git-svn.perl 110.0 KB
Newer Older
E
Eric Wong 已提交
1
#!/usr/bin/env perl
2 3
# Copyright (C) 2006, Eric Wong <normalperson@yhbt.net>
# License: GPL v2 or later
E
Eric Wong 已提交
4 5 6
use warnings;
use strict;
use vars qw/	$AUTHOR $VERSION
7 8
		$sha1 $sha1_short $_revision
		$_q $_authors %users/;
E
Eric Wong 已提交
9
$AUTHOR = 'Eric Wong <normalperson@yhbt.net>';
E
Eric Wong 已提交
10
$VERSION = '@@GIT_VERSION@@';
11

12
my $git_dir_user_set = 1 if defined $ENV{GIT_DIR};
13
$ENV{GIT_DIR} ||= '.git';
14
$Git::SVN::default_repo_id = 'svn';
15
$Git::SVN::default_ref_id = $ENV{GIT_SVN_ID} || 'git-svn';
16
$Git::SVN::Ra::_log_window_size = 100;
17

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

22
sub fatal (@) { print STDERR @_; exit 1 }
23 24 25 26 27 28
require SVN::Core; # use()-ing this causes segfaults for me... *shrug*
require SVN::Ra;
require SVN::Delta;
if ($SVN::Core::VERSION lt '1.1.0') {
	fatal "Need SVN::Core 1.1.0 or better (got $SVN::Core::VERSION)\n";
}
29
push @Git::SVN::Ra::ISA, 'SVN::Ra';
30 31
push @SVN::Git::Editor::ISA, 'SVN::Delta::Editor';
push @SVN::Git::Fetcher::ISA, 'SVN::Delta::Editor';
E
Eric Wong 已提交
32 33 34 35
use Carp qw/croak/;
use IO::File qw//;
use File::Basename qw/dirname basename/;
use File::Path qw/mkpath/;
36
use Getopt::Long qw/:config gnu_getopt no_ignore_case auto_abbrev/;
37
use IPC::Open3;
38
use Git;
39

40 41 42 43 44
BEGIN {
	my $s;
	foreach (qw/command command_oneline command_noisy command_output_pipe
	            command_input_pipe command_close_pipe/) {
		$s .= "*SVN::Git::Editor::$_ = *SVN::Git::Fetcher::$_ = ".
45
		      "*Git::SVN::Migration::$_ = ".
46
		      "*Git::SVN::Log::$_ = *Git::SVN::$_ = *$_ = *Git::$_; ";
47 48 49 50
	}
	eval $s;
}

51
my ($SVN);
52

53 54
$sha1 = qr/[a-f\d]{40}/;
$sha1_short = qr/[a-f\d]{4,40}/;
55
my ($_stdin, $_help, $_edit,
56
	$_message, $_file,
57
	$_template, $_shared,
58
	$_version, $_fetch_all,
59
	$_merge, $_strategy, $_dry_run, $_local,
E
Eric Wong 已提交
60
	$_prefix, $_no_checkout, $_verbose);
61
$Git::SVN::_follow_parent = 1;
62 63 64
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 );
65
my %fc_opts = ( 'follow-parent|follow!' => \$Git::SVN::_follow_parent,
66
		'authors-file|A=s' => \$_authors,
E
Eric Wong 已提交
67
		'repack:i' => \$Git::SVN::_repack,
68 69
		'noMetadata' => \$Git::SVN::_no_metadata,
		'useSvmProps' => \$Git::SVN::_use_svm_props,
70
		'useSvnsyncProps' => \$Git::SVN::_use_svnsync_props,
71
		'log-window-size=i' => \$Git::SVN::Ra::_log_window_size,
72
		'no-checkout' => \$_no_checkout,
73
		'quiet|q' => \$_q,
E
Eric Wong 已提交
74 75
		'repack-flags|repack-args|repack-opts=s' =>
		   \$Git::SVN::_repack_flags,
76
		%remote_opts );
77

78
my ($_trunk, $_tags, $_branches);
79
my %icv;
80 81 82
my %init_opts = ( 'template=s' => \$_template, 'shared:s' => \$_shared,
                  'trunk|T=s' => \$_trunk, 'tags|t=s' => \$_tags,
                  'branches|b=s' => \$_branches, 'prefix=s' => \$_prefix,
83 84 85 86
		  '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] },
87
                  %remote_opts );
E
Eric Wong 已提交
88
my %cmt_opts = ( 'edit|e' => \$_edit,
89 90 91 92
		'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
93
);
94

E
Eric Wong 已提交
95
my %cmd = (
96
	fetch => [ \&cmd_fetch, "Download new revisions from SVN",
97
			{ 'revision|r=s' => \$_revision,
E
Eric Wong 已提交
98
			  'fetch-all|all' => \$_fetch_all,
99
			   %fc_opts } ],
100 101 102
	clone => [ \&cmd_clone, "Initialize and fetch revisions",
			{ 'revision|r=s' => \$_revision,
			   %fc_opts, %init_opts } ],
103
	init => [ \&cmd_init, "Initialize a repo for tracking" .
104
			  " (requires URL argument)",
105
			  \%init_opts ],
106 107 108 109
	'multi-init' => [ \&cmd_multi_init,
	                  "Deprecated alias for ".
			  "'$0 init -T<trunk> -b<branches> -t<tags>'",
			  \%init_opts ],
110 111
	dcommit => [ \&cmd_dcommit,
	             'Commit several diffs to merge with upstream',
112 113
			{ 'merge|m|M' => \$_merge,
			  'strategy|s=s' => \$_strategy,
E
Eric Wong 已提交
114
			  'verbose|v' => \$_verbose,
115
			  'dry-run|n' => \$_dry_run,
E
Eric Wong 已提交
116
			  'fetch-all|all' => \$_fetch_all,
117
			%cmt_opts, %fc_opts } ],
118 119 120
	'set-tree' => [ \&cmd_set_tree,
	                "Set an SVN repository to a git tree-ish",
			{ 'stdin|' => \$_stdin, %cmt_opts, %fc_opts, } ],
121
	'show-ignore' => [ \&cmd_show_ignore, "Show svn:ignore listings",
122
			{ 'revision|r=i' => \$_revision } ],
123
	'multi-fetch' => [ \&cmd_multi_fetch,
124 125
	                   "Deprecated alias for $0 fetch --all",
			   { 'revision|r=s' => \$_revision, %fc_opts } ],
126 127 128 129
	'migrate' => [ sub { },
	               # no-op, we automatically run this anyways,
	               'Migrate configuration/metadata/layout from
		        previous versions of git-svn',
130 131
                       { 'minimize' => \$Git::SVN::Migration::_minimize,
			 %remote_opts } ],
132 133
	'log' => [ \&Git::SVN::Log::cmd_show_log, 'Show commit logs',
			{ 'limit=i' => \$Git::SVN::Log::limit,
134
			  'revision|r=s' => \$_revision,
135 136 137 138 139
			  '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,
140
			  'authors-file|A=s' => \$_authors,
141 142
			  'color' => \$Git::SVN::Log::color,
			  'pager=s' => \$Git::SVN::Log::pager,
143
			} ],
E
Eric Wong 已提交
144 145 146 147
	'rebase' => [ \&cmd_rebase, "Fetch and rebase your working directory",
			{ 'merge|m|M' => \$_merge,
			  'verbose|v' => \$_verbose,
			  'strategy|s=s' => \$_strategy,
148
			  'local|l' => \$_local,
E
Eric Wong 已提交
149 150
			  'fetch-all|all' => \$_fetch_all,
			  %fc_opts } ],
151 152
	'commit-diff' => [ \&cmd_commit_diff,
	                   'Commit a diff between two trees',
E
Eric Wong 已提交
153 154
			{ 'message|m=s' => \$_message,
			  'file|F=s' => \$_file,
155
			  'revision|r=s' => \$_revision,
E
Eric Wong 已提交
156
			%cmt_opts } ],
E
Eric Wong 已提交
157
);
158

E
Eric Wong 已提交
159 160 161 162 163 164 165 166 167
my $cmd;
for (my $i = 0; $i < @ARGV; $i++) {
	if (defined $cmd{$ARGV[$i]}) {
		$cmd = $ARGV[$i];
		splice @ARGV, $i, 1;
		last;
	}
};

168
my %opts = %{$cmd{$cmd}->[2]} if (defined $cmd);
169

170
read_repo_config(\%opts);
171
Getopt::Long::Configure('pass_through') if ($cmd && $cmd eq 'log');
172 173 174
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,
175 176 177
                    'svn-remote|remote|R=s' => sub {
                       $Git::SVN::no_reuse_existing = 1;
                       $Git::SVN::default_repo_id = $_[1] });
178
exit 1 if (!$rv && $cmd && $cmd ne 'log');
179

E
Eric Wong 已提交
180
usage(0) if $_help;
181
version() if $_version;
182 183
usage(1) unless defined $cmd;
load_authors() if $_authors;
184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205

# make sure we're always running
unless ($cmd =~ /(?:clone|init|multi-init)$/) {
	unless (-d $ENV{GIT_DIR}) {
		if ($git_dir_user_set) {
			die "GIT_DIR=$ENV{GIT_DIR} explicitly set, ",
			    "but it is not a directory\n";
		}
		my $git_dir = delete $ENV{GIT_DIR};
		chomp(my $cdup = command_oneline(qw/rev-parse --show-cdup/));
		unless (length $cdup) {
			die "Already at toplevel, but $git_dir ",
			    "not found '$cdup'\n";
		}
		chdir $cdup or die "Unable to chdir up to '$cdup'\n";
		unless (-d $git_dir) {
			die "$git_dir still not found after going to ",
			    "'$cdup'\n";
		}
		$ENV{GIT_DIR} = $git_dir;
	}
}
206
unless ($cmd =~ /^(?:clone|init|multi-init|commit-diff)$/) {
207 208
	Git::SVN::Migration::migration_check();
}
E
Eric Wong 已提交
209
Git::SVN::init_vars();
210 211 212 213 214
eval {
	Git::SVN::verify_remotes_sanity();
	$cmd{$cmd}->[0]->(@ARGV);
};
fatal $@ if $@;
215
post_fetch_checkout();
E
Eric Wong 已提交
216 217 218 219 220 221 222 223 224
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
225 226

	print $fd "Available commands:\n" unless $cmd;
E
Eric Wong 已提交
227 228

	foreach (sort keys %cmd) {
229
		next if $cmd && $cmd ne $_;
230
		next if /^multi-/; # don't show deprecated commands
231
		print $fd '  ',pack('A17',$_),$cmd{$_}->[1],"\n";
232
		foreach (keys %{$cmd{$_}->[2]}) {
233 234
			# mixed-case options are for .git/config only
			next if /[A-Z]/ && /^[a-z]+$/i;
235
			# prints out arguments as they should be passed:
236
			my $x = s#[:=]s$## ? '<arg>' : s#[:=]i$## ? '<num>' : '';
237
			print $fd ' ' x 21, join(', ', map { length $_ > 1 ?
238 239 240
							"--$_" : "-$_" }
						split /\|/,$_)," $x\n";
		}
E
Eric Wong 已提交
241 242
	}
	print $fd <<"";
243 244 245 246
\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
247 248 249 250

	exit $exit;
}

251
sub version {
252
	print "git-svn version $VERSION (svn $SVN::Core::VERSION)\n";
253 254 255
	exit 0;
}

256 257 258 259
sub do_git_init_db {
	unless (-d $ENV{GIT_DIR}) {
		my @init_db = ('init');
		push @init_db, "--template=$_template" if defined $_template;
260 261 262 263 264 265 266
		if (defined $_shared) {
			if ($_shared =~ /[a-z]/) {
				push @init_db, "--shared=$_shared";
			} else {
				push @init_db, "--shared";
			}
		}
267 268
		command_noisy(@init_db);
	}
269 270 271 272 273 274 275 276
	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;
	}
277 278
}

279 280 281 282
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";
283
	$ENV{GIT_DIR} = '.git';
284 285
}

286 287 288 289 290 291 292 293
sub cmd_clone {
	my ($url, $path) = @_;
	if (!defined $path &&
	    (defined $_trunk || defined $_branches || defined $_tags) &&
	    $url !~ m#^[a-z\+]+://#) {
		$path = $url;
	}
	$path = basename($url) if !defined $path || !length $path;
294
	cmd_init($url, $path);
295 296 297
	Git::SVN::fetch_all($Git::SVN::default_repo_id);
}

298
sub cmd_init {
299 300
	if (defined $_trunk || defined $_branches || defined $_tags) {
		return cmd_multi_init(@_);
301
	}
302 303 304
	my $url = shift or die "SVN repository location required ",
	                       "as a command-line argument\n";
	init_subdir(@_);
305
	do_git_init_db();
306

307
	Git::SVN->init($url);
E
Eric Wong 已提交
308 309
}

310
sub cmd_fetch {
311 312 313
	if (grep /^\d+=./, @_) {
		die "'<rev>=<commit>' fetch arguments are ",
		    "no longer supported.\n";
314
	}
315 316
	my ($remote) = @_;
	if (@_ > 1) {
E
Eric Wong 已提交
317
		die "Usage: $0 fetch [--all] [svn-remote]\n";
318 319 320 321 322 323
	}
	$remote ||= $Git::SVN::default_repo_id;
	if ($_fetch_all) {
		cmd_multi_fetch();
	} else {
		Git::SVN::fetch_all($remote, Git::SVN::read_all_remotes());
324
	}
325 326
}

327
sub cmd_set_tree {
E
Eric Wong 已提交
328 329 330 331 332
	my (@commits) = @_;
	if ($_stdin || !@commits) {
		print "Reading from stdin...\n";
		@commits = ();
		while (<STDIN>) {
333
			if (/\b($sha1_short)\b/o) {
E
Eric Wong 已提交
334 335 336 337 338
				unshift @commits, $1;
			}
		}
	}
	my @revs;
339
	foreach my $c (@commits) {
E
Eric Wong 已提交
340
		my @tmp = command('rev-parse',$c);
341 342 343
		if (scalar @tmp == 1) {
			push @revs, $tmp[0];
		} elsif (scalar @tmp > 1) {
E
Eric Wong 已提交
344
			push @revs, reverse(command('rev-list',@tmp));
345
		} else {
346
			fatal "Failed to rev-parse $c\n";
347
		}
E
Eric Wong 已提交
348
	}
349 350 351
	my $gs = Git::SVN->new;
	my ($r_last, $cmt_last) = $gs->last_rev_commit;
	$gs->fetch;
352
	if (defined $gs->{last_rev} && $r_last != $gs->{last_rev}) {
353 354 355 356
		fatal "There are new revisions that were fetched ",
		      "and need to be merged (or acknowledged) ",
		      "before committing.\nlast rev: $r_last\n",
		      " current: $gs->{last_rev}\n";
357
	}
358 359
	$gs->set_tree($_) foreach @revs;
	print "Done committing ",scalar @revs," revisions to SVN\n";
360
}
361

362 363 364
sub cmd_dcommit {
	my $head = shift;
	$head ||= 'HEAD';
365
	my @refs;
366 367
	my ($url, $rev, $uuid, $gs) = working_head_info($head, \@refs);
	unless ($gs) {
368
		die "Unable to determine upstream SVN information from ",
E
Eric Wong 已提交
369
		    "$head history\n";
370
	}
371
	my $c = $refs[-1];
372
	my $last_rev;
373
	foreach my $d (@refs) {
E
Eric Wong 已提交
374
		if (!verify_ref("$d~1")) {
375 376 377 378 379
			fatal "Commit $d\n",
			      "has no parent commit, and therefore ",
			      "nothing to diff against.\n",
			      "You should be working from a repository ",
			      "originally created by git-svn\n";
380
		}
381 382 383
		unless (defined $last_rev) {
			(undef, $last_rev, undef) = cmt_metadata("$d~1");
			unless (defined $last_rev) {
384 385
				fatal "Unable to extract revision information ",
				      "from commit $d~1\n";
386 387
			}
		}
E
Eric Wong 已提交
388 389 390
		if ($_dry_run) {
			print "diff-tree $d~1 $d\n";
		} else {
391
			my %ed_opts = ( r => $last_rev,
392
			                log => get_commit_entry($d)->{log},
393
			                ra => Git::SVN::Ra->new($url),
394 395 396 397 398
			                tree_a => "$d~1",
			                tree_b => $d,
			                editor_cb => sub {
			                       print "Committed r$_[0]\n";
			                       $last_rev = $_[0]; },
399
			                svn_path => '');
400
			if (!SVN::Git::Editor->new(\%ed_opts)->apply_diff) {
401 402
				print "No changes\n$d~1 == $d\n";
			}
E
Eric Wong 已提交
403 404 405
		}
	}
	return if $_dry_run;
406 407 408 409 410 411 412
	unless ($gs) {
		warn "Could not determine fetch information for $url\n",
		     "Will not attempt to fetch and rebase commits.\n",
		     "This probably means you have useSvmProps and should\n",
		     "now resync your SVN::Mirror repository.\n";
		return;
	}
E
Eric Wong 已提交
413
	$_fetch_all ? $gs->fetch_all : $gs->fetch;
414 415 416
	# we always want to rebase against the current HEAD, not any
	# head that was passed to us
	my @diff = command('diff-tree', 'HEAD', $gs->refname, '--');
E
Eric Wong 已提交
417 418
	my @finish;
	if (@diff) {
E
Eric Wong 已提交
419
		@finish = rebase_cmd();
420 421
		print STDERR "W: HEAD and ", $gs->refname, " differ, ",
		             "using @finish:\n", "@diff";
E
Eric Wong 已提交
422
	} else {
423 424 425
		print "No changes between current HEAD and ",
		      $gs->refname, "\nResetting to the latest ",
		      $gs->refname, "\n";
426
		@finish = qw/reset --mixed/;
E
Eric Wong 已提交
427
	}
428
	command_noisy(@finish, $gs->refname);
E
Eric Wong 已提交
429 430
}

E
Eric Wong 已提交
431 432
sub cmd_rebase {
	command_noisy(qw/update-index --refresh/);
433 434
	my ($url, $rev, $uuid, $gs) = working_head_info('HEAD');
	unless ($gs) {
E
Eric Wong 已提交
435 436 437 438 439 440 441 442
		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;
	}
443 444 445
	unless ($_local) {
		$_fetch_all ? $gs->fetch_all : $gs->fetch;
	}
E
Eric Wong 已提交
446 447 448
	command_noisy(rebase_cmd(), $gs->refname);
}

449
sub cmd_show_ignore {
450 451
	my ($url, $rev, $uuid, $gs) = working_head_info('HEAD');
	$gs ||= Git::SVN->new;
452
	my $r = (defined $_revision ? $_revision : $gs->ra->get_latest_revnum);
453
	$gs->traverse_ignore(\*STDOUT, $gs->{path}, $r);
454 455
}

456
sub cmd_multi_init {
457
	my $url = shift;
458 459
	unless (defined $_trunk || defined $_branches || defined $_tags) {
		usage(1);
460
	}
461
	$_prefix = '' unless defined $_prefix;
462 463 464 465
	if (defined $url) {
		$url =~ s#/+$##;
		init_subdir(@_);
	}
466
	do_git_init_db();
467
	if (defined $_trunk) {
468 469 470
		my $trunk_ref = $_prefix . 'trunk';
		# try both old-style and new-style lookups:
		my $gs_trunk = eval { Git::SVN->new($trunk_ref) };
471
		unless ($gs_trunk) {
472 473 474 475
			my ($trunk_url, $trunk_path) =
			                      complete_svn_url($url, $_trunk);
			$gs_trunk = Git::SVN->init($trunk_url, $trunk_path,
						   undef, $trunk_ref);
476
		}
477
	}
478
	return unless defined $_branches || defined $_tags;
479 480 481
	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/');
482 483
}

484
sub cmd_multi_fetch {
485 486
	my $remotes = Git::SVN::read_all_remotes();
	foreach my $repo_id (sort keys %$remotes) {
487
		if ($remotes->{$repo_id}->{url}) {
488 489
			Git::SVN::fetch_all($repo_id, $remotes);
		}
490 491 492
	}
}

493 494 495 496 497 498
# this command is special because it requires no metadata
sub cmd_commit_diff {
	my ($ta, $tb, $url) = @_;
	my $usage = "Usage: $0 commit-diff -r<revision> ".
	            "<tree-ish> <tree-ish> [<URL>]\n";
	fatal($usage) if (!defined $ta || !defined $tb);
499
	my $svn_path;
500 501 502 503 504 505 506
	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};
507
		$svn_path = $gs->{path};
508 509 510 511 512 513 514 515 516 517 518 519 520 521 522
	}
	unless (defined $_revision) {
		fatal("-r|--revision is a required argument\n", $usage);
	}
	if (defined $_message && defined $_file) {
		fatal("Both --message/-m and --file/-F specified ",
		      "for the commit message.\n",
		      "I have no idea what you mean\n");
	}
	if (defined $_file) {
		$_message = file_to_s($_file);
	} else {
		$_message ||= get_commit_entry($tb)->{log};
	}
	my $ra ||= Git::SVN::Ra->new($url);
523
	$svn_path ||= $ra->{svn_path};
524 525 526 527 528 529
	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";
	}
530 531 532 533 534 535 536 537
	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 => $svn_path );
	if (!SVN::Git::Editor->new(\%ed_opts)->apply_diff) {
538 539 540 541
		print "No changes\n$ta == $tb\n";
	}
}

E
Eric Wong 已提交
542 543
########################### utility functions #########################

E
Eric Wong 已提交
544 545 546 547 548 549 550 551
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;
}

552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572
sub post_fetch_checkout {
	return if $_no_checkout;
	my $gs = $Git::SVN::_head or return;
	return if verify_ref('refs/heads/master^0');

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

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

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

573 574 575 576 577 578 579 580
sub complete_svn_url {
	my ($url, $path) = @_;
	$path =~ s#/+$##;
	if ($path !~ m#^[a-z\+]+://#) {
		if (!defined $url || $url !~ m#^[a-z\+]+://#) {
			fatal("E: '$path' is not a complete URL ",
			      "and a separate URL is not specified\n");
		}
581
		return ($url, $path);
582
	}
583
	return ($path, '');
584 585
}

586
sub complete_url_ls_init {
587 588
	my ($ra, $repo_path, $switch, $pfx) = @_;
	unless ($repo_path) {
589 590 591
		print STDERR "W: $switch not specified\n";
		return;
	}
592 593 594 595
	$repo_path =~ s#/+$##;
	if ($repo_path =~ m#^[a-z\+]+://#) {
		$ra = Git::SVN::Ra->new($repo_path);
		$repo_path = '';
596
	} else {
597
		$repo_path =~ s#^/+##;
598
		unless ($ra) {
599
			fatal("E: '$repo_path' is not a complete URL ",
600
			      "and a separate URL is not specified\n");
601
		}
602
	}
603
	my $url = $ra->{url};
604 605 606 607 608 609
	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";
610
	}
611 612 613 614 615 616 617
	command_oneline('config', $k, $gs->{url}) unless $orig_url;
	my $remote_path = "$ra->{svn_path}/$repo_path/*";
	$remote_path =~ s#/+#/#g;
	$remote_path =~ s#^/##g;
	my ($n) = ($switch =~ /^--(\w+)/);
	if (length $pfx && $pfx !~ m#/$#) {
		die "--prefix='$pfx' must have a trailing slash '/'\n";
618
	}
619 620
	command_noisy('config', "svn-remote.$gs->{repo_id}.$n",
				"$remote_path:refs/remotes/$pfx*");
621 622
}

E
Eric Wong 已提交
623 624
sub verify_ref {
	my ($ref) = @_;
625 626
	eval { command_oneline([ 'rev-parse', '--verify', $ref ],
	                       { STDERR => 0 }); };
E
Eric Wong 已提交
627 628
}

629
sub get_tree_from_treeish {
630
	my ($treeish) = @_;
631
	# $treeish can be a symbolic ref, too:
E
Eric Wong 已提交
632
	my $type = command_oneline(qw/cat-file -t/, $treeish);
633 634
	my $expected;
	while ($type eq 'tag') {
E
Eric Wong 已提交
635
		($treeish, $type) = command(qw/cat-file tag/, $treeish);
636 637
	}
	if ($type eq 'commit') {
E
Eric Wong 已提交
638 639
		$expected = (grep /^tree /, command(qw/cat-file commit/,
		                                    $treeish))[0];
640
		($expected) = ($expected =~ /^tree ($sha1)$/o);
641 642 643 644 645 646
		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";
	}
647 648 649
	return $expected;
}

650 651 652 653 654 655
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
656

657
	my $type = command_oneline(qw/cat-file -t/, $treeish);
658
	if ($type eq 'commit' || $type eq 'tag') {
E
Eric Wong 已提交
659
		my ($msg_fh, $ctx) = command_output_pipe('cat-file',
660
		                                         $type, $treeish);
E
Eric Wong 已提交
661 662 663 664
		my $in_msg = 0;
		while (<$msg_fh>) {
			if (!$in_msg) {
				$in_msg = 1 if (/^\s*$/);
665
			} elsif (/^git-svn-id: /) {
666 667 668
				# 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
669
			} else {
670
				print $log_fh $_ or croak $!;
E
Eric Wong 已提交
671 672
			}
		}
E
Eric Wong 已提交
673
		command_close_pipe($msg_fh, $ctx);
E
Eric Wong 已提交
674
	}
675
	close $log_fh or croak $!;
E
Eric Wong 已提交
676 677 678

	if ($_edit || ($type eq 'tree')) {
		my $editor = $ENV{VISUAL} || $ENV{EDITOR} || 'vi';
679 680
		# TODO: strip out spaces, comments, like git-commit.sh
		system($editor, $commit_editmsg);
E
Eric Wong 已提交
681
	}
682 683 684 685 686 687
	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;
688 689
}

E
Eric Wong 已提交
690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707
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;
}

708 709 710
# '<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";
711
	my $log = $cmd eq 'log';
712 713
	while (<$authors>) {
		chomp;
714
		next unless /^(\S+?|\(no author\))\s*=\s*(.+?)\s*<(.+)>\s*$/;
715
		my ($user, $name, $email) = ($1, $2, $3);
716 717 718 719 720
		if ($log) {
			$Git::SVN::Log::rusers{"$name <$email>"} = $user;
		} else {
			$users{$user} = [$name, $email];
		}
721 722 723 724
	}
	close $authors or croak $!;
}

725
# convert GetOpt::Long specs for use by git-config
726
sub read_repo_config {
727
	return unless -d $ENV{GIT_DIR};
728
	my $opts = shift;
729
	my @config_only;
730
	foreach my $o (keys %$opts) {
731 732 733 734
		# 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);
735
		my $v = $opts->{$o};
736
		my ($key) = ($o =~ /^([a-zA-Z\-]+)/);
737
		$key =~ s/-//g;
738
		my $arg = 'git-config';
739 740 741 742 743 744 745
		$arg .= ' --int' if ($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.$key`);
746
			if ($tmp && !($arg =~ / --bool/ && $tmp eq 'false')) {
747 748 749 750
				$$v = $tmp;
			}
		}
	}
751
	delete @$opts{@config_only} if @config_only;
752 753
}

754
sub extract_metadata {
755
	my $id = shift or return (undef, undef, undef);
756 757
	my ($url, $rev, $uuid) = ($id =~ /^git-svn-id:\s(\S+?)\@(\d+)
							\s([a-f\d\-]+)$/x);
758
	if (!defined $rev || !$uuid || !$url) {
759
		# some of the original repositories I made had
760
		# identifiers like this:
761 762 763 764 765
		($rev, $uuid) = ($id =~/^git-svn-id:\s(\d+)\@([a-f\d\-]+)/);
	}
	return ($url, $rev, $uuid);
}

766 767
sub cmt_metadata {
	return extract_metadata((grep(/^git-svn-id: /,
E
Eric Wong 已提交
768
		command(qw/cat-file commit/, shift)))[-1]);
769 770
}

E
Eric Wong 已提交
771 772 773 774 775
sub working_head_info {
	my ($head, $refs) = @_;
	my ($fh, $ctx) = command_output_pipe('rev-list', $head);
	while (<$fh>) {
		chomp;
776 777 778 779 780 781 782 783 784 785
		my ($url, $rev, $uuid) = cmt_metadata($_);
		if (defined $url && defined $rev) {
			if (my $gs = Git::SVN->find_by_url($url)) {
				my $c = $gs->rev_db_get($rev);
				if ($c && $c eq $_) {
					close $fh; # break the pipe
					return ($url, $rev, $uuid, $gs);
				}
			}
		}
E
Eric Wong 已提交
786 787
		unshift @$refs, $_ if $refs;
	}
788 789
	command_close_pipe($fh, $ctx);
	(undef, undef, undef, undef);
E
Eric Wong 已提交
790 791
}

792 793 794
package Git::SVN;
use strict;
use warnings;
E
Eric Wong 已提交
795
use vars qw/$default_repo_id $default_ref_id $_no_metadata $_follow_parent
796
            $_repack $_repack_flags $_use_svm_props $_head
797
            $_use_svnsync_props $no_reuse_existing/;
798 799
use Carp qw/croak/;
use File::Path qw/mkpath/;
800
use File::Copy qw/copy/;
801 802
use IPC::Open3;

E
Eric Wong 已提交
803
my $_repack_nr;
804 805 806 807 808 809 810 811 812
# 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/;
813 814 815 816 817

	# some options are read globally, but can be overridden locally
	# per [svn-remote "..."] section.  Command-line options will *NOT*
	# override options set in an [svn-remote "..."] section
	my $e;
818 819
	foreach (qw/follow_parent no_metadata use_svm_props
	            use_svnsync_props/) {
820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836
		my $key = $_;
		$key =~ tr/_//d;
		$e .= "sub $_ {
			my (\$self) = \@_;
			return \$self->{-$_} if exists \$self->{-$_};
			my \$k = \"svn-remote.\$self->{repo_id}\.$key\";
			eval { command_oneline(qw/config --get/, \$k) };
			if (\$@) {
				\$self->{-$_} = \$Git::SVN::_$_;
			} else {
				my \$v = command_oneline(qw/config --bool/,\$k);
				\$self->{-$_} = \$v eq 'false' ? 0 : 1;
			}
			return \$self->{-$_} }\n";
	}
	$e .= "1;\n";
	eval $e or die $@;
837 838
}

839 840 841
my %LOCKFILES;
END { unlink keys %LOCKFILES if %LOCKFILES }

842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858
sub resolve_local_globs {
	my ($url, $fetch, $glob_spec) = @_;
	return unless defined $glob_spec;
	my $ref = $glob_spec->{ref};
	my $path = $glob_spec->{path};
	foreach (command(qw#for-each-ref --format=%(refname) refs/remotes#)) {
		next unless m#^refs/remotes/$ref->{regex}$#;
		my $p = $1;
		my $pathname = $path->full_path($p);
		my $refname = $ref->full_path($p);
		if (my $existing = $fetch->{$pathname}) {
			if ($existing ne $refname) {
				die "Refspec conflict:\n",
				    "existing: refs/remotes/$existing\n",
				    " globbed: refs/remotes/$refname\n";
			}
			my $u = (::cmt_metadata("refs/remotes/$refname"))[0];
859
			$u =~ s!^\Q$url\E(/|$)!! or die
860 861 862 863 864 865 866 867 868 869 870 871 872 873 874
			  "refs/remotes/$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;
		}
	}
}

875 876 877 878 879 880 881 882 883 884 885 886 887
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";
}

888
sub fetch_all {
889
	my ($repo_id, $remotes) = @_;
E
Eric Wong 已提交
890 891 892 893 894 895
	if (ref $repo_id) {
		my $gs = $repo_id;
		$repo_id = undef;
		$repo_id = $gs->{repo_id};
	}
	$remotes ||= read_all_remotes();
896 897
	my $remote = $remotes->{$repo_id} or
	             die "[svn-remote \"$repo_id\"] unknown\n";
898
	my $fetch = $remote->{fetch};
899
	my $url = $remote->{url} or die "svn-remote.$repo_id.url not defined\n";
900
	my (@gs, @globs);
901
	my $ra = Git::SVN::Ra->new($url);
902
	my $uuid = $ra->get_uuid;
903
	my $head = $ra->get_latest_revnum;
E
Eric Wong 已提交
904
	my $base = defined $fetch ? $head : 0;
905 906 907 908 909

	# read the max revs for wildcard expansion (branches/*, tags/*)
	foreach my $t (qw/branches tags/) {
		defined $remote->{$t} or next;
		push @globs, $remote->{$t};
910 911 912 913
		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;
914 915
		} elsif (!defined $max_rev) {
			$base = 0;
916 917 918
		}
	}

919 920 921 922 923 924 925 926
	if ($fetch) {
		foreach my $p (sort keys %$fetch) {
			my $gs = Git::SVN->new($fetch->{$p}, $repo_id, $p);
			my $lr = $gs->rev_db_max;
			if (defined $lr) {
				$base = $lr if ($lr < $base);
			}
			push @gs, $gs;
927 928
		}
	}
929 930

	($base, $head) = parse_revision_argument($base, $head);
931
	$ra->gs_fetch_loop_common($base, $head, \@gs, \@globs);
932 933
}

934 935
sub read_all_remotes {
	my $r = {};
936
	foreach (grep { s/^svn-remote\.// } command(qw/config -l/)) {
937 938 939 940
		if (m!^(.+)\.fetch=\s*(.*)\s*:\s*refs/remotes/(.+)\s*$!) {
			$r->{$1}->{fetch}->{$2} = $3;
		} elsif (m!^(.+)\.url=\s*(.*)\s*$!) {
			$r->{$1}->{url} = $2;
941 942 943 944
		} elsif (m!^(.+)\.(branches|tags)=
		           (.*):refs/remotes/(.+)\s*$/!x) {
			my ($p, $g) = ($3, $4);
			my $rs = $r->{$1}->{$2} = {
945
			                  t => $2,
946
					  remote => $1,
947 948 949 950 951 952
			                  path => Git::SVN::GlobSpec->new($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";
			}
953 954 955 956 957
		}
	}
	$r;
}

E
Eric Wong 已提交
958 959 960 961 962 963 964 965
sub init_vars {
	if (defined $_repack) {
		$_repack = 1000 if ($_repack <= 0);
		$_repack_nr = $_repack;
		$_repack_flags ||= '-d';
	}
}

966
sub verify_remotes_sanity {
967
	return unless -d $ENV{GIT_DIR};
968 969 970 971 972 973 974 975 976 977 978 979 980 981 982
	my %seen;
	foreach (command(qw/config -l/)) {
		if (m!^svn-remote\.(?:.+)\.fetch=.*:refs/remotes/(\S+)\s*$!) {
			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} = $_;
		}
	}
}

983
# we allow more chars than remotes2config.sh...
984 985
sub sanitize_remote_name {
	my ($name) = @_;
986
	$name =~ tr{A-Za-z0-9:,/+-}{.}c;
987 988 989
	$name;
}

990 991
sub find_existing_remote {
	my ($url, $remotes) = @_;
992
	return undef if $no_reuse_existing;
993 994 995 996 997 998 999 1000 1001
	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;
}
1002

1003
sub init_remote_config {
1004
	my ($self, $url, $no_write) = @_;
1005 1006 1007 1008
	$url =~ s!/+$!!; # strip trailing slash
	my $r = read_all_remotes();
	my $existing = find_existing_remote($url, $r);
	if ($existing) {
1009 1010 1011 1012
		unless ($no_write) {
			print STDERR "Using existing ",
				     "[svn-remote \"$existing\"]\n";
		}
1013 1014 1015 1016 1017
		$self->{repo_id} = $existing;
	} else {
		my $min_url = Git::SVN::Ra->new($url)->minimize_url;
		$existing = find_existing_remote($min_url, $r);
		if ($existing) {
1018 1019 1020 1021
			unless ($no_write) {
				print STDERR "Using existing ",
					     "[svn-remote \"$existing\"]\n";
			}
1022 1023 1024
			$self->{repo_id} = $existing;
		}
		if ($min_url ne $url) {
1025 1026 1027 1028
			unless ($no_write) {
				print STDERR "Using higher level of URL: ",
					     "$url => $min_url\n";
			}
1029 1030
			my $old_path = $self->{path};
			$self->{path} = $url;
1031
			$self->{path} =~ s!^\Q$min_url\E(/|$)!!;
1032 1033 1034 1035 1036 1037 1038 1039
			if (length $old_path) {
				$self->{path} .= "/$old_path";
			}
			$url = $min_url;
		}
	}
	my $orig_url;
	if (!$existing) {
1040
		# verify that we aren't overwriting anything:
1041
		$orig_url = eval {
1042
			command_oneline('config', '--get',
1043
					"svn-remote.$self->{repo_id}.url")
1044
		};
1045
		if ($orig_url && ($orig_url ne $url)) {
1046
			die "svn-remote.$self->{repo_id}.url already set: ",
1047 1048
			    "$orig_url\nwanted to set to: $url\n";
		}
1049
	}
1050 1051 1052 1053 1054
	my ($xrepo_id, $xpath) = find_ref($self->refname);
	if (defined $xpath) {
		die "svn-remote.$xrepo_id.fetch already set to track ",
		    "$xpath:refs/remotes/", $self->refname, "\n";
	}
1055 1056 1057 1058 1059 1060 1061
	unless ($no_write) {
		command_noisy('config',
			      "svn-remote.$self->{repo_id}.url", $url);
		command_noisy('config', '--add',
			      "svn-remote.$self->{repo_id}.fetch",
			      "$self->{path}:".$self->refname);
	}
1062
	$self->{url} = $url;
1063 1064
}

1065 1066
sub find_by_url { # repos_root and, path are optional
	my ($class, $full_url, $repos_root, $path) = @_;
1067
	return undef unless defined $full_url;
1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094
	my $remotes = read_all_remotes();
	if (defined $full_url && defined $repos_root && !defined $path) {
		$path = $full_url;
		$path =~ s#^\Q$repos_root\E(?:/|$)##;
	}
	foreach my $repo_id (keys %$remotes) {
		my $u = $remotes->{$repo_id}->{url} or next;
		next if defined $repos_root && $repos_root ne $u;

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

1095
sub init {
1096
	my ($class, $url, $path, $repo_id, $ref_id, $no_write) = @_;
1097 1098
	my $self = _new($class, $repo_id, $ref_id, $path);
	if (defined $url) {
1099
		$self->init_remote_config($url, $no_write);
1100
	}
1101 1102 1103
	$self;
}

1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117
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);
}

1118
sub new {
1119 1120 1121 1122 1123 1124 1125 1126 1127 1128
	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);
1129 1130 1131 1132 1133 1134 1135 1136
	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);
	}
1137 1138 1139
	$self->{url} = command_oneline('config', '--get',
	                               "svn-remote.$repo_id.url") or
                  die "Failed to read \"svn-remote.$repo_id.url\" in config\n";
1140
	$self->rebuild;
1141 1142 1143
	$self;
}

1144
sub refname { "refs/remotes/$_[0]->{ref_id}" }
1145

1146 1147 1148 1149 1150 1151 1152 1153 1154
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};
}
1155

1156 1157 1158 1159
sub svm {
	my ($self) = @_;
	return $self->{svm} if $self->{svm};
	my $svm;
1160 1161
	# see if we have it in our config, first:
	eval {
1162 1163
		my $section = "svn-remote.$self->{repo_id}";
		$svm = {
1164 1165
		  source => tmp_config('--get', "$section.svm-source"),
		  uuid => tmp_config('--get', "$section.svm-uuid"),
1166
		  replace => tmp_config('--get', "$section.svm-replace"),
1167 1168
		}
	};
1169 1170 1171
	if ($svm && $svm->{source} && $svm->{uuid} && $svm->{replace}) {
		$self->{svm} = $svm;
	}
1172 1173 1174 1175 1176
	$self->{svm};
}

sub _set_svm_vars {
	my ($self, $ra) = @_;
1177 1178 1179
	return $ra if $self->svm;

	my @err = ( "useSvmProps set, but failed to read SVM properties\n",
1180
		    "(svm:source, svm:uuid) ",
1181 1182
		    "from the following URLs:\n" );
	sub read_svm_props {
1183 1184
		my ($self, $ra, $path, $r) = @_;
		my $props = ($ra->get_dir($path, $r))[2];
1185 1186
		my $src = $props->{'svm:source'};
		my $uuid = $props->{'svm:uuid'};
1187
		return undef if (!$src || !$uuid);
1188

1189
		chomp($src, $uuid);
1190

1191 1192
		$uuid =~ m{^[0-9a-f\-]{30,}$}
		    or die "doesn't look right - svm:uuid is '$uuid'\n";
1193 1194 1195

		# the '!' is used to mark the repos_root!/relative/path
		$src =~ s{/?!/?}{/};
1196
		$src =~ s{/+$}{}; # no trailing slashes please
1197
		# username is of no interest
1198 1199
		$src =~ s{(^[a-z\+]*://)[^/@]*@}{$1};

1200 1201 1202
		my $replace = $ra->{url};
		$replace .= "/$path" if length $path;

1203
		my $section = "svn-remote.$self->{repo_id}";
1204 1205 1206 1207 1208 1209 1210 1211
		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
		};
1212 1213 1214 1215
	}

	my $r = $ra->get_latest_revnum;
	my $path = $self->{path};
1216
	my %tried;
1217
	while (length $path) {
1218 1219 1220
		unless ($tried{"$self->{url}/$path"}) {
			return $ra if $self->read_svm_props($ra, $path, $r);
			$tried{"$self->{url}/$path"} = 1;
1221
		}
1222
		$path =~ s#/?[^/]+$##;
1223
	}
1224 1225 1226
	die "Path: '$path' should be ''\n" if $path ne '';
	return $ra if $self->read_svm_props($ra, $path, $r);
	$tried{"$self->{url}/$path"} = 1;
1227 1228

	if ($ra->{repos_root} eq $self->{url}) {
1229
		die @err, (map { "  $_\n" } keys %tried), "\n";
1230 1231 1232 1233 1234 1235 1236 1237
	}

	# 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 $path) {
1238 1239 1240 1241 1242 1243
		unless ($tried{"$ra->{url}/$path"}) {
			$ok = $self->read_svm_props($ra, $path, $r);
			last if $ok;
			$tried{"$ra->{url}/$path"} = 1;
		}
		$path =~ s#/?[^/]+$##;
1244
	}
1245 1246 1247
	die "Path: '$path' should be ''\n" if $path ne '';
	$ok ||= $self->read_svm_props($ra, $path, $r);
	$tried{"$ra->{url}/$path"} = 1;
1248
	if (!$ok) {
1249
		die @err, (map { "  $_\n" } keys %tried), "\n";
1250 1251
	}
	Git::SVN::Ra->new($self->{url});
1252 1253
}

1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297
sub svnsync {
	my ($self) = @_;
	return $self->{svnsync} if $self->{svnsync};

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

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

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

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

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

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

1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315
# 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};
}

1316 1317
sub ra {
	my ($self) = shift;
1318
	my $ra = Git::SVN::Ra->new($self->{url});
1319 1320
	if ($self->use_svm_props && !$self->{svm}) {
		if ($self->no_metadata) {
1321 1322
			die "Can't have both 'noMetadata' and ",
			    "'useSvmProps' options set!\n";
1323 1324 1325
		} elsif ($self->use_svnsync_props) {
			die "Can't have both 'useSvnsyncProps' and ",
			    "'useSvmProps' options set!\n";
1326
		}
1327
		$ra = $self->_set_svm_vars($ra);
1328 1329 1330
		$self->{-want_revprops} = 1;
	}
	$ra;
1331 1332
}

1333 1334 1335 1336
sub rel_path {
	my ($self) = @_;
	my $repos_root = $self->ra->{repos_root};
	return $self->{path} if ($self->{url} eq $repos_root);
1337 1338 1339 1340
	my $url = $self->{url} .
	          (length $self->{path} ? "/$self->{path}" : $self->{path});
	$url =~ s!^\Q$repos_root\E(?:/+|$)!!g;
	$url;
1341 1342
}

1343 1344 1345
sub traverse_ignore {
	my ($self, $fh, $path, $r) = @_;
	$path =~ s#^/+##g;
1346 1347
	my $ra = $self->ra;
	my ($dirent, undef, $props) = $ra->get_dir($path, $r);
1348
	my $p = $path;
1349
	$p =~ s#^\Q$self->{path}\E(/|$)##;
1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367
	print $fh length $p ? "\n# $p\n" : "\n# /\n";
	if (my $s = $props->{'svn:ignore'}) {
		$s =~ s/[\r\n]+/\n/g;
		chomp $s;
		if (length $p == 0) {
			$s =~ s#\n#\n/$p#g;
			print $fh "/$s\n";
		} else {
			$s =~ s#\n#\n/$p/#g;
			print $fh "/$p/$s\n";
		}
	}
	foreach (sort keys %$dirent) {
		next if $dirent->{$_}->kind != $SVN::Node::dir;
		$self->traverse_ignore($fh, "$path/$_", $r);
	}
}

1368 1369 1370
sub last_rev { ($_[0]->last_rev_commit)[0] }
sub last_commit { ($_[0]->last_rev_commit)[1] }

1371 1372 1373 1374 1375 1376
# 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});
	}
1377
	my $c = ::verify_ref($self->refname.'^0');
1378
	if ($c && !$self->use_svm_props && !$self->no_metadata) {
1379
		my $rev = (::cmt_metadata($c))[1];
1380 1381 1382 1383 1384
		if (defined $rev) {
			($self->{last_rev}, $self->{last_commit}) = ($rev, $c);
			return ($rev, $c);
		}
	}
1385 1386 1387 1388 1389
	my $db_path = $self->db_path;
	unless (-e $db_path) {
		($self->{last_rev}, $self->{last_commit}) = (undef, undef);
		return (undef, undef);
	}
1390 1391
	my $offset = -41; # from tail
	my $rl;
1392
	open my $fh, '<', $db_path or croak "$db_path not readable: $!\n";
1393 1394
	sysseek($fh, $offset, 2); # don't care for errors
	sysread($fh, $rl, 41) == 41 or return (undef, undef);
1395
	chomp $rl;
1396
	while (('0' x40) eq $rl && sysseek($fh, 0, 1) != 0) {
1397
		$offset -= 41;
1398 1399
		sysseek($fh, $offset, 2); # don't care for errors
		sysread($fh, $rl, 41) == 41 or return (undef, undef);
1400 1401
		chomp $rl;
	}
1402
	if ($c && $c ne $rl) {
1403
		die "$db_path and ", $self->refname,
1404 1405
		    " inconsistent!:\n$c != $rl\n";
	}
1406
	my $rev = sysseek($fh, 0, 1) or croak $!;
1407 1408 1409 1410 1411 1412
	$rev =  ($rev - 41) / 41;
	close $fh or croak $!;
	($self->{last_rev}, $self->{last_commit}) = ($rev, $c);
	return ($rev, $c);
}

1413 1414 1415
sub get_fetch_range {
	my ($self, $min, $max) = @_;
	$max ||= $self->ra->get_latest_revnum;
1416
	$min ||= $self->rev_db_max;
1417
	(++$min, $max);
1418 1419
}

1420
sub tmp_config {
1421
	my (@args) = @_;
1422 1423 1424 1425 1426 1427
	my $old_def_config = "$ENV{GIT_DIR}/svn/config";
	my $config = "$ENV{GIT_DIR}/svn/.metadata";
	if (-e $old_def_config && ! -e $config) {
		rename $old_def_config, $config or
		       die "Failed rename $old_def_config => $config: $!\n";
	}
1428
	my $old_config = $ENV{GIT_CONFIG};
1429
	$ENV{GIT_CONFIG} = $config;
1430
	$@ = undef;
1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444
	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);
	};
1445 1446 1447 1448 1449 1450 1451 1452 1453 1454
	my $err = $@;
	if (defined $old_config) {
		$ENV{GIT_CONFIG} = $old_config;
	} else {
		delete $ENV{GIT_CONFIG};
	}
	die $err if $err;
	wantarray ? @ret : $ret[0];
}

1455 1456 1457 1458
sub tmp_index_do {
	my ($self, $sub) = @_;
	my $old_index = $ENV{GIT_INDEX_FILE};
	$ENV{GIT_INDEX_FILE} = $self->{index};
1459
	$@ = undef;
1460 1461 1462 1463 1464
	my @ret = eval {
		my ($dir, $base) = ($self->{index} =~ m#^(.*?)/?([^/]+)$#);
		mkpath([$dir]) unless -d $dir;
		&$sub;
	};
1465 1466
	my $err = $@;
	if (defined $old_index) {
1467 1468 1469 1470
		$ENV{GIT_INDEX_FILE} = $old_index;
	} else {
		delete $ENV{GIT_INDEX_FILE};
	}
1471
	die $err if $err;
1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482
	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);
1483 1484 1485 1486 1487
		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);
1488 1489 1490 1491 1492 1493 1494 1495 1496
		$x = command_oneline('write-tree');
		if ($y ne $x) {
			::fatal "trees ($treeish) $y != $x\n",
			        "Something is seriously wrong...\n";
		}
	});
}

sub get_commit_parents {
1497
	my ($self, $log_entry) = @_;
1498
	my (%seen, @ret, @tmp);
1499 1500 1501 1502
	# 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;
1503 1504
		}
	}
1505
	if (my $cur = ::verify_ref($self->refname.'^0')) {
1506 1507
		push @tmp, $cur;
	}
1508
	push @tmp, $_ foreach (@{$log_entry->{parents}}, @tmp);
1509 1510 1511 1512 1513 1514 1515 1516
	while (my $p = shift @tmp) {
		next if $seen{$p};
		$seen{$p} = 1;
		push @ret, $p;
		# MAXPARENT is defined to 16 in commit-tree.c:
		last if @ret >= 16;
	}
	if (@tmp) {
1517
		die "r$log_entry->{revision}: No room for parents:\n\t",
1518 1519 1520 1521 1522
		    join("\n\t", @tmp), "\n";
	}
	@ret;
}

1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542
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} : '');
}

1543
sub full_url {
1544
	my ($self) = @_;
1545
	$self->{url} . (length $self->{path} ? '/' . $self->{path} : '');
1546 1547 1548
}

sub do_git_commit {
1549
	my ($self, $log_entry) = @_;
1550 1551 1552 1553 1554 1555
	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";
	}
1556 1557
	if (my $c = $self->rev_db_get($log_entry->{revision})) {
		croak "$log_entry->{revision} = $c already exists! ",
1558 1559
		      "Why are we refetching it?\n";
	}
1560 1561 1562
	$ENV{GIT_AUTHOR_NAME} = $ENV{GIT_COMMITTER_NAME} = $log_entry->{name};
	$ENV{GIT_AUTHOR_EMAIL} = $ENV{GIT_COMMITTER_EMAIL} =
	                                                  $log_entry->{email};
1563
	$ENV{GIT_AUTHOR_DATE} = $ENV{GIT_COMMITTER_DATE} = $log_entry->{date};
1564

1565
	my $tree = $log_entry->{tree};
1566 1567 1568 1569 1570 1571 1572
	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', $tree);
1573
	foreach ($self->get_commit_parents($log_entry)) {
1574 1575 1576 1577
		push @exec, '-p', $_;
	}
	defined(my $pid = open3(my $msg_fh, my $out_fh, '>&STDERR', @exec))
	                                                           or croak $!;
1578
	print $msg_fh $log_entry->{log} or croak $!;
1579
	unless ($self->no_metadata) {
1580 1581
		print $msg_fh "\ngit-svn-id: $log_entry->{metadata}\n"
		              or croak $!;
1582
	}
1583 1584 1585 1586 1587 1588 1589 1590 1591 1592
	$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";
	}

1593
	$self->rev_db_set($log_entry->{revision}, $commit, 1);
1594

1595
	$self->{last_rev} = $log_entry->{revision};
1596
	$self->{last_commit} = $commit;
1597 1598 1599
	print "r$log_entry->{revision}";
	if (defined $log_entry->{svm_revision}) {
		 print " (\@$log_entry->{svm_revision})";
1600 1601
		 $self->rev_db_set($log_entry->{svm_revision}, $commit,
		                   0, $self->svm_uuid);
1602 1603
	}
	print " = $commit ($self->{ref_id})\n";
E
Eric Wong 已提交
1604 1605 1606 1607 1608 1609 1610
	if (defined $_repack && (--$_repack_nr == 0)) {
		$_repack_nr = $_repack;
		# repack doesn't use any arguments with spaces in them, does it?
		print "Running git repack $_repack_flags ...\n";
		command_noisy('repack', split(/\s+/, $_repack_flags));
		print "Done repacking\n";
	}
1611 1612 1613
	return $commit;
}

1614 1615
sub match_paths {
	my ($self, $paths, $r) = @_;
1616
	return 1 if $self->{path} eq '';
1617 1618 1619
	if (my $path = $paths->{"/$self->{path}"}) {
		return ($path->{action} eq 'D') ? 0 : 1;
	}
1620
	$self->{path_regex} ||= qr/^\/\Q$self->{path}\E\//;
1621 1622 1623 1624 1625 1626
	if (grep /$self->{path_regex}/, keys %$paths) {
		return 1;
	}
	my $c = '';
	foreach (split m#/#, $self->{path}) {
		$c .= "/$_";
1627 1628
		next unless ($paths->{$c} &&
		             ($paths->{$c}->{action} =~ /^[AR]$/));
1629 1630
		if ($self->ra->check_path($self->{path}, $r) ==
		    $SVN::Node::dir) {
1631 1632 1633 1634 1635 1636
			return 1;
		}
	}
	return 0;
}

1637 1638
sub find_parent_branch {
	my ($self, $paths, $rev) = @_;
1639
	return undef unless $self->follow_parent;
1640
	unless (defined $paths) {
1641 1642
		my $err_handler = $SVN::Error::handler;
		$SVN::Error::handler = \&Git::SVN::Ra::skip_unknown_revs;
1643 1644 1645
		$self->ra->get_log([$self->{path}], $rev, $rev, 0, 1, 1, sub {
		                   $paths =
				      Git::SVN::Ra::dup_changed_paths($_[0]) });
1646
		$SVN::Error::handler = $err_handler;
1647 1648
	}
	return undef unless defined $paths;
1649 1650

	# look for a parent from another branch:
1651 1652 1653 1654 1655
	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)};
1656
		last if $i && defined $i->{copyfrom_path};
1657 1658
		unshift(@a_path_components, pop(@b_path_components));
	}
1659 1660
	return undef unless defined $i && defined $i->{copyfrom_path};
	my $branch_from = $i->{copyfrom_path};
1661 1662 1663 1664 1665
	if (@a_path_components) {
		print STDERR "branch_from: $branch_from => ";
		$branch_from .= '/'.join('/', @a_path_components);
		print STDERR $branch_from, "\n";
	}
1666
	my $r = $i->{copyfrom_rev};
1667 1668 1669 1670 1671 1672
	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#^/##;
1673
	my $gs = Git::SVN->find_by_url($new_url, $repos_root, $branch_from);
1674
	unless ($gs) {
1675 1676 1677
		my $ref_id = $self->{ref_id};
		$ref_id =~ s/\@\d+$//;
		$ref_id .= "\@$r";
1678 1679
		# just grow a tail if we're not unique enough :x
		$ref_id .= '-' while find_ref($ref_id);
1680
		print STDERR "Initializing parent: $ref_id\n";
1681
		$gs = Git::SVN->init($new_url, '', $ref_id, $ref_id, 1);
1682 1683
	}
	my ($r0, $parent) = $gs->find_rev_before($r, 1);
1684
	if (!defined $r0 || !defined $parent) {
1685 1686 1687 1688
		my ($base, $head) = parse_revision_argument(0, $r);
		if ($base <= $r) {
			$gs->fetch($base, $r);
		}
1689 1690
		($r0, $parent) = $gs->last_rev_commit;
	}
1691
	if (defined $r0 && defined $parent) {
1692 1693 1694
		print STDERR "Found branch parent: ($self->{ref_id}) $parent\n";
		my $ed;
		if ($self->ra->can_do_switch) {
1695
			$self->assert_index_clean($parent);
1696
			print STDERR "Following parent with do_switch\n";
1697
			# do_switch works with svn/trunk >= r22312, but that
1698
			# is not included with SVN 1.4.3 (the latest version
1699 1700 1701
			# at the moment), so we can't rely on it
			$self->{last_commit} = $parent;
			$ed = SVN::Git::Fetcher->new($self);
1702
			$gs->ra->gs_do_switch($r0, $rev, $gs,
1703 1704 1705
					      $self->full_url, $ed)
			  or die "SVN connection failed somewhere...\n";
		} else {
1706
			print STDERR "Following parent with do_update\n";
1707
			$ed = SVN::Git::Fetcher->new($self);
1708
			$self->ra->gs_do_update($rev, $rev, $self, $ed)
1709 1710
			  or die "SVN connection failed somewhere...\n";
		}
1711
		print STDERR "Successfully followed parent\n";
1712 1713 1714 1715 1716
		return $self->make_log_entry($rev, [$parent], $ed);
	}
	return undef;
}

1717
sub do_fetch {
1718
	my ($self, $paths, $rev) = @_;
1719
	my $ed;
1720
	my ($last_rev, @parents);
1721 1722 1723 1724 1725 1726 1727 1728 1729
	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;
		}
1730
		$ed = SVN::Git::Fetcher->new($self);
1731
		$last_rev = $self->{last_rev};
1732 1733
		$ed->{c} = $lc;
		@parents = ($lc);
1734 1735
	} else {
		$last_rev = $rev;
1736 1737 1738 1739
		if (my $log_entry = $self->find_parent_branch($paths, $rev)) {
			return $log_entry;
		}
		$ed = SVN::Git::Fetcher->new($self);
1740
	}
1741
	unless ($self->ra->gs_do_update($last_rev, $rev, $self, $ed)) {
1742 1743 1744 1745 1746
		die "SVN connection failed somewhere...\n";
	}
	$self->make_log_entry($rev, \@parents, $ed);
}

1747 1748 1749 1750
sub get_untracked {
	my ($self, $ed) = @_;
	my @out;
	my $h = $ed->{empty};
1751 1752
	foreach (sort keys %$h) {
		my $act = $h->{$_} ? '+empty_dir' : '-empty_dir';
1753
		push @out, "  $act: " . uri_encode($_);
1754 1755 1756
		warn "W: $act: $_\n";
	}
	foreach my $t (qw/dir_prop file_prop/) {
1757
		$h = $ed->{$t} or next;
1758 1759 1760
		foreach my $path (sort keys %$h) {
			my $ppath = $path eq '' ? '.' : $path;
			foreach my $prop (sort keys %{$h->{$path}}) {
1761
				next if $SKIP_PROP{$prop};
1762
				my $v = $h->{$path}->{$prop};
1763 1764 1765
				my $t_ppath_prop = "$t: " .
				                    uri_encode($ppath) . ' ' .
				                    uri_encode($prop);
1766
				if (defined $v) {
1767 1768
					push @out, "  +$t_ppath_prop " .
					           uri_encode($v);
1769
				} else {
1770
					push @out, "  -$t_ppath_prop";
1771 1772 1773 1774 1775
				}
			}
		}
	}
	foreach my $t (qw/absent_file absent_directory/) {
1776
		$h = $ed->{$t} or next;
1777 1778
		foreach my $parent (sort keys %$h) {
			foreach my $path (sort @{$h->{$parent}}) {
1779 1780
				push @out, "  $t: " .
				           uri_encode("$parent/$path");
1781 1782 1783 1784 1785
				warn "W: $t: $parent/$path ",
				     "Insufficient permissions?\n";
			}
		}
	}
1786
	\@out;
1787 1788
}

1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807
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;
}

1808
sub make_log_entry {
1809 1810 1811
	my ($self, $rev, $parents, $ed) = @_;
	my $untracked = $self->get_untracked($ed);

1812
	open my $un, '>>', "$self->{dir}/unhandled.log" or croak $!;
1813 1814 1815 1816
	print $un "r$rev\n" or croak $!;
	print $un $_, "\n" foreach @$untracked;
	my %log_entry = ( parents => $parents || [], revision => $rev,
	                  log => '');
1817

1818
	my $headrev;
1819
	my $logged = delete $self->{logged_rev_props};
1820
	if (!$logged || $self->{-want_revprops}) {
1821 1822 1823 1824 1825
		my $rp = $self->ra->rev_proplist($rev);
		foreach (sort keys %$rp) {
			my $v = $rp->{$_};
			if (/^svn:(author|date|log)$/) {
				$log_entry{$1} = $v;
1826 1827
			} elsif ($_ eq 'svm:headrev') {
				$headrev = $v;
1828 1829 1830 1831
			} else {
				print $un "  rev_prop: ", uri_encode($_), ' ',
					  uri_encode($v), "\n";
			}
1832
		}
1833 1834
	} else {
		map { $log_entry{$_} = $logged->{$_} } keys %$logged;
1835 1836
	}
	close $un or croak $!;
1837

1838 1839
	$log_entry{date} = parse_svn_date($log_entry{date});
	$log_entry{log} .= "\n";
1840 1841 1842
	my $author = $log_entry{author} = check_author($log_entry{author});
	my ($name, $email) = defined $::users{$author} ? @{$::users{$author}}
	                                               : ($author, undef);
1843
	if (defined $headrev && $self->use_svm_props) {
1844 1845 1846 1847
		if ($self->rewrite_root) {
			die "Can't have both 'useSvmProps' and 'rewriteRoot' ",
			    "options set!\n";
		}
1848
		my ($uuid, $r) = $headrev =~ m{^([a-f\d\-]{30,}):(\d+)$};
1849 1850 1851 1852
		# we don't want "SVM: initializing mirror for junk" ...
		return undef if $r == 0;
		my $svm = $self->svm;
		if ($uuid ne $svm->{uuid}) {
1853
			die "UUID mismatch on SVM path:\n",
1854
			    "expected: $svm->{uuid}\n",
1855 1856
			    "     got: $uuid\n";
		}
1857 1858 1859 1860
		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 $full_url\n";
1861 1862
		# throw away username for storing in records
		remove_username($full_url);
1863 1864
		$log_entry{metadata} = "$full_url\@$r $uuid";
		$log_entry{svm_revision} = $r;
1865
		$email ||= "$author\@$uuid"
1866 1867 1868 1869 1870 1871
	} elsif ($self->use_svnsync_props) {
		my $full_url = $self->svnsync->{url};
		$full_url .= "/$self->{path}" if length $self->{path};
		my $uuid = $self->svnsync->{uuid};
		$log_entry{metadata} = "$full_url\@$rev $uuid";
		$email ||= "$author\@$uuid"
1872
	} else {
1873
		$log_entry{metadata} = $self->metadata_url. "\@$rev " .
1874
		                       $self->ra->get_uuid;
1875
		$email ||= "$author\@" . $self->ra->get_uuid;
1876
	}
1877 1878
	$log_entry{name} = $name;
	$log_entry{email} = $email;
1879 1880 1881 1882
	\%log_entry;
}

sub fetch {
1883
	my ($self, $min_rev, $max_rev, @parents) = @_;
1884
	my ($last_rev, $last_commit) = $self->last_rev_commit;
1885
	my ($base, $head) = $self->get_fetch_range($min_rev, $max_rev);
1886
	$self->ra->gs_fetch_loop_common($base, $head, [$self]);
1887 1888 1889 1890
}

sub set_tree_cb {
	my ($self, $log_entry, $tree, $rev, $date, $author) = @_;
1891 1892
	$self->{inject_parents} = { $rev => $tree };
	$self->fetch(undef, undef);
1893 1894 1895 1896
}

sub set_tree {
	my ($self, $tree) = (shift, shift);
1897
	my $log_entry = ::get_commit_entry($tree);
1898 1899 1900
	unless ($self->{last_rev}) {
		fatal("Must have an existing revision to commit\n");
	}
1901 1902 1903 1904 1905 1906 1907 1908 1909
	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 => $self->{path} );
	if (!SVN::Git::Editor->new(\%ed_opts)->apply_diff) {
1910 1911 1912 1913
		print "No changes\nr$self->{last_rev} = $tree\n";
	}
}

1914 1915
sub rebuild {
	my ($self) = @_;
1916
	my $db_path = $self->db_path;
1917 1918
	return if (-e $db_path && ! -z $db_path);
	return unless ::verify_ref($self->refname.'^0');
1919 1920 1921 1922 1923 1924 1925 1926 1927
	if (-f $self->{db_root}) {
		rename $self->{db_root}, $db_path or die
		     "rename $self->{db_root} => $db_path failed: $!\n";
		my ($dir, $base) = ($db_path =~ m#^(.*?)/?([^/]+)$#);
		symlink $base, $self->{db_root} or die
		     "symlink $base => $self->{db_root} failed: $!\n";
		return;
	}
	print "Rebuilding $db_path ...\n";
1928 1929 1930
	my ($rev_list, $ctx) = command_output_pipe("rev-list", $self->refname);
	my $latest;
	my $full_url = $self->full_url;
1931
	remove_username($full_url);
1932 1933 1934 1935 1936 1937
	my $svn_uuid;
	while (<$rev_list>) {
		chomp;
		my $c = $_;
		die "Non-SHA1: $c\n" unless $c =~ /^$::sha1$/o;
		my ($url, $rev, $uuid) = ::cmt_metadata($c);
1938
		remove_username($url);
1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955

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

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

		$self->rev_db_set($rev, $c);
		print "r$rev = $c\n";
	}
	command_close_pipe($rev_list, $ctx);
1956
	print "Done rebuilding $db_path\n";
1957 1958
}

1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969
# rev_db:
# Tie::File seems to be prone to offset errors if revisions get sparse,
# it's not that fast, either.  Tie::File is also not in Perl 5.6.  So
# one of my favorite modules is out :<  Next up would be one of the DBM
# modules, but I'm not sure which is most portable...  So I'll just
# go with something that's plain-text, but still capable of
# being randomly accessed.  So here's my ultra-simple fixed-width
# database.  All records are 40 characters + "\n", so it's easy to seek
# to a revision: (41 * rev) is the byte offset.
# A record of 40 0s denotes an empty revision.
# And yes, it's still pretty fast (faster than Tie::File).
1970
# These files are disposable unless noMetadata or useSvmProps is set
1971

1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996
sub _rev_db_set {
	my ($fh, $rev, $commit) = @_;
	my $offset = $rev * 41;
	# assume that append is the common case:
	seek $fh, 0, 2 or croak $!;
	my $pos = tell $fh;
	if ($pos < $offset) {
		for (1 .. (($offset - $pos) / 41)) {
			print $fh (('0' x 40),"\n") or croak $!;
		}
	}
	seek $fh, $offset, 0 or croak $!;
	print $fh $commit,"\n" or croak $!;
}

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

1997
sub rev_db_set {
1998 1999 2000 2001
	my ($self, $rev, $commit, $update_ref, $uuid) = @_;
	length $commit == 40 or die "arg3 must be a full SHA1 hexsum\n";
	my $db = $self->db_path($uuid);
	my $db_lock = "$db.lock";
2002 2003 2004 2005 2006
	my $sig;
	if ($update_ref) {
		$SIG{INT} = $SIG{HUP} = $SIG{TERM} = $SIG{ALRM} = $SIG{PIPE} =
		            $SIG{USR1} = $SIG{USR2} = sub { $sig = $_[0] };
	}
2007 2008
	mkfile($db);

2009
	$LOCKFILES{$db_lock} = 1;
2010 2011 2012 2013 2014
	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) {
		$sync = 1;
2015
		copy($db, $db_lock) or die "rev_db_set(@_): ",
2016
					   "Failed to copy: ",
2017 2018 2019
					   "$db => $db_lock ($!)\n";
	} else {
		rename $db, $db_lock or die "rev_db_set(@_): ",
2020
					    "Failed to rename: ",
2021 2022
					    "$db => $db_lock ($!)\n";
	}
2023 2024
	open my $fh, '+<', $db_lock or die "Couldn't open $db_lock: $!\n";
	_rev_db_set($fh, $rev, $commit);
2025 2026 2027 2028
	if ($sync) {
		$fh->flush or die "Couldn't flush $db_lock: $!\n";
		$fh->sync or die "Couldn't sync $db_lock: $!\n";
	}
2029
	close $fh or croak $!;
2030
	if ($update_ref) {
2031
		$_head = $self;
2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042
		command_noisy('update-ref', '-m', "r$rev",
		              $self->refname, $commit);
	}
	rename $db_lock, $db or die "rev_db_set(@_): ", "Failed to rename: ",
	                            "$db_lock => $db ($!)\n";
	delete $LOCKFILES{$db_lock};
	if ($update_ref) {
		$SIG{INT} = $SIG{HUP} = $SIG{TERM} = $SIG{ALRM} = $SIG{PIPE} =
		            $SIG{USR1} = $SIG{USR2} = 'DEFAULT';
		kill $sig, $$ if defined $sig;
	}
2043 2044
}

2045 2046
sub rev_db_max {
	my ($self) = @_;
2047
	$self->rebuild;
2048 2049 2050
	my $db_path = $self->db_path;
	my @stat = stat $db_path or return 0;
	($stat[7] % 41) == 0 or die "$db_path inconsistent size: $stat[7]\n";
2051 2052 2053 2054
	my $max = $stat[7] / 41;
	(($max > 0) ? $max - 1 : 0);
}

2055
sub rev_db_get {
2056
	my ($self, $rev, $uuid) = @_;
2057 2058
	my $ret;
	my $offset = $rev * 41;
2059 2060 2061
	my $db_path = $self->db_path($uuid);
	return undef unless -e $db_path;
	open my $fh, '<', $db_path or croak $!;
2062 2063 2064
	if (sysseek($fh, $offset, 0) == $offset) {
		my $read = sysread($fh, $ret, 40);
		$ret = undef if ($read != 40 || $ret eq ('0'x40));
2065 2066 2067 2068 2069
	}
	close $fh or croak $!;
	$ret;
}

2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081
sub find_rev_before {
	my ($self, $rev, $eq_ok) = @_;
	--$rev unless $eq_ok;
	while ($rev > 0) {
		if (my $c = $self->rev_db_get($rev)) {
			return ($rev, $c);
		}
		--$rev;
	}
	return (undef, undef);
}

2082
sub _new {
2083 2084 2085 2086 2087
	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) {
2088
		$_[2] = $ref_id = $Git::SVN::default_ref_id;
2089 2090 2091 2092
	}
	$_[1] = $repo_id = sanitize_remote_name($repo_id);
	my $dir = "$ENV{GIT_DIR}/svn/$ref_id";
	$_[3] = $path = '' unless (defined $path);
2093
	mkpath(["$ENV{GIT_DIR}/svn"]);
2094 2095
	bless {
		ref_id => $ref_id, dir => $dir, index => "$dir/index",
2096
	        path => $path, config => "$ENV{GIT_DIR}/svn/config",
2097 2098 2099 2100 2101 2102 2103
	        db_root => "$dir/.rev_db", repo_id => $repo_id }, $class;
}

sub db_path {
	my ($self, $uuid) = @_;
	$uuid ||= $self->ra_uuid;
	"$self->{db_root}.$uuid";
2104 2105
}

2106 2107 2108 2109 2110
sub uri_encode {
	my ($f) = @_;
	$f =~ s#([^a-zA-Z0-9\*!\:_\./\-])#uc sprintf("%%%02x",ord($1))#eg;
	$f
}
2111

2112 2113 2114 2115
sub remove_username {
	$_[0] =~ s{^([^:]*://)[^@]+@}{$1};
}

2116 2117 2118 2119 2120 2121 2122
package Git::SVN::Prompt;
use strict;
use warnings;
require SVN::Core;
use vars qw/$_no_auth_cache $_username/;

sub simple {
2123 2124 2125 2126 2127
	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) {
2128 2129
			print STDERR "Authentication realm: $realm\n";
			STDERR->flush;
2130 2131 2132
		}
		$cred->username($default_username);
	} else {
2133
		username($cred, $realm, $may_save, $pool);
2134 2135 2136 2137 2138 2139 2140
	}
	$cred->password(_read_password("Password for '" .
	                               $cred->username . "': ", $realm));
	$cred->may_save($may_save);
	$SVN::_Core::SVN_NO_ERROR;
}

2141
sub ssl_server_trust {
2142 2143
	my ($cred, $realm, $failures, $cert_info, $may_save, $pool) = @_;
	$may_save = undef if $_no_auth_cache;
2144
	print STDERR "Error validating server certificate for '$realm':\n";
2145
	if ($failures & $SVN::Auth::SSL::UNKNOWNCA) {
2146
		print STDERR " - The certificate is not issued by a trusted ",
2147 2148 2149 2150
		      "authority. Use the\n",
	              "   fingerprint to validate the certificate manually!\n";
	}
	if ($failures & $SVN::Auth::SSL::CNMISMATCH) {
2151
		print STDERR " - The certificate hostname does not match.\n";
2152 2153
	}
	if ($failures & $SVN::Auth::SSL::NOTYETVALID) {
2154
		print STDERR " - The certificate is not yet valid.\n";
2155 2156
	}
	if ($failures & $SVN::Auth::SSL::EXPIRED) {
2157
		print STDERR " - The certificate has expired.\n";
2158 2159
	}
	if ($failures & $SVN::Auth::SSL::OTHER) {
2160
		print STDERR " - The certificate has an unknown error.\n";
2161
	}
2162 2163
	printf STDERR
	        "Certificate information:\n".
2164 2165 2166 2167 2168
	        " - Hostname: %s\n".
	        " - Valid: from %s until %s\n".
	        " - Issuer: %s\n".
	        " - Fingerprint: %s\n",
	        map $cert_info->$_, qw(hostname valid_from valid_until
2169
	                               issuer_dname fingerprint);
2170 2171
	my $choice;
prompt:
2172
	print STDERR $may_save ?
2173 2174
	      "(R)eject, accept (t)emporarily or accept (p)ermanently? " :
	      "(R)eject or accept (t)emporarily? ";
2175
	STDERR->flush;
2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189
	$choice = lc(substr(<STDIN> || 'R', 0, 1));
	if ($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;
}

2190
sub ssl_client_cert {
2191 2192
	my ($cred, $realm, $may_save, $pool) = @_;
	$may_save = undef if $_no_auth_cache;
2193 2194
	print STDERR "Client certificate filename: ";
	STDERR->flush;
2195 2196 2197 2198 2199 2200
	chomp(my $filename = <STDIN>);
	$cred->cert_file($filename);
	$cred->may_save($may_save);
	$SVN::_Core::SVN_NO_ERROR;
}

2201
sub ssl_client_cert_pw {
2202 2203 2204 2205 2206 2207 2208
	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;
}

2209
sub username {
2210 2211 2212
	my ($cred, $realm, $may_save, $pool) = @_;
	$may_save = undef if $_no_auth_cache;
	if (defined $realm && length $realm) {
2213
		print STDERR "Authentication realm: $realm\n";
2214 2215 2216 2217 2218
	}
	my $username;
	if (defined $_username) {
		$username = $_username;
	} else {
2219 2220
		print STDERR "Username: ";
		STDERR->flush;
2221 2222 2223 2224 2225 2226 2227 2228 2229
		chomp($username = <STDIN>);
	}
	$cred->username($username);
	$cred->may_save($may_save);
	$SVN::_Core::SVN_NO_ERROR;
}

sub _read_password {
	my ($prompt, $realm) = @_;
2230 2231
	print STDERR $prompt;
	STDERR->flush;
2232 2233 2234 2235 2236 2237 2238 2239
	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');
2240 2241
	print STDERR "\n";
	STDERR->flush;
2242 2243 2244
	$password;
}

2245 2246
package main;

2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258
{
	my $kill_stupid_warnings = $SVN::Node::none.$SVN::Node::file.
				$SVN::Node::dir.$SVN::Node::unknown.
				$SVN::Node::none.$SVN::Node::file.
				$SVN::Node::dir.$SVN::Node::unknown.
				$SVN::Auth::SSL::CNMISMATCH.
				$SVN::Auth::SSL::NOTYETVALID.
				$SVN::Auth::SSL::EXPIRED.
				$SVN::Auth::SSL::UNKNOWNCA.
				$SVN::Auth::SSL::OTHER;
}

2259 2260 2261 2262 2263 2264
package SVN::Git::Fetcher;
use vars qw/@ISA/;
use strict;
use warnings;
use Carp qw/croak/;
use IO::File qw//;
2265
use Digest::MD5;
2266 2267 2268 2269 2270 2271

# 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;
2272
	$self->{c} = $git_svn->{last_commit} if exists $git_svn->{last_commit};
2273 2274 2275 2276 2277
	$self->{empty} = {};
	$self->{dir_prop} = {};
	$self->{file_prop} = {};
	$self->{absent_dir} = {};
	$self->{absent_file} = {};
2278
	$self->{gii} = $git_svn->tmp_index_do(sub { Git::IndexInfo->new });
2279 2280 2281
	$self;
}

2282 2283
sub set_path_strip {
	my ($self, $path) = @_;
2284
	$self->{path_strip} = qr/^\Q$path\E(\/|$)/ if length $path;
2285 2286
}

2287 2288 2289 2290 2291 2292 2293 2294 2295
sub open_root {
	{ path => '' };
}

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

2296 2297
sub git_path {
	my ($self, $path) = @_;
2298 2299 2300 2301
	if ($self->{path_strip}) {
		$path =~ s!$self->{path_strip}!! or
		  die "Failed to strip path '$path' ($self->{path_strip})\n";
	}
2302 2303 2304
	$path;
}

2305 2306
sub delete_entry {
	my ($self, $path, $rev, $pb) = @_;
2307

2308
	my $gpath = $self->git_path($path);
2309 2310
	return undef if ($gpath eq '');

2311
	# remove entire directories.
2312
	if (command('ls-tree', $self->{c}, '--', $gpath) =~ /^040000 tree/) {
2313 2314
		my ($ls, $ctx) = command_output_pipe(qw/ls-tree
		                                     -r --name-only -z/,
2315
				                     $self->{c}, '--', $gpath);
2316 2317
		local $/ = "\0";
		while (<$ls>) {
2318 2319
			chomp;
			$self->{gii}->remove($_);
2320
			print "\tD\t$_\n" unless $::_q;
2321
		}
2322
		print "\tD\t$gpath/\n" unless $::_q;
2323 2324 2325
		command_close_pipe($ls, $ctx);
		$self->{empty}->{$path} = 0
	} else {
2326
		$self->{gii}->remove($gpath);
2327
		print "\tD\t$gpath\n" unless $::_q;
2328
	}
2329 2330 2331 2332 2333
	undef;
}

sub open_file {
	my ($self, $path, $pb, $rev) = @_;
2334 2335
	my $gpath = $self->git_path($path);
	my ($mode, $blob) = (command('ls-tree', $self->{c}, '--', $gpath)
2336
	                     =~ /^(\d{6}) blob ([a-f\d]{40})\t/);
2337 2338 2339
	unless (defined $mode && defined $blob) {
		die "$path was not found in commit $self->{c} (r$rev)\n";
	}
2340
	{ path => $path, mode_a => $mode, mode_b => $mode, blob => $blob,
2341
	  pool => SVN::Pool->new, action => 'M' };
2342 2343 2344 2345
}

sub add_file {
	my ($self, $path, $pb, $cp_path, $cp_rev) = @_;
2346 2347
	my ($dir, $file) = ($path =~ m#^(.*?)/?([^/]+)$#);
	delete $self->{empty}->{$dir};
2348
	{ path => $path, mode_a => 100644, mode_b => 100644,
2349
	  pool => SVN::Pool->new, action => 'A' };
2350 2351
}

2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380
sub add_directory {
	my ($self, $path, $cp_path, $cp_rev) = @_;
	my ($dir, $file) = ($path =~ m#^(.*?)/?([^/]+)$#);
	delete $self->{empty}->{$dir};
	$self->{empty}->{$path} = 1;
	{ path => $path };
}

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

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

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

2381 2382 2383 2384 2385 2386 2387 2388
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;
2389 2390 2391
	} else {
		$self->{file_prop}->{$fb->{path}} ||= {};
		$self->{file_prop}->{$fb->{path}}->{$prop} = $value;
2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433
	}
	undef;
}

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

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

sub close_file {
	my ($self, $fb, $exp) = @_;
	my $hash;
2434
	my $path = $self->git_path($fb->{path});
2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461
	if (my $fh = $fb->{fh}) {
		seek($fh, 0, 0) or croak $!;
		my $md5 = Digest::MD5->new;
		$md5->addfile($fh);
		my $got = $md5->hexdigest;
		die "Checksum mismatch: $path\n",
		    "expected: $exp\n    got: $got\n" if ($got ne $exp);
		seek($fh, 0, 0) or croak $!;
		if ($fb->{mode_b} == 120000) {
			read($fh, my $buf, 5) == 5 or croak $!;
			$buf eq 'link ' or die "$path has mode 120000",
			                       "but is not a link\n";
		}
		defined(my $pid = open my $out,'-|') or die "Can't fork: $!\n";
		if (!$pid) {
			open STDIN, '<&', $fh or croak $!;
			exec qw/git-hash-object -w --stdin/ or croak $!;
		}
		chomp($hash = do { local $/; <$out> });
		close $out or croak $!;
		close $fh or croak $!;
		$hash =~ /^[a-f\d]{40}$/ or die "not a sha1: $hash\n";
		close $fb->{base} or croak $!;
	} else {
		$hash = $fb->{blob} or die "no blob information\n";
	}
	$fb->{pool}->clear;
2462
	$self->{gii}->update($fb->{mode_b}, $hash, $path) or croak $!;
2463
	print "\t$fb->{action}\t$path\n" if $fb->{action} && ! $::_q;
2464 2465 2466 2467 2468
	undef;
}

sub abort_edit {
	my $self = shift;
2469 2470
	$self->{nr} = $self->{gii}->{nr};
	delete $self->{gii};
2471 2472 2473 2474 2475
	$self->SUPER::abort_edit(@_);
}

sub close_edit {
	my $self = shift;
2476
	$self->{git_commit_ok} = 1;
2477 2478
	$self->{nr} = $self->{gii}->{nr};
	delete $self->{gii};
2479 2480
	$self->SUPER::close_edit(@_);
}
2481

2482
package SVN::Git::Editor;
2483
use vars qw/@ISA $_rmdir $_cp_similarity $_find_copies_harder $_rename_limit/;
2484 2485 2486 2487
use strict;
use warnings;
use Carp qw/croak/;
use IO::File;
2488
use Digest::MD5;
2489 2490

sub new {
2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504
	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);
2505
	bless $self, $class;
2506 2507
	foreach (qw/svn_path r tree_a tree_b/) {
		$self->{$_} = $opts->{$_};
2508
	}
2509 2510 2511 2512
	$self->{url} = $opts->{ra}->{url};
	$self->{mods} = $mods;
	$self->{types} = $types;
	$self->{pool} = $pool;
2513 2514
	$self->{bat} = { '' => $self->open_root($self->{r}, $self->{pool}) };
	$self->{rm} = { };
2515 2516
	$self->{path_prefix} = length $self->{svn_path} ?
	                       "$self->{svn_path}/" : '';
2517 2518 2519
	return $self;
}

2520 2521 2522
sub generate_diff {
	my ($tree_a, $tree_b) = @_;
	my @diff_tree = qw(diff-tree -z -r);
2523 2524
	if ($_cp_similarity) {
		push @diff_tree, "-C$_cp_similarity";
2525 2526 2527
	} else {
		push @diff_tree, '-C';
	}
2528 2529
	push @diff_tree, '--find-copies-harder' if $_find_copies_harder;
	push @diff_tree, "-l$_rename_limit" if defined $_rename_limit;
2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602
	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;
}

2603 2604 2605 2606 2607
sub split_path {
	return ($_[0] =~ m#^(.*?)/?([^/]+)$#);
}

sub repo_path {
2608 2609
	my ($self, $path) = @_;
	$self->{path_prefix}.(defined $path ? $path : '');
2610 2611 2612 2613
}

sub url_path {
	my ($self, $path) = @_;
2614
	$self->{url} . '/' . $self->repo_path($path);
2615 2616 2617
}

sub rmdirs {
2618
	my ($self) = @_;
2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635
	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;

2636 2637
	my ($fh, $ctx) = command_output_pipe(qw/ls-tree --name-only -r -z/,
	                                     $self->{tree_b});
2638 2639 2640
	local $/ = "\0";
	while (<$fh>) {
		chomp;
2641
		my @dn = split m#/#, $_;
2642 2643 2644 2645
		while (pop @dn) {
			delete $rm->{join '/', @dn};
		}
		unless (%$rm) {
2646
			close $fh;
2647 2648
			return;
		}
2649
	}
E
Eric Wong 已提交
2650
	command_close_pipe($fh, $ctx);
2651

2652 2653 2654 2655
	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) = ($d =~ m#^(.*?)/?(?:[^/]+)$#);
2656
		print "\tD+\t$d/\n" unless $::_q;
2657 2658 2659 2660 2661 2662 2663
		$self->SUPER::delete_entry($d, $r, $bat->{$dn}, $p);
		delete $bat->{$d};
	}
}

sub open_or_add_dir {
	my ($self, $full_path, $baton) = @_;
2664 2665 2666 2667
	my $t = $self->{types}->{$full_path};
	if (!defined $t) {
		die "$full_path not known in r$self->{r} or we have a bug!\n";
	}
2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683
	if ($t == $SVN::Node::none) {
		return $self->add_directory($full_path, $baton,
						undef, -1, $self->{pool});
	} elsif ($t == $SVN::Node::dir) {
		return $self->open_directory($full_path, $baton,
						$self->{r}, $self->{pool});
	}
	print STDERR "$full_path already exists in repository at ",
		"r$self->{r} and it is not a directory (",
		($t == $SVN::Node::file ? 'file' : 'unknown'),"/$t)\n";
	exit 1;
}

sub ensure_path {
	my ($self, $path) = @_;
	my $bat = $self->{bat};
2684 2685 2686
	my $repo_path = $self->repo_path($path);
	return $bat->{''} unless (length $repo_path);
	my @p = split m#/+#, $repo_path;
2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697
	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 {
2698
	my ($self, $m) = @_;
2699 2700 2701 2702
	my ($dir, $file) = split_path($m->{file_b});
	my $pbat = $self->ensure_path($dir);
	my $fbat = $self->add_file($self->repo_path($m->{file_b}), $pbat,
					undef, -1);
2703
	print "\tA\t$m->{file_b}\n" unless $::_q;
2704 2705 2706 2707 2708
	$self->chg_file($fbat, $m);
	$self->close_file($fbat,undef,$self->{pool});
}

sub C {
2709
	my ($self, $m) = @_;
2710 2711 2712 2713
	my ($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}), $self->{r});
2714
	print "\tC\t$m->{file_a} => $m->{file_b}\n" unless $::_q;
2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727
	$self->chg_file($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 {
2728
	my ($self, $m) = @_;
2729 2730 2731 2732
	my ($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}), $self->{r});
2733
	print "\tR\t$m->{file_a} => $m->{file_b}\n" unless $::_q;
2734 2735 2736 2737 2738 2739 2740 2741 2742
	$self->chg_file($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 {
2743
	my ($self, $m) = @_;
2744 2745 2746 2747
	my ($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},$self->{pool});
2748
	print "\t$m->{chg}\t$m->{file_b}\n" unless $::_q;
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 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788
	$self->chg_file($fbat, $m);
	$self->close_file($fbat,undef,$self->{pool});
}

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

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

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

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

	my $exp = $md5->hexdigest;
2789 2790 2791
	my $pool = SVN::Pool->new;
	my $atd = $self->apply_textdelta($fbat, undef, $pool);
	my $got = SVN::TxDelta::send_stream($fh, @$atd, $pool);
2792
	die "Checksum mismatch\nexpected: $exp\ngot: $got\n" if ($got ne $exp);
2793
	$pool->clear;
2794 2795 2796 2797 2798

	close $fh or croak $!;
}

sub D {
2799
	my ($self, $m) = @_;
2800 2801
	my ($dir, $file) = split_path($m->{file_b});
	my $pbat = $self->ensure_path($dir);
2802
	print "\tD\t$m->{file_b}\n" unless $::_q;
2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818
	$self->delete_entry($m->{file_b}, $pbat);
}

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

sub abort_edit {
	my ($self) = @_;
	$self->SUPER::abort_edit($self->{pool});
2819 2820 2821 2822 2823
}

sub DESTROY {
	my $self = shift;
	$self->SUPER::DESTROY(@_);
2824 2825 2826
	$self->{pool}->clear;
}

2827 2828
# this drives the editor
sub apply_diff {
2829 2830
	my ($self) = @_;
	my $mods = $self->{mods};
2831
	my %o = ( D => 1, R => 0, C => -1, A => 3, M => 3, T => 3 );
2832
	foreach my $m (sort { $o{$a->{chg}} <=> $o{$b->{chg}} } @$mods) {
2833 2834 2835 2836 2837 2838 2839
		my $f = $m->{chg};
		if (defined $o{$f}) {
			$self->$f($m);
		} else {
			fatal("Invalid change type: $f\n");
		}
	}
2840
	$self->rmdirs if $_rmdir;
2841
	if (@$mods == 0) {
2842 2843 2844 2845
		$self->abort_edit;
	} else {
		$self->close_edit;
	}
2846
	return scalar @$mods;
2847 2848
}

2849
package Git::SVN::Ra;
2850
use vars qw/@ISA $config_dir $_log_window_size/;
2851 2852
use strict;
use warnings;
2853
my ($can_do_switch, %ignored_err, $RA);
2854 2855 2856 2857

BEGIN {
	# enforce temporary pool usage for some simple functions
	my $e;
2858
	foreach (qw/get_latest_revnum get_uuid get_repos_root/) {
2859 2860 2861 2862 2863 2864 2865
		$e .= "sub $_ {
			my \$self = shift;
			my \$pool = SVN::Pool->new;
			my \@ret = \$self->SUPER::$_(\@_,\$pool);
			\$pool->clear;
			wantarray ? \@ret : \$ret[0]; }\n";
	}
2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889

	# get_dir needs $pool held in cache for dirents to work,
	# check_path is cacheable and rev_proplist is close enough
	# for our purposes.
	foreach (qw/check_path get_dir rev_proplist/) {
		$e .= "my \%${_}_cache; my \$${_}_rev = 0; sub $_ {
			my \$self = shift;
			my \$r = pop;
			my \$k = join(\"\\0\", \@_);
			if (my \$x = \$${_}_cache{\$r}->{\$k}) {
				return wantarray ? \@\$x : \$x->[0];
			}
			my \$pool = SVN::Pool->new;
			my \@ret = \$self->SUPER::$_(\@_, \$r, \$pool);
			if (\$r != \$${_}_rev) {
				\%${_}_cache = ( pool => [] );
				\$${_}_rev = \$r;
			}
			\$${_}_cache{\$r}->{\$k} = \\\@ret;
			push \@{\$${_}_cache{pool}}, \$pool;
			wantarray ? \@ret : \$ret[0]; }\n";
	}
	$e .= "\n1;";
	eval $e or die $@;
2890 2891 2892 2893
}

sub new {
	my ($class, $url) = @_;
2894
	$url =~ s!/+$!!;
2895
	return $RA if ($RA && $RA->{url} eq $url);
2896
	$RA->{pool}->clear if $RA;
2897

2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920
	SVN::_Core::svn_config_ensure($config_dir, undef);
	my ($baton, $callbacks) = SVN::Core::auth_open_helper([
	    SVN::Client::get_simple_provider(),
	    SVN::Client::get_ssl_server_trust_file_provider(),
	    SVN::Client::get_simple_prompt_provider(
	      \&Git::SVN::Prompt::simple, 2),
	    SVN::Client::get_ssl_client_cert_prompt_provider(
	      \&Git::SVN::Prompt::ssl_client_cert, 2),
	    SVN::Client::get_ssl_client_cert_pw_prompt_provider(
	      \&Git::SVN::Prompt::ssl_client_cert_pw, 2),
	    SVN::Client::get_username_provider(),
	    SVN::Client::get_ssl_server_trust_prompt_provider(
	      \&Git::SVN::Prompt::ssl_server_trust),
	    SVN::Client::get_username_prompt_provider(
	      \&Git::SVN::Prompt::username, 2),
	  ]);
	my $config = SVN::Core::config_get_config($config_dir);
	my $self = SVN::Ra->new(url => $url, auth => $baton,
	                      config => $config,
			      pool => SVN::Pool->new,
	                      auth_provider_callbacks => $callbacks);
	$self->{svn_path} = $url;
	$self->{repos_root} = $self->get_repos_root;
2921
	$self->{svn_path} =~ s#^\Q$self->{repos_root}\E(/|$)##;
2922
	$RA = bless $self, $class;
2923 2924 2925
}

sub DESTROY {
2926
	# do not call the real DESTROY since we store ourselves in $RA
2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938
}

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

sub get_commit_editor {
2939
	my ($self, $log, $cb, $pool) = @_;
2940
	my @lock = $SVN::Core::VERSION ge '1.2.0' ? (undef, 0) : ();
2941
	$self->SUPER::get_commit_editor($log, $cb, @lock, $pool);
2942 2943 2944
}

sub gs_do_update {
2945 2946 2947 2948
	my ($self, $rev_a, $rev_b, $gs, $editor) = @_;
	my $new = ($rev_a == $rev_b);
	my $path = $gs->{path};

2949 2950 2951 2952
	if ($new && -e $gs->{index}) {
		unlink $gs->{index} or die
		  "Couldn't unlink index: $gs->{index}: $!\n";
	}
2953
	my $pool = SVN::Pool->new;
2954
	$editor->set_path_strip($path);
2955 2956
	my (@pc) = split m#/#, $path;
	my $reporter = $self->do_update($rev_b, (@pc ? shift @pc : ''),
2957
	                                1, $editor, $pool);
2958
	my @lock = $SVN::Core::VERSION ge '1.2.0' ? (undef) : ();
2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973

	# 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);

2974 2975 2976 2977 2978
	$reporter->finish_report($pool);
	$pool->clear;
	$editor->{git_commit_ok};
}

2979 2980
# 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)
2981
sub gs_do_switch {
2982 2983
	my ($self, $rev_a, $rev_b, $gs, $url_b, $editor) = @_;
	my $path = $gs->{path};
2984
	my $pool = SVN::Pool->new;
2985 2986 2987 2988

	my $full_url = $self->{url};
	my $old_url = $full_url;
	$full_url .= "/$path" if length $path;
2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000
	my ($ra, $reparented);
	if ($old_url ne $full_url) {
		if ($old_url !~ m#^svn(\+ssh)?://#) {
			SVN::_Ra::svn_ra_reparent($self->{session}, $full_url,
			                          $pool);
			$self->{url} = $full_url;
			$reparented = 1;
		} else {
			$ra = Git::SVN::Ra->new($full_url);
		}
	}
	$ra ||= $self;
3001
	my $reporter = $ra->do_switch($rev_b, '', 1, $url_b, $editor, $pool);
3002
	my @lock = $SVN::Core::VERSION ge '1.2.0' ? (undef) : ();
3003
	$reporter->set_path('', $rev_a, 0, @lock, $pool);
3004
	$reporter->finish_report($pool);
3005

3006 3007 3008 3009
	if ($reparented) {
		SVN::_Ra::svn_ra_reparent($self->{session}, $old_url, $pool);
		$self->{url} = $old_url;
	}
3010

3011 3012 3013 3014
	$pool->clear;
	$editor->{git_commit_ok};
}

3015
sub gs_fetch_loop_common {
3016 3017
	my ($self, $base, $head, $gsv, $globs) = @_;
	return if ($base > $head);
3018
	my $inc = $_log_window_size;
3019
	my ($min, $max) = ($base, $head < $base + $inc ? $head : $base + $inc);
3020
	my %common;
3021 3022 3023
	my $common_max = scalar @$gsv;

	foreach my $gs (@$gsv) {
3024 3025 3026 3027 3028 3029 3030 3031
		my @tmp = split m#/#, $gs->{path};
		my $p = '';
		foreach (@tmp) {
			$p .= length($p) ? "/$_" : $_;
			$common{$p} ||= 0;
			$common{$p}++;
		}
	}
3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043
	$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}++;
		}
	}

3044 3045
	my $longest_path = '';
	foreach (sort {length $b <=> length $a} keys %common) {
3046
		if ($common{$_} == $common_max) {
3047 3048 3049
			$longest_path = $_;
			last;
		}
3050 3051
	}
	while (1) {
3052
		my %revs;
3053
		my $err;
3054
		my $err_handler = $SVN::Error::handler;
3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085
		$SVN::Error::handler = sub {
			($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;
				}
			}
		}
3086
		$SVN::Error::handler = $err_handler;
3087

3088
		my %exists = map { $_->{path} => $_ } @$gsv;
3089
		foreach my $r (sort {$a <=> $b} keys %revs) {
3090
			my ($paths, $logged) = @{$revs{$r}};
3091 3092 3093

			foreach my $gs ($self->match_globs(\%exists, $paths,
			                                   $globs, $r)) {
3094 3095 3096 3097 3098
				if ($gs->rev_db_max >= $r) {
					next;
				}
				next unless $gs->match_paths($paths, $r);
				$gs->{logged_rev_props} = $logged;
3099 3100 3101
				if (my $last_commit = $gs->last_commit) {
					$gs->assert_index_clean($last_commit);
				}
3102 3103
				my $log_entry = $gs->do_fetch($paths, $r);
				if ($log_entry) {
3104 3105 3106
					$gs->do_git_commit($log_entry);
				}
			}
3107
			foreach my $g (@$globs) {
3108 3109 3110
				my $k = "svn-remote.$g->{remote}." .
				        "$g->{t}-maxRev";
				Git::SVN::tmp_config($k, $r);
3111
			}
3112
		}
3113 3114
		# pre-fill the .rev_db since it'll eventually get filled in
		# with '0' x40 if something new gets committed
3115
		foreach my $gs (@$gsv) {
3116 3117 3118
			next if defined $gs->rev_db_get($max);
			$gs->rev_db_set($max, 0 x40);
		}
3119 3120 3121 3122
		foreach my $g (@$globs) {
			my $k = "svn-remote.$g->{remote}.$g->{t}-maxRev";
			Git::SVN::tmp_config($k, $max);
		}
3123 3124 3125 3126 3127 3128 3129
		last if $max >= $head;
		$min = $max + 1;
		$max += $inc;
		$max = $head if ($max > $head);
	}
}

3130 3131
sub match_globs {
	my ($self, $exists, $paths, $globs, $r) = @_;
3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148

	sub get_dir_check {
		my ($self, $exists, $g, $r) = @_;
		my @x = eval { $self->get_dir($g->{path}->{left}, $r) };
		return unless scalar @x == 3;
		my $dirents = $x[0];
		foreach my $de (keys %$dirents) {
			next if $dirents->{$de}->kind != $SVN::Node::dir;
			my $p = $g->{path}->full_path($de);
			next if $exists->{$p};
			next if (length $g->{path}->{right} &&
				 ($self->check_path($p, $r) !=
				  $SVN::Node::dir));
			$exists->{$p} = Git::SVN->init($self->{url}, $p, undef,
					 $g->{ref}->full_path($de), 1);
		}
	}
3149
	foreach my $g (@$globs) {
3150 3151 3152 3153 3154
		if (my $path = $paths->{"/$g->{path}->{left}"}) {
			if ($path->{action} =~ /^[AR]$/) {
				get_dir_check($self, $exists, $g, $r);
			}
		}
3155
		foreach (keys %$paths) {
E
Eric Wong 已提交
3156 3157
			if (/$g->{path}->{left_regex}/ &&
			    !/$g->{path}->{regex}/) {
3158 3159 3160
				next if $paths->{$_}->{action} !~ /^[AR]$/;
				get_dir_check($self, $exists, $g, $r);
			}
3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172
			next unless /$g->{path}->{regex}/;
			my $p = $1;
			my $pathname = $g->{path}->full_path($p);
			next if $exists->{$pathname};
			$exists->{$pathname} = Git::SVN->init(
			                      $self->{url}, $pathname, undef,
			                      $g->{ref}->full_path($p), 1);
		}
		my $c = '';
		foreach (split m#/#, $g->{path}->{left}) {
			$c .= "/$_";
			next unless ($paths->{$c} &&
3173 3174
			             ($paths->{$c}->{action} =~ /^[AR]$/));
			get_dir_check($self, $exists, $g, $r);
3175 3176 3177 3178 3179
		}
	}
	values %$exists;
}

3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192
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;
}

3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211
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;
}

3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224
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) {
3225 3226 3227 3228 3229 3230 3231 3232 3233 3234
		my $err_key = $err->expanded_message;
		# revision numbers change every time, filter them out
		$err_key =~ s/\d+/\0/g;
		$err_key = "$errno\0$err_key";
		unless ($ignored_err{$err_key}) {
			warn "W: Ignoring error from SVN, path probably ",
			     "does not exist: ($errno): ",
			     $err->expanded_message,"\n";
			$ignored_err{$err_key} = 1;
		}
3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257
		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;
}

3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268
package Git::SVN::Log;
use strict;
use warnings;
use POSIX qw/strftime/;
use vars qw/$TZ $limit $color $pager $non_recursive $verbose $oneline
            %rusers $show_commit $incremental/;
my $l_fmt;

sub cmt_showable {
	my ($c) = @_;
	return 1 if defined $c->{r};
3269 3270

	# big commit message got truncated by the 16k pretty buffer in rev-list
3271 3272
	if ($c->{l} && $c->{l}->[-1] eq "...\n" &&
				$c->{a_raw} =~ /\@([a-f\d\-]+)>$/) {
3273
		@{$c->{l}} = ();
3274
		my @log = command(qw/cat-file commit/, $c->{c});
3275 3276 3277

		# shift off the headers
		shift @log while ($log[0] ne '');
3278
		shift @log;
3279 3280 3281

		# TODO: make $c->{l} not have a trailing newline in the future
		@{$c->{l}} = map { "$_\n" } grep !/^git-svn-id: /, @log;
3282 3283

		(undef, $c->{r}, undef) = ::extract_metadata(
3284
				(grep(/^git-svn-id: /, @log))[-1]);
3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325
	}
	return defined $c->{r};
}

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

sub git_svn_log_cmd {
3326 3327 3328 3329 3330 3331 3332 3333 3334
	my ($r_min, $r_max, @args) = @_;
	my $head = 'HEAD';
	foreach my $x (@args) {
		last if $x eq '--';
		next unless ::verify_ref("$x^0");
		$head = $x;
		last;
	}

3335 3336
	my ($url, $rev, $uuid, $gs) = ::working_head_info($head);
	$gs ||= Git::SVN->_new;
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 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390
	my @cmd = (qw/log --abbrev-commit --pretty=raw --default/,
	           $gs->refname);
	push @cmd, '-r' unless $non_recursive;
	push @cmd, qw/--raw --name-status/ if $verbose;
	push @cmd, '--color' if log_use_color();
	return @cmd unless defined $r_max;
	if ($r_max == $r_min) {
		push @cmd, '--max-count=1';
		if (my $c = $gs->rev_db_get($r_max)) {
			push @cmd, $c;
		}
	} else {
		my ($c_min, $c_max);
		$c_max = $gs->rev_db_get($r_max);
		$c_min = $gs->rev_db_get($r_min);
		if (defined $c_min && defined $c_max) {
			if ($r_max > $r_max) {
				push @cmd, "$c_min..$c_max";
			} else {
				push @cmd, "$c_max..$c_min";
			}
		} elsif ($r_max > $r_min) {
			push @cmd, $c_max;
		} else {
			push @cmd, $c_min;
		}
	}
	return @cmd;
}

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

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

3391 3392 3393 3394 3395 3396
sub tz_to_s_offset {
	my ($tz) = @_;
	$tz =~ s/(\d\d)$//;
	return ($1 * 60) + ($tz * 3600);
}

3397 3398 3399 3400 3401
sub get_author_info {
	my ($dest, $author, $t, $tz) = @_;
	$author =~ s/(?:^\s*|\s*$)//g;
	$dest->{a_raw} = $author;
	my $au;
3402
	if ($::_authors) {
3403 3404 3405 3406 3407 3408 3409 3410 3411 3412
		$au = $rusers{$author} || undef;
	}
	if (!$au) {
		($au) = ($author =~ /<([^>]+)\@[^>]+>$/);
	}
	$dest->{t} = $t;
	$dest->{tz} = $tz;
	$dest->{a} = $au;
	# Date::Parse isn't in the standard Perl distro :(
	if ($tz =~ s/^\+//) {
3413
		$t += tz_to_s_offset($tz);
3414
	} elsif ($tz =~ s/^\-//) {
3415
		$t -= tz_to_s_offset($tz);
3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499
	}
	$dest->{t_utc} = $t;
}

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

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

sub show_commit_changed_paths {
	my ($c) = @_;
	return unless $c->{changed};
	print "Changed paths:\n", @{$c->{changed}};
}

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

	if (my $l = $c->{l}) {
		while ($l->[$#$l] eq "\n" && $#$l > 0
		                          && $l->[($#$l - 1)] eq "\n") {
			pop @$l;
		}
		$nr_line = scalar @$l;
		if (!$nr_line) {
			print "1 line\n\n\n";
		} else {
			if ($nr_line == 1) {
				$nr_line = '1 line';
			} else {
				$nr_line .= ' lines';
			}
			print $nr_line, "\n";
			show_commit_changed_paths($c);
			print "\n";
			print $_ foreach @$l;
		}
	} else {
		print "1 line\n";
		show_commit_changed_paths($c);
		print "\n";

	}
3500
	foreach my $x (qw/raw stat diff/) {
3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528
		if ($c->{$x}) {
			print "\n";
			print $_ foreach @{$c->{$x}}
		}
	}
}

sub cmd_show_log {
	my (@args) = @_;
	my ($r_min, $r_max);
	my $r_last = -1; # prevent dupes
	if (defined $TZ) {
		$ENV{TZ} = $TZ;
	} else {
		delete $ENV{TZ};
	}
	if (defined $::_revision) {
		if ($::_revision =~ /^(\d+):(\d+)$/) {
			($r_min, $r_max) = ($1, $2);
		} elsif ($::_revision =~ /^\d+$/) {
			$r_min = $r_max = $::_revision;
		} else {
			::fatal "-r$::_revision is not supported, use ",
				"standard \'git log\' arguments instead\n";
		}
	}

	config_pager();
3529
	@args = (git_svn_log_cmd($r_min, $r_max, @args), @args);
3530 3531
	my $log = command_output_pipe(@args);
	run_pager();
3532
	my (@k, $c, $d, $stat);
3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559
	my $esc_color = qr/(?:\033\[(?:(?:\d+;)*\d*)?m)*/;
	while (<$log>) {
		if (/^${esc_color}commit ($::sha1_short)/o) {
			my $cmt = $1;
			if ($c && cmt_showable($c) && $c->{r} != $r_last) {
				$r_last = $c->{r};
				process_commit($c, $r_min, $r_max, \@k) or
								goto out;
			}
			$d = undef;
			$c = { c => $cmt };
		} elsif (/^${esc_color}author (.+) (\d+) ([\-\+]?\d+)$/o) {
			get_author_info($c, $1, $2, $3);
		} elsif (/^${esc_color}(?:tree|parent|committer) /o) {
			# ignore
		} elsif (/^${esc_color}:\d{6} \d{6} $::sha1_short/o) {
			push @{$c->{raw}}, $_;
		} elsif (/^${esc_color}[ACRMDT]\t/) {
			# we could add $SVN->{svn_path} here, but that requires
			# remote access at the moment (repo_path_split)...
			s#^(${esc_color})([ACRMDT])\t#$1   $2 #o;
			push @{$c->{changed}}, $_;
		} elsif (/^${esc_color}diff /o) {
			$d = 1;
			push @{$c->{diff}}, $_;
		} elsif ($d) {
			push @{$c->{diff}}, $_;
3560 3561 3562 3563 3564 3565 3566
		} 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}}, $_;
			$stat = undef;
3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583
		} elsif (/^${esc_color}    (git-svn-id:.+)$/o) {
			($c->{url}, $c->{r}, undef) = ::extract_metadata($1);
		} elsif (s/^${esc_color}    //o) {
			push @{$c->{l}}, $_;
		}
	}
	if ($c && defined $c->{r} && $c->{r} != $r_last) {
		$r_last = $c->{r};
		process_commit($c, $r_min, $r_max, \@k);
	}
	if (@k) {
		my $swap = $r_max;
		$r_max = $r_min;
		$r_min = $swap;
		process_commit($_, $r_min, $r_max) foreach reverse @k;
	}
out:
3584
	close $log;
3585 3586 3587
	print '-' x72,"\n" unless $incremental || $oneline;
}

3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601
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
3602 3603 3604
# v3.1 layout (auto migrated):
#            - .rev_db => .rev_db.$UUID, .rev_db will remain as a symlink
#              for backwards compatibility
3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615
#
# v4 layout: .git/svn/$repo_id/$id, refs/remotes/$repo_id/$id
#            - this is only created for newly multi-init-ed
#              repositories.  Similar in spirit to the
#              --use-separate-remotes option in git-clone (now default)
#            - we do not automatically migrate to this (following
#              the example set by core git)
use strict;
use warnings;
use Carp qw/croak/;
use File::Path qw/mkpath/;
3616 3617
use File::Basename qw/dirname basename/;
use vars qw/$_minimize/;
3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726

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 $ref_id (sort keys %l_map) {
3727 3728 3729 3730
		eval { Git::SVN->init($l_map{$ref_id}, '', undef, $ref_id) };
		if ($@) {
			Git::SVN->init($l_map{$ref_id}, '', $ref_id, $ref_id);
		}
3731 3732 3733 3734 3735
		$migrated++;
	}
	$migrated;
}

3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754
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};
3755
		$root_path =~ s#^\Q$ra->{repos_root}\E(/|$)##;
3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797
		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/$x->{ref_id}");
3798
			command_noisy(qw/config --unset/,
3799 3800 3801 3802
			              "$pfx.fetch", '^'. $old_fetch . '$');
			delete $r->{$x->{old_repo_id}}->
			       {fetch}->{$x->{old_path}};
			if (!keys %{$r->{$x->{old_repo_id}}->{fetch}}) {
3803
				command_noisy(qw/config --unset/,
3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819
				              "$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;
	}
}

3820 3821 3822 3823
sub migration_check {
	migrate_from_v0();
	migrate_from_v1();
	migrate_from_v2();
3824
	minimize_connections() if $_minimize;
3825 3826
}

3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858
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});
}

3859 3860 3861 3862 3863 3864 3865 3866
package Git::SVN::GlobSpec;
use strict;
use warnings;

sub new {
	my ($class, $glob) = @_;
	my $re = $glob;
	$re =~ s!/+$!!g; # no need for trailing slashes
3867
	my $nr = ($re =~ s!^(.*)\*(.*)$!\(\[^/\]+\)!g);
3868 3869
	my ($left, $right) = ($1, $2);
	if ($nr > 1) {
3870 3871
		die "Only one '*' wildcard expansion ",
		    "is supported (got $nr): '$glob'\n";
3872
	} elsif ($nr == 0) {
3873
		die "One '*' is needed for glob: '$glob'\n";
3874 3875
	}
	$re = quotemeta($left) . $re . quotemeta($right);
3876 3877 3878 3879 3880 3881
	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";
	}
3882 3883
	my $left_re = qr/^\/\Q$left\E(\/|$)/;
	bless { left => $left, right => $right, left_regex => $left_re,
3884 3885 3886 3887 3888 3889 3890 3891 3892
	        regex => qr/$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
3893 3894 3895 3896
__END__

Data structures:

3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923

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

3924
$log_entry hashref as returned by libsvn_log_entry()
E
Eric Wong 已提交
3925
{
3926
	log => 'whitespace-formatted log entry
E
Eric Wong 已提交
3927 3928 3929 3930 3931 3932
',						# trailing newline is preserved
	revision => '8',			# integer
	date => '2004-02-24T17:01:44.108345Z',	# commit date
	author => 'committer name'
};

3933 3934

# this is generated by generate_diff();
E
Eric Wong 已提交
3935 3936 3937 3938 3939 3940 3941 3942
@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,
3943
	chg => change type [MCRADT],
E
Eric Wong 已提交
3944 3945 3946 3947
	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)
}
;
3948

3949 3950 3951 3952 3953 3954 3955 3956 3957 3958
# 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',
	},
}

3959 3960 3961
Notes:
	I don't trust the each() function on unless I created %hash myself
	because the internal iterator may not have started at base.