git-svn.perl 115.5 KB
Newer Older
E
Eric Wong 已提交
1
#!/usr/bin/env perl
2 3
# Copyright (C) 2006, Eric Wong <normalperson@yhbt.net>
# License: GPL v2 or later
E
Eric Wong 已提交
4 5 6
use warnings;
use strict;
use vars qw/	$AUTHOR $VERSION
7 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
my $git_dir_user_set = 1 if defined $ENV{GIT_DIR};
13
$ENV{GIT_DIR} ||= '.git';
14
$Git::SVN::default_repo_id = 'svn';
15
$Git::SVN::default_ref_id = $ENV{GIT_SVN_ID} || 'git-svn';
16
$Git::SVN::Ra::_log_window_size = 100;
17

18
$Git::SVN::Log::TZ = $ENV{TZ};
E
Eric Wong 已提交
19
$ENV{TZ} = 'UTC';
20
$| = 1; # unbuffer STDOUT
E
Eric Wong 已提交
21

22
sub fatal (@) { print STDERR @_; exit 1 }
23 24 25 26 27 28
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";
}
29
push @Git::SVN::Ra::ISA, 'SVN::Ra';
30 31
push @SVN::Git::Editor::ISA, 'SVN::Delta::Editor';
push @SVN::Git::Fetcher::ISA, 'SVN::Delta::Editor';
E
Eric Wong 已提交
32 33 34 35
use Carp qw/croak/;
use IO::File qw//;
use File::Basename qw/dirname basename/;
use File::Path qw/mkpath/;
36
use Getopt::Long qw/:config gnu_getopt no_ignore_case auto_abbrev/;
37
use IPC::Open3;
38
use Git;
39

40
BEGIN {
41 42
	# import functions from Git into our packages, en masse
	no strict 'refs';
43 44
	foreach (qw/command command_oneline command_noisy command_output_pipe
	            command_input_pipe command_close_pipe/) {
45 46 47 48 49
		for my $package ( qw(SVN::Git::Editor SVN::Git::Fetcher
			Git::SVN::Migration Git::SVN::Log Git::SVN),
			__PACKAGE__) {
			*{"${package}::$_"} = \&{"Git::$_"};
		}
50 51 52
	}
}

53
my ($SVN);
54

55 56
$sha1 = qr/[a-f\d]{40}/;
$sha1_short = qr/[a-f\d]{4,40}/;
57
my ($_stdin, $_help, $_edit,
58
	$_message, $_file,
59
	$_template, $_shared,
60
	$_version, $_fetch_all, $_no_rebase,
61
	$_merge, $_strategy, $_dry_run, $_local,
E
Eric Wong 已提交
62
	$_prefix, $_no_checkout, $_verbose);
63
$Git::SVN::_follow_parent = 1;
64 65 66
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 );
67
my %fc_opts = ( 'follow-parent|follow!' => \$Git::SVN::_follow_parent,
68
		'authors-file|A=s' => \$_authors,
E
Eric Wong 已提交
69
		'repack:i' => \$Git::SVN::_repack,
70 71
		'noMetadata' => \$Git::SVN::_no_metadata,
		'useSvmProps' => \$Git::SVN::_use_svm_props,
72
		'useSvnsyncProps' => \$Git::SVN::_use_svnsync_props,
73
		'log-window-size=i' => \$Git::SVN::Ra::_log_window_size,
74
		'no-checkout' => \$_no_checkout,
75
		'quiet|q' => \$_q,
E
Eric Wong 已提交
76 77
		'repack-flags|repack-args|repack-opts=s' =>
		   \$Git::SVN::_repack_flags,
78
		%remote_opts );
79

80
my ($_trunk, $_tags, $_branches, $_stdlayout);
81
my %icv;
82 83 84
my %init_opts = ( 'template=s' => \$_template, 'shared:s' => \$_shared,
                  'trunk|T=s' => \$_trunk, 'tags|t=s' => \$_tags,
                  'branches|b=s' => \$_branches, 'prefix=s' => \$_prefix,
85
                  'stdlayout|s' => \$_stdlayout,
86
                  'minimize-url|m' => \$Git::SVN::_minimize_url,
87 88 89 90
		  'no-metadata' => sub { $icv{noMetadata} = 1 },
		  'use-svm-props' => sub { $icv{useSvmProps} = 1 },
		  'use-svnsync-props' => sub { $icv{useSvnsyncProps} = 1 },
		  'rewrite-root=s' => sub { $icv{rewriteRoot} = $_[1] },
91
                  %remote_opts );
E
Eric Wong 已提交
92
my %cmt_opts = ( 'edit|e' => \$_edit,
93 94 95 96
		'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
97
);
98

E
Eric Wong 已提交
99
my %cmd = (
100
	fetch => [ \&cmd_fetch, "Download new revisions from SVN",
101
			{ 'revision|r=s' => \$_revision,
E
Eric Wong 已提交
102
			  'fetch-all|all' => \$_fetch_all,
103
			   %fc_opts } ],
104 105 106
	clone => [ \&cmd_clone, "Initialize and fetch revisions",
			{ 'revision|r=s' => \$_revision,
			   %fc_opts, %init_opts } ],
107
	init => [ \&cmd_init, "Initialize a repo for tracking" .
108
			  " (requires URL argument)",
109
			  \%init_opts ],
110 111 112 113
	'multi-init' => [ \&cmd_multi_init,
	                  "Deprecated alias for ".
			  "'$0 init -T<trunk> -b<branches> -t<tags>'",
			  \%init_opts ],
114 115
	dcommit => [ \&cmd_dcommit,
	             'Commit several diffs to merge with upstream',
116 117
			{ 'merge|m|M' => \$_merge,
			  'strategy|s=s' => \$_strategy,
E
Eric Wong 已提交
118
			  'verbose|v' => \$_verbose,
119
			  'dry-run|n' => \$_dry_run,
E
Eric Wong 已提交
120
			  'fetch-all|all' => \$_fetch_all,
121
			  'no-rebase' => \$_no_rebase,
122
			%cmt_opts, %fc_opts } ],
123 124 125
	'set-tree' => [ \&cmd_set_tree,
	                "Set an SVN repository to a git tree-ish",
			{ 'stdin|' => \$_stdin, %cmt_opts, %fc_opts, } ],
126
	'show-ignore' => [ \&cmd_show_ignore, "Show svn:ignore listings",
127
			{ 'revision|r=i' => \$_revision } ],
128
	'multi-fetch' => [ \&cmd_multi_fetch,
129 130
	                   "Deprecated alias for $0 fetch --all",
			   { 'revision|r=s' => \$_revision, %fc_opts } ],
131 132 133 134
	'migrate' => [ sub { },
	               # no-op, we automatically run this anyways,
	               'Migrate configuration/metadata/layout from
		        previous versions of git-svn',
135 136
                       { 'minimize' => \$Git::SVN::Migration::_minimize,
			 %remote_opts } ],
137 138
	'log' => [ \&Git::SVN::Log::cmd_show_log, 'Show commit logs',
			{ 'limit=i' => \$Git::SVN::Log::limit,
139
			  'revision|r=s' => \$_revision,
140 141 142 143 144
			  '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,
145
			  'authors-file|A=s' => \$_authors,
146 147
			  'color' => \$Git::SVN::Log::color,
			  'pager=s' => \$Git::SVN::Log::pager,
148
			} ],
A
Adam Roben 已提交
149 150
	'find-rev' => [ \&cmd_find_rev, "Translate between SVN revision numbers and tree-ish",
			{ } ],
E
Eric Wong 已提交
151 152 153 154
	'rebase' => [ \&cmd_rebase, "Fetch and rebase your working directory",
			{ 'merge|m|M' => \$_merge,
			  'verbose|v' => \$_verbose,
			  'strategy|s=s' => \$_strategy,
155
			  'local|l' => \$_local,
E
Eric Wong 已提交
156 157
			  'fetch-all|all' => \$_fetch_all,
			  %fc_opts } ],
158 159
	'commit-diff' => [ \&cmd_commit_diff,
	                   'Commit a diff between two trees',
E
Eric Wong 已提交
160 161
			{ 'message|m=s' => \$_message,
			  'file|F=s' => \$_file,
162
			  'revision|r=s' => \$_revision,
E
Eric Wong 已提交
163
			%cmt_opts } ],
E
Eric Wong 已提交
164
);
165

E
Eric Wong 已提交
166 167 168 169 170 171 172 173 174
my $cmd;
for (my $i = 0; $i < @ARGV; $i++) {
	if (defined $cmd{$ARGV[$i]}) {
		$cmd = $ARGV[$i];
		splice @ARGV, $i, 1;
		last;
	}
};

175
my %opts = %{$cmd{$cmd}->[2]} if (defined $cmd);
176

177
read_repo_config(\%opts);
178
Getopt::Long::Configure('pass_through') if ($cmd && $cmd eq 'log');
179 180 181
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,
182 183 184
                    'svn-remote|remote|R=s' => sub {
                       $Git::SVN::no_reuse_existing = 1;
                       $Git::SVN::default_repo_id = $_[1] });
185
exit 1 if (!$rv && $cmd && $cmd ne 'log');
186

E
Eric Wong 已提交
187
usage(0) if $_help;
188
version() if $_version;
189 190
usage(1) unless defined $cmd;
load_authors() if $_authors;
191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212

# make sure we're always running
unless ($cmd =~ /(?:clone|init|multi-init)$/) {
	unless (-d $ENV{GIT_DIR}) {
		if ($git_dir_user_set) {
			die "GIT_DIR=$ENV{GIT_DIR} explicitly set, ",
			    "but it is not a directory\n";
		}
		my $git_dir = delete $ENV{GIT_DIR};
		chomp(my $cdup = command_oneline(qw/rev-parse --show-cdup/));
		unless (length $cdup) {
			die "Already at toplevel, but $git_dir ",
			    "not found '$cdup'\n";
		}
		chdir $cdup or die "Unable to chdir up to '$cdup'\n";
		unless (-d $git_dir) {
			die "$git_dir still not found after going to ",
			    "'$cdup'\n";
		}
		$ENV{GIT_DIR} = $git_dir;
	}
}
213
unless ($cmd =~ /^(?:clone|init|multi-init|commit-diff)$/) {
214 215
	Git::SVN::Migration::migration_check();
}
E
Eric Wong 已提交
216
Git::SVN::init_vars();
217 218 219 220 221
eval {
	Git::SVN::verify_remotes_sanity();
	$cmd{$cmd}->[0]->(@ARGV);
};
fatal $@ if $@;
222
post_fetch_checkout();
E
Eric Wong 已提交
223 224 225 226 227 228 229 230 231
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
232 233

	print $fd "Available commands:\n" unless $cmd;
E
Eric Wong 已提交
234 235

	foreach (sort keys %cmd) {
236
		next if $cmd && $cmd ne $_;
237
		next if /^multi-/; # don't show deprecated commands
238
		print $fd '  ',pack('A17',$_),$cmd{$_}->[1],"\n";
239
		foreach (keys %{$cmd{$_}->[2]}) {
240 241
			# mixed-case options are for .git/config only
			next if /[A-Z]/ && /^[a-z]+$/i;
242
			# prints out arguments as they should be passed:
243
			my $x = s#[:=]s$## ? '<arg>' : s#[:=]i$## ? '<num>' : '';
244
			print $fd ' ' x 21, join(', ', map { length $_ > 1 ?
245 246 247
							"--$_" : "-$_" }
						split /\|/,$_)," $x\n";
		}
E
Eric Wong 已提交
248 249
	}
	print $fd <<"";
250 251 252 253
\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
254 255 256 257

	exit $exit;
}

258
sub version {
259
	print "git-svn version $VERSION (svn $SVN::Core::VERSION)\n";
260 261 262
	exit 0;
}

263 264 265 266
sub do_git_init_db {
	unless (-d $ENV{GIT_DIR}) {
		my @init_db = ('init');
		push @init_db, "--template=$_template" if defined $_template;
267 268 269 270 271 272 273
		if (defined $_shared) {
			if ($_shared =~ /[a-z]/) {
				push @init_db, "--shared=$_shared";
			} else {
				push @init_db, "--shared";
			}
		}
274 275
		command_noisy(@init_db);
	}
276 277 278 279 280 281 282 283
	my $set;
	my $pfx = "svn-remote.$Git::SVN::default_repo_id";
	foreach my $i (keys %icv) {
		die "'$set' and '$i' cannot both be set\n" if $set;
		next unless defined $icv{$i};
		command_noisy('config', "$pfx.$i", $icv{$i});
		$set = $i;
	}
284 285
}

286 287 288 289
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";
290
	$ENV{GIT_DIR} = '.git';
291 292
}

293 294 295
sub cmd_clone {
	my ($url, $path) = @_;
	if (!defined $path &&
296 297
	    (defined $_trunk || defined $_branches || defined $_tags ||
	     defined $_stdlayout) &&
298 299 300 301
	    $url !~ m#^[a-z\+]+://#) {
		$path = $url;
	}
	$path = basename($url) if !defined $path || !length $path;
302
	cmd_init($url, $path);
303 304 305
	Git::SVN::fetch_all($Git::SVN::default_repo_id);
}

306
sub cmd_init {
307 308 309 310 311
	if (defined $_stdlayout) {
		$_trunk = 'trunk' if (!defined $_trunk);
		$_tags = 'tags' if (!defined $_tags);
		$_branches = 'branches' if (!defined $_branches);
	}
312 313
	if (defined $_trunk || defined $_branches || defined $_tags) {
		return cmd_multi_init(@_);
314
	}
315 316 317
	my $url = shift or die "SVN repository location required ",
	                       "as a command-line argument\n";
	init_subdir(@_);
318
	do_git_init_db();
319

320
	Git::SVN->init($url);
E
Eric Wong 已提交
321 322
}

323
sub cmd_fetch {
324 325 326
	if (grep /^\d+=./, @_) {
		die "'<rev>=<commit>' fetch arguments are ",
		    "no longer supported.\n";
327
	}
328 329
	my ($remote) = @_;
	if (@_ > 1) {
E
Eric Wong 已提交
330
		die "Usage: $0 fetch [--all] [svn-remote]\n";
331 332 333 334 335 336
	}
	$remote ||= $Git::SVN::default_repo_id;
	if ($_fetch_all) {
		cmd_multi_fetch();
	} else {
		Git::SVN::fetch_all($remote, Git::SVN::read_all_remotes());
337
	}
338 339
}

340
sub cmd_set_tree {
E
Eric Wong 已提交
341 342 343 344 345
	my (@commits) = @_;
	if ($_stdin || !@commits) {
		print "Reading from stdin...\n";
		@commits = ();
		while (<STDIN>) {
346
			if (/\b($sha1_short)\b/o) {
E
Eric Wong 已提交
347 348 349 350 351
				unshift @commits, $1;
			}
		}
	}
	my @revs;
352
	foreach my $c (@commits) {
E
Eric Wong 已提交
353
		my @tmp = command('rev-parse',$c);
354 355 356
		if (scalar @tmp == 1) {
			push @revs, $tmp[0];
		} elsif (scalar @tmp > 1) {
E
Eric Wong 已提交
357
			push @revs, reverse(command('rev-list',@tmp));
358
		} else {
359
			fatal "Failed to rev-parse $c\n";
360
		}
E
Eric Wong 已提交
361
	}
362 363 364
	my $gs = Git::SVN->new;
	my ($r_last, $cmt_last) = $gs->last_rev_commit;
	$gs->fetch;
365
	if (defined $gs->{last_rev} && $r_last != $gs->{last_rev}) {
366 367 368 369
		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";
370
	}
371 372
	$gs->set_tree($_) foreach @revs;
	print "Done committing ",scalar @revs," revisions to SVN\n";
373
}
374

375 376 377
sub cmd_dcommit {
	my $head = shift;
	$head ||= 'HEAD';
378
	my @refs;
379
	my ($url, $rev, $uuid, $gs) = working_head_info($head, \@refs);
380
	print "Committing to $url ...\n";
381
	unless ($gs) {
382
		die "Unable to determine upstream SVN information from ",
E
Eric Wong 已提交
383
		    "$head history\n";
384
	}
385
	my $last_rev;
386
	my ($linear_refs, $parents) = linearize_history($gs, \@refs);
387 388 389 390 391 392
	if ($_no_rebase && scalar(@$linear_refs) > 1) {
		warn "Attempting to commit more than one change while ",
		     "--no-rebase is enabled.\n",
		     "If these changes depend on each other, re-running ",
		     "without --no-rebase will be required."
	}
393
	foreach my $d (@$linear_refs) {
394 395 396
		unless (defined $last_rev) {
			(undef, $last_rev, undef) = cmt_metadata("$d~1");
			unless (defined $last_rev) {
397 398
				fatal "Unable to extract revision information ",
				      "from commit $d~1\n";
399 400
			}
		}
E
Eric Wong 已提交
401 402 403
		if ($_dry_run) {
			print "diff-tree $d~1 $d\n";
		} else {
404
			my $cmt_rev;
405
			my %ed_opts = ( r => $last_rev,
406
			                log => get_commit_entry($d)->{log},
407
			                ra => Git::SVN::Ra->new($gs->full_url),
408 409 410 411
			                tree_a => "$d~1",
			                tree_b => $d,
			                editor_cb => sub {
			                       print "Committed r$_[0]\n";
412 413
			                       $cmt_rev = $_[0];
			                },
414
			                svn_path => '');
415
			if (!SVN::Git::Editor->new(\%ed_opts)->apply_diff) {
416
				print "No changes\n$d~1 == $d\n";
417
			} elsif ($parents->{$d} && @{$parents->{$d}}) {
418
				$gs->{inject_parents_dcommit}->{$cmt_rev} =
419
				                               $parents->{$d};
420
			}
421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442
			$_fetch_all ? $gs->fetch_all : $gs->fetch;
			next if $_no_rebase;

			# 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, '--');
			my @finish;
			if (@diff) {
				@finish = rebase_cmd();
				print STDERR "W: HEAD and ", $gs->refname,
				             " differ, using @finish:\n",
				             "@diff";
			} else {
				print "No changes between current HEAD and ",
				      $gs->refname,
				      "\nResetting to the latest ",
				      $gs->refname, "\n";
				@finish = qw/reset --mixed/;
			}
			command_noisy(@finish, $gs->refname);
			$last_rev = $cmt_rev;
E
Eric Wong 已提交
443 444 445 446
		}
	}
}

A
Adam Roben 已提交
447 448 449 450
sub cmd_find_rev {
	my $revision_or_hash = shift;
	my $result;
	if ($revision_or_hash =~ /^r\d+$/) {
A
Adam Roben 已提交
451 452 453 454 455 456 457
		my $head = shift;
		$head ||= 'HEAD';
		my @refs;
		my (undef, undef, undef, $gs) = working_head_info($head, \@refs);
		unless ($gs) {
			die "Unable to determine upstream SVN information from ",
			    "$head history\n";
A
Adam Roben 已提交
458
		}
A
Adam Roben 已提交
459 460
		my $desired_revision = substr($revision_or_hash, 1);
		$result = $gs->rev_db_get($desired_revision);
A
Adam Roben 已提交
461 462 463 464 465 466 467
	} else {
		my (undef, $rev, undef) = cmt_metadata($revision_or_hash);
		$result = $rev;
	}
	print "$result\n" if $result;
}

E
Eric Wong 已提交
468 469
sub cmd_rebase {
	command_noisy(qw/update-index --refresh/);
470 471
	my ($url, $rev, $uuid, $gs) = working_head_info('HEAD');
	unless ($gs) {
E
Eric Wong 已提交
472 473 474 475 476 477 478 479
		die "Unable to determine upstream SVN information from ",
		    "working tree history\n";
	}
	if (command(qw/diff-index HEAD --/)) {
		print STDERR "Cannot rebase with uncommited changes:\n";
		command_noisy('status');
		exit 1;
	}
480 481 482
	unless ($_local) {
		$_fetch_all ? $gs->fetch_all : $gs->fetch;
	}
E
Eric Wong 已提交
483 484 485
	command_noisy(rebase_cmd(), $gs->refname);
}

486
sub cmd_show_ignore {
487 488
	my ($url, $rev, $uuid, $gs) = working_head_info('HEAD');
	$gs ||= Git::SVN->new;
489
	my $r = (defined $_revision ? $_revision : $gs->ra->get_latest_revnum);
490
	$gs->traverse_ignore(\*STDOUT, $gs->{path}, $r);
491 492
}

493
sub cmd_multi_init {
494
	my $url = shift;
495 496
	unless (defined $_trunk || defined $_branches || defined $_tags) {
		usage(1);
497
	}
498 499 500 501 502

	# there are currently some bugs that prevent multi-init/multi-fetch
	# setups from working well without this.
	$Git::SVN::_minimize_url = 1;

503
	$_prefix = '' unless defined $_prefix;
504 505 506 507
	if (defined $url) {
		$url =~ s#/+$##;
		init_subdir(@_);
	}
508
	do_git_init_db();
509
	if (defined $_trunk) {
510 511 512
		my $trunk_ref = $_prefix . 'trunk';
		# try both old-style and new-style lookups:
		my $gs_trunk = eval { Git::SVN->new($trunk_ref) };
513
		unless ($gs_trunk) {
514 515 516 517
			my ($trunk_url, $trunk_path) =
			                      complete_svn_url($url, $_trunk);
			$gs_trunk = Git::SVN->init($trunk_url, $trunk_path,
						   undef, $trunk_ref);
518
		}
519
	}
520
	return unless defined $_branches || defined $_tags;
521 522 523
	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/');
524 525
}

526
sub cmd_multi_fetch {
527 528
	my $remotes = Git::SVN::read_all_remotes();
	foreach my $repo_id (sort keys %$remotes) {
529
		if ($remotes->{$repo_id}->{url}) {
530 531
			Git::SVN::fetch_all($repo_id, $remotes);
		}
532 533 534
	}
}

535 536 537 538 539 540
# 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);
541
	my $svn_path;
542 543 544 545 546 547 548
	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};
549
		$svn_path = $gs->{path};
550 551 552 553 554 555 556 557 558 559 560 561 562 563 564
	}
	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);
565
	$svn_path ||= $ra->{svn_path};
566 567 568 569 570 571
	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";
	}
572 573 574 575 576 577 578 579
	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 => $svn_path );
	if (!SVN::Git::Editor->new(\%ed_opts)->apply_diff) {
580 581 582 583
		print "No changes\n$ta == $tb\n";
	}
}

E
Eric Wong 已提交
584 585
########################### utility functions #########################

E
Eric Wong 已提交
586 587 588 589 590 591 592 593
sub rebase_cmd {
	my @cmd = qw/rebase/;
	push @cmd, '-v' if $_verbose;
	push @cmd, qw/--merge/ if $_merge;
	push @cmd, "--strategy=$_strategy" if $_strategy;
	@cmd;
}

594 595 596 597 598 599 600 601 602 603 604 605 606
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;

607
	return if command_oneline(qw/rev-parse --is-inside-work-tree/) eq 'false';
608 609 610 611 612 613
	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";
}

614 615 616 617 618 619 620 621
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");
		}
622
		return ($url, $path);
623
	}
624
	return ($path, '');
625 626
}

627
sub complete_url_ls_init {
628 629
	my ($ra, $repo_path, $switch, $pfx) = @_;
	unless ($repo_path) {
630 631 632
		print STDERR "W: $switch not specified\n";
		return;
	}
633 634 635 636
	$repo_path =~ s#/+$##;
	if ($repo_path =~ m#^[a-z\+]+://#) {
		$ra = Git::SVN::Ra->new($repo_path);
		$repo_path = '';
637
	} else {
638
		$repo_path =~ s#^/+##;
639
		unless ($ra) {
640
			fatal("E: '$repo_path' is not a complete URL ",
641
			      "and a separate URL is not specified\n");
642
		}
643
	}
644
	my $url = $ra->{url};
645 646 647 648 649 650
	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";
651
	}
652 653 654 655 656 657 658
	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='$pfx' must have a trailing slash '/'\n";
659
	}
660 661
	command_noisy('config', "svn-remote.$gs->{repo_id}.$n",
				"$remote_path:refs/remotes/$pfx*");
662 663
}

E
Eric Wong 已提交
664 665
sub verify_ref {
	my ($ref) = @_;
666 667
	eval { command_oneline([ 'rev-parse', '--verify', $ref ],
	                       { STDERR => 0 }); };
E
Eric Wong 已提交
668 669
}

670
sub get_tree_from_treeish {
671
	my ($treeish) = @_;
672
	# $treeish can be a symbolic ref, too:
E
Eric Wong 已提交
673
	my $type = command_oneline(qw/cat-file -t/, $treeish);
674 675
	my $expected;
	while ($type eq 'tag') {
E
Eric Wong 已提交
676
		($treeish, $type) = command(qw/cat-file tag/, $treeish);
677 678
	}
	if ($type eq 'commit') {
E
Eric Wong 已提交
679 680
		$expected = (grep /^tree /, command(qw/cat-file commit/,
		                                    $treeish))[0];
681
		($expected) = ($expected =~ /^tree ($sha1)$/o);
682 683 684 685 686 687
		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";
	}
688 689 690
	return $expected;
}

691 692 693 694 695 696
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
697

698
	my $type = command_oneline(qw/cat-file -t/, $treeish);
699
	if ($type eq 'commit' || $type eq 'tag') {
E
Eric Wong 已提交
700
		my ($msg_fh, $ctx) = command_output_pipe('cat-file',
701
		                                         $type, $treeish);
E
Eric Wong 已提交
702 703 704 705
		my $in_msg = 0;
		while (<$msg_fh>) {
			if (!$in_msg) {
				$in_msg = 1 if (/^\s*$/);
706
			} elsif (/^git-svn-id: /) {
707 708 709
				# 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
710
			} else {
711
				print $log_fh $_ or croak $!;
E
Eric Wong 已提交
712 713
			}
		}
E
Eric Wong 已提交
714
		command_close_pipe($msg_fh, $ctx);
E
Eric Wong 已提交
715
	}
716
	close $log_fh or croak $!;
E
Eric Wong 已提交
717 718 719

	if ($_edit || ($type eq 'tree')) {
		my $editor = $ENV{VISUAL} || $ENV{EDITOR} || 'vi';
720 721
		# TODO: strip out spaces, comments, like git-commit.sh
		system($editor, $commit_editmsg);
E
Eric Wong 已提交
722
	}
723 724 725 726 727 728
	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;
729 730
}

E
Eric Wong 已提交
731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748
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;
}

749 750 751
# '<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";
752
	my $log = $cmd eq 'log';
753 754
	while (<$authors>) {
		chomp;
755
		next unless /^(.+?|\(no author\))\s*=\s*(.+?)\s*<(.+)>\s*$/;
756
		my ($user, $name, $email) = ($1, $2, $3);
757 758 759 760 761
		if ($log) {
			$Git::SVN::Log::rusers{"$name <$email>"} = $user;
		} else {
			$users{$user} = [$name, $email];
		}
762 763 764 765
	}
	close $authors or croak $!;
}

766
# convert GetOpt::Long specs for use by git-config
767
sub read_repo_config {
768
	return unless -d $ENV{GIT_DIR};
769
	my $opts = shift;
770
	my @config_only;
771
	foreach my $o (keys %$opts) {
772 773 774 775
		# 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);
776
		my $v = $opts->{$o};
777
		my ($key) = ($o =~ /^([a-zA-Z\-]+)/);
778
		$key =~ s/-//g;
779
		my $arg = 'git-config';
780 781 782 783 784 785 786
		$arg .= ' --int' if ($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.$key`);
787
			if ($tmp && !($arg =~ / --bool/ && $tmp eq 'false')) {
788 789 790 791
				$$v = $tmp;
			}
		}
	}
792
	delete @$opts{@config_only} if @config_only;
793 794
}

795
sub extract_metadata {
796
	my $id = shift or return (undef, undef, undef);
797
	my ($url, $rev, $uuid) = ($id =~ /^\s*git-svn-id:\s+(.*)\@(\d+)
798
							\s([a-f\d\-]+)$/x);
799
	if (!defined $rev || !$uuid || !$url) {
800
		# some of the original repositories I made had
801
		# identifiers like this:
802
		($rev, $uuid) = ($id =~/^\s*git-svn-id:\s(\d+)\@([a-f\d\-]+)/);
803 804 805 806
	}
	return ($url, $rev, $uuid);
}

807 808
sub cmt_metadata {
	return extract_metadata((grep(/^git-svn-id: /,
E
Eric Wong 已提交
809
		command(qw/cat-file commit/, shift)))[-1]);
810 811
}

E
Eric Wong 已提交
812 813
sub working_head_info {
	my ($head, $refs) = @_;
814
	my ($fh, $ctx) = command_output_pipe('log', '--no-color', $head);
815
	my $hash;
816
	my %max;
817 818 819 820 821 822 823 824
	while (<$fh>) {
		if ( m{^commit ($::sha1)$} ) {
			unshift @$refs, $hash if $hash and $refs;
			$hash = $1;
			next;
		}
		next unless s{^\s*(git-svn-id:)}{$1};
		my ($url, $rev, $uuid) = extract_metadata($_);
825
		if (defined $url && defined $rev) {
826
			next if $max{$url} and $max{$url} < $rev;
827 828
			if (my $gs = Git::SVN->find_by_url($url)) {
				my $c = $gs->rev_db_get($rev);
829
				if ($c && $c eq $hash) {
830 831
					close $fh; # break the pipe
					return ($url, $rev, $uuid, $gs);
832 833
				} else {
					$max{$url} ||= $gs->rev_db_max;
834 835 836
				}
			}
		}
E
Eric Wong 已提交
837
	}
838 839
	command_close_pipe($fh, $ctx);
	(undef, undef, undef, undef);
E
Eric Wong 已提交
840 841
}

842 843
sub read_commit_parents {
	my ($parents, $c) = @_;
844 845 846
	chomp(my $p = command_oneline(qw/rev-list --parents -1/, $c));
	$p =~ s/^($c)\s*// or die "rev-list --parents -1 $c failed!\n";
	@{$parents->{$c}} = split(/ /, $p);
847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889
}

sub linearize_history {
	my ($gs, $refs) = @_;
	my %parents;
	foreach my $c (@$refs) {
		read_commit_parents(\%parents, $c);
	}

	my @linear_refs;
	my %skip = ();
	my $last_svn_commit = $gs->last_commit;
	foreach my $c (reverse @$refs) {
		next if $c eq $last_svn_commit;
		last if $skip{$c};

		unshift @linear_refs, $c;
		$skip{$c} = 1;

		# we only want the first parent to diff against for linear
		# history, we save the rest to inject when we finalize the
		# svn commit
		my $fp_a = verify_ref("$c~1");
		my $fp_b = shift @{$parents{$c}} if $parents{$c};
		if (!$fp_a || !$fp_b) {
			die "Commit $c\n",
			    "has no parent commit, and therefore ",
			    "nothing to diff against.\n",
			    "You should be working from a repository ",
			    "originally created by git-svn\n";
		}
		if ($fp_a ne $fp_b) {
			die "$c~1 = $fp_a, however parsing commit $c ",
			    "revealed that:\n$c~1 = $fp_b\nBUG!\n";
		}

		foreach my $p (@{$parents{$c}}) {
			$skip{$p} = 1;
		}
	}
	(\@linear_refs, \%parents);
}

890 891 892
package Git::SVN;
use strict;
use warnings;
E
Eric Wong 已提交
893
use vars qw/$default_repo_id $default_ref_id $_no_metadata $_follow_parent
894
            $_repack $_repack_flags $_use_svm_props $_head
895
            $_use_svnsync_props $no_reuse_existing $_minimize_url/;
896 897
use Carp qw/croak/;
use File::Path qw/mkpath/;
898
use File::Copy qw/copy/;
899 900
use IPC::Open3;

E
Eric Wong 已提交
901
my $_repack_nr;
902 903 904 905 906 907 908 909 910
# 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/;
911 912 913 914

	# 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
915 916 917 918
	no strict 'refs';
	for my $option (qw/follow_parent no_metadata use_svm_props
			   use_svnsync_props/) {
		my $key = $option;
919
		$key =~ tr/_//d;
920 921 922 923 924 925 926 927
		my $prop = "-$option";
		*$option = sub {
			my ($self) = @_;
			return $self->{$prop} if exists $self->{$prop};
			my $k = "svn-remote.$self->{repo_id}.$key";
			eval { command_oneline(qw/config --get/, $k) };
			if ($@) {
				$self->{$prop} = ${"Git::SVN::_$option"};
928
			} else {
929 930
				my $v = command_oneline(qw/config --bool/,$k);
				$self->{$prop} = $v eq 'false' ? 0 : 1;
931
			}
932 933
			return $self->{$prop};
		}
934
	}
935 936
}

937 938 939
my %LOCKFILES;
END { unlink keys %LOCKFILES if %LOCKFILES }

940 941 942 943 944 945 946 947
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;
948 949
		my $pathname = desanitize_refname($path->full_path($p));
		my $refname = desanitize_refname($ref->full_path($p));
950 951 952 953 954 955 956
		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];
957
			$u =~ s!^\Q$url\E(/|$)!! or die
958 959 960 961 962 963 964 965 966 967 968 969 970 971 972
			  "refs/remotes/$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;
		}
	}
}

973 974 975 976 977 978 979 980 981 982 983 984 985
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";
}

986
sub fetch_all {
987
	my ($repo_id, $remotes) = @_;
E
Eric Wong 已提交
988 989 990 991 992 993
	if (ref $repo_id) {
		my $gs = $repo_id;
		$repo_id = undef;
		$repo_id = $gs->{repo_id};
	}
	$remotes ||= read_all_remotes();
994 995
	my $remote = $remotes->{$repo_id} or
	             die "[svn-remote \"$repo_id\"] unknown\n";
996
	my $fetch = $remote->{fetch};
997
	my $url = $remote->{url} or die "svn-remote.$repo_id.url not defined\n";
998
	my (@gs, @globs);
999
	my $ra = Git::SVN::Ra->new($url);
1000
	my $uuid = $ra->get_uuid;
1001
	my $head = $ra->get_latest_revnum;
E
Eric Wong 已提交
1002
	my $base = defined $fetch ? $head : 0;
1003 1004 1005 1006 1007

	# read the max revs for wildcard expansion (branches/*, tags/*)
	foreach my $t (qw/branches tags/) {
		defined $remote->{$t} or next;
		push @globs, $remote->{$t};
1008 1009 1010 1011
		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;
1012 1013
		} elsif (!defined $max_rev) {
			$base = 0;
1014 1015 1016
		}
	}

1017 1018 1019 1020 1021 1022 1023 1024
	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;
1025 1026
		}
	}
1027 1028

	($base, $head) = parse_revision_argument($base, $head);
1029
	$ra->gs_fetch_loop_common($base, $head, \@gs, \@globs);
1030 1031
}

1032 1033
sub read_all_remotes {
	my $r = {};
1034
	foreach (grep { s/^svn-remote\.// } command(qw/config -l/)) {
1035
		if (m!^(.+)\.fetch=\s*(.*)\s*:\s*refs/remotes/(.+)\s*$!) {
1036 1037 1038
			my ($remote, $local_ref, $remote_ref) = ($1, $2, $3);
			$local_ref =~ s{^/}{};
			$r->{$remote}->{fetch}->{$local_ref} = $remote_ref;
1039 1040
		} elsif (m!^(.+)\.url=\s*(.*)\s*$!) {
			$r->{$1}->{url} = $2;
1041 1042 1043 1044
		} elsif (m!^(.+)\.(branches|tags)=
		           (.*):refs/remotes/(.+)\s*$/!x) {
			my ($p, $g) = ($3, $4);
			my $rs = $r->{$1}->{$2} = {
1045
			                  t => $2,
1046
					  remote => $1,
1047 1048 1049 1050 1051 1052
			                  path => Git::SVN::GlobSpec->new($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";
			}
1053 1054 1055 1056 1057
		}
	}
	$r;
}

E
Eric Wong 已提交
1058 1059 1060 1061 1062 1063 1064 1065
sub init_vars {
	if (defined $_repack) {
		$_repack = 1000 if ($_repack <= 0);
		$_repack_nr = $_repack;
		$_repack_flags ||= '-d';
	}
}

1066
sub verify_remotes_sanity {
1067
	return unless -d $ENV{GIT_DIR};
1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082
	my %seen;
	foreach (command(qw/config -l/)) {
		if (m!^svn-remote\.(?:.+)\.fetch=.*:refs/remotes/(\S+)\s*$!) {
			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} = $_;
		}
	}
}

1083
# we allow more chars than remotes2config.sh...
1084 1085
sub sanitize_remote_name {
	my ($name) = @_;
1086
	$name =~ tr{A-Za-z0-9:,/+-}{.}c;
1087 1088 1089
	$name;
}

1090 1091
sub find_existing_remote {
	my ($url, $remotes) = @_;
1092
	return undef if $no_reuse_existing;
1093 1094 1095 1096 1097 1098 1099 1100 1101
	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;
}
1102

1103
sub init_remote_config {
1104
	my ($self, $url, $no_write) = @_;
1105 1106 1107 1108
	$url =~ s!/+$!!; # strip trailing slash
	my $r = read_all_remotes();
	my $existing = find_existing_remote($url, $r);
	if ($existing) {
1109 1110 1111 1112
		unless ($no_write) {
			print STDERR "Using existing ",
				     "[svn-remote \"$existing\"]\n";
		}
1113
		$self->{repo_id} = $existing;
1114
	} elsif ($_minimize_url) {
1115 1116 1117
		my $min_url = Git::SVN::Ra->new($url)->minimize_url;
		$existing = find_existing_remote($min_url, $r);
		if ($existing) {
1118 1119 1120 1121
			unless ($no_write) {
				print STDERR "Using existing ",
					     "[svn-remote \"$existing\"]\n";
			}
1122 1123 1124
			$self->{repo_id} = $existing;
		}
		if ($min_url ne $url) {
1125 1126 1127 1128
			unless ($no_write) {
				print STDERR "Using higher level of URL: ",
					     "$url => $min_url\n";
			}
1129 1130
			my $old_path = $self->{path};
			$self->{path} = $url;
1131
			$self->{path} =~ s!^\Q$min_url\E(/|$)!!;
1132 1133 1134 1135 1136 1137 1138 1139
			if (length $old_path) {
				$self->{path} .= "/$old_path";
			}
			$url = $min_url;
		}
	}
	my $orig_url;
	if (!$existing) {
1140
		# verify that we aren't overwriting anything:
1141
		$orig_url = eval {
1142
			command_oneline('config', '--get',
1143
					"svn-remote.$self->{repo_id}.url")
1144
		};
1145
		if ($orig_url && ($orig_url ne $url)) {
1146
			die "svn-remote.$self->{repo_id}.url already set: ",
1147 1148
			    "$orig_url\nwanted to set to: $url\n";
		}
1149
	}
1150 1151 1152 1153 1154
	my ($xrepo_id, $xpath) = find_ref($self->refname);
	if (defined $xpath) {
		die "svn-remote.$xrepo_id.fetch already set to track ",
		    "$xpath:refs/remotes/", $self->refname, "\n";
	}
1155 1156 1157
	unless ($no_write) {
		command_noisy('config',
			      "svn-remote.$self->{repo_id}.url", $url);
1158
		$self->{path} =~ s{^/}{};
1159 1160 1161 1162
		command_noisy('config', '--add',
			      "svn-remote.$self->{repo_id}.fetch",
			      "$self->{path}:".$self->refname);
	}
1163
	$self->{url} = $url;
1164 1165
}

1166 1167
sub find_by_url { # repos_root and, path are optional
	my ($class, $full_url, $repos_root, $path) = @_;
1168

1169
	return undef unless defined $full_url;
1170 1171
	remove_username($full_url);
	remove_username($repos_root) if defined $repos_root;
1172 1173 1174 1175 1176 1177 1178
	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;
1179
		remove_username($u);
1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199
		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;
}

1200
sub init {
1201
	my ($class, $url, $path, $repo_id, $ref_id, $no_write) = @_;
1202 1203
	my $self = _new($class, $repo_id, $ref_id, $path);
	if (defined $url) {
1204
		$self->init_remote_config($url, $no_write);
1205
	}
1206 1207 1208
	$self;
}

1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222
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);
}

1223
sub new {
1224 1225 1226 1227 1228 1229 1230 1231 1232 1233
	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);
1234 1235 1236 1237 1238 1239 1240 1241
	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);
	}
1242 1243 1244
	$self->{url} = command_oneline('config', '--get',
	                               "svn-remote.$repo_id.url") or
                  die "Failed to read \"svn-remote.$repo_id.url\" in config\n";
1245
	$self->rebuild;
1246 1247 1248
	$self;
}

1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282
sub refname {
	my ($refname) = "refs/remotes/$_[0]->{ref_id}" ;

	# It cannot end with a slash /, we'll throw up on this because
	# SVN can't have directories with a slash in their name, either:
	if ($refname =~ m{/$}) {
		die "ref: '$refname' ends with a trailing slash, this is ",
		    "not permitted by git nor Subversion\n";
	}

	# It cannot have ASCII control character space, tilde ~, caret ^,
	# colon :, question-mark ?, asterisk *, space, or open bracket [
	# anywhere.
	#
	# Additionally, % must be escaped because it is used for escaping
	# and we want our escaped refname to be reversible
	$refname =~ s{([ \%~\^:\?\*\[\t])}{uc sprintf('%%%02x',ord($1))}eg;

	# no slash-separated component can begin with a dot .
	# /.* becomes /%2E*
	$refname =~ s{/\.}{/%2E}g;

	# It cannot have two consecutive dots .. anywhere
	# .. becomes %2E%2E
	$refname =~ s{\.\.}{%2E%2E}g;

	return $refname;
}

sub desanitize_refname {
	my ($refname) = @_;
	$refname =~ s{%(?:([0-9A-F]{2}))}{chr hex($1)}eg;
	return $refname;
}
1283

1284 1285 1286 1287 1288 1289 1290 1291 1292
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};
}
1293

1294 1295 1296 1297
sub svm {
	my ($self) = @_;
	return $self->{svm} if $self->{svm};
	my $svm;
1298 1299
	# see if we have it in our config, first:
	eval {
1300 1301
		my $section = "svn-remote.$self->{repo_id}";
		$svm = {
1302 1303
		  source => tmp_config('--get', "$section.svm-source"),
		  uuid => tmp_config('--get', "$section.svm-uuid"),
1304
		  replace => tmp_config('--get', "$section.svm-replace"),
1305 1306
		}
	};
1307 1308 1309
	if ($svm && $svm->{source} && $svm->{uuid} && $svm->{replace}) {
		$self->{svm} = $svm;
	}
1310 1311 1312 1313 1314
	$self->{svm};
}

sub _set_svm_vars {
	my ($self, $ra) = @_;
1315 1316 1317
	return $ra if $self->svm;

	my @err = ( "useSvmProps set, but failed to read SVM properties\n",
1318
		    "(svm:source, svm:uuid) ",
1319 1320
		    "from the following URLs:\n" );
	sub read_svm_props {
1321 1322
		my ($self, $ra, $path, $r) = @_;
		my $props = ($ra->get_dir($path, $r))[2];
1323 1324
		my $src = $props->{'svm:source'};
		my $uuid = $props->{'svm:uuid'};
1325
		return undef if (!$src || !$uuid);
1326

1327
		chomp($src, $uuid);
1328

1329 1330
		$uuid =~ m{^[0-9a-f\-]{30,}$}
		    or die "doesn't look right - svm:uuid is '$uuid'\n";
1331 1332 1333

		# the '!' is used to mark the repos_root!/relative/path
		$src =~ s{/?!/?}{/};
1334
		$src =~ s{/+$}{}; # no trailing slashes please
1335
		# username is of no interest
1336 1337
		$src =~ s{(^[a-z\+]*://)[^/@]*@}{$1};

1338 1339 1340
		my $replace = $ra->{url};
		$replace .= "/$path" if length $path;

1341
		my $section = "svn-remote.$self->{repo_id}";
1342 1343 1344 1345 1346 1347 1348 1349
		tmp_config("$section.svm-source", $src);
		tmp_config("$section.svm-replace", $replace);
		tmp_config("$section.svm-uuid", $uuid);
		$self->{svm} = {
			source => $src,
			uuid => $uuid,
			replace => $replace
		};
1350 1351 1352 1353
	}

	my $r = $ra->get_latest_revnum;
	my $path = $self->{path};
1354
	my %tried;
1355
	while (length $path) {
1356 1357 1358
		unless ($tried{"$self->{url}/$path"}) {
			return $ra if $self->read_svm_props($ra, $path, $r);
			$tried{"$self->{url}/$path"} = 1;
1359
		}
1360
		$path =~ s#/?[^/]+$##;
1361
	}
1362 1363 1364
	die "Path: '$path' should be ''\n" if $path ne '';
	return $ra if $self->read_svm_props($ra, $path, $r);
	$tried{"$self->{url}/$path"} = 1;
1365 1366

	if ($ra->{repos_root} eq $self->{url}) {
1367
		die @err, (map { "  $_\n" } keys %tried), "\n";
1368 1369 1370 1371 1372 1373 1374 1375
	}

	# nope, make sure we're connected to the repository root:
	my $ok;
	my @tried_b;
	$path = $ra->{svn_path};
	$ra = Git::SVN::Ra->new($ra->{repos_root});
	while (length $path) {
1376 1377 1378 1379 1380 1381
		unless ($tried{"$ra->{url}/$path"}) {
			$ok = $self->read_svm_props($ra, $path, $r);
			last if $ok;
			$tried{"$ra->{url}/$path"} = 1;
		}
		$path =~ s#/?[^/]+$##;
1382
	}
1383 1384 1385
	die "Path: '$path' should be ''\n" if $path ne '';
	$ok ||= $self->read_svm_props($ra, $path, $r);
	$tried{"$ra->{url}/$path"} = 1;
1386
	if (!$ok) {
1387
		die @err, (map { "  $_\n" } keys %tried), "\n";
1388 1389
	}
	Git::SVN::Ra->new($self->{url});
1390 1391
}

1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435
sub svnsync {
	my ($self) = @_;
	return $self->{svnsync} if $self->{svnsync};

	if ($self->no_metadata) {
		die "Can't have both 'noMetadata' and ",
		    "'useSvnsyncProps' options set!\n";
	}
	if ($self->rewrite_root) {
		die "Can't have both 'useSvnsyncProps' and 'rewriteRoot' ",
		    "options set!\n";
	}

	my $svnsync;
	# see if we have it in our config, first:
	eval {
		my $section = "svn-remote.$self->{repo_id}";
		$svnsync = {
		  url => tmp_config('--get', "$section.svnsync-url"),
		  uuid => tmp_config('--get', "$section.svnsync-uuid"),
		}
	};
	if ($svnsync && $svnsync->{url} && $svnsync->{uuid}) {
		return $self->{svnsync} = $svnsync;
	}

	my $err = "useSvnsyncProps set, but failed to read " .
	          "svnsync property: svn:sync-from-";
	my $rp = $self->ra->rev_proplist(0);

	my $url = $rp->{'svn:sync-from-url'} or die $err . "url\n";
	$url =~ m{^[a-z\+]+://} or
	           die "doesn't look right - svn:sync-from-url is '$url'\n";

	my $uuid = $rp->{'svn:sync-from-uuid'} or die $err . "uuid\n";
	$uuid =~ m{^[0-9a-f\-]{30,}$} or
	           die "doesn't look right - svn:sync-from-uuid is '$uuid'\n";

	my $section = "svn-remote.$self->{repo_id}";
	tmp_config('--add', "$section.svnsync-uuid", $uuid);
	tmp_config('--add', "$section.svnsync-url", $url);
	return $self->{svnsync} = { url => $url, uuid => $uuid };
}

1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453
# 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};
}

1454 1455
sub ra {
	my ($self) = shift;
1456
	my $ra = Git::SVN::Ra->new($self->{url});
1457 1458
	if ($self->use_svm_props && !$self->{svm}) {
		if ($self->no_metadata) {
1459 1460
			die "Can't have both 'noMetadata' and ",
			    "'useSvmProps' options set!\n";
1461 1462 1463
		} elsif ($self->use_svnsync_props) {
			die "Can't have both 'useSvnsyncProps' and ",
			    "'useSvmProps' options set!\n";
1464
		}
1465
		$ra = $self->_set_svm_vars($ra);
1466 1467 1468
		$self->{-want_revprops} = 1;
	}
	$ra;
1469 1470
}

1471 1472 1473 1474
sub rel_path {
	my ($self) = @_;
	my $repos_root = $self->ra->{repos_root};
	return $self->{path} if ($self->{url} eq $repos_root);
1475 1476 1477 1478
	my $url = $self->{url} .
	          (length $self->{path} ? "/$self->{path}" : $self->{path});
	$url =~ s!^\Q$repos_root\E(?:/+|$)!!g;
	$url;
1479 1480
}

1481 1482 1483
sub traverse_ignore {
	my ($self, $fh, $path, $r) = @_;
	$path =~ s#^/+##g;
1484 1485
	my $ra = $self->ra;
	my ($dirent, undef, $props) = $ra->get_dir($path, $r);
1486
	my $p = $path;
1487
	$p =~ s#^\Q$self->{path}\E(/|$)##;
1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500
	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) {
1501
		next if $dirent->{$_}->{kind} != $SVN::Node::dir;
1502 1503 1504 1505
		$self->traverse_ignore($fh, "$path/$_", $r);
	}
}

1506 1507 1508
sub last_rev { ($_[0]->last_rev_commit)[0] }
sub last_commit { ($_[0]->last_rev_commit)[1] }

1509 1510 1511 1512 1513 1514
# 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});
	}
1515
	my $c = ::verify_ref($self->refname.'^0');
1516
	if ($c && !$self->use_svm_props && !$self->no_metadata) {
1517
		my $rev = (::cmt_metadata($c))[1];
1518 1519 1520 1521 1522
		if (defined $rev) {
			($self->{last_rev}, $self->{last_commit}) = ($rev, $c);
			return ($rev, $c);
		}
	}
1523 1524 1525 1526 1527
	my $db_path = $self->db_path;
	unless (-e $db_path) {
		($self->{last_rev}, $self->{last_commit}) = (undef, undef);
		return (undef, undef);
	}
1528 1529
	my $offset = -41; # from tail
	my $rl;
1530
	open my $fh, '<', $db_path or croak "$db_path not readable: $!\n";
1531 1532
	sysseek($fh, $offset, 2); # don't care for errors
	sysread($fh, $rl, 41) == 41 or return (undef, undef);
1533
	chomp $rl;
1534
	while (('0' x40) eq $rl && sysseek($fh, 0, 1) != 0) {
1535
		$offset -= 41;
1536 1537
		sysseek($fh, $offset, 2); # don't care for errors
		sysread($fh, $rl, 41) == 41 or return (undef, undef);
1538 1539
		chomp $rl;
	}
1540
	if ($c && $c ne $rl) {
1541
		die "$db_path and ", $self->refname,
1542 1543
		    " inconsistent!:\n$c != $rl\n";
	}
1544
	my $rev = sysseek($fh, 0, 1) or croak $!;
1545 1546 1547 1548 1549 1550
	$rev =  ($rev - 41) / 41;
	close $fh or croak $!;
	($self->{last_rev}, $self->{last_commit}) = ($rev, $c);
	return ($rev, $c);
}

1551 1552 1553
sub get_fetch_range {
	my ($self, $min, $max) = @_;
	$max ||= $self->ra->get_latest_revnum;
1554
	$min ||= $self->rev_db_max;
1555
	(++$min, $max);
1556 1557
}

1558
sub tmp_config {
1559
	my (@args) = @_;
1560 1561
	my $old_def_config = "$ENV{GIT_DIR}/svn/config";
	my $config = "$ENV{GIT_DIR}/svn/.metadata";
1562
	if (! -f $config && -f $old_def_config) {
1563 1564 1565
		rename $old_def_config, $config or
		       die "Failed rename $old_def_config => $config: $!\n";
	}
1566
	my $old_config = $ENV{GIT_CONFIG};
1567
	$ENV{GIT_CONFIG} = $config;
1568
	$@ = undef;
1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582
	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);
	};
1583 1584 1585 1586 1587 1588 1589 1590 1591 1592
	my $err = $@;
	if (defined $old_config) {
		$ENV{GIT_CONFIG} = $old_config;
	} else {
		delete $ENV{GIT_CONFIG};
	}
	die $err if $err;
	wantarray ? @ret : $ret[0];
}

1593 1594 1595 1596
sub tmp_index_do {
	my ($self, $sub) = @_;
	my $old_index = $ENV{GIT_INDEX_FILE};
	$ENV{GIT_INDEX_FILE} = $self->{index};
1597
	$@ = undef;
1598 1599 1600 1601 1602
	my @ret = eval {
		my ($dir, $base) = ($self->{index} =~ m#^(.*?)/?([^/]+)$#);
		mkpath([$dir]) unless -d $dir;
		&$sub;
	};
1603 1604
	my $err = $@;
	if (defined $old_index) {
1605 1606 1607 1608
		$ENV{GIT_INDEX_FILE} = $old_index;
	} else {
		delete $ENV{GIT_INDEX_FILE};
	}
1609
	die $err if $err;
1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620
	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);
1621 1622 1623 1624 1625
		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);
1626 1627 1628 1629 1630 1631 1632 1633 1634
		$x = command_oneline('write-tree');
		if ($y ne $x) {
			::fatal "trees ($treeish) $y != $x\n",
			        "Something is seriously wrong...\n";
		}
	});
}

sub get_commit_parents {
1635
	my ($self, $log_entry) = @_;
1636
	my (%seen, @ret, @tmp);
1637 1638 1639 1640
	# 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;
1641 1642
		}
	}
1643
	if (my $cur = ::verify_ref($self->refname.'^0')) {
1644 1645
		push @tmp, $cur;
	}
1646 1647 1648 1649 1650
	if (my $ipd = $self->{inject_parents_dcommit}) {
		if (my $commit = delete $ipd->{$log_entry->{revision}}) {
			push @tmp, @$commit;
		}
	}
1651
	push @tmp, $_ foreach (@{$log_entry->{parents}}, @tmp);
1652 1653 1654 1655 1656 1657 1658 1659
	while (my $p = shift @tmp) {
		next if $seen{$p};
		$seen{$p} = 1;
		push @ret, $p;
		# MAXPARENT is defined to 16 in commit-tree.c:
		last if @ret >= 16;
	}
	if (@tmp) {
1660
		die "r$log_entry->{revision}: No room for parents:\n\t",
1661 1662 1663 1664 1665
		    join("\n\t", @tmp), "\n";
	}
	@ret;
}

1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685
sub rewrite_root {
	my ($self) = @_;
	return $self->{-rewrite_root} if exists $self->{-rewrite_root};
	my $k = "svn-remote.$self->{repo_id}.rewriteRoot";
	my $rwr = eval { command_oneline(qw/config --get/, $k) };
	if ($rwr) {
		$rwr =~ s#/+$##;
		if ($rwr !~ m#^[a-z\+]+://#) {
			die "$rwr is not a valid URL (key: $k)\n";
		}
	}
	$self->{-rewrite_root} = $rwr;
}

sub metadata_url {
	my ($self) = @_;
	($self->rewrite_root || $self->{url}) .
	   (length $self->{path} ? '/' . $self->{path} : '');
}

1686
sub full_url {
1687
	my ($self) = @_;
1688
	$self->{url} . (length $self->{path} ? '/' . $self->{path} : '');
1689 1690 1691
}

sub do_git_commit {
1692
	my ($self, $log_entry) = @_;
1693 1694 1695 1696 1697 1698
	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";
	}
1699 1700
	if (my $c = $self->rev_db_get($log_entry->{revision})) {
		croak "$log_entry->{revision} = $c already exists! ",
1701 1702
		      "Why are we refetching it?\n";
	}
1703 1704 1705
	$ENV{GIT_AUTHOR_NAME} = $ENV{GIT_COMMITTER_NAME} = $log_entry->{name};
	$ENV{GIT_AUTHOR_EMAIL} = $ENV{GIT_COMMITTER_EMAIL} =
	                                                  $log_entry->{email};
1706
	$ENV{GIT_AUTHOR_DATE} = $ENV{GIT_COMMITTER_DATE} = $log_entry->{date};
1707

1708
	my $tree = $log_entry->{tree};
1709 1710 1711 1712 1713 1714 1715
	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', $tree);
1716
	foreach ($self->get_commit_parents($log_entry)) {
1717 1718 1719 1720
		push @exec, '-p', $_;
	}
	defined(my $pid = open3(my $msg_fh, my $out_fh, '>&STDERR', @exec))
	                                                           or croak $!;
1721
	print $msg_fh $log_entry->{log} or croak $!;
1722
	unless ($self->no_metadata) {
1723 1724
		print $msg_fh "\ngit-svn-id: $log_entry->{metadata}\n"
		              or croak $!;
1725
	}
1726 1727 1728 1729 1730 1731 1732 1733 1734 1735
	$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";
	}

1736
	$self->rev_db_set($log_entry->{revision}, $commit, 1);
1737

1738
	$self->{last_rev} = $log_entry->{revision};
1739
	$self->{last_commit} = $commit;
1740 1741 1742
	print "r$log_entry->{revision}";
	if (defined $log_entry->{svm_revision}) {
		 print " (\@$log_entry->{svm_revision})";
1743 1744
		 $self->rev_db_set($log_entry->{svm_revision}, $commit,
		                   0, $self->svm_uuid);
1745 1746
	}
	print " = $commit ($self->{ref_id})\n";
E
Eric Wong 已提交
1747 1748 1749 1750 1751 1752 1753
	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";
	}
1754 1755 1756
	return $commit;
}

1757 1758
sub match_paths {
	my ($self, $paths, $r) = @_;
1759
	return 1 if $self->{path} eq '';
1760 1761 1762
	if (my $path = $paths->{"/$self->{path}"}) {
		return ($path->{action} eq 'D') ? 0 : 1;
	}
1763
	$self->{path_regex} ||= qr/^\/\Q$self->{path}\E\//;
1764 1765 1766 1767 1768 1769
	if (grep /$self->{path_regex}/, keys %$paths) {
		return 1;
	}
	my $c = '';
	foreach (split m#/#, $self->{path}) {
		$c .= "/$_";
1770 1771
		next unless ($paths->{$c} &&
		             ($paths->{$c}->{action} =~ /^[AR]$/));
1772 1773
		if ($self->ra->check_path($self->{path}, $r) ==
		    $SVN::Node::dir) {
1774 1775 1776 1777 1778 1779
			return 1;
		}
	}
	return 0;
}

1780 1781
sub find_parent_branch {
	my ($self, $paths, $rev) = @_;
1782
	return undef unless $self->follow_parent;
1783
	unless (defined $paths) {
1784 1785
		my $err_handler = $SVN::Error::handler;
		$SVN::Error::handler = \&Git::SVN::Ra::skip_unknown_revs;
1786 1787 1788
		$self->ra->get_log([$self->{path}], $rev, $rev, 0, 1, 1, sub {
		                   $paths =
				      Git::SVN::Ra::dup_changed_paths($_[0]) });
1789
		$SVN::Error::handler = $err_handler;
1790 1791
	}
	return undef unless defined $paths;
1792 1793

	# look for a parent from another branch:
1794 1795 1796 1797 1798
	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)};
1799
		last if $i && defined $i->{copyfrom_path};
1800 1801
		unshift(@a_path_components, pop(@b_path_components));
	}
1802 1803
	return undef unless defined $i && defined $i->{copyfrom_path};
	my $branch_from = $i->{copyfrom_path};
1804 1805 1806 1807 1808
	if (@a_path_components) {
		print STDERR "branch_from: $branch_from => ";
		$branch_from .= '/'.join('/', @a_path_components);
		print STDERR $branch_from, "\n";
	}
1809
	my $r = $i->{copyfrom_rev};
1810 1811 1812 1813 1814 1815
	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#^/##;
1816
	my $gs = Git::SVN->find_by_url($new_url, $repos_root, $branch_from);
1817
	unless ($gs) {
1818 1819 1820
		my $ref_id = $self->{ref_id};
		$ref_id =~ s/\@\d+$//;
		$ref_id .= "\@$r";
1821 1822
		# just grow a tail if we're not unique enough :x
		$ref_id .= '-' while find_ref($ref_id);
1823
		print STDERR "Initializing parent: $ref_id\n";
1824
		$gs = Git::SVN->init($new_url, '', $ref_id, $ref_id, 1);
1825 1826
	}
	my ($r0, $parent) = $gs->find_rev_before($r, 1);
1827
	if (!defined $r0 || !defined $parent) {
1828 1829 1830 1831
		my ($base, $head) = parse_revision_argument(0, $r);
		if ($base <= $r) {
			$gs->fetch($base, $r);
		}
1832 1833
		($r0, $parent) = $gs->last_rev_commit;
	}
1834
	if (defined $r0 && defined $parent) {
1835 1836 1837
		print STDERR "Found branch parent: ($self->{ref_id}) $parent\n";
		my $ed;
		if ($self->ra->can_do_switch) {
1838
			$self->assert_index_clean($parent);
1839
			print STDERR "Following parent with do_switch\n";
1840
			# do_switch works with svn/trunk >= r22312, but that
1841
			# is not included with SVN 1.4.3 (the latest version
1842 1843 1844
			# at the moment), so we can't rely on it
			$self->{last_commit} = $parent;
			$ed = SVN::Git::Fetcher->new($self);
1845
			$gs->ra->gs_do_switch($r0, $rev, $gs,
1846 1847 1848
					      $self->full_url, $ed)
			  or die "SVN connection failed somewhere...\n";
		} else {
1849
			print STDERR "Following parent with do_update\n";
1850
			$ed = SVN::Git::Fetcher->new($self);
1851
			$self->ra->gs_do_update($rev, $rev, $self, $ed)
1852 1853
			  or die "SVN connection failed somewhere...\n";
		}
1854
		print STDERR "Successfully followed parent\n";
1855 1856 1857 1858 1859
		return $self->make_log_entry($rev, [$parent], $ed);
	}
	return undef;
}

1860
sub do_fetch {
1861
	my ($self, $paths, $rev) = @_;
1862
	my $ed;
1863
	my ($last_rev, @parents);
1864 1865 1866 1867 1868 1869 1870 1871 1872
	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;
		}
1873
		$ed = SVN::Git::Fetcher->new($self);
1874
		$last_rev = $self->{last_rev};
1875 1876
		$ed->{c} = $lc;
		@parents = ($lc);
1877 1878
	} else {
		$last_rev = $rev;
1879 1880 1881 1882
		if (my $log_entry = $self->find_parent_branch($paths, $rev)) {
			return $log_entry;
		}
		$ed = SVN::Git::Fetcher->new($self);
1883
	}
1884
	unless ($self->ra->gs_do_update($last_rev, $rev, $self, $ed)) {
1885 1886 1887 1888 1889
		die "SVN connection failed somewhere...\n";
	}
	$self->make_log_entry($rev, \@parents, $ed);
}

1890 1891 1892 1893
sub get_untracked {
	my ($self, $ed) = @_;
	my @out;
	my $h = $ed->{empty};
1894 1895
	foreach (sort keys %$h) {
		my $act = $h->{$_} ? '+empty_dir' : '-empty_dir';
1896
		push @out, "  $act: " . uri_encode($_);
1897 1898 1899
		warn "W: $act: $_\n";
	}
	foreach my $t (qw/dir_prop file_prop/) {
1900
		$h = $ed->{$t} or next;
1901 1902 1903
		foreach my $path (sort keys %$h) {
			my $ppath = $path eq '' ? '.' : $path;
			foreach my $prop (sort keys %{$h->{$path}}) {
1904
				next if $SKIP_PROP{$prop};
1905
				my $v = $h->{$path}->{$prop};
1906 1907 1908
				my $t_ppath_prop = "$t: " .
				                    uri_encode($ppath) . ' ' .
				                    uri_encode($prop);
1909
				if (defined $v) {
1910 1911
					push @out, "  +$t_ppath_prop " .
					           uri_encode($v);
1912
				} else {
1913
					push @out, "  -$t_ppath_prop";
1914 1915 1916 1917 1918
				}
			}
		}
	}
	foreach my $t (qw/absent_file absent_directory/) {
1919
		$h = $ed->{$t} or next;
1920 1921
		foreach my $parent (sort keys %$h) {
			foreach my $path (sort @{$h->{$parent}}) {
1922 1923
				push @out, "  $t: " .
				           uri_encode("$parent/$path");
1924 1925 1926 1927 1928
				warn "W: $t: $parent/$path ",
				     "Insufficient permissions?\n";
			}
		}
	}
1929
	\@out;
1930 1931
}

1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950
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;
}

1951
sub make_log_entry {
1952 1953 1954
	my ($self, $rev, $parents, $ed) = @_;
	my $untracked = $self->get_untracked($ed);

1955
	open my $un, '>>', "$self->{dir}/unhandled.log" or croak $!;
1956 1957 1958 1959
	print $un "r$rev\n" or croak $!;
	print $un $_, "\n" foreach @$untracked;
	my %log_entry = ( parents => $parents || [], revision => $rev,
	                  log => '');
1960

1961
	my $headrev;
1962
	my $logged = delete $self->{logged_rev_props};
1963
	if (!$logged || $self->{-want_revprops}) {
1964 1965 1966 1967 1968
		my $rp = $self->ra->rev_proplist($rev);
		foreach (sort keys %$rp) {
			my $v = $rp->{$_};
			if (/^svn:(author|date|log)$/) {
				$log_entry{$1} = $v;
1969 1970
			} elsif ($_ eq 'svm:headrev') {
				$headrev = $v;
1971 1972 1973 1974
			} else {
				print $un "  rev_prop: ", uri_encode($_), ' ',
					  uri_encode($v), "\n";
			}
1975
		}
1976 1977
	} else {
		map { $log_entry{$_} = $logged->{$_} } keys %$logged;
1978 1979
	}
	close $un or croak $!;
1980

1981 1982
	$log_entry{date} = parse_svn_date($log_entry{date});
	$log_entry{log} .= "\n";
1983 1984 1985
	my $author = $log_entry{author} = check_author($log_entry{author});
	my ($name, $email) = defined $::users{$author} ? @{$::users{$author}}
	                                               : ($author, undef);
1986
	if (defined $headrev && $self->use_svm_props) {
1987 1988 1989 1990
		if ($self->rewrite_root) {
			die "Can't have both 'useSvmProps' and 'rewriteRoot' ",
			    "options set!\n";
		}
1991
		my ($uuid, $r) = $headrev =~ m{^([a-f\d\-]{30,}):(\d+)$};
1992 1993 1994 1995
		# we don't want "SVM: initializing mirror for junk" ...
		return undef if $r == 0;
		my $svm = $self->svm;
		if ($uuid ne $svm->{uuid}) {
1996
			die "UUID mismatch on SVM path:\n",
1997
			    "expected: $svm->{uuid}\n",
1998 1999
			    "     got: $uuid\n";
		}
2000 2001 2002 2003
		my $full_url = $self->full_url;
		$full_url =~ s#^\Q$svm->{replace}\E(/|$)#$svm->{source}$1# or
		             die "Failed to replace '$svm->{replace}' with ",
		                 "'$svm->{source}' in $full_url\n";
2004 2005
		# throw away username for storing in records
		remove_username($full_url);
2006 2007
		$log_entry{metadata} = "$full_url\@$r $uuid";
		$log_entry{svm_revision} = $r;
2008
		$email ||= "$author\@$uuid"
2009 2010 2011
	} elsif ($self->use_svnsync_props) {
		my $full_url = $self->svnsync->{url};
		$full_url .= "/$self->{path}" if length $self->{path};
2012
		remove_username($full_url);
2013 2014 2015
		my $uuid = $self->svnsync->{uuid};
		$log_entry{metadata} = "$full_url\@$rev $uuid";
		$email ||= "$author\@$uuid"
2016
	} else {
2017 2018 2019
		my $url = $self->metadata_url;
		remove_username($url);
		$log_entry{metadata} = "$url\@$rev " .
2020
		                       $self->ra->get_uuid;
2021
		$email ||= "$author\@" . $self->ra->get_uuid;
2022
	}
2023 2024
	$log_entry{name} = $name;
	$log_entry{email} = $email;
2025 2026 2027 2028
	\%log_entry;
}

sub fetch {
2029
	my ($self, $min_rev, $max_rev, @parents) = @_;
2030
	my ($last_rev, $last_commit) = $self->last_rev_commit;
2031
	my ($base, $head) = $self->get_fetch_range($min_rev, $max_rev);
2032
	$self->ra->gs_fetch_loop_common($base, $head, [$self]);
2033 2034 2035 2036
}

sub set_tree_cb {
	my ($self, $log_entry, $tree, $rev, $date, $author) = @_;
2037 2038
	$self->{inject_parents} = { $rev => $tree };
	$self->fetch(undef, undef);
2039 2040 2041 2042
}

sub set_tree {
	my ($self, $tree) = (shift, shift);
2043
	my $log_entry = ::get_commit_entry($tree);
2044 2045 2046
	unless ($self->{last_rev}) {
		fatal("Must have an existing revision to commit\n");
	}
2047 2048 2049 2050 2051 2052 2053 2054 2055
	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 => $self->{path} );
	if (!SVN::Git::Editor->new(\%ed_opts)->apply_diff) {
2056 2057 2058 2059
		print "No changes\nr$self->{last_rev} = $tree\n";
	}
}

2060 2061
sub rebuild {
	my ($self) = @_;
2062
	my $db_path = $self->db_path;
2063 2064
	return if (-e $db_path && ! -z $db_path);
	return unless ::verify_ref($self->refname.'^0');
2065 2066 2067 2068 2069 2070 2071 2072 2073
	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 $db_path ...\n";
2074
	my ($log, $ctx) = command_output_pipe("log", '--no-color', $self->refname);
2075 2076
	my $latest;
	my $full_url = $self->full_url;
2077
	remove_username($full_url);
2078
	my $svn_uuid;
2079 2080 2081 2082 2083 2084 2085 2086
	my $c;
	while (<$log>) {
		if ( m{^commit ($::sha1)$} ) {
			$c = $1;
			next;
		}
		next unless s{^\s*(git-svn-id:)}{$1};
		my ($url, $rev, $uuid) = ::extract_metadata($_);
2087
		remove_username($url);
2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103

		# 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 = $c\n";
	}
2104
	command_close_pipe($log, $ctx);
2105
	print "Done rebuilding $db_path\n";
2106 2107
}

2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118
# 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).
2119
# These files are disposable unless noMetadata or useSvmProps is set
2120

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
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";
	}
}

2146
sub rev_db_set {
2147 2148 2149 2150
	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";
2151 2152 2153 2154 2155
	my $sig;
	if ($update_ref) {
		$SIG{INT} = $SIG{HUP} = $SIG{TERM} = $SIG{ALRM} = $SIG{PIPE} =
		            $SIG{USR1} = $SIG{USR2} = sub { $sig = $_[0] };
	}
2156 2157
	mkfile($db);

2158
	$LOCKFILES{$db_lock} = 1;
2159 2160 2161 2162 2163
	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) {
		$sync = 1;
2164
		copy($db, $db_lock) or die "rev_db_set(@_): ",
2165
					   "Failed to copy: ",
2166 2167 2168
					   "$db => $db_lock ($!)\n";
	} else {
		rename $db, $db_lock or die "rev_db_set(@_): ",
2169
					    "Failed to rename: ",
2170 2171
					    "$db => $db_lock ($!)\n";
	}
2172 2173
	open my $fh, '+<', $db_lock or die "Couldn't open $db_lock: $!\n";
	_rev_db_set($fh, $rev, $commit);
2174 2175 2176 2177
	if ($sync) {
		$fh->flush or die "Couldn't flush $db_lock: $!\n";
		$fh->sync or die "Couldn't sync $db_lock: $!\n";
	}
2178
	close $fh or croak $!;
2179
	if ($update_ref) {
2180
		$_head = $self;
2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191
		command_noisy('update-ref', '-m', "r$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;
	}
2192 2193
}

2194 2195
sub rev_db_max {
	my ($self) = @_;
2196
	$self->rebuild;
2197 2198 2199
	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";
2200 2201 2202 2203
	my $max = $stat[7] / 41;
	(($max > 0) ? $max - 1 : 0);
}

2204
sub rev_db_get {
2205
	my ($self, $rev, $uuid) = @_;
2206 2207
	my $ret;
	my $offset = $rev * 41;
2208 2209 2210
	my $db_path = $self->db_path($uuid);
	return undef unless -e $db_path;
	open my $fh, '<', $db_path or croak $!;
2211 2212 2213
	if (sysseek($fh, $offset, 0) == $offset) {
		my $read = sysread($fh, $ret, 40);
		$ret = undef if ($read != 40 || $ret eq ('0'x40));
2214 2215 2216 2217 2218
	}
	close $fh or croak $!;
	$ret;
}

2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230
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);
}

2231
sub _new {
2232 2233 2234 2235 2236
	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) {
2237
		$_[2] = $ref_id = $Git::SVN::default_ref_id;
2238 2239 2240 2241
	}
	$_[1] = $repo_id = sanitize_remote_name($repo_id);
	my $dir = "$ENV{GIT_DIR}/svn/$ref_id";
	$_[3] = $path = '' unless (defined $path);
2242
	mkpath(["$ENV{GIT_DIR}/svn"]);
2243 2244
	bless {
		ref_id => $ref_id, dir => $dir, index => "$dir/index",
2245
	        path => $path, config => "$ENV{GIT_DIR}/svn/config",
2246 2247 2248 2249 2250 2251 2252
	        db_root => "$dir/.rev_db", repo_id => $repo_id }, $class;
}

sub db_path {
	my ($self, $uuid) = @_;
	$uuid ||= $self->ra_uuid;
	"$self->{db_root}.$uuid";
2253 2254
}

2255 2256 2257 2258 2259
sub uri_encode {
	my ($f) = @_;
	$f =~ s#([^a-zA-Z0-9\*!\:_\./\-])#uc sprintf("%%%02x",ord($1))#eg;
	$f
}
2260

2261 2262 2263 2264
sub remove_username {
	$_[0] =~ s{^([^:]*://)[^@]+@}{$1};
}

2265 2266 2267 2268 2269 2270 2271
package Git::SVN::Prompt;
use strict;
use warnings;
require SVN::Core;
use vars qw/$_no_auth_cache $_username/;

sub simple {
2272 2273 2274 2275 2276
	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) {
2277 2278
			print STDERR "Authentication realm: $realm\n";
			STDERR->flush;
2279 2280 2281
		}
		$cred->username($default_username);
	} else {
2282
		username($cred, $realm, $may_save, $pool);
2283 2284 2285 2286 2287 2288 2289
	}
	$cred->password(_read_password("Password for '" .
	                               $cred->username . "': ", $realm));
	$cred->may_save($may_save);
	$SVN::_Core::SVN_NO_ERROR;
}

2290
sub ssl_server_trust {
2291 2292
	my ($cred, $realm, $failures, $cert_info, $may_save, $pool) = @_;
	$may_save = undef if $_no_auth_cache;
2293
	print STDERR "Error validating server certificate for '$realm':\n";
2294
	if ($failures & $SVN::Auth::SSL::UNKNOWNCA) {
2295
		print STDERR " - The certificate is not issued by a trusted ",
2296 2297 2298 2299
		      "authority. Use the\n",
	              "   fingerprint to validate the certificate manually!\n";
	}
	if ($failures & $SVN::Auth::SSL::CNMISMATCH) {
2300
		print STDERR " - The certificate hostname does not match.\n";
2301 2302
	}
	if ($failures & $SVN::Auth::SSL::NOTYETVALID) {
2303
		print STDERR " - The certificate is not yet valid.\n";
2304 2305
	}
	if ($failures & $SVN::Auth::SSL::EXPIRED) {
2306
		print STDERR " - The certificate has expired.\n";
2307 2308
	}
	if ($failures & $SVN::Auth::SSL::OTHER) {
2309
		print STDERR " - The certificate has an unknown error.\n";
2310
	}
2311 2312
	printf STDERR
	        "Certificate information:\n".
2313 2314 2315 2316 2317
	        " - Hostname: %s\n".
	        " - Valid: from %s until %s\n".
	        " - Issuer: %s\n".
	        " - Fingerprint: %s\n",
	        map $cert_info->$_, qw(hostname valid_from valid_until
2318
	                               issuer_dname fingerprint);
2319 2320
	my $choice;
prompt:
2321
	print STDERR $may_save ?
2322 2323
	      "(R)eject, accept (t)emporarily or accept (p)ermanently? " :
	      "(R)eject or accept (t)emporarily? ";
2324
	STDERR->flush;
2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338
	$choice = lc(substr(<STDIN> || 'R', 0, 1));
	if ($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;
}

2339
sub ssl_client_cert {
2340 2341
	my ($cred, $realm, $may_save, $pool) = @_;
	$may_save = undef if $_no_auth_cache;
2342 2343
	print STDERR "Client certificate filename: ";
	STDERR->flush;
2344 2345 2346 2347 2348 2349
	chomp(my $filename = <STDIN>);
	$cred->cert_file($filename);
	$cred->may_save($may_save);
	$SVN::_Core::SVN_NO_ERROR;
}

2350
sub ssl_client_cert_pw {
2351 2352 2353 2354 2355 2356 2357
	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;
}

2358
sub username {
2359 2360 2361
	my ($cred, $realm, $may_save, $pool) = @_;
	$may_save = undef if $_no_auth_cache;
	if (defined $realm && length $realm) {
2362
		print STDERR "Authentication realm: $realm\n";
2363 2364 2365 2366 2367
	}
	my $username;
	if (defined $_username) {
		$username = $_username;
	} else {
2368 2369
		print STDERR "Username: ";
		STDERR->flush;
2370 2371 2372 2373 2374 2375 2376 2377 2378
		chomp($username = <STDIN>);
	}
	$cred->username($username);
	$cred->may_save($may_save);
	$SVN::_Core::SVN_NO_ERROR;
}

sub _read_password {
	my ($prompt, $realm) = @_;
2379 2380
	print STDERR $prompt;
	STDERR->flush;
2381 2382 2383 2384 2385 2386 2387 2388
	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');
2389 2390
	print STDERR "\n";
	STDERR->flush;
2391 2392 2393
	$password;
}

2394 2395
package main;

2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407
{
	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;
}

2408 2409 2410 2411 2412 2413
package SVN::Git::Fetcher;
use vars qw/@ISA/;
use strict;
use warnings;
use Carp qw/croak/;
use IO::File qw//;
2414
use Digest::MD5;
2415 2416 2417 2418 2419 2420

# 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;
2421
	$self->{c} = $git_svn->{last_commit} if exists $git_svn->{last_commit};
2422 2423 2424 2425 2426
	$self->{empty} = {};
	$self->{dir_prop} = {};
	$self->{file_prop} = {};
	$self->{absent_dir} = {};
	$self->{absent_file} = {};
2427
	$self->{gii} = $git_svn->tmp_index_do(sub { Git::IndexInfo->new });
2428 2429 2430
	$self;
}

2431 2432
sub set_path_strip {
	my ($self, $path) = @_;
2433
	$self->{path_strip} = qr/^\Q$path\E(\/|$)/ if length $path;
2434 2435
}

2436 2437 2438 2439 2440 2441 2442 2443 2444
sub open_root {
	{ path => '' };
}

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

2445 2446
sub git_path {
	my ($self, $path) = @_;
2447 2448 2449 2450
	if ($self->{path_strip}) {
		$path =~ s!$self->{path_strip}!! or
		  die "Failed to strip path '$path' ($self->{path_strip})\n";
	}
2451 2452 2453
	$path;
}

2454 2455
sub delete_entry {
	my ($self, $path, $rev, $pb) = @_;
2456

2457
	my $gpath = $self->git_path($path);
2458 2459
	return undef if ($gpath eq '');

2460
	# remove entire directories.
2461
	if (command('ls-tree', $self->{c}, '--', $gpath) =~ /^040000 tree/) {
2462 2463
		my ($ls, $ctx) = command_output_pipe(qw/ls-tree
		                                     -r --name-only -z/,
2464
				                     $self->{c}, '--', $gpath);
2465 2466
		local $/ = "\0";
		while (<$ls>) {
2467 2468
			chomp;
			$self->{gii}->remove($_);
2469
			print "\tD\t$_\n" unless $::_q;
2470
		}
2471
		print "\tD\t$gpath/\n" unless $::_q;
2472 2473 2474
		command_close_pipe($ls, $ctx);
		$self->{empty}->{$path} = 0
	} else {
2475
		$self->{gii}->remove($gpath);
2476
		print "\tD\t$gpath\n" unless $::_q;
2477
	}
2478 2479 2480 2481 2482
	undef;
}

sub open_file {
	my ($self, $path, $pb, $rev) = @_;
2483 2484
	my $gpath = $self->git_path($path);
	my ($mode, $blob) = (command('ls-tree', $self->{c}, '--', $gpath)
2485
	                     =~ /^(\d{6}) blob ([a-f\d]{40})\t/);
2486 2487 2488
	unless (defined $mode && defined $blob) {
		die "$path was not found in commit $self->{c} (r$rev)\n";
	}
2489
	{ path => $path, mode_a => $mode, mode_b => $mode, blob => $blob,
2490
	  pool => SVN::Pool->new, action => 'M' };
2491 2492 2493 2494
}

sub add_file {
	my ($self, $path, $pb, $cp_path, $cp_rev) = @_;
2495 2496
	my ($dir, $file) = ($path =~ m#^(.*?)/?([^/]+)$#);
	delete $self->{empty}->{$dir};
2497
	{ path => $path, mode_a => 100644, mode_b => 100644,
2498
	  pool => SVN::Pool->new, action => 'A' };
2499 2500
}

2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529
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;
}

2530 2531 2532 2533 2534 2535 2536 2537
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;
2538 2539 2540
	} else {
		$self->{file_prop}->{$fb->{path}} ||= {};
		$self->{file_prop}->{$fb->{path}}->{$prop} = $value;
2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582
	}
	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;
2583
	my $path = $self->git_path($fb->{path});
2584
	if (my $fh = $fb->{fh}) {
2585 2586 2587 2588 2589 2590 2591 2592 2593 2594
		if (defined $exp) {
			seek($fh, 0, 0) or croak $!;
			my $md5 = Digest::MD5->new;
			$md5->addfile($fh);
			my $got = $md5->hexdigest;
			if ($got ne $exp) {
				die "Checksum mismatch: $path\n",
				    "expected: $exp\n    got: $got\n";
			}
		}
2595
		sysseek($fh, 0, 0) or croak $!;
2596
		if ($fb->{mode_b} == 120000) {
2597
			sysread($fh, my $buf, 5) == 5 or croak $!;
2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614
			$buf eq 'link ' or die "$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;
2615
	$self->{gii}->update($fb->{mode_b}, $hash, $path) or croak $!;
2616
	print "\t$fb->{action}\t$path\n" if $fb->{action} && ! $::_q;
2617 2618 2619 2620 2621
	undef;
}

sub abort_edit {
	my $self = shift;
2622 2623
	$self->{nr} = $self->{gii}->{nr};
	delete $self->{gii};
2624 2625 2626 2627 2628
	$self->SUPER::abort_edit(@_);
}

sub close_edit {
	my $self = shift;
2629
	$self->{git_commit_ok} = 1;
2630 2631
	$self->{nr} = $self->{gii}->{nr};
	delete $self->{gii};
2632 2633
	$self->SUPER::close_edit(@_);
}
2634

2635
package SVN::Git::Editor;
2636
use vars qw/@ISA $_rmdir $_cp_similarity $_find_copies_harder $_rename_limit/;
2637 2638 2639 2640
use strict;
use warnings;
use Carp qw/croak/;
use IO::File;
2641
use Digest::MD5;
2642 2643

sub new {
2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657
	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);
2658
	bless $self, $class;
2659 2660
	foreach (qw/svn_path r tree_a tree_b/) {
		$self->{$_} = $opts->{$_};
2661
	}
2662 2663 2664 2665
	$self->{url} = $opts->{ra}->{url};
	$self->{mods} = $mods;
	$self->{types} = $types;
	$self->{pool} = $pool;
2666 2667
	$self->{bat} = { '' => $self->open_root($self->{r}, $self->{pool}) };
	$self->{rm} = { };
2668 2669
	$self->{path_prefix} = length $self->{svn_path} ?
	                       "$self->{svn_path}/" : '';
2670 2671 2672
	return $self;
}

2673 2674 2675
sub generate_diff {
	my ($tree_a, $tree_b) = @_;
	my @diff_tree = qw(diff-tree -z -r);
2676 2677
	if ($_cp_similarity) {
		push @diff_tree, "-C$_cp_similarity";
2678 2679 2680
	} else {
		push @diff_tree, '-C';
	}
2681 2682
	push @diff_tree, '--find-copies-harder' if $_find_copies_harder;
	push @diff_tree, "-l$_rename_limit" if defined $_rename_limit;
2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755
	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;
}

2756 2757 2758 2759 2760
sub split_path {
	return ($_[0] =~ m#^(.*?)/?([^/]+)$#);
}

sub repo_path {
2761 2762
	my ($self, $path) = @_;
	$self->{path_prefix}.(defined $path ? $path : '');
2763 2764 2765 2766
}

sub url_path {
	my ($self, $path) = @_;
2767 2768 2769
	if ($self->{url} =~ m#^https?://#) {
		$path =~ s/([^a-zA-Z0-9_.-])/uc sprintf("%%%02x",ord($1))/eg;
	}
2770
	$self->{url} . '/' . $self->repo_path($path);
2771 2772 2773
}

sub rmdirs {
2774
	my ($self) = @_;
2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791
	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;

2792 2793
	my ($fh, $ctx) = command_output_pipe(qw/ls-tree --name-only -r -z/,
	                                     $self->{tree_b});
2794 2795 2796
	local $/ = "\0";
	while (<$fh>) {
		chomp;
2797
		my @dn = split m#/#, $_;
2798 2799 2800 2801
		while (pop @dn) {
			delete $rm->{join '/', @dn};
		}
		unless (%$rm) {
2802
			close $fh;
2803 2804
			return;
		}
2805
	}
E
Eric Wong 已提交
2806
	command_close_pipe($fh, $ctx);
2807

2808 2809 2810 2811
	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) = ($d =~ m#^(.*?)/?(?:[^/]+)$#);
2812
		print "\tD+\t$d/\n" unless $::_q;
2813 2814 2815 2816 2817 2818 2819
		$self->SUPER::delete_entry($d, $r, $bat->{$dn}, $p);
		delete $bat->{$d};
	}
}

sub open_or_add_dir {
	my ($self, $full_path, $baton) = @_;
2820 2821 2822 2823
	my $t = $self->{types}->{$full_path};
	if (!defined $t) {
		die "$full_path not known in r$self->{r} or we have a bug!\n";
	}
2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839
	if ($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};
2840 2841 2842
	my $repo_path = $self->repo_path($path);
	return $bat->{''} unless (length $repo_path);
	my @p = split m#/+#, $repo_path;
2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853
	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 {
2854
	my ($self, $m) = @_;
2855 2856 2857 2858
	my ($dir, $file) = split_path($m->{file_b});
	my $pbat = $self->ensure_path($dir);
	my $fbat = $self->add_file($self->repo_path($m->{file_b}), $pbat,
					undef, -1);
2859
	print "\tA\t$m->{file_b}\n" unless $::_q;
2860 2861 2862 2863 2864
	$self->chg_file($fbat, $m);
	$self->close_file($fbat,undef,$self->{pool});
}

sub C {
2865
	my ($self, $m) = @_;
2866 2867 2868 2869
	my ($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}), $self->{r});
2870
	print "\tC\t$m->{file_a} => $m->{file_b}\n" unless $::_q;
2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883
	$self->chg_file($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 {
2884
	my ($self, $m) = @_;
2885 2886 2887 2888
	my ($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}), $self->{r});
2889
	print "\tR\t$m->{file_a} => $m->{file_b}\n" unless $::_q;
2890 2891 2892 2893 2894 2895 2896 2897 2898
	$self->chg_file($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 {
2899
	my ($self, $m) = @_;
2900 2901 2902 2903
	my ($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},$self->{pool});
2904
	print "\t$m->{chg}\t$m->{file_b}\n" unless $::_q;
2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944
	$self->chg_file($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;
2945 2946 2947
	my $pool = SVN::Pool->new;
	my $atd = $self->apply_textdelta($fbat, undef, $pool);
	my $got = SVN::TxDelta::send_stream($fh, @$atd, $pool);
2948
	die "Checksum mismatch\nexpected: $exp\ngot: $got\n" if ($got ne $exp);
2949
	$pool->clear;
2950 2951 2952 2953 2954

	close $fh or croak $!;
}

sub D {
2955
	my ($self, $m) = @_;
2956 2957
	my ($dir, $file) = split_path($m->{file_b});
	my $pbat = $self->ensure_path($dir);
2958
	print "\tD\t$m->{file_b}\n" unless $::_q;
2959 2960 2961 2962 2963 2964 2965
	$self->delete_entry($m->{file_b}, $pbat);
}

sub close_edit {
	my ($self) = @_;
	my ($p,$bat) = ($self->{pool}, $self->{bat});
	foreach (sort { $b =~ tr#/#/# <=> $a =~ tr#/#/# } keys %$bat) {
2966
		next if $_ eq '';
2967 2968
		$self->close_directory($bat->{$_}, $p);
	}
2969
	$self->close_directory($bat->{''}, $p);
2970 2971 2972 2973 2974 2975 2976
	$self->SUPER::close_edit($p);
	$p->clear;
}

sub abort_edit {
	my ($self) = @_;
	$self->SUPER::abort_edit($self->{pool});
2977 2978 2979 2980 2981
}

sub DESTROY {
	my $self = shift;
	$self->SUPER::DESTROY(@_);
2982 2983 2984
	$self->{pool}->clear;
}

2985 2986
# this drives the editor
sub apply_diff {
2987 2988
	my ($self) = @_;
	my $mods = $self->{mods};
2989
	my %o = ( D => 1, R => 0, C => -1, A => 3, M => 3, T => 3 );
2990
	foreach my $m (sort { $o{$a->{chg}} <=> $o{$b->{chg}} } @$mods) {
2991 2992 2993 2994 2995 2996 2997
		my $f = $m->{chg};
		if (defined $o{$f}) {
			$self->$f($m);
		} else {
			fatal("Invalid change type: $f\n");
		}
	}
2998
	$self->rmdirs if $_rmdir;
2999
	if (@$mods == 0) {
3000 3001 3002 3003
		$self->abort_edit;
	} else {
		$self->close_edit;
	}
3004
	return scalar @$mods;
3005 3006
}

3007
package Git::SVN::Ra;
3008
use vars qw/@ISA $config_dir $_log_window_size/;
3009 3010
use strict;
use warnings;
3011
my ($ra_invalid, $can_do_switch, %ignored_err, $RA);
3012 3013 3014

BEGIN {
	# enforce temporary pool usage for some simple functions
3015 3016 3017 3018 3019 3020 3021 3022 3023 3024
	no strict 'refs';
	for my $f (qw/rev_proplist get_latest_revnum get_uuid get_repos_root/) {
		my $SUPER = "SUPER::$f";
		*$f = sub {
			my $self = shift;
			my $pool = SVN::Pool->new;
			my @ret = $self->$SUPER(@_,$pool);
			$pool->clear;
			wantarray ? @ret : $ret[0];
		};
3025 3026 3027 3028 3029
	}
}

sub new {
	my ($class, $url) = @_;
3030
	$url =~ s!/+$!!;
3031
	return $RA if ($RA && $RA->{url} eq $url);
3032

3033 3034 3035 3036 3037 3038
	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),
3039
	    SVN::Client::get_ssl_client_cert_file_provider(),
3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050
	    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);
3051
	$RA = undef;
3052 3053 3054 3055 3056 3057
	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;
3058
	$self->{svn_path} =~ s#^\Q$self->{repos_root}\E(/|$)##;
3059 3060
	$self->{cache} = { check_path => { r => 0, data => {} },
	                   get_dir => { r => 0, data => {} } };
3061
	$RA = bless $self, $class;
3062 3063
}

3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099
sub check_path {
	my ($self, $path, $r) = @_;
	my $cache = $self->{cache}->{check_path};
	if ($r == $cache->{r} && exists $cache->{data}->{$path}) {
		return $cache->{data}->{$path};
	}
	my $pool = SVN::Pool->new;
	my $t = $self->SUPER::check_path($path, $r, $pool);
	$pool->clear;
	if ($r != $cache->{r}) {
		%{$cache->{data}} = ();
		$cache->{r} = $r;
	}
	$cache->{data}->{$path} = $t;
}

sub get_dir {
	my ($self, $dir, $r) = @_;
	my $cache = $self->{cache}->{get_dir};
	if ($r == $cache->{r}) {
		if (my $x = $cache->{data}->{$dir}) {
			return wantarray ? @$x : $x->[0];
		}
	}
	my $pool = SVN::Pool->new;
	my ($d, undef, $props) = $self->SUPER::get_dir($dir, $r, $pool);
	my %dirents = map { $_ => { kind => $d->{$_}->kind } } keys %$d;
	$pool->clear;
	if ($r != $cache->{r}) {
		%{$cache->{data}} = ();
		$cache->{r} = $r;
	}
	$cache->{data}->{$dir} = [ \%dirents, $r, $props ];
	wantarray ? (\%dirents, $r, $props) : \%dirents;
}

3100
sub DESTROY {
3101
	# do not call the real DESTROY since we store ourselves in $RA
3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113
}

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 {
3114
	my ($self, $log, $cb, $pool) = @_;
3115
	my @lock = $SVN::Core::VERSION ge '1.2.0' ? (undef, 0) : ();
3116
	$self->SUPER::get_commit_editor($log, $cb, @lock, $pool);
3117 3118 3119
}

sub gs_do_update {
3120 3121 3122 3123
	my ($self, $rev_a, $rev_b, $gs, $editor) = @_;
	my $new = ($rev_a == $rev_b);
	my $path = $gs->{path};

3124 3125 3126 3127
	if ($new && -e $gs->{index}) {
		unlink $gs->{index} or die
		  "Couldn't unlink index: $gs->{index}: $!\n";
	}
3128
	my $pool = SVN::Pool->new;
3129
	$editor->set_path_strip($path);
3130 3131
	my (@pc) = split m#/#, $path;
	my $reporter = $self->do_update($rev_b, (@pc ? shift @pc : ''),
3132
	                                1, $editor, $pool);
3133
	my @lock = $SVN::Core::VERSION ge '1.2.0' ? (undef) : ();
3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148

	# 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);

3149 3150 3151 3152 3153
	$reporter->finish_report($pool);
	$pool->clear;
	$editor->{git_commit_ok};
}

3154 3155
# 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)
3156
sub gs_do_switch {
3157 3158
	my ($self, $rev_a, $rev_b, $gs, $url_b, $editor) = @_;
	my $path = $gs->{path};
3159
	my $pool = SVN::Pool->new;
3160 3161 3162 3163

	my $full_url = $self->{url};
	my $old_url = $full_url;
	$full_url .= "/$path" if length $path;
3164 3165 3166 3167 3168 3169 3170 3171
	my ($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 {
3172 3173 3174
			$_[0] = undef;
			$self = undef;
			$RA = undef;
3175
			$ra = Git::SVN::Ra->new($full_url);
3176
			$ra_invalid = 1;
3177 3178 3179
		}
	}
	$ra ||= $self;
3180
	my $reporter = $ra->do_switch($rev_b, '', 1, $url_b, $editor, $pool);
3181
	my @lock = $SVN::Core::VERSION ge '1.2.0' ? (undef) : ();
3182
	$reporter->set_path('', $rev_a, 0, @lock, $pool);
3183
	$reporter->finish_report($pool);
3184

3185 3186 3187 3188
	if ($reparented) {
		SVN::_Ra::svn_ra_reparent($self->{session}, $old_url, $pool);
		$self->{url} = $old_url;
	}
3189

3190 3191 3192 3193
	$pool->clear;
	$editor->{git_commit_ok};
}

3194 3195
sub longest_common_path {
	my ($gsv, $globs) = @_;
3196
	my %common;
3197 3198 3199
	my $common_max = scalar @$gsv;

	foreach my $gs (@$gsv) {
3200 3201 3202 3203 3204 3205 3206 3207
		my @tmp = split m#/#, $gs->{path};
		my $p = '';
		foreach (@tmp) {
			$p .= length($p) ? "/$_" : $_;
			$common{$p} ||= 0;
			$common{$p}++;
		}
	}
3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219
	$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}++;
		}
	}

3220 3221
	my $longest_path = '';
	foreach (sort {length $b <=> length $a} keys %common) {
3222
		if ($common{$_} == $common_max) {
3223 3224 3225
			$longest_path = $_;
			last;
		}
3226
	}
3227 3228 3229 3230 3231 3232 3233 3234 3235
	$longest_path;
}

sub gs_fetch_loop_common {
	my ($self, $base, $head, $gsv, $globs) = @_;
	return if ($base > $head);
	my $inc = $_log_window_size;
	my ($min, $max) = ($base, $head < $base + $inc ? $head : $base + $inc);
	my $longest_path = longest_common_path($gsv, $globs);
3236
	my $ra_url = $self->{url};
3237
	while (1) {
3238
		my %revs;
3239
		my $err;
3240
		my $err_handler = $SVN::Error::handler;
3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271
		$SVN::Error::handler = sub {
			($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;
				}
			}
		}
3272
		$SVN::Error::handler = $err_handler;
3273

3274
		my %exists = map { $_->{path} => $_ } @$gsv;
3275
		foreach my $r (sort {$a <=> $b} keys %revs) {
3276
			my ($paths, $logged) = @{$revs{$r}};
3277 3278 3279

			foreach my $gs ($self->match_globs(\%exists, $paths,
			                                   $globs, $r)) {
3280 3281 3282 3283 3284
				if ($gs->rev_db_max >= $r) {
					next;
				}
				next unless $gs->match_paths($paths, $r);
				$gs->{logged_rev_props} = $logged;
3285 3286 3287
				if (my $last_commit = $gs->last_commit) {
					$gs->assert_index_clean($last_commit);
				}
3288 3289
				my $log_entry = $gs->do_fetch($paths, $r);
				if ($log_entry) {
3290 3291 3292
					$gs->do_git_commit($log_entry);
				}
			}
3293
			foreach my $g (@$globs) {
3294 3295 3296
				my $k = "svn-remote.$g->{remote}." .
				        "$g->{t}-maxRev";
				Git::SVN::tmp_config($k, $r);
3297
			}
3298 3299 3300 3301 3302 3303 3304
			if ($ra_invalid) {
				$_[0] = undef;
				$self = undef;
				$RA = undef;
				$self = Git::SVN::Ra->new($ra_url);
				$ra_invalid = undef;
			}
3305
		}
3306 3307
		# pre-fill the .rev_db since it'll eventually get filled in
		# with '0' x40 if something new gets committed
3308
		foreach my $gs (@$gsv) {
3309 3310 3311
			next if defined $gs->rev_db_get($max);
			$gs->rev_db_set($max, 0 x40);
		}
3312 3313 3314 3315
		foreach my $g (@$globs) {
			my $k = "svn-remote.$g->{remote}.$g->{t}-maxRev";
			Git::SVN::tmp_config($k, $max);
		}
3316 3317 3318 3319 3320 3321 3322
		last if $max >= $head;
		$min = $max + 1;
		$max += $inc;
		$max = $head if ($max > $head);
	}
}

3323 3324
sub match_globs {
	my ($self, $exists, $paths, $globs, $r) = @_;
3325 3326 3327 3328 3329 3330 3331

	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) {
3332
			next if $dirents->{$de}->{kind} != $SVN::Node::dir;
3333 3334 3335 3336 3337 3338 3339 3340 3341
			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);
		}
	}
3342
	foreach my $g (@$globs) {
3343 3344 3345 3346 3347
		if (my $path = $paths->{"/$g->{path}->{left}"}) {
			if ($path->{action} =~ /^[AR]$/) {
				get_dir_check($self, $exists, $g, $r);
			}
		}
3348
		foreach (keys %$paths) {
E
Eric Wong 已提交
3349 3350
			if (/$g->{path}->{left_regex}/ &&
			    !/$g->{path}->{regex}/) {
3351 3352 3353
				next if $paths->{$_}->{action} !~ /^[AR]$/;
				get_dir_check($self, $exists, $g, $r);
			}
3354 3355 3356 3357
			next unless /$g->{path}->{regex}/;
			my $p = $1;
			my $pathname = $g->{path}->full_path($p);
			next if $exists->{$pathname};
3358 3359
			next if ($self->check_path($pathname, $r) !=
			         $SVN::Node::dir);
3360 3361 3362 3363 3364 3365 3366 3367
			$exists->{$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} &&
3368 3369
			             ($paths->{$c}->{action} =~ /^[AR]$/));
			get_dir_check($self, $exists, $g, $r);
3370 3371 3372 3373 3374
		}
	}
	values %$exists;
}

3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387
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;
}

3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406
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;
}

3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419
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) {
3420 3421 3422 3423 3424 3425 3426 3427 3428 3429
		my $err_key = $err->expanded_message;
		# revision numbers change every time, filter them out
		$err_key =~ s/\d+/\0/g;
		$err_key = "$errno\0$err_key";
		unless ($ignored_err{$err_key}) {
			warn "W: Ignoring error from SVN, path probably ",
			     "does not exist: ($errno): ",
			     $err->expanded_message,"\n";
			$ignored_err{$err_key} = 1;
		}
3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452
		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;
}

3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463
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};
3464 3465

	# big commit message got truncated by the 16k pretty buffer in rev-list
3466 3467
	if ($c->{l} && $c->{l}->[-1] eq "...\n" &&
				$c->{a_raw} =~ /\@([a-f\d\-]+)>$/) {
3468
		@{$c->{l}} = ();
3469
		my @log = command(qw/cat-file commit/, $c->{c});
3470 3471 3472

		# shift off the headers
		shift @log while ($log[0] ne '');
3473
		shift @log;
3474 3475 3476

		# TODO: make $c->{l} not have a trailing newline in the future
		@{$c->{l}} = map { "$_\n" } grep !/^git-svn-id: /, @log;
3477 3478

		(undef, $c->{r}, undef) = ::extract_metadata(
3479
				(grep(/^git-svn-id: /, @log))[-1]);
3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520
	}
	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 {
3521 3522
	my ($r_min, $r_max, @args) = @_;
	my $head = 'HEAD';
3523
	my (@files, @log_opts);
3524
	foreach my $x (@args) {
3525 3526 3527 3528 3529 3530 3531 3532 3533
		if ($x eq '--' || @files) {
			push @files, $x;
		} else {
			if (::verify_ref("$x^0")) {
				$head = $x;
			} else {
				push @log_opts, $x;
			}
		}
3534 3535
	}

3536 3537
	my ($url, $rev, $uuid, $gs) = ::working_head_info($head);
	$gs ||= Git::SVN->_new;
3538 3539 3540 3541 3542
	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();
3543 3544
	push @cmd, @log_opts;
	if (defined $r_max && $r_max == $r_min) {
3545 3546 3547 3548
		push @cmd, '--max-count=1';
		if (my $c = $gs->rev_db_get($r_max)) {
			push @cmd, $c;
		}
3549
	} elsif (defined $r_max) {
3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564
		my ($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;
		}
	}
3565
	return (@cmd, @files);
3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578
}

# 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 {
3579
	return unless -t *STDOUT && defined $pager;
3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591
	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";
}

3592 3593 3594 3595 3596 3597
sub tz_to_s_offset {
	my ($tz) = @_;
	$tz =~ s/(\d\d)$//;
	return ($1 * 60) + ($tz * 3600);
}

3598 3599 3600 3601 3602
sub get_author_info {
	my ($dest, $author, $t, $tz) = @_;
	$author =~ s/(?:^\s*|\s*$)//g;
	$dest->{a_raw} = $author;
	my $au;
3603
	if ($::_authors) {
3604 3605 3606 3607 3608 3609 3610 3611 3612 3613
		$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/^\+//) {
3614
		$t += tz_to_s_offset($tz);
3615
	} elsif ($tz =~ s/^\-//) {
3616
		$t -= tz_to_s_offset($tz);
3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 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 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700
	}
	$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";

	}
3701
	foreach my $x (qw/raw stat diff/) {
3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729
		if ($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();
3730
	@args = git_svn_log_cmd($r_min, $r_max, @args);
3731 3732
	my $log = command_output_pipe(@args);
	run_pager();
3733
	my (@k, $c, $d, $stat);
3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760
	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}}, $_;
3761 3762 3763 3764 3765 3766 3767
		} 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}}, $_;
			$stat = undef;
3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784
		} elsif (/^${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:
3785
	close $log;
3786 3787 3788
	print '-' x72,"\n" unless $incremental || $oneline;
}

3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802
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
3803 3804 3805
# v3.1 layout (auto migrated):
#            - .rev_db => .rev_db.$UUID, .rev_db will remain as a symlink
#              for backwards compatibility
3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816
#
# v4 layout: .git/svn/$repo_id/$id, refs/remotes/$repo_id/$id
#            - this is only created for newly multi-init-ed
#              repositories.  Similar in spirit to the
#              --use-separate-remotes option in git-clone (now default)
#            - we do not automatically migrate to this (following
#              the example set by core git)
use strict;
use warnings;
use Carp qw/croak/;
use File::Path qw/mkpath/;
3817 3818
use File::Basename qw/dirname basename/;
use vars qw/$_minimize/;
3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927

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 $ref_id (sort keys %l_map) {
3928 3929 3930 3931
		eval { Git::SVN->init($l_map{$ref_id}, '', undef, $ref_id) };
		if ($@) {
			Git::SVN->init($l_map{$ref_id}, '', $ref_id, $ref_id);
		}
3932 3933 3934 3935 3936
		$migrated++;
	}
	$migrated;
}

3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955
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};
3956
		$root_path =~ s#^\Q$ra->{repos_root}\E(/|$)##;
3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998
		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/$x->{ref_id}");
3999
			command_noisy(qw/config --unset/,
4000 4001 4002 4003
			              "$pfx.fetch", '^'. $old_fetch . '$');
			delete $r->{$x->{old_repo_id}}->
			       {fetch}->{$x->{old_path}};
			if (!keys %{$r->{$x->{old_repo_id}}->{fetch}}) {
4004
				command_noisy(qw/config --unset/,
4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020
				              "$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;
	}
}

4021 4022 4023 4024
sub migration_check {
	migrate_from_v0();
	migrate_from_v1();
	migrate_from_v2();
4025
	minimize_connections() if $_minimize;
4026 4027
}

4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059
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});
}

4060 4061 4062 4063 4064 4065 4066 4067
package Git::SVN::GlobSpec;
use strict;
use warnings;

sub new {
	my ($class, $glob) = @_;
	my $re = $glob;
	$re =~ s!/+$!!g; # no need for trailing slashes
4068
	my $nr = ($re =~ s!^(.*)\*(.*)$!\(\[^/\]+\)!g);
4069 4070
	my ($left, $right) = ($1, $2);
	if ($nr > 1) {
4071 4072
		die "Only one '*' wildcard expansion ",
		    "is supported (got $nr): '$glob'\n";
4073
	} elsif ($nr == 0) {
4074
		die "One '*' is needed for glob: '$glob'\n";
4075 4076
	}
	$re = quotemeta($left) . $re . quotemeta($right);
4077 4078 4079 4080 4081 4082
	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";
	}
4083 4084
	my $left_re = qr/^\/\Q$left\E(\/|$)/;
	bless { left => $left, right => $right, left_regex => $left_re,
4085 4086 4087 4088 4089 4090 4091 4092 4093
	        regex => qr/$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
4094 4095 4096 4097
__END__

Data structures:

4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124

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

4125
$log_entry hashref as returned by libsvn_log_entry()
E
Eric Wong 已提交
4126
{
4127
	log => 'whitespace-formatted log entry
E
Eric Wong 已提交
4128 4129 4130 4131 4132 4133
',						# trailing newline is preserved
	revision => '8',			# integer
	date => '2004-02-24T17:01:44.108345Z',	# commit date
	author => 'committer name'
};

4134 4135

# this is generated by generate_diff();
E
Eric Wong 已提交
4136 4137 4138 4139 4140 4141 4142 4143
@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,
4144
	chg => change type [MCRADT],
E
Eric Wong 已提交
4145 4146 4147 4148
	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)
}
;
4149

4150 4151 4152 4153 4154 4155 4156 4157 4158 4159
# 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',
	},
}

4160 4161 4162
Notes:
	I don't trust the each() function on unless I created %hash myself
	because the internal iterator may not have started at base.