git-svn.perl 103.0 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 8
		$sha1 $sha1_short $_revision
		$_q $_authors %users/;
E
Eric Wong 已提交
9
$AUTHOR = 'Eric Wong <normalperson@yhbt.net>';
E
Eric Wong 已提交
10
$VERSION = '@@GIT_VERSION@@';
11

12
$ENV{GIT_DIR} ||= '.git';
13
$Git::SVN::default_repo_id = 'svn';
14
$Git::SVN::default_ref_id = $ENV{GIT_SVN_ID} || 'git-svn';
15
$Git::SVN::Ra::_log_window_size = 100;
16

17
$Git::SVN::Log::TZ = $ENV{TZ};
E
Eric Wong 已提交
18
$ENV{TZ} = 'UTC';
19
$| = 1; # unbuffer STDOUT
E
Eric Wong 已提交
20

21
sub fatal (@) { print STDERR @_; exit 1 }
22 23 24 25 26 27
require SVN::Core; # use()-ing this causes segfaults for me... *shrug*
require SVN::Ra;
require SVN::Delta;
if ($SVN::Core::VERSION lt '1.1.0') {
	fatal "Need SVN::Core 1.1.0 or better (got $SVN::Core::VERSION)\n";
}
28
push @Git::SVN::Ra::ISA, 'SVN::Ra';
29 30
push @SVN::Git::Editor::ISA, 'SVN::Delta::Editor';
push @SVN::Git::Fetcher::ISA, 'SVN::Delta::Editor';
E
Eric Wong 已提交
31 32 33 34
use Carp qw/croak/;
use IO::File qw//;
use File::Basename qw/dirname basename/;
use File::Path qw/mkpath/;
35
use Getopt::Long qw/:config gnu_getopt no_ignore_case auto_abbrev pass_through/;
36
use IPC::Open3;
37
use Git;
38

39 40 41 42 43
BEGIN {
	my $s;
	foreach (qw/command command_oneline command_noisy command_output_pipe
	            command_input_pipe command_close_pipe/) {
		$s .= "*SVN::Git::Editor::$_ = *SVN::Git::Fetcher::$_ = ".
44
		      "*Git::SVN::Migration::$_ = ".
45
		      "*Git::SVN::Log::$_ = *Git::SVN::$_ = *$_ = *Git::$_; ";
46 47 48 49
	}
	eval $s;
}

50
my ($SVN);
51

52 53
$sha1 = qr/[a-f\d]{40}/;
$sha1_short = qr/[a-f\d]{4,40}/;
54
my ($_stdin, $_help, $_edit,
55
	$_message, $_file,
56
	$_template, $_shared,
57
	$_version, $_fetch_all,
58
	$_merge, $_strategy, $_dry_run,
59
	$_prefix, $_no_checkout);
60
$Git::SVN::_follow_parent = 1;
61 62 63
my %remote_opts = ( 'username=s' => \$Git::SVN::Prompt::_username,
                    'config-dir=s' => \$Git::SVN::Ra::config_dir,
                    'no-auth-cache' => \$Git::SVN::Prompt::_no_auth_cache );
64
my %fc_opts = ( 'follow-parent|follow!' => \$Git::SVN::_follow_parent,
65
		'authors-file|A=s' => \$_authors,
E
Eric Wong 已提交
66
		'repack:i' => \$Git::SVN::_repack,
67 68
		'noMetadata' => \$Git::SVN::_no_metadata,
		'useSvmProps' => \$Git::SVN::_use_svm_props,
69
		'log-window-size=i' => \$Git::SVN::Ra::_log_window_size,
70
		'no-checkout' => \$_no_checkout,
71
		'quiet|q' => \$_q,
E
Eric Wong 已提交
72 73
		'repack-flags|repack-args|repack-opts=s' =>
		   \$Git::SVN::_repack_flags,
74
		%remote_opts );
75

76
my ($_trunk, $_tags, $_branches);
77 78 79 80
my %init_opts = ( 'template=s' => \$_template, 'shared:s' => \$_shared,
                  'trunk|T=s' => \$_trunk, 'tags|t=s' => \$_tags,
                  'branches|b=s' => \$_branches, 'prefix=s' => \$_prefix,
                  %remote_opts );
E
Eric Wong 已提交
81
my %cmt_opts = ( 'edit|e' => \$_edit,
82 83 84 85
		'rmdir' => \$SVN::Git::Editor::_rmdir,
		'find-copies-harder' => \$SVN::Git::Editor::_find_copies_harder,
		'l=i' => \$SVN::Git::Editor::_rename_limit,
		'copy-similarity|C=i'=> \$SVN::Git::Editor::_cp_similarity
E
Eric Wong 已提交
86
);
87

E
Eric Wong 已提交
88
my %cmd = (
89
	fetch => [ \&cmd_fetch, "Download new revisions from SVN",
90 91 92
			{ 'revision|r=s' => \$_revision,
			  'all|a' => \$_fetch_all,
			   %fc_opts } ],
93
	init => [ \&cmd_init, "Initialize a repo for tracking" .
94
			  " (requires URL argument)",
95
			  \%init_opts ],
96 97 98 99
	'multi-init' => [ \&cmd_multi_init,
	                  "Deprecated alias for ".
			  "'$0 init -T<trunk> -b<branches> -t<tags>'",
			  \%init_opts ],
100 101
	dcommit => [ \&cmd_dcommit,
	             'Commit several diffs to merge with upstream',
102 103 104
			{ 'merge|m|M' => \$_merge,
			  'strategy|s=s' => \$_strategy,
			  'dry-run|n' => \$_dry_run,
105
			%cmt_opts, %fc_opts } ],
106 107 108
	'set-tree' => [ \&cmd_set_tree,
	                "Set an SVN repository to a git tree-ish",
			{ 'stdin|' => \$_stdin, %cmt_opts, %fc_opts, } ],
109
	'show-ignore' => [ \&cmd_show_ignore, "Show svn:ignore listings",
110
			{ 'revision|r=i' => \$_revision } ],
111
	'multi-fetch' => [ \&cmd_multi_fetch,
112 113
	                   "Deprecated alias for $0 fetch --all",
			   { 'revision|r=s' => \$_revision, %fc_opts } ],
114 115 116 117
	'migrate' => [ sub { },
	               # no-op, we automatically run this anyways,
	               'Migrate configuration/metadata/layout from
		        previous versions of git-svn',
118 119
                       { 'minimize' => \$Git::SVN::Migration::_minimize,
			 %remote_opts } ],
120 121
	'log' => [ \&Git::SVN::Log::cmd_show_log, 'Show commit logs',
			{ 'limit=i' => \$Git::SVN::Log::limit,
122
			  'revision|r=s' => \$_revision,
123 124 125 126 127
			  'verbose|v' => \$Git::SVN::Log::verbose,
			  'incremental' => \$Git::SVN::Log::incremental,
			  'oneline' => \$Git::SVN::Log::oneline,
			  'show-commit' => \$Git::SVN::Log::show_commit,
			  'non-recursive' => \$Git::SVN::Log::non_recursive,
128
			  'authors-file|A=s' => \$_authors,
129 130
			  'color' => \$Git::SVN::Log::color,
			  'pager=s' => \$Git::SVN::Log::pager,
131
			} ],
132 133
	'commit-diff' => [ \&cmd_commit_diff,
	                   'Commit a diff between two trees',
E
Eric Wong 已提交
134 135
			{ 'message|m=s' => \$_message,
			  'file|F=s' => \$_file,
136
			  'revision|r=s' => \$_revision,
E
Eric Wong 已提交
137
			%cmt_opts } ],
E
Eric Wong 已提交
138
);
139

E
Eric Wong 已提交
140 141 142 143 144 145 146 147 148
my $cmd;
for (my $i = 0; $i < @ARGV; $i++) {
	if (defined $cmd{$ARGV[$i]}) {
		$cmd = $ARGV[$i];
		splice @ARGV, $i, 1;
		last;
	}
};

149
my %opts = %{$cmd{$cmd}->[2]} if (defined $cmd);
150

151
read_repo_config(\%opts);
152 153 154 155
my $rv = GetOptions(%opts, 'help|H|h' => \$_help, 'version|V' => \$_version,
                    'minimize-connections' => \$Git::SVN::Migration::_minimize,
                    'id|i=s' => \$Git::SVN::default_ref_id,
                    'svn-remote|remote|R=s' => \$Git::SVN::default_repo_id);
156
exit 1 if (!$rv && $cmd ne 'log');
157

E
Eric Wong 已提交
158
usage(0) if $_help;
159
version() if $_version;
160 161
usage(1) unless defined $cmd;
load_authors() if $_authors;
162
unless ($cmd =~ /^(?:init|multi-init|commit-diff)$/) {
163 164
	Git::SVN::Migration::migration_check();
}
E
Eric Wong 已提交
165
Git::SVN::init_vars();
166 167 168 169 170
eval {
	Git::SVN::verify_remotes_sanity();
	$cmd{$cmd}->[0]->(@ARGV);
};
fatal $@ if $@;
171
post_fetch_checkout();
E
Eric Wong 已提交
172 173 174 175 176 177 178 179 180
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
181 182

	print $fd "Available commands:\n" unless $cmd;
E
Eric Wong 已提交
183 184

	foreach (sort keys %cmd) {
185
		next if $cmd && $cmd ne $_;
186
		next if /^multi-/; # don't show deprecated commands
187
		print $fd '  ',pack('A17',$_),$cmd{$_}->[1],"\n";
188 189
		foreach (keys %{$cmd{$_}->[2]}) {
			# prints out arguments as they should be passed:
190
			my $x = s#[:=]s$## ? '<arg>' : s#[:=]i$## ? '<num>' : '';
191
			print $fd ' ' x 21, join(', ', map { length $_ > 1 ?
192 193 194
							"--$_" : "-$_" }
						split /\|/,$_)," $x\n";
		}
E
Eric Wong 已提交
195 196
	}
	print $fd <<"";
197 198 199 200
\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
201 202 203 204

	exit $exit;
}

205
sub version {
206
	print "git-svn version $VERSION (svn $SVN::Core::VERSION)\n";
207 208 209
	exit 0;
}

210 211 212 213
sub do_git_init_db {
	unless (-d $ENV{GIT_DIR}) {
		my @init_db = ('init');
		push @init_db, "--template=$_template" if defined $_template;
214 215 216 217 218 219 220
		if (defined $_shared) {
			if ($_shared =~ /[a-z]/) {
				push @init_db, "--shared=$_shared";
			} else {
				push @init_db, "--shared";
			}
		}
221 222 223 224
		command_noisy(@init_db);
	}
}

225 226 227 228 229 230 231
sub init_subdir {
	my $repo_path = shift or return;
	mkpath([$repo_path]) unless -d $repo_path;
	chdir $repo_path or die "Couldn't chdir to $repo_path: $!\n";
	$ENV{GIT_DIR} = $repo_path . "/.git";
}

232
sub cmd_init {
233 234
	if (defined $_trunk || defined $_branches || defined $_tags) {
		return cmd_multi_init(@_);
235
	}
236 237 238
	my $url = shift or die "SVN repository location required ",
	                       "as a command-line argument\n";
	init_subdir(@_);
239
	do_git_init_db();
240

241
	Git::SVN->init($url);
E
Eric Wong 已提交
242 243
}

244
sub cmd_fetch {
245 246 247
	if (grep /^\d+=./, @_) {
		die "'<rev>=<commit>' fetch arguments are ",
		    "no longer supported.\n";
248
	}
249 250 251 252 253 254 255 256 257
	my ($remote) = @_;
	if (@_ > 1) {
		die "Usage: $0 fetch [--all|-a] [svn-remote]\n";
	}
	$remote ||= $Git::SVN::default_repo_id;
	if ($_fetch_all) {
		cmd_multi_fetch();
	} else {
		Git::SVN::fetch_all($remote, Git::SVN::read_all_remotes());
258
	}
259 260
}

261
sub cmd_set_tree {
E
Eric Wong 已提交
262 263 264 265 266
	my (@commits) = @_;
	if ($_stdin || !@commits) {
		print "Reading from stdin...\n";
		@commits = ();
		while (<STDIN>) {
267
			if (/\b($sha1_short)\b/o) {
E
Eric Wong 已提交
268 269 270 271 272
				unshift @commits, $1;
			}
		}
	}
	my @revs;
273
	foreach my $c (@commits) {
E
Eric Wong 已提交
274
		my @tmp = command('rev-parse',$c);
275 276 277
		if (scalar @tmp == 1) {
			push @revs, $tmp[0];
		} elsif (scalar @tmp > 1) {
E
Eric Wong 已提交
278
			push @revs, reverse(command('rev-list',@tmp));
279
		} else {
280
			fatal "Failed to rev-parse $c\n";
281
		}
E
Eric Wong 已提交
282
	}
283 284 285
	my $gs = Git::SVN->new;
	my ($r_last, $cmt_last) = $gs->last_rev_commit;
	$gs->fetch;
286
	if (defined $gs->{last_rev} && $r_last != $gs->{last_rev}) {
287 288 289 290
		fatal "There are new revisions that were fetched ",
		      "and need to be merged (or acknowledged) ",
		      "before committing.\nlast rev: $r_last\n",
		      " current: $gs->{last_rev}\n";
291
	}
292 293
	$gs->set_tree($_) foreach @revs;
	print "Done committing ",scalar @revs," revisions to SVN\n";
294
}
295

296 297 298
sub cmd_dcommit {
	my $head = shift;
	$head ||= 'HEAD';
299
	my ($url, $rev, $uuid);
300
	my ($fh, $ctx) = command_output_pipe('rev-list', $head);
301 302 303 304 305 306 307 308 309 310 311 312 313 314
	my @refs;
	my $c;
	while (<$fh>) {
		$c = $_;
		chomp $c;
		($url, $rev, $uuid) = cmt_metadata($c);
		last if (defined $url && defined $rev && defined $uuid);
		unshift @refs, $c;
	}
	close $fh; # most likely breaking the pipe
	unless (defined $url && defined $rev && defined $uuid) {
		die "Unable to determine upstream SVN information from ",
		    "$head history:\n  $ctx\n";
	}
315
	my $gs = Git::SVN->find_by_url($url);
316
	my $last_rev;
317
	foreach my $d (@refs) {
E
Eric Wong 已提交
318
		if (!verify_ref("$d~1")) {
319 320 321 322 323
			fatal "Commit $d\n",
			      "has no parent commit, and therefore ",
			      "nothing to diff against.\n",
			      "You should be working from a repository ",
			      "originally created by git-svn\n";
324
		}
325 326 327
		unless (defined $last_rev) {
			(undef, $last_rev, undef) = cmt_metadata("$d~1");
			unless (defined $last_rev) {
328 329
				fatal "Unable to extract revision information ",
				      "from commit $d~1\n";
330 331
			}
		}
E
Eric Wong 已提交
332 333 334
		if ($_dry_run) {
			print "diff-tree $d~1 $d\n";
		} else {
335
			my %ed_opts = ( r => $last_rev,
336
			                log => get_commit_entry($d)->{log},
337
			                ra => Git::SVN::Ra->new($url),
338 339 340 341 342
			                tree_a => "$d~1",
			                tree_b => $d,
			                editor_cb => sub {
			                       print "Committed r$_[0]\n";
			                       $last_rev = $_[0]; },
343
			                svn_path => '');
344
			if (!SVN::Git::Editor->new(\%ed_opts)->apply_diff) {
345 346
				print "No changes\n$d~1 == $d\n";
			}
E
Eric Wong 已提交
347 348 349
		}
	}
	return if $_dry_run;
350 351 352 353 354 355 356
	unless ($gs) {
		warn "Could not determine fetch information for $url\n",
		     "Will not attempt to fetch and rebase commits.\n",
		     "This probably means you have useSvmProps and should\n",
		     "now resync your SVN::Mirror repository.\n";
		return;
	}
357 358 359 360
	$gs->fetch;
	# we always want to rebase against the current HEAD, not any
	# head that was passed to us
	my @diff = command('diff-tree', 'HEAD', $gs->refname, '--');
E
Eric Wong 已提交
361 362 363 364 365
	my @finish;
	if (@diff) {
		@finish = qw/rebase/;
		push @finish, qw/--merge/ if $_merge;
		push @finish, "--strategy=$_strategy" if $_strategy;
366 367
		print STDERR "W: HEAD and ", $gs->refname, " differ, ",
		             "using @finish:\n", "@diff";
E
Eric Wong 已提交
368
	} else {
369 370 371
		print "No changes between current HEAD and ",
		      $gs->refname, "\nResetting to the latest ",
		      $gs->refname, "\n";
372
		@finish = qw/reset --mixed/;
E
Eric Wong 已提交
373
	}
374
	command_noisy(@finish, $gs->refname);
E
Eric Wong 已提交
375 376
}

377 378 379 380
sub cmd_show_ignore {
	my $gs = Git::SVN->new;
	my $r = (defined $_revision ? $_revision : $gs->ra->get_latest_revnum);
	$gs->traverse_ignore(\*STDOUT, '', $r);
381 382
}

383
sub cmd_multi_init {
384
	my $url = shift;
385 386
	unless (defined $_trunk || defined $_branches || defined $_tags) {
		usage(1);
387
	}
388 389
	do_git_init_db();
	$_prefix = '' unless defined $_prefix;
390 391 392 393
	if (defined $url) {
		$url =~ s#/+$##;
		init_subdir(@_);
	}
394
	if (defined $_trunk) {
395 396 397
		my $trunk_ref = $_prefix . 'trunk';
		# try both old-style and new-style lookups:
		my $gs_trunk = eval { Git::SVN->new($trunk_ref) };
398
		unless ($gs_trunk) {
399 400 401 402
			my ($trunk_url, $trunk_path) =
			                      complete_svn_url($url, $_trunk);
			$gs_trunk = Git::SVN->init($trunk_url, $trunk_path,
						   undef, $trunk_ref);
403
		}
404
	}
405
	return unless defined $_branches || defined $_tags;
406 407 408
	my $ra = $url ? Git::SVN::Ra->new($url) : undef;
	complete_url_ls_init($ra, $_branches, '--branches/-b', $_prefix);
	complete_url_ls_init($ra, $_tags, '--tags/-t', $_prefix . 'tags/');
409 410
}

411
sub cmd_multi_fetch {
412 413
	my $remotes = Git::SVN::read_all_remotes();
	foreach my $repo_id (sort keys %$remotes) {
414
		if ($remotes->{$repo_id}->{url}) {
415 416
			Git::SVN::fetch_all($repo_id, $remotes);
		}
417 418 419
	}
}

420 421 422 423 424 425
# this command is special because it requires no metadata
sub cmd_commit_diff {
	my ($ta, $tb, $url) = @_;
	my $usage = "Usage: $0 commit-diff -r<revision> ".
	            "<tree-ish> <tree-ish> [<URL>]\n";
	fatal($usage) if (!defined $ta || !defined $tb);
426
	my $svn_path;
427 428 429 430 431 432 433
	if (!defined $url) {
		my $gs = eval { Git::SVN->new };
		if (!$gs) {
			fatal("Needed URL or usable git-svn --id in ",
			      "the command-line\n", $usage);
		}
		$url = $gs->{url};
434
		$svn_path = $gs->{path};
435 436 437 438 439 440 441 442 443 444 445 446 447 448 449
	}
	unless (defined $_revision) {
		fatal("-r|--revision is a required argument\n", $usage);
	}
	if (defined $_message && defined $_file) {
		fatal("Both --message/-m and --file/-F specified ",
		      "for the commit message.\n",
		      "I have no idea what you mean\n");
	}
	if (defined $_file) {
		$_message = file_to_s($_file);
	} else {
		$_message ||= get_commit_entry($tb)->{log};
	}
	my $ra ||= Git::SVN::Ra->new($url);
450
	$svn_path ||= $ra->{svn_path};
451 452 453 454 455 456
	my $r = $_revision;
	if ($r eq 'HEAD') {
		$r = $ra->get_latest_revnum;
	} elsif ($r !~ /^\d+$/) {
		die "revision argument: $r not understood by git-svn\n";
	}
457 458 459 460 461 462 463 464
	my %ed_opts = ( r => $r,
	                log => $_message,
	                ra => $ra,
	                tree_a => $ta,
	                tree_b => $tb,
	                editor_cb => sub { print "Committed r$_[0]\n" },
	                svn_path => $svn_path );
	if (!SVN::Git::Editor->new(\%ed_opts)->apply_diff) {
465 466 467 468
		print "No changes\n$ta == $tb\n";
	}
}

E
Eric Wong 已提交
469 470
########################### utility functions #########################

471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491
sub post_fetch_checkout {
	return if $_no_checkout;
	my $gs = $Git::SVN::_head or return;
	return if verify_ref('refs/heads/master^0');

	my $valid_head = verify_ref('HEAD^0');
	command_noisy(qw(update-ref refs/heads/master), $gs->refname);
	return if ($valid_head || !verify_ref('HEAD^0'));

	return if $ENV{GIT_DIR} !~ m#^(?:.*/)?\.git$#;
	my $index = $ENV{GIT_INDEX_FILE} || "$ENV{GIT_DIR}/index";
	return if -f $index;

	chomp(my $bare = `git config --bool --get core.bare`);
	return if $bare eq 'true';
	return if command_oneline(qw/rev-parse --is-inside-git-dir/) eq 'true';
	command_noisy(qw/read-tree -m -u -v HEAD HEAD/);
	print STDERR "Checked out HEAD:\n  ",
	             $gs->full_url, " r", $gs->last_rev, "\n";
}

492 493 494 495 496 497 498 499
sub complete_svn_url {
	my ($url, $path) = @_;
	$path =~ s#/+$##;
	if ($path !~ m#^[a-z\+]+://#) {
		if (!defined $url || $url !~ m#^[a-z\+]+://#) {
			fatal("E: '$path' is not a complete URL ",
			      "and a separate URL is not specified\n");
		}
500
		return ($url, $path);
501
	}
502
	return ($path, '');
503 504
}

505
sub complete_url_ls_init {
506 507
	my ($ra, $repo_path, $switch, $pfx) = @_;
	unless ($repo_path) {
508 509 510
		print STDERR "W: $switch not specified\n";
		return;
	}
511 512 513 514
	$repo_path =~ s#/+$##;
	if ($repo_path =~ m#^[a-z\+]+://#) {
		$ra = Git::SVN::Ra->new($repo_path);
		$repo_path = '';
515
	} else {
516
		$repo_path =~ s#^/+##;
517
		unless ($ra) {
518
			fatal("E: '$repo_path' is not a complete URL ",
519
			      "and a separate URL is not specified\n");
520
		}
521
	}
522
	my $url = $ra->{url};
523 524 525 526 527 528
	my $gs = Git::SVN->init($url, undef, undef, undef, 1);
	my $k = "svn-remote.$gs->{repo_id}.url";
	my $orig_url = eval { command_oneline(qw/config --get/, $k) };
	if ($orig_url && ($orig_url ne $gs->{url})) {
		die "$k already set: $orig_url\n",
		    "wanted to set to: $gs->{url}\n";
529
	}
530 531 532 533 534 535 536
	command_oneline('config', $k, $gs->{url}) unless $orig_url;
	my $remote_path = "$ra->{svn_path}/$repo_path/*";
	$remote_path =~ s#/+#/#g;
	$remote_path =~ s#^/##g;
	my ($n) = ($switch =~ /^--(\w+)/);
	if (length $pfx && $pfx !~ m#/$#) {
		die "--prefix='$pfx' must have a trailing slash '/'\n";
537
	}
538 539
	command_noisy('config', "svn-remote.$gs->{repo_id}.$n",
				"$remote_path:refs/remotes/$pfx*");
540 541
}

E
Eric Wong 已提交
542 543
sub verify_ref {
	my ($ref) = @_;
544 545
	eval { command_oneline([ 'rev-parse', '--verify', $ref ],
	                       { STDERR => 0 }); };
E
Eric Wong 已提交
546 547
}

548
sub get_tree_from_treeish {
549
	my ($treeish) = @_;
550
	# $treeish can be a symbolic ref, too:
E
Eric Wong 已提交
551
	my $type = command_oneline(qw/cat-file -t/, $treeish);
552 553
	my $expected;
	while ($type eq 'tag') {
E
Eric Wong 已提交
554
		($treeish, $type) = command(qw/cat-file tag/, $treeish);
555 556
	}
	if ($type eq 'commit') {
E
Eric Wong 已提交
557 558
		$expected = (grep /^tree /, command(qw/cat-file commit/,
		                                    $treeish))[0];
559
		($expected) = ($expected =~ /^tree ($sha1)$/o);
560 561 562 563 564 565
		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";
	}
566 567 568
	return $expected;
}

569 570 571 572 573 574
sub get_commit_entry {
	my ($treeish) = shift;
	my %log_entry = ( log => '', tree => get_tree_from_treeish($treeish) );
	my $commit_editmsg = "$ENV{GIT_DIR}/COMMIT_EDITMSG";
	my $commit_msg = "$ENV{GIT_DIR}/COMMIT_MSG";
	open my $log_fh, '>', $commit_editmsg or croak $!;
E
Eric Wong 已提交
575

576
	my $type = command_oneline(qw/cat-file -t/, $treeish);
577
	if ($type eq 'commit' || $type eq 'tag') {
E
Eric Wong 已提交
578
		my ($msg_fh, $ctx) = command_output_pipe('cat-file',
579
		                                         $type, $treeish);
E
Eric Wong 已提交
580 581 582 583
		my $in_msg = 0;
		while (<$msg_fh>) {
			if (!$in_msg) {
				$in_msg = 1 if (/^\s*$/);
584
			} elsif (/^git-svn-id: /) {
585 586 587
				# skip this for now, we regenerate the
				# correct one on re-fetch anyways
				# TODO: set *:merge properties or like...
E
Eric Wong 已提交
588
			} else {
589
				print $log_fh $_ or croak $!;
E
Eric Wong 已提交
590 591
			}
		}
E
Eric Wong 已提交
592
		command_close_pipe($msg_fh, $ctx);
E
Eric Wong 已提交
593
	}
594
	close $log_fh or croak $!;
E
Eric Wong 已提交
595 596 597

	if ($_edit || ($type eq 'tree')) {
		my $editor = $ENV{VISUAL} || $ENV{EDITOR} || 'vi';
598 599
		# TODO: strip out spaces, comments, like git-commit.sh
		system($editor, $commit_editmsg);
E
Eric Wong 已提交
600
	}
601 602 603 604 605 606
	rename $commit_editmsg, $commit_msg or croak $!;
	open $log_fh, '<', $commit_msg or croak $!;
	{ local $/; chomp($log_entry{log} = <$log_fh>); }
	close $log_fh or croak $!;
	unlink $commit_msg;
	\%log_entry;
607 608
}

E
Eric Wong 已提交
609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626
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;
}

627 628 629
# '<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";
630
	my $log = $cmd eq 'log';
631 632
	while (<$authors>) {
		chomp;
633
		next unless /^(\S+?|\(no author\))\s*=\s*(.+?)\s*<(.+)>\s*$/;
634
		my ($user, $name, $email) = ($1, $2, $3);
635 636 637 638 639
		if ($log) {
			$Git::SVN::Log::rusers{"$name <$email>"} = $user;
		} else {
			$users{$user} = [$name, $email];
		}
640 641 642 643
	}
	close $authors or croak $!;
}

644
# convert GetOpt::Long specs for use by git-config
645
sub read_repo_config {
646
	return unless -d $ENV{GIT_DIR};
647
	my $opts = shift;
648
	my @config_only;
649
	foreach my $o (keys %$opts) {
650 651 652 653
		# if we have mixedCase and a long option-only, then
		# it's a config-only variable that we don't need for
		# the command-line.
		push @config_only, $o if ($o =~ /[A-Z]/ && $o =~ /^[a-z]+$/i);
654
		my $v = $opts->{$o};
655
		my ($key) = ($o =~ /^([a-zA-Z\-]+)/);
656
		$key =~ s/-//g;
657
		my $arg = 'git-config';
658 659 660 661 662 663 664
		$arg .= ' --int' if ($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.$key`);
665
			if ($tmp && !($arg =~ / --bool/ && $tmp eq 'false')) {
666 667 668 669
				$$v = $tmp;
			}
		}
	}
670
	delete @$opts{@config_only} if @config_only;
671 672
}

673
sub extract_metadata {
674
	my $id = shift or return (undef, undef, undef);
675 676
	my ($url, $rev, $uuid) = ($id =~ /^git-svn-id:\s(\S+?)\@(\d+)
							\s([a-f\d\-]+)$/x);
677
	if (!defined $rev || !$uuid || !$url) {
678
		# some of the original repositories I made had
679
		# identifiers like this:
680 681 682 683 684
		($rev, $uuid) = ($id =~/^git-svn-id:\s(\d+)\@([a-f\d\-]+)/);
	}
	return ($url, $rev, $uuid);
}

685 686
sub cmt_metadata {
	return extract_metadata((grep(/^git-svn-id: /,
E
Eric Wong 已提交
687
		command(qw/cat-file commit/, shift)))[-1]);
688 689
}

690 691 692
package Git::SVN;
use strict;
use warnings;
E
Eric Wong 已提交
693
use vars qw/$default_repo_id $default_ref_id $_no_metadata $_follow_parent
694
            $_repack $_repack_flags $_use_svm_props $_head/;
695 696
use Carp qw/croak/;
use File::Path qw/mkpath/;
697
use File::Copy qw/copy/;
698 699
use IPC::Open3;

E
Eric Wong 已提交
700
my $_repack_nr;
701 702 703 704 705 706 707 708 709
# properties that we do not log:
my %SKIP_PROP;
BEGIN {
	%SKIP_PROP = map { $_ => 1 } qw/svn:wc:ra_dav:version-url
	                                svn:special svn:executable
	                                svn:entry:committed-rev
	                                svn:entry:last-author
	                                svn:entry:uuid
	                                svn:entry:committed-date/;
710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732

	# some options are read globally, but can be overridden locally
	# per [svn-remote "..."] section.  Command-line options will *NOT*
	# override options set in an [svn-remote "..."] section
	my $e;
	foreach (qw/follow_parent no_metadata use_svm_props/) {
		my $key = $_;
		$key =~ tr/_//d;
		$e .= "sub $_ {
			my (\$self) = \@_;
			return \$self->{-$_} if exists \$self->{-$_};
			my \$k = \"svn-remote.\$self->{repo_id}\.$key\";
			eval { command_oneline(qw/config --get/, \$k) };
			if (\$@) {
				\$self->{-$_} = \$Git::SVN::_$_;
			} else {
				my \$v = command_oneline(qw/config --bool/,\$k);
				\$self->{-$_} = \$v eq 'false' ? 0 : 1;
			}
			return \$self->{-$_} }\n";
	}
	$e .= "1;\n";
	eval $e or die $@;
733 734
}

735 736 737
my %LOCKFILES;
END { unlink keys %LOCKFILES if %LOCKFILES }

738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754
sub resolve_local_globs {
	my ($url, $fetch, $glob_spec) = @_;
	return unless defined $glob_spec;
	my $ref = $glob_spec->{ref};
	my $path = $glob_spec->{path};
	foreach (command(qw#for-each-ref --format=%(refname) refs/remotes#)) {
		next unless m#^refs/remotes/$ref->{regex}$#;
		my $p = $1;
		my $pathname = $path->full_path($p);
		my $refname = $ref->full_path($p);
		if (my $existing = $fetch->{$pathname}) {
			if ($existing ne $refname) {
				die "Refspec conflict:\n",
				    "existing: refs/remotes/$existing\n",
				    " globbed: refs/remotes/$refname\n";
			}
			my $u = (::cmt_metadata("refs/remotes/$refname"))[0];
755
			$u =~ s!^\Q$url\E(/|$)!! or die
756 757 758 759 760 761 762 763 764 765 766 767 768 769 770
			  "refs/remotes/$refname: '$url' not found in '$u'\n";
			if ($pathname ne $u) {
				warn "W: Refspec glob conflict ",
				     "(ref: refs/remotes/$refname):\n",
				     "expected path: $pathname\n",
				     "    real path: $u\n",
				     "Continuing ahead with $u\n";
				next;
			}
		} else {
			$fetch->{$pathname} = $refname;
		}
	}
}

771 772 773 774 775 776 777 778 779 780 781 782 783
sub parse_revision_argument {
	my ($base, $head) = @_;
	if (!defined $::_revision || $::_revision eq 'BASE:HEAD') {
		return ($base, $head);
	}
	return ($1, $2) if ($::_revision =~ /^(\d+):(\d+)$/);
	return ($::_revision, $::_revision) if ($::_revision =~ /^\d+$/);
	return ($head, $head) if ($::_revision eq 'HEAD');
	return ($base, $1) if ($::_revision =~ /^BASE:(\d+)$/);
	return ($1, $head) if ($::_revision =~ /^(\d+):HEAD$/);
	die "revision argument: $::_revision not understood by git-svn\n";
}

784
sub fetch_all {
785
	my ($repo_id, $remotes) = @_;
786 787
	my $remote = $remotes->{$repo_id} or
	             die "[svn-remote \"$repo_id\"] unknown\n";
788
	my $fetch = $remote->{fetch};
789
	my $url = $remote->{url} or die "svn-remote.$repo_id.url not defined\n";
790
	my (@gs, @globs);
791
	my $ra = Git::SVN::Ra->new($url);
792
	my $uuid = $ra->get_uuid;
793
	my $head = $ra->get_latest_revnum;
E
Eric Wong 已提交
794
	my $base = defined $fetch ? $head : 0;
795 796 797 798 799

	# read the max revs for wildcard expansion (branches/*, tags/*)
	foreach my $t (qw/branches tags/) {
		defined $remote->{$t} or next;
		push @globs, $remote->{$t};
800 801 802 803
		my $max_rev = eval { tmp_config(qw/--int --get/,
		                         "svn-remote.$repo_id.${t}-maxRev") };
		if (defined $max_rev && ($max_rev < $base)) {
			$base = $max_rev;
804 805 806
		}
	}

807 808 809 810 811 812 813 814
	if ($fetch) {
		foreach my $p (sort keys %$fetch) {
			my $gs = Git::SVN->new($fetch->{$p}, $repo_id, $p);
			my $lr = $gs->rev_db_max;
			if (defined $lr) {
				$base = $lr if ($lr < $base);
			}
			push @gs, $gs;
815 816
		}
	}
817 818

	($base, $head) = parse_revision_argument($base, $head);
819
	$ra->gs_fetch_loop_common($base, $head, \@gs, \@globs);
820 821
}

822 823
sub read_all_remotes {
	my $r = {};
824
	foreach (grep { s/^svn-remote\.// } command(qw/config -l/)) {
825 826 827 828
		if (m!^(.+)\.fetch=\s*(.*)\s*:\s*refs/remotes/(.+)\s*$!) {
			$r->{$1}->{fetch}->{$2} = $3;
		} elsif (m!^(.+)\.url=\s*(.*)\s*$!) {
			$r->{$1}->{url} = $2;
829 830 831 832
		} elsif (m!^(.+)\.(branches|tags)=
		           (.*):refs/remotes/(.+)\s*$/!x) {
			my ($p, $g) = ($3, $4);
			my $rs = $r->{$1}->{$2} = {
833
			                  t => $2,
834
					  remote => $1,
835 836 837 838 839 840
			                  path => Git::SVN::GlobSpec->new($p),
			                  ref => Git::SVN::GlobSpec->new($g) };
			if (length($rs->{ref}->{right}) != 0) {
				die "The '*' glob character must be the last ",
				    "character of '$g'\n";
			}
841 842 843 844 845
		}
	}
	$r;
}

E
Eric Wong 已提交
846 847 848 849 850 851 852 853
sub init_vars {
	if (defined $_repack) {
		$_repack = 1000 if ($_repack <= 0);
		$_repack_nr = $_repack;
		$_repack_flags ||= '-d';
	}
}

854
sub verify_remotes_sanity {
855
	return unless -d $ENV{GIT_DIR};
856 857 858 859 860 861 862 863 864 865 866 867 868 869 870
	my %seen;
	foreach (command(qw/config -l/)) {
		if (m!^svn-remote\.(?:.+)\.fetch=.*:refs/remotes/(\S+)\s*$!) {
			if ($seen{$1}) {
				die "Remote ref refs/remote/$1 is tracked by",
				    "\n  \"$_\"\nand\n  \"$seen{$1}\"\n",
				    "Please resolve this ambiguity in ",
				    "your git configuration file before ",
				    "continuing\n";
			}
			$seen{$1} = $_;
		}
	}
}

871
# we allow more chars than remotes2config.sh...
872 873
sub sanitize_remote_name {
	my ($name) = @_;
874
	$name =~ tr{A-Za-z0-9:,/+-}{.}c;
875 876 877
	$name;
}

878 879 880 881 882 883 884 885 886 887 888
sub find_existing_remote {
	my ($url, $remotes) = @_;
	my $existing;
	foreach my $repo_id (keys %$remotes) {
		my $u = $remotes->{$repo_id}->{url} or next;
		next if $u ne $url;
		$existing = $repo_id;
		last;
	}
	$existing;
}
889

890
sub init_remote_config {
891
	my ($self, $url, $no_write) = @_;
892 893 894 895
	$url =~ s!/+$!!; # strip trailing slash
	my $r = read_all_remotes();
	my $existing = find_existing_remote($url, $r);
	if ($existing) {
896 897 898 899
		unless ($no_write) {
			print STDERR "Using existing ",
				     "[svn-remote \"$existing\"]\n";
		}
900 901 902 903 904
		$self->{repo_id} = $existing;
	} else {
		my $min_url = Git::SVN::Ra->new($url)->minimize_url;
		$existing = find_existing_remote($min_url, $r);
		if ($existing) {
905 906 907 908
			unless ($no_write) {
				print STDERR "Using existing ",
					     "[svn-remote \"$existing\"]\n";
			}
909 910 911
			$self->{repo_id} = $existing;
		}
		if ($min_url ne $url) {
912 913 914 915
			unless ($no_write) {
				print STDERR "Using higher level of URL: ",
					     "$url => $min_url\n";
			}
916 917
			my $old_path = $self->{path};
			$self->{path} = $url;
918
			$self->{path} =~ s!^\Q$min_url\E(/|$)!!;
919 920 921 922 923 924 925 926
			if (length $old_path) {
				$self->{path} .= "/$old_path";
			}
			$url = $min_url;
		}
	}
	my $orig_url;
	if (!$existing) {
927
		# verify that we aren't overwriting anything:
928
		$orig_url = eval {
929
			command_oneline('config', '--get',
930
					"svn-remote.$self->{repo_id}.url")
931
		};
932
		if ($orig_url && ($orig_url ne $url)) {
933
			die "svn-remote.$self->{repo_id}.url already set: ",
934 935
			    "$orig_url\nwanted to set to: $url\n";
		}
936
	}
937 938 939 940 941
	my ($xrepo_id, $xpath) = find_ref($self->refname);
	if (defined $xpath) {
		die "svn-remote.$xrepo_id.fetch already set to track ",
		    "$xpath:refs/remotes/", $self->refname, "\n";
	}
942 943 944 945 946 947 948
	unless ($no_write) {
		command_noisy('config',
			      "svn-remote.$self->{repo_id}.url", $url);
		command_noisy('config', '--add',
			      "svn-remote.$self->{repo_id}.fetch",
			      "$self->{path}:".$self->refname);
	}
949
	$self->{url} = $url;
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
sub find_by_url { # repos_root and, path are optional
	my ($class, $full_url, $repos_root, $path) = @_;
	my $remotes = read_all_remotes();
	if (defined $full_url && defined $repos_root && !defined $path) {
		$path = $full_url;
		$path =~ s#^\Q$repos_root\E(?:/|$)##;
	}
	foreach my $repo_id (keys %$remotes) {
		my $u = $remotes->{$repo_id}->{url} or next;
		next if defined $repos_root && $repos_root ne $u;

		my $fetch = $remotes->{$repo_id}->{fetch} || {};
		foreach (qw/branches tags/) {
			resolve_local_globs($u, $fetch,
			                    $remotes->{$repo_id}->{$_});
		}
		my $p = $path;
		unless (defined $p) {
			$p = $full_url;
			$p =~ s#^\Q$u\E(?:/|$)## or next;
		}
		foreach my $f (keys %$fetch) {
			next if $f ne $p;
			return Git::SVN->new($fetch->{$f}, $repo_id, $f);
		}
	}
	undef;
}

981
sub init {
982
	my ($class, $url, $path, $repo_id, $ref_id, $no_write) = @_;
983 984
	my $self = _new($class, $repo_id, $ref_id, $path);
	if (defined $url) {
985
		$self->init_remote_config($url, $no_write);
986
	}
987 988 989
	$self;
}

990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003
sub find_ref {
	my ($ref_id) = @_;
	foreach (command(qw/config -l/)) {
		next unless m!^svn-remote\.(.+)\.fetch=
		              \s*(.*)\s*:\s*refs/remotes/(.+)\s*$!x;
		my ($repo_id, $path, $ref) = ($1, $2, $3);
		if ($ref eq $ref_id) {
			$path = '' if ($path =~ m#^\./?#);
			return ($repo_id, $path);
		}
	}
	(undef, undef, undef);
}

1004
sub new {
1005 1006 1007 1008 1009 1010 1011 1012 1013 1014
	my ($class, $ref_id, $repo_id, $path) = @_;
	if (defined $ref_id && !defined $repo_id && !defined $path) {
		($repo_id, $path) = find_ref($ref_id);
		if (!defined $repo_id) {
			die "Could not find a \"svn-remote.*.fetch\" key ",
			    "in the repository configuration matching: ",
			    "refs/remotes/$ref_id\n";
		}
	}
	my $self = _new($class, $repo_id, $ref_id, $path);
1015 1016 1017 1018 1019 1020 1021 1022
	if (!defined $self->{path} || !length $self->{path}) {
		my $fetch = command_oneline('config', '--get',
		                            "svn-remote.$repo_id.fetch",
		                            ":refs/remotes/$ref_id\$") or
		     die "Failed to read \"svn-remote.$repo_id.fetch\" ",
		         "\":refs/remotes/$ref_id\$\" in config\n";
		($self->{path}, undef) = split(/\s*:\s*/, $fetch);
	}
1023 1024 1025
	$self->{url} = command_oneline('config', '--get',
	                               "svn-remote.$repo_id.url") or
                  die "Failed to read \"svn-remote.$repo_id.url\" in config\n";
1026 1027
	if ((-z $self->db_path || ! -e $self->db_path) &&
	    ::verify_ref($self->refname.'^0')) {
1028 1029
		$self->rebuild;
	}
1030 1031 1032
	$self;
}

1033
sub refname { "refs/remotes/$_[0]->{ref_id}" }
1034

1035 1036 1037 1038 1039 1040 1041 1042 1043
sub svm_uuid {
	my ($self) = @_;
	return $self->{svm}->{uuid} if $self->svm;
	$self->ra;
	unless ($self->{svm}) {
		die "SVM UUID not cached, and reading remotely failed\n";
	}
	$self->{svm}->{uuid};
}
1044

1045 1046 1047 1048
sub svm {
	my ($self) = @_;
	return $self->{svm} if $self->{svm};
	my $svm;
1049 1050
	# see if we have it in our config, first:
	eval {
1051 1052
		my $section = "svn-remote.$self->{repo_id}";
		$svm = {
1053 1054
		  source => tmp_config('--get', "$section.svm-source"),
		  uuid => tmp_config('--get', "$section.svm-uuid"),
1055 1056
		}
	};
1057 1058 1059 1060 1061 1062
	$self->{svm} = $svm if ($svm && $svm->{source} && $svm->{uuid});
	$self->{svm};
}

sub _set_svm_vars {
	my ($self, $ra) = @_;
1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073
	return $ra if $self->svm;

	my @err = ( "useSvmProps set, but failed to read SVM properties\n",
		    "(svm:source, svm:mirror, svm:mirror) ",
		    "from the following URLs:\n" );
	sub read_svm_props {
		my ($self, $props) = @_;
		my $src = $props->{'svm:source'};
		my $mirror = $props->{'svm:mirror'};
		my $uuid = $props->{'svm:uuid'};
		return undef if (!$src || !$mirror || !$uuid);
1074

1075
		chomp($src, $mirror, $uuid);
1076

1077 1078
		$uuid =~ m{^[0-9a-f\-]{30,}$}
		    or die "doesn't look right - svm:uuid is '$uuid'\n";
1079 1080
		# don't know what a '!' is there for, also the
		# username is of no interest
1081 1082
		$src =~ s{/?!$}{$mirror};
		$src =~ s{/+$}{}; # no trailing slashes please
1083 1084
		$src =~ s{(^[a-z\+]*://)[^/@]*@}{$1};

1085 1086
		my $section = "svn-remote.$self->{repo_id}";
		tmp_config('--add', "$section.svm-source", $src);
1087
		tmp_config('--add', "$section.svm-uuid", $uuid);
1088
		$self->{svm} = { source => $src , uuid => $uuid };
1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099
		return 1;
	}

	my $r = $ra->get_latest_revnum;
	my $path = $self->{path};
	my @tried_a = ($path);
	while (length $path) {
		if ($self->read_svm_props(($ra->get_dir($path, $r))[2])) {
			return $ra;
		}
		$path =~ s#/?[^/]+$## && push @tried_a, $path;
1100
	}
1101 1102
	if ($self->read_svm_props(($ra->get_dir('', $r))[2])) {
		return $ra;
1103
	}
1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125

	if ($ra->{repos_root} eq $self->{url}) {
		die @err, map { "  $self->{url}/$_\n" } @tried_a, "\n";
	}

	# nope, make sure we're connected to the repository root:
	my $ok;
	my @tried_b;
	$path = $ra->{svn_path};
	$path =~ s#/?[^/]+$##; # we already tried this one above
	$ra = Git::SVN::Ra->new($ra->{repos_root});
	while (length $path) {
		$ok = $self->read_svm_props(($ra->get_dir($path, $r))[2]);
		last if $ok;
		$path =~ s#/?[^/]+$## && push @tried_b, $path;
	}
	$ok = $self->read_svm_props(($ra->get_dir('', $r))[2]) unless $ok;
	if (!$ok) {
		die @err, map { "  $self->{url}/$_\n" } @tried_a, "\n",
		          map { "  $ra->{url}/$_\n" } @tried_b, "\n"
	}
	Git::SVN::Ra->new($self->{url});
1126 1127
}

1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145
# this allows us to memoize our SVN::Ra UUID locally and avoid a
# remote lookup (useful for 'git svn log').
sub ra_uuid {
	my ($self) = @_;
	unless ($self->{ra_uuid}) {
		my $key = "svn-remote.$self->{repo_id}.uuid";
		my $uuid = eval { tmp_config('--get', $key) };
		if (!$@ && $uuid && $uuid =~ /^([a-f\d\-]{30,})$/) {
			$self->{ra_uuid} = $uuid;
		} else {
			die "ra_uuid called without URL\n" unless $self->{url};
			$self->{ra_uuid} = $self->ra->get_uuid;
			tmp_config('--add', $key, $self->{ra_uuid});
		}
	}
	$self->{ra_uuid};
}

1146 1147
sub ra {
	my ($self) = shift;
1148
	my $ra = Git::SVN::Ra->new($self->{url});
1149 1150
	if ($self->use_svm_props && !$self->{svm}) {
		if ($self->no_metadata) {
1151 1152
			die "Can't have both 'noMetadata' and ",
			    "'useSvmProps' options set!\n";
1153
		}
1154
		$ra = $self->_set_svm_vars($ra);
1155 1156 1157
		$self->{-want_revprops} = 1;
	}
	$ra;
1158 1159
}

1160 1161 1162 1163
sub rel_path {
	my ($self) = @_;
	my $repos_root = $self->ra->{repos_root};
	return $self->{path} if ($self->{url} eq $repos_root);
1164 1165
	die "BUG: rel_path failed! repos_root: $repos_root, Ra URL: ",
	    $self->ra->{url}, " path: $self->{path},  URL: $self->{url}\n";
1166 1167
}

1168 1169 1170
sub traverse_ignore {
	my ($self, $fh, $path, $r) = @_;
	$path =~ s#^/+##g;
1171 1172
	my $ra = $self->ra;
	my ($dirent, undef, $props) = $ra->get_dir($path, $r);
1173
	my $p = $path;
1174
	$p =~ s#^\Q$ra->{svn_path}\E/##;
1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192
	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;
		$self->traverse_ignore($fh, "$path/$_", $r);
	}
}

1193 1194 1195
sub last_rev { ($_[0]->last_rev_commit)[0] }
sub last_commit { ($_[0]->last_rev_commit)[1] }

1196 1197 1198 1199 1200 1201
# returns the newest SVN revision number and newest commit SHA1
sub last_rev_commit {
	my ($self) = @_;
	if (defined $self->{last_rev} && defined $self->{last_commit}) {
		return ($self->{last_rev}, $self->{last_commit});
	}
1202
	my $c = ::verify_ref($self->refname.'^0');
1203
	if ($c && !$self->use_svm_props && !$self->no_metadata) {
1204
		my $rev = (::cmt_metadata($c))[1];
1205 1206 1207 1208 1209
		if (defined $rev) {
			($self->{last_rev}, $self->{last_commit}) = ($rev, $c);
			return ($rev, $c);
		}
	}
1210 1211 1212 1213 1214
	my $db_path = $self->db_path;
	unless (-e $db_path) {
		($self->{last_rev}, $self->{last_commit}) = (undef, undef);
		return (undef, undef);
	}
1215 1216
	my $offset = -41; # from tail
	my $rl;
1217
	open my $fh, '<', $db_path or croak "$db_path not readable: $!\n";
1218 1219
	sysseek($fh, $offset, 2); # don't care for errors
	sysread($fh, $rl, 41) == 41 or return (undef, undef);
1220
	chomp $rl;
1221
	while (('0' x40) eq $rl && sysseek($fh, 0, 1) != 0) {
1222
		$offset -= 41;
1223 1224
		sysseek($fh, $offset, 2); # don't care for errors
		sysread($fh, $rl, 41) == 41 or return (undef, undef);
1225 1226
		chomp $rl;
	}
1227
	if ($c && $c ne $rl) {
1228
		die "$db_path and ", $self->refname,
1229 1230
		    " inconsistent!:\n$c != $rl\n";
	}
1231
	my $rev = sysseek($fh, 0, 1) or croak $!;
1232 1233 1234 1235 1236 1237
	$rev =  ($rev - 41) / 41;
	close $fh or croak $!;
	($self->{last_rev}, $self->{last_commit}) = ($rev, $c);
	return ($rev, $c);
}

1238 1239 1240
sub get_fetch_range {
	my ($self, $min, $max) = @_;
	$max ||= $self->ra->get_latest_revnum;
1241
	$min ||= $self->rev_db_max;
1242
	(++$min, $max);
1243 1244
}

1245
sub tmp_config {
1246 1247
	my (@args) = @_;
	my $config = "$ENV{GIT_DIR}/svn/config";
1248
	my $old_config = $ENV{GIT_CONFIG};
1249
	$ENV{GIT_CONFIG} = $config;
1250
	$@ = undef;
1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264
	my @ret = eval {
		unless (-f $config) {
			mkfile($config);
			open my $fh, '>', $config or
			    die "Can't open $config: $!\n";
			print $fh "; This file is used internally by ",
			          "git-svn\n" or die
				  "Couldn't write to $config: $!\n";
			print $fh "; You should not have to edit it\n" or
			      die "Couldn't write to $config: $!\n";
			close $fh or die "Couldn't close $config: $!\n";
		}
		command('config', @args);
	};
1265 1266 1267 1268 1269 1270 1271 1272 1273 1274
	my $err = $@;
	if (defined $old_config) {
		$ENV{GIT_CONFIG} = $old_config;
	} else {
		delete $ENV{GIT_CONFIG};
	}
	die $err if $err;
	wantarray ? @ret : $ret[0];
}

1275 1276 1277 1278
sub tmp_index_do {
	my ($self, $sub) = @_;
	my $old_index = $ENV{GIT_INDEX_FILE};
	$ENV{GIT_INDEX_FILE} = $self->{index};
1279
	$@ = undef;
1280 1281 1282 1283 1284
	my @ret = eval {
		my ($dir, $base) = ($self->{index} =~ m#^(.*?)/?([^/]+)$#);
		mkpath([$dir]) unless -d $dir;
		&$sub;
	};
1285 1286
	my $err = $@;
	if (defined $old_index) {
1287 1288 1289 1290
		$ENV{GIT_INDEX_FILE} = $old_index;
	} else {
		delete $ENV{GIT_INDEX_FILE};
	}
1291
	die $err if $err;
1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302
	wantarray ? @ret : $ret[0];
}

sub assert_index_clean {
	my ($self, $treeish) = @_;

	$self->tmp_index_do(sub {
		command_noisy('read-tree', $treeish) unless -e $self->{index};
		my $x = command_oneline('write-tree');
		my ($y) = (command(qw/cat-file commit/, $treeish) =~
		           /^tree ($::sha1)/mo);
1303 1304 1305 1306 1307
		return if $y eq $x;

		warn "Index mismatch: $y != $x\nrereading $treeish\n";
		unlink $self->{index} or die "unlink $self->{index}: $!\n";
		command_noisy('read-tree', $treeish);
1308 1309 1310 1311 1312 1313 1314 1315 1316
		$x = command_oneline('write-tree');
		if ($y ne $x) {
			::fatal "trees ($treeish) $y != $x\n",
			        "Something is seriously wrong...\n";
		}
	});
}

sub get_commit_parents {
1317
	my ($self, $log_entry) = @_;
1318
	my (%seen, @ret, @tmp);
1319 1320 1321 1322
	# legacy support for 'set-tree'; this is only used by set_tree_cb:
	if (my $ip = $self->{inject_parents}) {
		if (my $commit = delete $ip->{$log_entry->{revision}}) {
			push @tmp, $commit;
1323 1324
		}
	}
1325
	if (my $cur = ::verify_ref($self->refname.'^0')) {
1326 1327
		push @tmp, $cur;
	}
1328
	push @tmp, $_ foreach (@{$log_entry->{parents}}, @tmp);
1329 1330 1331 1332 1333 1334 1335 1336
	while (my $p = shift @tmp) {
		next if $seen{$p};
		$seen{$p} = 1;
		push @ret, $p;
		# MAXPARENT is defined to 16 in commit-tree.c:
		last if @ret >= 16;
	}
	if (@tmp) {
1337
		die "r$log_entry->{revision}: No room for parents:\n\t",
1338 1339 1340 1341 1342
		    join("\n\t", @tmp), "\n";
	}
	@ret;
}

1343
sub full_url {
1344
	my ($self) = @_;
1345
	$self->{url} . (length $self->{path} ? '/' . $self->{path} : '');
1346 1347 1348
}

sub do_git_commit {
1349
	my ($self, $log_entry) = @_;
1350 1351 1352 1353 1354 1355
	my $lr = $self->last_rev;
	if (defined $lr && $lr >= $log_entry->{revision}) {
		die "Last fetched revision of ", $self->refname,
		    " was r$lr, but we are about to fetch: ",
		    "r$log_entry->{revision}!\n";
	}
1356 1357
	if (my $c = $self->rev_db_get($log_entry->{revision})) {
		croak "$log_entry->{revision} = $c already exists! ",
1358 1359
		      "Why are we refetching it?\n";
	}
1360 1361 1362
	$ENV{GIT_AUTHOR_NAME} = $ENV{GIT_COMMITTER_NAME} = $log_entry->{name};
	$ENV{GIT_AUTHOR_EMAIL} = $ENV{GIT_COMMITTER_EMAIL} =
	                                                  $log_entry->{email};
1363
	$ENV{GIT_AUTHOR_DATE} = $ENV{GIT_COMMITTER_DATE} = $log_entry->{date};
1364

1365
	my $tree = $log_entry->{tree};
1366 1367 1368 1369 1370 1371 1372
	if (!defined $tree) {
		$tree = $self->tmp_index_do(sub {
		                            command_oneline('write-tree') });
	}
	die "Tree is not a valid sha1: $tree\n" if $tree !~ /^$::sha1$/o;

	my @exec = ('git-commit-tree', $tree);
1373
	foreach ($self->get_commit_parents($log_entry)) {
1374 1375 1376 1377
		push @exec, '-p', $_;
	}
	defined(my $pid = open3(my $msg_fh, my $out_fh, '>&STDERR', @exec))
	                                                           or croak $!;
1378
	print $msg_fh $log_entry->{log} or croak $!;
1379
	unless ($self->no_metadata) {
1380 1381
		print $msg_fh "\ngit-svn-id: $log_entry->{metadata}\n"
		              or croak $!;
1382
	}
1383 1384 1385 1386 1387 1388 1389 1390 1391 1392
	$msg_fh->flush == 0 or croak $!;
	close $msg_fh or croak $!;
	chomp(my $commit = do { local $/; <$out_fh> });
	close $out_fh or croak $!;
	waitpid $pid, 0;
	croak $? if $?;
	if ($commit !~ /^$::sha1$/o) {
		die "Failed to commit, invalid sha1: $commit\n";
	}

1393
	$self->rev_db_set($log_entry->{revision}, $commit, 1);
1394

1395
	$self->{last_rev} = $log_entry->{revision};
1396
	$self->{last_commit} = $commit;
1397 1398 1399
	print "r$log_entry->{revision}";
	if (defined $log_entry->{svm_revision}) {
		 print " (\@$log_entry->{svm_revision})";
1400 1401
		 $self->rev_db_set($log_entry->{svm_revision}, $commit,
		                   0, $self->svm_uuid);
1402 1403
	}
	print " = $commit ($self->{ref_id})\n";
E
Eric Wong 已提交
1404 1405 1406 1407 1408 1409 1410
	if (defined $_repack && (--$_repack_nr == 0)) {
		$_repack_nr = $_repack;
		# repack doesn't use any arguments with spaces in them, does it?
		print "Running git repack $_repack_flags ...\n";
		command_noisy('repack', split(/\s+/, $_repack_flags));
		print "Done repacking\n";
	}
1411 1412 1413
	return $commit;
}

1414 1415
sub match_paths {
	my ($self, $paths, $r) = @_;
1416
	return 1 if $self->{path} eq '';
1417 1418 1419
	if (my $path = $paths->{"/$self->{path}"}) {
		return ($path->{action} eq 'D') ? 0 : 1;
	}
1420
	$self->{path_regex} ||= qr/^\/\Q$self->{path}\E\//;
1421 1422 1423 1424 1425 1426
	if (grep /$self->{path_regex}/, keys %$paths) {
		return 1;
	}
	my $c = '';
	foreach (split m#/#, $self->{path}) {
		$c .= "/$_";
1427 1428
		next unless ($paths->{$c} &&
		             ($paths->{$c}->{action} =~ /^[AR]$/));
1429 1430
		if ($self->ra->check_path($self->{path}, $r) ==
		    $SVN::Node::dir) {
1431 1432 1433 1434 1435 1436
			return 1;
		}
	}
	return 0;
}

1437 1438
sub find_parent_branch {
	my ($self, $paths, $rev) = @_;
1439
	return undef unless $self->follow_parent;
1440
	unless (defined $paths) {
1441 1442
		my $err_handler = $SVN::Error::handler;
		$SVN::Error::handler = \&Git::SVN::Ra::skip_unknown_revs;
1443 1444 1445
		$self->ra->get_log([$self->{path}], $rev, $rev, 0, 1, 1, sub {
		                   $paths =
				      Git::SVN::Ra::dup_changed_paths($_[0]) });
1446
		$SVN::Error::handler = $err_handler;
1447 1448
	}
	return undef unless defined $paths;
1449 1450

	# look for a parent from another branch:
1451 1452 1453 1454 1455
	my @b_path_components = split m#/#, $self->rel_path;
	my @a_path_components;
	my $i;
	while (@b_path_components) {
		$i = $paths->{'/'.join('/', @b_path_components)};
1456
		last if $i && defined $i->{copyfrom_path};
1457 1458
		unshift(@a_path_components, pop(@b_path_components));
	}
1459 1460
	return undef unless defined $i && defined $i->{copyfrom_path};
	my $branch_from = $i->{copyfrom_path};
1461 1462 1463 1464 1465
	if (@a_path_components) {
		print STDERR "branch_from: $branch_from => ";
		$branch_from .= '/'.join('/', @a_path_components);
		print STDERR $branch_from, "\n";
	}
1466
	my $r = $i->{copyfrom_rev};
1467 1468 1469 1470 1471 1472
	my $repos_root = $self->ra->{repos_root};
	my $url = $self->ra->{url};
	my $new_url = $repos_root . $branch_from;
	print STDERR  "Found possible branch point: ",
	              "$new_url => ", $self->full_url, ", $r\n";
	$branch_from =~ s#^/##;
1473
	my $gs = Git::SVN->find_by_url($new_url, $repos_root, $branch_from);
1474
	unless ($gs) {
1475 1476 1477
		my $ref_id = $self->{ref_id};
		$ref_id =~ s/\@\d+$//;
		$ref_id .= "\@$r";
1478 1479
		# just grow a tail if we're not unique enough :x
		$ref_id .= '-' while find_ref($ref_id);
1480
		print STDERR "Initializing parent: $ref_id\n";
1481
		$gs = Git::SVN->init($new_url, '', $ref_id, $ref_id, 1);
1482 1483
	}
	my ($r0, $parent) = $gs->find_rev_before($r, 1);
1484
	if (!defined $r0 || !defined $parent) {
1485
		$gs->fetch(0, $r);
1486 1487
		($r0, $parent) = $gs->last_rev_commit;
	}
1488
	if (defined $r0 && defined $parent) {
1489
		print STDERR "Found branch parent: ($self->{ref_id}) $parent\n";
1490
		$self->assert_index_clean($parent);
1491 1492
		my $ed;
		if ($self->ra->can_do_switch) {
1493
			print STDERR "Following parent with do_switch\n";
1494
			# do_switch works with svn/trunk >= r22312, but that
1495
			# is not included with SVN 1.4.3 (the latest version
1496 1497 1498
			# at the moment), so we can't rely on it
			$self->{last_commit} = $parent;
			$ed = SVN::Git::Fetcher->new($self);
1499
			$gs->ra->gs_do_switch($r0, $rev, $gs,
1500 1501 1502
					      $self->full_url, $ed)
			  or die "SVN connection failed somewhere...\n";
		} else {
1503
			print STDERR "Following parent with do_update\n";
1504
			$ed = SVN::Git::Fetcher->new($self);
1505
			$self->ra->gs_do_update($rev, $rev, $self, $ed)
1506 1507
			  or die "SVN connection failed somewhere...\n";
		}
1508
		print STDERR "Successfully followed parent\n";
1509 1510 1511 1512 1513
		return $self->make_log_entry($rev, [$parent], $ed);
	}
	return undef;
}

1514
sub do_fetch {
1515
	my ($self, $paths, $rev) = @_;
1516
	my $ed;
1517
	my ($last_rev, @parents);
1518 1519 1520 1521 1522 1523 1524 1525 1526
	if (my $lc = $self->last_commit) {
		# we can have a branch that was deleted, then re-added
		# under the same name but copied from another path, in
		# which case we'll have multiple parents (we don't
		# want to break the original ref, nor lose copypath info):
		if (my $log_entry = $self->find_parent_branch($paths, $rev)) {
			push @{$log_entry->{parents}}, $lc;
			return $log_entry;
		}
1527
		$ed = SVN::Git::Fetcher->new($self);
1528
		$last_rev = $self->{last_rev};
1529 1530
		$ed->{c} = $lc;
		@parents = ($lc);
1531 1532
	} else {
		$last_rev = $rev;
1533 1534 1535 1536
		if (my $log_entry = $self->find_parent_branch($paths, $rev)) {
			return $log_entry;
		}
		$ed = SVN::Git::Fetcher->new($self);
1537
	}
1538
	unless ($self->ra->gs_do_update($last_rev, $rev, $self, $ed)) {
1539 1540 1541 1542 1543
		die "SVN connection failed somewhere...\n";
	}
	$self->make_log_entry($rev, \@parents, $ed);
}

1544 1545 1546 1547
sub get_untracked {
	my ($self, $ed) = @_;
	my @out;
	my $h = $ed->{empty};
1548 1549
	foreach (sort keys %$h) {
		my $act = $h->{$_} ? '+empty_dir' : '-empty_dir';
1550
		push @out, "  $act: " . uri_encode($_);
1551 1552 1553
		warn "W: $act: $_\n";
	}
	foreach my $t (qw/dir_prop file_prop/) {
1554
		$h = $ed->{$t} or next;
1555 1556 1557
		foreach my $path (sort keys %$h) {
			my $ppath = $path eq '' ? '.' : $path;
			foreach my $prop (sort keys %{$h->{$path}}) {
1558
				next if $SKIP_PROP{$prop};
1559
				my $v = $h->{$path}->{$prop};
1560 1561 1562
				my $t_ppath_prop = "$t: " .
				                    uri_encode($ppath) . ' ' .
				                    uri_encode($prop);
1563
				if (defined $v) {
1564 1565
					push @out, "  +$t_ppath_prop " .
					           uri_encode($v);
1566
				} else {
1567
					push @out, "  -$t_ppath_prop";
1568 1569 1570 1571 1572
				}
			}
		}
	}
	foreach my $t (qw/absent_file absent_directory/) {
1573
		$h = $ed->{$t} or next;
1574 1575
		foreach my $parent (sort keys %$h) {
			foreach my $path (sort @{$h->{$parent}}) {
1576 1577
				push @out, "  $t: " .
				           uri_encode("$parent/$path");
1578 1579 1580 1581 1582
				warn "W: $t: $parent/$path ",
				     "Insufficient permissions?\n";
			}
		}
	}
1583
	\@out;
1584 1585
}

1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604
sub parse_svn_date {
	my $date = shift || return '+0000 1970-01-01 00:00:00';
	my ($Y,$m,$d,$H,$M,$S) = ($date =~ /^(\d{4})\-(\d\d)\-(\d\d)T
	                                    (\d\d)\:(\d\d)\:(\d\d).\d+Z$/x) or
	                                 croak "Unable to parse date: $date\n";
	"+0000 $Y-$m-$d $H:$M:$S";
}

sub check_author {
	my ($author) = @_;
	if (!defined $author || length $author == 0) {
		$author = '(no author)';
	}
	if (defined $::_authors && ! defined $::users{$author}) {
		die "Author: $author not defined in $::_authors file\n";
	}
	$author;
}

1605
sub make_log_entry {
1606 1607 1608
	my ($self, $rev, $parents, $ed) = @_;
	my $untracked = $self->get_untracked($ed);

1609
	open my $un, '>>', "$self->{dir}/unhandled.log" or croak $!;
1610 1611 1612 1613
	print $un "r$rev\n" or croak $!;
	print $un $_, "\n" foreach @$untracked;
	my %log_entry = ( parents => $parents || [], revision => $rev,
	                  log => '');
1614

1615
	my $headrev;
1616
	my $logged = delete $self->{logged_rev_props};
1617
	if (!$logged || $self->{-want_revprops}) {
1618 1619 1620 1621 1622
		my $rp = $self->ra->rev_proplist($rev);
		foreach (sort keys %$rp) {
			my $v = $rp->{$_};
			if (/^svn:(author|date|log)$/) {
				$log_entry{$1} = $v;
1623 1624
			} elsif ($_ eq 'svm:headrev') {
				$headrev = $v;
1625 1626 1627 1628
			} else {
				print $un "  rev_prop: ", uri_encode($_), ' ',
					  uri_encode($v), "\n";
			}
1629
		}
1630 1631
	} else {
		map { $log_entry{$_} = $logged->{$_} } keys %$logged;
1632 1633
	}
	close $un or croak $!;
1634

1635 1636
	$log_entry{date} = parse_svn_date($log_entry{date});
	$log_entry{log} .= "\n";
1637 1638 1639
	my $author = $log_entry{author} = check_author($log_entry{author});
	my ($name, $email) = defined $::users{$author} ? @{$::users{$author}}
	                                               : ($author, undef);
1640
	if (defined $headrev && $self->use_svm_props) {
1641 1642 1643 1644 1645 1646 1647 1648 1649 1650
		my ($uuid, $r) = $headrev =~ m{^([a-f\d\-]{30,}):(\d+)$};
		if ($uuid ne $self->{svm}->{uuid}) {
			die "UUID mismatch on SVM path:\n",
			    "expected: $self->{svm}->{uuid}\n",
			    "     got: $uuid\n";
		}
		my $full_url = $self->{svm}->{source};
		$full_url .= "/$self->{path}" if length $self->{path};
		$log_entry{metadata} = "$full_url\@$r $uuid";
		$log_entry{svm_revision} = $r;
1651
		$email ||= "$author\@$uuid"
1652 1653
	} else {
		$log_entry{metadata} = $self->full_url . "\@$rev " .
1654
		                       $self->ra->get_uuid;
1655
		$email ||= "$author\@" . $self->ra->get_uuid;
1656
	}
1657 1658
	$log_entry{name} = $name;
	$log_entry{email} = $email;
1659 1660 1661 1662
	\%log_entry;
}

sub fetch {
1663
	my ($self, $min_rev, $max_rev, @parents) = @_;
1664
	my ($last_rev, $last_commit) = $self->last_rev_commit;
1665
	my ($base, $head) = $self->get_fetch_range($min_rev, $max_rev);
1666
	$self->ra->gs_fetch_loop_common($base, $head, [$self]);
1667 1668 1669 1670
}

sub set_tree_cb {
	my ($self, $log_entry, $tree, $rev, $date, $author) = @_;
1671 1672
	$self->{inject_parents} = { $rev => $tree };
	$self->fetch(undef, undef);
1673 1674 1675 1676
}

sub set_tree {
	my ($self, $tree) = (shift, shift);
1677
	my $log_entry = ::get_commit_entry($tree);
1678 1679 1680
	unless ($self->{last_rev}) {
		fatal("Must have an existing revision to commit\n");
	}
1681 1682 1683 1684 1685 1686 1687 1688 1689
	my %ed_opts = ( r => $self->{last_rev},
	                log => $log_entry->{log},
	                ra => $self->ra,
	                tree_a => $self->{last_commit},
	                tree_b => $tree,
	                editor_cb => sub {
			       $self->set_tree_cb($log_entry, $tree, @_) },
	                svn_path => $self->{path} );
	if (!SVN::Git::Editor->new(\%ed_opts)->apply_diff) {
1690 1691 1692 1693
		print "No changes\nr$self->{last_rev} = $tree\n";
	}
}

1694 1695
sub rebuild {
	my ($self) = @_;
1696 1697 1698 1699 1700 1701 1702 1703 1704 1705
	my $db_path = $self->db_path;
	if (-f $self->{db_root}) {
		rename $self->{db_root}, $db_path or die
		     "rename $self->{db_root} => $db_path failed: $!\n";
		my ($dir, $base) = ($db_path =~ m#^(.*?)/?([^/]+)$#);
		symlink $base, $self->{db_root} or die
		     "symlink $base => $self->{db_root} failed: $!\n";
		return;
	}
	print "Rebuilding $db_path ...\n";
1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731
	my ($rev_list, $ctx) = command_output_pipe("rev-list", $self->refname);
	my $latest;
	my $full_url = $self->full_url;
	my $svn_uuid;
	while (<$rev_list>) {
		chomp;
		my $c = $_;
		die "Non-SHA1: $c\n" unless $c =~ /^$::sha1$/o;
		my ($url, $rev, $uuid) = ::cmt_metadata($c);

		# ignore merges (from set-tree)
		next if (!defined $rev || !$uuid);

		# if we merged or otherwise started elsewhere, this is
		# how we break out of it
		if ((defined $svn_uuid && ($uuid ne $svn_uuid)) ||
		    ($full_url && $url && ($url ne $full_url))) {
			next;
		}
		$latest ||= $rev;
		$svn_uuid ||= $uuid;

		$self->rev_db_set($rev, $c);
		print "r$rev = $c\n";
	}
	command_close_pipe($rev_list, $ctx);
1732
	print "Done rebuilding $db_path\n";
1733 1734
}

1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745
# rev_db:
# 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).
1746
# These files are disposable unless noMetadata or useSvmProps is set
1747

1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772
sub _rev_db_set {
	my ($fh, $rev, $commit) = @_;
	my $offset = $rev * 41;
	# assume that append is the common case:
	seek $fh, 0, 2 or croak $!;
	my $pos = tell $fh;
	if ($pos < $offset) {
		for (1 .. (($offset - $pos) / 41)) {
			print $fh (('0' x 40),"\n") or croak $!;
		}
	}
	seek $fh, $offset, 0 or croak $!;
	print $fh $commit,"\n" or croak $!;
}

sub mkfile {
	my ($path) = @_;
	unless (-e $path) {
		my ($dir, $base) = ($path =~ m#^(.*?)/?([^/]+)$#);
		mkpath([$dir]) unless -d $dir;
		open my $fh, '>>', $path or die "Couldn't create $path: $!\n";
		close $fh or die "Couldn't close (create) $path: $!\n";
	}
}

1773
sub rev_db_set {
1774 1775 1776 1777
	my ($self, $rev, $commit, $update_ref, $uuid) = @_;
	length $commit == 40 or die "arg3 must be a full SHA1 hexsum\n";
	my $db = $self->db_path($uuid);
	my $db_lock = "$db.lock";
1778 1779 1780 1781 1782
	my $sig;
	if ($update_ref) {
		$SIG{INT} = $SIG{HUP} = $SIG{TERM} = $SIG{ALRM} = $SIG{PIPE} =
		            $SIG{USR1} = $SIG{USR2} = sub { $sig = $_[0] };
	}
1783 1784
	mkfile($db);

1785
	$LOCKFILES{$db_lock} = 1;
1786 1787 1788 1789 1790
	my $sync;
	# both of these options make our .rev_db file very, very important
	# and we can't afford to lose it because rebuild() won't work
	if ($self->use_svm_props || $self->no_metadata) {
		$sync = 1;
1791
		copy($db, $db_lock) or die "rev_db_set(@_): ",
1792
					   "Failed to copy: ",
1793 1794 1795
					   "$db => $db_lock ($!)\n";
	} else {
		rename $db, $db_lock or die "rev_db_set(@_): ",
1796
					    "Failed to rename: ",
1797 1798
					    "$db => $db_lock ($!)\n";
	}
1799 1800
	open my $fh, '+<', $db_lock or die "Couldn't open $db_lock: $!\n";
	_rev_db_set($fh, $rev, $commit);
1801 1802 1803 1804
	if ($sync) {
		$fh->flush or die "Couldn't flush $db_lock: $!\n";
		$fh->sync or die "Couldn't sync $db_lock: $!\n";
	}
1805
	close $fh or croak $!;
1806
	if ($update_ref) {
1807
		$_head = $self;
1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818
		command_noisy('update-ref', '-m', "r$rev",
		              $self->refname, $commit);
	}
	rename $db_lock, $db or die "rev_db_set(@_): ", "Failed to rename: ",
	                            "$db_lock => $db ($!)\n";
	delete $LOCKFILES{$db_lock};
	if ($update_ref) {
		$SIG{INT} = $SIG{HUP} = $SIG{TERM} = $SIG{ALRM} = $SIG{PIPE} =
		            $SIG{USR1} = $SIG{USR2} = 'DEFAULT';
		kill $sig, $$ if defined $sig;
	}
1819 1820
}

1821 1822
sub rev_db_max {
	my ($self) = @_;
1823 1824 1825
	my $db_path = $self->db_path;
	my @stat = stat $db_path or return 0;
	($stat[7] % 41) == 0 or die "$db_path inconsistent size: $stat[7]\n";
1826 1827 1828 1829
	my $max = $stat[7] / 41;
	(($max > 0) ? $max - 1 : 0);
}

1830
sub rev_db_get {
1831
	my ($self, $rev, $uuid) = @_;
1832 1833
	my $ret;
	my $offset = $rev * 41;
1834 1835 1836
	my $db_path = $self->db_path($uuid);
	return undef unless -e $db_path;
	open my $fh, '<', $db_path or croak $!;
1837 1838 1839
	if (sysseek($fh, $offset, 0) == $offset) {
		my $read = sysread($fh, $ret, 40);
		$ret = undef if ($read != 40 || $ret eq ('0'x40));
1840 1841 1842 1843 1844
	}
	close $fh or croak $!;
	$ret;
}

1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856
sub find_rev_before {
	my ($self, $rev, $eq_ok) = @_;
	--$rev unless $eq_ok;
	while ($rev > 0) {
		if (my $c = $self->rev_db_get($rev)) {
			return ($rev, $c);
		}
		--$rev;
	}
	return (undef, undef);
}

1857
sub _new {
1858 1859 1860 1861 1862
	my ($class, $repo_id, $ref_id, $path) = @_;
	unless (defined $repo_id && length $repo_id) {
		$repo_id = $Git::SVN::default_repo_id;
	}
	unless (defined $ref_id && length $ref_id) {
1863
		$_[2] = $ref_id = $Git::SVN::default_ref_id;
1864 1865 1866 1867
	}
	$_[1] = $repo_id = sanitize_remote_name($repo_id);
	my $dir = "$ENV{GIT_DIR}/svn/$ref_id";
	$_[3] = $path = '' unless (defined $path);
1868
	mkpath(["$ENV{GIT_DIR}/svn"]);
1869 1870
	bless {
		ref_id => $ref_id, dir => $dir, index => "$dir/index",
1871
	        path => $path, config => "$ENV{GIT_DIR}/svn/config",
1872 1873 1874 1875 1876 1877 1878
	        db_root => "$dir/.rev_db", repo_id => $repo_id }, $class;
}

sub db_path {
	my ($self, $uuid) = @_;
	$uuid ||= $self->ra_uuid;
	"$self->{db_root}.$uuid";
1879 1880
}

1881 1882 1883 1884 1885
sub uri_encode {
	my ($f) = @_;
	$f =~ s#([^a-zA-Z0-9\*!\:_\./\-])#uc sprintf("%%%02x",ord($1))#eg;
	$f
}
1886

1887 1888 1889 1890 1891 1892 1893
package Git::SVN::Prompt;
use strict;
use warnings;
require SVN::Core;
use vars qw/$_no_auth_cache $_username/;

sub simple {
1894 1895 1896 1897 1898
	my ($cred, $realm, $default_username, $may_save, $pool) = @_;
	$may_save = undef if $_no_auth_cache;
	$default_username = $_username if defined $_username;
	if (defined $default_username && length $default_username) {
		if (defined $realm && length $realm) {
1899 1900
			print STDERR "Authentication realm: $realm\n";
			STDERR->flush;
1901 1902 1903
		}
		$cred->username($default_username);
	} else {
1904
		username($cred, $realm, $may_save, $pool);
1905 1906 1907 1908 1909 1910 1911
	}
	$cred->password(_read_password("Password for '" .
	                               $cred->username . "': ", $realm));
	$cred->may_save($may_save);
	$SVN::_Core::SVN_NO_ERROR;
}

1912
sub ssl_server_trust {
1913 1914
	my ($cred, $realm, $failures, $cert_info, $may_save, $pool) = @_;
	$may_save = undef if $_no_auth_cache;
1915
	print STDERR "Error validating server certificate for '$realm':\n";
1916
	if ($failures & $SVN::Auth::SSL::UNKNOWNCA) {
1917
		print STDERR " - The certificate is not issued by a trusted ",
1918 1919 1920 1921
		      "authority. Use the\n",
	              "   fingerprint to validate the certificate manually!\n";
	}
	if ($failures & $SVN::Auth::SSL::CNMISMATCH) {
1922
		print STDERR " - The certificate hostname does not match.\n";
1923 1924
	}
	if ($failures & $SVN::Auth::SSL::NOTYETVALID) {
1925
		print STDERR " - The certificate is not yet valid.\n";
1926 1927
	}
	if ($failures & $SVN::Auth::SSL::EXPIRED) {
1928
		print STDERR " - The certificate has expired.\n";
1929 1930
	}
	if ($failures & $SVN::Auth::SSL::OTHER) {
1931
		print STDERR " - The certificate has an unknown error.\n";
1932
	}
1933 1934
	printf STDERR
	        "Certificate information:\n".
1935 1936 1937 1938 1939
	        " - Hostname: %s\n".
	        " - Valid: from %s until %s\n".
	        " - Issuer: %s\n".
	        " - Fingerprint: %s\n",
	        map $cert_info->$_, qw(hostname valid_from valid_until
1940
	                               issuer_dname fingerprint);
1941 1942
	my $choice;
prompt:
1943
	print STDERR $may_save ?
1944 1945
	      "(R)eject, accept (t)emporarily or accept (p)ermanently? " :
	      "(R)eject or accept (t)emporarily? ";
1946
	STDERR->flush;
1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960
	$choice = lc(substr(<STDIN> || 'R', 0, 1));
	if ($choice =~ /^t$/i) {
		$cred->may_save(undef);
	} elsif ($choice =~ /^r$/i) {
		return -1;
	} elsif ($may_save && $choice =~ /^p$/i) {
		$cred->may_save($may_save);
	} else {
		goto prompt;
	}
	$cred->accepted_failures($failures);
	$SVN::_Core::SVN_NO_ERROR;
}

1961
sub ssl_client_cert {
1962 1963
	my ($cred, $realm, $may_save, $pool) = @_;
	$may_save = undef if $_no_auth_cache;
1964 1965
	print STDERR "Client certificate filename: ";
	STDERR->flush;
1966 1967 1968 1969 1970 1971
	chomp(my $filename = <STDIN>);
	$cred->cert_file($filename);
	$cred->may_save($may_save);
	$SVN::_Core::SVN_NO_ERROR;
}

1972
sub ssl_client_cert_pw {
1973 1974 1975 1976 1977 1978 1979
	my ($cred, $realm, $may_save, $pool) = @_;
	$may_save = undef if $_no_auth_cache;
	$cred->password(_read_password("Password: ", $realm));
	$cred->may_save($may_save);
	$SVN::_Core::SVN_NO_ERROR;
}

1980
sub username {
1981 1982 1983
	my ($cred, $realm, $may_save, $pool) = @_;
	$may_save = undef if $_no_auth_cache;
	if (defined $realm && length $realm) {
1984
		print STDERR "Authentication realm: $realm\n";
1985 1986 1987 1988 1989
	}
	my $username;
	if (defined $_username) {
		$username = $_username;
	} else {
1990 1991
		print STDERR "Username: ";
		STDERR->flush;
1992 1993 1994 1995 1996 1997 1998 1999 2000
		chomp($username = <STDIN>);
	}
	$cred->username($username);
	$cred->may_save($may_save);
	$SVN::_Core::SVN_NO_ERROR;
}

sub _read_password {
	my ($prompt, $realm) = @_;
2001 2002
	print STDERR $prompt;
	STDERR->flush;
2003 2004 2005 2006 2007 2008 2009 2010
	require Term::ReadKey;
	Term::ReadKey::ReadMode('noecho');
	my $password = '';
	while (defined(my $key = Term::ReadKey::ReadKey(0))) {
		last if $key =~ /[\012\015]/; # \n\r
		$password .= $key;
	}
	Term::ReadKey::ReadMode('restore');
2011 2012
	print STDERR "\n";
	STDERR->flush;
2013 2014 2015
	$password;
}

2016 2017
package main;

2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029
{
	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.
				$SVN::Auth::SSL::CNMISMATCH.
				$SVN::Auth::SSL::NOTYETVALID.
				$SVN::Auth::SSL::EXPIRED.
				$SVN::Auth::SSL::UNKNOWNCA.
				$SVN::Auth::SSL::OTHER;
}

2030 2031 2032 2033 2034 2035
package SVN::Git::Fetcher;
use vars qw/@ISA/;
use strict;
use warnings;
use Carp qw/croak/;
use IO::File qw//;
2036
use Digest::MD5;
2037 2038 2039 2040 2041 2042

# file baton members: path, mode_a, mode_b, pool, fh, blob, base
sub new {
	my ($class, $git_svn) = @_;
	my $self = SVN::Delta::Editor->new;
	bless $self, $class;
2043
	$self->{c} = $git_svn->{last_commit} if exists $git_svn->{last_commit};
2044 2045 2046 2047 2048
	$self->{empty} = {};
	$self->{dir_prop} = {};
	$self->{file_prop} = {};
	$self->{absent_dir} = {};
	$self->{absent_file} = {};
2049
	$self->{gii} = $git_svn->tmp_index_do(sub { Git::IndexInfo->new });
2050 2051 2052
	$self;
}

2053 2054
sub set_path_strip {
	my ($self, $path) = @_;
2055
	$self->{path_strip} = qr/^\Q$path\E(\/|$)/ if length $path;
2056 2057
}

2058 2059 2060 2061 2062 2063 2064 2065 2066
sub open_root {
	{ path => '' };
}

sub open_directory {
	my ($self, $path, $pb, $rev) = @_;
	{ path => $path };
}

2067 2068
sub git_path {
	my ($self, $path) = @_;
2069 2070 2071 2072
	if ($self->{path_strip}) {
		$path =~ s!$self->{path_strip}!! or
		  die "Failed to strip path '$path' ($self->{path_strip})\n";
	}
2073 2074 2075
	$path;
}

2076 2077
sub delete_entry {
	my ($self, $path, $rev, $pb) = @_;
2078

2079
	my $gpath = $self->git_path($path);
2080 2081
	return undef if ($gpath eq '');

2082
	# remove entire directories.
2083
	if (command('ls-tree', $self->{c}, '--', $gpath) =~ /^040000 tree/) {
2084 2085
		my ($ls, $ctx) = command_output_pipe(qw/ls-tree
		                                     -r --name-only -z/,
2086
				                     $self->{c}, '--', $gpath);
2087 2088
		local $/ = "\0";
		while (<$ls>) {
2089 2090
			chomp;
			$self->{gii}->remove($_);
2091
			print "\tD\t$_\n" unless $::_q;
2092
		}
2093
		print "\tD\t$gpath/\n" unless $::_q;
2094 2095 2096
		command_close_pipe($ls, $ctx);
		$self->{empty}->{$path} = 0
	} else {
2097
		$self->{gii}->remove($gpath);
2098
		print "\tD\t$gpath\n" unless $::_q;
2099
	}
2100 2101 2102 2103 2104
	undef;
}

sub open_file {
	my ($self, $path, $pb, $rev) = @_;
2105 2106
	my $gpath = $self->git_path($path);
	my ($mode, $blob) = (command('ls-tree', $self->{c}, '--', $gpath)
2107
	                     =~ /^(\d{6}) blob ([a-f\d]{40})\t/);
2108 2109 2110
	unless (defined $mode && defined $blob) {
		die "$path was not found in commit $self->{c} (r$rev)\n";
	}
2111
	{ path => $path, mode_a => $mode, mode_b => $mode, blob => $blob,
2112
	  pool => SVN::Pool->new, action => 'M' };
2113 2114 2115 2116
}

sub add_file {
	my ($self, $path, $pb, $cp_path, $cp_rev) = @_;
2117 2118
	my ($dir, $file) = ($path =~ m#^(.*?)/?([^/]+)$#);
	delete $self->{empty}->{$dir};
2119
	{ path => $path, mode_a => 100644, mode_b => 100644,
2120
	  pool => SVN::Pool->new, action => 'A' };
2121 2122
}

2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151
sub add_directory {
	my ($self, $path, $cp_path, $cp_rev) = @_;
	my ($dir, $file) = ($path =~ m#^(.*?)/?([^/]+)$#);
	delete $self->{empty}->{$dir};
	$self->{empty}->{$path} = 1;
	{ path => $path };
}

sub change_dir_prop {
	my ($self, $db, $prop, $value) = @_;
	$self->{dir_prop}->{$db->{path}} ||= {};
	$self->{dir_prop}->{$db->{path}}->{$prop} = $value;
	undef;
}

sub absent_directory {
	my ($self, $path, $pb) = @_;
	$self->{absent_dir}->{$pb->{path}} ||= [];
	push @{$self->{absent_dir}->{$pb->{path}}}, $path;
	undef;
}

sub absent_file {
	my ($self, $path, $pb) = @_;
	$self->{absent_file}->{$pb->{path}} ||= [];
	push @{$self->{absent_file}->{$pb->{path}}}, $path;
	undef;
}

2152 2153 2154 2155 2156 2157 2158 2159
sub change_file_prop {
	my ($self, $fb, $prop, $value) = @_;
	if ($prop eq 'svn:executable') {
		if ($fb->{mode_b} != 120000) {
			$fb->{mode_b} = defined $value ? 100755 : 100644;
		}
	} elsif ($prop eq 'svn:special') {
		$fb->{mode_b} = defined $value ? 120000 : 100644;
2160 2161 2162
	} else {
		$self->{file_prop}->{$fb->{path}} ||= {};
		$self->{file_prop}->{$fb->{path}}->{$prop} = $value;
2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204
	}
	undef;
}

sub apply_textdelta {
	my ($self, $fb, $exp) = @_;
	my $fh = IO::File->new_tmpfile;
	$fh->autoflush(1);
	# $fh gets auto-closed() by SVN::TxDelta::apply(),
	# (but $base does not,) so dup() it for reading in close_file
	open my $dup, '<&', $fh or croak $!;
	my $base = IO::File->new_tmpfile;
	$base->autoflush(1);
	if ($fb->{blob}) {
		defined (my $pid = fork) or croak $!;
		if (!$pid) {
			open STDOUT, '>&', $base or croak $!;
			print STDOUT 'link ' if ($fb->{mode_a} == 120000);
			exec qw/git-cat-file blob/, $fb->{blob} or croak $!;
		}
		waitpid $pid, 0;
		croak $? if $?;

		if (defined $exp) {
			seek $base, 0, 0 or croak $!;
			my $md5 = Digest::MD5->new;
			$md5->addfile($base);
			my $got = $md5->hexdigest;
			die "Checksum mismatch: $fb->{path} $fb->{blob}\n",
			    "expected: $exp\n",
			    "     got: $got\n" if ($got ne $exp);
		}
	}
	seek $base, 0, 0 or croak $!;
	$fb->{fh} = $dup;
	$fb->{base} = $base;
	[ SVN::TxDelta::apply($base, $fh, undef, $fb->{path}, $fb->{pool}) ];
}

sub close_file {
	my ($self, $fb, $exp) = @_;
	my $hash;
2205
	my $path = $self->git_path($fb->{path});
2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232
	if (my $fh = $fb->{fh}) {
		seek($fh, 0, 0) or croak $!;
		my $md5 = Digest::MD5->new;
		$md5->addfile($fh);
		my $got = $md5->hexdigest;
		die "Checksum mismatch: $path\n",
		    "expected: $exp\n    got: $got\n" if ($got ne $exp);
		seek($fh, 0, 0) or croak $!;
		if ($fb->{mode_b} == 120000) {
			read($fh, my $buf, 5) == 5 or croak $!;
			$buf eq 'link ' or die "$path has mode 120000",
			                       "but is not a link\n";
		}
		defined(my $pid = open my $out,'-|') or die "Can't fork: $!\n";
		if (!$pid) {
			open STDIN, '<&', $fh or croak $!;
			exec qw/git-hash-object -w --stdin/ or croak $!;
		}
		chomp($hash = do { local $/; <$out> });
		close $out or croak $!;
		close $fh or croak $!;
		$hash =~ /^[a-f\d]{40}$/ or die "not a sha1: $hash\n";
		close $fb->{base} or croak $!;
	} else {
		$hash = $fb->{blob} or die "no blob information\n";
	}
	$fb->{pool}->clear;
2233
	$self->{gii}->update($fb->{mode_b}, $hash, $path) or croak $!;
2234
	print "\t$fb->{action}\t$path\n" if $fb->{action} && ! $::_q;
2235 2236 2237 2238 2239
	undef;
}

sub abort_edit {
	my $self = shift;
2240 2241
	$self->{nr} = $self->{gii}->{nr};
	delete $self->{gii};
2242 2243 2244 2245 2246
	$self->SUPER::abort_edit(@_);
}

sub close_edit {
	my $self = shift;
2247
	$self->{git_commit_ok} = 1;
2248 2249
	$self->{nr} = $self->{gii}->{nr};
	delete $self->{gii};
2250 2251
	$self->SUPER::close_edit(@_);
}
2252

2253
package SVN::Git::Editor;
2254
use vars qw/@ISA $_rmdir $_cp_similarity $_find_copies_harder $_rename_limit/;
2255 2256 2257 2258
use strict;
use warnings;
use Carp qw/croak/;
use IO::File;
2259
use Digest::MD5;
2260 2261

sub new {
2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275
	my ($class, $opts) = @_;
	foreach (qw/svn_path r ra tree_a tree_b log editor_cb/) {
		die "$_ required!\n" unless (defined $opts->{$_});
	}

	my $pool = SVN::Pool->new;
	my $mods = generate_diff($opts->{tree_a}, $opts->{tree_b});
	my $types = check_diff_paths($opts->{ra}, $opts->{svn_path},
	                             $opts->{r}, $mods);

	# $opts->{ra} functions should not be used after this:
	my @ce  = $opts->{ra}->get_commit_editor($opts->{log},
	                                        $opts->{editor_cb}, $pool);
	my $self = SVN::Delta::Editor->new(@ce, $pool);
2276
	bless $self, $class;
2277 2278
	foreach (qw/svn_path r tree_a tree_b/) {
		$self->{$_} = $opts->{$_};
2279
	}
2280 2281 2282 2283
	$self->{url} = $opts->{ra}->{url};
	$self->{mods} = $mods;
	$self->{types} = $types;
	$self->{pool} = $pool;
2284 2285
	$self->{bat} = { '' => $self->open_root($self->{r}, $self->{pool}) };
	$self->{rm} = { };
2286 2287
	$self->{path_prefix} = length $self->{svn_path} ?
	                       "$self->{svn_path}/" : '';
2288 2289 2290
	return $self;
}

2291 2292 2293
sub generate_diff {
	my ($tree_a, $tree_b) = @_;
	my @diff_tree = qw(diff-tree -z -r);
2294 2295
	if ($_cp_similarity) {
		push @diff_tree, "-C$_cp_similarity";
2296 2297 2298
	} else {
		push @diff_tree, '-C';
	}
2299 2300
	push @diff_tree, '--find-copies-harder' if $_find_copies_harder;
	push @diff_tree, "-l$_rename_limit" if defined $_rename_limit;
2301 2302 2303 2304 2305 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 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373
	push @diff_tree, $tree_a, $tree_b;
	my ($diff_fh, $ctx) = command_output_pipe(@diff_tree);
	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') {
			my $x = $mods[$#mods] or croak "Empty array\n";
			if ($x->{chg} !~ /^(?:C|R)$/) {
				croak "Error parsing $_, $x->{chg}\n";
			}
			$x->{file_a} = $_;
			$state = 'file_b';
		} elsif ($state eq 'file_b') {
			my $x = $mods[$#mods] or croak "Empty array\n";
			if (exists $x->{file_a} && $x->{chg} !~ /^(?:C|R)$/) {
				croak "Error parsing $_, $x->{chg}\n";
			}
			if (!exists $x->{file_a} && $x->{chg} =~ /^(?:C|R)$/) {
				croak "Error parsing $_, $x->{chg}\n";
			}
			$x->{file_b} = $_;
			$state = 'meta';
		} else {
			croak "Error parsing $_\n";
		}
	}
	command_close_pipe($diff_fh, $ctx);
	\@mods;
}

sub check_diff_paths {
	my ($ra, $pfx, $rev, $mods) = @_;
	my %types;
	$pfx .= '/' if length $pfx;

	sub type_diff_paths {
		my ($ra, $types, $path, $rev) = @_;
		my @p = split m#/+#, $path;
		my $c = shift @p;
		unless (defined $types->{$c}) {
			$types->{$c} = $ra->check_path($c, $rev);
		}
		while (@p) {
			$c .= '/' . shift @p;
			next if defined $types->{$c};
			$types->{$c} = $ra->check_path($c, $rev);
		}
	}

	foreach my $m (@$mods) {
		foreach my $f (qw/file_a file_b/) {
			next unless defined $m->{$f};
			my ($dir) = ($m->{$f} =~ m#^(.*?)/?(?:[^/]+)$#);
			if (length $pfx.$dir && ! defined $types{$dir}) {
				type_diff_paths($ra, \%types, $pfx.$dir, $rev);
			}
		}
	}
	\%types;
}

2374 2375 2376 2377 2378
sub split_path {
	return ($_[0] =~ m#^(.*?)/?([^/]+)$#);
}

sub repo_path {
2379 2380
	my ($self, $path) = @_;
	$self->{path_prefix}.(defined $path ? $path : '');
2381 2382 2383 2384
}

sub url_path {
	my ($self, $path) = @_;
2385
	$self->{url} . '/' . $self->repo_path($path);
2386 2387 2388
}

sub rmdirs {
2389
	my ($self) = @_;
2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406
	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;

2407 2408
	my ($fh, $ctx) = command_output_pipe(qw/ls-tree --name-only -r -z/,
	                                     $self->{tree_b});
2409 2410 2411
	local $/ = "\0";
	while (<$fh>) {
		chomp;
2412
		my @dn = split m#/#, $_;
2413 2414 2415 2416
		while (pop @dn) {
			delete $rm->{join '/', @dn};
		}
		unless (%$rm) {
2417
			close $fh;
2418 2419
			return;
		}
2420
	}
E
Eric Wong 已提交
2421
	command_close_pipe($fh, $ctx);
2422

2423 2424 2425 2426
	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) = ($d =~ m#^(.*?)/?(?:[^/]+)$#);
2427
		print "\tD+\t$d/\n" unless $::_q;
2428 2429 2430 2431 2432 2433 2434
		$self->SUPER::delete_entry($d, $r, $bat->{$dn}, $p);
		delete $bat->{$d};
	}
}

sub open_or_add_dir {
	my ($self, $full_path, $baton) = @_;
2435 2436 2437 2438
	my $t = $self->{types}->{$full_path};
	if (!defined $t) {
		die "$full_path not known in r$self->{r} or we have a bug!\n";
	}
2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454
	if ($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};
2455 2456 2457
	my $repo_path = $self->repo_path($path);
	return $bat->{''} unless (length $repo_path);
	my @p = split m#/+#, $repo_path;
2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468
	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 {
2469
	my ($self, $m) = @_;
2470 2471 2472 2473
	my ($dir, $file) = split_path($m->{file_b});
	my $pbat = $self->ensure_path($dir);
	my $fbat = $self->add_file($self->repo_path($m->{file_b}), $pbat,
					undef, -1);
2474
	print "\tA\t$m->{file_b}\n" unless $::_q;
2475 2476 2477 2478 2479
	$self->chg_file($fbat, $m);
	$self->close_file($fbat,undef,$self->{pool});
}

sub C {
2480
	my ($self, $m) = @_;
2481 2482 2483 2484
	my ($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}), $self->{r});
2485
	print "\tC\t$m->{file_a} => $m->{file_b}\n" unless $::_q;
2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498
	$self->chg_file($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 {
2499
	my ($self, $m) = @_;
2500 2501 2502 2503
	my ($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}), $self->{r});
2504
	print "\tR\t$m->{file_a} => $m->{file_b}\n" unless $::_q;
2505 2506 2507 2508 2509 2510 2511 2512 2513
	$self->chg_file($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 {
2514
	my ($self, $m) = @_;
2515 2516 2517 2518
	my ($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},$self->{pool});
2519
	print "\t$m->{chg}\t$m->{file_b}\n" unless $::_q;
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
	$self->chg_file($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;
2560 2561 2562
	my $pool = SVN::Pool->new;
	my $atd = $self->apply_textdelta($fbat, undef, $pool);
	my $got = SVN::TxDelta::send_stream($fh, @$atd, $pool);
2563
	die "Checksum mismatch\nexpected: $exp\ngot: $got\n" if ($got ne $exp);
2564
	$pool->clear;
2565 2566 2567 2568 2569

	close $fh or croak $!;
}

sub D {
2570
	my ($self, $m) = @_;
2571 2572
	my ($dir, $file) = split_path($m->{file_b});
	my $pbat = $self->ensure_path($dir);
2573
	print "\tD\t$m->{file_b}\n" unless $::_q;
2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589
	$self->delete_entry($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});
2590 2591 2592 2593 2594
}

sub DESTROY {
	my $self = shift;
	$self->SUPER::DESTROY(@_);
2595 2596 2597
	$self->{pool}->clear;
}

2598 2599
# this drives the editor
sub apply_diff {
2600 2601
	my ($self) = @_;
	my $mods = $self->{mods};
2602
	my %o = ( D => 1, R => 0, C => -1, A => 3, M => 3, T => 3 );
2603
	foreach my $m (sort { $o{$a->{chg}} <=> $o{$b->{chg}} } @$mods) {
2604 2605 2606 2607 2608 2609 2610
		my $f = $m->{chg};
		if (defined $o{$f}) {
			$self->$f($m);
		} else {
			fatal("Invalid change type: $f\n");
		}
	}
2611
	$self->rmdirs if $_rmdir;
2612
	if (@$mods == 0) {
2613 2614 2615 2616
		$self->abort_edit;
	} else {
		$self->close_edit;
	}
2617
	return scalar @$mods;
2618 2619
}

2620
package Git::SVN::Ra;
2621
use vars qw/@ISA $config_dir $_log_window_size/;
2622 2623 2624
use strict;
use warnings;
my ($can_do_switch);
2625
my $RA;
2626 2627 2628 2629

BEGIN {
	# enforce temporary pool usage for some simple functions
	my $e;
2630
	foreach (qw/get_latest_revnum get_uuid get_repos_root/) {
2631 2632 2633 2634 2635 2636 2637
		$e .= "sub $_ {
			my \$self = shift;
			my \$pool = SVN::Pool->new;
			my \@ret = \$self->SUPER::$_(\@_,\$pool);
			\$pool->clear;
			wantarray ? \@ret : \$ret[0]; }\n";
	}
2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661

	# get_dir needs $pool held in cache for dirents to work,
	# check_path is cacheable and rev_proplist is close enough
	# for our purposes.
	foreach (qw/check_path get_dir rev_proplist/) {
		$e .= "my \%${_}_cache; my \$${_}_rev = 0; sub $_ {
			my \$self = shift;
			my \$r = pop;
			my \$k = join(\"\\0\", \@_);
			if (my \$x = \$${_}_cache{\$r}->{\$k}) {
				return wantarray ? \@\$x : \$x->[0];
			}
			my \$pool = SVN::Pool->new;
			my \@ret = \$self->SUPER::$_(\@_, \$r, \$pool);
			if (\$r != \$${_}_rev) {
				\%${_}_cache = ( pool => [] );
				\$${_}_rev = \$r;
			}
			\$${_}_cache{\$r}->{\$k} = \\\@ret;
			push \@{\$${_}_cache{pool}}, \$pool;
			wantarray ? \@ret : \$ret[0]; }\n";
	}
	$e .= "\n1;";
	eval $e or die $@;
2662 2663 2664 2665
}

sub new {
	my ($class, $url) = @_;
2666
	$url =~ s!/+$!!;
2667
	return $RA if ($RA && $RA->{url} eq $url);
2668

2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691
	SVN::_Core::svn_config_ensure($config_dir, undef);
	my ($baton, $callbacks) = SVN::Core::auth_open_helper([
	    SVN::Client::get_simple_provider(),
	    SVN::Client::get_ssl_server_trust_file_provider(),
	    SVN::Client::get_simple_prompt_provider(
	      \&Git::SVN::Prompt::simple, 2),
	    SVN::Client::get_ssl_client_cert_prompt_provider(
	      \&Git::SVN::Prompt::ssl_client_cert, 2),
	    SVN::Client::get_ssl_client_cert_pw_prompt_provider(
	      \&Git::SVN::Prompt::ssl_client_cert_pw, 2),
	    SVN::Client::get_username_provider(),
	    SVN::Client::get_ssl_server_trust_prompt_provider(
	      \&Git::SVN::Prompt::ssl_server_trust),
	    SVN::Client::get_username_prompt_provider(
	      \&Git::SVN::Prompt::username, 2),
	  ]);
	my $config = SVN::Core::config_get_config($config_dir);
	my $self = SVN::Ra->new(url => $url, auth => $baton,
	                      config => $config,
			      pool => SVN::Pool->new,
	                      auth_provider_callbacks => $callbacks);
	$self->{svn_path} = $url;
	$self->{repos_root} = $self->get_repos_root;
2692
	$self->{svn_path} =~ s#^\Q$self->{repos_root}\E(/|$)##;
2693
	$RA = bless $self, $class;
2694 2695 2696
}

sub DESTROY {
2697
	# do not call the real DESTROY since we store ourselves in $RA
2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709
}

sub get_log {
	my ($self, @args) = @_;
	my $pool = SVN::Pool->new;
	splice(@args, 3, 1) if ($SVN::Core::VERSION le '1.2.0');
	my $ret = $self->SUPER::get_log(@args, $pool);
	$pool->clear;
	$ret;
}

sub get_commit_editor {
2710
	my ($self, $log, $cb, $pool) = @_;
2711
	my @lock = $SVN::Core::VERSION ge '1.2.0' ? (undef, 0) : ();
2712
	$self->SUPER::get_commit_editor($log, $cb, @lock, $pool);
2713 2714 2715
}

sub gs_do_update {
2716 2717 2718 2719
	my ($self, $rev_a, $rev_b, $gs, $editor) = @_;
	my $new = ($rev_a == $rev_b);
	my $path = $gs->{path};

2720
	my $pool = SVN::Pool->new;
2721
	$editor->set_path_strip($path);
2722 2723
	my (@pc) = split m#/#, $path;
	my $reporter = $self->do_update($rev_b, (@pc ? shift @pc : ''),
2724
	                                1, $editor, $pool);
2725
	my @lock = $SVN::Core::VERSION ge '1.2.0' ? (undef) : ();
2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740

	# Since we can't rely on svn_ra_reparent being available, we'll
	# just have to do some magic with set_path to make it so
	# we only want a partial path.
	my $sp = '';
	my $final = join('/', @pc);
	while (@pc) {
		$reporter->set_path($sp, $rev_b, 0, @lock, $pool);
		$sp .= '/' if length $sp;
		$sp .= shift @pc;
	}
	die "BUG: '$sp' != '$final'\n" if ($sp ne $final);

	$reporter->set_path($sp, $rev_a, $new, @lock, $pool);

2741 2742 2743 2744 2745
	$reporter->finish_report($pool);
	$pool->clear;
	$editor->{git_commit_ok};
}

2746 2747
# this requires SVN 1.4.3 or later (do_switch didn't work before 1.4.3, and
# svn_ra_reparent didn't work before 1.4)
2748
sub gs_do_switch {
2749 2750
	my ($self, $rev_a, $rev_b, $gs, $url_b, $editor) = @_;
	my $path = $gs->{path};
2751
	my $pool = SVN::Pool->new;
2752 2753 2754 2755

	my $full_url = $self->{url};
	my $old_url = $full_url;
	$full_url .= "/$path" if length $path;
2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767
	my ($ra, $reparented);
	if ($old_url ne $full_url) {
		if ($old_url !~ m#^svn(\+ssh)?://#) {
			SVN::_Ra::svn_ra_reparent($self->{session}, $full_url,
			                          $pool);
			$self->{url} = $full_url;
			$reparented = 1;
		} else {
			$ra = Git::SVN::Ra->new($full_url);
		}
	}
	$ra ||= $self;
2768
	my $reporter = $ra->do_switch($rev_b, '', 1, $url_b, $editor, $pool);
2769
	my @lock = $SVN::Core::VERSION ge '1.2.0' ? (undef) : ();
2770
	$reporter->set_path('', $rev_a, 0, @lock, $pool);
2771
	$reporter->finish_report($pool);
2772

2773 2774 2775 2776
	if ($reparented) {
		SVN::_Ra::svn_ra_reparent($self->{session}, $old_url, $pool);
		$self->{url} = $old_url;
	}
2777

2778 2779 2780 2781
	$pool->clear;
	$editor->{git_commit_ok};
}

2782
sub gs_fetch_loop_common {
2783 2784
	my ($self, $base, $head, $gsv, $globs) = @_;
	return if ($base > $head);
2785
	my $inc = $_log_window_size;
2786
	my ($min, $max) = ($base, $head < $base + $inc ? $head : $base + $inc);
2787
	my %common;
2788 2789 2790
	my $common_max = scalar @$gsv;

	foreach my $gs (@$gsv) {
2791 2792 2793 2794 2795 2796 2797 2798
		my @tmp = split m#/#, $gs->{path};
		my $p = '';
		foreach (@tmp) {
			$p .= length($p) ? "/$_" : $_;
			$common{$p} ||= 0;
			$common{$p}++;
		}
	}
2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810
	$globs ||= [];
	$common_max += scalar @$globs;
	foreach my $glob (@$globs) {
		my @tmp = split m#/#, $glob->{path}->{left};
		my $p = '';
		foreach (@tmp) {
			$p .= length($p) ? "/$_" : $_;
			$common{$p} ||= 0;
			$common{$p}++;
		}
	}

2811 2812
	my $longest_path = '';
	foreach (sort {length $b <=> length $a} keys %common) {
2813
		if ($common{$_} == $common_max) {
2814 2815 2816
			$longest_path = $_;
			last;
		}
2817 2818
	}
	while (1) {
2819
		my %revs;
2820
		my $err;
2821
		my $err_handler = $SVN::Error::handler;
2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852
		$SVN::Error::handler = sub {
			($err) = @_;
			skip_unknown_revs($err);
		};
		sub _cb {
			my ($paths, $r, $author, $date, $log) = @_;
			[ dup_changed_paths($paths),
			  { author => $author, date => $date, log => $log } ];
		}
		$self->get_log([$longest_path], $min, $max, 0, 1, 1,
		               sub { $revs{$_[1]} = _cb(@_) });
		if ($err && $max >= $head) {
			print STDERR "Path '$longest_path' ",
				     "was probably deleted:\n",
				     $err->expanded_message,
				     "\nWill attempt to follow ",
				     "revisions r$min .. r$max ",
				     "committed before the deletion\n";
			my $hi = $max;
			while (--$hi >= $min) {
				my $ok;
				$self->get_log([$longest_path], $min, $hi,
				               0, 1, 1, sub {
				               $ok ||= $_[1];
				               $revs{$_[1]} = _cb(@_) });
				if ($ok) {
					print STDERR "r$min .. r$ok OK\n";
					last;
				}
			}
		}
2853
		$SVN::Error::handler = $err_handler;
2854

2855
		my %exists = map { $_->{path} => $_ } @$gsv;
2856
		foreach my $r (sort {$a <=> $b} keys %revs) {
2857
			my ($paths, $logged) = @{$revs{$r}};
2858 2859 2860

			foreach my $gs ($self->match_globs(\%exists, $paths,
			                                   $globs, $r)) {
2861 2862 2863 2864 2865
				if ($gs->rev_db_max >= $r) {
					next;
				}
				next unless $gs->match_paths($paths, $r);
				$gs->{logged_rev_props} = $logged;
2866 2867 2868
				if (my $last_commit = $gs->last_commit) {
					$gs->assert_index_clean($last_commit);
				}
2869 2870
				my $log_entry = $gs->do_fetch($paths, $r);
				if ($log_entry) {
2871 2872 2873
					$gs->do_git_commit($log_entry);
				}
			}
2874
			foreach my $g (@$globs) {
2875 2876 2877
				my $k = "svn-remote.$g->{remote}." .
				        "$g->{t}-maxRev";
				Git::SVN::tmp_config($k, $r);
2878
			}
2879
		}
2880 2881
		# pre-fill the .rev_db since it'll eventually get filled in
		# with '0' x40 if something new gets committed
2882
		foreach my $gs (@$gsv) {
2883 2884 2885
			next if defined $gs->rev_db_get($max);
			$gs->rev_db_set($max, 0 x40);
		}
2886 2887 2888 2889
		foreach my $g (@$globs) {
			my $k = "svn-remote.$g->{remote}.$g->{t}-maxRev";
			Git::SVN::tmp_config($k, $max);
		}
2890 2891 2892 2893 2894 2895 2896
		last if $max >= $head;
		$min = $max + 1;
		$max += $inc;
		$max = $head if ($max > $head);
	}
}

2897 2898
sub match_globs {
	my ($self, $exists, $paths, $globs, $r) = @_;
2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915

	sub get_dir_check {
		my ($self, $exists, $g, $r) = @_;
		my @x = eval { $self->get_dir($g->{path}->{left}, $r) };
		return unless scalar @x == 3;
		my $dirents = $x[0];
		foreach my $de (keys %$dirents) {
			next if $dirents->{$de}->kind != $SVN::Node::dir;
			my $p = $g->{path}->full_path($de);
			next if $exists->{$p};
			next if (length $g->{path}->{right} &&
				 ($self->check_path($p, $r) !=
				  $SVN::Node::dir));
			$exists->{$p} = Git::SVN->init($self->{url}, $p, undef,
					 $g->{ref}->full_path($de), 1);
		}
	}
2916
	foreach my $g (@$globs) {
2917 2918 2919 2920 2921
		if (my $path = $paths->{"/$g->{path}->{left}"}) {
			if ($path->{action} =~ /^[AR]$/) {
				get_dir_check($self, $exists, $g, $r);
			}
		}
2922
		foreach (keys %$paths) {
E
Eric Wong 已提交
2923 2924
			if (/$g->{path}->{left_regex}/ &&
			    !/$g->{path}->{regex}/) {
2925 2926 2927
				next if $paths->{$_}->{action} !~ /^[AR]$/;
				get_dir_check($self, $exists, $g, $r);
			}
2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939
			next unless /$g->{path}->{regex}/;
			my $p = $1;
			my $pathname = $g->{path}->full_path($p);
			next if $exists->{$pathname};
			$exists->{$pathname} = Git::SVN->init(
			                      $self->{url}, $pathname, undef,
			                      $g->{ref}->full_path($p), 1);
		}
		my $c = '';
		foreach (split m#/#, $g->{path}->{left}) {
			$c .= "/$_";
			next unless ($paths->{$c} &&
2940 2941
			             ($paths->{$c}->{action} =~ /^[AR]$/));
			get_dir_check($self, $exists, $g, $r);
2942 2943 2944 2945 2946
		}
	}
	values %$exists;
}

2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959
sub minimize_url {
	my ($self) = @_;
	return $self->{url} if ($self->{url} eq $self->{repos_root});
	my $url = $self->{repos_root};
	my @components = split(m!/!, $self->{svn_path});
	my $c = '';
	do {
		$url .= "/$c" if length $c;
		eval { (ref $self)->new($url)->get_latest_revnum };
	} while ($@ && ($c = shift @components));
	$url;
}

2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978
sub can_do_switch {
	my $self = shift;
	unless (defined $can_do_switch) {
		my $pool = SVN::Pool->new;
		my $rep = eval {
			$self->do_switch(1, '', 0, $self->{url},
			                 SVN::Delta::Editor->new, $pool);
		};
		if ($@) {
			$can_do_switch = 0;
		} else {
			$rep->abort_report($pool);
			$can_do_switch = 1;
		}
		$pool->clear;
	}
	$can_do_switch;
}

2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991
sub skip_unknown_revs {
	my ($err) = @_;
	my $errno = $err->apr_err();
	# Maybe the branch we're tracking didn't
	# exist when the repo started, so it's
	# not an error if it doesn't, just continue
	#
	# Wonderfully consistent library, eh?
	# 160013 - svn:// and file://
	# 175002 - http(s)://
	# 175007 - http(s):// (this repo required authorization, too...)
	#   More codes may be discovered later...
	if ($errno == 175007 || $errno == 175002 || $errno == 160013) {
2992 2993 2994
		warn "W: Ignoring error from SVN, path probably ",
		     "does not exist: ($errno): ",
		     $err->expanded_message,"\n";
2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017
		return;
	}
	die "Error from SVN, ($errno): ", $err->expanded_message,"\n";
}

# svn_log_changed_path_t objects passed to get_log are likely to be
# overwritten even if only the refs are copied to an external variable,
# so we should dup the structures in their entirety.  Using an externally
# passed pool (instead of our temporary and quickly cleared pool in
# Git::SVN::Ra) does not help matters at all...
sub dup_changed_paths {
	my ($paths) = @_;
	return undef unless $paths;
	my %ret;
	foreach my $p (keys %$paths) {
		my $i = $paths->{$p};
		my %s = map { $_ => $i->$_ }
		              qw/copyfrom_path copyfrom_rev action/;
		$ret{$p} = \%s;
	}
	\%ret;
}

3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030
package Git::SVN::Log;
use strict;
use warnings;
use POSIX qw/strftime/;
use vars qw/$TZ $limit $color $pager $non_recursive $verbose $oneline
            %rusers $show_commit $incremental/;
my $l_fmt;

sub cmt_showable {
	my ($c) = @_;
	return 1 if defined $c->{r};
	if ($c->{l} && $c->{l}->[-1] eq "...\n" &&
				$c->{a_raw} =~ /\@([a-f\d\-]+)>$/) {
3031 3032 3033 3034
		my @log = command(qw/cat-file commit/, $c->{c});
		shift @log while ($log[0] ne "\n");
		shift @log;
		@{$c->{l}} = grep !/^git-svn-id: /, @log;
3035 3036

		(undef, $c->{r}, undef) = ::extract_metadata(
3037
				(grep(/^git-svn-id: /, @log))[-1]);
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
	}
	return defined $c->{r};
}

sub log_use_color {
	return 1 if $color;
	my ($dc, $dcvar);
	$dcvar = 'color.diff';
	$dc = `git-config --get $dcvar`;
	if ($dc eq '') {
		# nothing at all; fallback to "diff.color"
		$dcvar = 'diff.color';
		$dc = `git-config --get $dcvar`;
	}
	chomp($dc);
	if ($dc eq 'auto') {
		my $pc;
		$pc = `git-config --get color.pager`;
		if ($pc eq '') {
			# does not have it -- fallback to pager.color
			$pc = `git-config --bool --get pager.color`;
		}
		else {
			$pc = `git-config --bool --get color.pager`;
			if ($?) {
				$pc = 'false';
			}
		}
		chomp($pc);
		if (-t *STDOUT || (defined $pager && $pc eq 'true')) {
			return ($ENV{TERM} && $ENV{TERM} ne 'dumb');
		}
		return 0;
	}
	return 0 if $dc eq 'never';
	return 1 if $dc eq 'always';
	chomp($dc = `git-config --bool --get $dcvar`);
	return ($dc eq 'true');
}

sub git_svn_log_cmd {
3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097
	my ($r_min, $r_max, @args) = @_;
	my $head = 'HEAD';
	foreach my $x (@args) {
		last if $x eq '--';
		next unless ::verify_ref("$x^0");
		$head = $x;
		last;
	}

	my $url;
	my ($fh, $ctx) = command_output_pipe('rev-list', $head);
	while (<$fh>) {
		chomp;
		$url = (::cmt_metadata($_))[0];
		last if defined $url;
	}
	close $fh; # break the pipe

	my $gs = Git::SVN->find_by_url($url) || Git::SVN->_new;
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 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151
	my @cmd = (qw/log --abbrev-commit --pretty=raw --default/,
	           $gs->refname);
	push @cmd, '-r' unless $non_recursive;
	push @cmd, qw/--raw --name-status/ if $verbose;
	push @cmd, '--color' if log_use_color();
	return @cmd unless defined $r_max;
	if ($r_max == $r_min) {
		push @cmd, '--max-count=1';
		if (my $c = $gs->rev_db_get($r_max)) {
			push @cmd, $c;
		}
	} else {
		my ($c_min, $c_max);
		$c_max = $gs->rev_db_get($r_max);
		$c_min = $gs->rev_db_get($r_min);
		if (defined $c_min && defined $c_max) {
			if ($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;
}

# adapted from pager.c
sub config_pager {
	$pager ||= $ENV{GIT_PAGER} || $ENV{PAGER};
	if (!defined $pager) {
		$pager = 'less';
	} elsif (length $pager == 0 || $pager eq 'cat') {
		$pager = undef;
	}
}

sub run_pager {
	return unless -t *STDOUT;
	pipe my $rfd, my $wfd or return;
	defined(my $pid = fork) or ::fatal "Can't fork: $!\n";
	if (!$pid) {
		open STDOUT, '>&', $wfd or
		                     ::fatal "Can't redirect to stdout: $!\n";
		return;
	}
	open STDIN, '<&', $rfd or ::fatal "Can't redirect stdin: $!\n";
	$ENV{LESS} ||= 'FRSX';
	exec $pager or ::fatal "Can't run pager: $! ($pager)\n";
}

3152 3153 3154 3155 3156 3157
sub tz_to_s_offset {
	my ($tz) = @_;
	$tz =~ s/(\d\d)$//;
	return ($1 * 60) + ($tz * 3600);
}

3158 3159 3160 3161 3162
sub get_author_info {
	my ($dest, $author, $t, $tz) = @_;
	$author =~ s/(?:^\s*|\s*$)//g;
	$dest->{a_raw} = $author;
	my $au;
3163
	if ($::_authors) {
3164 3165 3166 3167 3168 3169 3170 3171 3172 3173
		$au = $rusers{$author} || undef;
	}
	if (!$au) {
		($au) = ($author =~ /<([^>]+)\@[^>]+>$/);
	}
	$dest->{t} = $t;
	$dest->{tz} = $tz;
	$dest->{a} = $au;
	# Date::Parse isn't in the standard Perl distro :(
	if ($tz =~ s/^\+//) {
3174
		$t += tz_to_s_offset($tz);
3175
	} elsif ($tz =~ s/^\-//) {
3176
		$t -= tz_to_s_offset($tz);
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 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260
	}
	$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_changed_paths {
	my ($c) = @_;
	return unless $c->{changed};
	print "Changed paths:\n", @{$c->{changed}};
}

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 > 0
		                          && $l->[($#$l - 1)] eq "\n") {
			pop @$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 $nr_line, "\n";
			show_commit_changed_paths($c);
			print "\n";
			print $_ foreach @$l;
		}
	} else {
		print "1 line\n";
		show_commit_changed_paths($c);
		print "\n";

	}
3261
	foreach my $x (qw/raw stat diff/) {
3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289
		if ($c->{$x}) {
			print "\n";
			print $_ foreach @{$c->{$x}}
		}
	}
}

sub cmd_show_log {
	my (@args) = @_;
	my ($r_min, $r_max);
	my $r_last = -1; # prevent dupes
	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 = $::_revision;
		} else {
			::fatal "-r$::_revision is not supported, use ",
				"standard \'git log\' arguments instead\n";
		}
	}

	config_pager();
3290
	@args = (git_svn_log_cmd($r_min, $r_max, @args), @args);
3291 3292
	my $log = command_output_pipe(@args);
	run_pager();
3293
	my (@k, $c, $d, $stat);
3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320
	my $esc_color = qr/(?:\033\[(?:(?:\d+;)*\d*)?m)*/;
	while (<$log>) {
		if (/^${esc_color}commit ($::sha1_short)/o) {
			my $cmt = $1;
			if ($c && cmt_showable($c) && $c->{r} != $r_last) {
				$r_last = $c->{r};
				process_commit($c, $r_min, $r_max, \@k) or
								goto out;
			}
			$d = undef;
			$c = { c => $cmt };
		} elsif (/^${esc_color}author (.+) (\d+) ([\-\+]?\d+)$/o) {
			get_author_info($c, $1, $2, $3);
		} elsif (/^${esc_color}(?:tree|parent|committer) /o) {
			# ignore
		} elsif (/^${esc_color}:\d{6} \d{6} $::sha1_short/o) {
			push @{$c->{raw}}, $_;
		} elsif (/^${esc_color}[ACRMDT]\t/) {
			# we could add $SVN->{svn_path} here, but that requires
			# remote access at the moment (repo_path_split)...
			s#^(${esc_color})([ACRMDT])\t#$1   $2 #o;
			push @{$c->{changed}}, $_;
		} elsif (/^${esc_color}diff /o) {
			$d = 1;
			push @{$c->{diff}}, $_;
		} elsif ($d) {
			push @{$c->{diff}}, $_;
3321 3322 3323 3324 3325 3326 3327
		} elsif (/^\ .+\ \|\s*\d+\ $esc_color[\+\-]*
		          $esc_color*[\+\-]*$esc_color$/x) {
			$stat = 1;
			push @{$c->{stat}}, $_;
		} elsif ($stat && /^ \d+ files changed, \d+ insertions/) {
			push @{$c->{stat}}, $_;
			$stat = undef;
3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344
		} elsif (/^${esc_color}    (git-svn-id:.+)$/o) {
			($c->{url}, $c->{r}, undef) = ::extract_metadata($1);
		} elsif (s/^${esc_color}    //o) {
			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:
3345
	close $log;
3346 3347 3348
	print '-' x72,"\n" unless $incremental || $oneline;
}

3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362
package Git::SVN::Migration;
# these version numbers do NOT correspond to actual version numbers
# of git nor git-svn.  They are just relative.
#
# v0 layout: .git/$id/info/url, refs/heads/$id-HEAD
#
# v1 layout: .git/$id/info/url, refs/remotes/$id
#
# v2 layout: .git/svn/$id/info/url, refs/remotes/$id
#
# v3 layout: .git/svn/$id, refs/remotes/$id
#            - info/url may remain for backwards compatibility
#            - this is what we migrate up to this layout automatically,
#            - this will be used by git svn init on single branches
3363 3364 3365
# v3.1 layout (auto migrated):
#            - .rev_db => .rev_db.$UUID, .rev_db will remain as a symlink
#              for backwards compatibility
3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376
#
# v4 layout: .git/svn/$repo_id/$id, refs/remotes/$repo_id/$id
#            - this is only created for newly multi-init-ed
#              repositories.  Similar in spirit to the
#              --use-separate-remotes option in git-clone (now default)
#            - we do not automatically migrate to this (following
#              the example set by core git)
use strict;
use warnings;
use Carp qw/croak/;
use File::Path qw/mkpath/;
3377 3378
use File::Basename qw/dirname basename/;
use vars qw/$_minimize/;
3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487

sub migrate_from_v0 {
	my $git_dir = $ENV{GIT_DIR};
	return undef unless -d $git_dir;
	my ($fh, $ctx) = command_output_pipe(qw/rev-parse --symbolic --all/);
	my $migrated = 0;
	while (<$fh>) {
		chomp;
		my ($id, $orig_ref) = ($_, $_);
		next unless $id =~ s#^refs/heads/(.+)-HEAD$#$1#;
		next unless -f "$git_dir/$id/info/url";
		my $new_ref = "refs/remotes/$id";
		if (::verify_ref("$new_ref^0")) {
			print STDERR "W: $orig_ref is probably an old ",
			             "branch used by an ancient version of ",
				     "git-svn.\n",
				     "However, $new_ref also exists.\n",
				     "We will not be able ",
				     "to use this branch until this ",
				     "ambiguity is resolved.\n";
			next;
		}
		print STDERR "Migrating from v0 layout...\n" if !$migrated;
		print STDERR "Renaming ref: $orig_ref => $new_ref\n";
		command_noisy('update-ref', $new_ref, $orig_ref);
		command_noisy('update-ref', '-d', $orig_ref, $orig_ref);
		$migrated++;
	}
	command_close_pipe($fh, $ctx);
	print STDERR "Done migrating from v0 layout...\n" if $migrated;
	$migrated;
}

sub migrate_from_v1 {
	my $git_dir = $ENV{GIT_DIR};
	my $migrated = 0;
	return $migrated unless -d $git_dir;
	my $svn_dir = "$git_dir/svn";

	# just in case somebody used 'svn' as their $id at some point...
	return $migrated if -d $svn_dir && ! -f "$svn_dir/info/url";

	print STDERR "Migrating from a git-svn v1 layout...\n";
	mkpath([$svn_dir]);
	print STDERR "Data from a previous version of git-svn exists, but\n\t",
	             "$svn_dir\n\t(required for this version ",
	             "($::VERSION) of git-svn) does not. exist\n";
	my ($fh, $ctx) = command_output_pipe(qw/rev-parse --symbolic --all/);
	while (<$fh>) {
		my $x = $_;
		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 $dn;
		if ($x eq 'svn') { # they used 'svn' as GIT_SVN_ID:
			mkpath(["$git_dir/svn/svn"]);
			print STDERR " - $git_dir/$x/info => ",
			                "$git_dir/svn/$x/info\n";
			rename "$git_dir/$x/info", "$git_dir/svn/$x/info" or
			       croak "$!: $x";
			# don't worry too much about these, they probably
			# don't exist with repos this old (save for index,
			# and we can easily regenerate that)
			foreach my $f (qw/unhandled.log index .rev_db/) {
				rename "$git_dir/$x/$f", "$git_dir/svn/$x/$f";
			}
		} else {
			print STDERR " - $git_dir/$x => $git_dir/svn/$x\n";
			rename "$git_dir/$x", "$git_dir/svn/$x" or
			       croak "$!: $x";
		}
		$migrated++;
	}
	command_close_pipe($fh, $ctx);
	print STDERR "Done migrating from a git-svn v1 layout\n";
	$migrated;
}

sub read_old_urls {
	my ($l_map, $pfx, $path) = @_;
	my @dir;
	foreach (<$path/*>) {
		if (-r "$_/info/url") {
			$pfx .= '/' if $pfx && $pfx !~ m!/$!;
			my $ref_id = $pfx . basename $_;
			my $url = ::file_to_s("$_/info/url");
			$l_map->{$ref_id} = $url;
		} elsif (-d $_) {
			push @dir, $_;
		}
	}
	foreach (@dir) {
		my $x = $_;
		$x =~ s!^\Q$ENV{GIT_DIR}\E/svn/!!o;
		read_old_urls($l_map, $x, $_);
	}
}

sub migrate_from_v2 {
	my @cfg = command(qw/config -l/);
	return if grep /^svn-remote\..+\.url=/, @cfg;
	my %l_map;
	read_old_urls(\%l_map, '', "$ENV{GIT_DIR}/svn");
	my $migrated = 0;

	foreach my $ref_id (sort keys %l_map) {
3488 3489 3490 3491
		eval { Git::SVN->init($l_map{$ref_id}, '', undef, $ref_id) };
		if ($@) {
			Git::SVN->init($l_map{$ref_id}, '', $ref_id, $ref_id);
		}
3492 3493 3494 3495 3496
		$migrated++;
	}
	$migrated;
}

3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515
sub minimize_connections {
	my $r = Git::SVN::read_all_remotes();
	my $new_urls = {};
	my $root_repos = {};
	foreach my $repo_id (keys %$r) {
		my $url = $r->{$repo_id}->{url} or next;
		my $fetch = $r->{$repo_id}->{fetch} or next;
		my $ra = Git::SVN::Ra->new($url);

		# skip existing cases where we already connect to the root
		if (($ra->{url} eq $ra->{repos_root}) ||
		    (Git::SVN::sanitize_remote_name($ra->{repos_root}) eq
		     $repo_id)) {
			$root_repos->{$ra->{url}} = $repo_id;
			next;
		}

		my $root_ra = Git::SVN::Ra->new($ra->{repos_root});
		my $root_path = $ra->{url};
3516
		$root_path =~ s#^\Q$ra->{repos_root}\E(/|$)##;
3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558
		foreach my $path (keys %$fetch) {
			my $ref_id = $fetch->{$path};
			my $gs = Git::SVN->new($ref_id, $repo_id, $path);

			# make sure we can read when connecting to
			# a higher level of a repository
			my ($last_rev, undef) = $gs->last_rev_commit;
			if (!defined $last_rev) {
				$last_rev = eval {
					$root_ra->get_latest_revnum;
				};
				next if $@;
			}
			my $new = $root_path;
			$new .= length $path ? "/$path" : '';
			eval {
				$root_ra->get_log([$new], $last_rev, $last_rev,
			                          0, 0, 1, sub { });
			};
			next if $@;
			$new_urls->{$ra->{repos_root}}->{$new} =
			        { ref_id => $ref_id,
				  old_repo_id => $repo_id,
				  old_path => $path };
		}
	}

	my @emptied;
	foreach my $url (keys %$new_urls) {
		# see if we can re-use an existing [svn-remote "repo_id"]
		# instead of creating a(n ugly) new section:
		my $repo_id = $root_repos->{$url} ||
		              Git::SVN::sanitize_remote_name($url);

		my $fetch = $new_urls->{$url};
		foreach my $path (keys %$fetch) {
			my $x = $fetch->{$path};
			Git::SVN->init($url, $path, $repo_id, $x->{ref_id});
			my $pfx = "svn-remote.$x->{old_repo_id}";

			my $old_fetch = quotemeta("$x->{old_path}:".
			                          "refs/remotes/$x->{ref_id}");
3559
			command_noisy(qw/config --unset/,
3560 3561 3562 3563
			              "$pfx.fetch", '^'. $old_fetch . '$');
			delete $r->{$x->{old_repo_id}}->
			       {fetch}->{$x->{old_path}};
			if (!keys %{$r->{$x->{old_repo_id}}->{fetch}}) {
3564
				command_noisy(qw/config --unset/,
3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580
				              "$pfx.url");
				push @emptied, $x->{old_repo_id}
			}
		}
	}
	if (@emptied) {
		my $file = $ENV{GIT_CONFIG} || $ENV{GIT_CONFIG_LOCAL} ||
		           "$ENV{GIT_DIR}/config";
		print STDERR <<EOF;
The following [svn-remote] sections in your config file ($file) are empty
and can be safely removed:
EOF
		print STDERR "[svn-remote \"$_\"]\n" foreach @emptied;
	}
}

3581 3582 3583 3584
sub migration_check {
	migrate_from_v0();
	migrate_from_v1();
	migrate_from_v2();
3585
	minimize_connections() if $_minimize;
3586 3587
}

3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619
package Git::IndexInfo;
use strict;
use warnings;
use Git qw/command_input_pipe command_close_pipe/;

sub new {
	my ($class) = @_;
	my ($gui, $ctx) = command_input_pipe(qw/update-index -z --index-info/);
	bless { gui => $gui, ctx => $ctx, nr => 0}, $class;
}

sub remove {
	my ($self, $path) = @_;
	if (print { $self->{gui} } '0 ', 0 x 40, "\t", $path, "\0") {
		return ++$self->{nr};
	}
	undef;
}

sub update {
	my ($self, $mode, $hash, $path) = @_;
	if (print { $self->{gui} } $mode, ' ', $hash, "\t", $path, "\0") {
		return ++$self->{nr};
	}
	undef;
}

sub DESTROY {
	my ($self) = @_;
	command_close_pipe($self->{gui}, $self->{ctx});
}

3620 3621 3622 3623 3624 3625 3626 3627
package Git::SVN::GlobSpec;
use strict;
use warnings;

sub new {
	my ($class, $glob) = @_;
	my $re = $glob;
	$re =~ s!/+$!!g; # no need for trailing slashes
3628
	my $nr = ($re =~ s!^(.*)\*(.*)$!\(\[^/\]+\)!g);
3629 3630
	my ($left, $right) = ($1, $2);
	if ($nr > 1) {
3631 3632
		die "Only one '*' wildcard expansion ",
		    "is supported (got $nr): '$glob'\n";
3633
	} elsif ($nr == 0) {
3634
		die "One '*' is needed for glob: '$glob'\n";
3635 3636
	}
	$re = quotemeta($left) . $re . quotemeta($right);
3637 3638 3639 3640 3641 3642
	if (length $left && !($left =~ s!/+$!!g)) {
		die "Missing trailing '/' on left side of: '$glob' ($left)\n";
	}
	if (length $right && !($right =~ s!^/+!!g)) {
		die "Missing leading '/' on right side of: '$glob' ($right)\n";
	}
3643 3644
	my $left_re = qr/^\/\Q$left\E(\/|$)/;
	bless { left => $left, right => $right, left_regex => $left_re,
3645 3646 3647 3648 3649 3650 3651 3652 3653
	        regex => qr/$re/, glob => $glob }, $class;
}

sub full_path {
	my ($self, $path) = @_;
	return (length $self->{left} ? "$self->{left}/" : '') .
	       $path . (length $self->{right} ? "/$self->{right}" : '');
}

E
Eric Wong 已提交
3654 3655 3656 3657
__END__

Data structures:

3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684

$remotes = { # returned by read_all_remotes()
	'svn' => {
		# svn-remote.svn.url=https://svn.musicpd.org
		url => 'https://svn.musicpd.org',
		# svn-remote.svn.fetch=mpd/trunk:trunk
		fetch => {
			'mpd/trunk' => 'trunk',
		},
		# svn-remote.svn.tags=mpd/tags/*:tags/*
		tags => {
			path => {
				left => 'mpd/tags',
				right => '',
				regex => qr!mpd/tags/([^/]+)$!,
				glob => 'tags/*',
			},
			ref => {
				left => 'tags',
				right => '',
				regex => qr!tags/([^/]+)$!,
				glob => 'tags/*',
			},
		}
	}
};

3685
$log_entry hashref as returned by libsvn_log_entry()
E
Eric Wong 已提交
3686
{
3687
	log => 'whitespace-formatted log entry
E
Eric Wong 已提交
3688 3689 3690 3691 3692 3693
',						# trailing newline is preserved
	revision => '8',			# integer
	date => '2004-02-24T17:01:44.108345Z',	# commit date
	author => 'committer name'
};

3694 3695

# this is generated by generate_diff();
E
Eric Wong 已提交
3696 3697 3698 3699 3700 3701 3702 3703
@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,
3704
	chg => change type [MCRADT],
E
Eric Wong 已提交
3705 3706 3707 3708
	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)
}
;
3709

3710 3711 3712 3713 3714 3715 3716 3717 3718 3719
# 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',
	},
}

3720 3721 3722
Notes:
	I don't trust the each() function on unless I created %hash myself
	because the internal iterator may not have started at base.