[thirdparty/git.git] / perl / Git / SVN / Ra.pm

package Git::SVN::Ra;
use vars qw/@ISA $config_dir $_ignore_refs_regex $_log_window_size/;
use strict;
use warnings;
use SVN::Client;
use SVN::Ra;
BEGIN {
	@ISA = qw(SVN::Ra);
}

my ($ra_invalid, $can_do_switch, %ignored_err, $RA);

BEGIN {
	# enforce temporary pool usage for some simple functions
	no strict 'refs';
	for my $f (qw/rev_proplist get_latest_revnum get_uuid get_repos_root
	              get_file/) {
		my $SUPER = "SUPER::$f";
		*$f = sub {
			my $self = shift;
			my $pool = SVN::Pool->new;
			my @ret = $self->$SUPER(@_,$pool);
			$pool->clear;
			wantarray ? @ret : $ret[0];
		};
	}
}

sub _auth_providers () {
	my @rv = (
	  SVN::Client::get_simple_provider(),
	  SVN::Client::get_ssl_server_trust_file_provider(),
	  SVN::Client::get_simple_prompt_provider(
	    \&Git::SVN::Prompt::simple, 2),
	  SVN::Client::get_ssl_client_cert_file_provider(),
	  SVN::Client::get_ssl_client_cert_prompt_provider(
	    \&Git::SVN::Prompt::ssl_client_cert, 2),
	  SVN::Client::get_ssl_client_cert_pw_file_provider(),
	  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)
	);

	# earlier 1.6.x versions would segfault, and <= 1.5.x didn't have
	# this function
	if (::compare_svn_version('1.6.15') >= 0) {
		my $config = SVN::Core::config_get_config($config_dir);
		my ($p, @a);
		# config_get_config returns all config files from
		# ~/.subversion, auth_get_platform_specific_client_providers
		# just wants the config "file".
		@a = ($config->{'config'}, undef);
		$p = SVN::Core::auth_get_platform_specific_client_providers(@a);
		# Insert the return value from
		# auth_get_platform_specific_providers
		unshift @rv, @$p;
	}
	\@rv;
}

sub escape_uri_only {
	my ($uri) = @_;
	my @tmp;
	foreach (split m{/}, $uri) {
		s/([^~\w.%+-]|%(?![a-fA-F0-9]{2}))/sprintf("%%%02X",ord($1))/eg;
		push @tmp, $_;
	}
	join('/', @tmp);
}

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

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

	::_req_svn();

	SVN::_Core::svn_config_ensure($config_dir, undef);
	my ($baton, $callbacks) = SVN::Core::auth_open_helper(_auth_providers);
	my $config = SVN::Core::config_get_config($config_dir);
	$RA = undef;
	my $dont_store_passwords = 1;
	my $conf_t = ${$config}{'config'};
	{
		no warnings 'once';
		# The usage of $SVN::_Core::SVN_CONFIG_* variables
		# produces warnings that variables are used only once.
		# I had not found the better way to shut them up, so
		# the warnings of type 'once' are disabled in this block.
		if (SVN::_Core::svn_config_get_bool($conf_t,
		    $SVN::_Core::SVN_CONFIG_SECTION_AUTH,
		    $SVN::_Core::SVN_CONFIG_OPTION_STORE_PASSWORDS,
		    1) == 0) {
			SVN::_Core::svn_auth_set_parameter($baton,
			    $SVN::_Core::SVN_AUTH_PARAM_DONT_STORE_PASSWORDS,
			    bless (\$dont_store_passwords, "_p_void"));
		}
		if (SVN::_Core::svn_config_get_bool($conf_t,
		    $SVN::_Core::SVN_CONFIG_SECTION_AUTH,
		    $SVN::_Core::SVN_CONFIG_OPTION_STORE_AUTH_CREDS,
		    1) == 0) {
			$Git::SVN::Prompt::_no_auth_cache = 1;
		}
	} # no warnings 'once'
	my $self = SVN::Ra->new(url => escape_url($url), auth => $baton,
	                      config => $config,
			      pool => SVN::Pool->new,
	                      auth_provider_callbacks => $callbacks);
	$self->{url} = $url;
	$self->{svn_path} = $url;
	$self->{repos_root} = $self->get_repos_root;
	$self->{svn_path} =~ s#^\Q$self->{repos_root}\E(/|$)##;
	$self->{cache} = { check_path => { r => 0, data => {} },
	                   get_dir => { r => 0, data => {} } };
	$RA = bless $self, $class;
}

sub check_path {
	my ($self, $path, $r) = @_;
	my $cache = $self->{cache}->{check_path};
	if ($r == $cache->{r} && exists $cache->{data}->{$path}) {
		return $cache->{data}->{$path};
	}
	my $pool = SVN::Pool->new;
	my $t = $self->SUPER::check_path($path, $r, $pool);
	$pool->clear;
	if ($r != $cache->{r}) {
		%{$cache->{data}} = ();
		$cache->{r} = $r;
	}
	$cache->{data}->{$path} = $t;
}

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

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

# get_log(paths, start, end, limit,
#         discover_changed_paths, strict_node_history, receiver)
sub get_log {
	my ($self, @args) = @_;
	my $pool = SVN::Pool->new;

	# 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...
	my $receiver = pop @args;
	my $prefix = "/".$self->{svn_path};
	$prefix =~ s#/+($)##;
	my $prefix_regex = qr#^\Q$prefix\E#;
	push(@args, sub {
		my ($paths) = $_[0];
		return &$receiver(@_) unless $paths;
		$_[0] = ();
		foreach my $p (keys %$paths) {
			my $i = $paths->{$p};
			# Make path relative to our url, not repos_root
			$p =~ s/$prefix_regex//;
			my %s = map { $_ => $i->$_; }
				qw/copyfrom_path copyfrom_rev action/;
			if ($s{'copyfrom_path'}) {
				$s{'copyfrom_path'} =~ s/$prefix_regex//;
			}
			$_[0]{$p} = \%s;
		}
		&$receiver(@_);
	});


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

sub trees_match {
	my ($self, $url1, $rev1, $url2, $rev2) = @_;
	my $ctx = SVN::Client->new(auth => _auth_providers);
	my $out = IO::File->new_tmpfile;

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

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

	$ret;
}

sub get_commit_editor {
	my ($self, $log, $cb, $pool) = @_;

	my @lock = (::compare_svn_version('1.2.0') >= 0) ? (undef, 0) : ();
	$self->SUPER::get_commit_editor($log, $cb, @lock, $pool);
}

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

	if ($new && -e $gs->{index}) {
		unlink $gs->{index} or die
		  "Couldn't unlink index: $gs->{index}: $!\n";
	}
	my $pool = SVN::Pool->new;
	$editor->set_path_strip($path);
	my (@pc) = split m#/#, $path;
	my $reporter = $self->do_update($rev_b, (@pc ? shift @pc : ''),
	                                1, $editor, $pool);
	my @lock = (::compare_svn_version('1.2.0') >= 0) ? (undef) : ();

	# 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);

	$reporter->finish_report($pool);
	$pool->clear;
	$editor->{git_commit_ok};
}

# 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)
sub gs_do_switch {
	my ($self, $rev_a, $rev_b, $gs, $url_b, $editor) = @_;
	my $path = $gs->{path};
	my $pool = SVN::Pool->new;

	my $full_url = $self->{url};
	my $old_url = $full_url;
	$full_url .= '/' . $path if length $path;
	my ($ra, $reparented);

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

	$ra ||= $self;
	$url_b = escape_url($url_b);
	my $reporter = $ra->do_switch($rev_b, '', 1, $url_b, $editor, $pool);
	my @lock = (::compare_svn_version('1.2.0') >= 0) ? (undef) : ();
	$reporter->set_path('', $rev_a, 0, @lock, $pool);
	$reporter->finish_report($pool);

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

	$pool->clear;
	$editor->{git_commit_ok};
}

sub longest_common_path {
	my ($gsv, $globs) = @_;
	my %common;
	my $common_max = scalar @$gsv;

	foreach my $gs (@$gsv) {
		my @tmp = split m#/#, $gs->{path};
		my $p = '';
		foreach (@tmp) {
			$p .= length($p) ? "/$_" : $_;
			$common{$p} ||= 0;
			$common{$p}++;
		}
	}
	$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}++;
		}
	}

	my $longest_path = '';
	foreach (sort {length $b <=> length $a} keys %common) {
		if ($common{$_} == $common_max) {
			$longest_path = $_;
			last;
		}
	}
	$longest_path;
}

sub gs_fetch_loop_common {
	my ($self, $base, $head, $gsv, $globs) = @_;
	return if ($base > $head);
	my $inc = $_log_window_size;
	my ($min, $max) = ($base, $head < $base + $inc ? $head : $base + $inc);
	my $longest_path = longest_common_path($gsv, $globs);
	my $ra_url = $self->{url};
	my $find_trailing_edge;
	while (1) {
		my %revs;
		my $err;
		my $err_handler = $SVN::Error::handler;
		$SVN::Error::handler = sub {
			($err) = @_;
			skip_unknown_revs($err);
		};
		sub _cb {
			my ($paths, $r, $author, $date, $log) = @_;
			[ $paths,
			  { author => $author, date => $date, log => $log } ];
		}
		$self->get_log([$longest_path], $min, $max, 0, 1, 1,
		               sub { $revs{$_[1]} = _cb(@_) });
		if ($err) {
			print "Checked through r$max\r";
		} else {
			$find_trailing_edge = 1;
		}
		if ($err and $find_trailing_edge) {
			print STDERR "Path '$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;
				}
			}
			$find_trailing_edge = 0;
		}
		$SVN::Error::handler = $err_handler;

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

			foreach my $gs ($self->match_globs(\%exists, $paths,
			                                   $globs, $r)) {
				if ($gs->rev_map_max >= $r) {
					next;
				}
				next unless $gs->match_paths($paths, $r);
				$gs->{logged_rev_props} = $logged;
				if (my $last_commit = $gs->last_commit) {
					$gs->assert_index_clean($last_commit);
				}
				my $log_entry = $gs->do_fetch($paths, $r);
				if ($log_entry) {
					$gs->do_git_commit($log_entry);
				}
				$Git::SVN::INDEX_FILES{$gs->{index}} = 1;
			}
			foreach my $g (@$globs) {
				my $k = "svn-remote.$g->{remote}." .
				        "$g->{t}-maxRev";
				Git::SVN::tmp_config($k, $r);
			}
			if ($ra_invalid) {
				$_[0] = undef;
				$self = undef;
				$RA = undef;
				$self = Git::SVN::Ra->new($ra_url);
				$ra_invalid = undef;
			}
		}
		# pre-fill the .rev_db since it'll eventually get filled in
		# with '0' x40 if something new gets committed
		foreach my $gs (@$gsv) {
			next if $gs->rev_map_max >= $max;
			next if defined $gs->rev_map_get($max);
			$gs->rev_map_set($max, 0 x40);
		}
		foreach my $g (@$globs) {
			my $k = "svn-remote.$g->{remote}.$g->{t}-maxRev";
			Git::SVN::tmp_config($k, $max);
		}
		last if $max >= $head;
		$min = $max + 1;
		$max += $inc;
		$max = $head if ($max > $head);
	}
	Git::SVN::gc();
}

sub get_dir_globbed {
	my ($self, $left, $depth, $r) = @_;

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

# return value: 0 -- don't ignore, 1 -- ignore
sub is_ref_ignored {
	my ($g, $p) = @_;
	my $refname = $g->{ref}->full_path($p);
	return 1 if defined($g->{ignore_refs_regex}) &&
	            $refname =~ m!$g->{ignore_refs_regex}!;
	return 0 unless defined($_ignore_refs_regex);
	return 1 if $refname =~ m!$_ignore_refs_regex!o;
	return 0;
}

sub match_globs {
	my ($self, $exists, $paths, $globs, $r) = @_;

	sub get_dir_check {
		my ($self, $exists, $g, $r) = @_;

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

		foreach my $de (@dirs) {
			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));
			next unless $p =~ /$g->{path}->{regex}/;
			$exists->{$p} = Git::SVN->init($self->{url}, $p, undef,
					 $g->{ref}->full_path($de), 1);
		}
	}
	foreach my $g (@$globs) {
		if (my $path = $paths->{"/$g->{path}->{left}"}) {
			if ($path->{action} =~ /^[AR]$/) {
				get_dir_check($self, $exists, $g, $r);
			}
		}
		foreach (keys %$paths) {
			if (/$g->{path}->{left_regex}/ &&
			    !/$g->{path}->{regex}/) {
				next if $paths->{$_}->{action} !~ /^[AR]$/;
				get_dir_check($self, $exists, $g, $r);
			}
			next unless /$g->{path}->{regex}/;
			my $p = $1;
			my $pathname = $g->{path}->full_path($p);
			next if is_ref_ignored($g, $p);
			next if $exists->{$pathname};
			next if ($self->check_path($pathname, $r) !=
			         $SVN::Node::dir);
			$exists->{$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} &&
			             ($paths->{$c}->{action} =~ /^[AR]$/));
			get_dir_check($self, $exists, $g, $r);
		}
	}
	values %$exists;
}

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 {
			my $ra = (ref $self)->new($url);
			my $latest = $ra->get_latest_revnum;
			$ra->get_log("", $latest, 0, 1, 0, 1, sub {});
		};
	} while ($@ && ($c = shift @components));
	$url;
}

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;
}

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) {
		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";
			warn "W: Do not be alarmed at the above message ",
			     "git-svn is just searching aggressively for ",
			     "old history.\n",
			     "This may take a while on large repositories\n";
			$ignored_err{$err_key} = 1;
		}
		return;
	}
	die "Error from SVN, ($errno): ", $err->expanded_message,"\n";
}

1;
__END__

Git::SVN::Ra - Subversion remote access functions for git-svn

=head1 SYNOPSIS

    use Git::SVN::Ra;

    my $ra = Git::SVN::Ra->new($branchurl);
    my ($dirents, $fetched_revnum, $props) =
        $ra->get_dir('.', $SVN::Core::INVALID_REVNUM);

=head1 DESCRIPTION

This is a wrapper around the L<SVN::Ra> module for use by B<git-svn>.
It fills in some default parameters (such as the authentication
scheme), smooths over incompatibilities between libsvn versions, adds
caching, and implements some functions specific to B<git-svn>.

Do not use it unless you are developing git-svn.  The interface will
change as git-svn evolves.

=head1 DEPENDENCIES

Subversion perl bindings,
L<Git::SVN>.

C<Git::SVN::Ra> has not been tested using callers other than
B<git-svn> itself.

=head1 SEE ALSO

L<SVN::Ra>.

=head1 INCOMPATIBILITIES

None reported.

=head1 BUGS

None.
Commit	Line	Data
9f7ad147 JN	1	package Git::SVN::Ra;
	2	use vars qw/@ISA $config_dir $_ignore_refs_regex $_log_window_size/;
	3	use strict;
	4	use warnings;
	5	use SVN::Client;
	6	use SVN::Ra;
	7	BEGIN {
	8	@ISA = qw(SVN::Ra);
	9	}
	10
	11	my ($ra_invalid, $can_do_switch, %ignored_err, $RA);
	12
	13	BEGIN {
	14	# enforce temporary pool usage for some simple functions
	15	no strict 'refs';
	16	for my $f (qw/rev_proplist get_latest_revnum get_uuid get_repos_root
	17	get_file/) {
	18	my $SUPER = "SUPER::$f";
	19	*$f = sub {
	20	my $self = shift;
	21	my $pool = SVN::Pool->new;
	22	my @ret = $self->$SUPER(@_,$pool);
	23	$pool->clear;
	24	wantarray ? @ret : $ret[0];
	25	};
	26	}
	27	}
	28
	29	sub _auth_providers () {
	30	my @rv = (
	31	SVN::Client::get_simple_provider(),
	32	SVN::Client::get_ssl_server_trust_file_provider(),
	33	SVN::Client::get_simple_prompt_provider(
	34	\&Git::SVN::Prompt::simple, 2),
	35	SVN::Client::get_ssl_client_cert_file_provider(),
	36	SVN::Client::get_ssl_client_cert_prompt_provider(
	37	\&Git::SVN::Prompt::ssl_client_cert, 2),
	38	SVN::Client::get_ssl_client_cert_pw_file_provider(),
	39	SVN::Client::get_ssl_client_cert_pw_prompt_provider(
	40	\&Git::SVN::Prompt::ssl_client_cert_pw, 2),
	41	SVN::Client::get_username_provider(),
	42	SVN::Client::get_ssl_server_trust_prompt_provider(
	43	\&Git::SVN::Prompt::ssl_server_trust),
	44	SVN::Client::get_username_prompt_provider(
	45	\&Git::SVN::Prompt::username, 2)
	46	);
	47
	48	# earlier 1.6.x versions would segfault, and <= 1.5.x didn't have
	49	# this function
	50	if (::compare_svn_version('1.6.15') >= 0) {
	51	my $config = SVN::Core::config_get_config($config_dir);
	52	my ($p, @a);
	53	# config_get_config returns all config files from
	54	# ~/.subversion, auth_get_platform_specific_client_providers
	55	# just wants the config "file".
	56	@a = ($config->{'config'}, undef);
	57	$p = SVN::Core::auth_get_platform_specific_client_providers(@a);
	58	# Insert the return value from
	59	# auth_get_platform_specific_providers
	60	unshift @rv, @$p;
	61	}
	62	\@rv;
	63	}
	64
65	sub escape_uri_only {
66	my ($uri) = @_;
67	my @tmp;
68	foreach (split m{/}, $uri) {
69	s/([^~\w.%+-]\|%(?![a-fA-F0-9]{2}))/sprintf("%%%02X",ord($1))/eg;
70	push @tmp, $_;
71	}
72	join('/', @tmp);
73	}
74
75	sub escape_url {
76	my ($url) = @_;
77	if ($url =~ m#^(https?)://([^/]+)(.*)$#) {
78	my ($scheme, $domain, $uri) = ($1, $2, escape_uri_only($3));
79	$url = "$scheme://$domain$uri";
80	}
81	$url;
82	}
83
84	sub new {
85	my ($class, $url) = @_;
86	$url =~ s!/+$!!;
87	return $RA if ($RA && $RA->{url} eq $url);
88
89	::_req_svn();
90
91	SVN::_Core::svn_config_ensure($config_dir, undef);
92	my ($baton, $callbacks) = SVN::Core::auth_open_helper(_auth_providers);
93	my $config = SVN::Core::config_get_config($config_dir);
94	$RA = undef;
95	my $dont_store_passwords = 1;
96	my $conf_t = ${$config}{'config'};
97	{
98	no warnings 'once';
99	# The usage of $SVN::_Core::SVN_CONFIG_* variables
100	# produces warnings that variables are used only once.
101	# I had not found the better way to shut them up, so
102	# the warnings of type 'once' are disabled in this block.
103	if (SVN::_Core::svn_config_get_bool($conf_t,
104	$SVN::_Core::SVN_CONFIG_SECTION_AUTH,
105	$SVN::_Core::SVN_CONFIG_OPTION_STORE_PASSWORDS,
106	1) == 0) {
107	SVN::_Core::svn_auth_set_parameter($baton,
108	$SVN::_Core::SVN_AUTH_PARAM_DONT_STORE_PASSWORDS,
109	bless (\$dont_store_passwords, "_p_void"));
110	}
111	if (SVN::_Core::svn_config_get_bool($conf_t,
112	$SVN::_Core::SVN_CONFIG_SECTION_AUTH,
113	$SVN::_Core::SVN_CONFIG_OPTION_STORE_AUTH_CREDS,
114	1) == 0) {
115	$Git::SVN::Prompt::_no_auth_cache = 1;
116	}
117	} # no warnings 'once'
118	my $self = SVN::Ra->new(url => escape_url($url), auth => $baton,
119	config => $config,
120	pool => SVN::Pool->new,
121	auth_provider_callbacks => $callbacks);
122	$self->{url} = $url;
123	$self->{svn_path} = $url;
124	$self->{repos_root} = $self->get_repos_root;
125	$self->{svn_path} =~ s#^\Q$self->{repos_root}\E(/\|$)##;
126	$self->{cache} = { check_path => { r => 0, data => {} },
127	get_dir => { r => 0, data => {} } };
128	$RA = bless $self, $class;
129	}
130
131	sub check_path {
132	my ($self, $path, $r) = @_;
133	my $cache = $self->{cache}->{check_path};
134	if ($r == $cache->{r} && exists $cache->{data}->{$path}) {
135	return $cache->{data}->{$path};
136	}
137	my $pool = SVN::Pool->new;
138	my $t = $self->SUPER::check_path($path, $r, $pool);
139	$pool->clear;
140	if ($r != $cache->{r}) {
141	%{$cache->{data}} = ();
142	$cache->{r} = $r;
143	}
144	$cache->{data}->{$path} = $t;
145	}
146
147	sub get_dir {
148	my ($self, $dir, $r) = @_;
149	my $cache = $self->{cache}->{get_dir};
150	if ($r == $cache->{r}) {
151	if (my $x = $cache->{data}->{$dir}) {
152	return wantarray ? @$x : $x->[0];
153	}
154	}
155	my $pool = SVN::Pool->new;
156	my ($d, undef, $props) = $self->SUPER::get_dir($dir, $r, $pool);
157	my %dirents = map { $_ => { kind => $d->{$_}->kind } } keys %$d;
158	$pool->clear;
159	if ($r != $cache->{r}) {
160	%{$cache->{data}} = ();
161	$cache->{r} = $r;
162	}
163	$cache->{data}->{$dir} = [ \%dirents, $r, $props ];
164	wantarray ? (\%dirents, $r, $props) : \%dirents;
165	}
166
167	sub DESTROY {
168	# do not call the real DESTROY since we store ourselves in $RA
169	}
170
171	# get_log(paths, start, end, limit,
172	# discover_changed_paths, strict_node_history, receiver)
173	sub get_log {
174	my ($self, @args) = @_;
175	my $pool = SVN::Pool->new;
176
177	# svn_log_changed_path_t objects passed to get_log are likely to be
178	# overwritten even if only the refs are copied to an external variable,
179	# so we should dup the structures in their entirety. Using an
180	# externally passed pool (instead of our temporary and quickly cleared
181	# pool in Git::SVN::Ra) does not help matters at all...
182	my $receiver = pop @args;
183	my $prefix = "/".$self->{svn_path};
184	$prefix =~ s#/+($)##;
185	my $prefix_regex = qr#^\Q$prefix\E#;
186	push(@args, sub {
187	my ($paths) = $_[0];
188	return &$receiver(@_) unless $paths;
189	$_[0] = ();
190	foreach my $p (keys %$paths) {
191	my $i = $paths->{$p};
192	# Make path relative to our url, not repos_root
193	$p =~ s/$prefix_regex//;
194	my %s = map { $_ => $i->$_; }
195	qw/copyfrom_path copyfrom_rev action/;
196	if ($s{'copyfrom_path'}) {
197	$s{'copyfrom_path'} =~ s/$prefix_regex//;
198	}
199	$_[0]{$p} = \%s;
200	}
201	&$receiver(@_);
202	});
203
204
205	# the limit parameter was not supported in SVN 1.1.x, so we
206	# drop it. Therefore, the receiver callback passed to it
207	# is made aware of this limitation by being wrapped if
208	# the limit passed to is being wrapped.
209	if (::compare_svn_version('1.2.0') <= 0) {
210	my $limit = splice(@args, 3, 1);
211	if ($limit > 0) {
212	my $receiver = pop @args;
213	push(@args, sub { &$receiver(@_) if (--$limit >= 0) });
214	}
215	}
216	my $ret = $self->SUPER::get_log(@args, $pool);
217	$pool->clear;
218	$ret;
219	}
220
221	sub trees_match {
222	my ($self, $url1, $rev1, $url2, $rev2) = @_;
223	my $ctx = SVN::Client->new(auth => _auth_providers);
224	my $out = IO::File->new_tmpfile;
225
226	# older SVN (1.1.x) doesn't take $pool as the last parameter for
227	# $ctx->diff(), so we'll create a default one
228	my $pool = SVN::Pool->new_default_sub;
229
230	$ra_invalid = 1; # this will open a new SVN::Ra connection to $url1
231	$ctx->diff([], $url1, $rev1, $url2, $rev2, 1, 1, 0, $out, $out);
232	$out->flush;
233	my $ret = (($out->stat)[7] == 0);
234	close $out or croak $!;
235
236	$ret;
237	}
238
239	sub get_commit_editor {
240	my ($self, $log, $cb, $pool) = @_;
241
242	my @lock = (::compare_svn_version('1.2.0') >= 0) ? (undef, 0) : ();
243	$self->SUPER::get_commit_editor($log, $cb, @lock, $pool);
244	}
245
246	sub gs_do_update {
247	my ($self, $rev_a, $rev_b, $gs, $editor) = @_;
248	my $new = ($rev_a == $rev_b);
249	my $path = $gs->{path};
250
251	if ($new && -e $gs->{index}) {
252	unlink $gs->{index} or die
253	"Couldn't unlink index: $gs->{index}: $!\n";
254	}
255	my $pool = SVN::Pool->new;
256	$editor->set_path_strip($path);
257	my (@pc) = split m#/#, $path;
258	my $reporter = $self->do_update($rev_b, (@pc ? shift @pc : ''),
259	1, $editor, $pool);
260	my @lock = (::compare_svn_version('1.2.0') >= 0) ? (undef) : ();
261
262	# Since we can't rely on svn_ra_reparent being available, we'll
263	# just have to do some magic with set_path to make it so
264	# we only want a partial path.
265	my $sp = '';
266	my $final = join('/', @pc);
267	while (@pc) {
268	$reporter->set_path($sp, $rev_b, 0, @lock, $pool);
269	$sp .= '/' if length $sp;
270	$sp .= shift @pc;
271	}
272	die "BUG: '$sp' != '$final'\n" if ($sp ne $final);
273
274	$reporter->set_path($sp, $rev_a, $new, @lock, $pool);
275
276	$reporter->finish_report($pool);
277	$pool->clear;
278	$editor->{git_commit_ok};
279	}
280
281	# this requires SVN 1.4.3 or later (do_switch didn't work before 1.4.3, and
282	# svn_ra_reparent didn't work before 1.4)
283	sub gs_do_switch {
284	my ($self, $rev_a, $rev_b, $gs, $url_b, $editor) = @_;
285	my $path = $gs->{path};
286	my $pool = SVN::Pool->new;
287
288	my $full_url = $self->{url};
289	my $old_url = $full_url;
290	$full_url .= '/' . $path if length $path;
291	my ($ra, $reparented);
292
293	if ($old_url =~ m#^svn(\+ssh)?://# \|\|
294	($full_url =~ m#^https?://# &&
295	escape_url($full_url) ne $full_url)) {
296	$_[0] = undef;
297	$self = undef;
298	$RA = undef;
299	$ra = Git::SVN::Ra->new($full_url);
300	$ra_invalid = 1;
301	} elsif ($old_url ne $full_url) {
302	SVN::_Ra::svn_ra_reparent($self->{session}, $full_url, $pool);
303	$self->{url} = $full_url;
304	$reparented = 1;
305	}
306
307	$ra \|\|= $self;
308	$url_b = escape_url($url_b);
309	my $reporter = $ra->do_switch($rev_b, '', 1, $url_b, $editor, $pool);
310	my @lock = (::compare_svn_version('1.2.0') >= 0) ? (undef) : ();
311	$reporter->set_path('', $rev_a, 0, @lock, $pool);
312	$reporter->finish_report($pool);
313
314	if ($reparented) {
315	SVN::_Ra::svn_ra_reparent($self->{session}, $old_url, $pool);
316	$self->{url} = $old_url;
317	}
318
319	$pool->clear;
320	$editor->{git_commit_ok};
321	}
322
323	sub longest_common_path {
324	my ($gsv, $globs) = @_;
325	my %common;
326	my $common_max = scalar @$gsv;
327
328	foreach my $gs (@$gsv) {
329	my @tmp = split m#/#, $gs->{path};
330	my $p = '';
331	foreach (@tmp) {
332	$p .= length($p) ? "/$_" : $_;
333	$common{$p} \|\|= 0;
334	$common{$p}++;
335	}
336	}
337	$globs \|\|= [];
338	$common_max += scalar @$globs;
339	foreach my $glob (@$globs) {
340	my @tmp = split m#/#, $glob->{path}->{left};
341	my $p = '';
342	foreach (@tmp) {
343	$p .= length($p) ? "/$_" : $_;
344	$common{$p} \|\|= 0;
345	$common{$p}++;
346	}
347	}
348
349	my $longest_path = '';
350	foreach (sort {length $b <=> length $a} keys %common) {
351	if ($common{$_} == $common_max) {
352	$longest_path = $_;
353	last;
354	}
355	}
356	$longest_path;
357	}
358
359	sub gs_fetch_loop_common {
360	my ($self, $base, $head, $gsv, $globs) = @_;
361	return if ($base > $head);
362	my $inc = $_log_window_size;
363	my ($min, $max) = ($base, $head < $base + $inc ? $head : $base + $inc);
364	my $longest_path = longest_common_path($gsv, $globs);
365	my $ra_url = $self->{url};
366	my $find_trailing_edge;
367	while (1) {
368	my %revs;
369	my $err;
370	my $err_handler = $SVN::Error::handler;
371	$SVN::Error::handler = sub {
372	($err) = @_;
373	skip_unknown_revs($err);
374	};
375	sub _cb {
376	my ($paths, $r, $author, $date, $log) = @_;
377	[ $paths,
378	{ author => $author, date => $date, log => $log } ];
379	}
380	$self->get_log([$longest_path], $min, $max, 0, 1, 1,
381	sub { $revs{$_[1]} = _cb(@_) });
382	if ($err) {
383	print "Checked through r$max\r";
384	} else {
385	$find_trailing_edge = 1;
386	}
387	if ($err and $find_trailing_edge) {
388	print STDERR "Path '$longest_path' ",
389	"was probably deleted:\n",
390	$err->expanded_message,
391	"\nWill attempt to follow ",
392	"revisions r$min .. r$max ",
393	"committed before the deletion\n";
394	my $hi = $max;
395	while (--$hi >= $min) {
396	my $ok;
397	$self->get_log([$longest_path], $min, $hi,
398	0, 1, 1, sub {
399	$ok = $_[1];
400	$revs{$_[1]} = _cb(@_) });
401	if ($ok) {
402	print STDERR "r$min .. r$ok OK\n";
403	last;
404	}
405	}
406	$find_trailing_edge = 0;
407	}
408	$SVN::Error::handler = $err_handler;
409
410	my %exists = map { $_->{path} => $_ } @$gsv;
411	foreach my $r (sort {$a <=> $b} keys %revs) {
412	my ($paths, $logged) = @{$revs{$r}};
413
414	foreach my $gs ($self->match_globs(\%exists, $paths,
415	$globs, $r)) {
416	if ($gs->rev_map_max >= $r) {
417	next;
418	}
419	next unless $gs->match_paths($paths, $r);
420	$gs->{logged_rev_props} = $logged;
421	if (my $last_commit = $gs->last_commit) {
422	$gs->assert_index_clean($last_commit);
423	}
424	my $log_entry = $gs->do_fetch($paths, $r);
425	if ($log_entry) {
426	$gs->do_git_commit($log_entry);
427	}
428	$Git::SVN::INDEX_FILES{$gs->{index}} = 1;
429	}
430	foreach my $g (@$globs) {
431	my $k = "svn-remote.$g->{remote}." .
432	"$g->{t}-maxRev";
433	Git::SVN::tmp_config($k, $r);
434	}
435	if ($ra_invalid) {
436	$_[0] = undef;
437	$self = undef;
438	$RA = undef;
439	$self = Git::SVN::Ra->new($ra_url);
440	$ra_invalid = undef;
441	}
442	}
443	# pre-fill the .rev_db since it'll eventually get filled in
444	# with '0' x40 if something new gets committed
445	foreach my $gs (@$gsv) {
446	next if $gs->rev_map_max >= $max;
447	next if defined $gs->rev_map_get($max);
448	$gs->rev_map_set($max, 0 x40);
449	}
450	foreach my $g (@$globs) {
451	my $k = "svn-remote.$g->{remote}.$g->{t}-maxRev";
452	Git::SVN::tmp_config($k, $max);
453	}
454	last if $max >= $head;
455	$min = $max + 1;
456	$max += $inc;
457	$max = $head if ($max > $head);
458	}
459	Git::SVN::gc();
460	}
461
462	sub get_dir_globbed {
463	my ($self, $left, $depth, $r) = @_;
464
465	my @x = eval { $self->get_dir($left, $r) };
466	return unless scalar @x == 3;
467	my $dirents = $x[0];
468	my @finalents;
469	foreach my $de (keys %$dirents) {
470	next if $dirents->{$de}->{kind} != $SVN::Node::dir;
471	if ($depth > 1) {
472	my @args = ("$left/$de", $depth - 1, $r);
473	foreach my $dir ($self->get_dir_globbed(@args)) {
474	push @finalents, "$de/$dir";
475	}
476	} else {
477	push @finalents, $de;
478	}
479	}
480	@finalents;
481	}
482
483	# return value: 0 -- don't ignore, 1 -- ignore
484	sub is_ref_ignored {
485	my ($g, $p) = @_;
486	my $refname = $g->{ref}->full_path($p);
487	return 1 if defined($g->{ignore_refs_regex}) &&
488	$refname =~ m!$g->{ignore_refs_regex}!;
489	return 0 unless defined($_ignore_refs_regex);
490	return 1 if $refname =~ m!$_ignore_refs_regex!o;
491	return 0;
492	}
493
494	sub match_globs {
495	my ($self, $exists, $paths, $globs, $r) = @_;
496
497	sub get_dir_check {
498	my ($self, $exists, $g, $r) = @_;
499
500	my @dirs = $self->get_dir_globbed($g->{path}->{left},
501	$g->{path}->{depth},
502	$r);
503
504	foreach my $de (@dirs) {
505	my $p = $g->{path}->full_path($de);
506	next if $exists->{$p};
507	next if (length $g->{path}->{right} &&
508	($self->check_path($p, $r) !=
509	$SVN::Node::dir));
510	next unless $p =~ /$g->{path}->{regex}/;
511	$exists->{$p} = Git::SVN->init($self->{url}, $p, undef,
512	$g->{ref}->full_path($de), 1);
513	}
514	}
515	foreach my $g (@$globs) {
516	if (my $path = $paths->{"/$g->{path}->{left}"}) {
517	if ($path->{action} =~ /^[AR]$/) {
518	get_dir_check($self, $exists, $g, $r);
519	}
520	}
521	foreach (keys %$paths) {
522	if (/$g->{path}->{left_regex}/ &&
523	!/$g->{path}->{regex}/) {
524	next if $paths->{$_}->{action} !~ /^[AR]$/;
525	get_dir_check($self, $exists, $g, $r);
526	}
527	next unless /$g->{path}->{regex}/;
528	my $p = $1;
529	my $pathname = $g->{path}->full_path($p);
530	next if is_ref_ignored($g, $p);
531	next if $exists->{$pathname};
532	next if ($self->check_path($pathname, $r) !=
533	$SVN::Node::dir);
534	$exists->{$pathname} = Git::SVN->init(
535	$self->{url}, $pathname, undef,
536	$g->{ref}->full_path($p), 1);
537	}
538	my $c = '';
539	foreach (split m#/#, $g->{path}->{left}) {
540	$c .= "/$_";
541	next unless ($paths->{$c} &&
542	($paths->{$c}->{action} =~ /^[AR]$/));
543	get_dir_check($self, $exists, $g, $r);
544	}
545	}
546	values %$exists;
547	}
548
549	sub minimize_url {
550	my ($self) = @_;
551	return $self->{url} if ($self->{url} eq $self->{repos_root});
552	my $url = $self->{repos_root};
553	my @components = split(m!/!, $self->{svn_path});
554	my $c = '';
555	do {
556	$url .= "/$c" if length $c;
557	eval {
558	my $ra = (ref $self)->new($url);
559	my $latest = $ra->get_latest_revnum;
560	$ra->get_log("", $latest, 0, 1, 0, 1, sub {});
561	};
562	} while ($@ && ($c = shift @components));
563	$url;
564	}
565
566	sub can_do_switch {
567	my $self = shift;
568	unless (defined $can_do_switch) {
569	my $pool = SVN::Pool->new;
570	my $rep = eval {
571	$self->do_switch(1, '', 0, $self->{url},
572	SVN::Delta::Editor->new, $pool);
573	};
574	if ($@) {
575	$can_do_switch = 0;
576	} else {
577	$rep->abort_report($pool);
578	$can_do_switch = 1;
579	}
580	$pool->clear;
581	}
582	$can_do_switch;
583	}
584
585	sub skip_unknown_revs {
586	my ($err) = @_;
587	my $errno = $err->apr_err();
588	# Maybe the branch we're tracking didn't
589	# exist when the repo started, so it's
590	# not an error if it doesn't, just continue
591	#
592	# Wonderfully consistent library, eh?
593	# 160013 - svn:// and file://
594	# 175002 - http(s)://
595	# 175007 - http(s):// (this repo required authorization, too...)
596	# More codes may be discovered later...
597	if ($errno == 175007 \|\| $errno == 175002 \|\| $errno == 160013) {
598	my $err_key = $err->expanded_message;
599	# revision numbers change every time, filter them out
600	$err_key =~ s/\d+/\0/g;
601	$err_key = "$errno\0$err_key";
602	unless ($ignored_err{$err_key}) {
603	warn "W: Ignoring error from SVN, path probably ",
604	"does not exist: ($errno): ",
605	$err->expanded_message,"\n";
606	warn "W: Do not be alarmed at the above message ",
607	"git-svn is just searching aggressively for ",
608	"old history.\n",
609	"This may take a while on large repositories\n";
610	$ignored_err{$err_key} = 1;
611	}
612	return;
613	}
614	die "Error from SVN, ($errno): ", $err->expanded_message,"\n";
615	}
616
617	1;
618	__END__
619
620	Git::SVN::Ra - Subversion remote access functions for git-svn
621
622	=head1 SYNOPSIS
623
624	use Git::SVN::Ra;
625
626	my $ra = Git::SVN::Ra->new($branchurl);
627	my ($dirents, $fetched_revnum, $props) =
628	$ra->get_dir('.', $SVN::Core::INVALID_REVNUM);
629
630	=head1 DESCRIPTION
631
632	This is a wrapper around the L<SVN::Ra> module for use by B<git-svn>.
633	It fills in some default parameters (such as the authentication
634	scheme), smooths over incompatibilities between libsvn versions, adds
635	caching, and implements some functions specific to B<git-svn>.
636
637	Do not use it unless you are developing git-svn. The interface will
638	change as git-svn evolves.
639
640	=head1 DEPENDENCIES
641
642	Subversion perl bindings,
643	L<Git::SVN>.
644
645	C<Git::SVN::Ra> has not been tested using callers other than
646	B<git-svn> itself.
647
648	=head1 SEE ALSO
649
650	L<SVN::Ra>.
651
652	=head1 INCOMPATIBILITIES
653
654	None reported.
655
656	=head1 BUGS
657
658	None.