git-svn.perl 136.0 KB
Newer Older
E
Eric Wong 已提交
1
#!/usr/bin/env perl
2 3
# Copyright (C) 2006, Eric Wong <normalperson@yhbt.net>
# License: GPL v2 or later
E
Eric Wong 已提交
4 5 6
use warnings;
use strict;
use vars qw/	$AUTHOR $VERSION
7 8
		$sha1 $sha1_short $_revision
		$_q $_authors %users/;
E
Eric Wong 已提交
9
$AUTHOR = 'Eric Wong <normalperson@yhbt.net>';
E
Eric Wong 已提交
10
$VERSION = '@@GIT_VERSION@@';
11

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,
D
David D. Kilzer 已提交
68
	$_prefix, $_no_checkout, $_url, $_verbose);
69
$Git::SVN::_follow_parent = 1;
70 71 72
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 );
73
my %fc_opts = ( 'follow-parent|follow!' => \$Git::SVN::_follow_parent,
74
		'authors-file|A=s' => \$_authors,
E
Eric Wong 已提交
75
		'repack:i' => \$Git::SVN::_repack,
76 77
		'noMetadata' => \$Git::SVN::_no_metadata,
		'useSvmProps' => \$Git::SVN::_use_svm_props,
78
		'useSvnsyncProps' => \$Git::SVN::_use_svnsync_props,
79
		'log-window-size=i' => \$Git::SVN::Ra::_log_window_size,
80
		'no-checkout' => \$_no_checkout,
81
		'quiet|q' => \$_q,
E
Eric Wong 已提交
82 83
		'repack-flags|repack-args|repack-opts=s' =>
		   \$Git::SVN::_repack_flags,
84
		'use-log-author' => \$Git::SVN::_use_log_author,
85
		%remote_opts );
86

87
my ($_trunk, $_tags, $_branches, $_stdlayout);
88
my %icv;
89 90 91
my %init_opts = ( 'template=s' => \$_template, 'shared:s' => \$_shared,
                  'trunk|T=s' => \$_trunk, 'tags|t=s' => \$_tags,
                  'branches|b=s' => \$_branches, 'prefix=s' => \$_prefix,
92
                  'stdlayout|s' => \$_stdlayout,
93
                  'minimize-url|m' => \$Git::SVN::_minimize_url,
94 95 96 97
		  '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] },
98
                  %remote_opts );
E
Eric Wong 已提交
99
my %cmt_opts = ( 'edit|e' => \$_edit,
100 101 102 103
		'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
104
);
105

E
Eric Wong 已提交
106
my %cmd = (
107
	fetch => [ \&cmd_fetch, "Download new revisions from SVN",
108
			{ 'revision|r=s' => \$_revision,
E
Eric Wong 已提交
109
			  'fetch-all|all' => \$_fetch_all,
110
			   %fc_opts } ],
111 112 113
	clone => [ \&cmd_clone, "Initialize and fetch revisions",
			{ 'revision|r=s' => \$_revision,
			   %fc_opts, %init_opts } ],
114
	init => [ \&cmd_init, "Initialize a repo for tracking" .
115
			  " (requires URL argument)",
116
			  \%init_opts ],
117 118 119 120
	'multi-init' => [ \&cmd_multi_init,
	                  "Deprecated alias for ".
			  "'$0 init -T<trunk> -b<branches> -t<tags>'",
			  \%init_opts ],
121 122
	dcommit => [ \&cmd_dcommit,
	             'Commit several diffs to merge with upstream',
123 124
			{ 'merge|m|M' => \$_merge,
			  'strategy|s=s' => \$_strategy,
E
Eric Wong 已提交
125
			  'verbose|v' => \$_verbose,
126
			  'dry-run|n' => \$_dry_run,
E
Eric Wong 已提交
127
			  'fetch-all|all' => \$_fetch_all,
128
			  'no-rebase' => \$_no_rebase,
129
			%cmt_opts, %fc_opts } ],
130 131 132
	'set-tree' => [ \&cmd_set_tree,
	                "Set an SVN repository to a git tree-ish",
			{ 'stdin|' => \$_stdin, %cmt_opts, %fc_opts, } ],
133 134 135 136
	'create-ignore' => [ \&cmd_create_ignore,
			     'Create a .gitignore per svn:ignore',
			     { 'revision|r=i' => \$_revision
			     } ],
B
Benoit Sigoure 已提交
137 138 139
        'propget' => [ \&cmd_propget,
		       'Print the value of a property on a file or directory',
		       { 'revision|r=i' => \$_revision } ],
B
Benoit Sigoure 已提交
140 141 142
        'proplist' => [ \&cmd_proplist,
		       'List all properties of a file or directory',
		       { 'revision|r=i' => \$_revision } ],
143
	'show-ignore' => [ \&cmd_show_ignore, "Show svn:ignore listings",
L
Lars Hjemli 已提交
144
			{ 'revision|r=i' => \$_revision
145
			} ],
146 147 148
	'show-externals' => [ \&cmd_show_externals, "Show svn:externals listings",
			{ 'revision|r=i' => \$_revision
			} ],
149
	'multi-fetch' => [ \&cmd_multi_fetch,
150 151
	                   "Deprecated alias for $0 fetch --all",
			   { 'revision|r=s' => \$_revision, %fc_opts } ],
152 153 154 155
	'migrate' => [ sub { },
	               # no-op, we automatically run this anyways,
	               'Migrate configuration/metadata/layout from
		        previous versions of git-svn',
156 157
                       { 'minimize' => \$Git::SVN::Migration::_minimize,
			 %remote_opts } ],
158 159
	'log' => [ \&Git::SVN::Log::cmd_show_log, 'Show commit logs',
			{ 'limit=i' => \$Git::SVN::Log::limit,
160
			  'revision|r=s' => \$_revision,
161 162 163 164 165
			  '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,
166
			  'authors-file|A=s' => \$_authors,
167
			  'color' => \$Git::SVN::Log::color,
L
Lars Hjemli 已提交
168
			  'pager=s' => \$Git::SVN::Log::pager
169
			} ],
A
Adam Roben 已提交
170
	'find-rev' => [ \&cmd_find_rev, "Translate between SVN revision numbers and tree-ish",
L
Lars Hjemli 已提交
171
			{} ],
E
Eric Wong 已提交
172 173 174 175
	'rebase' => [ \&cmd_rebase, "Fetch and rebase your working directory",
			{ 'merge|m|M' => \$_merge,
			  'verbose|v' => \$_verbose,
			  'strategy|s=s' => \$_strategy,
176
			  'local|l' => \$_local,
E
Eric Wong 已提交
177 178
			  'fetch-all|all' => \$_fetch_all,
			  %fc_opts } ],
179 180
	'commit-diff' => [ \&cmd_commit_diff,
	                   'Commit a diff between two trees',
E
Eric Wong 已提交
181 182
			{ 'message|m=s' => \$_message,
			  'file|F=s' => \$_file,
183
			  'revision|r=s' => \$_revision,
E
Eric Wong 已提交
184
			%cmt_opts } ],
185 186 187
	'info' => [ \&cmd_info,
		    "Show info about the latest SVN revision
		     on the current branch",
D
David D. Kilzer 已提交
188
		    { 'url' => \$_url, } ],
T
Tim Stoakes 已提交
189 190 191
	'blame' => [ \&Git::SVN::Log::cmd_blame,
	            "Show what revision and author last modified each line of a file",
	            {} ],
E
Eric Wong 已提交
192
);
193

E
Eric Wong 已提交
194 195 196 197 198 199 200 201 202
my $cmd;
for (my $i = 0; $i < @ARGV; $i++) {
	if (defined $cmd{$ARGV[$i]}) {
		$cmd = $ARGV[$i];
		splice @ARGV, $i, 1;
		last;
	}
};

203 204
# make sure we're always running at the top-level working directory
unless ($cmd && $cmd =~ /(?:clone|init|multi-init)$/) {
205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223
	unless (-d $ENV{GIT_DIR}) {
		if ($git_dir_user_set) {
			die "GIT_DIR=$ENV{GIT_DIR} explicitly set, ",
			    "but it is not a directory\n";
		}
		my $git_dir = delete $ENV{GIT_DIR};
		chomp(my $cdup = command_oneline(qw/rev-parse --show-cdup/));
		unless (length $cdup) {
			die "Already at toplevel, but $git_dir ",
			    "not found '$cdup'\n";
		}
		chdir $cdup or die "Unable to chdir up to '$cdup'\n";
		unless (-d $git_dir) {
			die "$git_dir still not found after going to ",
			    "'$cdup'\n";
		}
		$ENV{GIT_DIR} = $git_dir;
	}
}
224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241

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

read_repo_config(\%opts);
Getopt::Long::Configure('pass_through') if ($cmd && $cmd eq 'log');
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;

242
unless ($cmd =~ /^(?:clone|init|multi-init|commit-diff)$/) {
243 244
	Git::SVN::Migration::migration_check();
}
E
Eric Wong 已提交
245
Git::SVN::init_vars();
246 247 248 249 250
eval {
	Git::SVN::verify_remotes_sanity();
	$cmd{$cmd}->[0]->(@ARGV);
};
fatal $@ if $@;
251
post_fetch_checkout();
E
Eric Wong 已提交
252 253 254 255 256 257 258 259 260
exit 0;

####################### primary functions ######################
sub usage {
	my $exit = shift || 0;
	my $fd = $exit ? \*STDERR : \*STDOUT;
	print $fd <<"";
git-svn - bidirectional operations between a single Subversion tree and git
Usage: $0 <command> [options] [arguments]\n
261 262

	print $fd "Available commands:\n" unless $cmd;
E
Eric Wong 已提交
263 264

	foreach (sort keys %cmd) {
265
		next if $cmd && $cmd ne $_;
266
		next if /^multi-/; # don't show deprecated commands
267
		print $fd '  ',pack('A17',$_),$cmd{$_}->[1],"\n";
268
		foreach (sort keys %{$cmd{$_}->[2]}) {
269 270
			# mixed-case options are for .git/config only
			next if /[A-Z]/ && /^[a-z]+$/i;
271
			# prints out arguments as they should be passed:
272
			my $x = s#[:=]s$## ? '<arg>' : s#[:=]i$## ? '<num>' : '';
273
			print $fd ' ' x 21, join(', ', map { length $_ > 1 ?
274 275 276
							"--$_" : "-$_" }
						split /\|/,$_)," $x\n";
		}
E
Eric Wong 已提交
277 278
	}
	print $fd <<"";
279 280 281 282
\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
283 284 285 286

	exit $exit;
}

287
sub version {
288
	print "git-svn version $VERSION (svn $SVN::Core::VERSION)\n";
289 290 291
	exit 0;
}

292 293 294 295
sub do_git_init_db {
	unless (-d $ENV{GIT_DIR}) {
		my @init_db = ('init');
		push @init_db, "--template=$_template" if defined $_template;
296 297 298 299 300 301 302
		if (defined $_shared) {
			if ($_shared =~ /[a-z]/) {
				push @init_db, "--shared=$_shared";
			} else {
				push @init_db, "--shared";
			}
		}
303 304
		command_noisy(@init_db);
	}
305 306 307 308 309 310 311 312
	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;
	}
313 314
}

315 316 317 318
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";
319
	$ENV{GIT_DIR} = '.git';
320 321
}

322 323 324
sub cmd_clone {
	my ($url, $path) = @_;
	if (!defined $path &&
325 326
	    (defined $_trunk || defined $_branches || defined $_tags ||
	     defined $_stdlayout) &&
327 328 329 330
	    $url !~ m#^[a-z\+]+://#) {
		$path = $url;
	}
	$path = basename($url) if !defined $path || !length $path;
331
	cmd_init($url, $path);
332 333 334
	Git::SVN::fetch_all($Git::SVN::default_repo_id);
}

335
sub cmd_init {
336 337 338 339 340
	if (defined $_stdlayout) {
		$_trunk = 'trunk' if (!defined $_trunk);
		$_tags = 'tags' if (!defined $_tags);
		$_branches = 'branches' if (!defined $_branches);
	}
341 342
	if (defined $_trunk || defined $_branches || defined $_tags) {
		return cmd_multi_init(@_);
343
	}
344 345 346
	my $url = shift or die "SVN repository location required ",
	                       "as a command-line argument\n";
	init_subdir(@_);
347
	do_git_init_db();
348

349
	Git::SVN->init($url);
E
Eric Wong 已提交
350 351
}

352
sub cmd_fetch {
353 354 355
	if (grep /^\d+=./, @_) {
		die "'<rev>=<commit>' fetch arguments are ",
		    "no longer supported.\n";
356
	}
357 358
	my ($remote) = @_;
	if (@_ > 1) {
E
Eric Wong 已提交
359
		die "Usage: $0 fetch [--all] [svn-remote]\n";
360 361 362 363 364 365
	}
	$remote ||= $Git::SVN::default_repo_id;
	if ($_fetch_all) {
		cmd_multi_fetch();
	} else {
		Git::SVN::fetch_all($remote, Git::SVN::read_all_remotes());
366
	}
367 368
}

369
sub cmd_set_tree {
E
Eric Wong 已提交
370 371 372 373 374
	my (@commits) = @_;
	if ($_stdin || !@commits) {
		print "Reading from stdin...\n";
		@commits = ();
		while (<STDIN>) {
375
			if (/\b($sha1_short)\b/o) {
E
Eric Wong 已提交
376 377 378 379 380
				unshift @commits, $1;
			}
		}
	}
	my @revs;
381
	foreach my $c (@commits) {
E
Eric Wong 已提交
382
		my @tmp = command('rev-parse',$c);
383 384 385
		if (scalar @tmp == 1) {
			push @revs, $tmp[0];
		} elsif (scalar @tmp > 1) {
E
Eric Wong 已提交
386
			push @revs, reverse(command('rev-list',@tmp));
387
		} else {
388
			fatal "Failed to rev-parse $c";
389
		}
E
Eric Wong 已提交
390
	}
391 392 393
	my $gs = Git::SVN->new;
	my ($r_last, $cmt_last) = $gs->last_rev_commit;
	$gs->fetch;
394
	if (defined $gs->{last_rev} && $r_last != $gs->{last_rev}) {
395 396 397
		fatal "There are new revisions that were fetched ",
		      "and need to be merged (or acknowledged) ",
		      "before committing.\nlast rev: $r_last\n",
398
		      " current: $gs->{last_rev}";
399
	}
400 401
	$gs->set_tree($_) foreach @revs;
	print "Done committing ",scalar @revs," revisions to SVN\n";
402
	unlink $gs->{index};
403
}
404

405 406
sub cmd_dcommit {
	my $head = shift;
407
	git_cmd_try { command_oneline(qw/diff-index --quiet HEAD/) }
408
		'Cannot dcommit with a dirty index.  Commit your changes first, '
409
		. "or stash them with `git stash'.\n";
410
	$head ||= 'HEAD';
411
	my @refs;
412
	my ($url, $rev, $uuid, $gs) = working_head_info($head, \@refs);
413
	print "Committing to $url ...\n";
414
	unless ($gs) {
415
		die "Unable to determine upstream SVN information from ",
E
Eric Wong 已提交
416
		    "$head history\n";
417
	}
418
	my $last_rev;
419
	my ($linear_refs, $parents) = linearize_history($gs, \@refs);
420 421 422 423
	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 ",
424
		     "without --no-rebase may be required."
425
	}
426 427
	while (1) {
		my $d = shift @$linear_refs or last;
428 429 430
		unless (defined $last_rev) {
			(undef, $last_rev, undef) = cmt_metadata("$d~1");
			unless (defined $last_rev) {
431
				fatal "Unable to extract revision information ",
432
				      "from commit $d~1";
433 434
			}
		}
E
Eric Wong 已提交
435 436 437
		if ($_dry_run) {
			print "diff-tree $d~1 $d\n";
		} else {
438
			my $cmt_rev;
439
			my %ed_opts = ( r => $last_rev,
440
			                log => get_commit_entry($d)->{log},
441
			                ra => Git::SVN::Ra->new($gs->full_url),
442 443 444
			                config => SVN::Core::config_get_config(
			                        $Git::SVN::Ra::config_dir
			                ),
445 446 447 448
			                tree_a => "$d~1",
			                tree_b => $d,
			                editor_cb => sub {
			                       print "Committed r$_[0]\n";
449 450
			                       $cmt_rev = $_[0];
			                },
451
			                svn_path => '');
452
			if (!SVN::Git::Editor->new(\%ed_opts)->apply_diff) {
453
				print "No changes\n$d~1 == $d\n";
454
			} elsif ($parents->{$d} && @{$parents->{$d}}) {
455
				$gs->{inject_parents_dcommit}->{$cmt_rev} =
456
				                               $parents->{$d};
457
			}
458
			$_fetch_all ? $gs->fetch_all : $gs->fetch;
459
			$last_rev = $cmt_rev;
460 461 462 463
			next if $_no_rebase;

			# we always want to rebase against the current HEAD,
			# not any head that was passed to us
464
			my @diff = command('diff-tree', $d,
465 466 467 468
			                   $gs->refname, '--');
			my @finish;
			if (@diff) {
				@finish = rebase_cmd();
469
				print STDERR "W: $d and ", $gs->refname,
470
				             " differ, using @finish:\n",
471
				             join("\n", @diff), "\n";
472 473 474 475 476 477 478 479
			} else {
				print "No changes between current HEAD and ",
				      $gs->refname,
				      "\nResetting to the latest ",
				      $gs->refname, "\n";
				@finish = qw/reset --mixed/;
			}
			command_noisy(@finish, $gs->refname);
480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518
			if (@diff) {
				@refs = ();
				my ($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 ',
					  $gs->refname,
					  "\nBefore dcommitting";
				}
				if ($url_ ne $url) {
					fatal "URL mismatch after rebase: ",
					      "$url_ != $url";
				}
				if ($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
519 520
		}
	}
521
	unlink $gs->{index};
E
Eric Wong 已提交
522 523
}

A
Adam Roben 已提交
524
sub cmd_find_rev {
525 526
	my $revision_or_hash = shift or die "SVN or git revision required ",
	                                    "as a command-line argument\n";
A
Adam Roben 已提交
527 528
	my $result;
	if ($revision_or_hash =~ /^r\d+$/) {
A
Adam Roben 已提交
529 530 531 532 533 534 535
		my $head = shift;
		$head ||= 'HEAD';
		my @refs;
		my (undef, undef, undef, $gs) = working_head_info($head, \@refs);
		unless ($gs) {
			die "Unable to determine upstream SVN information from ",
			    "$head history\n";
A
Adam Roben 已提交
536
		}
A
Adam Roben 已提交
537
		my $desired_revision = substr($revision_or_hash, 1);
538
		$result = $gs->rev_map_get($desired_revision);
A
Adam Roben 已提交
539 540 541 542 543 544 545
	} else {
		my (undef, $rev, undef) = cmt_metadata($revision_or_hash);
		$result = $rev;
	}
	print "$result\n" if $result;
}

E
Eric Wong 已提交
546 547
sub cmd_rebase {
	command_noisy(qw/update-index --refresh/);
548 549
	my ($url, $rev, $uuid, $gs) = working_head_info('HEAD');
	unless ($gs) {
E
Eric Wong 已提交
550 551 552 553 554 555 556 557
		die "Unable to determine upstream SVN information from ",
		    "working tree history\n";
	}
	if (command(qw/diff-index HEAD --/)) {
		print STDERR "Cannot rebase with uncommited changes:\n";
		command_noisy('status');
		exit 1;
	}
558
	unless ($_local) {
559 560
		# rebase will checkout for us, so no need to do it explicitly
		$_no_checkout = 'true';
561 562
		$_fetch_all ? $gs->fetch_all : $gs->fetch;
	}
E
Eric Wong 已提交
563 564 565
	command_noisy(rebase_cmd(), $gs->refname);
}

566
sub cmd_show_ignore {
567 568
	my ($url, $rev, $uuid, $gs) = working_head_info('HEAD');
	$gs ||= Git::SVN->new;
569
	my $r = (defined $_revision ? $_revision : $gs->ra->get_latest_revnum);
570 571 572 573 574 575 576 577 578
	$gs->prop_walk($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";
	});
579 580
}

581 582 583 584 585 586 587 588 589 590 591 592 593 594 595
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";
	});
}

596 597 598 599 600 601 602 603 604 605
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, '>', $ignore)
606
		  or fatal("Failed to open `$ignore' for writing: $!");
607 608 609 610 611 612 613
		$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)
614
		  or fatal("Failed to close `$ignore': $!");
615 616 617 618
		command_noisy('add', $ignore);
	});
}

619 620
sub canonicalize_path {
	my ($path) = @_;
621 622 623 624 625
	my $dot_slash_added = 0;
	if (substr($path, 0, 1) ne "/") {
		$path = "./" . $path;
		$dot_slash_added = 1;
	}
626 627 628 629 630 631
	# 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;
632
	$path =~ s#^\./## if $dot_slash_added;
633 634 635
	return $path;
}

B
Benoit Sigoure 已提交
636 637
# get_svnprops(PATH)
# ------------------
B
Benoit Sigoure 已提交
638
# Helper for cmd_propget and cmd_proplist below.
B
Benoit Sigoure 已提交
639 640 641 642 643 644 645 646
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;
647
	fatal("No such file or directory: $path") unless -e $path;
B
Benoit Sigoure 已提交
648 649 650 651 652
	my $is_dir = -d $path ? 1 : 0;
	$path = $gs->{path} . '/' . $path;

	# canonicalize the path (otherwise libsvn will abort or fail to
	# find the file)
653
	$path = canonicalize_path($path);
B
Benoit Sigoure 已提交
654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674

	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}) {
675
		fatal("`$path' does not have a `$prop' SVN property.");
B
Benoit Sigoure 已提交
676 677 678 679
	}
	print $props->{$prop} . "\n";
}

B
Benoit Sigoure 已提交
680 681 682 683 684 685 686 687 688 689 690 691 692
# 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";
	}
}

693
sub cmd_multi_init {
694
	my $url = shift;
695 696
	unless (defined $_trunk || defined $_branches || defined $_tags) {
		usage(1);
697
	}
698 699 700 701 702

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

703
	$_prefix = '' unless defined $_prefix;
704 705 706 707
	if (defined $url) {
		$url =~ s#/+$##;
		init_subdir(@_);
	}
708
	do_git_init_db();
709
	if (defined $_trunk) {
710 711 712
		my $trunk_ref = $_prefix . 'trunk';
		# try both old-style and new-style lookups:
		my $gs_trunk = eval { Git::SVN->new($trunk_ref) };
713
		unless ($gs_trunk) {
714 715 716 717
			my ($trunk_url, $trunk_path) =
			                      complete_svn_url($url, $_trunk);
			$gs_trunk = Git::SVN->init($trunk_url, $trunk_path,
						   undef, $trunk_ref);
718
		}
719
	}
720
	return unless defined $_branches || defined $_tags;
721 722 723
	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/');
724 725
}

726
sub cmd_multi_fetch {
727 728
	my $remotes = Git::SVN::read_all_remotes();
	foreach my $repo_id (sort keys %$remotes) {
729
		if ($remotes->{$repo_id}->{url}) {
730 731
			Git::SVN::fetch_all($repo_id, $remotes);
		}
732 733 734
	}
}

735 736 737 738
# this command is special because it requires no metadata
sub cmd_commit_diff {
	my ($ta, $tb, $url) = @_;
	my $usage = "Usage: $0 commit-diff -r<revision> ".
739
	            "<tree-ish> <tree-ish> [<URL>]";
740
	fatal($usage) if (!defined $ta || !defined $tb);
741
	my $svn_path;
742 743 744 745 746 747 748
	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};
749
		$svn_path = $gs->{path};
750 751 752 753 754 755 756
	}
	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",
757
		      "I have no idea what you mean");
758 759 760 761 762 763 764
	}
	if (defined $_file) {
		$_message = file_to_s($_file);
	} else {
		$_message ||= get_commit_entry($tb)->{log};
	}
	my $ra ||= Git::SVN::Ra->new($url);
765
	$svn_path ||= $ra->{svn_path};
766 767 768 769 770 771
	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";
	}
772 773 774 775 776 777 778 779
	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 => $svn_path );
	if (!SVN::Git::Editor->new(\%ed_opts)->apply_diff) {
780 781 782 783
		print "No changes\n$ta == $tb\n";
	}
}

784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803
sub cmd_info {
	my $path = canonicalize_path(shift or ".");
	unless (scalar(@_) == 0) {
		die "Too many arguments specified\n";
	}

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

	if (!$file_type && !$diff_status) {
		print STDERR "$path:  (Not a versioned resource)\n\n";
		return;
	}

	my ($url, $rev, $uuid, $gs) = working_head_info('HEAD');
	unless ($gs) {
		die "Unable to determine upstream SVN information from ",
		    "working tree history\n";
	}
	my $full_url = $url . ($path eq "." ? "" : "/$path");

D
David D. Kilzer 已提交
804 805 806 807 808
	if ($_url) {
		print $full_url, "\n";
		return;
	}

809 810 811 812
	my $result = "Path: $path\n";
	$result .= "Name: " . basename($path) . "\n" if $file_type ne "dir";
	$result .= "URL: " . $full_url . "\n";

813 814 815 816 817 818 819 820
	eval {
		my $repos_root = $gs->repos_root;
		Git::SVN::remove_username($repos_root);
		$result .= "Repository Root: $repos_root\n";
	};
	if ($@) {
		$result .= "Repository Root: (offline)\n";
	}
821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870
	$result .= "Repository UUID: $uuid\n" unless $diff_status eq "A";
	$result .= "Revision: " . ($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, $lc_date_utc);
	my @args = Git::SVN::Log::git_svn_log_cmd($rev, $rev, "--", $path);
	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>;
871
				$checksum = md5sum("link $file_name");
872
			} else {
873
				$checksum = md5sum($fh);
874 875 876 877 878 879
			}
			command_close_pipe($fh, $ctx);
		} elsif ($file_type eq "link") {
			my $file_name =
			    command(qw(cat-file blob), "HEAD:$path");
			$checksum =
880
			    md5sum("link " . $file_name);
881 882
		} else {
			open FILE, "<", $path or die $!;
883
			$checksum = md5sum(\*FILE);
884 885 886 887 888 889 890 891
			close FILE or die $!;
		}
		$result .= "Checksum: " . $checksum . "\n";
	}

	print $result, "\n";
}

E
Eric Wong 已提交
892 893
########################### utility functions #########################

E
Eric Wong 已提交
894 895 896 897 898 899 900 901
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;
}

902 903 904 905 906 907 908 909 910 911 912 913 914
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;

915
	return if command_oneline(qw/rev-parse --is-inside-work-tree/) eq 'false';
916 917 918 919 920 921
	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";
}

922 923 924 925 926 927
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 ",
928
			      "and a separate URL is not specified");
929
		}
930
		return ($url, $path);
931
	}
932
	return ($path, '');
933 934
}

935
sub complete_url_ls_init {
936 937
	my ($ra, $repo_path, $switch, $pfx) = @_;
	unless ($repo_path) {
938 939 940
		print STDERR "W: $switch not specified\n";
		return;
	}
941 942 943 944
	$repo_path =~ s#/+$##;
	if ($repo_path =~ m#^[a-z\+]+://#) {
		$ra = Git::SVN::Ra->new($repo_path);
		$repo_path = '';
945
	} else {
946
		$repo_path =~ s#^/+##;
947
		unless ($ra) {
948
			fatal("E: '$repo_path' is not a complete URL ",
949
			      "and a separate URL is not specified");
950
		}
951
	}
952
	my $url = $ra->{url};
953 954 955 956 957 958
	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";
959
	}
960
	command_oneline('config', $k, $gs->{url}) unless $orig_url;
961
	my $remote_path = "$ra->{svn_path}/$repo_path";
962 963
	$remote_path =~ s#/+#/#g;
	$remote_path =~ s#^/##g;
964
	$remote_path .= "/*" if $remote_path !~ /\*/;
965 966 967
	my ($n) = ($switch =~ /^--(\w+)/);
	if (length $pfx && $pfx !~ m#/$#) {
		die "--prefix='$pfx' must have a trailing slash '/'\n";
968
	}
969 970
	command_noisy('config', "svn-remote.$gs->{repo_id}.$n",
				"$remote_path:refs/remotes/$pfx*");
971 972
}

E
Eric Wong 已提交
973 974
sub verify_ref {
	my ($ref) = @_;
975 976
	eval { command_oneline([ 'rev-parse', '--verify', $ref ],
	                       { STDERR => 0 }); };
E
Eric Wong 已提交
977 978
}

979
sub get_tree_from_treeish {
980
	my ($treeish) = @_;
981
	# $treeish can be a symbolic ref, too:
E
Eric Wong 已提交
982
	my $type = command_oneline(qw/cat-file -t/, $treeish);
983 984
	my $expected;
	while ($type eq 'tag') {
E
Eric Wong 已提交
985
		($treeish, $type) = command(qw/cat-file tag/, $treeish);
986 987
	}
	if ($type eq 'commit') {
E
Eric Wong 已提交
988 989
		$expected = (grep /^tree /, command(qw/cat-file commit/,
		                                    $treeish))[0];
990
		($expected) = ($expected =~ /^tree ($sha1)$/o);
991 992 993 994 995 996
		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";
	}
997 998 999
	return $expected;
}

1000 1001 1002 1003 1004 1005
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
1006

1007
	my $type = command_oneline(qw/cat-file -t/, $treeish);
1008
	if ($type eq 'commit' || $type eq 'tag') {
E
Eric Wong 已提交
1009
		my ($msg_fh, $ctx) = command_output_pipe('cat-file',
1010
		                                         $type, $treeish);
E
Eric Wong 已提交
1011 1012 1013 1014
		my $in_msg = 0;
		while (<$msg_fh>) {
			if (!$in_msg) {
				$in_msg = 1 if (/^\s*$/);
1015
			} elsif (/^git-svn-id: /) {
1016 1017 1018
				# 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
1019
			} else {
1020
				print $log_fh $_ or croak $!;
E
Eric Wong 已提交
1021 1022
			}
		}
E
Eric Wong 已提交
1023
		command_close_pipe($msg_fh, $ctx);
E
Eric Wong 已提交
1024
	}
1025
	close $log_fh or croak $!;
E
Eric Wong 已提交
1026 1027 1028

	if ($_edit || ($type eq 'tree')) {
		my $editor = $ENV{VISUAL} || $ENV{EDITOR} || 'vi';
1029 1030
		# TODO: strip out spaces, comments, like git-commit.sh
		system($editor, $commit_editmsg);
E
Eric Wong 已提交
1031
	}
1032 1033 1034 1035 1036 1037
	rename $commit_editmsg, $commit_msg or croak $!;
	open $log_fh, '<', $commit_msg or croak $!;
	{ local $/; chomp($log_entry{log} = <$log_fh>); }
	close $log_fh or croak $!;
	unlink $commit_msg;
	\%log_entry;
1038 1039
}

E
Eric Wong 已提交
1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057
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;
}

1058 1059 1060
# '<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";
1061
	my $log = $cmd eq 'log';
1062 1063
	while (<$authors>) {
		chomp;
1064
		next unless /^(.+?|\(no author\))\s*=\s*(.+?)\s*<(.+)>\s*$/;
1065
		my ($user, $name, $email) = ($1, $2, $3);
1066 1067 1068 1069 1070
		if ($log) {
			$Git::SVN::Log::rusers{"$name <$email>"} = $user;
		} else {
			$users{$user} = [$name, $email];
		}
1071 1072 1073 1074
	}
	close $authors or croak $!;
}

1075
# convert GetOpt::Long specs for use by git-config
1076
sub read_repo_config {
1077
	return unless -d $ENV{GIT_DIR};
1078
	my $opts = shift;
1079
	my @config_only;
1080
	foreach my $o (keys %$opts) {
1081 1082 1083 1084
		# 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);
1085
		my $v = $opts->{$o};
1086
		my ($key) = ($o =~ /^([a-zA-Z\-]+)/);
1087
		$key =~ s/-//g;
1088
		my $arg = 'git-config';
1089 1090 1091 1092 1093 1094 1095
		$arg .= ' --int' if ($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.$key`);
1096
			if ($tmp && !($arg =~ / --bool/ && $tmp eq 'false')) {
1097 1098 1099 1100
				$$v = $tmp;
			}
		}
	}
1101
	delete @$opts{@config_only} if @config_only;
1102 1103
}

1104
sub extract_metadata {
1105
	my $id = shift or return (undef, undef, undef);
1106
	my ($url, $rev, $uuid) = ($id =~ /^\s*git-svn-id:\s+(.*)\@(\d+)
1107
							\s([a-f\d\-]+)$/x);
1108
	if (!defined $rev || !$uuid || !$url) {
1109
		# some of the original repositories I made had
1110
		# identifiers like this:
1111
		($rev, $uuid) = ($id =~/^\s*git-svn-id:\s(\d+)\@([a-f\d\-]+)/);
1112 1113 1114 1115
	}
	return ($url, $rev, $uuid);
}

1116 1117
sub cmt_metadata {
	return extract_metadata((grep(/^git-svn-id: /,
E
Eric Wong 已提交
1118
		command(qw/cat-file commit/, shift)))[-1]);
1119 1120
}

E
Eric Wong 已提交
1121 1122
sub working_head_info {
	my ($head, $refs) = @_;
L
Lars Hjemli 已提交
1123
	my @args = ('log', '--no-color', '--first-parent');
1124
	my ($fh, $ctx) = command_output_pipe(@args, $head);
1125
	my $hash;
1126
	my %max;
1127 1128 1129 1130 1131 1132 1133 1134
	while (<$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, $uuid) = extract_metadata($_);
1135
		if (defined $url && defined $rev) {
1136
			next if $max{$url} and $max{$url} < $rev;
1137
			if (my $gs = Git::SVN->find_by_url($url)) {
1138
				my $c = $gs->rev_map_get($rev);
1139
				if ($c && $c eq $hash) {
1140 1141
					close $fh; # break the pipe
					return ($url, $rev, $uuid, $gs);
1142
				} else {
1143
					$max{$url} ||= $gs->rev_map_max;
1144 1145 1146
				}
			}
		}
E
Eric Wong 已提交
1147
	}
1148 1149
	command_close_pipe($fh, $ctx);
	(undef, undef, undef, undef);
E
Eric Wong 已提交
1150 1151
}

1152 1153
sub read_commit_parents {
	my ($parents, $c) = @_;
1154 1155 1156
	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);
1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199
}

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);
}

1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224
sub find_file_type_and_diff_status {
	my ($path) = @_;
	return ('dir', '') if $path eq '.';

	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);
}

1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240
sub md5sum {
	my $arg = shift;
	my $ref = ref $arg;
	my $md5 = Digest::MD5->new();
        if ($ref eq 'GLOB' || $ref eq 'IO::File') {
		$md5->addfile($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();
}

1241 1242 1243
package Git::SVN;
use strict;
use warnings;
1244 1245
use Fcntl qw/:DEFAULT :seek/;
use constant rev_map_fmt => 'NH40';
E
Eric Wong 已提交
1246
use vars qw/$default_repo_id $default_ref_id $_no_metadata $_follow_parent
1247
            $_repack $_repack_flags $_use_svm_props $_head
1248 1249
            $_use_svnsync_props $no_reuse_existing $_minimize_url
	    $_use_log_author/;
1250 1251
use Carp qw/croak/;
use File::Path qw/mkpath/;
1252
use File::Copy qw/copy/;
1253 1254
use IPC::Open3;

1255 1256
my ($_gc_nr, $_gc_period);

1257 1258 1259 1260 1261 1262 1263 1264 1265
# 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/;
1266 1267 1268 1269

	# 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
1270 1271 1272 1273
	no strict 'refs';
	for my $option (qw/follow_parent no_metadata use_svm_props
			   use_svnsync_props/) {
		my $key = $option;
1274
		$key =~ tr/_//d;
1275 1276 1277 1278 1279 1280 1281 1282
		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"};
1283
			} else {
1284 1285
				my $v = command_oneline(qw/config --bool/,$k);
				$self->{$prop} = $v eq 'false' ? 0 : 1;
1286
			}
1287 1288
			return $self->{$prop};
		}
1289
	}
1290 1291
}

1292 1293 1294 1295 1296
my (%LOCKFILES, %INDEX_FILES);
END {
	unlink keys %LOCKFILES if %LOCKFILES;
	unlink keys %INDEX_FILES if %INDEX_FILES;
}
1297

1298 1299 1300 1301 1302 1303 1304 1305
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;
1306 1307
		my $pathname = desanitize_refname($path->full_path($p));
		my $refname = desanitize_refname($ref->full_path($p));
1308 1309 1310 1311 1312 1313 1314
		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];
1315
			$u =~ s!^\Q$url\E(/|$)!! or die
1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330
			  "refs/remotes/$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;
		}
	}
}

1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343
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";
}

1344
sub fetch_all {
1345
	my ($repo_id, $remotes) = @_;
E
Eric Wong 已提交
1346 1347 1348 1349 1350 1351
	if (ref $repo_id) {
		my $gs = $repo_id;
		$repo_id = undef;
		$repo_id = $gs->{repo_id};
	}
	$remotes ||= read_all_remotes();
1352 1353
	my $remote = $remotes->{$repo_id} or
	             die "[svn-remote \"$repo_id\"] unknown\n";
1354
	my $fetch = $remote->{fetch};
1355
	my $url = $remote->{url} or die "svn-remote.$repo_id.url not defined\n";
1356
	my (@gs, @globs);
1357
	my $ra = Git::SVN::Ra->new($url);
1358
	my $uuid = $ra->get_uuid;
1359
	my $head = $ra->get_latest_revnum;
E
Eric Wong 已提交
1360
	my $base = defined $fetch ? $head : 0;
1361 1362 1363 1364 1365

	# read the max revs for wildcard expansion (branches/*, tags/*)
	foreach my $t (qw/branches tags/) {
		defined $remote->{$t} or next;
		push @globs, $remote->{$t};
1366 1367 1368 1369
		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;
1370 1371
		} elsif (!defined $max_rev) {
			$base = 0;
1372 1373 1374
		}
	}

1375 1376 1377
	if ($fetch) {
		foreach my $p (sort keys %$fetch) {
			my $gs = Git::SVN->new($fetch->{$p}, $repo_id, $p);
1378
			my $lr = $gs->rev_map_max;
1379 1380 1381 1382
			if (defined $lr) {
				$base = $lr if ($lr < $base);
			}
			push @gs, $gs;
1383 1384
		}
	}
1385 1386

	($base, $head) = parse_revision_argument($base, $head);
1387
	$ra->gs_fetch_loop_common($base, $head, \@gs, \@globs);
1388 1389
}

1390 1391
sub read_all_remotes {
	my $r = {};
1392
	foreach (grep { s/^svn-remote\.// } command(qw/config -l/)) {
1393
		if (m!^(.+)\.fetch=\s*(.*)\s*:\s*refs/remotes/(.+)\s*$!) {
1394 1395 1396
			my ($remote, $local_ref, $remote_ref) = ($1, $2, $3);
			$local_ref =~ s{^/}{};
			$r->{$remote}->{fetch}->{$local_ref} = $remote_ref;
1397 1398
		} elsif (m!^(.+)\.url=\s*(.*)\s*$!) {
			$r->{$1}->{url} = $2;
1399 1400 1401 1402
		} elsif (m!^(.+)\.(branches|tags)=
		           (.*):refs/remotes/(.+)\s*$/!x) {
			my ($p, $g) = ($3, $4);
			my $rs = $r->{$1}->{$2} = {
1403
			                  t => $2,
1404
					  remote => $1,
1405 1406 1407 1408 1409 1410
			                  path => Git::SVN::GlobSpec->new($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";
			}
1411 1412 1413 1414 1415
		}
	}
	$r;
}

E
Eric Wong 已提交
1416
sub init_vars {
1417
	$_gc_nr = $_gc_period = 1000;
1418 1419 1420
	if (defined $_repack || defined $_repack_flags) {
	       warn "Repack options are obsolete; they have no effect.\n";
	}
E
Eric Wong 已提交
1421 1422
}

1423
sub verify_remotes_sanity {
1424
	return unless -d $ENV{GIT_DIR};
1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439
	my %seen;
	foreach (command(qw/config -l/)) {
		if (m!^svn-remote\.(?:.+)\.fetch=.*:refs/remotes/(\S+)\s*$!) {
			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} = $_;
		}
	}
}

1440
# we allow more chars than remotes2config.sh...
1441 1442
sub sanitize_remote_name {
	my ($name) = @_;
1443
	$name =~ tr{A-Za-z0-9:,/+-}{.}c;
1444 1445 1446
	$name;
}

1447 1448
sub find_existing_remote {
	my ($url, $remotes) = @_;
1449
	return undef if $no_reuse_existing;
1450 1451 1452 1453 1454 1455 1456 1457 1458
	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;
}
1459

1460
sub init_remote_config {
1461
	my ($self, $url, $no_write) = @_;
1462 1463 1464 1465
	$url =~ s!/+$!!; # strip trailing slash
	my $r = read_all_remotes();
	my $existing = find_existing_remote($url, $r);
	if ($existing) {
1466 1467 1468 1469
		unless ($no_write) {
			print STDERR "Using existing ",
				     "[svn-remote \"$existing\"]\n";
		}
1470
		$self->{repo_id} = $existing;
1471
	} elsif ($_minimize_url) {
1472 1473 1474
		my $min_url = Git::SVN::Ra->new($url)->minimize_url;
		$existing = find_existing_remote($min_url, $r);
		if ($existing) {
1475 1476 1477 1478
			unless ($no_write) {
				print STDERR "Using existing ",
					     "[svn-remote \"$existing\"]\n";
			}
1479 1480 1481
			$self->{repo_id} = $existing;
		}
		if ($min_url ne $url) {
1482 1483 1484 1485
			unless ($no_write) {
				print STDERR "Using higher level of URL: ",
					     "$url => $min_url\n";
			}
1486 1487
			my $old_path = $self->{path};
			$self->{path} = $url;
1488
			$self->{path} =~ s!^\Q$min_url\E(/|$)!!;
1489 1490 1491 1492 1493 1494 1495 1496
			if (length $old_path) {
				$self->{path} .= "/$old_path";
			}
			$url = $min_url;
		}
	}
	my $orig_url;
	if (!$existing) {
1497
		# verify that we aren't overwriting anything:
1498
		$orig_url = eval {
1499
			command_oneline('config', '--get',
1500
					"svn-remote.$self->{repo_id}.url")
1501
		};
1502
		if ($orig_url && ($orig_url ne $url)) {
1503
			die "svn-remote.$self->{repo_id}.url already set: ",
1504 1505
			    "$orig_url\nwanted to set to: $url\n";
		}
1506
	}
1507 1508 1509 1510 1511
	my ($xrepo_id, $xpath) = find_ref($self->refname);
	if (defined $xpath) {
		die "svn-remote.$xrepo_id.fetch already set to track ",
		    "$xpath:refs/remotes/", $self->refname, "\n";
	}
1512 1513 1514
	unless ($no_write) {
		command_noisy('config',
			      "svn-remote.$self->{repo_id}.url", $url);
1515
		$self->{path} =~ s{^/}{};
1516 1517 1518 1519
		command_noisy('config', '--add',
			      "svn-remote.$self->{repo_id}.fetch",
			      "$self->{path}:".$self->refname);
	}
1520
	$self->{url} = $url;
1521 1522
}

1523 1524
sub find_by_url { # repos_root and, path are optional
	my ($class, $full_url, $repos_root, $path) = @_;
1525

1526
	return undef unless defined $full_url;
1527 1528
	remove_username($full_url);
	remove_username($repos_root) if defined $repos_root;
1529 1530 1531 1532 1533 1534 1535
	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;
1536
		remove_username($u);
1537 1538 1539 1540 1541 1542 1543 1544
		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;
1545
		my $rwr = rewrite_root({repo_id => $repo_id});
1546 1547
		unless (defined $p) {
			$p = $full_url;
1548 1549 1550 1551 1552
			my $z = $u;
			if ($rwr) {
				$z = $rwr;
			}
			$p =~ s#^\Q$z\E(?:/|$)## or next;
1553 1554 1555 1556 1557 1558 1559 1560 1561
		}
		foreach my $f (keys %$fetch) {
			next if $f ne $p;
			return Git::SVN->new($fetch->{$f}, $repo_id, $f);
		}
	}
	undef;
}

1562
sub init {
1563
	my ($class, $url, $path, $repo_id, $ref_id, $no_write) = @_;
1564 1565
	my $self = _new($class, $repo_id, $ref_id, $path);
	if (defined $url) {
1566
		$self->init_remote_config($url, $no_write);
1567
	}
1568 1569 1570
	$self;
}

1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584
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);
}

1585
sub new {
1586 1587 1588 1589 1590 1591 1592 1593 1594 1595
	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);
1596 1597 1598 1599 1600 1601 1602 1603
	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);
	}
1604 1605 1606
	$self->{url} = command_oneline('config', '--get',
	                               "svn-remote.$repo_id.url") or
                  die "Failed to read \"svn-remote.$repo_id.url\" in config\n";
1607
	$self->rebuild;
1608 1609 1610
	$self;
}

1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644
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;
}
1645

1646 1647 1648 1649 1650 1651 1652 1653 1654
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};
}
1655

1656 1657 1658 1659
sub svm {
	my ($self) = @_;
	return $self->{svm} if $self->{svm};
	my $svm;
1660 1661
	# see if we have it in our config, first:
	eval {
1662 1663
		my $section = "svn-remote.$self->{repo_id}";
		$svm = {
1664 1665
		  source => tmp_config('--get', "$section.svm-source"),
		  uuid => tmp_config('--get', "$section.svm-uuid"),
1666
		  replace => tmp_config('--get', "$section.svm-replace"),
1667 1668
		}
	};
1669 1670 1671
	if ($svm && $svm->{source} && $svm->{uuid} && $svm->{replace}) {
		$self->{svm} = $svm;
	}
1672 1673 1674 1675 1676
	$self->{svm};
}

sub _set_svm_vars {
	my ($self, $ra) = @_;
1677 1678 1679
	return $ra if $self->svm;

	my @err = ( "useSvmProps set, but failed to read SVM properties\n",
1680
		    "(svm:source, svm:uuid) ",
1681 1682
		    "from the following URLs:\n" );
	sub read_svm_props {
1683 1684
		my ($self, $ra, $path, $r) = @_;
		my $props = ($ra->get_dir($path, $r))[2];
1685 1686
		my $src = $props->{'svm:source'};
		my $uuid = $props->{'svm:uuid'};
1687
		return undef if (!$src || !$uuid);
1688

1689
		chomp($src, $uuid);
1690

1691 1692
		$uuid =~ m{^[0-9a-f\-]{30,}$}
		    or die "doesn't look right - svm:uuid is '$uuid'\n";
1693 1694 1695

		# the '!' is used to mark the repos_root!/relative/path
		$src =~ s{/?!/?}{/};
1696
		$src =~ s{/+$}{}; # no trailing slashes please
1697
		# username is of no interest
1698 1699
		$src =~ s{(^[a-z\+]*://)[^/@]*@}{$1};

1700 1701 1702
		my $replace = $ra->{url};
		$replace .= "/$path" if length $path;

1703
		my $section = "svn-remote.$self->{repo_id}";
1704 1705 1706 1707 1708 1709 1710 1711
		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
		};
1712 1713 1714 1715
	}

	my $r = $ra->get_latest_revnum;
	my $path = $self->{path};
1716
	my %tried;
1717
	while (length $path) {
1718 1719 1720
		unless ($tried{"$self->{url}/$path"}) {
			return $ra if $self->read_svm_props($ra, $path, $r);
			$tried{"$self->{url}/$path"} = 1;
1721
		}
1722
		$path =~ s#/?[^/]+$##;
1723
	}
1724 1725 1726
	die "Path: '$path' should be ''\n" if $path ne '';
	return $ra if $self->read_svm_props($ra, $path, $r);
	$tried{"$self->{url}/$path"} = 1;
1727 1728

	if ($ra->{repos_root} eq $self->{url}) {
1729
		die @err, (map { "  $_\n" } keys %tried), "\n";
1730 1731 1732 1733 1734 1735 1736 1737
	}

	# 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 $path) {
1738 1739 1740 1741 1742 1743
		unless ($tried{"$ra->{url}/$path"}) {
			$ok = $self->read_svm_props($ra, $path, $r);
			last if $ok;
			$tried{"$ra->{url}/$path"} = 1;
		}
		$path =~ s#/?[^/]+$##;
1744
	}
1745 1746 1747
	die "Path: '$path' should be ''\n" if $path ne '';
	$ok ||= $self->read_svm_props($ra, $path, $r);
	$tried{"$ra->{url}/$path"} = 1;
1748
	if (!$ok) {
1749
		die @err, (map { "  $_\n" } keys %tried), "\n";
1750 1751
	}
	Git::SVN::Ra->new($self->{url});
1752 1753
}

1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770
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}";
1771 1772 1773 1774 1775 1776 1777 1778 1779 1780

		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 => $uuid }
1781 1782 1783 1784 1785 1786 1787 1788 1789 1790
	};
	if ($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 $err . "url\n";
1791
	($url) = ($url =~ m{^([a-z\+]+://\S+)$}) or
1792 1793 1794
	           die "doesn't look right - svn:sync-from-url is '$url'\n";

	my $uuid = $rp->{'svn:sync-from-uuid'} or die $err . "uuid\n";
1795
	($uuid) = ($uuid =~ m{^([0-9a-f\-]{30,})$}) or
1796 1797 1798 1799 1800 1801 1802 1803
	           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 };
}

1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821
# 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};
}

1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835
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;
}

1836 1837
sub ra {
	my ($self) = shift;
1838
	my $ra = Git::SVN::Ra->new($self->{url});
1839
	$self->_set_repos_root($ra->{repos_root});
1840 1841
	if ($self->use_svm_props && !$self->{svm}) {
		if ($self->no_metadata) {
1842 1843
			die "Can't have both 'noMetadata' and ",
			    "'useSvmProps' options set!\n";
1844 1845 1846
		} elsif ($self->use_svnsync_props) {
			die "Can't have both 'useSvnsyncProps' and ",
			    "'useSvmProps' options set!\n";
1847
		}
1848
		$ra = $self->_set_svm_vars($ra);
1849 1850 1851
		$self->{-want_revprops} = 1;
	}
	$ra;
1852 1853
}

1854 1855 1856 1857
sub rel_path {
	my ($self) = @_;
	my $repos_root = $self->ra->{repos_root};
	return $self->{path} if ($self->{url} eq $repos_root);
1858 1859 1860 1861
	my $url = $self->{url} .
	          (length $self->{path} ? "/$self->{path}" : $self->{path});
	$url =~ s!^\Q$repos_root\E(?:/+|$)!!g;
	$url;
1862 1863
}

1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876
# 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) = @_;

1877
	$path =~ s#^/##;
1878 1879
	my ($dirent, undef, $props) = $self->ra->get_dir($path, $rev);
	$path =~ s#^/*#/#g;
1880
	my $p = $path;
1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900
	# 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;

1901
	foreach (sort keys %$dirent) {
1902
		next if $dirent->{$_}->{kind} != $SVN::Node::dir;
1903
		$self->prop_walk($path . '/' . $_, $rev, $sub);
1904 1905 1906
	}
}

1907 1908 1909
sub last_rev { ($_[0]->last_rev_commit)[0] }
sub last_commit { ($_[0]->last_rev_commit)[1] }

1910 1911 1912 1913 1914 1915
# 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});
	}
1916
	my $c = ::verify_ref($self->refname.'^0');
1917
	if ($c && !$self->use_svm_props && !$self->no_metadata) {
1918
		my $rev = (::cmt_metadata($c))[1];
1919 1920 1921 1922 1923
		if (defined $rev) {
			($self->{last_rev}, $self->{last_commit}) = ($rev, $c);
			return ($rev, $c);
		}
	}
1924 1925
	my $map_path = $self->map_path;
	unless (-e $map_path) {
1926 1927 1928
		($self->{last_rev}, $self->{last_commit}) = (undef, undef);
		return (undef, undef);
	}
1929
	my ($rev, $commit) = $self->rev_map_max(1);
1930 1931
	($self->{last_rev}, $self->{last_commit}) = ($rev, $commit);
	return ($rev, $commit);
1932 1933
}

1934 1935 1936
sub get_fetch_range {
	my ($self, $min, $max) = @_;
	$max ||= $self->ra->get_latest_revnum;
1937
	$min ||= $self->rev_map_max;
1938
	(++$min, $max);
1939 1940
}

1941
sub tmp_config {
1942
	my (@args) = @_;
1943 1944
	my $old_def_config = "$ENV{GIT_DIR}/svn/config";
	my $config = "$ENV{GIT_DIR}/svn/.metadata";
1945
	if (! -f $config && -f $old_def_config) {
1946 1947 1948
		rename $old_def_config, $config or
		       die "Failed rename $old_def_config => $config: $!\n";
	}
1949
	my $old_config = $ENV{GIT_CONFIG};
1950
	$ENV{GIT_CONFIG} = $config;
1951
	$@ = undef;
1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965
	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);
	};
1966 1967 1968 1969 1970 1971 1972 1973 1974 1975
	my $err = $@;
	if (defined $old_config) {
		$ENV{GIT_CONFIG} = $old_config;
	} else {
		delete $ENV{GIT_CONFIG};
	}
	die $err if $err;
	wantarray ? @ret : $ret[0];
}

1976 1977 1978 1979
sub tmp_index_do {
	my ($self, $sub) = @_;
	my $old_index = $ENV{GIT_INDEX_FILE};
	$ENV{GIT_INDEX_FILE} = $self->{index};
1980
	$@ = undef;
1981 1982 1983 1984 1985
	my @ret = eval {
		my ($dir, $base) = ($self->{index} =~ m#^(.*?)/?([^/]+)$#);
		mkpath([$dir]) unless -d $dir;
		&$sub;
	};
1986 1987
	my $err = $@;
	if (defined $old_index) {
1988 1989 1990 1991
		$ENV{GIT_INDEX_FILE} = $old_index;
	} else {
		delete $ENV{GIT_INDEX_FILE};
	}
1992
	die $err if $err;
1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003
	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);
2004 2005 2006 2007 2008
		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);
2009 2010 2011
		$x = command_oneline('write-tree');
		if ($y ne $x) {
			::fatal "trees ($treeish) $y != $x\n",
2012
			        "Something is seriously wrong...";
2013 2014 2015 2016 2017
		}
	});
}

sub get_commit_parents {
2018
	my ($self, $log_entry) = @_;
2019
	my (%seen, @ret, @tmp);
2020 2021 2022 2023
	# 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;
2024 2025
		}
	}
2026
	if (my $cur = ::verify_ref($self->refname.'^0')) {
2027 2028
		push @tmp, $cur;
	}
2029 2030 2031 2032 2033
	if (my $ipd = $self->{inject_parents_dcommit}) {
		if (my $commit = delete $ipd->{$log_entry->{revision}}) {
			push @tmp, @$commit;
		}
	}
2034
	push @tmp, $_ foreach (@{$log_entry->{parents}}, @tmp);
2035 2036 2037 2038 2039 2040 2041 2042
	while (my $p = shift @tmp) {
		next if $seen{$p};
		$seen{$p} = 1;
		push @ret, $p;
		# MAXPARENT is defined to 16 in commit-tree.c:
		last if @ret >= 16;
	}
	if (@tmp) {
2043
		die "r$log_entry->{revision}: No room for parents:\n\t",
2044 2045 2046 2047 2048
		    join("\n\t", @tmp), "\n";
	}
	@ret;
}

2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068
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} : '');
}

2069
sub full_url {
2070
	my ($self) = @_;
2071
	$self->{url} . (length $self->{path} ? '/' . $self->{path} : '');
2072 2073
}

2074 2075 2076 2077 2078 2079 2080 2081

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}"};
		}
2082
	}
2083

2084 2085
	$ENV{GIT_AUTHOR_NAME} = $log_entry->{name};
	$ENV{GIT_AUTHOR_EMAIL} = $log_entry->{email};
2086
	$ENV{GIT_AUTHOR_DATE} = $ENV{GIT_COMMITTER_DATE} = $log_entry->{date};
2087

2088 2089 2090 2091 2092 2093
	$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};
2094 2095
	\%env;
}
2096

2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110
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};
			}
		}
	}
}

2111 2112 2113 2114
sub gc {
	command_noisy('gc', '--auto');
};

2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127
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);
2128
	my $tree = $log_entry->{tree};
2129 2130 2131 2132 2133 2134 2135
	if (!defined $tree) {
		$tree = $self->tmp_index_do(sub {
		                            command_oneline('write-tree') });
	}
	die "Tree is not a valid sha1: $tree\n" if $tree !~ /^$::sha1$/o;

	my @exec = ('git-commit-tree', $tree);
2136
	foreach ($self->get_commit_parents($log_entry)) {
2137 2138 2139 2140
		push @exec, '-p', $_;
	}
	defined(my $pid = open3(my $msg_fh, my $out_fh, '>&STDERR', @exec))
	                                                           or croak $!;
2141
	print $msg_fh $log_entry->{log} or croak $!;
2142
	restore_commit_header_env($old_env);
2143
	unless ($self->no_metadata) {
2144 2145
		print $msg_fh "\ngit-svn-id: $log_entry->{metadata}\n"
		              or croak $!;
2146
	}
2147 2148 2149 2150 2151 2152 2153 2154 2155 2156
	$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";
	}

2157
	$self->rev_map_set($log_entry->{revision}, $commit, 1);
2158

2159
	$self->{last_rev} = $log_entry->{revision};
2160
	$self->{last_commit} = $commit;
2161 2162 2163
	print "r$log_entry->{revision}";
	if (defined $log_entry->{svm_revision}) {
		 print " (\@$log_entry->{svm_revision})";
2164
		 $self->rev_map_set($log_entry->{svm_revision}, $commit,
2165
		                   0, $self->svm_uuid);
2166 2167
	}
	print " = $commit ($self->{ref_id})\n";
2168 2169 2170 2171
	if (--$_gc_nr == 0) {
		$_gc_nr = $_gc_period;
		gc();
	}
2172 2173 2174
	return $commit;
}

2175 2176
sub match_paths {
	my ($self, $paths, $r) = @_;
2177
	return 1 if $self->{path} eq '';
2178 2179 2180
	if (my $path = $paths->{"/$self->{path}"}) {
		return ($path->{action} eq 'D') ? 0 : 1;
	}
2181
	$self->{path_regex} ||= qr/^\/\Q$self->{path}\E\//;
2182 2183 2184 2185 2186 2187
	if (grep /$self->{path_regex}/, keys %$paths) {
		return 1;
	}
	my $c = '';
	foreach (split m#/#, $self->{path}) {
		$c .= "/$_";
2188 2189
		next unless ($paths->{$c} &&
		             ($paths->{$c}->{action} =~ /^[AR]$/));
2190 2191
		if ($self->ra->check_path($self->{path}, $r) ==
		    $SVN::Node::dir) {
2192 2193 2194 2195 2196 2197
			return 1;
		}
	}
	return 0;
}

2198 2199
sub find_parent_branch {
	my ($self, $paths, $rev) = @_;
2200
	return undef unless $self->follow_parent;
2201
	unless (defined $paths) {
2202 2203
		my $err_handler = $SVN::Error::handler;
		$SVN::Error::handler = \&Git::SVN::Ra::skip_unknown_revs;
2204 2205 2206
		$self->ra->get_log([$self->{path}], $rev, $rev, 0, 1, 1, sub {
		                   $paths =
				      Git::SVN::Ra::dup_changed_paths($_[0]) });
2207
		$SVN::Error::handler = $err_handler;
2208 2209
	}
	return undef unless defined $paths;
2210 2211

	# look for a parent from another branch:
2212 2213 2214 2215 2216
	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)};
2217
		last if $i && defined $i->{copyfrom_path};
2218 2219
		unshift(@a_path_components, pop(@b_path_components));
	}
2220 2221
	return undef unless defined $i && defined $i->{copyfrom_path};
	my $branch_from = $i->{copyfrom_path};
2222 2223 2224 2225 2226
	if (@a_path_components) {
		print STDERR "branch_from: $branch_from => ";
		$branch_from .= '/'.join('/', @a_path_components);
		print STDERR $branch_from, "\n";
	}
2227
	my $r = $i->{copyfrom_rev};
2228 2229 2230 2231 2232 2233
	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#^/##;
2234
	my $gs = Git::SVN->find_by_url($new_url, $repos_root, $branch_from);
2235
	unless ($gs) {
2236 2237 2238
		my $ref_id = $self->{ref_id};
		$ref_id =~ s/\@\d+$//;
		$ref_id .= "\@$r";
2239 2240
		# just grow a tail if we're not unique enough :x
		$ref_id .= '-' while find_ref($ref_id);
2241
		print STDERR "Initializing parent: $ref_id\n";
2242 2243 2244 2245 2246 2247
		my ($u, $p) = ($new_url, '');
		if ($u =~ s#^\Q$url\E(/|$)##) {
			$p = $u;
			$u = $url;
		}
		$gs = Git::SVN->init($u, $p, $self->{repo_id}, $ref_id, 1);
2248 2249
	}
	my ($r0, $parent) = $gs->find_rev_before($r, 1);
2250
	if (!defined $r0 || !defined $parent) {
2251 2252 2253 2254
		my ($base, $head) = parse_revision_argument(0, $r);
		if ($base <= $r) {
			$gs->fetch($base, $r);
		}
2255 2256
		($r0, $parent) = $gs->last_rev_commit;
	}
2257
	if (defined $r0 && defined $parent) {
2258 2259 2260
		print STDERR "Found branch parent: ($self->{ref_id}) $parent\n";
		my $ed;
		if ($self->ra->can_do_switch) {
2261
			$self->assert_index_clean($parent);
2262
			print STDERR "Following parent with do_switch\n";
2263
			# do_switch works with svn/trunk >= r22312, but that
2264
			# is not included with SVN 1.4.3 (the latest version
2265 2266 2267
			# at the moment), so we can't rely on it
			$self->{last_commit} = $parent;
			$ed = SVN::Git::Fetcher->new($self);
2268
			$gs->ra->gs_do_switch($r0, $rev, $gs,
2269 2270
					      $self->full_url, $ed)
			  or die "SVN connection failed somewhere...\n";
2271 2272 2273 2274 2275 2276 2277 2278 2279 2280
		} elsif ($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;
2281
		} else {
2282
			print STDERR "Following parent with do_update\n";
2283
			$ed = SVN::Git::Fetcher->new($self);
2284
			$self->ra->gs_do_update($rev, $rev, $self, $ed)
2285 2286
			  or die "SVN connection failed somewhere...\n";
		}
2287
		print STDERR "Successfully followed parent\n";
2288 2289 2290 2291 2292
		return $self->make_log_entry($rev, [$parent], $ed);
	}
	return undef;
}

2293
sub do_fetch {
2294
	my ($self, $paths, $rev) = @_;
2295
	my $ed;
2296
	my ($last_rev, @parents);
2297 2298 2299 2300 2301 2302 2303 2304 2305
	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;
		}
2306
		$ed = SVN::Git::Fetcher->new($self);
2307
		$last_rev = $self->{last_rev};
2308 2309
		$ed->{c} = $lc;
		@parents = ($lc);
2310 2311
	} else {
		$last_rev = $rev;
2312 2313 2314 2315
		if (my $log_entry = $self->find_parent_branch($paths, $rev)) {
			return $log_entry;
		}
		$ed = SVN::Git::Fetcher->new($self);
2316
	}
2317
	unless ($self->ra->gs_do_update($last_rev, $rev, $self, $ed)) {
2318 2319 2320 2321 2322
		die "SVN connection failed somewhere...\n";
	}
	$self->make_log_entry($rev, \@parents, $ed);
}

2323 2324 2325 2326
sub get_untracked {
	my ($self, $ed) = @_;
	my @out;
	my $h = $ed->{empty};
2327 2328
	foreach (sort keys %$h) {
		my $act = $h->{$_} ? '+empty_dir' : '-empty_dir';
2329
		push @out, "  $act: " . uri_encode($_);
2330 2331 2332
		warn "W: $act: $_\n";
	}
	foreach my $t (qw/dir_prop file_prop/) {
2333
		$h = $ed->{$t} or next;
2334 2335 2336
		foreach my $path (sort keys %$h) {
			my $ppath = $path eq '' ? '.' : $path;
			foreach my $prop (sort keys %{$h->{$path}}) {
2337
				next if $SKIP_PROP{$prop};
2338
				my $v = $h->{$path}->{$prop};
2339 2340 2341
				my $t_ppath_prop = "$t: " .
				                    uri_encode($ppath) . ' ' .
				                    uri_encode($prop);
2342
				if (defined $v) {
2343 2344
					push @out, "  +$t_ppath_prop " .
					           uri_encode($v);
2345
				} else {
2346
					push @out, "  -$t_ppath_prop";
2347 2348 2349 2350 2351
				}
			}
		}
	}
	foreach my $t (qw/absent_file absent_directory/) {
2352
		$h = $ed->{$t} or next;
2353 2354
		foreach my $parent (sort keys %$h) {
			foreach my $path (sort @{$h->{$parent}}) {
2355 2356
				push @out, "  $t: " .
				           uri_encode("$parent/$path");
2357 2358 2359 2360 2361
				warn "W: $t: $parent/$path ",
				     "Insufficient permissions?\n";
			}
		}
	}
2362
	\@out;
2363 2364
}

2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383
sub parse_svn_date {
	my $date = shift || return '+0000 1970-01-01 00:00:00';
	my ($Y,$m,$d,$H,$M,$S) = ($date =~ /^(\d{4})\-(\d\d)\-(\d\d)T
	                                    (\d\d)\:(\d\d)\:(\d\d).\d+Z$/x) or
	                                 croak "Unable to parse date: $date\n";
	"+0000 $Y-$m-$d $H:$M:$S";
}

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

2384
sub make_log_entry {
2385 2386 2387
	my ($self, $rev, $parents, $ed) = @_;
	my $untracked = $self->get_untracked($ed);

2388
	open my $un, '>>', "$self->{dir}/unhandled.log" or croak $!;
2389 2390 2391 2392
	print $un "r$rev\n" or croak $!;
	print $un $_, "\n" foreach @$untracked;
	my %log_entry = ( parents => $parents || [], revision => $rev,
	                  log => '');
2393

2394
	my $headrev;
2395
	my $logged = delete $self->{logged_rev_props};
2396
	if (!$logged || $self->{-want_revprops}) {
2397 2398 2399 2400 2401
		my $rp = $self->ra->rev_proplist($rev);
		foreach (sort keys %$rp) {
			my $v = $rp->{$_};
			if (/^svn:(author|date|log)$/) {
				$log_entry{$1} = $v;
2402 2403
			} elsif ($_ eq 'svm:headrev') {
				$headrev = $v;
2404 2405 2406 2407
			} else {
				print $un "  rev_prop: ", uri_encode($_), ' ',
					  uri_encode($v), "\n";
			}
2408
		}
2409 2410
	} else {
		map { $log_entry{$_} = $logged->{$_} } keys %$logged;
2411 2412
	}
	close $un or croak $!;
2413

2414 2415
	$log_entry{date} = parse_svn_date($log_entry{date});
	$log_entry{log} .= "\n";
2416 2417
	my $author = $log_entry{author} = check_author($log_entry{author});
	my ($name, $email) = defined $::users{$author} ? @{$::users{$author}}
2418 2419 2420 2421
						       : ($author, undef);

	my ($commit_name, $commit_email) = ($name, $email);
	if ($_use_log_author) {
2422 2423 2424 2425 2426 2427 2428 2429 2430
		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 $name_field) {
			#
		} elsif ($name_field =~ /(.*?)\s+<(.*)>/) {
2431
			($name, $email) = ($1, $2);
2432 2433 2434 2435
		} elsif ($name_field =~ /(.*)@/) {
			($name, $email) = ($1, $name_field);
		} else {
			($name, $email) = ($name_field, 'unknown');
2436 2437
		}
	}
2438
	if (defined $headrev && $self->use_svm_props) {
2439 2440 2441 2442
		if ($self->rewrite_root) {
			die "Can't have both 'useSvmProps' and 'rewriteRoot' ",
			    "options set!\n";
		}
2443
		my ($uuid, $r) = $headrev =~ m{^([a-f\d\-]{30,}):(\d+)$};
2444 2445 2446 2447
		# we don't want "SVM: initializing mirror for junk" ...
		return undef if $r == 0;
		my $svm = $self->svm;
		if ($uuid ne $svm->{uuid}) {
2448
			die "UUID mismatch on SVM path:\n",
2449
			    "expected: $svm->{uuid}\n",
2450 2451
			    "     got: $uuid\n";
		}
2452 2453 2454 2455
		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 $full_url\n";
2456 2457
		# throw away username for storing in records
		remove_username($full_url);
2458 2459
		$log_entry{metadata} = "$full_url\@$r $uuid";
		$log_entry{svm_revision} = $r;
2460 2461
		$email ||= "$author\@$uuid";
		$commit_email ||= "$author\@$uuid";
2462 2463 2464
	} elsif ($self->use_svnsync_props) {
		my $full_url = $self->svnsync->{url};
		$full_url .= "/$self->{path}" if length $self->{path};
2465
		remove_username($full_url);
2466 2467
		my $uuid = $self->svnsync->{uuid};
		$log_entry{metadata} = "$full_url\@$rev $uuid";
2468 2469
		$email ||= "$author\@$uuid";
		$commit_email ||= "$author\@$uuid";
2470
	} else {
2471 2472 2473
		my $url = $self->metadata_url;
		remove_username($url);
		$log_entry{metadata} = "$url\@$rev " .
2474
		                       $self->ra->get_uuid;
2475
		$email ||= "$author\@" . $self->ra->get_uuid;
2476
		$commit_email ||= "$author\@" . $self->ra->get_uuid;
2477
	}
2478 2479
	$log_entry{name} = $name;
	$log_entry{email} = $email;
2480 2481
	$log_entry{commit_name} = $commit_name;
	$log_entry{commit_email} = $commit_email;
2482 2483 2484 2485
	\%log_entry;
}

sub fetch {
2486
	my ($self, $min_rev, $max_rev, @parents) = @_;
2487
	my ($last_rev, $last_commit) = $self->last_rev_commit;
2488
	my ($base, $head) = $self->get_fetch_range($min_rev, $max_rev);
2489
	$self->ra->gs_fetch_loop_common($base, $head, [$self]);
2490 2491 2492 2493
}

sub set_tree_cb {
	my ($self, $log_entry, $tree, $rev, $date, $author) = @_;
2494 2495
	$self->{inject_parents} = { $rev => $tree };
	$self->fetch(undef, undef);
2496 2497 2498 2499
}

sub set_tree {
	my ($self, $tree) = (shift, shift);
2500
	my $log_entry = ::get_commit_entry($tree);
2501
	unless ($self->{last_rev}) {
2502
		fatal("Must have an existing revision to commit");
2503
	}
2504 2505 2506 2507 2508 2509 2510 2511 2512
	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 => $self->{path} );
	if (!SVN::Git::Editor->new(\%ed_opts)->apply_diff) {
2513 2514 2515 2516
		print "No changes\nr$self->{last_rev} = $tree\n";
	}
}

2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532
sub rebuild_from_rev_db {
	my ($self, $path) = @_;
	my $r = -1;
	open my $fh, '<', $path or croak "open: $!";
	while (<$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: $!";
}

2533 2534
sub rebuild {
	my ($self) = @_;
2535 2536
	my $map_path = $self->map_path;
	return if (-e $map_path && ! -z $map_path);
2537
	return unless ::verify_ref($self->refname.'^0');
2538 2539 2540 2541 2542 2543 2544 2545
	if ($self->use_svm_props || $self->no_metadata) {
		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;
2546 2547
		return;
	}
2548 2549 2550 2551
	print "Rebuilding $map_path ...\n";
	my ($log, $ctx) =
	    command_output_pipe(qw/rev-list --pretty=raw --no-color --reverse/,
	                        $self->refname, '--');
2552
	my $full_url = $self->full_url;
2553
	remove_username($full_url);
2554
	my $svn_uuid = $self->ra_uuid;
2555 2556 2557 2558 2559 2560 2561 2562
	my $c;
	while (<$log>) {
		if ( m{^commit ($::sha1)$} ) {
			$c = $1;
			next;
		}
		next unless s{^\s*(git-svn-id:)}{$1};
		my ($url, $rev, $uuid) = ::extract_metadata($_);
2563
		remove_username($url);
2564 2565 2566 2567 2568 2569

		# 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
2570
		if (($uuid ne $svn_uuid) ||
2571 2572 2573 2574
		    ($full_url && $url && ($url ne $full_url))) {
			next;
		}

2575
		$self->rev_map_set($rev, $c);
2576 2577
		print "r$rev = $c\n";
	}
2578
	command_close_pipe($log, $ctx);
2579 2580 2581 2582 2583 2584
	print "Done rebuilding $map_path\n";
	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;
2585 2586
}

2587
# rev_map:
2588 2589 2590
# 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
2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601
# 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
2602
#     (except the last record, which can be overwritten)
2603 2604 2605
#   - new records are written append-only since SVN revision numbers
#     increase monotonically
#   - lookups on SVN revision number are done via a binary search
2606 2607 2608 2609 2610 2611
#   - 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
2612
#
2613
# These files are disposable unless noMetadata or useSvmProps is set
2614

2615
sub _rev_map_set {
2616
	my ($fh, $rev, $commit) = @_;
2617 2618 2619 2620

	my $size = (stat($fh))[7];
	($size % 24) == 0 or croak "inconsistent size: $size";

2621
	my $wr_offset = 0;
2622 2623 2624 2625 2626
	if ($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, $buf);
2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643
		if ($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";
			}
			$wr_offset = -24;
2644 2645
		}
	}
2646
	sysseek($fh, $wr_offset, SEEK_END) or croak "seek: $!";
2647 2648
	syswrite($fh, pack(rev_map_fmt, $rev, $commit), 24) == 24 or
	  croak "write: $!";
2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660
}

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";
	}
}

2661
sub rev_map_set {
2662 2663
	my ($self, $rev, $commit, $update_ref, $uuid) = @_;
	length $commit == 40 or die "arg3 must be a full SHA1 hexsum\n";
2664
	my $db = $self->map_path($uuid);
2665
	my $db_lock = "$db.lock";
2666 2667 2668 2669 2670
	my $sig;
	if ($update_ref) {
		$SIG{INT} = $SIG{HUP} = $SIG{TERM} = $SIG{ALRM} = $SIG{PIPE} =
		            $SIG{USR1} = $SIG{USR2} = sub { $sig = $_[0] };
	}
2671 2672
	mkfile($db);

2673
	$LOCKFILES{$db_lock} = 1;
2674 2675 2676 2677 2678
	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) {
		$sync = 1;
2679
		copy($db, $db_lock) or die "rev_map_set(@_): ",
2680
					   "Failed to copy: ",
2681 2682
					   "$db => $db_lock ($!)\n";
	} else {
2683
		rename $db, $db_lock or die "rev_map_set(@_): ",
2684
					    "Failed to rename: ",
2685 2686
					    "$db => $db_lock ($!)\n";
	}
2687

2688
	sysopen(my $fh, $db_lock, O_RDWR | O_CREAT)
2689 2690
	     or croak "Couldn't open $db_lock: $!\n";
	_rev_map_set($fh, $rev, $commit);
2691 2692 2693 2694
	if ($sync) {
		$fh->flush or die "Couldn't flush $db_lock: $!\n";
		$fh->sync or die "Couldn't sync $db_lock: $!\n";
	}
2695
	close $fh or croak $!;
2696
	if ($update_ref) {
2697
		$_head = $self;
2698 2699 2700
		command_noisy('update-ref', '-m', "r$rev",
		              $self->refname, $commit);
	}
2701
	rename $db_lock, $db or die "rev_map_set(@_): ", "Failed to rename: ",
2702 2703 2704 2705 2706 2707 2708
	                            "$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;
	}
2709 2710
}

2711 2712 2713 2714
# 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).
2715
sub rev_map_max {
2716
	my ($self, $want_commit) = @_;
2717
	$self->rebuild;
2718
	my $map_path = $self->map_path;
2719
	stat $map_path or return $want_commit ? (0, undef) : 0;
2720 2721 2722 2723 2724 2725
	sysopen(my $fh, $map_path, O_RDONLY) or croak "open: $!";
	my $size = (stat($fh))[7];
	($size % 24) == 0 or croak "inconsistent size: $size";

	if ($size == 0) {
		close $fh or croak "close: $!";
2726
		return $want_commit ? (0, undef) : 0;
2727 2728
	}

2729
	sysseek($fh, -24, SEEK_END) or croak "seek: $!";
2730 2731
	sysread($fh, my $buf, 24) == 24 or croak "read: $!";
	my ($r, $c) = unpack(rev_map_fmt, $buf);
2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744
	if ($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;
2745 2746
}

2747
sub rev_map_get {
2748
	my ($self, $rev, $uuid) = @_;
2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775
	my $map_path = $self->map_path($uuid);
	return undef unless -e $map_path;

	sysopen(my $fh, $map_path, O_RDONLY) or croak "open: $!";
	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: $!";
2776
			return $c eq ('0' x 40) ? undef : $c;
2777
		}
2778
	}
2779 2780
	close($fh) or croak "close: $!";
	undef;
2781 2782
}

2783 2784 2785 2786
# 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 $min_rev.  Returns the git commit hash and svn revision number
# if found, else (undef, undef).
2787
sub find_rev_before {
2788
	my ($self, $rev, $eq_ok, $min_rev) = @_;
2789
	--$rev unless $eq_ok;
2790 2791
	$min_rev ||= 1;
	while ($rev >= $min_rev) {
2792
		if (my $c = $self->rev_map_get($rev)) {
2793 2794 2795 2796 2797 2798 2799
			return ($rev, $c);
		}
		--$rev;
	}
	return (undef, undef);
}

2800 2801 2802 2803 2804 2805 2806
# 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;
2807
	$max_rev ||= $self->rev_map_max;
2808
	while ($rev <= $max_rev) {
2809
		if (my $c = $self->rev_map_get($rev)) {
2810 2811 2812 2813 2814 2815 2816
			return ($rev, $c);
		}
		++$rev;
	}
	return (undef, undef);
}

2817
sub _new {
2818 2819 2820 2821 2822
	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) {
2823
		$_[2] = $ref_id = $Git::SVN::default_ref_id;
2824 2825 2826 2827
	}
	$_[1] = $repo_id = sanitize_remote_name($repo_id);
	my $dir = "$ENV{GIT_DIR}/svn/$ref_id";
	$_[3] = $path = '' unless (defined $path);
2828
	mkpath(["$ENV{GIT_DIR}/svn"]);
2829 2830
	bless {
		ref_id => $ref_id, dir => $dir, index => "$dir/index",
2831
	        path => $path, config => "$ENV{GIT_DIR}/svn/config",
2832
	        map_root => "$dir/.rev_map", repo_id => $repo_id }, $class;
2833 2834
}

2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854
# 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 {
2855 2856
	my ($self, $uuid) = @_;
	$uuid ||= $self->ra_uuid;
2857
	"$self->{map_root}.$uuid";
2858 2859
}

2860 2861 2862 2863 2864
sub uri_encode {
	my ($f) = @_;
	$f =~ s#([^a-zA-Z0-9\*!\:_\./\-])#uc sprintf("%%%02x",ord($1))#eg;
	$f
}
2865

2866 2867 2868 2869
sub remove_username {
	$_[0] =~ s{^([^:]*://)[^@]+@}{$1};
}

2870 2871 2872 2873 2874 2875 2876
package Git::SVN::Prompt;
use strict;
use warnings;
require SVN::Core;
use vars qw/$_no_auth_cache $_username/;

sub simple {
2877 2878 2879 2880 2881
	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) {
2882 2883
			print STDERR "Authentication realm: $realm\n";
			STDERR->flush;
2884 2885 2886
		}
		$cred->username($default_username);
	} else {
2887
		username($cred, $realm, $may_save, $pool);
2888 2889 2890 2891 2892 2893 2894
	}
	$cred->password(_read_password("Password for '" .
	                               $cred->username . "': ", $realm));
	$cred->may_save($may_save);
	$SVN::_Core::SVN_NO_ERROR;
}

2895
sub ssl_server_trust {
2896 2897
	my ($cred, $realm, $failures, $cert_info, $may_save, $pool) = @_;
	$may_save = undef if $_no_auth_cache;
2898
	print STDERR "Error validating server certificate for '$realm':\n";
2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923
	{
		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'
2924 2925
	printf STDERR
	        "Certificate information:\n".
2926 2927 2928 2929 2930
	        " - Hostname: %s\n".
	        " - Valid: from %s until %s\n".
	        " - Issuer: %s\n".
	        " - Fingerprint: %s\n",
	        map $cert_info->$_, qw(hostname valid_from valid_until
2931
	                               issuer_dname fingerprint);
2932 2933
	my $choice;
prompt:
2934
	print STDERR $may_save ?
2935 2936
	      "(R)eject, accept (t)emporarily or accept (p)ermanently? " :
	      "(R)eject or accept (t)emporarily? ";
2937
	STDERR->flush;
2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951
	$choice = lc(substr(<STDIN> || 'R', 0, 1));
	if ($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;
}

2952
sub ssl_client_cert {
2953 2954
	my ($cred, $realm, $may_save, $pool) = @_;
	$may_save = undef if $_no_auth_cache;
2955 2956
	print STDERR "Client certificate filename: ";
	STDERR->flush;
2957 2958 2959 2960 2961 2962
	chomp(my $filename = <STDIN>);
	$cred->cert_file($filename);
	$cred->may_save($may_save);
	$SVN::_Core::SVN_NO_ERROR;
}

2963
sub ssl_client_cert_pw {
2964 2965 2966 2967 2968 2969 2970
	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;
}

2971
sub username {
2972 2973 2974
	my ($cred, $realm, $may_save, $pool) = @_;
	$may_save = undef if $_no_auth_cache;
	if (defined $realm && length $realm) {
2975
		print STDERR "Authentication realm: $realm\n";
2976 2977 2978 2979 2980
	}
	my $username;
	if (defined $_username) {
		$username = $_username;
	} else {
2981 2982
		print STDERR "Username: ";
		STDERR->flush;
2983 2984 2985 2986 2987 2988 2989 2990 2991
		chomp($username = <STDIN>);
	}
	$cred->username($username);
	$cred->may_save($may_save);
	$SVN::_Core::SVN_NO_ERROR;
}

sub _read_password {
	my ($prompt, $realm) = @_;
2992 2993
	print STDERR $prompt;
	STDERR->flush;
2994 2995 2996 2997 2998 2999 3000 3001
	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');
3002 3003
	print STDERR "\n";
	STDERR->flush;
3004 3005 3006
	$password;
}

3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018
package SVN::Git::Fetcher;
use vars qw/@ISA/;
use strict;
use warnings;
use Carp qw/croak/;
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;
3019
	$self->{c} = $git_svn->{last_commit} if exists $git_svn->{last_commit};
3020 3021 3022 3023 3024
	$self->{empty} = {};
	$self->{dir_prop} = {};
	$self->{file_prop} = {};
	$self->{absent_dir} = {};
	$self->{absent_file} = {};
3025
	$self->{gii} = $git_svn->tmp_index_do(sub { Git::IndexInfo->new });
3026 3027 3028
	$self;
}

3029 3030
sub set_path_strip {
	my ($self, $path) = @_;
3031
	$self->{path_strip} = qr/^\Q$path\E(\/|$)/ if length $path;
3032 3033
}

3034 3035 3036 3037 3038 3039 3040 3041 3042
sub open_root {
	{ path => '' };
}

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

3043 3044
sub git_path {
	my ($self, $path) = @_;
3045 3046 3047 3048
	if ($self->{path_strip}) {
		$path =~ s!$self->{path_strip}!! or
		  die "Failed to strip path '$path' ($self->{path_strip})\n";
	}
3049 3050 3051
	$path;
}

3052 3053
sub delete_entry {
	my ($self, $path, $rev, $pb) = @_;
3054

3055
	my $gpath = $self->git_path($path);
3056 3057
	return undef if ($gpath eq '');

3058
	# remove entire directories.
3059
	if (command('ls-tree', $self->{c}, '--', $gpath) =~ /^040000 tree/) {
3060 3061
		my ($ls, $ctx) = command_output_pipe(qw/ls-tree
		                                     -r --name-only -z/,
3062
				                     $self->{c}, '--', $gpath);
3063 3064
		local $/ = "\0";
		while (<$ls>) {
3065 3066
			chomp;
			$self->{gii}->remove($_);
3067
			print "\tD\t$_\n" unless $::_q;
3068
		}
3069
		print "\tD\t$gpath/\n" unless $::_q;
3070 3071 3072
		command_close_pipe($ls, $ctx);
		$self->{empty}->{$path} = 0
	} else {
3073
		$self->{gii}->remove($gpath);
3074
		print "\tD\t$gpath\n" unless $::_q;
3075
	}
3076 3077 3078 3079 3080
	undef;
}

sub open_file {
	my ($self, $path, $pb, $rev) = @_;
3081 3082
	my $gpath = $self->git_path($path);
	my ($mode, $blob) = (command('ls-tree', $self->{c}, '--', $gpath)
3083
	                     =~ /^(\d{6}) blob ([a-f\d]{40})\t/);
3084 3085 3086
	unless (defined $mode && defined $blob) {
		die "$path was not found in commit $self->{c} (r$rev)\n";
	}
3087
	{ path => $path, mode_a => $mode, mode_b => $mode, blob => $blob,
3088
	  pool => SVN::Pool->new, action => 'M' };
3089 3090 3091 3092
}

sub add_file {
	my ($self, $path, $pb, $cp_path, $cp_rev) = @_;
3093 3094
	my ($dir, $file) = ($path =~ m#^(.*?)/?([^/]+)$#);
	delete $self->{empty}->{$dir};
3095
	{ path => $path, mode_a => 100644, mode_b => 100644,
3096
	  pool => SVN::Pool->new, action => 'A' };
3097 3098
}

3099 3100
sub add_directory {
	my ($self, $path, $cp_path, $cp_rev) = @_;
3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114
	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;
	}
3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141
	my ($dir, $file) = ($path =~ m#^(.*?)/?([^/]+)$#);
	delete $self->{empty}->{$dir};
	$self->{empty}->{$path} = 1;
	{ path => $path };
}

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

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

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

3142 3143 3144 3145 3146 3147 3148 3149
sub change_file_prop {
	my ($self, $fb, $prop, $value) = @_;
	if ($prop eq 'svn:executable') {
		if ($fb->{mode_b} != 120000) {
			$fb->{mode_b} = defined $value ? 100755 : 100644;
		}
	} elsif ($prop eq 'svn:special') {
		$fb->{mode_b} = defined $value ? 120000 : 100644;
3150 3151 3152
	} else {
		$self->{file_prop}->{$fb->{path}} ||= {};
		$self->{file_prop}->{$fb->{path}}->{$prop} = $value;
3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177
	}
	undef;
}

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

		if (defined $exp) {
			seek $base, 0, 0 or croak $!;
3178
			my $got = ::md5sum($base);
3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192
			die "Checksum mismatch: $fb->{path} $fb->{blob}\n",
			    "expected: $exp\n",
			    "     got: $got\n" if ($got ne $exp);
		}
	}
	seek $base, 0, 0 or croak $!;
	$fb->{fh} = $dup;
	$fb->{base} = $base;
	[ SVN::TxDelta::apply($base, $fh, undef, $fb->{path}, $fb->{pool}) ];
}

sub close_file {
	my ($self, $fb, $exp) = @_;
	my $hash;
3193
	my $path = $self->git_path($fb->{path});
3194
	if (my $fh = $fb->{fh}) {
3195 3196
		if (defined $exp) {
			seek($fh, 0, 0) or croak $!;
3197
			my $got = ::md5sum($fh);
3198 3199 3200 3201 3202
			if ($got ne $exp) {
				die "Checksum mismatch: $path\n",
				    "expected: $exp\n    got: $got\n";
			}
		}
3203
		sysseek($fh, 0, 0) or croak $!;
3204
		if ($fb->{mode_b} == 120000) {
3205 3206 3207 3208 3209 3210 3211 3212 3213
			eval {
				sysread($fh, my $buf, 5) == 5 or croak $!;
				$buf eq 'link ' or die "$path has mode 120000",
						       " but is not a link";
			};
			if ($@) {
				warn "$@\n";
				sysseek($fh, 0, 0) or croak $!;
			}
3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228
		}
		defined(my $pid = open my $out,'-|') or die "Can't fork: $!\n";
		if (!$pid) {
			open STDIN, '<&', $fh or croak $!;
			exec qw/git-hash-object -w --stdin/ or croak $!;
		}
		chomp($hash = do { local $/; <$out> });
		close $out or croak $!;
		close $fh or croak $!;
		$hash =~ /^[a-f\d]{40}$/ or die "not a sha1: $hash\n";
		close $fb->{base} or croak $!;
	} else {
		$hash = $fb->{blob} or die "no blob information\n";
	}
	$fb->{pool}->clear;
3229
	$self->{gii}->update($fb->{mode_b}, $hash, $path) or croak $!;
3230
	print "\t$fb->{action}\t$path\n" if $fb->{action} && ! $::_q;
3231 3232 3233 3234 3235
	undef;
}

sub abort_edit {
	my $self = shift;
3236 3237
	$self->{nr} = $self->{gii}->{nr};
	delete $self->{gii};
3238 3239 3240 3241 3242
	$self->SUPER::abort_edit(@_);
}

sub close_edit {
	my $self = shift;
3243
	$self->{git_commit_ok} = 1;
3244 3245
	$self->{nr} = $self->{gii}->{nr};
	delete $self->{gii};
3246 3247
	$self->SUPER::close_edit(@_);
}
3248

3249
package SVN::Git::Editor;
3250
use vars qw/@ISA $_rmdir $_cp_similarity $_find_copies_harder $_rename_limit/;
3251 3252 3253 3254 3255 3256
use strict;
use warnings;
use Carp qw/croak/;
use IO::File;

sub new {
3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270
	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);
3271
	bless $self, $class;
3272 3273
	foreach (qw/svn_path r tree_a tree_b/) {
		$self->{$_} = $opts->{$_};
3274
	}
3275 3276 3277 3278
	$self->{url} = $opts->{ra}->{url};
	$self->{mods} = $mods;
	$self->{types} = $types;
	$self->{pool} = $pool;
3279 3280
	$self->{bat} = { '' => $self->open_root($self->{r}, $self->{pool}) };
	$self->{rm} = { };
3281 3282
	$self->{path_prefix} = length $self->{svn_path} ?
	                       "$self->{svn_path}/" : '';
3283 3284 3285
	return $self;
}

3286 3287 3288
sub generate_diff {
	my ($tree_a, $tree_b) = @_;
	my @diff_tree = qw(diff-tree -z -r);
3289 3290
	if ($_cp_similarity) {
		push @diff_tree, "-C$_cp_similarity";
3291 3292 3293
	} else {
		push @diff_tree, '-C';
	}
3294 3295
	push @diff_tree, '--find-copies-harder' if $_find_copies_harder;
	push @diff_tree, "-l$_rename_limit" if defined $_rename_limit;
3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368
	push @diff_tree, $tree_a, $tree_b;
	my ($diff_fh, $ctx) = command_output_pipe(@diff_tree);
	local $/ = "\0";
	my $state = 'meta';
	my @mods;
	while (<$diff_fh>) {
		chomp $_; # this gets rid of the trailing "\0"
		if ($state eq 'meta' && /^:(\d{6})\s(\d{6})\s
					$::sha1\s($::sha1)\s
					([MTCRAD])\d*$/xo) {
			push @mods, {	mode_a => $1, mode_b => $2,
					sha1_b => $3, chg => $4 };
			if ($4 =~ /^(?:C|R)$/) {
				$state = 'file_a';
			} else {
				$state = 'file_b';
			}
		} elsif ($state eq 'file_a') {
			my $x = $mods[$#mods] or croak "Empty array\n";
			if ($x->{chg} !~ /^(?:C|R)$/) {
				croak "Error parsing $_, $x->{chg}\n";
			}
			$x->{file_a} = $_;
			$state = 'file_b';
		} elsif ($state eq 'file_b') {
			my $x = $mods[$#mods] or croak "Empty array\n";
			if (exists $x->{file_a} && $x->{chg} !~ /^(?:C|R)$/) {
				croak "Error parsing $_, $x->{chg}\n";
			}
			if (!exists $x->{file_a} && $x->{chg} =~ /^(?:C|R)$/) {
				croak "Error parsing $_, $x->{chg}\n";
			}
			$x->{file_b} = $_;
			$state = 'meta';
		} else {
			croak "Error parsing $_\n";
		}
	}
	command_close_pipe($diff_fh, $ctx);
	\@mods;
}

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

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

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

3369 3370 3371 3372 3373
sub split_path {
	return ($_[0] =~ m#^(.*?)/?([^/]+)$#);
}

sub repo_path {
3374 3375
	my ($self, $path) = @_;
	$self->{path_prefix}.(defined $path ? $path : '');
3376 3377 3378 3379
}

sub url_path {
	my ($self, $path) = @_;
3380 3381 3382
	if ($self->{url} =~ m#^https?://#) {
		$path =~ s/([^a-zA-Z0-9_.-])/uc sprintf("%%%02x",ord($1))/eg;
	}
3383
	$self->{url} . '/' . $self->repo_path($path);
3384 3385 3386
}

sub rmdirs {
3387
	my ($self) = @_;
3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404
	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;

3405 3406
	my ($fh, $ctx) = command_output_pipe(qw/ls-tree --name-only -r -z/,
	                                     $self->{tree_b});
3407 3408 3409
	local $/ = "\0";
	while (<$fh>) {
		chomp;
3410
		my @dn = split m#/#, $_;
3411 3412 3413 3414
		while (pop @dn) {
			delete $rm->{join '/', @dn};
		}
		unless (%$rm) {
3415
			close $fh;
3416 3417
			return;
		}
3418
	}
E
Eric Wong 已提交
3419
	command_close_pipe($fh, $ctx);
3420

3421 3422 3423 3424
	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) = ($d =~ m#^(.*?)/?(?:[^/]+)$#);
3425
		print "\tD+\t$d/\n" unless $::_q;
3426 3427 3428 3429 3430 3431 3432
		$self->SUPER::delete_entry($d, $r, $bat->{$dn}, $p);
		delete $bat->{$d};
	}
}

sub open_or_add_dir {
	my ($self, $full_path, $baton) = @_;
3433 3434 3435 3436
	my $t = $self->{types}->{$full_path};
	if (!defined $t) {
		die "$full_path not known in r$self->{r} or we have a bug!\n";
	}
3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451
	{
		no warnings 'once';
		# SVN::Node::none and SVN::Node::file are used only once,
		# so we're shutting up Perl's warnings about them.
		if ($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'
3452 3453 3454 3455 3456 3457
	exit 1;
}

sub ensure_path {
	my ($self, $path) = @_;
	my $bat = $self->{bat};
3458 3459 3460
	my $repo_path = $self->repo_path($path);
	return $bat->{''} unless (length $repo_path);
	my @p = split m#/+#, $repo_path;
3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471
	my $c = shift @p;
	$bat->{$c} ||= $self->open_or_add_dir($c, $bat->{''});
	while (@p) {
		my $c0 = $c;
		$c .= '/' . shift @p;
		$bat->{$c} ||= $self->open_or_add_dir($c, $bat->{$c0});
	}
	return $bat->{$c};
}

sub A {
3472
	my ($self, $m) = @_;
3473 3474 3475 3476
	my ($dir, $file) = split_path($m->{file_b});
	my $pbat = $self->ensure_path($dir);
	my $fbat = $self->add_file($self->repo_path($m->{file_b}), $pbat,
					undef, -1);
3477
	print "\tA\t$m->{file_b}\n" unless $::_q;
3478 3479 3480 3481 3482
	$self->chg_file($fbat, $m);
	$self->close_file($fbat,undef,$self->{pool});
}

sub C {
3483
	my ($self, $m) = @_;
3484 3485 3486 3487
	my ($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}), $self->{r});
3488
	print "\tC\t$m->{file_a} => $m->{file_b}\n" unless $::_q;
3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501
	$self->chg_file($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 {
3502
	my ($self, $m) = @_;
3503 3504 3505 3506
	my ($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}), $self->{r});
3507
	print "\tR\t$m->{file_a} => $m->{file_b}\n" unless $::_q;
3508 3509 3510 3511 3512 3513 3514 3515 3516
	$self->chg_file($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 {
3517
	my ($self, $m) = @_;
3518 3519 3520 3521
	my ($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},$self->{pool});
3522
	print "\t$m->{chg}\t$m->{file_b}\n" unless $::_q;
3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557
	$self->chg_file($fbat, $m);
	$self->close_file($fbat,undef,$self->{pool});
}

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

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

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

3558
	my $exp = ::md5sum($fh);
3559 3560
	seek $fh, 0, 0 or croak $!;

3561 3562 3563
	my $pool = SVN::Pool->new;
	my $atd = $self->apply_textdelta($fbat, undef, $pool);
	my $got = SVN::TxDelta::send_stream($fh, @$atd, $pool);
3564
	die "Checksum mismatch\nexpected: $exp\ngot: $got\n" if ($got ne $exp);
3565
	$pool->clear;
3566 3567 3568 3569 3570

	close $fh or croak $!;
}

sub D {
3571
	my ($self, $m) = @_;
3572 3573
	my ($dir, $file) = split_path($m->{file_b});
	my $pbat = $self->ensure_path($dir);
3574
	print "\tD\t$m->{file_b}\n" unless $::_q;
3575 3576 3577 3578 3579 3580 3581
	$self->delete_entry($m->{file_b}, $pbat);
}

sub close_edit {
	my ($self) = @_;
	my ($p,$bat) = ($self->{pool}, $self->{bat});
	foreach (sort { $b =~ tr#/#/# <=> $a =~ tr#/#/# } keys %$bat) {
3582
		next if $_ eq '';
3583 3584
		$self->close_directory($bat->{$_}, $p);
	}
3585
	$self->close_directory($bat->{''}, $p);
3586 3587 3588 3589 3590 3591 3592
	$self->SUPER::close_edit($p);
	$p->clear;
}

sub abort_edit {
	my ($self) = @_;
	$self->SUPER::abort_edit($self->{pool});
3593 3594 3595 3596 3597
}

sub DESTROY {
	my $self = shift;
	$self->SUPER::DESTROY(@_);
3598 3599 3600
	$self->{pool}->clear;
}

3601 3602
# this drives the editor
sub apply_diff {
3603 3604
	my ($self) = @_;
	my $mods = $self->{mods};
3605
	my %o = ( D => 1, R => 0, C => -1, A => 3, M => 3, T => 3 );
3606
	foreach my $m (sort { $o{$a->{chg}} <=> $o{$b->{chg}} } @$mods) {
3607 3608 3609 3610
		my $f = $m->{chg};
		if (defined $o{$f}) {
			$self->$f($m);
		} else {
3611
			fatal("Invalid change type: $f");
3612 3613
		}
	}
3614
	$self->rmdirs if $_rmdir;
3615
	if (@$mods == 0) {
3616 3617 3618 3619
		$self->abort_edit;
	} else {
		$self->close_edit;
	}
3620
	return scalar @$mods;
3621 3622
}

3623
package Git::SVN::Ra;
3624
use vars qw/@ISA $config_dir $_log_window_size/;
3625 3626
use strict;
use warnings;
3627
my ($ra_invalid, $can_do_switch, %ignored_err, $RA);
3628 3629 3630

BEGIN {
	# enforce temporary pool usage for some simple functions
3631 3632 3633 3634 3635 3636 3637 3638 3639 3640
	no strict 'refs';
	for my $f (qw/rev_proplist get_latest_revnum get_uuid get_repos_root/) {
		my $SUPER = "SUPER::$f";
		*$f = sub {
			my $self = shift;
			my $pool = SVN::Pool->new;
			my @ret = $self->$SUPER(@_,$pool);
			$pool->clear;
			wantarray ? @ret : $ret[0];
		};
3641 3642 3643
	}
}

3644 3645 3646 3647 3648 3649 3650 3651 3652
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),
3653
	  SVN::Client::get_ssl_client_cert_pw_file_provider(),
3654 3655 3656 3657 3658 3659 3660 3661 3662 3663
	  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)
	]
}

3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682
sub escape_uri_only {
	my ($uri) = @_;
	my @tmp;
	foreach (split m{/}, $uri) {
		s/([^\w.-])/sprintf("%%%02X",ord($1))/eg;
		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;
}

3683 3684
sub new {
	my ($class, $url) = @_;
3685
	$url =~ s!/+$!!;
3686
	return $RA if ($RA && $RA->{url} eq $url);
3687

3688
	SVN::_Core::svn_config_ensure($config_dir, undef);
3689
	my ($baton, $callbacks) = SVN::Core::auth_open_helper(_auth_providers);
3690
	my $config = SVN::Core::config_get_config($config_dir);
3691
	$RA = undef;
3692 3693 3694
	my $dont_store_passwords = 1;
	my $conf_t = ${$config}{'config'};
	{
3695
		no warnings 'once';
3696 3697 3698
		# The usage of $SVN::_Core::SVN_CONFIG_* variables
		# produces warnings that variables are used only once.
		# I had not found the better way to shut them up, so
3699
		# the warnings of type 'once' are disabled in this block.
3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713
		if (SVN::_Core::svn_config_get_bool($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;
		}
3714
	} # no warnings 'once'
3715
	my $self = SVN::Ra->new(url => escape_url($url), auth => $baton,
3716 3717 3718
	                      config => $config,
			      pool => SVN::Pool->new,
	                      auth_provider_callbacks => $callbacks);
3719
	$self->{url} = $url;
3720 3721
	$self->{svn_path} = $url;
	$self->{repos_root} = $self->get_repos_root;
3722
	$self->{svn_path} =~ s#^\Q$self->{repos_root}\E(/|$)##;
3723 3724
	$self->{cache} = { check_path => { r => 0, data => {} },
	                   get_dir => { r => 0, data => {} } };
3725
	$RA = bless $self, $class;
3726 3727
}

3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763
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;
}

3764
sub DESTROY {
3765
	# do not call the real DESTROY since we store ourselves in $RA
3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776
}

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

3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794
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;
}

3795
sub get_commit_editor {
3796
	my ($self, $log, $cb, $pool) = @_;
3797
	my @lock = $SVN::Core::VERSION ge '1.2.0' ? (undef, 0) : ();
3798
	$self->SUPER::get_commit_editor($log, $cb, @lock, $pool);
3799 3800 3801
}

sub gs_do_update {
3802 3803 3804 3805
	my ($self, $rev_a, $rev_b, $gs, $editor) = @_;
	my $new = ($rev_a == $rev_b);
	my $path = $gs->{path};

3806 3807 3808 3809
	if ($new && -e $gs->{index}) {
		unlink $gs->{index} or die
		  "Couldn't unlink index: $gs->{index}: $!\n";
	}
3810
	my $pool = SVN::Pool->new;
3811
	$editor->set_path_strip($path);
3812 3813
	my (@pc) = split m#/#, $path;
	my $reporter = $self->do_update($rev_b, (@pc ? shift @pc : ''),
3814
	                                1, $editor, $pool);
3815
	my @lock = $SVN::Core::VERSION ge '1.2.0' ? (undef) : ();
3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830

	# 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);

3831 3832 3833 3834 3835
	$reporter->finish_report($pool);
	$pool->clear;
	$editor->{git_commit_ok};
}

3836 3837
# 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)
3838
sub gs_do_switch {
3839 3840
	my ($self, $rev_a, $rev_b, $gs, $url_b, $editor) = @_;
	my $path = $gs->{path};
3841
	my $pool = SVN::Pool->new;
3842 3843 3844

	my $full_url = $self->{url};
	my $old_url = $full_url;
3845
	$full_url .= '/' . escape_uri_only($path) if length $path;
3846 3847 3848 3849 3850 3851 3852 3853
	my ($ra, $reparented);
	if ($old_url ne $full_url) {
		if ($old_url !~ m#^svn(\+ssh)?://#) {
			SVN::_Ra::svn_ra_reparent($self->{session}, $full_url,
			                          $pool);
			$self->{url} = $full_url;
			$reparented = 1;
		} else {
3854 3855 3856
			$_[0] = undef;
			$self = undef;
			$RA = undef;
3857
			$ra = Git::SVN::Ra->new($full_url);
3858
			$ra_invalid = 1;
3859 3860 3861
		}
	}
	$ra ||= $self;
3862
	my $reporter = $ra->do_switch($rev_b, '', 1, $url_b, $editor, $pool);
3863
	my @lock = $SVN::Core::VERSION ge '1.2.0' ? (undef) : ();
3864
	$reporter->set_path('', $rev_a, 0, @lock, $pool);
3865
	$reporter->finish_report($pool);
3866

3867 3868 3869 3870
	if ($reparented) {
		SVN::_Ra::svn_ra_reparent($self->{session}, $old_url, $pool);
		$self->{url} = $old_url;
	}
3871

3872 3873 3874 3875
	$pool->clear;
	$editor->{git_commit_ok};
}

3876 3877
sub longest_common_path {
	my ($gsv, $globs) = @_;
3878
	my %common;
3879 3880 3881
	my $common_max = scalar @$gsv;

	foreach my $gs (@$gsv) {
3882 3883 3884 3885 3886 3887 3888 3889
		my @tmp = split m#/#, $gs->{path};
		my $p = '';
		foreach (@tmp) {
			$p .= length($p) ? "/$_" : $_;
			$common{$p} ||= 0;
			$common{$p}++;
		}
	}
3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901
	$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}++;
		}
	}

3902 3903
	my $longest_path = '';
	foreach (sort {length $b <=> length $a} keys %common) {
3904
		if ($common{$_} == $common_max) {
3905 3906 3907
			$longest_path = $_;
			last;
		}
3908
	}
3909 3910 3911 3912 3913 3914 3915 3916 3917
	$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);
3918
	my $ra_url = $self->{url};
3919
	while (1) {
3920
		my %revs;
3921
		my $err;
3922
		my $err_handler = $SVN::Error::handler;
3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953
		$SVN::Error::handler = sub {
			($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;
				}
			}
		}
3954
		$SVN::Error::handler = $err_handler;
3955

3956
		my %exists = map { $_->{path} => $_ } @$gsv;
3957
		foreach my $r (sort {$a <=> $b} keys %revs) {
3958
			my ($paths, $logged) = @{$revs{$r}};
3959 3960 3961

			foreach my $gs ($self->match_globs(\%exists, $paths,
			                                   $globs, $r)) {
3962
				if ($gs->rev_map_max >= $r) {
3963 3964 3965 3966
					next;
				}
				next unless $gs->match_paths($paths, $r);
				$gs->{logged_rev_props} = $logged;
3967 3968 3969
				if (my $last_commit = $gs->last_commit) {
					$gs->assert_index_clean($last_commit);
				}
3970 3971
				my $log_entry = $gs->do_fetch($paths, $r);
				if ($log_entry) {
3972 3973
					$gs->do_git_commit($log_entry);
				}
3974
				$INDEX_FILES{$gs->{index}} = 1;
3975
			}
3976
			foreach my $g (@$globs) {
3977 3978 3979
				my $k = "svn-remote.$g->{remote}." .
				        "$g->{t}-maxRev";
				Git::SVN::tmp_config($k, $r);
3980
			}
3981 3982 3983 3984 3985 3986 3987
			if ($ra_invalid) {
				$_[0] = undef;
				$self = undef;
				$RA = undef;
				$self = Git::SVN::Ra->new($ra_url);
				$ra_invalid = undef;
			}
3988
		}
3989 3990
		# pre-fill the .rev_db since it'll eventually get filled in
		# with '0' x40 if something new gets committed
3991
		foreach my $gs (@$gsv) {
3992 3993 3994
			next if $gs->rev_map_max >= $max;
			next if defined $gs->rev_map_get($max);
			$gs->rev_map_set($max, 0 x40);
3995
		}
3996 3997 3998 3999
		foreach my $g (@$globs) {
			my $k = "svn-remote.$g->{remote}.$g->{t}-maxRev";
			Git::SVN::tmp_config($k, $max);
		}
4000 4001 4002 4003 4004
		last if $max >= $head;
		$min = $max + 1;
		$max += $inc;
		$max = $head if ($max > $head);
	}
4005
	Git::SVN::gc();
4006 4007
}

4008 4009
sub match_globs {
	my ($self, $exists, $paths, $globs, $r) = @_;
4010 4011 4012 4013 4014 4015 4016

	sub get_dir_check {
		my ($self, $exists, $g, $r) = @_;
		my @x = eval { $self->get_dir($g->{path}->{left}, $r) };
		return unless scalar @x == 3;
		my $dirents = $x[0];
		foreach my $de (keys %$dirents) {
4017
			next if $dirents->{$de}->{kind} != $SVN::Node::dir;
4018 4019 4020 4021 4022 4023 4024 4025 4026
			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);
		}
	}
4027
	foreach my $g (@$globs) {
4028 4029 4030 4031 4032
		if (my $path = $paths->{"/$g->{path}->{left}"}) {
			if ($path->{action} =~ /^[AR]$/) {
				get_dir_check($self, $exists, $g, $r);
			}
		}
4033
		foreach (keys %$paths) {
E
Eric Wong 已提交
4034 4035
			if (/$g->{path}->{left_regex}/ &&
			    !/$g->{path}->{regex}/) {
4036 4037 4038
				next if $paths->{$_}->{action} !~ /^[AR]$/;
				get_dir_check($self, $exists, $g, $r);
			}
4039 4040 4041 4042
			next unless /$g->{path}->{regex}/;
			my $p = $1;
			my $pathname = $g->{path}->full_path($p);
			next if $exists->{$pathname};
4043 4044
			next if ($self->check_path($pathname, $r) !=
			         $SVN::Node::dir);
4045 4046 4047 4048 4049 4050 4051 4052
			$exists->{$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} &&
4053 4054
			             ($paths->{$c}->{action} =~ /^[AR]$/));
			get_dir_check($self, $exists, $g, $r);
4055 4056 4057 4058 4059
		}
	}
	values %$exists;
}

4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072
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;
}

4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091
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;
}

4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104
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) {
4105 4106 4107 4108 4109 4110 4111 4112
		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";
4113 4114 4115 4116
			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";
4117 4118
			$ignored_err{$err_key} = 1;
		}
4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141
		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;
}

4142 4143 4144 4145
package Git::SVN::Log;
use strict;
use warnings;
use POSIX qw/strftime/;
4146
use constant commit_log_separator => ('-' x 72) . "\n";
4147 4148 4149 4150 4151 4152 4153
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};
4154 4155

	# big commit message got truncated by the 16k pretty buffer in rev-list
4156 4157
	if ($c->{l} && $c->{l}->[-1] eq "...\n" &&
				$c->{a_raw} =~ /\@([a-f\d\-]+)>$/) {
4158
		@{$c->{l}} = ();
4159
		my @log = command(qw/cat-file commit/, $c->{c});
4160 4161 4162

		# shift off the headers
		shift @log while ($log[0] ne '');
4163
		shift @log;
4164 4165 4166

		# TODO: make $c->{l} not have a trailing newline in the future
		@{$c->{l}} = map { "$_\n" } grep !/^git-svn-id: /, @log;
4167 4168

		(undef, $c->{r}, undef) = ::extract_metadata(
4169
				(grep(/^git-svn-id: /, @log))[-1]);
4170 4171 4172 4173 4174
	}
	return defined $c->{r};
}

sub log_use_color {
4175
	return $color || Git->repository->get_colorbool('color.diff');
4176 4177 4178
}

sub git_svn_log_cmd {
4179 4180
	my ($r_min, $r_max, @args) = @_;
	my $head = 'HEAD';
4181
	my (@files, @log_opts);
4182
	foreach my $x (@args) {
4183 4184 4185 4186 4187 4188 4189 4190 4191
		if ($x eq '--' || @files) {
			push @files, $x;
		} else {
			if (::verify_ref("$x^0")) {
				$head = $x;
			} else {
				push @log_opts, $x;
			}
		}
4192 4193
	}

4194 4195
	my ($url, $rev, $uuid, $gs) = ::working_head_info($head);
	$gs ||= Git::SVN->_new;
4196 4197 4198 4199 4200
	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();
4201 4202
	push @cmd, @log_opts;
	if (defined $r_max && $r_max == $r_min) {
4203
		push @cmd, '--max-count=1';
4204
		if (my $c = $gs->rev_map_get($r_max)) {
4205 4206
			push @cmd, $c;
		}
4207
	} elsif (defined $r_max) {
4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218
		if ($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', $c_min;
4219
		} else {
4220
			push @cmd, '--boundary', "$c_min..$c_max";
4221 4222
		}
	}
4223
	return (@cmd, @files);
4224 4225 4226 4227 4228 4229 4230 4231 4232 4233
}

# 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;
	}
4234
	$ENV{GIT_PAGER_IN_USE} = defined($pager);
4235 4236 4237
}

sub run_pager {
4238
	return unless -t *STDOUT && defined $pager;
4239
	pipe my $rfd, my $wfd or return;
4240
	defined(my $pid = fork) or ::fatal "Can't fork: $!";
4241 4242
	if (!$pid) {
		open STDOUT, '>&', $wfd or
4243
		                     ::fatal "Can't redirect to stdout: $!";
4244 4245
		return;
	}
4246
	open STDIN, '<&', $rfd or ::fatal "Can't redirect stdin: $!";
4247
	$ENV{LESS} ||= 'FRSX';
4248
	exec $pager or ::fatal "Can't run pager: $! ($pager)";
4249 4250
}

4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273
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};
	}
}

4274 4275 4276 4277 4278 4279
sub tz_to_s_offset {
	my ($tz) = @_;
	$tz =~ s/(\d\d)$//;
	return ($1 * 60) + ($tz * 3600);
}

4280 4281 4282 4283 4284
sub get_author_info {
	my ($dest, $author, $t, $tz) = @_;
	$author =~ s/(?:^\s*|\s*$)//g;
	$dest->{a_raw} = $author;
	my $au;
4285
	if ($::_authors) {
4286 4287 4288 4289 4290 4291 4292 4293
		$au = $rusers{$author} || undef;
	}
	if (!$au) {
		($au) = ($author =~ /<([^>]+)\@[^>]+>$/);
	}
	$dest->{t} = $t;
	$dest->{tz} = $tz;
	$dest->{a} = $au;
4294
	$dest->{t_utc} = parse_git_date($t, $tz);
4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345
}

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 ($c) = @_;
4346
	print commit_log_separator, "r$c->{r} | ";
4347
	print "$c->{c} | " if $show_commit;
4348
	print "$c->{a} | ", format_svn_date($c->{t_utc}), ' | ';
4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375
	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";

	}
4376
	foreach my $x (qw/raw stat diff/) {
4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387
		if ($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
4388
	set_local_timezone();
4389 4390 4391 4392 4393 4394 4395
	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 ",
4396
				"standard 'git log' arguments instead";
4397 4398 4399 4400
		}
	}

	config_pager();
4401
	@args = git_svn_log_cmd($r_min, $r_max, @args);
4402 4403 4404 4405
	if (!@args) {
		print commit_log_separator unless $incremental || $oneline;
		return;
	}
4406 4407
	my $log = command_output_pipe(@args);
	run_pager();
4408
	my (@k, $c, $d, $stat);
4409 4410
	my $esc_color = qr/(?:\033\[(?:(?:\d+;)*\d*)?m)*/;
	while (<$log>) {
4411
		if (/^${esc_color}commit -?($::sha1_short)/o) {
4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435
			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}}, $_;
4436 4437 4438 4439 4440 4441 4442
		} 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}}, $_;
			$stat = undef;
4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453
		} elsif (/^${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, $r_max, \@k);
	}
	if (@k) {
4454
		($r_min, $r_max) = ($r_max, $r_min);
4455 4456 4457
		process_commit($_, $r_min, $r_max) foreach reverse @k;
	}
out:
4458
	close $log;
4459
	print commit_log_separator unless $incremental || $oneline;
4460 4461
}

T
Tim Stoakes 已提交
4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479
sub cmd_blame {
	my $path = shift;

	config_pager();
	run_pager();

	my ($fh, $ctx) = command_output_pipe('blame', @_, $path);
	while (my $line = <$fh>) {
		if ($line =~ /^\^?([[:xdigit:]]+)\s/) {
			my (undef, $rev, undef) = ::cmt_metadata($1);
			$rev = sprintf('%-10s', $rev);
			$line =~ s/^\^?[[:xdigit:]]+(\s)/$rev$1/;
		}
		print $line;
	}
	command_close_pipe($fh, $ctx);
}

4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493
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
4494 4495 4496
# v3.1 layout (auto migrated):
#            - .rev_db => .rev_db.$UUID, .rev_db will remain as a symlink
#              for backwards compatibility
4497 4498 4499 4500 4501 4502 4503
#
# v4 layout: .git/svn/$repo_id/$id, refs/remotes/$repo_id/$id
#            - this is only created for newly multi-init-ed
#              repositories.  Similar in spirit to the
#              --use-separate-remotes option in git-clone (now default)
#            - we do not automatically migrate to this (following
#              the example set by core git)
4504 4505 4506 4507 4508 4509 4510 4511 4512 4513
#
# v5 layout: .rev_db.$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.
4514 4515 4516 4517
use strict;
use warnings;
use Carp qw/croak/;
use File::Path qw/mkpath/;
4518 4519
use File::Basename qw/dirname basename/;
use vars qw/$_minimize/;
4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628

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

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

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

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

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

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

	foreach my $ref_id (sort keys %l_map) {
4629 4630 4631 4632
		eval { Git::SVN->init($l_map{$ref_id}, '', undef, $ref_id) };
		if ($@) {
			Git::SVN->init($l_map{$ref_id}, '', $ref_id, $ref_id);
		}
4633 4634 4635 4636 4637
		$migrated++;
	}
	$migrated;
}

4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656
sub minimize_connections {
	my $r = Git::SVN::read_all_remotes();
	my $new_urls = {};
	my $root_repos = {};
	foreach my $repo_id (keys %$r) {
		my $url = $r->{$repo_id}->{url} or next;
		my $fetch = $r->{$repo_id}->{fetch} or next;
		my $ra = Git::SVN::Ra->new($url);

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

		my $root_ra = Git::SVN::Ra->new($ra->{repos_root});
		my $root_path = $ra->{url};
4657
		$root_path =~ s#^\Q$ra->{repos_root}\E(/|$)##;
4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699
		foreach my $path (keys %$fetch) {
			my $ref_id = $fetch->{$path};
			my $gs = Git::SVN->new($ref_id, $repo_id, $path);

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

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

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

			my $old_fetch = quotemeta("$x->{old_path}:".
			                          "refs/remotes/$x->{ref_id}");
4700
			command_noisy(qw/config --unset/,
4701 4702 4703 4704
			              "$pfx.fetch", '^'. $old_fetch . '$');
			delete $r->{$x->{old_repo_id}}->
			       {fetch}->{$x->{old_path}};
			if (!keys %{$r->{$x->{old_repo_id}}->{fetch}}) {
4705
				command_noisy(qw/config --unset/,
4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721
				              "$pfx.url");
				push @emptied, $x->{old_repo_id}
			}
		}
	}
	if (@emptied) {
		my $file = $ENV{GIT_CONFIG} || $ENV{GIT_CONFIG_LOCAL} ||
		           "$ENV{GIT_DIR}/config";
		print STDERR <<EOF;
The following [svn-remote] sections in your config file ($file) are empty
and can be safely removed:
EOF
		print STDERR "[svn-remote \"$_\"]\n" foreach @emptied;
	}
}

4722 4723 4724 4725
sub migration_check {
	migrate_from_v0();
	migrate_from_v1();
	migrate_from_v2();
4726
	minimize_connections() if $_minimize;
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
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});
}

4761 4762 4763 4764 4765 4766 4767 4768
package Git::SVN::GlobSpec;
use strict;
use warnings;

sub new {
	my ($class, $glob) = @_;
	my $re = $glob;
	$re =~ s!/+$!!g; # no need for trailing slashes
4769
	my $nr = ($re =~ s!^(.*)\*(.*)$!\(\[^/\]+\)!g);
4770 4771
	my ($left, $right) = ($1, $2);
	if ($nr > 1) {
4772 4773
		die "Only one '*' wildcard expansion ",
		    "is supported (got $nr): '$glob'\n";
4774
	} elsif ($nr == 0) {
4775
		die "One '*' is needed for glob: '$glob'\n";
4776 4777
	}
	$re = quotemeta($left) . $re . quotemeta($right);
4778 4779 4780 4781 4782 4783
	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";
	}
4784 4785
	my $left_re = qr/^\/\Q$left\E(\/|$)/;
	bless { left => $left, right => $right, left_regex => $left_re,
4786 4787 4788 4789 4790 4791 4792 4793 4794
	        regex => qr/$re/, glob => $glob }, $class;
}

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

E
Eric Wong 已提交
4795 4796 4797 4798
__END__

Data structures:

4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825

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

4826
$log_entry hashref as returned by libsvn_log_entry()
E
Eric Wong 已提交
4827
{
4828
	log => 'whitespace-formatted log entry
E
Eric Wong 已提交
4829 4830 4831 4832 4833 4834
',						# trailing newline is preserved
	revision => '8',			# integer
	date => '2004-02-24T17:01:44.108345Z',	# commit date
	author => 'committer name'
};

4835 4836

# this is generated by generate_diff();
E
Eric Wong 已提交
4837 4838 4839 4840 4841 4842 4843 4844
@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,
4845
	chg => change type [MCRADT],
E
Eric Wong 已提交
4846 4847 4848 4849
	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)
}
;
4850

4851 4852 4853 4854 4855 4856 4857 4858 4859 4860
# 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',
	},
}

4861 4862 4863
Notes:
	I don't trust the each() function on unless I created %hash myself
	because the internal iterator may not have started at base.