;
}

2902 2903 2904 2905 2906 2907 2908 2909
sub libsvn_get_log {
	my ($ra, @args) = @_;
	if ($SVN::Core::VERSION le '1.2.0') {
		splice(@args, 3, 1);
	}
	$ra->get_log(@args);
}

2910 2911 2912 2913 2914
sub libsvn_new_tree {
	if (my $log_entry = libsvn_find_parent_branch(@_)) {
		return $log_entry;
	}
	my ($paths, $rev, $author, $date, $msg) = @_;
2915 2916 2917 2918
	open my $gui, '| git-update-index -z --index-info' or croak $!;
	my $pool = SVN::Pool->new;
	libsvn_traverse($gui, '', $SVN_PATH, $rev, $pool);
	$pool->clear;
2919
	close $gui or croak $?;
2920 2921 2922 2923 2924 2925 2926 2927
	return libsvn_log_entry($rev, $author, $date, $msg);
}

sub find_graft_path_commit {
	my ($tree_paths, $p1, $r1) = @_;
	foreach my $x (keys %$tree_paths) {
		next unless ($p1 =~ /^\Q$x\E/);
		my $i = $tree_paths->{$x};
2928 2929
		my ($r0, $parent) = find_rev_before($r1,$i,1);
		return $parent if (defined $r0 && $r0 == $r1);
2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940
		print STDERR "r$r1 of $i not imported\n";
		next;
	}
	return undef;
}

sub find_graft_path_parents {
	my ($grafts, $tree_paths, $c, $p0, $r0) = @_;
	foreach my $x (keys %$tree_paths) {
		next unless ($p0 =~ /^\Q$x\E/);
		my $i = $tree_paths->{$x};
2941 2942
		my ($r, $parent) = find_rev_before($r0, $i, 1);
		if (defined $r && defined $parent && revisions_eq($x,$r,$r0)) {
2943 2944 2945 2946
			my ($url_b, undef, $uuid_b) = cmt_metadata($c);
			my ($url_a, undef, $uuid_a) = cmt_metadata($parent);
			next if ($url_a && $url_b && $url_a eq $url_b &&
							$uuid_b eq $uuid_a);
2947
			$grafts->{$c}->{$parent} = 1;
2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985
		}
	}
}

sub libsvn_graft_file_copies {
	my ($grafts, $tree_paths, $path, $paths, $rev) = @_;
	foreach (keys %$paths) {
		my $i = $paths->{$_};
		my ($m, $p0, $r0) = ($i->action, $i->copyfrom_path,
					$i->copyfrom_rev);
		next unless (defined $p0 && defined $r0);

		my $p1 = $_;
		$p1 =~ s#^/##;
		$p0 =~ s#^/##;
		my $c = find_graft_path_commit($tree_paths, $p1, $rev);
		next unless $c;
		find_graft_path_parents($grafts, $tree_paths, $c, $p0, $r0);
	}
}

sub set_index {
	my $old = $ENV{GIT_INDEX_FILE};
	$ENV{GIT_INDEX_FILE} = shift;
	return $old;
}

sub restore_index {
	my ($old) = @_;
	if (defined $old) {
		$ENV{GIT_INDEX_FILE} = $old;
	} else {
		delete $ENV{GIT_INDEX_FILE};
	}
}

sub libsvn_commit_cb {
	my ($rev, $date, $committer, $c, $msg, $r_last, $cmt_last) = @_;
2986
	if ($_optimize_commits && $rev == ($r_last + 1)) {
2987 2988 2989 2990 2991 2992 2993 2994 2995 2996
		my $log = libsvn_log_entry($rev,$committer,$date,$msg);
		$log->{tree} = get_tree_from_treeish($c);
		my $cmt = git_commit($log, $cmt_last, $c);
		my @diff = safe_qx('git-diff-tree', $cmt, $c);
		if (@diff) {
			print STDERR "Trees differ: $cmt $c\n",
					join('',@diff),"\n";
			exit 1;
		}
	} else {
2997
		fetch("$rev=$c");
2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035
	}
}

sub libsvn_ls_fullurl {
	my $fullurl = shift;
	my ($repo, $path) = repo_path_split($fullurl);
	$SVN ||= libsvn_connect($repo);
	my @ret;
	my $pool = SVN::Pool->new;
	my ($dirent, undef, undef) = $SVN->get_dir($path,
						$SVN->get_latest_revnum, $pool);
	foreach my $d (keys %$dirent) {
		if ($dirent->{$d}->kind == $SVN::Node::dir) {
			push @ret, "$d/"; # add '/' for compat with cli svn
		}
	}
	$pool->clear;
	return @ret;
}


sub libsvn_skip_unknown_revs {
	my $err = shift;
	my $errno = $err->apr_err();
	# Maybe the branch we're tracking didn't
	# exist when the repo started, so it's
	# not an error if it doesn't, just continue
	#
	# Wonderfully consistent library, eh?
	# 160013 - svn:// and file://
	# 175002 - http(s)://
	#   More codes may be discovered later...
	if ($errno == 175002 || $errno == 160013) {
		return;
	}
	croak "Error from SVN, ($errno): ", $err->expanded_message,"\n";
};

3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078
# Tie::File seems to be prone to offset errors if revisions get sparse,
# it's not that fast, either.  Tie::File is also not in Perl 5.6.  So
# one of my favorite modules is out :<  Next up would be one of the DBM
# modules, but I'm not sure which is most portable...  So I'll just
# go with something that's plain-text, but still capable of
# being randomly accessed.  So here's my ultra-simple fixed-width
# database.  All records are 40 characters + "\n", so it's easy to seek
# to a revision: (41 * rev) is the byte offset.
# A record of 40 0s denotes an empty revision.
# And yes, it's still pretty fast (faster than Tie::File).
sub revdb_set {
	my ($file, $rev, $commit) = @_;
	length $commit == 40 or croak "arg3 must be a full SHA1 hexsum\n";
	open my $fh, '+<', $file or croak $!;
	my $offset = $rev * 41;
	# assume that append is the common case:
	seek $fh, 0, 2 or croak $!;
	my $pos = tell $fh;
	if ($pos < $offset) {
		print $fh (('0' x 40),"\n") x (($offset - $pos) / 41);
	}
	seek $fh, $offset, 0 or croak $!;
	print $fh $commit,"\n";
	close $fh or croak $!;
}

sub revdb_get {
	my ($file, $rev) = @_;
	my $ret;
	my $offset = $rev * 41;
	open my $fh, '<', $file or croak $!;
	seek $fh, $offset, 0;
	if (tell $fh == $offset) {
		$ret = readline $fh;
		if (defined $ret) {
			chomp $ret;
			$ret = undef if ($ret =~ /^0{40}$/);
		}
	}
	close $fh or croak $!;
	return $ret;
}

3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089
sub copy_remote_ref {
	my $origin = $_cp_remote ? $_cp_remote : 'origin';
	my $ref = "refs/remotes/$GIT_SVN";
	if (safe_qx('git-ls-remote', $origin, $ref)) {
		sys(qw/git fetch/, $origin, "$ref:$ref");
	} else {
		die "Unable to find remote reference: ",
				"refs/remotes/$GIT_SVN on $origin\n";
	}
}

3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127
package SVN::Git::Editor;
use vars qw/@ISA/;
use strict;
use warnings;
use Carp qw/croak/;
use IO::File;

sub new {
	my $class = shift;
	my $git_svn = shift;
	my $self = SVN::Delta::Editor->new(@_);
	bless $self, $class;
	foreach (qw/svn_path c r ra /) {
		die "$_ required!\n" unless (defined $git_svn->{$_});
		$self->{$_} = $git_svn->{$_};
	}
	$self->{pool} = SVN::Pool->new;
	$self->{bat} = { '' => $self->open_root($self->{r}, $self->{pool}) };
	$self->{rm} = { };
	require Digest::MD5;
	return $self;
}

sub split_path {
	return ($_[0] =~ m#^(.*?)/?([^/]+)$#);
}

sub repo_path {
	(defined $_[1] && length $_[1]) ? "$_[0]->{svn_path}/$_[1]"
					: $_[0]->{svn_path}
}

sub url_path {
	my ($self, $path) = @_;
	$self->{ra}->{url} . '/' . $self->repo_path($path);
}

sub rmdirs {
3128
	my ($self, $q) = @_;
3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150
	my $rm = $self->{rm};
	delete $rm->{''}; # we never delete the url we're tracking
	return unless %$rm;

	foreach (keys %$rm) {
		my @d = split m#/#, $_;
		my $c = shift @d;
		$rm->{$c} = 1;
		while (@d) {
			$c .= '/' . shift @d;
			$rm->{$c} = 1;
		}
	}
	delete $rm->{$self->{svn_path}};
	delete $rm->{''}; # we never delete the url we're tracking
	return unless %$rm;

	defined(my $pid = open my $fh,'-|') or croak $!;
	if (!$pid) {
		exec qw/git-ls-tree --name-only -r -z/, $self->{c} or croak $!;
	}
	local $/ = "\0";
3151
	my @svn_path = split m#/#, $self->{svn_path};
3152 3153
	while (<$fh>) {
		chomp;
3154 3155 3156 3157 3158 3159 3160 3161
		my @dn = (@svn_path, (split m#/#, $_));
		while (pop @dn) {
			delete $rm->{join '/', @dn};
		}
		unless (%$rm) {
			close $fh;
			return;
		}
3162
	}
3163 3164
	close $fh;

3165 3166 3167 3168
	my ($r, $p, $bat) = ($self->{r}, $self->{pool}, $self->{bat});
	foreach my $d (sort { $b =~ tr#/#/# <=> $a =~ tr#/#/# } keys %$rm) {
		$self->close_directory($bat->{$d}, $p);
		my ($dn) = ($d =~ m#^(.*?)/?(?:[^/]+)$#);
3169
		print "\tD+\t/$d/\n" unless $q;
3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209
		$self->SUPER::delete_entry($d, $r, $bat->{$dn}, $p);
		delete $bat->{$d};
	}
}

sub open_or_add_dir {
	my ($self, $full_path, $baton) = @_;
	my $p = SVN::Pool->new;
	my $t = $self->{ra}->check_path($full_path, $self->{r}, $p);
	$p->clear;
	if ($t == $SVN::Node::none) {
		return $self->add_directory($full_path, $baton,
						undef, -1, $self->{pool});
	} elsif ($t == $SVN::Node::dir) {
		return $self->open_directory($full_path, $baton,
						$self->{r}, $self->{pool});
	}
	print STDERR "$full_path already exists in repository at ",
		"r$self->{r} and it is not a directory (",
		($t == $SVN::Node::file ? 'file' : 'unknown'),"/$t)\n";
	exit 1;
}

sub ensure_path {
	my ($self, $path) = @_;
	my $bat = $self->{bat};
	$path = $self->repo_path($path);
	return $bat->{''} unless (length $path);
	my @p = split m#/+#, $path;
	my $c = shift @p;
	$bat->{$c} ||= $self->open_or_add_dir($c, $bat->{''});
	while (@p) {
		my $c0 = $c;
		$c .= '/' . shift @p;
		$bat->{$c} ||= $self->open_or_add_dir($c, $bat->{$c0});
	}
	return $bat->{$c};
}

sub A {
3210
	my ($self, $m, $q) = @_;
3211 3212 3213 3214
	my ($dir, $file) = split_path($m->{file_b});
	my $pbat = $self->ensure_path($dir);
	my $fbat = $self->add_file($self->repo_path($m->{file_b}), $pbat,
					undef, -1);
3215
	print "\tA\t$m->{file_b}\n" unless $q;
3216 3217 3218 3219 3220
	$self->chg_file($fbat, $m);
	$self->close_file($fbat,undef,$self->{pool});
}

sub C {
3221
	my ($self, $m, $q) = @_;
3222 3223 3224 3225
	my ($dir, $file) = split_path($m->{file_b});
	my $pbat = $self->ensure_path($dir);
	my $fbat = $self->add_file($self->repo_path($m->{file_b}), $pbat,
				$self->url_path($m->{file_a}), $self->{r});
3226
	print "\tC\t$m->{file_a} => $m->{file_b}\n" unless $q;
3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239
	$self->chg_file($fbat, $m);
	$self->close_file($fbat,undef,$self->{pool});
}

sub delete_entry {
	my ($self, $path, $pbat) = @_;
	my $rpath = $self->repo_path($path);
	my ($dir, $file) = split_path($rpath);
	$self->{rm}->{$dir} = 1;
	$self->SUPER::delete_entry($rpath, $self->{r}, $pbat, $self->{pool});
}

sub R {
3240
	my ($self, $m, $q) = @_;
3241 3242 3243 3244
	my ($dir, $file) = split_path($m->{file_b});
	my $pbat = $self->ensure_path($dir);
	my $fbat = $self->add_file($self->repo_path($m->{file_b}), $pbat,
				$self->url_path($m->{file_a}), $self->{r});
3245
	print "\tR\t$m->{file_a} => $m->{file_b}\n" unless $q;
3246 3247 3248 3249 3250 3251 3252 3253 3254
	$self->chg_file($fbat, $m);
	$self->close_file($fbat,undef,$self->{pool});

	($dir, $file) = split_path($m->{file_a});
	$pbat = $self->ensure_path($dir);
	$self->delete_entry($m->{file_a}, $pbat);
}

sub M {
3255
	my ($self, $m, $q) = @_;
3256 3257 3258 3259
	my ($dir, $file) = split_path($m->{file_b});
	my $pbat = $self->ensure_path($dir);
	my $fbat = $self->open_file($self->repo_path($m->{file_b}),
				$pbat,$self->{r},$self->{pool});
3260
	print "\t$m->{chg}\t$m->{file_b}\n" unless $q;
3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308
	$self->chg_file($fbat, $m);
	$self->close_file($fbat,undef,$self->{pool});
}

sub T { shift->M(@_) }

sub change_file_prop {
	my ($self, $fbat, $pname, $pval) = @_;
	$self->SUPER::change_file_prop($fbat, $pname, $pval, $self->{pool});
}

sub chg_file {
	my ($self, $fbat, $m) = @_;
	if ($m->{mode_b} =~ /755$/ && $m->{mode_a} !~ /755$/) {
		$self->change_file_prop($fbat,'svn:executable','*');
	} elsif ($m->{mode_b} !~ /755$/ && $m->{mode_a} =~ /755$/) {
		$self->change_file_prop($fbat,'svn:executable',undef);
	}
	my $fh = IO::File->new_tmpfile or croak $!;
	if ($m->{mode_b} =~ /^120/) {
		print $fh 'link ' or croak $!;
		$self->change_file_prop($fbat,'svn:special','*');
	} elsif ($m->{mode_a} =~ /^120/ && $m->{mode_b} !~ /^120/) {
		$self->change_file_prop($fbat,'svn:special',undef);
	}
	defined(my $pid = fork) or croak $!;
	if (!$pid) {
		open STDOUT, '>&', $fh or croak $!;
		exec qw/git-cat-file blob/, $m->{sha1_b} or croak $!;
	}
	waitpid $pid, 0;
	croak $? if $?;
	$fh->flush == 0 or croak $!;
	seek $fh, 0, 0 or croak $!;

	my $md5 = Digest::MD5->new;
	$md5->addfile($fh) or croak $!;
	seek $fh, 0, 0 or croak $!;

	my $exp = $md5->hexdigest;
	my $atd = $self->apply_textdelta($fbat, undef, $self->{pool});
	my $got = SVN::TxDelta::send_stream($fh, @$atd, $self->{pool});
	die "Checksum mismatch\nexpected: $exp\ngot: $got\n" if ($got ne $exp);

	close $fh or croak $!;
}

sub D {
3309
	my ($self, $m, $q) = @_;
3310 3311
	my ($dir, $file) = split_path($m->{file_b});
	my $pbat = $self->ensure_path($dir);
3312
	print "\tD\t$m->{file_b}\n" unless $q;
3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331
	$self->delete_entry($m->{file_b}, $pbat);
}

sub close_edit {
	my ($self) = @_;
	my ($p,$bat) = ($self->{pool}, $self->{bat});
	foreach (sort { $b =~ tr#/#/# <=> $a =~ tr#/#/# } keys %$bat) {
		$self->close_directory($bat->{$_}, $p);
	}
	$self->SUPER::close_edit($p);
	$p->clear;
}

sub abort_edit {
	my ($self) = @_;
	$self->SUPER::abort_edit($self->{pool});
	$self->{pool}->clear;
}

E
Eric Wong 已提交
3332 3333 3334 3335
__END__

Data structures:

3336 3337 3338 3339 3340
$svn_log hashref (as returned by svn_log_raw)
{
	fh => file handle of the log file,
	state => state of the log file parser (sep/msg/rev/msg_start...)
}
E
Eric Wong 已提交
3341

3342
$log_msg hashref as returned by next_log_entry($svn_log)
E
Eric Wong 已提交
3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359
{
	msg => 'whitespace-formatted log entry
',						# trailing newline is preserved
	revision => '8',			# integer
	date => '2004-02-24T17:01:44.108345Z',	# commit date
	author => 'committer name'
};


@mods = array of diff-index line hashes, each element represents one line
	of diff-index output

diff-index line ($m hash)
{
	mode_a => first column of diff-index output, no leading ':',
	mode_b => second column of diff-index output,
	sha1_b => sha1sum of the final blob,
3360
	chg => change type [MCRADT],
E
Eric Wong 已提交
3361 3362 3363 3364
	file_a => original file name of a file (iff chg is 'C' or 'R')
	file_b => new/current file name of a file (any chg)
}
;
3365

3366 3367 3368 3369 3370 3371 3372 3373 3374 3375
# retval of read_url_paths{,_all}();
$l_map = {
	# repository root url
	'https://svn.musicpd.org' => {
		# repository path 		# GIT_SVN_ID
		'mpd/trunk'		=>	'trunk',
		'mpd/tags/0.11.5'	=>	'tags/0.11.5',
	},
}

3376 3377 3378
Notes:
	I don't trust the each() function on unless I created %hash myself
	because the internal iterator may not have started at base.