git-svn.perl 148.8 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
A
Adam Roben 已提交
7
		$sha1 $sha1_short $_revision $_repository
8
		$_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

B
Benoit Sigoure 已提交
12 13 14 15 16
# From which subdir have we been invoked?
my $cmd_dir_prefix = eval {
	command_oneline([qw/rev-parse --show-prefix/], STDERR => 0)
} || '';

17
my $git_dir_user_set = 1 if defined $ENV{GIT_DIR};
18
$ENV{GIT_DIR} ||= '.git';
19
$Git::SVN::default_repo_id = 'svn';
20
$Git::SVN::default_ref_id = $ENV{GIT_SVN_ID} || 'git-svn';
21
$Git::SVN::Ra::_log_window_size = 100;
22

23
$Git::SVN::Log::TZ = $ENV{TZ};
E
Eric Wong 已提交
24
$ENV{TZ} = 'UTC';
25
$| = 1; # unbuffer STDOUT
E
Eric Wong 已提交
26

27
sub fatal (@) { print STDERR "@_\n"; exit 1 }
28 29 30 31
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') {
32
	fatal "Need SVN::Core 1.1.0 or better (got $SVN::Core::VERSION)";
33
}
34
push @Git::SVN::Ra::ISA, 'SVN::Ra';
35 36
push @SVN::Git::Editor::ISA, 'SVN::Delta::Editor';
push @SVN::Git::Fetcher::ISA, 'SVN::Delta::Editor';
E
Eric Wong 已提交
37
use Carp qw/croak/;
38
use Digest::MD5;
E
Eric Wong 已提交
39 40 41
use IO::File qw//;
use File::Basename qw/dirname basename/;
use File::Path qw/mkpath/;
42
use Getopt::Long qw/:config gnu_getopt no_ignore_case auto_abbrev/;
43
use IPC::Open3;
44
use Git;
45

46
BEGIN {
47 48
	# import functions from Git into our packages, en masse
	no strict 'refs';
49 50
	foreach (qw/command command_oneline command_noisy command_output_pipe
	            command_input_pipe command_close_pipe/) {
51
		for my $package ( qw(SVN::Git::Editor SVN::Git::Fetcher
52
			Git::SVN::Migration Git::SVN::Log Git::SVN),
53 54 55
			__PACKAGE__) {
			*{"${package}::$_"} = \&{"Git::$_"};
		}
56 57 58
	}
}

59
my ($SVN);
60

61 62
$sha1 = qr/[a-f\d]{40}/;
$sha1_short = qr/[a-f\d]{4,40}/;
63
my ($_stdin, $_help, $_edit,
64
	$_message, $_file,
65
	$_template, $_shared,
66
	$_version, $_fetch_all, $_no_rebase,
67
	$_merge, $_strategy, $_dry_run, $_local,
68
	$_prefix, $_no_checkout, $_url, $_verbose,
69
	$_git_format, $_commit_url, $_tag);
70
$Git::SVN::_follow_parent = 1;
71 72 73
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 );
74
my %fc_opts = ( 'follow-parent|follow!' => \$Git::SVN::_follow_parent,
75
		'authors-file|A=s' => \$_authors,
E
Eric Wong 已提交
76
		'repack:i' => \$Git::SVN::_repack,
77 78
		'noMetadata' => \$Git::SVN::_no_metadata,
		'useSvmProps' => \$Git::SVN::_use_svm_props,
79
		'useSvnsyncProps' => \$Git::SVN::_use_svnsync_props,
80
		'log-window-size=i' => \$Git::SVN::Ra::_log_window_size,
81
		'no-checkout' => \$_no_checkout,
82
		'quiet|q' => \$_q,
E
Eric Wong 已提交
83 84
		'repack-flags|repack-args|repack-opts=s' =>
		   \$Git::SVN::_repack_flags,
85
		'use-log-author' => \$Git::SVN::_use_log_author,
86
		'add-author-from' => \$Git::SVN::_add_author_from,
87
		'localtime' => \$Git::SVN::_localtime,
88
		%remote_opts );
89

90
my ($_trunk, $_tags, $_branches, $_stdlayout);
91
my %icv;
92 93 94
my %init_opts = ( 'template=s' => \$_template, 'shared:s' => \$_shared,
                  'trunk|T=s' => \$_trunk, 'tags|t=s' => \$_tags,
                  'branches|b=s' => \$_branches, 'prefix=s' => \$_prefix,
95
                  'stdlayout|s' => \$_stdlayout,
96
                  'minimize-url|m' => \$Git::SVN::_minimize_url,
97 98 99 100
		  '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] },
101
                  %remote_opts );
E
Eric Wong 已提交
102
my %cmt_opts = ( 'edit|e' => \$_edit,
103 104 105 106
		'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
107
);
108

E
Eric Wong 已提交
109
my %cmd = (
110
	fetch => [ \&cmd_fetch, "Download new revisions from SVN",
111
			{ 'revision|r=s' => \$_revision,
E
Eric Wong 已提交
112
			  'fetch-all|all' => \$_fetch_all,
113
			   %fc_opts } ],
114 115 116
	clone => [ \&cmd_clone, "Initialize and fetch revisions",
			{ 'revision|r=s' => \$_revision,
			   %fc_opts, %init_opts } ],
117
	init => [ \&cmd_init, "Initialize a repo for tracking" .
118
			  " (requires URL argument)",
119
			  \%init_opts ],
120 121 122 123
	'multi-init' => [ \&cmd_multi_init,
	                  "Deprecated alias for ".
			  "'$0 init -T<trunk> -b<branches> -t<tags>'",
			  \%init_opts ],
124 125
	dcommit => [ \&cmd_dcommit,
	             'Commit several diffs to merge with upstream',
126 127
			{ 'merge|m|M' => \$_merge,
			  'strategy|s=s' => \$_strategy,
E
Eric Wong 已提交
128
			  'verbose|v' => \$_verbose,
129
			  'dry-run|n' => \$_dry_run,
E
Eric Wong 已提交
130
			  'fetch-all|all' => \$_fetch_all,
131 132
			  'commit-url=s' => \$_commit_url,
			  'revision|r=i' => \$_revision,
133
			  'no-rebase' => \$_no_rebase,
134
			%cmt_opts, %fc_opts } ],
135 136 137 138 139 140 141 142 143
	branch => [ \&cmd_branch,
	            'Create a branch in the SVN repository',
	            { 'message|m=s' => \$_message,
	              'dry-run|n' => \$_dry_run,
		      'tag|t' => \$_tag } ],
	tag => [ sub { $_tag = 1; cmd_branch(@_) },
	         'Create a tag in the SVN repository',
	         { 'message|m=s' => \$_message,
	           'dry-run|n' => \$_dry_run } ],
144 145 146
	'set-tree' => [ \&cmd_set_tree,
	                "Set an SVN repository to a git tree-ish",
			{ 'stdin|' => \$_stdin, %cmt_opts, %fc_opts, } ],
147 148 149 150
	'create-ignore' => [ \&cmd_create_ignore,
			     'Create a .gitignore per svn:ignore',
			     { 'revision|r=i' => \$_revision
			     } ],
B
Benoit Sigoure 已提交
151 152 153
        'propget' => [ \&cmd_propget,
		       'Print the value of a property on a file or directory',
		       { 'revision|r=i' => \$_revision } ],
B
Benoit Sigoure 已提交
154 155 156
        'proplist' => [ \&cmd_proplist,
		       'List all properties of a file or directory',
		       { 'revision|r=i' => \$_revision } ],
157
	'show-ignore' => [ \&cmd_show_ignore, "Show svn:ignore listings",
L
Lars Hjemli 已提交
158
			{ 'revision|r=i' => \$_revision
159
			} ],
160 161 162
	'show-externals' => [ \&cmd_show_externals, "Show svn:externals listings",
			{ 'revision|r=i' => \$_revision
			} ],
163
	'multi-fetch' => [ \&cmd_multi_fetch,
164 165
	                   "Deprecated alias for $0 fetch --all",
			   { 'revision|r=s' => \$_revision, %fc_opts } ],
166 167 168 169
	'migrate' => [ sub { },
	               # no-op, we automatically run this anyways,
	               'Migrate configuration/metadata/layout from
		        previous versions of git-svn',
170 171
                       { 'minimize' => \$Git::SVN::Migration::_minimize,
			 %remote_opts } ],
172 173
	'log' => [ \&Git::SVN::Log::cmd_show_log, 'Show commit logs',
			{ 'limit=i' => \$Git::SVN::Log::limit,
174
			  'revision|r=s' => \$_revision,
175 176 177 178 179
			  '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,
180
			  'authors-file|A=s' => \$_authors,
181
			  'color' => \$Git::SVN::Log::color,
L
Lars Hjemli 已提交
182
			  'pager=s' => \$Git::SVN::Log::pager
183
			} ],
184 185
	'find-rev' => [ \&cmd_find_rev,
	                "Translate between SVN revision numbers and tree-ish",
L
Lars Hjemli 已提交
186
			{} ],
E
Eric Wong 已提交
187 188 189 190
	'rebase' => [ \&cmd_rebase, "Fetch and rebase your working directory",
			{ 'merge|m|M' => \$_merge,
			  'verbose|v' => \$_verbose,
			  'strategy|s=s' => \$_strategy,
191
			  'local|l' => \$_local,
E
Eric Wong 已提交
192
			  'fetch-all|all' => \$_fetch_all,
193
			  'dry-run|n' => \$_dry_run,
E
Eric Wong 已提交
194
			  %fc_opts } ],
195 196
	'commit-diff' => [ \&cmd_commit_diff,
	                   'Commit a diff between two trees',
E
Eric Wong 已提交
197 198
			{ 'message|m=s' => \$_message,
			  'file|F=s' => \$_file,
199
			  'revision|r=s' => \$_revision,
E
Eric Wong 已提交
200
			%cmt_opts } ],
201 202 203
	'info' => [ \&cmd_info,
		    "Show info about the latest SVN revision
		     on the current branch",
D
David D. Kilzer 已提交
204
		    { 'url' => \$_url, } ],
T
Tim Stoakes 已提交
205 206
	'blame' => [ \&Git::SVN::Log::cmd_blame,
	            "Show what revision and author last modified each line of a file",
207
		    { 'git-format' => \$_git_format } ],
E
Eric Wong 已提交
208
);
209

E
Eric Wong 已提交
210 211 212 213 214 215 216 217 218
my $cmd;
for (my $i = 0; $i < @ARGV; $i++) {
	if (defined $cmd{$ARGV[$i]}) {
		$cmd = $ARGV[$i];
		splice @ARGV, $i, 1;
		last;
	}
};

219 220
# make sure we're always running at the top-level working directory
unless ($cmd && $cmd =~ /(?:clone|init|multi-init)$/) {
221 222 223 224 225 226
	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};
227 228 229 230 231 232 233
		my $cdup = undef;
		git_cmd_try {
			$cdup = command_oneline(qw/rev-parse --show-cdup/);
			$git_dir = '.' unless ($cdup);
			chomp $cdup if ($cdup);
			$cdup = "." unless ($cdup && length $cdup);
		} "Already at toplevel, but $git_dir not found\n";
234 235 236 237 238 239 240
		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;
	}
A
Adam Roben 已提交
241
	$_repository = Git->repository(Repository => $ENV{GIT_DIR});
242
}
243 244 245 246

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

read_repo_config(\%opts);
247 248 249
if ($cmd && ($cmd eq 'log' || $cmd eq 'blame')) {
	Getopt::Long::Configure('pass_through');
}
250 251 252 253 254 255 256 257 258 259 260 261 262
my $rv = GetOptions(%opts, 'help|H|h' => \$_help, 'version|V' => \$_version,
                    'minimize-connections' => \$Git::SVN::Migration::_minimize,
                    'id|i=s' => \$Git::SVN::default_ref_id,
                    'svn-remote|remote|R=s' => sub {
                       $Git::SVN::no_reuse_existing = 1;
                       $Git::SVN::default_repo_id = $_[1] });
exit 1 if (!$rv && $cmd && $cmd ne 'log');

usage(0) if $_help;
version() if $_version;
usage(1) unless defined $cmd;
load_authors() if $_authors;

263
unless ($cmd =~ /^(?:clone|init|multi-init|commit-diff)$/) {
264 265
	Git::SVN::Migration::migration_check();
}
E
Eric Wong 已提交
266
Git::SVN::init_vars();
267 268 269 270 271
eval {
	Git::SVN::verify_remotes_sanity();
	$cmd{$cmd}->[0]->(@ARGV);
};
fatal $@ if $@;
272
post_fetch_checkout();
E
Eric Wong 已提交
273 274 275 276 277 278 279 280
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
S
Stephan Beyer 已提交
281
Usage: git svn <command> [options] [arguments]\n
282 283

	print $fd "Available commands:\n" unless $cmd;
E
Eric Wong 已提交
284 285

	foreach (sort keys %cmd) {
286
		next if $cmd && $cmd ne $_;
287
		next if /^multi-/; # don't show deprecated commands
288
		print $fd '  ',pack('A17',$_),$cmd{$_}->[1],"\n";
289
		foreach (sort keys %{$cmd{$_}->[2]}) {
290 291
			# mixed-case options are for .git/config only
			next if /[A-Z]/ && /^[a-z]+$/i;
292
			# prints out arguments as they should be passed:
293
			my $x = s#[:=]s$## ? '<arg>' : s#[:=]i$## ? '<num>' : '';
294
			print $fd ' ' x 21, join(', ', map { length $_ > 1 ?
295 296 297
							"--$_" : "-$_" }
						split /\|/,$_)," $x\n";
		}
E
Eric Wong 已提交
298 299
	}
	print $fd <<"";
300 301 302 303
\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
304 305 306 307

	exit $exit;
}

308
sub version {
309
	print "git-svn version $VERSION (svn $SVN::Core::VERSION)\n";
310 311 312
	exit 0;
}

313 314 315 316
sub do_git_init_db {
	unless (-d $ENV{GIT_DIR}) {
		my @init_db = ('init');
		push @init_db, "--template=$_template" if defined $_template;
317 318 319 320 321 322 323
		if (defined $_shared) {
			if ($_shared =~ /[a-z]/) {
				push @init_db, "--shared=$_shared";
			} else {
				push @init_db, "--shared";
			}
		}
324
		command_noisy(@init_db);
A
Adam Roben 已提交
325
		$_repository = Git->repository(Repository => ".git");
326
	}
327 328 329 330 331 332 333 334
	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;
	}
335 336
}

337 338 339 340
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";
341
	$ENV{GIT_DIR} = '.git';
A
Adam Roben 已提交
342
	$_repository = Git->repository(Repository => $ENV{GIT_DIR});
343 344
}

345 346 347
sub cmd_clone {
	my ($url, $path) = @_;
	if (!defined $path &&
348 349
	    (defined $_trunk || defined $_branches || defined $_tags ||
	     defined $_stdlayout) &&
350 351 352 353
	    $url !~ m#^[a-z\+]+://#) {
		$path = $url;
	}
	$path = basename($url) if !defined $path || !length $path;
354
	cmd_init($url, $path);
355 356 357
	Git::SVN::fetch_all($Git::SVN::default_repo_id);
}

358
sub cmd_init {
359 360 361 362 363
	if (defined $_stdlayout) {
		$_trunk = 'trunk' if (!defined $_trunk);
		$_tags = 'tags' if (!defined $_tags);
		$_branches = 'branches' if (!defined $_branches);
	}
364 365
	if (defined $_trunk || defined $_branches || defined $_tags) {
		return cmd_multi_init(@_);
366
	}
367 368 369
	my $url = shift or die "SVN repository location required ",
	                       "as a command-line argument\n";
	init_subdir(@_);
370
	do_git_init_db();
371

372
	Git::SVN->init($url);
E
Eric Wong 已提交
373 374
}

375
sub cmd_fetch {
376 377 378
	if (grep /^\d+=./, @_) {
		die "'<rev>=<commit>' fetch arguments are ",
		    "no longer supported.\n";
379
	}
380 381
	my ($remote) = @_;
	if (@_ > 1) {
E
Eric Wong 已提交
382
		die "Usage: $0 fetch [--all] [svn-remote]\n";
383 384 385 386 387 388
	}
	$remote ||= $Git::SVN::default_repo_id;
	if ($_fetch_all) {
		cmd_multi_fetch();
	} else {
		Git::SVN::fetch_all($remote, Git::SVN::read_all_remotes());
389
	}
390 391
}

392
sub cmd_set_tree {
E
Eric Wong 已提交
393 394 395 396 397
	my (@commits) = @_;
	if ($_stdin || !@commits) {
		print "Reading from stdin...\n";
		@commits = ();
		while (<STDIN>) {
398
			if (/\b($sha1_short)\b/o) {
E
Eric Wong 已提交
399 400 401 402 403
				unshift @commits, $1;
			}
		}
	}
	my @revs;
404
	foreach my $c (@commits) {
E
Eric Wong 已提交
405
		my @tmp = command('rev-parse',$c);
406 407 408
		if (scalar @tmp == 1) {
			push @revs, $tmp[0];
		} elsif (scalar @tmp > 1) {
E
Eric Wong 已提交
409
			push @revs, reverse(command('rev-list',@tmp));
410
		} else {
411
			fatal "Failed to rev-parse $c";
412
		}
E
Eric Wong 已提交
413
	}
414 415 416
	my $gs = Git::SVN->new;
	my ($r_last, $cmt_last) = $gs->last_rev_commit;
	$gs->fetch;
417
	if (defined $gs->{last_rev} && $r_last != $gs->{last_rev}) {
418 419 420
		fatal "There are new revisions that were fetched ",
		      "and need to be merged (or acknowledged) ",
		      "before committing.\nlast rev: $r_last\n",
421
		      " current: $gs->{last_rev}";
422
	}
423 424
	$gs->set_tree($_) foreach @revs;
	print "Done committing ",scalar @revs," revisions to SVN\n";
425
	unlink $gs->{index};
426
}
427

428 429
sub cmd_dcommit {
	my $head = shift;
430
	git_cmd_try { command_oneline(qw/diff-index --quiet HEAD/) }
431
		'Cannot dcommit with a dirty index.  Commit your changes first, '
432
		. "or stash them with `git stash'.\n";
433
	$head ||= 'HEAD';
434
	my @refs;
435
	my ($url, $rev, $uuid, $gs) = working_head_info($head, \@refs);
436 437 438 439
	unless ($gs) {
		die "Unable to determine upstream SVN information from ",
		    "$head history.\nPerhaps the repository is empty.";
	}
440
	$url = defined $_commit_url ? $_commit_url : $gs->full_url;
441
	my $last_rev = $_revision if defined $_revision;
442 443 444
	if ($url) {
		print "Committing to $url ...\n";
	}
445
	my ($linear_refs, $parents) = linearize_history($gs, \@refs);
446 447 448 449
	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 ",
450
		     "without --no-rebase may be required."
451
	}
452 453
	my $expect_url = $url;
	Git::SVN::remove_username($expect_url);
454 455
	while (1) {
		my $d = shift @$linear_refs or last;
456 457 458
		unless (defined $last_rev) {
			(undef, $last_rev, undef) = cmt_metadata("$d~1");
			unless (defined $last_rev) {
459
				fatal "Unable to extract revision information ",
460
				      "from commit $d~1";
461 462
			}
		}
E
Eric Wong 已提交
463 464 465
		if ($_dry_run) {
			print "diff-tree $d~1 $d\n";
		} else {
466
			my $cmt_rev;
467
			my %ed_opts = ( r => $last_rev,
468
			                log => get_commit_entry($d)->{log},
469
			                ra => Git::SVN::Ra->new($url),
470 471 472
			                config => SVN::Core::config_get_config(
			                        $Git::SVN::Ra::config_dir
			                ),
473 474 475 476
			                tree_a => "$d~1",
			                tree_b => $d,
			                editor_cb => sub {
			                       print "Committed r$_[0]\n";
477 478
			                       $cmt_rev = $_[0];
			                },
479
			                svn_path => '');
480
			if (!SVN::Git::Editor->new(\%ed_opts)->apply_diff) {
481
				print "No changes\n$d~1 == $d\n";
482
			} elsif ($parents->{$d} && @{$parents->{$d}}) {
483
				$gs->{inject_parents_dcommit}->{$cmt_rev} =
484
				                               $parents->{$d};
485
			}
486
			$_fetch_all ? $gs->fetch_all : $gs->fetch;
487
			$last_rev = $cmt_rev;
488 489 490 491
			next if $_no_rebase;

			# we always want to rebase against the current HEAD,
			# not any head that was passed to us
492
			my @diff = command('diff-tree', $d,
493 494 495 496
			                   $gs->refname, '--');
			my @finish;
			if (@diff) {
				@finish = rebase_cmd();
497
				print STDERR "W: $d and ", $gs->refname,
498
				             " differ, using @finish:\n",
499
				             join("\n", @diff), "\n";
500 501 502 503 504 505 506 507
			} else {
				print "No changes between current HEAD and ",
				      $gs->refname,
				      "\nResetting to the latest ",
				      $gs->refname, "\n";
				@finish = qw/reset --mixed/;
			}
			command_noisy(@finish, $gs->refname);
508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527
			if (@diff) {
				@refs = ();
				my ($url_, $rev_, $uuid_, $gs_) =
				              working_head_info($head, \@refs);
				my ($linear_refs_, $parents_) =
				              linearize_history($gs_, \@refs);
				if (scalar(@$linear_refs) !=
				    scalar(@$linear_refs_)) {
					fatal "# of revisions changed ",
					  "\nbefore:\n",
					  join("\n", @$linear_refs),
					  "\n\nafter:\n",
					  join("\n", @$linear_refs_), "\n",
					  'If you are attempting to commit ',
					  "merges, try running:\n\t",
					  'git rebase --interactive',
					  '--preserve-merges ',
					  $gs->refname,
					  "\nBefore dcommitting";
				}
528
				if ($url_ ne $expect_url) {
529
					fatal "URL mismatch after rebase: ",
530
					      "$url_ != $expect_url";
531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546
				}
				if ($uuid_ ne $uuid) {
					fatal "uuid mismatch after rebase: ",
					      "$uuid_ != $uuid";
				}
				# remap parents
				my (%p, @l, $i);
				for ($i = 0; $i < scalar @$linear_refs; $i++) {
					my $new = $linear_refs_->[$i] or next;
					$p{$new} =
						$parents->{$linear_refs->[$i]};
					push @l, $new;
				}
				$parents = \%p;
				$linear_refs = \@l;
			}
E
Eric Wong 已提交
547 548
		}
	}
549
	unlink $gs->{index};
E
Eric Wong 已提交
550 551
}

552 553 554 555 556 557 558 559 560 561
sub cmd_branch {
	my ($branch_name, $head) = @_;

	unless (defined $branch_name && length $branch_name) {
		die(($_tag ? "tag" : "branch") . " name required\n");
	}
	$head ||= 'HEAD';

	my ($src, $rev, undef, $gs) = working_head_info($head);

562
	my $remote = Git::SVN::read_all_remotes()->{$gs->{repo_id}};
563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587
	my $glob = $remote->{ $_tag ? 'tags' : 'branches' };
	my ($lft, $rgt) = @{ $glob->{path} }{qw/left right/};
	my $dst = join '/', $remote->{url}, $lft, $branch_name, ($rgt || ());

	my $ctx = SVN::Client->new(
		auth    => Git::SVN::Ra::_auth_providers(),
		log_msg => sub {
			${ $_[0] } = defined $_message
				? $_message
				: 'Create ' . ($_tag ? 'tag ' : 'branch ' )
				. $branch_name;
		},
	);

	eval {
		$ctx->ls($dst, 'HEAD', 0);
	} and die "branch ${branch_name} already exists\n";

	print "Copying ${src} at r${rev} to ${dst}...\n";
	$ctx->copy($src, $rev, $dst)
		unless $_dry_run;

	$gs->fetch_all;
}

A
Adam Roben 已提交
588
sub cmd_find_rev {
589 590
	my $revision_or_hash = shift or die "SVN or git revision required ",
	                                    "as a command-line argument\n";
A
Adam Roben 已提交
591 592
	my $result;
	if ($revision_or_hash =~ /^r\d+$/) {
A
Adam Roben 已提交
593 594 595
		my $head = shift;
		$head ||= 'HEAD';
		my @refs;
596
		my (undef, undef, $uuid, $gs) = working_head_info($head, \@refs);
A
Adam Roben 已提交
597 598 599
		unless ($gs) {
			die "Unable to determine upstream SVN information from ",
			    "$head history\n";
A
Adam Roben 已提交
600
		}
A
Adam Roben 已提交
601
		my $desired_revision = substr($revision_or_hash, 1);
602
		$result = $gs->rev_map_get($desired_revision, $uuid);
A
Adam Roben 已提交
603 604 605 606 607 608 609
	} else {
		my (undef, $rev, undef) = cmt_metadata($revision_or_hash);
		$result = $rev;
	}
	print "$result\n" if $result;
}

E
Eric Wong 已提交
610 611
sub cmd_rebase {
	command_noisy(qw/update-index --refresh/);
612 613
	my ($url, $rev, $uuid, $gs) = working_head_info('HEAD');
	unless ($gs) {
E
Eric Wong 已提交
614 615 616
		die "Unable to determine upstream SVN information from ",
		    "working tree history\n";
	}
617 618 619 620 621
	if ($_dry_run) {
		print "Remote Branch: " . $gs->refname . "\n";
		print "SVN URL: " . $url . "\n";
		return;
	}
E
Eric Wong 已提交
622 623 624 625 626
	if (command(qw/diff-index HEAD --/)) {
		print STDERR "Cannot rebase with uncommited changes:\n";
		command_noisy('status');
		exit 1;
	}
627
	unless ($_local) {
628 629
		# rebase will checkout for us, so no need to do it explicitly
		$_no_checkout = 'true';
630 631
		$_fetch_all ? $gs->fetch_all : $gs->fetch;
	}
E
Eric Wong 已提交
632 633 634
	command_noisy(rebase_cmd(), $gs->refname);
}

635
sub cmd_show_ignore {
636 637
	my ($url, $rev, $uuid, $gs) = working_head_info('HEAD');
	$gs ||= Git::SVN->new;
638
	my $r = (defined $_revision ? $_revision : $gs->ra->get_latest_revnum);
639 640 641 642 643 644 645 646 647
	$gs->prop_walk($gs->{path}, $r, sub {
		my ($gs, $path, $props) = @_;
		print STDOUT "\n# $path\n";
		my $s = $props->{'svn:ignore'} or return;
		$s =~ s/[\r\n]+/\n/g;
		chomp $s;
		$s =~ s#^#$path#gm;
		print STDOUT "$s\n";
	});
648 649
}

650 651 652 653 654 655 656 657 658 659 660 661 662 663 664
sub cmd_show_externals {
	my ($url, $rev, $uuid, $gs) = working_head_info('HEAD');
	$gs ||= Git::SVN->new;
	my $r = (defined $_revision ? $_revision : $gs->ra->get_latest_revnum);
	$gs->prop_walk($gs->{path}, $r, sub {
		my ($gs, $path, $props) = @_;
		print STDOUT "\n# $path\n";
		my $s = $props->{'svn:externals'} or return;
		$s =~ s/[\r\n]+/\n/g;
		chomp $s;
		$s =~ s#^#$path#gm;
		print STDOUT "$s\n";
	});
}

665 666 667 668 669 670 671 672 673 674
sub cmd_create_ignore {
	my ($url, $rev, $uuid, $gs) = working_head_info('HEAD');
	$gs ||= Git::SVN->new;
	my $r = (defined $_revision ? $_revision : $gs->ra->get_latest_revnum);
	$gs->prop_walk($gs->{path}, $r, sub {
		my ($gs, $path, $props) = @_;
		# $path is of the form /path/to/dir/
		my $ignore = '.' . $path . '.gitignore';
		my $s = $props->{'svn:ignore'} or return;
		open(GITIGNORE, '>', $ignore)
675
		  or fatal("Failed to open `$ignore' for writing: $!");
676 677 678 679 680 681 682
		$s =~ s/[\r\n]+/\n/g;
		chomp $s;
		# Prefix all patterns so that the ignore doesn't apply
		# to sub-directories.
		$s =~ s#^#/#gm;
		print GITIGNORE "$s\n";
		close(GITIGNORE)
683
		  or fatal("Failed to close `$ignore': $!");
684
		command_noisy('add', '-f', $ignore);
685 686 687
	});
}

688 689
sub canonicalize_path {
	my ($path) = @_;
690 691 692 693 694
	my $dot_slash_added = 0;
	if (substr($path, 0, 1) ne "/") {
		$path = "./" . $path;
		$dot_slash_added = 1;
	}
695 696 697 698 699 700
	# File::Spec->canonpath doesn't collapse x/../y into y (for a
	# good reason), so let's do this manually.
	$path =~ s#/+#/#g;
	$path =~ s#/\.(?:/|$)#/#g;
	$path =~ s#/[^/]+/\.\.##g;
	$path =~ s#/$##g;
701
	$path =~ s#^\./## if $dot_slash_added;
702 703
	$path =~ s#^/##;
	$path =~ s#^\.$##;
704 705 706
	return $path;
}

B
Benoit Sigoure 已提交
707 708
# get_svnprops(PATH)
# ------------------
B
Benoit Sigoure 已提交
709
# Helper for cmd_propget and cmd_proplist below.
B
Benoit Sigoure 已提交
710 711 712 713 714 715 716 717
sub get_svnprops {
	my $path = shift;
	my ($url, $rev, $uuid, $gs) = working_head_info('HEAD');
	$gs ||= Git::SVN->new;

	# prefix THE PATH by the sub-directory from which the user
	# invoked us.
	$path = $cmd_dir_prefix . $path;
718
	fatal("No such file or directory: $path") unless -e $path;
B
Benoit Sigoure 已提交
719 720 721 722 723
	my $is_dir = -d $path ? 1 : 0;
	$path = $gs->{path} . '/' . $path;

	# canonicalize the path (otherwise libsvn will abort or fail to
	# find the file)
724
	$path = canonicalize_path($path);
B
Benoit Sigoure 已提交
725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745

	my $r = (defined $_revision ? $_revision : $gs->ra->get_latest_revnum);
	my $props;
	if ($is_dir) {
		(undef, undef, $props) = $gs->ra->get_dir($path, $r);
	}
	else {
		(undef, $props) = $gs->ra->get_file($path, $r, undef);
	}
	return $props;
}

# cmd_propget (PROP, PATH)
# ------------------------
# Print the SVN property PROP for PATH.
sub cmd_propget {
	my ($prop, $path) = @_;
	$path = '.' if not defined $path;
	usage(1) if not defined $prop;
	my $props = get_svnprops($path);
	if (not defined $props->{$prop}) {
746
		fatal("`$path' does not have a `$prop' SVN property.");
B
Benoit Sigoure 已提交
747 748 749 750
	}
	print $props->{$prop} . "\n";
}

B
Benoit Sigoure 已提交
751 752 753 754 755 756 757 758 759 760 761 762 763
# cmd_proplist (PATH)
# -------------------
# Print the list of SVN properties for PATH.
sub cmd_proplist {
	my $path = shift;
	$path = '.' if not defined $path;
	my $props = get_svnprops($path);
	print "Properties on '$path':\n";
	foreach (sort keys %{$props}) {
		print "  $_\n";
	}
}

764
sub cmd_multi_init {
765
	my $url = shift;
766 767
	unless (defined $_trunk || defined $_branches || defined $_tags) {
		usage(1);
768
	}
769 770 771 772 773

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

774
	$_prefix = '' unless defined $_prefix;
775 776 777 778
	if (defined $url) {
		$url =~ s#/+$##;
		init_subdir(@_);
	}
779
	do_git_init_db();
780
	if (defined $_trunk) {
781 782 783
		my $trunk_ref = $_prefix . 'trunk';
		# try both old-style and new-style lookups:
		my $gs_trunk = eval { Git::SVN->new($trunk_ref) };
784
		unless ($gs_trunk) {
785 786 787 788
			my ($trunk_url, $trunk_path) =
			                      complete_svn_url($url, $_trunk);
			$gs_trunk = Git::SVN->init($trunk_url, $trunk_path,
						   undef, $trunk_ref);
789
		}
790
	}
791
	return unless defined $_branches || defined $_tags;
792 793 794
	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/');
795 796
}

797
sub cmd_multi_fetch {
798 799
	my $remotes = Git::SVN::read_all_remotes();
	foreach my $repo_id (sort keys %$remotes) {
800
		if ($remotes->{$repo_id}->{url}) {
801 802
			Git::SVN::fetch_all($repo_id, $remotes);
		}
803 804 805
	}
}

806 807 808 809
# this command is special because it requires no metadata
sub cmd_commit_diff {
	my ($ta, $tb, $url) = @_;
	my $usage = "Usage: $0 commit-diff -r<revision> ".
810
	            "<tree-ish> <tree-ish> [<URL>]";
811
	fatal($usage) if (!defined $ta || !defined $tb);
812
	my $svn_path = '';
813 814 815 816 817 818 819
	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};
820
		$svn_path = $gs->{path};
821 822 823 824 825 826 827
	}
	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",
828
		      "I have no idea what you mean");
829 830 831 832 833 834 835 836 837 838 839 840 841
	}
	if (defined $_file) {
		$_message = file_to_s($_file);
	} else {
		$_message ||= get_commit_entry($tb)->{log};
	}
	my $ra ||= Git::SVN::Ra->new($url);
	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";
	}
842 843 844 845 846 847 848 849
	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 => $svn_path );
	if (!SVN::Git::Editor->new(\%ed_opts)->apply_diff) {
850 851 852 853
		print "No changes\n$ta == $tb\n";
	}
}

854 855 856 857
sub escape_uri_only {
	my ($uri) = @_;
	my @tmp;
	foreach (split m{/}, $uri) {
858
		s/([^~\w.%+-]|%(?![a-fA-F0-9]{2}))/sprintf("%%%02X",ord($1))/eg;
859 860 861 862 863 864 865 866 867 868 869 870 871 872
		push @tmp, $_;
	}
	join('/', @tmp);
}

sub escape_url {
	my ($url) = @_;
	if ($url =~ m#^([^:]+)://([^/]*)(.*)$#) {
		my ($scheme, $domain, $uri) = ($1, $2, escape_uri_only($3));
		$url = "$scheme://$domain$uri";
	}
	$url;
}

873
sub cmd_info {
874
	my $path = canonicalize_path(defined($_[0]) ? $_[0] : ".");
875
	my $fullpath = canonicalize_path($cmd_dir_prefix . $path);
876
	if (exists $_[1]) {
877 878 879 880 881 882
		die "Too many arguments specified\n";
	}

	my ($file_type, $diff_status) = find_file_type_and_diff_status($path);

	if (!$file_type && !$diff_status) {
883 884
		print STDERR "svn: '$path' is not under version control\n";
		exit 1;
885 886 887 888 889 890 891
	}

	my ($url, $rev, $uuid, $gs) = working_head_info('HEAD');
	unless ($gs) {
		die "Unable to determine upstream SVN information from ",
		    "working tree history\n";
	}
892 893 894 895

	# canonicalize_path() will return "" to make libsvn 1.5.x happy,
	$path = "." if $path eq "";

896
	my $full_url = $url . ($fullpath eq "" ? "" : "/$fullpath");
897

D
David D. Kilzer 已提交
898
	if ($_url) {
899
		print escape_url($full_url), "\n";
D
David D. Kilzer 已提交
900 901 902
		return;
	}

903 904
	my $result = "Path: $path\n";
	$result .= "Name: " . basename($path) . "\n" if $file_type ne "dir";
905
	$result .= "URL: " . escape_url($full_url) . "\n";
906

907 908 909
	eval {
		my $repos_root = $gs->repos_root;
		Git::SVN::remove_username($repos_root);
910
		$result .= "Repository Root: " . escape_url($repos_root) . "\n";
911 912 913 914
	};
	if ($@) {
		$result .= "Repository Root: (offline)\n";
	}
915 916
	$result .= "Repository UUID: $uuid\n" unless $diff_status eq "A" &&
		($SVN::Core::VERSION le '1.5.4' || $file_type ne "dir");
917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932
	$result .= "Revision: " . ($diff_status eq "A" ? 0 : $rev) . "\n";

	$result .= "Node Kind: " .
		   ($file_type eq "dir" ? "directory" : "file") . "\n";

	my $schedule = $diff_status eq "A"
		       ? "add"
		       : ($diff_status eq "D" ? "delete" : "normal");
	$result .= "Schedule: $schedule\n";

	if ($diff_status eq "A") {
		print $result, "\n";
		return;
	}

	my ($lc_author, $lc_rev, $lc_date_utc);
933
	my @args = Git::SVN::Log::git_svn_log_cmd($rev, $rev, "--", $fullpath);
934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965
	my $log = command_output_pipe(@args);
	my $esc_color = qr/(?:\033\[(?:(?:\d+;)*\d*)?m)*/;
	while (<$log>) {
		if (/^${esc_color}author (.+) <[^>]+> (\d+) ([\-\+]?\d+)$/o) {
			$lc_author = $1;
			$lc_date_utc = Git::SVN::Log::parse_git_date($2, $3);
		} elsif (/^${esc_color}    (git-svn-id:.+)$/o) {
			(undef, $lc_rev, undef) = ::extract_metadata($1);
		}
	}
	close $log;

	Git::SVN::Log::set_local_timezone();

	$result .= "Last Changed Author: $lc_author\n";
	$result .= "Last Changed Rev: $lc_rev\n";
	$result .= "Last Changed Date: " .
		   Git::SVN::Log::format_svn_date($lc_date_utc) . "\n";

	if ($file_type ne "dir") {
		my $text_last_updated_date =
		    ($diff_status eq "D" ? $lc_date_utc : (stat $path)[9]);
		$result .=
		    "Text Last Updated: " .
		    Git::SVN::Log::format_svn_date($text_last_updated_date) .
		    "\n";
		my $checksum;
		if ($diff_status eq "D") {
			my ($fh, $ctx) =
			    command_output_pipe(qw(cat-file blob), "HEAD:$path");
			if ($file_type eq "link") {
				my $file_name = <$fh>;
966
				$checksum = md5sum("link $file_name");
967
			} else {
968
				$checksum = md5sum($fh);
969 970 971 972 973 974
			}
			command_close_pipe($fh, $ctx);
		} elsif ($file_type eq "link") {
			my $file_name =
			    command(qw(cat-file blob), "HEAD:$path");
			$checksum =
975
			    md5sum("link " . $file_name);
976 977
		} else {
			open FILE, "<", $path or die $!;
978
			$checksum = md5sum(\*FILE);
979 980 981 982 983 984 985 986
			close FILE or die $!;
		}
		$result .= "Checksum: " . $checksum . "\n";
	}

	print $result, "\n";
}

E
Eric Wong 已提交
987 988
########################### utility functions #########################

E
Eric Wong 已提交
989 990 991 992 993 994 995 996
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;
}

997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009
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;

1010
	return if command_oneline(qw/rev-parse --is-inside-work-tree/) eq 'false';
1011 1012 1013 1014 1015 1016
	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";
}

1017 1018 1019 1020 1021 1022
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 ",
1023
			      "and a separate URL is not specified");
1024
		}
1025
		return ($url, $path);
1026
	}
1027
	return ($path, '');
1028 1029
}

1030
sub complete_url_ls_init {
1031 1032
	my ($ra, $repo_path, $switch, $pfx) = @_;
	unless ($repo_path) {
1033 1034 1035
		print STDERR "W: $switch not specified\n";
		return;
	}
1036 1037 1038 1039
	$repo_path =~ s#/+$##;
	if ($repo_path =~ m#^[a-z\+]+://#) {
		$ra = Git::SVN::Ra->new($repo_path);
		$repo_path = '';
1040
	} else {
1041
		$repo_path =~ s#^/+##;
1042
		unless ($ra) {
1043
			fatal("E: '$repo_path' is not a complete URL ",
1044
			      "and a separate URL is not specified");
1045
		}
1046
	}
1047
	my $url = $ra->{url};
1048 1049 1050 1051 1052 1053
	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";
1054
	}
1055
	command_oneline('config', $k, $gs->{url}) unless $orig_url;
1056
	my $remote_path = "$ra->{svn_path}/$repo_path";
1057 1058
	$remote_path =~ s#/+#/#g;
	$remote_path =~ s#^/##g;
1059
	$remote_path .= "/*" if $remote_path !~ /\*/;
1060 1061 1062
	my ($n) = ($switch =~ /^--(\w+)/);
	if (length $pfx && $pfx !~ m#/$#) {
		die "--prefix='$pfx' must have a trailing slash '/'\n";
1063
	}
1064 1065 1066 1067
	command_noisy('config',
	              "svn-remote.$gs->{repo_id}.$n",
	              "$remote_path:refs/remotes/$pfx*" .
	                ('/*' x (($remote_path =~ tr/*/*/) - 1)) );
1068 1069
}

E
Eric Wong 已提交
1070 1071
sub verify_ref {
	my ($ref) = @_;
1072 1073
	eval { command_oneline([ 'rev-parse', '--verify', $ref ],
	                       { STDERR => 0 }); };
E
Eric Wong 已提交
1074 1075
}

1076
sub get_tree_from_treeish {
1077
	my ($treeish) = @_;
1078
	# $treeish can be a symbolic ref, too:
E
Eric Wong 已提交
1079
	my $type = command_oneline(qw/cat-file -t/, $treeish);
1080 1081
	my $expected;
	while ($type eq 'tag') {
E
Eric Wong 已提交
1082
		($treeish, $type) = command(qw/cat-file tag/, $treeish);
1083 1084
	}
	if ($type eq 'commit') {
E
Eric Wong 已提交
1085 1086
		$expected = (grep /^tree /, command(qw/cat-file commit/,
		                                    $treeish))[0];
1087
		($expected) = ($expected =~ /^tree ($sha1)$/o);
1088 1089 1090 1091 1092 1093
		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";
	}
1094 1095 1096
	return $expected;
}

1097 1098 1099 1100 1101 1102
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
1103

1104
	my $type = command_oneline(qw/cat-file -t/, $treeish);
1105
	if ($type eq 'commit' || $type eq 'tag') {
E
Eric Wong 已提交
1106
		my ($msg_fh, $ctx) = command_output_pipe('cat-file',
1107
		                                         $type, $treeish);
E
Eric Wong 已提交
1108
		my $in_msg = 0;
1109 1110
		my $author;
		my $saw_from = 0;
1111
		my $msgbuf = "";
E
Eric Wong 已提交
1112 1113 1114
		while (<$msg_fh>) {
			if (!$in_msg) {
				$in_msg = 1 if (/^\s*$/);
1115
				$author = $1 if (/^author (.*>)/);
1116
			} elsif (/^git-svn-id: /) {
1117 1118 1119
				# 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
1120
			} else {
1121 1122 1123
				if (/^From:/ || /^Signed-off-by:/) {
					$saw_from = 1;
				}
1124
				$msgbuf .= $_;
E
Eric Wong 已提交
1125 1126
			}
		}
1127
		$msgbuf =~ s/\s+$//s;
1128 1129
		if ($Git::SVN::_add_author_from && defined($author)
		    && !$saw_from) {
1130
			$msgbuf .= "\n\nFrom: $author";
1131
		}
1132
		print $log_fh $msgbuf or croak $!;
E
Eric Wong 已提交
1133
		command_close_pipe($msg_fh, $ctx);
E
Eric Wong 已提交
1134
	}
1135
	close $log_fh or croak $!;
E
Eric Wong 已提交
1136 1137 1138

	if ($_edit || ($type eq 'tree')) {
		my $editor = $ENV{VISUAL} || $ENV{EDITOR} || 'vi';
1139 1140
		# TODO: strip out spaces, comments, like git-commit.sh
		system($editor, $commit_editmsg);
E
Eric Wong 已提交
1141
	}
1142
	rename $commit_editmsg, $commit_msg or croak $!;
1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155
	{
		# SVN requires messages to be UTF-8 when entering the repo
		local $/;
		open $log_fh, '<', $commit_msg or croak $!;
		binmode $log_fh;
		chomp($log_entry{log} = <$log_fh>);

		if (my $enc = Git::config('i18n.commitencoding')) {
			require Encode;
			Encode::from_to($log_entry{log}, $enc, 'UTF-8');
		}
		close $log_fh or croak $!;
	}
1156 1157
	unlink $commit_msg;
	\%log_entry;
1158 1159
}

E
Eric Wong 已提交
1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177
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;
}

1178 1179 1180
# '<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";
1181
	my $log = $cmd eq 'log';
1182 1183
	while (<$authors>) {
		chomp;
1184
		next unless /^(.+?|\(no author\))\s*=\s*(.+?)\s*<(.+)>\s*$/;
1185
		my ($user, $name, $email) = ($1, $2, $3);
1186 1187 1188 1189 1190
		if ($log) {
			$Git::SVN::Log::rusers{"$name <$email>"} = $user;
		} else {
			$users{$user} = [$name, $email];
		}
1191 1192 1193 1194
	}
	close $authors or croak $!;
}

1195
# convert GetOpt::Long specs for use by git-config
1196
sub read_repo_config {
1197
	return unless -d $ENV{GIT_DIR};
1198
	my $opts = shift;
1199
	my @config_only;
1200
	foreach my $o (keys %$opts) {
1201 1202 1203 1204
		# 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);
1205
		my $v = $opts->{$o};
1206
		my ($key) = ($o =~ /^([a-zA-Z\-]+)/);
1207
		$key =~ s/-//g;
1208
		my $arg = 'git config';
1209 1210 1211 1212 1213 1214 1215
		$arg .= ' --int' if ($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.$key`);
1216
			if ($tmp && !($arg =~ / --bool/ && $tmp eq 'false')) {
1217 1218 1219 1220
				$$v = $tmp;
			}
		}
	}
1221
	delete @$opts{@config_only} if @config_only;
1222 1223
}

1224
sub extract_metadata {
1225
	my $id = shift or return (undef, undef, undef);
1226
	my ($url, $rev, $uuid) = ($id =~ /^\s*git-svn-id:\s+(.*)\@(\d+)
1227
							\s([a-f\d\-]+)$/x);
1228
	if (!defined $rev || !$uuid || !$url) {
1229
		# some of the original repositories I made had
1230
		# identifiers like this:
1231
		($rev, $uuid) = ($id =~/^\s*git-svn-id:\s(\d+)\@([a-f\d\-]+)/);
1232 1233 1234 1235
	}
	return ($url, $rev, $uuid);
}

1236 1237
sub cmt_metadata {
	return extract_metadata((grep(/^git-svn-id: /,
E
Eric Wong 已提交
1238
		command(qw/cat-file commit/, shift)))[-1]);
1239 1240
}

E
Eric Wong 已提交
1241 1242
sub working_head_info {
	my ($head, $refs) = @_;
1243
	my @args = ('log', '--no-color', '--first-parent', '--pretty=medium');
1244
	my ($fh, $ctx) = command_output_pipe(@args, $head);
1245
	my $hash;
1246
	my %max;
1247 1248 1249 1250 1251 1252 1253 1254
	while (<$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, $uuid) = extract_metadata($_);
1255
		if (defined $url && defined $rev) {
1256
			next if $max{$url} and $max{$url} < $rev;
1257
			if (my $gs = Git::SVN->find_by_url($url)) {
1258
				my $c = $gs->rev_map_get($rev, $uuid);
1259
				if ($c && $c eq $hash) {
1260 1261
					close $fh; # break the pipe
					return ($url, $rev, $uuid, $gs);
1262
				} else {
1263
					$max{$url} ||= $gs->rev_map_max;
1264 1265 1266
				}
			}
		}
E
Eric Wong 已提交
1267
	}
1268 1269
	command_close_pipe($fh, $ctx);
	(undef, undef, undef, undef);
E
Eric Wong 已提交
1270 1271
}

1272 1273
sub read_commit_parents {
	my ($parents, $c) = @_;
1274 1275 1276
	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);
1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319
}

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);
}

1320 1321
sub find_file_type_and_diff_status {
	my ($path) = @_;
1322
	return ('dir', '') if $path eq '';
1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344

	my $diff_output =
	    command_oneline(qw(diff --cached --name-status --), $path) || "";
	my $diff_status = (split(' ', $diff_output))[0] || "";

	my $ls_tree = command_oneline(qw(ls-tree HEAD), $path) || "";

	return (undef, undef) if !$diff_status && !$ls_tree;

	if ($diff_status eq "A") {
		return ("link", $diff_status) if -l $path;
		return ("dir", $diff_status) if -d $path;
		return ("file", $diff_status);
	}

	my $mode = (split(' ', $ls_tree))[0] || "";

	return ("link", $diff_status) if $mode eq "120000";
	return ("dir", $diff_status) if $mode eq "040000";
	return ("file", $diff_status);
}

1345 1346 1347 1348
sub md5sum {
	my $arg = shift;
	my $ref = ref $arg;
	my $md5 = Digest::MD5->new();
1349
        if ($ref eq 'GLOB' || $ref eq 'IO::File' || $ref eq 'File::Temp') {
1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360
		$md5->addfile($arg) or croak $!;
	} elsif ($ref eq 'SCALAR') {
		$md5->add($$arg) or croak $!;
	} elsif (!$ref) {
		$md5->add($arg) or croak $!;
	} else {
		::fatal "Can't provide MD5 hash for unknown ref type: '", $ref, "'";
	}
	return $md5->hexdigest();
}

1361 1362 1363
package Git::SVN;
use strict;
use warnings;
1364 1365
use Fcntl qw/:DEFAULT :seek/;
use constant rev_map_fmt => 'NH40';
E
Eric Wong 已提交
1366
use vars qw/$default_repo_id $default_ref_id $_no_metadata $_follow_parent
1367
            $_repack $_repack_flags $_use_svm_props $_head
1368
            $_use_svnsync_props $no_reuse_existing $_minimize_url
1369
	    $_use_log_author $_add_author_from $_localtime/;
1370 1371
use Carp qw/croak/;
use File::Path qw/mkpath/;
1372
use File::Copy qw/copy/;
1373 1374
use IPC::Open3;

1375 1376
my ($_gc_nr, $_gc_period);

1377 1378 1379 1380 1381 1382 1383 1384 1385
# 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/;
1386 1387 1388 1389

	# 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
1390 1391 1392 1393
	no strict 'refs';
	for my $option (qw/follow_parent no_metadata use_svm_props
			   use_svnsync_props/) {
		my $key = $option;
1394
		$key =~ tr/_//d;
1395 1396 1397 1398 1399 1400 1401 1402
		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"};
1403
			} else {
1404 1405
				my $v = command_oneline(qw/config --bool/,$k);
				$self->{$prop} = $v eq 'false' ? 0 : 1;
1406
			}
1407 1408
			return $self->{$prop};
		}
1409
	}
1410 1411
}

1412

1413 1414 1415 1416 1417
my (%LOCKFILES, %INDEX_FILES);
END {
	unlink keys %LOCKFILES if %LOCKFILES;
	unlink keys %INDEX_FILES if %INDEX_FILES;
}
1418

1419 1420 1421 1422 1423 1424 1425 1426
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;
1427 1428
		my $pathname = desanitize_refname($path->full_path($p));
		my $refname = desanitize_refname($ref->full_path($p));
1429 1430 1431 1432 1433 1434 1435
		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];
1436
			$u =~ s!^\Q$url\E(/|$)!! or die
1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451
			  "refs/remotes/$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;
		}
	}
}

1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464
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";
}

1465
sub fetch_all {
1466
	my ($repo_id, $remotes) = @_;
E
Eric Wong 已提交
1467 1468 1469 1470 1471 1472
	if (ref $repo_id) {
		my $gs = $repo_id;
		$repo_id = undef;
		$repo_id = $gs->{repo_id};
	}
	$remotes ||= read_all_remotes();
1473 1474
	my $remote = $remotes->{$repo_id} or
	             die "[svn-remote \"$repo_id\"] unknown\n";
1475
	my $fetch = $remote->{fetch};
1476
	my $url = $remote->{url} or die "svn-remote.$repo_id.url not defined\n";
1477
	my (@gs, @globs);
1478
	my $ra = Git::SVN::Ra->new($url);
1479
	my $uuid = $ra->get_uuid;
1480
	my $head = $ra->get_latest_revnum;
E
Eric Wong 已提交
1481
	my $base = defined $fetch ? $head : 0;
1482 1483 1484 1485 1486

	# read the max revs for wildcard expansion (branches/*, tags/*)
	foreach my $t (qw/branches tags/) {
		defined $remote->{$t} or next;
		push @globs, $remote->{$t};
1487 1488 1489 1490
		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;
1491 1492
		} elsif (!defined $max_rev) {
			$base = 0;
1493 1494 1495
		}
	}

1496 1497 1498
	if ($fetch) {
		foreach my $p (sort keys %$fetch) {
			my $gs = Git::SVN->new($fetch->{$p}, $repo_id, $p);
1499
			my $lr = $gs->rev_map_max;
1500 1501 1502 1503
			if (defined $lr) {
				$base = $lr if ($lr < $base);
			}
			push @gs, $gs;
1504 1505
		}
	}
1506 1507

	($base, $head) = parse_revision_argument($base, $head);
1508
	$ra->gs_fetch_loop_common($base, $head, \@gs, \@globs);
1509 1510
}

1511 1512
sub read_all_remotes {
	my $r = {};
1513 1514 1515
	my $use_svm_props = eval { command_oneline(qw/config --bool
	    svn.useSvmProps/) };
	$use_svm_props = $use_svm_props eq 'true' if $use_svm_props;
1516
	foreach (grep { s/^svn-remote\.// } command(qw/config -l/)) {
1517 1518 1519 1520 1521 1522
		if (m!^(.+)\.fetch=\s*(.*)\s*:\s*(.+)\s*$!) {
			my ($remote, $local_ref, $_remote_ref) = ($1, $2, $3);
			die("svn-remote.$remote: remote ref '$_remote_ref' "
			    . "must start with 'refs/remotes/'\n")
				unless $_remote_ref =~ m{^refs/remotes/(.+)};
			my $remote_ref = $1;
1523 1524
			$local_ref =~ s{^/}{};
			$r->{$remote}->{fetch}->{$local_ref} = $remote_ref;
1525 1526 1527
			$r->{$remote}->{svm} = {} if $use_svm_props;
		} elsif (m!^(.+)\.usesvmprops=\s*(.*)\s*$!) {
			$r->{$1}->{svm} = {};
1528 1529
		} elsif (m!^(.+)\.url=\s*(.*)\s*$!) {
			$r->{$1}->{url} = $2;
1530 1531 1532 1533
		} elsif (m!^(.+)\.(branches|tags)=
		           (.*):refs/remotes/(.+)\s*$/!x) {
			my ($p, $g) = ($3, $4);
			my $rs = $r->{$1}->{$2} = {
1534
			                  t => $2,
1535
					  remote => $1,
1536 1537 1538 1539 1540 1541
			                  path => Git::SVN::GlobSpec->new($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";
			}
1542 1543
		}
	}
1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560

	map {
		if (defined $r->{$_}->{svm}) {
			my $svm;
			eval {
				my $section = "svn-remote.$_";
				$svm = {
					source => tmp_config('--get',
					    "$section.svm-source"),
					replace => tmp_config('--get',
					    "$section.svm-replace"),
				}
			};
			$r->{$_}->{svm} = $svm;
		}
	} keys %$r;

1561 1562 1563
	$r;
}

E
Eric Wong 已提交
1564
sub init_vars {
1565
	$_gc_nr = $_gc_period = 1000;
1566 1567 1568
	if (defined $_repack || defined $_repack_flags) {
	       warn "Repack options are obsolete; they have no effect.\n";
	}
E
Eric Wong 已提交
1569 1570
}

1571
sub verify_remotes_sanity {
1572
	return unless -d $ENV{GIT_DIR};
1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587
	my %seen;
	foreach (command(qw/config -l/)) {
		if (m!^svn-remote\.(?:.+)\.fetch=.*:refs/remotes/(\S+)\s*$!) {
			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} = $_;
		}
	}
}

1588 1589
sub find_existing_remote {
	my ($url, $remotes) = @_;
1590
	return undef if $no_reuse_existing;
1591 1592 1593 1594 1595 1596 1597 1598 1599
	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;
}
1600

1601
sub init_remote_config {
1602
	my ($self, $url, $no_write) = @_;
1603 1604 1605 1606
	$url =~ s!/+$!!; # strip trailing slash
	my $r = read_all_remotes();
	my $existing = find_existing_remote($url, $r);
	if ($existing) {
1607 1608 1609 1610
		unless ($no_write) {
			print STDERR "Using existing ",
				     "[svn-remote \"$existing\"]\n";
		}
1611
		$self->{repo_id} = $existing;
1612
	} elsif ($_minimize_url) {
1613 1614 1615
		my $min_url = Git::SVN::Ra->new($url)->minimize_url;
		$existing = find_existing_remote($min_url, $r);
		if ($existing) {
1616 1617 1618 1619
			unless ($no_write) {
				print STDERR "Using existing ",
					     "[svn-remote \"$existing\"]\n";
			}
1620 1621 1622
			$self->{repo_id} = $existing;
		}
		if ($min_url ne $url) {
1623 1624 1625 1626
			unless ($no_write) {
				print STDERR "Using higher level of URL: ",
					     "$url => $min_url\n";
			}
1627 1628
			my $old_path = $self->{path};
			$self->{path} = $url;
1629
			$self->{path} =~ s!^\Q$min_url\E(/|$)!!;
1630 1631 1632 1633 1634 1635 1636 1637
			if (length $old_path) {
				$self->{path} .= "/$old_path";
			}
			$url = $min_url;
		}
	}
	my $orig_url;
	if (!$existing) {
1638
		# verify that we aren't overwriting anything:
1639
		$orig_url = eval {
1640
			command_oneline('config', '--get',
1641
					"svn-remote.$self->{repo_id}.url")
1642
		};
1643
		if ($orig_url && ($orig_url ne $url)) {
1644
			die "svn-remote.$self->{repo_id}.url already set: ",
1645 1646
			    "$orig_url\nwanted to set to: $url\n";
		}
1647
	}
1648 1649 1650 1651 1652
	my ($xrepo_id, $xpath) = find_ref($self->refname);
	if (defined $xpath) {
		die "svn-remote.$xrepo_id.fetch already set to track ",
		    "$xpath:refs/remotes/", $self->refname, "\n";
	}
1653 1654 1655
	unless ($no_write) {
		command_noisy('config',
			      "svn-remote.$self->{repo_id}.url", $url);
1656
		$self->{path} =~ s{^/}{};
1657 1658 1659 1660
		command_noisy('config', '--add',
			      "svn-remote.$self->{repo_id}.fetch",
			      "$self->{path}:".$self->refname);
	}
1661
	$self->{url} = $url;
1662 1663
}

1664 1665
sub find_by_url { # repos_root and, path are optional
	my ($class, $full_url, $repos_root, $path) = @_;
1666

1667
	return undef unless defined $full_url;
1668 1669
	remove_username($full_url);
	remove_username($repos_root) if defined $repos_root;
1670 1671 1672 1673 1674 1675 1676
	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;
1677
		remove_username($u);
1678 1679 1680 1681 1682 1683 1684 1685
		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;
1686
		my $rwr = rewrite_root({repo_id => $repo_id});
1687 1688
		my $svm = $remotes->{$repo_id}->{svm}
			if defined $remotes->{$repo_id}->{svm};
1689 1690
		unless (defined $p) {
			$p = $full_url;
1691
			my $z = $u;
1692
			my $prefix = '';
1693 1694
			if ($rwr) {
				$z = $rwr;
1695 1696 1697 1698 1699
			} elsif (defined $svm) {
				$z = $svm->{source};
				$prefix = $svm->{replace};
				$prefix =~ s#^\Q$u\E(?:/|$)##;
				$prefix =~ s#/$##;
1700
			}
1701
			$p =~ s#^\Q$z\E(?:/|$)#$prefix# or next;
1702 1703 1704 1705 1706 1707 1708 1709 1710
		}
		foreach my $f (keys %$fetch) {
			next if $f ne $p;
			return Git::SVN->new($fetch->{$f}, $repo_id, $f);
		}
	}
	undef;
}

1711
sub init {
1712
	my ($class, $url, $path, $repo_id, $ref_id, $no_write) = @_;
1713 1714
	my $self = _new($class, $repo_id, $ref_id, $path);
	if (defined $url) {
1715
		$self->init_remote_config($url, $no_write);
1716
	}
1717 1718 1719
	$self;
}

1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733
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);
}

1734
sub new {
1735 1736 1737 1738 1739 1740 1741 1742 1743 1744
	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);
1745 1746 1747 1748 1749 1750 1751 1752
	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);
	}
1753 1754 1755
	$self->{url} = command_oneline('config', '--get',
	                               "svn-remote.$repo_id.url") or
                  die "Failed to read \"svn-remote.$repo_id.url\" in config\n";
1756
	$self->rebuild;
1757 1758 1759
	$self;
}

1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793
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;
}
1794

1795 1796 1797 1798 1799 1800 1801 1802 1803
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};
}
1804

1805 1806 1807 1808
sub svm {
	my ($self) = @_;
	return $self->{svm} if $self->{svm};
	my $svm;
1809 1810
	# see if we have it in our config, first:
	eval {
1811 1812
		my $section = "svn-remote.$self->{repo_id}";
		$svm = {
1813 1814
		  source => tmp_config('--get', "$section.svm-source"),
		  uuid => tmp_config('--get', "$section.svm-uuid"),
1815
		  replace => tmp_config('--get', "$section.svm-replace"),
1816 1817
		}
	};
1818 1819 1820
	if ($svm && $svm->{source} && $svm->{uuid} && $svm->{replace}) {
		$self->{svm} = $svm;
	}
1821 1822 1823 1824 1825
	$self->{svm};
}

sub _set_svm_vars {
	my ($self, $ra) = @_;
1826 1827 1828
	return $ra if $self->svm;

	my @err = ( "useSvmProps set, but failed to read SVM properties\n",
1829
		    "(svm:source, svm:uuid) ",
1830 1831
		    "from the following URLs:\n" );
	sub read_svm_props {
1832 1833
		my ($self, $ra, $path, $r) = @_;
		my $props = ($ra->get_dir($path, $r))[2];
1834 1835
		my $src = $props->{'svm:source'};
		my $uuid = $props->{'svm:uuid'};
1836
		return undef if (!$src || !$uuid);
1837

1838
		chomp($src, $uuid);
1839

1840 1841
		$uuid =~ m{^[0-9a-f\-]{30,}$}
		    or die "doesn't look right - svm:uuid is '$uuid'\n";
1842 1843 1844

		# the '!' is used to mark the repos_root!/relative/path
		$src =~ s{/?!/?}{/};
1845
		$src =~ s{/+$}{}; # no trailing slashes please
1846
		# username is of no interest
1847 1848
		$src =~ s{(^[a-z\+]*://)[^/@]*@}{$1};

1849 1850 1851
		my $replace = $ra->{url};
		$replace .= "/$path" if length $path;

1852
		my $section = "svn-remote.$self->{repo_id}";
1853 1854 1855 1856 1857 1858 1859 1860
		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
		};
1861 1862 1863 1864
	}

	my $r = $ra->get_latest_revnum;
	my $path = $self->{path};
1865
	my %tried;
1866
	while (length $path) {
1867 1868 1869
		unless ($tried{"$self->{url}/$path"}) {
			return $ra if $self->read_svm_props($ra, $path, $r);
			$tried{"$self->{url}/$path"} = 1;
1870
		}
1871
		$path =~ s#/?[^/]+$##;
1872
	}
1873 1874 1875
	die "Path: '$path' should be ''\n" if $path ne '';
	return $ra if $self->read_svm_props($ra, $path, $r);
	$tried{"$self->{url}/$path"} = 1;
1876 1877

	if ($ra->{repos_root} eq $self->{url}) {
1878
		die @err, (map { "  $_\n" } keys %tried), "\n";
1879 1880 1881 1882 1883 1884 1885 1886
	}

	# 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 $path) {
1887 1888 1889 1890 1891 1892
		unless ($tried{"$ra->{url}/$path"}) {
			$ok = $self->read_svm_props($ra, $path, $r);
			last if $ok;
			$tried{"$ra->{url}/$path"} = 1;
		}
		$path =~ s#/?[^/]+$##;
1893
	}
1894 1895 1896
	die "Path: '$path' should be ''\n" if $path ne '';
	$ok ||= $self->read_svm_props($ra, $path, $r);
	$tried{"$ra->{url}/$path"} = 1;
1897
	if (!$ok) {
1898
		die @err, (map { "  $_\n" } keys %tried), "\n";
1899 1900
	}
	Git::SVN::Ra->new($self->{url});
1901 1902
}

1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919
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}";
1920 1921 1922 1923 1924 1925 1926 1927 1928 1929

		my $url = tmp_config('--get', "$section.svnsync-url");
		($url) = ($url =~ m{^([a-z\+]+://\S+)$}) or
		   die "doesn't look right - svn:sync-from-url is '$url'\n";

		my $uuid = tmp_config('--get', "$section.svnsync-uuid");
		($uuid) = ($uuid =~ m{^([0-9a-f\-]{30,})$}) or
		   die "doesn't look right - svn:sync-from-uuid is '$uuid'\n";

		$svnsync = { url => $url, uuid => $uuid }
1930 1931 1932 1933 1934 1935 1936 1937 1938 1939
	};
	if ($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 $err . "url\n";
1940
	($url) = ($url =~ m{^([a-z\+]+://\S+)$}) or
1941 1942 1943
	           die "doesn't look right - svn:sync-from-url is '$url'\n";

	my $uuid = $rp->{'svn:sync-from-uuid'} or die $err . "uuid\n";
1944
	($uuid) = ($uuid =~ m{^([0-9a-f\-]{30,})$}) or
1945 1946 1947 1948 1949 1950 1951 1952
	           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 };
}

1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970
# 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};
}

1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984
sub _set_repos_root {
	my ($self, $repos_root) = @_;
	my $k = "svn-remote.$self->{repo_id}.reposRoot";
	$repos_root ||= $self->ra->{repos_root};
	tmp_config($k, $repos_root);
	$repos_root;
}

sub repos_root {
	my ($self) = @_;
	my $k = "svn-remote.$self->{repo_id}.reposRoot";
	eval { tmp_config('--get', $k) } || $self->_set_repos_root;
}

1985 1986
sub ra {
	my ($self) = shift;
1987
	my $ra = Git::SVN::Ra->new($self->{url});
1988
	$self->_set_repos_root($ra->{repos_root});
1989 1990
	if ($self->use_svm_props && !$self->{svm}) {
		if ($self->no_metadata) {
1991 1992
			die "Can't have both 'noMetadata' and ",
			    "'useSvmProps' options set!\n";
1993 1994 1995
		} elsif ($self->use_svnsync_props) {
			die "Can't have both 'useSvnsyncProps' and ",
			    "'useSvmProps' options set!\n";
1996
		}
1997
		$ra = $self->_set_svm_vars($ra);
1998 1999 2000
		$self->{-want_revprops} = 1;
	}
	$ra;
2001 2002
}

2003 2004 2005 2006
sub rel_path {
	my ($self) = @_;
	my $repos_root = $self->ra->{repos_root};
	return $self->{path} if ($self->{url} eq $repos_root);
2007 2008 2009 2010
	my $url = $self->{url} .
	          (length $self->{path} ? "/$self->{path}" : $self->{path});
	$url =~ s!^\Q$repos_root\E(?:/+|$)!!g;
	$url;
2011 2012
}

2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025
# prop_walk(PATH, REV, SUB)
# -------------------------
# Recursively traverse PATH at revision REV and invoke SUB for each
# directory that contains a SVN property.  SUB will be invoked as
# follows:  &SUB(gs, path, props);  where `gs' is this instance of
# Git::SVN, `path' the path to the directory where the properties
# `props' were found.  The `path' will be relative to point of checkout,
# that is, if url://repo/trunk is the current Git branch, and that
# directory contains a sub-directory `d', SUB will be invoked with `/d/'
# as `path' (note the trailing `/').
sub prop_walk {
	my ($self, $path, $rev, $sub) = @_;

2026
	$path =~ s#^/##;
2027 2028
	my ($dirent, undef, $props) = $self->ra->get_dir($path, $rev);
	$path =~ s#^/*#/#g;
2029
	my $p = $path;
2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049
	# Strip the irrelevant part of the path.
	$p =~ s#^/+\Q$self->{path}\E(/|$)#/#;
	# Ensure the path is terminated by a `/'.
	$p =~ s#/*$#/#;

	# The properties contain all the internal SVN stuff nobody
	# (usually) cares about.
	my $interesting_props = 0;
	foreach (keys %{$props}) {
		# If it doesn't start with `svn:', it must be a
		# user-defined property.
		++$interesting_props and next if $_ !~ /^svn:/;
		# FIXME: Fragile, if SVN adds new public properties,
		# this needs to be updated.
		++$interesting_props if /^svn:(?:ignore|keywords|executable
		                                 |eol-style|mime-type
						 |externals|needs-lock)$/x;
	}
	&$sub($self, $p, $props) if $interesting_props;

2050
	foreach (sort keys %$dirent) {
2051
		next if $dirent->{$_}->{kind} != $SVN::Node::dir;
2052
		$self->prop_walk($self->{path} . $p . $_, $rev, $sub);
2053 2054 2055
	}
}

2056 2057 2058
sub last_rev { ($_[0]->last_rev_commit)[0] }
sub last_commit { ($_[0]->last_rev_commit)[1] }

2059 2060 2061 2062 2063 2064
# 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});
	}
2065
	my $c = ::verify_ref($self->refname.'^0');
2066
	if ($c && !$self->use_svm_props && !$self->no_metadata) {
2067
		my $rev = (::cmt_metadata($c))[1];
2068 2069 2070 2071 2072
		if (defined $rev) {
			($self->{last_rev}, $self->{last_commit}) = ($rev, $c);
			return ($rev, $c);
		}
	}
2073 2074
	my $map_path = $self->map_path;
	unless (-e $map_path) {
2075 2076 2077
		($self->{last_rev}, $self->{last_commit}) = (undef, undef);
		return (undef, undef);
	}
2078
	my ($rev, $commit) = $self->rev_map_max(1);
2079 2080
	($self->{last_rev}, $self->{last_commit}) = ($rev, $commit);
	return ($rev, $commit);
2081 2082
}

2083 2084 2085
sub get_fetch_range {
	my ($self, $min, $max) = @_;
	$max ||= $self->ra->get_latest_revnum;
2086
	$min ||= $self->rev_map_max;
2087
	(++$min, $max);
2088 2089
}

2090
sub tmp_config {
2091
	my (@args) = @_;
2092 2093
	my $old_def_config = "$ENV{GIT_DIR}/svn/config";
	my $config = "$ENV{GIT_DIR}/svn/.metadata";
2094
	if (! -f $config && -f $old_def_config) {
2095 2096 2097
		rename $old_def_config, $config or
		       die "Failed rename $old_def_config => $config: $!\n";
	}
2098
	my $old_config = $ENV{GIT_CONFIG};
2099
	$ENV{GIT_CONFIG} = $config;
2100
	$@ = undef;
2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114
	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);
	};
2115 2116 2117 2118 2119 2120 2121 2122 2123 2124
	my $err = $@;
	if (defined $old_config) {
		$ENV{GIT_CONFIG} = $old_config;
	} else {
		delete $ENV{GIT_CONFIG};
	}
	die $err if $err;
	wantarray ? @ret : $ret[0];
}

2125 2126 2127 2128
sub tmp_index_do {
	my ($self, $sub) = @_;
	my $old_index = $ENV{GIT_INDEX_FILE};
	$ENV{GIT_INDEX_FILE} = $self->{index};
2129
	$@ = undef;
2130 2131 2132 2133 2134
	my @ret = eval {
		my ($dir, $base) = ($self->{index} =~ m#^(.*?)/?([^/]+)$#);
		mkpath([$dir]) unless -d $dir;
		&$sub;
	};
2135 2136
	my $err = $@;
	if (defined $old_index) {
2137 2138 2139 2140
		$ENV{GIT_INDEX_FILE} = $old_index;
	} else {
		delete $ENV{GIT_INDEX_FILE};
	}
2141
	die $err if $err;
2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152
	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);
2153 2154 2155 2156 2157
		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);
2158 2159 2160
		$x = command_oneline('write-tree');
		if ($y ne $x) {
			::fatal "trees ($treeish) $y != $x\n",
2161
			        "Something is seriously wrong...";
2162 2163 2164 2165 2166
		}
	});
}

sub get_commit_parents {
2167
	my ($self, $log_entry) = @_;
2168
	my (%seen, @ret, @tmp);
2169 2170 2171 2172
	# 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;
2173 2174
		}
	}
2175
	if (my $cur = ::verify_ref($self->refname.'^0')) {
2176 2177
		push @tmp, $cur;
	}
2178 2179 2180 2181 2182
	if (my $ipd = $self->{inject_parents_dcommit}) {
		if (my $commit = delete $ipd->{$log_entry->{revision}}) {
			push @tmp, @$commit;
		}
	}
2183
	push @tmp, $_ foreach (@{$log_entry->{parents}}, @tmp);
2184 2185 2186 2187 2188 2189 2190 2191
	while (my $p = shift @tmp) {
		next if $seen{$p};
		$seen{$p} = 1;
		push @ret, $p;
		# MAXPARENT is defined to 16 in commit-tree.c:
		last if @ret >= 16;
	}
	if (@tmp) {
2192
		die "r$log_entry->{revision}: No room for parents:\n\t",
2193 2194 2195 2196 2197
		    join("\n\t", @tmp), "\n";
	}
	@ret;
}

2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217
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} : '');
}

2218
sub full_url {
2219
	my ($self) = @_;
2220
	$self->{url} . (length $self->{path} ? '/' . $self->{path} : '');
2221 2222
}

2223 2224 2225 2226 2227 2228 2229 2230

sub set_commit_header_env {
	my ($log_entry) = @_;
	my %env;
	foreach my $ned (qw/NAME EMAIL DATE/) {
		foreach my $ac (qw/AUTHOR COMMITTER/) {
			$env{"GIT_${ac}_${ned}"} = $ENV{"GIT_${ac}_${ned}"};
		}
2231
	}
2232

2233 2234
	$ENV{GIT_AUTHOR_NAME} = $log_entry->{name};
	$ENV{GIT_AUTHOR_EMAIL} = $log_entry->{email};
2235
	$ENV{GIT_AUTHOR_DATE} = $ENV{GIT_COMMITTER_DATE} = $log_entry->{date};
2236

2237 2238 2239 2240 2241 2242
	$ENV{GIT_COMMITTER_NAME} = (defined $log_entry->{commit_name})
						? $log_entry->{commit_name}
						: $log_entry->{name};
	$ENV{GIT_COMMITTER_EMAIL} = (defined $log_entry->{commit_email})
						? $log_entry->{commit_email}
						: $log_entry->{email};
2243 2244
	\%env;
}
2245

2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259
sub restore_commit_header_env {
	my ($env) = @_;
	foreach my $ned (qw/NAME EMAIL DATE/) {
		foreach my $ac (qw/AUTHOR COMMITTER/) {
			my $k = "GIT_${ac}_${ned}";
			if (defined $env->{$k}) {
				$ENV{$k} = $env->{$k};
			} else {
				delete $ENV{$k};
			}
		}
	}
}

2260 2261 2262 2263
sub gc {
	command_noisy('gc', '--auto');
};

2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276
sub do_git_commit {
	my ($self, $log_entry) = @_;
	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";
	}
	if (my $c = $self->rev_map_get($log_entry->{revision})) {
		croak "$log_entry->{revision} = $c already exists! ",
		      "Why are we refetching it?\n";
	}
	my $old_env = set_commit_header_env($log_entry);
2277
	my $tree = $log_entry->{tree};
2278 2279 2280 2281 2282 2283
	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;

2284
	my @exec = ('git', 'commit-tree', $tree);
2285
	foreach ($self->get_commit_parents($log_entry)) {
2286 2287 2288 2289
		push @exec, '-p', $_;
	}
	defined(my $pid = open3(my $msg_fh, my $out_fh, '>&STDERR', @exec))
	                                                           or croak $!;
2290 2291 2292 2293 2294 2295 2296 2297
	binmode $msg_fh;

	# we always get UTF-8 from SVN, but we may want our commits in
	# a different encoding.
	if (my $enc = Git::config('i18n.commitencoding')) {
		require Encode;
		Encode::from_to($log_entry->{log}, 'UTF-8', $enc);
	}
2298
	print $msg_fh $log_entry->{log} or croak $!;
2299
	restore_commit_header_env($old_env);
2300
	unless ($self->no_metadata) {
2301 2302
		print $msg_fh "\ngit-svn-id: $log_entry->{metadata}\n"
		              or croak $!;
2303
	}
2304 2305 2306 2307 2308 2309 2310 2311 2312 2313
	$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";
	}

2314
	$self->rev_map_set($log_entry->{revision}, $commit, 1);
2315

2316
	$self->{last_rev} = $log_entry->{revision};
2317
	$self->{last_commit} = $commit;
2318 2319 2320
	print "r$log_entry->{revision}";
	if (defined $log_entry->{svm_revision}) {
		 print " (\@$log_entry->{svm_revision})";
2321
		 $self->rev_map_set($log_entry->{svm_revision}, $commit,
2322
		                   0, $self->svm_uuid);
2323 2324
	}
	print " = $commit ($self->{ref_id})\n";
2325 2326 2327 2328
	if (--$_gc_nr == 0) {
		$_gc_nr = $_gc_period;
		gc();
	}
2329 2330 2331
	return $commit;
}

2332 2333
sub match_paths {
	my ($self, $paths, $r) = @_;
2334
	return 1 if $self->{path} eq '';
2335 2336 2337
	if (my $path = $paths->{"/$self->{path}"}) {
		return ($path->{action} eq 'D') ? 0 : 1;
	}
2338
	$self->{path_regex} ||= qr/^\/\Q$self->{path}\E\//;
2339 2340 2341 2342 2343 2344
	if (grep /$self->{path_regex}/, keys %$paths) {
		return 1;
	}
	my $c = '';
	foreach (split m#/#, $self->{path}) {
		$c .= "/$_";
2345 2346
		next unless ($paths->{$c} &&
		             ($paths->{$c}->{action} =~ /^[AR]$/));
2347 2348
		if ($self->ra->check_path($self->{path}, $r) ==
		    $SVN::Node::dir) {
2349 2350 2351 2352 2353 2354
			return 1;
		}
	}
	return 0;
}

2355 2356
sub find_parent_branch {
	my ($self, $paths, $rev) = @_;
2357
	return undef unless $self->follow_parent;
2358
	unless (defined $paths) {
2359 2360
		my $err_handler = $SVN::Error::handler;
		$SVN::Error::handler = \&Git::SVN::Ra::skip_unknown_revs;
2361 2362 2363
		$self->ra->get_log([$self->{path}], $rev, $rev, 0, 1, 1, sub {
		                   $paths =
				      Git::SVN::Ra::dup_changed_paths($_[0]) });
2364
		$SVN::Error::handler = $err_handler;
2365 2366
	}
	return undef unless defined $paths;
2367 2368

	# look for a parent from another branch:
2369 2370 2371 2372 2373
	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)};
2374
		last if $i && defined $i->{copyfrom_path};
2375 2376
		unshift(@a_path_components, pop(@b_path_components));
	}
2377 2378
	return undef unless defined $i && defined $i->{copyfrom_path};
	my $branch_from = $i->{copyfrom_path};
2379 2380 2381 2382 2383
	if (@a_path_components) {
		print STDERR "branch_from: $branch_from => ";
		$branch_from .= '/'.join('/', @a_path_components);
		print STDERR $branch_from, "\n";
	}
2384
	my $r = $i->{copyfrom_rev};
2385 2386 2387 2388 2389 2390
	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#^/##;
2391
	my $gs = Git::SVN->find_by_url($new_url, $repos_root, $branch_from);
2392
	unless ($gs) {
2393 2394 2395
		my $ref_id = $self->{ref_id};
		$ref_id =~ s/\@\d+$//;
		$ref_id .= "\@$r";
2396 2397
		# just grow a tail if we're not unique enough :x
		$ref_id .= '-' while find_ref($ref_id);
2398
		print STDERR "Initializing parent: $ref_id\n";
2399
		my ($u, $p, $repo_id) = ($new_url, '', $ref_id);
2400 2401 2402
		if ($u =~ s#^\Q$url\E(/|$)##) {
			$p = $u;
			$u = $url;
2403
			$repo_id = $self->{repo_id};
2404
		}
2405
		$gs = Git::SVN->init($u, $p, $repo_id, $ref_id, 1);
2406 2407
	}
	my ($r0, $parent) = $gs->find_rev_before($r, 1);
2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418
	{
		my ($base, $head);
		if (!defined $r0 || !defined $parent) {
			($base, $head) = parse_revision_argument(0, $r);
		} else {
			if ($r0 < $r) {
				$gs->ra->get_log([$gs->{path}], $r0 + 1, $r, 1,
					0, 1, sub { $base = $_[1] - 1 });
			}
		}
		if (defined $base && $base <= $r) {
2419 2420
			$gs->fetch($base, $r);
		}
2421
		($r0, $parent) = $gs->find_rev_before($r, 1);
2422
	}
2423
	if (defined $r0 && defined $parent) {
2424 2425 2426
		print STDERR "Found branch parent: ($self->{ref_id}) $parent\n";
		my $ed;
		if ($self->ra->can_do_switch) {
2427
			$self->assert_index_clean($parent);
2428
			print STDERR "Following parent with do_switch\n";
2429
			# do_switch works with svn/trunk >= r22312, but that
2430
			# is not included with SVN 1.4.3 (the latest version
2431 2432 2433
			# at the moment), so we can't rely on it
			$self->{last_commit} = $parent;
			$ed = SVN::Git::Fetcher->new($self);
2434
			$gs->ra->gs_do_switch($r0, $rev, $gs,
2435 2436
					      $self->full_url, $ed)
			  or die "SVN connection failed somewhere...\n";
2437 2438 2439 2440 2441 2442 2443 2444 2445 2446
		} elsif ($self->ra->trees_match($new_url, $r0,
			                        $self->full_url, $rev)) {
			print STDERR "Trees match:\n",
			             "  $new_url\@$r0\n",
			             "  ${\$self->full_url}\@$rev\n",
				     "Following parent with no changes\n";
			$self->tmp_index_do(sub {
			    command_noisy('read-tree', $parent);
			});
			$self->{last_commit} = $parent;
2447
		} else {
2448
			print STDERR "Following parent with do_update\n";
2449
			$ed = SVN::Git::Fetcher->new($self);
2450
			$self->ra->gs_do_update($rev, $rev, $self, $ed)
2451 2452
			  or die "SVN connection failed somewhere...\n";
		}
2453
		print STDERR "Successfully followed parent\n";
2454 2455 2456 2457 2458
		return $self->make_log_entry($rev, [$parent], $ed);
	}
	return undef;
}

2459
sub do_fetch {
2460
	my ($self, $paths, $rev) = @_;
2461
	my $ed;
2462
	my ($last_rev, @parents);
2463 2464 2465 2466 2467 2468 2469 2470 2471
	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;
		}
2472
		$ed = SVN::Git::Fetcher->new($self);
2473
		$last_rev = $self->{last_rev};
2474 2475
		$ed->{c} = $lc;
		@parents = ($lc);
2476 2477
	} else {
		$last_rev = $rev;
2478 2479 2480 2481
		if (my $log_entry = $self->find_parent_branch($paths, $rev)) {
			return $log_entry;
		}
		$ed = SVN::Git::Fetcher->new($self);
2482
	}
2483
	unless ($self->ra->gs_do_update($last_rev, $rev, $self, $ed)) {
2484 2485 2486 2487 2488
		die "SVN connection failed somewhere...\n";
	}
	$self->make_log_entry($rev, \@parents, $ed);
}

2489 2490 2491 2492
sub get_untracked {
	my ($self, $ed) = @_;
	my @out;
	my $h = $ed->{empty};
2493 2494
	foreach (sort keys %$h) {
		my $act = $h->{$_} ? '+empty_dir' : '-empty_dir';
2495
		push @out, "  $act: " . uri_encode($_);
2496 2497 2498
		warn "W: $act: $_\n";
	}
	foreach my $t (qw/dir_prop file_prop/) {
2499
		$h = $ed->{$t} or next;
2500 2501 2502
		foreach my $path (sort keys %$h) {
			my $ppath = $path eq '' ? '.' : $path;
			foreach my $prop (sort keys %{$h->{$path}}) {
2503
				next if $SKIP_PROP{$prop};
2504
				my $v = $h->{$path}->{$prop};
2505 2506 2507
				my $t_ppath_prop = "$t: " .
				                    uri_encode($ppath) . ' ' .
				                    uri_encode($prop);
2508
				if (defined $v) {
2509 2510
					push @out, "  +$t_ppath_prop " .
					           uri_encode($v);
2511
				} else {
2512
					push @out, "  -$t_ppath_prop";
2513 2514 2515 2516 2517
				}
			}
		}
	}
	foreach my $t (qw/absent_file absent_directory/) {
2518
		$h = $ed->{$t} or next;
2519 2520
		foreach my $parent (sort keys %$h) {
			foreach my $path (sort @{$h->{$parent}}) {
2521 2522
				push @out, "  $t: " .
				           uri_encode("$parent/$path");
2523 2524 2525 2526 2527
				warn "W: $t: $parent/$path ",
				     "Insufficient permissions?\n";
			}
		}
	}
2528
	\@out;
2529 2530
}

2531 2532 2533 2534 2535 2536 2537
# parse_svn_date(DATE)
# --------------------
# Given a date (in UTC) from Subversion, return a string in the format
# "<TZ Offset> <local date/time>" that Git will use.
#
# By default the parsed date will be in UTC; if $Git::SVN::_localtime
# is true we'll convert it to the local timezone instead.
2538 2539 2540 2541 2542
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";
2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585
	my $parsed_date;    # Set next.

	if ($Git::SVN::_localtime) {
		# Translate the Subversion datetime to an epoch time.
		# Begin by switching ourselves to $date's timezone, UTC.
		my $old_env_TZ = $ENV{TZ};
		$ENV{TZ} = 'UTC';

		my $epoch_in_UTC =
		    POSIX::strftime('%s', $S, $M, $H, $d, $m - 1, $Y - 1900);

		# Determine our local timezone (including DST) at the
		# time of $epoch_in_UTC.  $Git::SVN::Log::TZ stored the
		# value of TZ, if any, at the time we were run.
		if (defined $Git::SVN::Log::TZ) {
			$ENV{TZ} = $Git::SVN::Log::TZ;
		} else {
			delete $ENV{TZ};
		}

		my $our_TZ =
		    POSIX::strftime('%Z', $S, $M, $H, $d, $m - 1, $Y - 1900);

		# This converts $epoch_in_UTC into our local timezone.
		my ($sec, $min, $hour, $mday, $mon, $year,
		    $wday, $yday, $isdst) = localtime($epoch_in_UTC);

		$parsed_date = sprintf('%s %04d-%02d-%02d %02d:%02d:%02d',
				       $our_TZ, $year + 1900, $mon + 1,
				       $mday, $hour, $min, $sec);

		# Reset us to the timezone in effect when we entered
		# this routine.
		if (defined $old_env_TZ) {
			$ENV{TZ} = $old_env_TZ;
		} else {
			delete $ENV{TZ};
		}
	} else {
		$parsed_date = "+0000 $Y-$m-$d $H:$M:$S";
	}

	return $parsed_date;
2586 2587 2588 2589 2590 2591
}

sub check_author {
	my ($author) = @_;
	if (!defined $author || length $author == 0) {
		$author = '(no author)';
2592
	} elsif (defined $::_authors && ! defined $::users{$author}) {
2593 2594 2595 2596 2597
		die "Author: $author not defined in $::_authors file\n";
	}
	$author;
}

2598
sub make_log_entry {
2599 2600 2601
	my ($self, $rev, $parents, $ed) = @_;
	my $untracked = $self->get_untracked($ed);

2602
	open my $un, '>>', "$self->{dir}/unhandled.log" or croak $!;
2603 2604 2605 2606
	print $un "r$rev\n" or croak $!;
	print $un $_, "\n" foreach @$untracked;
	my %log_entry = ( parents => $parents || [], revision => $rev,
	                  log => '');
2607

2608
	my $headrev;
2609
	my $logged = delete $self->{logged_rev_props};
2610
	if (!$logged || $self->{-want_revprops}) {
2611 2612 2613 2614 2615
		my $rp = $self->ra->rev_proplist($rev);
		foreach (sort keys %$rp) {
			my $v = $rp->{$_};
			if (/^svn:(author|date|log)$/) {
				$log_entry{$1} = $v;
2616 2617
			} elsif ($_ eq 'svm:headrev') {
				$headrev = $v;
2618 2619 2620 2621
			} else {
				print $un "  rev_prop: ", uri_encode($_), ' ',
					  uri_encode($v), "\n";
			}
2622
		}
2623 2624
	} else {
		map { $log_entry{$_} = $logged->{$_} } keys %$logged;
2625 2626
	}
	close $un or croak $!;
2627

2628 2629
	$log_entry{date} = parse_svn_date($log_entry{date});
	$log_entry{log} .= "\n";
2630 2631
	my $author = $log_entry{author} = check_author($log_entry{author});
	my ($name, $email) = defined $::users{$author} ? @{$::users{$author}}
2632 2633 2634 2635
						       : ($author, undef);

	my ($commit_name, $commit_email) = ($name, $email);
	if ($_use_log_author) {
2636 2637 2638 2639 2640 2641 2642
		my $name_field;
		if ($log_entry{log} =~ /From:\s+(.*\S)\s*\n/i) {
			$name_field = $1;
		} elsif ($log_entry{log} =~ /Signed-off-by:\s+(.*\S)\s*\n/i) {
			$name_field = $1;
		}
		if (!defined $name_field) {
2643 2644 2645
			if (!defined $email) {
				$email = $name;
			}
2646
		} elsif ($name_field =~ /(.*?)\s+<(.*)>/) {
2647
			($name, $email) = ($1, $2);
2648 2649 2650
		} elsif ($name_field =~ /(.*)@/) {
			($name, $email) = ($1, $name_field);
		} else {
2651
			($name, $email) = ($name_field, $name_field);
2652 2653
		}
	}
2654
	if (defined $headrev && $self->use_svm_props) {
2655 2656 2657 2658
		if ($self->rewrite_root) {
			die "Can't have both 'useSvmProps' and 'rewriteRoot' ",
			    "options set!\n";
		}
2659
		my ($uuid, $r) = $headrev =~ m{^([a-f\d\-]{30,}):(\d+)$};
2660 2661 2662 2663
		# we don't want "SVM: initializing mirror for junk" ...
		return undef if $r == 0;
		my $svm = $self->svm;
		if ($uuid ne $svm->{uuid}) {
2664
			die "UUID mismatch on SVM path:\n",
2665
			    "expected: $svm->{uuid}\n",
2666 2667
			    "     got: $uuid\n";
		}
2668 2669 2670 2671
		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 $full_url\n";
2672 2673
		# throw away username for storing in records
		remove_username($full_url);
2674 2675
		$log_entry{metadata} = "$full_url\@$r $uuid";
		$log_entry{svm_revision} = $r;
2676 2677
		$email ||= "$author\@$uuid";
		$commit_email ||= "$author\@$uuid";
2678 2679 2680
	} elsif ($self->use_svnsync_props) {
		my $full_url = $self->svnsync->{url};
		$full_url .= "/$self->{path}" if length $self->{path};
2681
		remove_username($full_url);
2682 2683
		my $uuid = $self->svnsync->{uuid};
		$log_entry{metadata} = "$full_url\@$rev $uuid";
2684 2685
		$email ||= "$author\@$uuid";
		$commit_email ||= "$author\@$uuid";
2686
	} else {
2687 2688 2689
		my $url = $self->metadata_url;
		remove_username($url);
		$log_entry{metadata} = "$url\@$rev " .
2690
		                       $self->ra->get_uuid;
2691
		$email ||= "$author\@" . $self->ra->get_uuid;
2692
		$commit_email ||= "$author\@" . $self->ra->get_uuid;
2693
	}
2694 2695
	$log_entry{name} = $name;
	$log_entry{email} = $email;
2696 2697
	$log_entry{commit_name} = $commit_name;
	$log_entry{commit_email} = $commit_email;
2698 2699 2700 2701
	\%log_entry;
}

sub fetch {
2702
	my ($self, $min_rev, $max_rev, @parents) = @_;
2703
	my ($last_rev, $last_commit) = $self->last_rev_commit;
2704
	my ($base, $head) = $self->get_fetch_range($min_rev, $max_rev);
2705
	$self->ra->gs_fetch_loop_common($base, $head, [$self]);
2706 2707 2708 2709
}

sub set_tree_cb {
	my ($self, $log_entry, $tree, $rev, $date, $author) = @_;
2710 2711
	$self->{inject_parents} = { $rev => $tree };
	$self->fetch(undef, undef);
2712 2713 2714 2715
}

sub set_tree {
	my ($self, $tree) = (shift, shift);
2716
	my $log_entry = ::get_commit_entry($tree);
2717
	unless ($self->{last_rev}) {
2718
		::fatal("Must have an existing revision to commit");
2719
	}
2720 2721 2722 2723 2724 2725 2726 2727 2728
	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 => $self->{path} );
	if (!SVN::Git::Editor->new(\%ed_opts)->apply_diff) {
2729 2730 2731 2732
		print "No changes\nr$self->{last_rev} = $tree\n";
	}
}

2733 2734 2735 2736
sub rebuild_from_rev_db {
	my ($self, $path) = @_;
	my $r = -1;
	open my $fh, '<', $path or croak "open: $!";
2737
	binmode $fh or croak "binmode: $!";
2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749
	while (<$fh>) {
		length($_) == 41 or croak "inconsistent size in ($_) != 41";
		chomp($_);
		++$r;
		next if $_ eq ('0' x 40);
		$self->rev_map_set($r, $_);
		print "r$r = $_\n";
	}
	close $fh or croak "close: $!";
	unlink $path or croak "unlink: $!";
}

2750 2751
sub rebuild {
	my ($self) = @_;
2752
	my $map_path = $self->map_path;
2753
	my $partial = (-e $map_path && ! -z $map_path);
2754
	return unless ::verify_ref($self->refname.'^0');
2755
	if (!$partial && ($self->use_svm_props || $self->no_metadata)) {
2756 2757 2758 2759 2760 2761 2762
		my $rev_db = $self->rev_db_path;
		$self->rebuild_from_rev_db($rev_db);
		if ($self->use_svm_props) {
			my $svm_rev_db = $self->rev_db_path($self->svm_uuid);
			$self->rebuild_from_rev_db($svm_rev_db);
		}
		$self->unlink_rev_db_symlink;
2763 2764
		return;
	}
2765 2766 2767
	print "Rebuilding $map_path ...\n" if (!$partial);
	my ($base_rev, $head) = ($partial ? $self->rev_map_max_norebuild(1) :
		(undef, undef));
2768 2769
	my ($log, $ctx) =
	    command_output_pipe(qw/rev-list --pretty=raw --no-color --reverse/,
2770 2771
				($head ? "$head.." : "") . $self->refname,
				'--');
2772 2773
	my $metadata_url = $self->metadata_url;
	remove_username($metadata_url);
2774
	my $svn_uuid = $self->ra_uuid;
2775 2776 2777 2778 2779 2780 2781 2782
	my $c;
	while (<$log>) {
		if ( m{^commit ($::sha1)$} ) {
			$c = $1;
			next;
		}
		next unless s{^\s*(git-svn-id:)}{$1};
		my ($url, $rev, $uuid) = ::extract_metadata($_);
2783
		remove_username($url);
2784 2785 2786 2787 2788 2789

		# 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
2790
		if (($uuid ne $svn_uuid) ||
2791
		    ($metadata_url && $url && ($url ne $metadata_url))) {
2792 2793
			next;
		}
2794 2795 2796 2797 2798
		if ($partial && $head) {
			print "Partial-rebuilding $map_path ...\n";
			print "Currently at $base_rev = $head\n";
			$head = undef;
		}
2799

2800
		$self->rev_map_set($rev, $c);
2801 2802
		print "r$rev = $c\n";
	}
2803
	command_close_pipe($log, $ctx);
2804
	print "Done rebuilding $map_path\n" if (!$partial || !$head);
2805 2806 2807 2808 2809
	my $rev_db_path = $self->rev_db_path;
	if (-f $self->rev_db_path) {
		unlink $self->rev_db_path or croak "unlink: $!";
	}
	$self->unlink_rev_db_symlink;
2810 2811
}

2812
# rev_map:
2813 2814 2815
# 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
2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826
# modules, but I'm not sure which is most portable...
#
# This is the replacement for the rev_db format, which was too big
# and inefficient for large repositories with a lot of sparse history
# (mainly tags)
#
# The format is this:
#   - 24 bytes for every record,
#     * 4 bytes for the integer representing an SVN revision number
#     * 20 bytes representing the sha1 of a git commit
#   - No empty padding records like the old format
2827
#     (except the last record, which can be overwritten)
2828 2829 2830
#   - new records are written append-only since SVN revision numbers
#     increase monotonically
#   - lookups on SVN revision number are done via a binary search
2831 2832 2833 2834 2835 2836
#   - Piping the file to xxd -c24 is a good way of dumping it for
#     viewing or editing (piped back through xxd -r), should the need
#     ever arise.
#   - The last record can be padding revision with an all-zero sha1
#     This is used to optimize fetch performance when using multiple
#     "fetch" directives in .git/config
2837
#
2838
# These files are disposable unless noMetadata or useSvmProps is set
2839

2840
sub _rev_map_set {
2841
	my ($fh, $rev, $commit) = @_;
2842

2843
	binmode $fh or croak "binmode: $!";
2844 2845 2846
	my $size = (stat($fh))[7];
	($size % 24) == 0 or croak "inconsistent size: $size";

2847
	my $wr_offset = 0;
2848 2849 2850 2851 2852
	if ($size > 0) {
		sysseek($fh, -24, SEEK_END) or croak "seek: $!";
		my $read = sysread($fh, my $buf, 24) or croak "read: $!";
		$read == 24 or croak "read only $read bytes (!= 24)";
		my ($last_rev, $last_commit) = unpack(rev_map_fmt, $buf);
2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869
		if ($last_commit eq ('0' x40)) {
			if ($size >= 48) {
				sysseek($fh, -48, SEEK_END) or croak "seek: $!";
				$read = sysread($fh, $buf, 24) or
				    croak "read: $!";
				$read == 24 or
				    croak "read only $read bytes (!= 24)";
				($last_rev, $last_commit) =
				    unpack(rev_map_fmt, $buf);
				if ($last_commit eq ('0' x40)) {
					croak "inconsistent .rev_map\n";
				}
			}
			if ($last_rev >= $rev) {
				croak "last_rev is higher!: $last_rev >= $rev";
			}
			$wr_offset = -24;
2870 2871
		}
	}
2872
	sysseek($fh, $wr_offset, SEEK_END) or croak "seek: $!";
2873 2874
	syswrite($fh, pack(rev_map_fmt, $rev, $commit), 24) == 24 or
	  croak "write: $!";
2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886
}

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";
	}
}

2887
sub rev_map_set {
2888 2889
	my ($self, $rev, $commit, $update_ref, $uuid) = @_;
	length $commit == 40 or die "arg3 must be a full SHA1 hexsum\n";
2890
	my $db = $self->map_path($uuid);
2891
	my $db_lock = "$db.lock";
2892 2893 2894 2895 2896
	my $sig;
	if ($update_ref) {
		$SIG{INT} = $SIG{HUP} = $SIG{TERM} = $SIG{ALRM} = $SIG{PIPE} =
		            $SIG{USR1} = $SIG{USR2} = sub { $sig = $_[0] };
	}
2897 2898
	mkfile($db);

2899
	$LOCKFILES{$db_lock} = 1;
2900 2901 2902 2903 2904
	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) {
		$sync = 1;
2905
		copy($db, $db_lock) or die "rev_map_set(@_): ",
2906
					   "Failed to copy: ",
2907 2908
					   "$db => $db_lock ($!)\n";
	} else {
2909
		rename $db, $db_lock or die "rev_map_set(@_): ",
2910
					    "Failed to rename: ",
2911 2912
					    "$db => $db_lock ($!)\n";
	}
2913

2914
	sysopen(my $fh, $db_lock, O_RDWR | O_CREAT)
2915 2916
	     or croak "Couldn't open $db_lock: $!\n";
	_rev_map_set($fh, $rev, $commit);
2917 2918 2919 2920
	if ($sync) {
		$fh->flush or die "Couldn't flush $db_lock: $!\n";
		$fh->sync or die "Couldn't sync $db_lock: $!\n";
	}
2921
	close $fh or croak $!;
2922
	if ($update_ref) {
2923
		$_head = $self;
2924 2925 2926
		command_noisy('update-ref', '-m', "r$rev",
		              $self->refname, $commit);
	}
2927
	rename $db_lock, $db or die "rev_map_set(@_): ", "Failed to rename: ",
2928 2929 2930 2931 2932 2933 2934
	                            "$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;
	}
2935 2936
}

2937 2938 2939 2940
# If want_commit, this will return an array of (rev, commit) where
# commit _must_ be a valid commit in the archive.
# Otherwise, it'll return the max revision (whether or not the
# commit is valid or just a 0x40 placeholder).
2941
sub rev_map_max {
2942
	my ($self, $want_commit) = @_;
2943
	$self->rebuild;
2944 2945 2946 2947 2948 2949
	my ($r, $c) = $self->rev_map_max_norebuild($want_commit);
	$want_commit ? ($r, $c) : $r;
}

sub rev_map_max_norebuild {
	my ($self, $want_commit) = @_;
2950
	my $map_path = $self->map_path;
2951
	stat $map_path or return $want_commit ? (0, undef) : 0;
2952
	sysopen(my $fh, $map_path, O_RDONLY) or croak "open: $!";
2953
	binmode $fh or croak "binmode: $!";
2954 2955 2956 2957 2958
	my $size = (stat($fh))[7];
	($size % 24) == 0 or croak "inconsistent size: $size";

	if ($size == 0) {
		close $fh or croak "close: $!";
2959
		return $want_commit ? (0, undef) : 0;
2960 2961
	}

2962
	sysseek($fh, -24, SEEK_END) or croak "seek: $!";
2963 2964
	sysread($fh, my $buf, 24) == 24 or croak "read: $!";
	my ($r, $c) = unpack(rev_map_fmt, $buf);
2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977
	if ($want_commit && $c eq ('0' x40)) {
		if ($size < 48) {
			return $want_commit ? (0, undef) : 0;
		}
		sysseek($fh, -48, SEEK_END) or croak "seek: $!";
		sysread($fh, $buf, 24) == 24 or croak "read: $!";
		($r, $c) = unpack(rev_map_fmt, $buf);
		if ($c eq ('0'x40)) {
			croak "Penultimate record is all-zeroes in $map_path";
		}
	}
	close $fh or croak "close: $!";
	$want_commit ? ($r, $c) : $r;
2978 2979
}

2980
sub rev_map_get {
2981
	my ($self, $rev, $uuid) = @_;
2982 2983 2984 2985
	my $map_path = $self->map_path($uuid);
	return undef unless -e $map_path;

	sysopen(my $fh, $map_path, O_RDONLY) or croak "open: $!";
2986
	binmode $fh or croak "binmode: $!";
2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009
	my $size = (stat($fh))[7];
	($size % 24) == 0 or croak "inconsistent size: $size";

	if ($size == 0) {
		close $fh or croak "close: $fh";
		return undef;
	}

	my ($l, $u) = (0, $size - 24);
	my ($r, $c, $buf);

	while ($l <= $u) {
		my $i = int(($l/24 + $u/24) / 2) * 24;
		sysseek($fh, $i, SEEK_SET) or croak "seek: $!";
		sysread($fh, my $buf, 24) == 24 or croak "read: $!";
		my ($r, $c) = unpack('NH40', $buf);

		if ($r < $rev) {
			$l = $i + 24;
		} elsif ($r > $rev) {
			$u = $i - 24;
		} else { # $r == $rev
			close($fh) or croak "close: $!";
3010
			return $c eq ('0' x 40) ? undef : $c;
3011
		}
3012
	}
3013 3014
	close($fh) or croak "close: $!";
	undef;
3015 3016
}

3017 3018 3019 3020
# Finds the first svn revision that exists on (if $eq_ok is true) or
# before $rev for the current branch.  It will not search any lower
# than $min_rev.  Returns the git commit hash and svn revision number
# if found, else (undef, undef).
3021
sub find_rev_before {
3022
	my ($self, $rev, $eq_ok, $min_rev) = @_;
3023
	--$rev unless $eq_ok;
3024 3025
	$min_rev ||= 1;
	while ($rev >= $min_rev) {
3026
		if (my $c = $self->rev_map_get($rev)) {
3027 3028 3029 3030 3031 3032 3033
			return ($rev, $c);
		}
		--$rev;
	}
	return (undef, undef);
}

3034 3035 3036 3037 3038 3039 3040
# Finds the first svn revision that exists on (if $eq_ok is true) or
# after $rev for the current branch.  It will not search any higher
# than $max_rev.  Returns the git commit hash and svn revision number
# if found, else (undef, undef).
sub find_rev_after {
	my ($self, $rev, $eq_ok, $max_rev) = @_;
	++$rev unless $eq_ok;
3041
	$max_rev ||= $self->rev_map_max;
3042
	while ($rev <= $max_rev) {
3043
		if (my $c = $self->rev_map_get($rev)) {
3044 3045 3046 3047 3048 3049 3050
			return ($rev, $c);
		}
		++$rev;
	}
	return (undef, undef);
}

3051
sub _new {
3052 3053 3054 3055 3056
	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) {
3057
		$_[2] = $ref_id = $Git::SVN::default_ref_id;
3058
	}
3059
	$_[1] = $repo_id;
3060 3061
	my $dir = "$ENV{GIT_DIR}/svn/$ref_id";
	$_[3] = $path = '' unless (defined $path);
3062
	mkpath(["$ENV{GIT_DIR}/svn"]);
3063 3064
	bless {
		ref_id => $ref_id, dir => $dir, index => "$dir/index",
3065
	        path => $path, config => "$ENV{GIT_DIR}/svn/config",
3066
	        map_root => "$dir/.rev_map", repo_id => $repo_id }, $class;
3067 3068
}

3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088
# for read-only access of old .rev_db formats
sub unlink_rev_db_symlink {
	my ($self) = @_;
	my $link = $self->rev_db_path;
	$link =~ s/\.[\w-]+$// or croak "missing UUID at the end of $link";
	if (-l $link) {
		unlink $link or croak "unlink: $link failed!";
	}
}

sub rev_db_path {
	my ($self, $uuid) = @_;
	my $db_path = $self->map_path($uuid);
	$db_path =~ s{/\.rev_map\.}{/\.rev_db\.}
	    or croak "map_path: $db_path does not contain '/.rev_map.' !";
	$db_path;
}

# the new replacement for .rev_db
sub map_path {
3089 3090
	my ($self, $uuid) = @_;
	$uuid ||= $self->ra_uuid;
3091
	"$self->{map_root}.$uuid";
3092 3093
}

3094 3095 3096 3097 3098
sub uri_encode {
	my ($f) = @_;
	$f =~ s#([^a-zA-Z0-9\*!\:_\./\-])#uc sprintf("%%%02x",ord($1))#eg;
	$f
}
3099

3100 3101 3102 3103
sub remove_username {
	$_[0] =~ s{^([^:]*://)[^@]+@}{$1};
}

3104 3105 3106 3107 3108 3109 3110
package Git::SVN::Prompt;
use strict;
use warnings;
require SVN::Core;
use vars qw/$_no_auth_cache $_username/;

sub simple {
3111 3112 3113 3114 3115
	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) {
3116 3117
			print STDERR "Authentication realm: $realm\n";
			STDERR->flush;
3118 3119 3120
		}
		$cred->username($default_username);
	} else {
3121
		username($cred, $realm, $may_save, $pool);
3122 3123 3124 3125 3126 3127 3128
	}
	$cred->password(_read_password("Password for '" .
	                               $cred->username . "': ", $realm));
	$cred->may_save($may_save);
	$SVN::_Core::SVN_NO_ERROR;
}

3129
sub ssl_server_trust {
3130 3131
	my ($cred, $realm, $failures, $cert_info, $may_save, $pool) = @_;
	$may_save = undef if $_no_auth_cache;
3132
	print STDERR "Error validating server certificate for '$realm':\n";
3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157
	{
		no warnings 'once';
		# All variables SVN::Auth::SSL::* are used only once,
		# so we're shutting up Perl warnings about this.
		if ($failures & $SVN::Auth::SSL::UNKNOWNCA) {
			print STDERR " - The certificate is not issued ",
			    "by a trusted authority. Use the\n",
			    "   fingerprint to validate ",
			    "the certificate manually!\n";
		}
		if ($failures & $SVN::Auth::SSL::CNMISMATCH) {
			print STDERR " - The certificate hostname ",
			    "does not match.\n";
		}
		if ($failures & $SVN::Auth::SSL::NOTYETVALID) {
			print STDERR " - The certificate is not yet valid.\n";
		}
		if ($failures & $SVN::Auth::SSL::EXPIRED) {
			print STDERR " - The certificate has expired.\n";
		}
		if ($failures & $SVN::Auth::SSL::OTHER) {
			print STDERR " - The certificate has ",
			    "an unknown error.\n";
		}
	} # no warnings 'once'
3158 3159
	printf STDERR
	        "Certificate information:\n".
3160 3161 3162 3163 3164
	        " - Hostname: %s\n".
	        " - Valid: from %s until %s\n".
	        " - Issuer: %s\n".
	        " - Fingerprint: %s\n",
	        map $cert_info->$_, qw(hostname valid_from valid_until
3165
	                               issuer_dname fingerprint);
3166 3167
	my $choice;
prompt:
3168
	print STDERR $may_save ?
3169 3170
	      "(R)eject, accept (t)emporarily or accept (p)ermanently? " :
	      "(R)eject or accept (t)emporarily? ";
3171
	STDERR->flush;
3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185
	$choice = lc(substr(<STDIN> || 'R', 0, 1));
	if ($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;
}

3186
sub ssl_client_cert {
3187 3188
	my ($cred, $realm, $may_save, $pool) = @_;
	$may_save = undef if $_no_auth_cache;
3189 3190
	print STDERR "Client certificate filename: ";
	STDERR->flush;
3191 3192 3193 3194 3195 3196
	chomp(my $filename = <STDIN>);
	$cred->cert_file($filename);
	$cred->may_save($may_save);
	$SVN::_Core::SVN_NO_ERROR;
}

3197
sub ssl_client_cert_pw {
3198 3199 3200 3201 3202 3203 3204
	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;
}

3205
sub username {
3206 3207 3208
	my ($cred, $realm, $may_save, $pool) = @_;
	$may_save = undef if $_no_auth_cache;
	if (defined $realm && length $realm) {
3209
		print STDERR "Authentication realm: $realm\n";
3210 3211 3212 3213 3214
	}
	my $username;
	if (defined $_username) {
		$username = $_username;
	} else {
3215 3216
		print STDERR "Username: ";
		STDERR->flush;
3217 3218 3219 3220 3221 3222 3223 3224 3225
		chomp($username = <STDIN>);
	}
	$cred->username($username);
	$cred->may_save($may_save);
	$SVN::_Core::SVN_NO_ERROR;
}

sub _read_password {
	my ($prompt, $realm) = @_;
3226 3227
	print STDERR $prompt;
	STDERR->flush;
3228 3229 3230 3231 3232 3233 3234 3235
	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');
3236 3237
	print STDERR "\n";
	STDERR->flush;
3238 3239 3240
	$password;
}

3241 3242 3243 3244 3245
package SVN::Git::Fetcher;
use vars qw/@ISA/;
use strict;
use warnings;
use Carp qw/croak/;
A
Adam Roben 已提交
3246
use File::Temp qw/tempfile/;
3247 3248 3249 3250 3251 3252 3253
use IO::File qw//;

# 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;
3254 3255 3256 3257
	if (exists $git_svn->{last_commit}) {
		$self->{c} = $git_svn->{last_commit};
		$self->{empty_symlinks} = _mark_empty_symlinks($git_svn);
	}
3258 3259 3260 3261 3262
	$self->{empty} = {};
	$self->{dir_prop} = {};
	$self->{file_prop} = {};
	$self->{absent_dir} = {};
	$self->{absent_file} = {};
3263
	$self->{gii} = $git_svn->tmp_index_do(sub { Git::IndexInfo->new });
3264 3265 3266
	$self;
}

3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294
# this uses the Ra object, so it must be called before do_{switch,update},
# not inside them (when the Git::SVN::Fetcher object is passed) to
# do_{switch,update}
sub _mark_empty_symlinks {
	my ($git_svn) = @_;
	my %ret;
	my ($rev, $cmt) = $git_svn->last_rev_commit;
	return {} unless ($rev && $cmt);

	chomp(my $empty_blob = `git hash-object -t blob --stdin < /dev/null`);
	my ($ls, $ctx) = command_output_pipe(qw/ls-tree -r -z/, $cmt);
	local $/ = "\0";
	my $pfx = $git_svn->{path};
	$pfx .= '/' if length($pfx);
	while (<$ls>) {
		chomp;
		s/\A100644 blob $empty_blob\t//o or next;
		my $path = $_;
		my (undef, $props) =
		               $git_svn->ra->get_file($pfx.$path, $rev, undef);
		if ($props->{'svn:special'}) {
			$ret{$path} = 1;
		}
	}
	command_close_pipe($ls, $ctx);
	\%ret;
}

3295 3296 3297 3298 3299
# returns true if a given path is inside a ".git" directory
sub in_dot_git {
	$_[0] =~ m{(?:^|/)\.git(?:/|$)};
}

3300 3301
sub set_path_strip {
	my ($self, $path) = @_;
3302
	$self->{path_strip} = qr/^\Q$path\E(\/|$)/ if length $path;
3303 3304
}

3305 3306 3307 3308 3309 3310 3311 3312 3313
sub open_root {
	{ path => '' };
}

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

3314 3315
sub git_path {
	my ($self, $path) = @_;
3316 3317 3318 3319
	if ($self->{path_strip}) {
		$path =~ s!$self->{path_strip}!! or
		  die "Failed to strip path '$path' ($self->{path_strip})\n";
	}
3320 3321 3322
	$path;
}

3323 3324
sub delete_entry {
	my ($self, $path, $rev, $pb) = @_;
3325
	return undef if in_dot_git($path);
3326

3327
	my $gpath = $self->git_path($path);
3328 3329
	return undef if ($gpath eq '');

3330
	# remove entire directories.
3331
	if (command('ls-tree', $self->{c}, '--', $gpath) =~ /^040000 tree/) {
3332 3333
		my ($ls, $ctx) = command_output_pipe(qw/ls-tree
		                                     -r --name-only -z/,
3334
				                     $self->{c}, '--', $gpath);
3335 3336
		local $/ = "\0";
		while (<$ls>) {
3337 3338
			chomp;
			$self->{gii}->remove($_);
3339
			print "\tD\t$_\n" unless $::_q;
3340
		}
3341
		print "\tD\t$gpath/\n" unless $::_q;
3342 3343 3344
		command_close_pipe($ls, $ctx);
		$self->{empty}->{$path} = 0
	} else {
3345
		$self->{gii}->remove($gpath);
3346
		print "\tD\t$gpath\n" unless $::_q;
3347
	}
3348 3349 3350 3351 3352
	undef;
}

sub open_file {
	my ($self, $path, $pb, $rev) = @_;
3353 3354 3355 3356
	my ($mode, $blob);

	goto out if in_dot_git($path);

3357
	my $gpath = $self->git_path($path);
3358
	($mode, $blob) = (command('ls-tree', $self->{c}, '--', $gpath)
3359
	                     =~ /^(\d{6}) blob ([a-f\d]{40})\t/);
3360 3361 3362
	unless (defined $mode && defined $blob) {
		die "$path was not found in commit $self->{c} (r$rev)\n";
	}
3363 3364 3365
	if ($mode eq '100644' && $self->{empty_symlinks}->{$path}) {
		$mode = '120000';
	}
3366
out:
3367
	{ path => $path, mode_a => $mode, mode_b => $mode, blob => $blob,
3368
	  pool => SVN::Pool->new, action => 'M' };
3369 3370 3371 3372
}

sub add_file {
	my ($self, $path, $pb, $cp_path, $cp_rev) = @_;
3373 3374 3375 3376 3377 3378 3379 3380
	my $mode;

	if (!in_dot_git($path)) {
		my ($dir, $file) = ($path =~ m#^(.*?)/?([^/]+)$#);
		delete $self->{empty}->{$dir};
		$mode = '100644';
	}
	{ path => $path, mode_a => $mode, mode_b => $mode,
3381
	  pool => SVN::Pool->new, action => 'A' };
3382 3383
}

3384 3385
sub add_directory {
	my ($self, $path, $cp_path, $cp_rev) = @_;
3386
	goto out if in_dot_git($path);
3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400
	my $gpath = $self->git_path($path);
	if ($gpath eq '') {
		my ($ls, $ctx) = command_output_pipe(qw/ls-tree
		                                     -r --name-only -z/,
				                     $self->{c});
		local $/ = "\0";
		while (<$ls>) {
			chomp;
			$self->{gii}->remove($_);
			print "\tD\t$_\n" unless $::_q;
		}
		command_close_pipe($ls, $ctx);
		$self->{empty}->{$path} = 0;
	}
3401 3402 3403
	my ($dir, $file) = ($path =~ m#^(.*?)/?([^/]+)$#);
	delete $self->{empty}->{$dir};
	$self->{empty}->{$path} = 1;
3404
out:
3405 3406 3407 3408 3409
	{ path => $path };
}

sub change_dir_prop {
	my ($self, $db, $prop, $value) = @_;
3410
	return undef if in_dot_git($db->{path});
3411 3412 3413 3414 3415 3416 3417
	$self->{dir_prop}->{$db->{path}} ||= {};
	$self->{dir_prop}->{$db->{path}}->{$prop} = $value;
	undef;
}

sub absent_directory {
	my ($self, $path, $pb) = @_;
3418
	return undef if in_dot_git($pb->{path});
3419 3420 3421 3422 3423 3424 3425
	$self->{absent_dir}->{$pb->{path}} ||= [];
	push @{$self->{absent_dir}->{$pb->{path}}}, $path;
	undef;
}

sub absent_file {
	my ($self, $path, $pb) = @_;
3426
	return undef if in_dot_git($pb->{path});
3427 3428 3429 3430 3431
	$self->{absent_file}->{$pb->{path}} ||= [];
	push @{$self->{absent_file}->{$pb->{path}}}, $path;
	undef;
}

3432 3433
sub change_file_prop {
	my ($self, $fb, $prop, $value) = @_;
3434
	return undef if in_dot_git($fb->{path});
3435 3436 3437 3438 3439 3440
	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;
3441 3442 3443
	} else {
		$self->{file_prop}->{$fb->{path}} ||= {};
		$self->{file_prop}->{$fb->{path}}->{$prop} = $value;
3444 3445 3446 3447 3448 3449
	}
	undef;
}

sub apply_textdelta {
	my ($self, $fb, $exp) = @_;
3450
	return undef if (in_dot_git($fb->{path}));
3451
	my $fh = $::_repository->temp_acquire('svn_delta');
3452 3453 3454
	# $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 $!;
3455
	my $base = $::_repository->temp_acquire('git_blob');
3456

3457
	if ($fb->{blob}) {
3458 3459
		my ($base_is_link, $size);

3460 3461 3462
		if ($fb->{mode_a} eq '120000' &&
		    ! $self->{empty_symlinks}->{$fb->{path}}) {
			print $base 'link ' or die "print $!\n";
3463
			$base_is_link = 1;
3464
		}
3465 3466
	retry:
		$size = $::_repository->cat_blob($fb->{blob}, $base);
3467
		die "Failed to read object $fb->{blob}" if ($size < 0);
3468 3469 3470

		if (defined $exp) {
			seek $base, 0, 0 or croak $!;
3471
			my $got = ::md5sum($base);
3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486
			if ($got ne $exp) {
				my $err = "Checksum mismatch: ".
				       "$fb->{path} $fb->{blob}\n" .
				       "expected: $exp\n" .
				       "     got: $got\n";
				if ($base_is_link) {
					warn $err,
					     "Retrying... (possibly ",
					     "a bad symlink from SVN)\n";
					$::_repository->temp_reset($base);
					$base_is_link = 0;
					goto retry;
				}
				die $err;
			}
3487 3488 3489
		}
	}
	seek $base, 0, 0 or croak $!;
3490
	$fb->{fh} = $fh;
3491
	$fb->{base} = $base;
3492
	[ SVN::TxDelta::apply($base, $dup, undef, $fb->{path}, $fb->{pool}) ];
3493 3494 3495 3496
}

sub close_file {
	my ($self, $fb, $exp) = @_;
3497 3498
	return undef if (in_dot_git($fb->{path}));

3499
	my $hash;
3500
	my $path = $self->git_path($fb->{path});
3501
	if (my $fh = $fb->{fh}) {
3502 3503
		if (defined $exp) {
			seek($fh, 0, 0) or croak $!;
3504
			my $got = ::md5sum($fh);
3505 3506 3507 3508 3509
			if ($got ne $exp) {
				die "Checksum mismatch: $path\n",
				    "expected: $exp\n    got: $got\n";
			}
		}
3510
		if ($fb->{mode_b} == 120000) {
3511
			sysseek($fh, 0, 0) or croak $!;
3512
			my $rd = sysread($fh, my $buf, 5);
A
Adam Roben 已提交
3513

3514 3515 3516 3517 3518 3519 3520 3521 3522
			if (!defined $rd) {
				croak "sysread: $!\n";
			} elsif ($rd == 0) {
				warn "$path has mode 120000",
				     " but it points to nothing\n",
				     "converting to an empty file with mode",
				     " 100644\n";
				$fb->{mode_b} = '100644';
			} elsif ($buf ne 'link ') {
3523
				warn "$path has mode 120000",
3524
				     " but is not a link\n";
3525
			} else {
3526 3527
				my $tmp_fh = $::_repository->temp_acquire(
					'svn_hash');
3528 3529 3530 3531 3532
				my $res;
				while ($res = sysread($fh, my $str, 1024)) {
					my $out = syswrite($tmp_fh, $str, $res);
					defined($out) && $out == $res
						or croak("write ",
3533
							Git::temp_path($tmp_fh),
3534 3535 3536
							": $!\n");
				}
				defined $res or croak $!;
A
Adam Roben 已提交
3537

3538 3539 3540 3541
				($fh, $tmp_fh) = ($tmp_fh, $fh);
				Git::temp_release($tmp_fh, 1);
			}
		}
3542 3543

		$hash = $::_repository->hash_and_insert_object(
3544
				Git::temp_path($fh));
3545
		$hash =~ /^[a-f\d]{40}$/ or die "not a sha1: $hash\n";
3546 3547

		Git::temp_release($fb->{base}, 1);
3548
		Git::temp_release($fh, 1);
3549 3550 3551 3552
	} else {
		$hash = $fb->{blob} or die "no blob information\n";
	}
	$fb->{pool}->clear;
3553
	$self->{gii}->update($fb->{mode_b}, $hash, $path) or croak $!;
3554
	print "\t$fb->{action}\t$path\n" if $fb->{action} && ! $::_q;
3555 3556 3557 3558 3559
	undef;
}

sub abort_edit {
	my $self = shift;
3560 3561
	$self->{nr} = $self->{gii}->{nr};
	delete $self->{gii};
3562 3563 3564 3565 3566
	$self->SUPER::abort_edit(@_);
}

sub close_edit {
	my $self = shift;
3567
	$self->{git_commit_ok} = 1;
3568 3569
	$self->{nr} = $self->{gii}->{nr};
	delete $self->{gii};
3570 3571
	$self->SUPER::close_edit(@_);
}
3572

3573
package SVN::Git::Editor;
3574
use vars qw/@ISA $_rmdir $_cp_similarity $_find_copies_harder $_rename_limit/;
3575 3576 3577 3578 3579 3580
use strict;
use warnings;
use Carp qw/croak/;
use IO::File;

sub new {
3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594
	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);
3595
	bless $self, $class;
3596 3597
	foreach (qw/svn_path r tree_a tree_b/) {
		$self->{$_} = $opts->{$_};
3598
	}
3599 3600 3601 3602
	$self->{url} = $opts->{ra}->{url};
	$self->{mods} = $mods;
	$self->{types} = $types;
	$self->{pool} = $pool;
3603 3604
	$self->{bat} = { '' => $self->open_root($self->{r}, $self->{pool}) };
	$self->{rm} = { };
3605 3606
	$self->{path_prefix} = length $self->{svn_path} ?
	                       "$self->{svn_path}/" : '';
3607
	$self->{config} = $opts->{config};
3608 3609 3610
	return $self;
}

3611 3612 3613
sub generate_diff {
	my ($tree_a, $tree_b) = @_;
	my @diff_tree = qw(diff-tree -z -r);
3614 3615
	if ($_cp_similarity) {
		push @diff_tree, "-C$_cp_similarity";
3616 3617 3618
	} else {
		push @diff_tree, '-C';
	}
3619 3620
	push @diff_tree, '--find-copies-harder' if $_find_copies_harder;
	push @diff_tree, "-l$_rename_limit" if defined $_rename_limit;
3621 3622 3623 3624 3625 3626 3627 3628
	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
3629
					($::sha1)\s($::sha1)\s
3630 3631
					([MTCRAD])\d*$/xo) {
			push @mods, {	mode_a => $1, mode_b => $2,
3632 3633 3634
					sha1_a => $3, sha1_b => $4,
					chg => $5 };
			if ($5 =~ /^(?:C|R)$/) {
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
				$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;
}

3695 3696 3697 3698 3699
sub split_path {
	return ($_[0] =~ m#^(.*?)/?([^/]+)$#);
}

sub repo_path {
3700 3701
	my ($self, $path) = @_;
	$self->{path_prefix}.(defined $path ? $path : '');
3702 3703 3704 3705
}

sub url_path {
	my ($self, $path) = @_;
3706
	if ($self->{url} =~ m#^https?://#) {
3707
		$path =~ s/([^~a-zA-Z0-9_.-])/uc sprintf("%%%02x",ord($1))/eg;
3708
	}
3709
	$self->{url} . '/' . $self->repo_path($path);
3710 3711 3712
}

sub rmdirs {
3713
	my ($self) = @_;
3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730
	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;

3731 3732
	my ($fh, $ctx) = command_output_pipe(qw/ls-tree --name-only -r -z/,
	                                     $self->{tree_b});
3733 3734 3735
	local $/ = "\0";
	while (<$fh>) {
		chomp;
3736
		my @dn = split m#/#, $_;
3737 3738 3739 3740
		while (pop @dn) {
			delete $rm->{join '/', @dn};
		}
		unless (%$rm) {
3741
			close $fh;
3742 3743
			return;
		}
3744
	}
E
Eric Wong 已提交
3745
	command_close_pipe($fh, $ctx);
3746

3747 3748 3749 3750
	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) = ($d =~ m#^(.*?)/?(?:[^/]+)$#);
3751
		print "\tD+\t$d/\n" unless $::_q;
3752 3753 3754 3755 3756 3757 3758
		$self->SUPER::delete_entry($d, $r, $bat->{$dn}, $p);
		delete $bat->{$d};
	}
}

sub open_or_add_dir {
	my ($self, $full_path, $baton) = @_;
3759 3760 3761 3762
	my $t = $self->{types}->{$full_path};
	if (!defined $t) {
		die "$full_path not known in r$self->{r} or we have a bug!\n";
	}
3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777
	{
		no warnings 'once';
		# SVN::Node::none and SVN::Node::file are used only once,
		# so we're shutting up Perl's warnings about them.
		if ($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}, $self->{pool});
		} # no warnings 'once'
		print STDERR "$full_path already exists in repository at ",
		    "r$self->{r} and it is not a directory (",
		    ($t == $SVN::Node::file ? 'file' : 'unknown'),"/$t)\n";
	} # no warnings 'once'
3778 3779 3780 3781 3782 3783
	exit 1;
}

sub ensure_path {
	my ($self, $path) = @_;
	my $bat = $self->{bat};
3784 3785 3786
	my $repo_path = $self->repo_path($path);
	return $bat->{''} unless (length $repo_path);
	my @p = split m#/+#, $repo_path;
3787 3788 3789 3790 3791 3792 3793 3794 3795 3796
	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};
}

3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 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
# Subroutine to convert a globbing pattern to a regular expression.
# From perl cookbook.
sub glob2pat {
	my $globstr = shift;
	my %patmap = ('*' => '.*', '?' => '.', '[' => '[', ']' => ']');
	$globstr =~ s{(.)} { $patmap{$1} || "\Q$1" }ge;
	return '^' . $globstr . '$';
}

sub check_autoprop {
	my ($self, $pattern, $properties, $file, $fbat) = @_;
	# Convert the globbing pattern to a regular expression.
	my $regex = glob2pat($pattern);
	# Check if the pattern matches the file name.
	if($file =~ m/($regex)/) {
		# Parse the list of properties to set.
		my @props = split(/;/, $properties);
		foreach my $prop (@props) {
			# Parse 'name=value' syntax and set the property.
			if ($prop =~ /([^=]+)=(.*)/) {
				my ($n,$v) = ($1,$2);
				for ($n, $v) {
					s/^\s+//; s/\s+$//;
				}
				$self->change_file_prop($fbat, $n, $v);
			}
		}
	}
}

sub apply_autoprops {
	my ($self, $file, $fbat) = @_;
	my $conf_t = ${$self->{config}}{'config'};
	no warnings 'once';
	# Check [miscellany]/enable-auto-props in svn configuration.
	if (SVN::_Core::svn_config_get_bool(
		$conf_t,
		$SVN::_Core::SVN_CONFIG_SECTION_MISCELLANY,
		$SVN::_Core::SVN_CONFIG_OPTION_ENABLE_AUTO_PROPS,
		0)) {
		# Auto-props are enabled.  Enumerate them to look for matches.
		my $callback = sub {
			$self->check_autoprop($_[0], $_[1], $file, $fbat);
		};
		SVN::_Core::svn_config_enumerate(
			$conf_t,
			$SVN::_Core::SVN_CONFIG_SECTION_AUTO_PROPS,
			$callback);
	}
}

3848
sub A {
3849
	my ($self, $m) = @_;
3850 3851 3852 3853
	my ($dir, $file) = split_path($m->{file_b});
	my $pbat = $self->ensure_path($dir);
	my $fbat = $self->add_file($self->repo_path($m->{file_b}), $pbat,
					undef, -1);
3854
	print "\tA\t$m->{file_b}\n" unless $::_q;
3855
	$self->apply_autoprops($file, $fbat);
3856 3857 3858 3859 3860
	$self->chg_file($fbat, $m);
	$self->close_file($fbat,undef,$self->{pool});
}

sub C {
3861
	my ($self, $m) = @_;
3862 3863 3864 3865
	my ($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}), $self->{r});
3866
	print "\tC\t$m->{file_a} => $m->{file_b}\n" unless $::_q;
3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879
	$self->chg_file($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 {
3880
	my ($self, $m) = @_;
3881 3882 3883 3884
	my ($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}), $self->{r});
3885
	print "\tR\t$m->{file_a} => $m->{file_b}\n" unless $::_q;
3886
	$self->apply_autoprops($file, $fbat);
3887 3888 3889 3890 3891 3892 3893 3894 3895
	$self->chg_file($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 {
3896
	my ($self, $m) = @_;
3897 3898 3899 3900
	my ($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},$self->{pool});
3901
	print "\t$m->{chg}\t$m->{file_b}\n" unless $::_q;
3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912
	$self->chg_file($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});
}

3913 3914
sub _chg_file_get_blob ($$$$) {
	my ($self, $fbat, $m, $which) = @_;
3915
	my $fh = $::_repository->temp_acquire("git_blob_$which");
3916
	if ($m->{"mode_$which"} =~ /^120/) {
3917 3918
		print $fh 'link ' or croak $!;
		$self->change_file_prop($fbat,'svn:special','*');
3919
	} elsif ($m->{mode_a} =~ /^120/ && $m->{"mode_$which"} !~ /^120/) {
3920 3921
		$self->change_file_prop($fbat,'svn:special',undef);
	}
3922 3923 3924 3925
	my $blob = $m->{"sha1_$which"};
	return ($fh,) if ($blob =~ /^0{40}$/);
	my $size = $::_repository->cat_blob($blob, $fh);
	croak "Failed to read object $blob" if ($size < 0);
3926 3927 3928
	$fh->flush == 0 or croak $!;
	seek $fh, 0, 0 or croak $!;

3929
	my $exp = ::md5sum($fh);
3930
	seek $fh, 0, 0 or croak $!;
3931 3932
	return ($fh, $exp);
}
3933

3934 3935 3936 3937 3938 3939 3940
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);
	}
3941 3942
	my ($fh_a, $exp_a) = _chg_file_get_blob $self, $fbat, $m, 'a';
	my ($fh_b, $exp_b) = _chg_file_get_blob $self, $fbat, $m, 'b';
3943
	my $pool = SVN::Pool->new;
3944 3945 3946
	my $atd = $self->apply_textdelta($fbat, $exp_a, $pool);
	if (-s $fh_a) {
		my $txstream = SVN::TxDelta::new ($fh_a, $fh_b, $pool);
3947 3948 3949 3950 3951
		my $res = SVN::TxDelta::send_txstream($txstream, @$atd, $pool);
		if (defined $res) {
			die "Unexpected result from send_txstream: $res\n",
			    "(SVN::Core::VERSION: $SVN::Core::VERSION)\n";
		}
3952 3953 3954 3955 3956 3957 3958
	} else {
		my $got = SVN::TxDelta::send_stream($fh_b, @$atd, $pool);
		die "Checksum mismatch\nexpected: $exp_b\ngot: $got\n"
		    if ($got ne $exp_b);
	}
	Git::temp_release($fh_b, 1);
	Git::temp_release($fh_a, 1);
3959
	$pool->clear;
3960 3961 3962
}

sub D {
3963
	my ($self, $m) = @_;
3964 3965
	my ($dir, $file) = split_path($m->{file_b});
	my $pbat = $self->ensure_path($dir);
3966
	print "\tD\t$m->{file_b}\n" unless $::_q;
3967 3968 3969 3970 3971 3972 3973
	$self->delete_entry($m->{file_b}, $pbat);
}

sub close_edit {
	my ($self) = @_;
	my ($p,$bat) = ($self->{pool}, $self->{bat});
	foreach (sort { $b =~ tr#/#/# <=> $a =~ tr#/#/# } keys %$bat) {
3974
		next if $_ eq '';
3975 3976
		$self->close_directory($bat->{$_}, $p);
	}
3977
	$self->close_directory($bat->{''}, $p);
3978 3979 3980 3981 3982 3983 3984
	$self->SUPER::close_edit($p);
	$p->clear;
}

sub abort_edit {
	my ($self) = @_;
	$self->SUPER::abort_edit($self->{pool});
3985 3986 3987 3988 3989
}

sub DESTROY {
	my $self = shift;
	$self->SUPER::DESTROY(@_);
3990 3991 3992
	$self->{pool}->clear;
}

3993 3994
# this drives the editor
sub apply_diff {
3995 3996
	my ($self) = @_;
	my $mods = $self->{mods};
3997
	my %o = ( D => 1, R => 0, C => -1, A => 3, M => 3, T => 3 );
3998
	foreach my $m (sort { $o{$a->{chg}} <=> $o{$b->{chg}} } @$mods) {
3999 4000 4001 4002
		my $f = $m->{chg};
		if (defined $o{$f}) {
			$self->$f($m);
		} else {
4003
			fatal("Invalid change type: $f");
4004 4005
		}
	}
4006
	$self->rmdirs if $_rmdir;
4007
	if (@$mods == 0) {
4008 4009 4010 4011
		$self->abort_edit;
	} else {
		$self->close_edit;
	}
4012
	return scalar @$mods;
4013 4014
}

4015
package Git::SVN::Ra;
4016
use vars qw/@ISA $config_dir $_log_window_size/;
4017 4018
use strict;
use warnings;
4019
my ($ra_invalid, $can_do_switch, %ignored_err, $RA);
4020 4021 4022

BEGIN {
	# enforce temporary pool usage for some simple functions
4023
	no strict 'refs';
4024 4025
	for my $f (qw/rev_proplist get_latest_revnum get_uuid get_repos_root
	              get_file/) {
4026 4027 4028 4029 4030 4031 4032 4033
		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];
		};
4034 4035 4036
	}
}

4037 4038 4039 4040 4041 4042 4043 4044 4045
sub _auth_providers () {
	[
	  SVN::Client::get_simple_provider(),
	  SVN::Client::get_ssl_server_trust_file_provider(),
	  SVN::Client::get_simple_prompt_provider(
	    \&Git::SVN::Prompt::simple, 2),
	  SVN::Client::get_ssl_client_cert_file_provider(),
	  SVN::Client::get_ssl_client_cert_prompt_provider(
	    \&Git::SVN::Prompt::ssl_client_cert, 2),
4046
	  SVN::Client::get_ssl_client_cert_pw_file_provider(),
4047 4048 4049 4050 4051 4052 4053 4054 4055 4056
	  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)
	]
}

4057 4058 4059 4060
sub escape_uri_only {
	my ($uri) = @_;
	my @tmp;
	foreach (split m{/}, $uri) {
4061
		s/([^~\w.%+-]|%(?![a-fA-F0-9]{2}))/sprintf("%%%02X",ord($1))/eg;
4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075
		push @tmp, $_;
	}
	join('/', @tmp);
}

sub escape_url {
	my ($url) = @_;
	if ($url =~ m#^(https?)://([^/]+)(.*)$#) {
		my ($scheme, $domain, $uri) = ($1, $2, escape_uri_only($3));
		$url = "$scheme://$domain$uri";
	}
	$url;
}

4076 4077
sub new {
	my ($class, $url) = @_;
4078
	$url =~ s!/+$!!;
4079
	return $RA if ($RA && $RA->{url} eq $url);
4080

4081
	SVN::_Core::svn_config_ensure($config_dir, undef);
4082
	my ($baton, $callbacks) = SVN::Core::auth_open_helper(_auth_providers);
4083
	my $config = SVN::Core::config_get_config($config_dir);
4084
	$RA = undef;
4085 4086 4087
	my $dont_store_passwords = 1;
	my $conf_t = ${$config}{'config'};
	{
4088
		no warnings 'once';
4089 4090 4091
		# The usage of $SVN::_Core::SVN_CONFIG_* variables
		# produces warnings that variables are used only once.
		# I had not found the better way to shut them up, so
4092
		# the warnings of type 'once' are disabled in this block.
4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106
		if (SVN::_Core::svn_config_get_bool($conf_t,
		    $SVN::_Core::SVN_CONFIG_SECTION_AUTH,
		    $SVN::_Core::SVN_CONFIG_OPTION_STORE_PASSWORDS,
		    1) == 0) {
			SVN::_Core::svn_auth_set_parameter($baton,
			    $SVN::_Core::SVN_AUTH_PARAM_DONT_STORE_PASSWORDS,
			    bless (\$dont_store_passwords, "_p_void"));
		}
		if (SVN::_Core::svn_config_get_bool($conf_t,
		    $SVN::_Core::SVN_CONFIG_SECTION_AUTH,
		    $SVN::_Core::SVN_CONFIG_OPTION_STORE_AUTH_CREDS,
		    1) == 0) {
			$Git::SVN::Prompt::_no_auth_cache = 1;
		}
4107
	} # no warnings 'once'
4108
	my $self = SVN::Ra->new(url => escape_url($url), auth => $baton,
4109 4110 4111
	                      config => $config,
			      pool => SVN::Pool->new,
	                      auth_provider_callbacks => $callbacks);
4112
	$self->{url} = $url;
4113 4114
	$self->{svn_path} = $url;
	$self->{repos_root} = $self->get_repos_root;
4115
	$self->{svn_path} =~ s#^\Q$self->{repos_root}\E(/|$)##;
4116 4117
	$self->{cache} = { check_path => { r => 0, data => {} },
	                   get_dir => { r => 0, data => {} } };
4118
	$RA = bless $self, $class;
4119 4120
}

4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156
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;
}

4157
sub DESTROY {
4158
	# do not call the real DESTROY since we store ourselves in $RA
4159 4160
}

E
Eric Wong 已提交
4161 4162
# get_log(paths, start, end, limit,
#         discover_changed_paths, strict_node_history, receiver)
4163 4164 4165
sub get_log {
	my ($self, @args) = @_;
	my $pool = SVN::Pool->new;
E
Eric Wong 已提交
4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177

	# the limit parameter was not supported in SVN 1.1.x, so we
	# drop it.  Therefore, the receiver callback passed to it
	# is made aware of this limitation by being wrapped if
	# the limit passed to is being wrapped.
	if ($SVN::Core::VERSION le '1.2.0') {
		my $limit = splice(@args, 3, 1);
		if ($limit > 0) {
			my $receiver = pop @args;
			push(@args, sub { &$receiver(@_) if (--$limit >= 0) });
		}
	}
4178 4179 4180 4181 4182
	my $ret = $self->SUPER::get_log(@args, $pool);
	$pool->clear;
	$ret;
}

4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200
sub trees_match {
	my ($self, $url1, $rev1, $url2, $rev2) = @_;
	my $ctx = SVN::Client->new(auth => _auth_providers);
	my $out = IO::File->new_tmpfile;

	# older SVN (1.1.x) doesn't take $pool as the last parameter for
	# $ctx->diff(), so we'll create a default one
	my $pool = SVN::Pool->new_default_sub;

	$ra_invalid = 1; # this will open a new SVN::Ra connection to $url1
	$ctx->diff([], $url1, $rev1, $url2, $rev2, 1, 1, 0, $out, $out);
	$out->flush;
	my $ret = (($out->stat)[7] == 0);
	close $out or croak $!;

	$ret;
}

4201
sub get_commit_editor {
4202
	my ($self, $log, $cb, $pool) = @_;
4203
	my @lock = $SVN::Core::VERSION ge '1.2.0' ? (undef, 0) : ();
4204
	$self->SUPER::get_commit_editor($log, $cb, @lock, $pool);
4205 4206 4207
}

sub gs_do_update {
4208 4209 4210 4211
	my ($self, $rev_a, $rev_b, $gs, $editor) = @_;
	my $new = ($rev_a == $rev_b);
	my $path = $gs->{path};

4212 4213 4214 4215
	if ($new && -e $gs->{index}) {
		unlink $gs->{index} or die
		  "Couldn't unlink index: $gs->{index}: $!\n";
	}
4216
	my $pool = SVN::Pool->new;
4217
	$editor->set_path_strip($path);
4218 4219
	my (@pc) = split m#/#, $path;
	my $reporter = $self->do_update($rev_b, (@pc ? shift @pc : ''),
4220
	                                1, $editor, $pool);
4221
	my @lock = $SVN::Core::VERSION ge '1.2.0' ? (undef) : ();
4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236

	# 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);

4237 4238 4239 4240 4241
	$reporter->finish_report($pool);
	$pool->clear;
	$editor->{git_commit_ok};
}

4242 4243
# 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)
4244
sub gs_do_switch {
4245 4246
	my ($self, $rev_a, $rev_b, $gs, $url_b, $editor) = @_;
	my $path = $gs->{path};
4247
	my $pool = SVN::Pool->new;
4248 4249 4250

	my $full_url = $self->{url};
	my $old_url = $full_url;
4251
	$full_url .= '/' . escape_uri_only($path) if length $path;
4252
	my ($ra, $reparented);
4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263

	if ($old_url =~ m#^svn(\+ssh)?://#) {
		$_[0] = undef;
		$self = undef;
		$RA = undef;
		$ra = Git::SVN::Ra->new($full_url);
		$ra_invalid = 1;
	} elsif ($old_url ne $full_url) {
		SVN::_Ra::svn_ra_reparent($self->{session}, $full_url, $pool);
		$self->{url} = $full_url;
		$reparented = 1;
4264
	}
4265

4266
	$ra ||= $self;
4267
	$url_b = escape_url($url_b);
4268
	my $reporter = $ra->do_switch($rev_b, '', 1, $url_b, $editor, $pool);
4269
	my @lock = $SVN::Core::VERSION ge '1.2.0' ? (undef) : ();
4270
	$reporter->set_path('', $rev_a, 0, @lock, $pool);
4271
	$reporter->finish_report($pool);
4272

4273 4274 4275 4276
	if ($reparented) {
		SVN::_Ra::svn_ra_reparent($self->{session}, $old_url, $pool);
		$self->{url} = $old_url;
	}
4277

4278 4279 4280 4281
	$pool->clear;
	$editor->{git_commit_ok};
}

4282 4283
sub longest_common_path {
	my ($gsv, $globs) = @_;
4284
	my %common;
4285 4286 4287
	my $common_max = scalar @$gsv;

	foreach my $gs (@$gsv) {
4288 4289 4290 4291 4292 4293 4294 4295
		my @tmp = split m#/#, $gs->{path};
		my $p = '';
		foreach (@tmp) {
			$p .= length($p) ? "/$_" : $_;
			$common{$p} ||= 0;
			$common{$p}++;
		}
	}
4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307
	$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}++;
		}
	}

4308 4309
	my $longest_path = '';
	foreach (sort {length $b <=> length $a} keys %common) {
4310
		if ($common{$_} == $common_max) {
4311 4312 4313
			$longest_path = $_;
			last;
		}
4314
	}
4315 4316 4317 4318 4319 4320 4321 4322 4323
	$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);
4324
	my $ra_url = $self->{url};
4325
	while (1) {
4326
		my %revs;
4327
		my $err;
4328
		my $err_handler = $SVN::Error::handler;
4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359
		$SVN::Error::handler = sub {
			($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;
				}
			}
		}
4360
		$SVN::Error::handler = $err_handler;
4361

4362
		my %exists = map { $_->{path} => $_ } @$gsv;
4363
		foreach my $r (sort {$a <=> $b} keys %revs) {
4364
			my ($paths, $logged) = @{$revs{$r}};
4365 4366 4367

			foreach my $gs ($self->match_globs(\%exists, $paths,
			                                   $globs, $r)) {
4368
				if ($gs->rev_map_max >= $r) {
4369 4370 4371 4372
					next;
				}
				next unless $gs->match_paths($paths, $r);
				$gs->{logged_rev_props} = $logged;
4373 4374 4375
				if (my $last_commit = $gs->last_commit) {
					$gs->assert_index_clean($last_commit);
				}
4376 4377
				my $log_entry = $gs->do_fetch($paths, $r);
				if ($log_entry) {
4378 4379
					$gs->do_git_commit($log_entry);
				}
4380
				$INDEX_FILES{$gs->{index}} = 1;
4381
			}
4382
			foreach my $g (@$globs) {
4383 4384 4385
				my $k = "svn-remote.$g->{remote}." .
				        "$g->{t}-maxRev";
				Git::SVN::tmp_config($k, $r);
4386
			}
4387 4388 4389 4390 4391 4392 4393
			if ($ra_invalid) {
				$_[0] = undef;
				$self = undef;
				$RA = undef;
				$self = Git::SVN::Ra->new($ra_url);
				$ra_invalid = undef;
			}
4394
		}
4395 4396
		# pre-fill the .rev_db since it'll eventually get filled in
		# with '0' x40 if something new gets committed
4397
		foreach my $gs (@$gsv) {
4398 4399 4400
			next if $gs->rev_map_max >= $max;
			next if defined $gs->rev_map_get($max);
			$gs->rev_map_set($max, 0 x40);
4401
		}
4402 4403 4404 4405
		foreach my $g (@$globs) {
			my $k = "svn-remote.$g->{remote}.$g->{t}-maxRev";
			Git::SVN::tmp_config($k, $max);
		}
4406 4407 4408 4409 4410
		last if $max >= $head;
		$min = $max + 1;
		$max += $inc;
		$max = $head if ($max > $head);
	}
4411
	Git::SVN::gc();
4412 4413
}

4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434
sub get_dir_globbed {
	my ($self, $left, $depth, $r) = @_;

	my @x = eval { $self->get_dir($left, $r) };
	return unless scalar @x == 3;
	my $dirents = $x[0];
	my @finalents;
	foreach my $de (keys %$dirents) {
		next if $dirents->{$de}->{kind} != $SVN::Node::dir;
		if ($depth > 1) {
			my @args = ("$left/$de", $depth - 1, $r);
			foreach my $dir ($self->get_dir_globbed(@args)) {
				push @finalents, "$de/$dir";
			}
		} else {
			push @finalents, $de;
		}
	}
	@finalents;
}

4435 4436
sub match_globs {
	my ($self, $exists, $paths, $globs, $r) = @_;
4437 4438 4439

	sub get_dir_check {
		my ($self, $exists, $g, $r) = @_;
4440 4441 4442 4443 4444 4445

		my @dirs = $self->get_dir_globbed($g->{path}->{left},
		                                  $g->{path}->{depth},
		                                  $r);

		foreach my $de (@dirs) {
4446 4447 4448 4449 4450 4451 4452 4453 4454
			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);
		}
	}
4455
	foreach my $g (@$globs) {
4456 4457 4458 4459 4460
		if (my $path = $paths->{"/$g->{path}->{left}"}) {
			if ($path->{action} =~ /^[AR]$/) {
				get_dir_check($self, $exists, $g, $r);
			}
		}
4461
		foreach (keys %$paths) {
E
Eric Wong 已提交
4462 4463
			if (/$g->{path}->{left_regex}/ &&
			    !/$g->{path}->{regex}/) {
4464 4465 4466
				next if $paths->{$_}->{action} !~ /^[AR]$/;
				get_dir_check($self, $exists, $g, $r);
			}
4467 4468 4469 4470
			next unless /$g->{path}->{regex}/;
			my $p = $1;
			my $pathname = $g->{path}->full_path($p);
			next if $exists->{$pathname};
4471 4472
			next if ($self->check_path($pathname, $r) !=
			         $SVN::Node::dir);
4473 4474 4475 4476 4477 4478 4479 4480
			$exists->{$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} &&
4481 4482
			             ($paths->{$c}->{action} =~ /^[AR]$/));
			get_dir_check($self, $exists, $g, $r);
4483 4484 4485 4486 4487
		}
	}
	values %$exists;
}

4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500
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;
}

4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519
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;
}

4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532
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) {
4533 4534 4535 4536 4537 4538 4539 4540
		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";
4541 4542 4543 4544
			warn "W: Do not be alarmed at the above message ",
			     "git-svn is just searching aggressively for ",
			     "old history.\n",
			     "This may take a while on large repositories\n";
4545 4546
			$ignored_err{$err_key} = 1;
		}
4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569
		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;
}

4570 4571 4572 4573
package Git::SVN::Log;
use strict;
use warnings;
use POSIX qw/strftime/;
4574
use constant commit_log_separator => ('-' x 72) . "\n";
4575 4576 4577 4578 4579 4580 4581
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};
4582 4583

	# big commit message got truncated by the 16k pretty buffer in rev-list
4584 4585
	if ($c->{l} && $c->{l}->[-1] eq "...\n" &&
				$c->{a_raw} =~ /\@([a-f\d\-]+)>$/) {
4586
		@{$c->{l}} = ();
4587
		my @log = command(qw/cat-file commit/, $c->{c});
4588 4589 4590

		# shift off the headers
		shift @log while ($log[0] ne '');
4591
		shift @log;
4592 4593 4594

		# TODO: make $c->{l} not have a trailing newline in the future
		@{$c->{l}} = map { "$_\n" } grep !/^git-svn-id: /, @log;
4595 4596

		(undef, $c->{r}, undef) = ::extract_metadata(
4597
				(grep(/^git-svn-id: /, @log))[-1]);
4598 4599 4600 4601 4602
	}
	return defined $c->{r};
}

sub log_use_color {
4603
	return $color || Git->repository->get_colorbool('color.diff');
4604 4605 4606
}

sub git_svn_log_cmd {
4607 4608
	my ($r_min, $r_max, @args) = @_;
	my $head = 'HEAD';
4609
	my (@files, @log_opts);
4610
	foreach my $x (@args) {
4611 4612 4613 4614 4615 4616 4617 4618 4619
		if ($x eq '--' || @files) {
			push @files, $x;
		} else {
			if (::verify_ref("$x^0")) {
				$head = $x;
			} else {
				push @log_opts, $x;
			}
		}
4620 4621
	}

4622 4623
	my ($url, $rev, $uuid, $gs) = ::working_head_info($head);
	$gs ||= Git::SVN->_new;
4624 4625 4626 4627 4628
	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();
4629 4630
	push @cmd, @log_opts;
	if (defined $r_max && $r_max == $r_min) {
4631
		push @cmd, '--max-count=1';
4632
		if (my $c = $gs->rev_map_get($r_max)) {
4633 4634
			push @cmd, $c;
		}
4635
	} elsif (defined $r_max) {
4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646
		if ($r_max < $r_min) {
			($r_min, $r_max) = ($r_max, $r_min);
		}
		my (undef, $c_max) = $gs->find_rev_before($r_max, 1, $r_min);
		my (undef, $c_min) = $gs->find_rev_after($r_min, 1, $r_max);
		# If there are no commits in the range, both $c_max and $c_min
		# will be undefined.  If there is at least 1 commit in the
		# range, both will be defined.
		return () if !defined $c_min || !defined $c_max;
		if ($c_min eq $c_max) {
			push @cmd, '--max-count=1', $c_min;
4647
		} else {
4648
			push @cmd, '--boundary', "$c_min..$c_max";
4649 4650
		}
	}
4651
	return (@cmd, @files);
4652 4653 4654 4655 4656 4657 4658 4659 4660 4661
}

# 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;
	}
4662
	$ENV{GIT_PAGER_IN_USE} = defined($pager);
4663 4664 4665
}

sub run_pager {
4666
	return unless -t *STDOUT && defined $pager;
4667
	pipe my ($rfd, $wfd) or return;
4668
	defined(my $pid = fork) or ::fatal "Can't fork: $!";
4669 4670
	if (!$pid) {
		open STDOUT, '>&', $wfd or
4671
		                     ::fatal "Can't redirect to stdout: $!";
4672 4673
		return;
	}
4674
	open STDIN, '<&', $rfd or ::fatal "Can't redirect stdin: $!";
4675
	$ENV{LESS} ||= 'FRSX';
4676
	exec $pager or ::fatal "Can't run pager: $! ($pager)";
4677 4678
}

4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701
sub format_svn_date {
	return strftime("%Y-%m-%d %H:%M:%S %z (%a, %d %b %Y)", localtime(shift));
}

sub parse_git_date {
	my ($t, $tz) = @_;
	# Date::Parse isn't in the standard Perl distro :(
	if ($tz =~ s/^\+//) {
		$t += tz_to_s_offset($tz);
	} elsif ($tz =~ s/^\-//) {
		$t -= tz_to_s_offset($tz);
	}
	return $t;
}

sub set_local_timezone {
	if (defined $TZ) {
		$ENV{TZ} = $TZ;
	} else {
		delete $ENV{TZ};
	}
}

4702 4703 4704 4705 4706 4707
sub tz_to_s_offset {
	my ($tz) = @_;
	$tz =~ s/(\d\d)$//;
	return ($1 * 60) + ($tz * 3600);
}

4708 4709 4710 4711 4712
sub get_author_info {
	my ($dest, $author, $t, $tz) = @_;
	$author =~ s/(?:^\s*|\s*$)//g;
	$dest->{a_raw} = $author;
	my $au;
4713
	if ($::_authors) {
4714 4715 4716 4717 4718 4719 4720 4721
		$au = $rusers{$author} || undef;
	}
	if (!$au) {
		($au) = ($author =~ /<([^>]+)\@[^>]+>$/);
	}
	$dest->{t} = $t;
	$dest->{tz} = $tz;
	$dest->{a} = $au;
4722
	$dest->{t_utc} = parse_git_date($t, $tz);
4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773
}

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 ($c) = @_;
4774
	print commit_log_separator, "r$c->{r} | ";
4775
	print "$c->{c} | " if $show_commit;
4776
	print "$c->{a} | ", format_svn_date($c->{t_utc}), ' | ';
4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803
	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";

	}
4804
	foreach my $x (qw/raw stat diff/) {
4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815
		if ($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
4816
	set_local_timezone();
4817 4818 4819 4820 4821 4822 4823
	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 ",
4824
				"standard 'git log' arguments instead";
4825 4826 4827 4828
		}
	}

	config_pager();
4829
	@args = git_svn_log_cmd($r_min, $r_max, @args);
4830 4831 4832 4833
	if (!@args) {
		print commit_log_separator unless $incremental || $oneline;
		return;
	}
4834 4835
	my $log = command_output_pipe(@args);
	run_pager();
4836
	my (@k, $c, $d, $stat);
4837 4838
	my $esc_color = qr/(?:\033\[(?:(?:\d+;)*\d*)?m)*/;
	while (<$log>) {
4839
		if (/^${esc_color}commit -?($::sha1_short)/o) {
4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863
			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}}, $_;
4864 4865 4866 4867 4868 4869 4870
		} 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}}, $_;
			$stat = undef;
4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881
		} elsif (/^${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, $r_max, \@k);
	}
	if (@k) {
4882
		($r_min, $r_max) = ($r_max, $r_min);
4883 4884 4885
		process_commit($_, $r_min, $r_max) foreach reverse @k;
	}
out:
4886
	close $log;
4887
	print commit_log_separator unless $incremental || $oneline;
4888 4889
}

T
Tim Stoakes 已提交
4890
sub cmd_blame {
4891
	my $path = pop;
T
Tim Stoakes 已提交
4892 4893 4894 4895

	config_pager();
	run_pager();

4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934
	my ($fh, $ctx, $rev);

	if ($_git_format) {
		($fh, $ctx) = command_output_pipe('blame', @_, $path);
		while (my $line = <$fh>) {
			if ($line =~ /^\^?([[:xdigit:]]+)\s/) {
				# Uncommitted edits show up as a rev ID of
				# all zeros, which we can't look up with
				# cmt_metadata
				if ($1 !~ /^0+$/) {
					(undef, $rev, undef) =
						::cmt_metadata($1);
					$rev = '0' if (!$rev);
				} else {
					$rev = '0';
				}
				$rev = sprintf('%-10s', $rev);
				$line =~ s/^\^?[[:xdigit:]]+(\s)/$rev$1/;
			}
			print $line;
		}
	} else {
		($fh, $ctx) = command_output_pipe('blame', '-p', @_, 'HEAD',
						  '--', $path);
		my ($sha1);
		my %authors;
		while (my $line = <$fh>) {
			if ($line =~ /^([[:xdigit:]]{40})\s\d+\s\d+/) {
				$sha1 = $1;
				(undef, $rev, undef) = ::cmt_metadata($1);
				$rev = '0' if (!$rev);
			}
			elsif ($line =~ /^author (.*)/) {
				$authors{$rev} = $1;
				$authors{$rev} =~ s/\s/_/g;
			}
			elsif ($line =~ /^\t(.*)$/) {
				printf("%6s %10s %s\n", $rev, $authors{$rev}, $1);
			}
T
Tim Stoakes 已提交
4935 4936 4937 4938 4939
		}
	}
	command_close_pipe($fh, $ctx);
}

4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953
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
4954 4955 4956
# v3.1 layout (auto migrated):
#            - .rev_db => .rev_db.$UUID, .rev_db will remain as a symlink
#              for backwards compatibility
4957 4958 4959 4960 4961 4962 4963
#
# v4 layout: .git/svn/$repo_id/$id, refs/remotes/$repo_id/$id
#            - this is only created for newly multi-init-ed
#              repositories.  Similar in spirit to the
#              --use-separate-remotes option in git-clone (now default)
#            - we do not automatically migrate to this (following
#              the example set by core git)
4964 4965 4966 4967 4968 4969 4970 4971 4972 4973
#
# v5 layout: .rev_db.$UUID => .rev_map.$UUID
#            - newer, more-efficient format that uses 24-bytes per record
#              with no filler space.
#            - use xxd -c24 < .rev_map.$UUID to view and debug
#            - This is a one-way migration, repositories updated to the
#              new format will not be able to use old git-svn without
#              rebuilding the .rev_db.  Rebuilding the rev_db is not
#              possible if noMetadata or useSvmProps are set; but should
#              be no problem for users that use the (sensible) defaults.
4974 4975 4976 4977
use strict;
use warnings;
use Carp qw/croak/;
use File::Path qw/mkpath/;
4978 4979
use File::Basename qw/dirname basename/;
use vars qw/$_minimize/;
4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025

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 ",
F
Frederik Schwarzer 已提交
5026
	             "($::VERSION) of git-svn) does not exist.\n";
5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088
	my ($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 $ref_id (sort keys %l_map) {
5089 5090 5091 5092
		eval { Git::SVN->init($l_map{$ref_id}, '', undef, $ref_id) };
		if ($@) {
			Git::SVN->init($l_map{$ref_id}, '', $ref_id, $ref_id);
		}
5093 5094 5095 5096 5097
		$migrated++;
	}
	$migrated;
}

5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108
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 $ra->{repos_root}) ||
5109
		    ($ra->{repos_root} eq $repo_id)) {
5110 5111 5112 5113 5114 5115
			$root_repos->{$ra->{url}} = $repo_id;
			next;
		}

		my $root_ra = Git::SVN::Ra->new($ra->{repos_root});
		my $root_path = $ra->{url};
5116
		$root_path =~ s#^\Q$ra->{repos_root}\E(/|$)##;
5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147
		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:
5148
		my $repo_id = $root_repos->{$url} || $url;
5149 5150 5151 5152 5153 5154 5155 5156 5157

		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/$x->{ref_id}");
5158
			command_noisy(qw/config --unset/,
5159 5160 5161 5162
			              "$pfx.fetch", '^'. $old_fetch . '$');
			delete $r->{$x->{old_repo_id}}->
			       {fetch}->{$x->{old_path}};
			if (!keys %{$r->{$x->{old_repo_id}}->{fetch}}) {
5163
				command_noisy(qw/config --unset/,
5164 5165 5166 5167 5168 5169
				              "$pfx.url");
				push @emptied, $x->{old_repo_id}
			}
		}
	}
	if (@emptied) {
5170
		my $file = $ENV{GIT_CONFIG} || "$ENV{GIT_DIR}/config";
5171 5172 5173 5174 5175 5176 5177 5178
		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;
	}
}

5179 5180 5181 5182
sub migration_check {
	migrate_from_v0();
	migrate_from_v1();
	migrate_from_v2();
5183
	minimize_connections() if $_minimize;
5184 5185
}

5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217
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});
}

5218 5219 5220 5221 5222 5223 5224 5225
package Git::SVN::GlobSpec;
use strict;
use warnings;

sub new {
	my ($class, $glob) = @_;
	my $re = $glob;
	$re =~ s!/+$!!g; # no need for trailing slashes
5226 5227 5228 5229 5230 5231 5232 5233 5234 5235
	$re =~ m!^([^*]*)(\*(?:/\*)*)([^*]*)$!;
	my $temp = $re;
	my ($left, $right) = ($1, $3);
	$re = $2;
	my $depth = $re =~ tr/*/*/;
	if ($depth != $temp =~ tr/*/*/) {
		die "Only one set of wildcard directories " .
			"(e.g. '*' or '*/*/*') is supported: '$glob'\n";
	}
	if ($depth == 0) {
5236
		die "One '*' is needed for glob: '$glob'\n";
5237
	}
5238 5239
	$re =~ s!\*!\[^/\]*!g;
	$re = quotemeta($left) . "($re)" . quotemeta($right);
5240 5241 5242 5243 5244 5245
	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";
	}
5246 5247
	my $left_re = qr/^\/\Q$left\E(\/|$)/;
	bless { left => $left, right => $right, left_regex => $left_re,
5248
	        regex => qr/$re/, glob => $glob, depth => $depth }, $class;
5249 5250 5251 5252 5253 5254 5255 5256
}

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

E
Eric Wong 已提交
5257 5258 5259 5260
__END__

Data structures:

5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287

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

5288
$log_entry hashref as returned by libsvn_log_entry()
E
Eric Wong 已提交
5289
{
5290
	log => 'whitespace-formatted log entry
E
Eric Wong 已提交
5291 5292 5293 5294 5295 5296
',						# trailing newline is preserved
	revision => '8',			# integer
	date => '2004-02-24T17:01:44.108345Z',	# commit date
	author => 'committer name'
};

5297 5298

# this is generated by generate_diff();
E
Eric Wong 已提交
5299 5300 5301 5302 5303 5304 5305 5306
@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,
5307
	chg => change type [MCRADT],
E
Eric Wong 已提交
5308 5309 5310 5311
	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)
}
;
5312

5313 5314 5315 5316 5317 5318 5319 5320 5321 5322
# 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',
	},
}

5323 5324 5325
Notes:
	I don't trust the each() function on unless I created %hash myself
	because the internal iterator may not have started at base.