[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 Git::SVN::Utils qw(
	canonicalize_url
	canonicalize_path
	add_path_to_url
);

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 new {
	my ($class, $url) = @_;
	$url = canonicalize_url($url);
	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 => $url, auth => $baton,
	                      config => $config,
			      pool => SVN::Pool->new,
	                      auth_provider_callbacks => $callbacks);
	$RA = bless $self, $class;

	# Make sure its canonicalized
	$self->url($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 => {} } };

	return $RA;
}

sub url {
	my $self = shift;

	if (@_) {
		my $url = shift;
		$self->{url} = canonicalize_url($url);
		return;
	}

	return $self->{url};
}

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//;
				$s{'copyfrom_path'} = canonicalize_path($s{'copyfrom_path'});
			}
			$_[0]{$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 $old_url = $self->url;
	my $full_url = add_path_to_url( $self->url, $path );
	my ($ra, $reparented);

	if ($old_url =~ m#^svn(\+\w+)?://# ||
	    ($full_url =~ m#^https?://# &&
	     canonicalize_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(
			$self->{session},
			canonicalize_url($full_url),
			$pool
		);
		$self->url($full_url);
		$reparented = 1;
	}

	$ra ||= $self;
	$url_b = canonicalize_url($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 {
		$url = add_path_to_url($url, $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));

	return canonicalize_url($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__

=head1 NAME

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 $_log_window_size/;
	3	use strict;
	4	use warnings;
	5	use SVN::Client;
565e56c2 MS	6	use Git::SVN::Utils qw(
565e56c2 MS	7	canonicalize_url
705b49cb	8	canonicalize_path
d2fd119c	9	add_path_to_url
565e56c2 MS	10	);
565e56c2 MS	11
9f7ad147 JN	12	use SVN::Ra;
	13	BEGIN {
	14	@ISA = qw(SVN::Ra);
	15	}
	16
	17	my ($ra_invalid, $can_do_switch, %ignored_err, $RA);
	18
	19	BEGIN {
	20	# enforce temporary pool usage for some simple functions
	21	no strict 'refs';
	22	for my $f (qw/rev_proplist get_latest_revnum get_uuid get_repos_root
	23	get_file/) {
	24	my $SUPER = "SUPER::$f";
	25	*$f = sub {
	26	my $self = shift;
	27	my $pool = SVN::Pool->new;
	28	my @ret = $self->$SUPER(@_,$pool);
	29	$pool->clear;
	30	wantarray ? @ret : $ret[0];
	31	};
	32	}
	33	}
	34
	35	sub _auth_providers () {
	36	my @rv = (
	37	SVN::Client::get_simple_provider(),
	38	SVN::Client::get_ssl_server_trust_file_provider(),
	39	SVN::Client::get_simple_prompt_provider(
	40	\&Git::SVN::Prompt::simple, 2),
	41	SVN::Client::get_ssl_client_cert_file_provider(),
	42	SVN::Client::get_ssl_client_cert_prompt_provider(
	43	\&Git::SVN::Prompt::ssl_client_cert, 2),
	44	SVN::Client::get_ssl_client_cert_pw_file_provider(),
	45	SVN::Client::get_ssl_client_cert_pw_prompt_provider(
	46	\&Git::SVN::Prompt::ssl_client_cert_pw, 2),
	47	SVN::Client::get_username_provider(),
	48	SVN::Client::get_ssl_server_trust_prompt_provider(
	49	\&Git::SVN::Prompt::ssl_server_trust),
	50	SVN::Client::get_username_prompt_provider(
	51	\&Git::SVN::Prompt::username, 2)
	52	);
	53
	54	# earlier 1.6.x versions would segfault, and <= 1.5.x didn't have
	55	# this function
	56	if (::compare_svn_version('1.6.15') >= 0) {
	57	my $config = SVN::Core::config_get_config($config_dir);
	58	my ($p, @a);
	59	# config_get_config returns all config files from
	60	# ~/.subversion, auth_get_platform_specific_client_providers
	61	# just wants the config "file".
	62	@a = ($config->{'config'}, undef);
	63	$p = SVN::Core::auth_get_platform_specific_client_providers(@a);
	64	# Insert the return value from
	65	# auth_get_platform_specific_providers
	66	unshift @rv, @$p;
	67	}
	68	\@rv;
	69	}
	70
9f7ad147 JN	71
	72	sub new {
	73	my ($class, $url) = @_;
8266fc8b	74	$url = canonicalize_url($url);
b4943dc9	75	return $RA if ($RA && $RA->url eq $url);
9f7ad147 JN	76
	77	::_req_svn();
	78
	79	SVN::_Core::svn_config_ensure($config_dir, undef);
	80	my ($baton, $callbacks) = SVN::Core::auth_open_helper(_auth_providers);
	81	my $config = SVN::Core::config_get_config($config_dir);
	82	$RA = undef;
	83	my $dont_store_passwords = 1;
	84	my $conf_t = ${$config}{'config'};
	85	{
	86	no warnings 'once';
	87	# The usage of $SVN::_Core::SVN_CONFIG_* variables
	88	# produces warnings that variables are used only once.
	89	# I had not found the better way to shut them up, so
	90	# the warnings of type 'once' are disabled in this block.
	91	if (SVN::_Core::svn_config_get_bool($conf_t,
	92	$SVN::_Core::SVN_CONFIG_SECTION_AUTH,
	93	$SVN::_Core::SVN_CONFIG_OPTION_STORE_PASSWORDS,
	94	1) == 0) {
	95	SVN::_Core::svn_auth_set_parameter($baton,
	96	$SVN::_Core::SVN_AUTH_PARAM_DONT_STORE_PASSWORDS,
	97	bless (\$dont_store_passwords, "_p_void"));
	98	}
	99	if (SVN::_Core::svn_config_get_bool($conf_t,
	100	$SVN::_Core::SVN_CONFIG_SECTION_AUTH,
	101	$SVN::_Core::SVN_CONFIG_OPTION_STORE_AUTH_CREDS,
	102	1) == 0) {
	103	$Git::SVN::Prompt::_no_auth_cache = 1;
	104	}
	105	} # no warnings 'once'
705b49cb	106
8266fc8b	107	my $self = SVN::Ra->new(url => $url, auth => $baton,
9f7ad147 JN	108	config => $config,
	109	pool => SVN::Pool->new,
	110	auth_provider_callbacks => $callbacks);
b4943dc9 MS	111	$RA = bless $self, $class;
	112
	113	# Make sure its canonicalized
	114	$self->url($url);
9f7ad147 JN	115	$self->{svn_path} = $url;
	116	$self->{repos_root} = $self->get_repos_root;
	117	$self->{svn_path} =~ s#^\Q$self->{repos_root}\E(/\|$)##;
	118	$self->{cache} = { check_path => { r => 0, data => {} },
	119	get_dir => { r => 0, data => {} } };
b4943dc9 MS	120
	121	return $RA;
	122	}
	123
	124	sub url {
	125	my $self = shift;
	126
	127	if (@_) {
	128	my $url = shift;
565e56c2	129	$self->{url} = canonicalize_url($url);
b4943dc9 MS	130	return;
	131	}
	132
	133	return $self->{url};
9f7ad147 JN	134	}
	135
	136	sub check_path {
	137	my ($self, $path, $r) = @_;
	138	my $cache = $self->{cache}->{check_path};
	139	if ($r == $cache->{r} && exists $cache->{data}->{$path}) {
	140	return $cache->{data}->{$path};
	141	}
	142	my $pool = SVN::Pool->new;
	143	my $t = $self->SUPER::check_path($path, $r, $pool);
	144	$pool->clear;
	145	if ($r != $cache->{r}) {
	146	%{$cache->{data}} = ();
	147	$cache->{r} = $r;
	148	}
	149	$cache->{data}->{$path} = $t;
	150	}
	151
	152	sub get_dir {
	153	my ($self, $dir, $r) = @_;
	154	my $cache = $self->{cache}->{get_dir};
	155	if ($r == $cache->{r}) {
	156	if (my $x = $cache->{data}->{$dir}) {
	157	return wantarray ? @$x : $x->[0];
	158	}
	159	}
	160	my $pool = SVN::Pool->new;
	161	my ($d, undef, $props) = $self->SUPER::get_dir($dir, $r, $pool);
	162	my %dirents = map { $_ => { kind => $d->{$_}->kind } } keys %$d;
	163	$pool->clear;
	164	if ($r != $cache->{r}) {
	165	%{$cache->{data}} = ();
	166	$cache->{r} = $r;
	167	}
	168	$cache->{data}->{$dir} = [ \%dirents, $r, $props ];
	169	wantarray ? (\%dirents, $r, $props) : \%dirents;
	170	}
	171
	172	sub DESTROY {
	173	# do not call the real DESTROY since we store ourselves in $RA
	174	}
	175
	176	# get_log(paths, start, end, limit,
	177	# discover_changed_paths, strict_node_history, receiver)
	178	sub get_log {
	179	my ($self, @args) = @_;
	180	my $pool = SVN::Pool->new;
	181
	182	# svn_log_changed_path_t objects passed to get_log are likely to be
	183	# overwritten even if only the refs are copied to an external variable,
	184	# so we should dup the structures in their entirety. Using an
	185	# externally passed pool (instead of our temporary and quickly cleared
	186	# pool in Git::SVN::Ra) does not help matters at all...
	187	my $receiver = pop @args;
	188	my $prefix = "/".$self->{svn_path};
	189	$prefix =~ s#/+($)##;
	190	my $prefix_regex = qr#^\Q$prefix\E#;
	191	push(@args, sub {
	192	my ($paths) = $_[0];
	193	return &$receiver(@_) unless $paths;
	194	$_[0] = ();
	195	foreach my $p (keys %$paths) {
	196	my $i = $paths->{$p};
	197	# Make path relative to our url, not repos_root
198	$p =~ s/$prefix_regex//;
199	my %s = map { $_ => $i->$_; }
200	qw/copyfrom_path copyfrom_rev action/;
201	if ($s{'copyfrom_path'}) {
202	$s{'copyfrom_path'} =~ s/$prefix_regex//;
705b49cb	203	$s{'copyfrom_path'} = canonicalize_path($s{'copyfrom_path'});
9f7ad147 JN	204	}
	205	$_[0]{$p} = \%s;
	206	}
	207	&$receiver(@_);
	208	});
	209
	210
	211	# the limit parameter was not supported in SVN 1.1.x, so we
	212	# drop it. Therefore, the receiver callback passed to it
	213	# is made aware of this limitation by being wrapped if
	214	# the limit passed to is being wrapped.
	215	if (::compare_svn_version('1.2.0') <= 0) {
	216	my $limit = splice(@args, 3, 1);
	217	if ($limit > 0) {
	218	my $receiver = pop @args;
	219	push(@args, sub { &$receiver(@_) if (--$limit >= 0) });
	220	}
	221	}
	222	my $ret = $self->SUPER::get_log(@args, $pool);
	223	$pool->clear;
	224	$ret;
	225	}
	226
	227	sub trees_match {
	228	my ($self, $url1, $rev1, $url2, $rev2) = @_;
	229	my $ctx = SVN::Client->new(auth => _auth_providers);
	230	my $out = IO::File->new_tmpfile;
	231
	232	# older SVN (1.1.x) doesn't take $pool as the last parameter for
	233	# $ctx->diff(), so we'll create a default one
	234	my $pool = SVN::Pool->new_default_sub;
	235
	236	$ra_invalid = 1; # this will open a new SVN::Ra connection to $url1
	237	$ctx->diff([], $url1, $rev1, $url2, $rev2, 1, 1, 0, $out, $out);
	238	$out->flush;
	239	my $ret = (($out->stat)[7] == 0);
	240	close $out or croak $!;
	241
	242	$ret;
	243	}
	244
	245	sub get_commit_editor {
	246	my ($self, $log, $cb, $pool) = @_;
	247
	248	my @lock = (::compare_svn_version('1.2.0') >= 0) ? (undef, 0) : ();
	249	$self->SUPER::get_commit_editor($log, $cb, @lock, $pool);
	250	}
	251
	252	sub gs_do_update {
	253	my ($self, $rev_a, $rev_b, $gs, $editor) = @_;
	254	my $new = ($rev_a == $rev_b);
6a8d999e	255	my $path = $gs->path;
9f7ad147 JN	256
	257	if ($new && -e $gs->{index}) {
	258	unlink $gs->{index} or die
	259	"Couldn't unlink index: $gs->{index}: $!\n";
	260	}
	261	my $pool = SVN::Pool->new;
	262	$editor->set_path_strip($path);
	263	my (@pc) = split m#/#, $path;
	264	my $reporter = $self->do_update($rev_b, (@pc ? shift @pc : ''),
	265	1, $editor, $pool);
	266	my @lock = (::compare_svn_version('1.2.0') >= 0) ? (undef) : ();
	267
	268	# Since we can't rely on svn_ra_reparent being available, we'll
	269	# just have to do some magic with set_path to make it so
	270	# we only want a partial path.
	271	my $sp = '';
	272	my $final = join('/', @pc);
	273	while (@pc) {
	274	$reporter->set_path($sp, $rev_b, 0, @lock, $pool);
	275	$sp .= '/' if length $sp;
	276	$sp .= shift @pc;
	277	}
	278	die "BUG: '$sp' != '$final'\n" if ($sp ne $final);
	279
	280	$reporter->set_path($sp, $rev_a, $new, @lock, $pool);
	281
	282	$reporter->finish_report($pool);
	283	$pool->clear;
	284	$editor->{git_commit_ok};
	285	}
	286
	287	# this requires SVN 1.4.3 or later (do_switch didn't work before 1.4.3, and
	288	# svn_ra_reparent didn't work before 1.4)
	289	sub gs_do_switch {
	290	my ($self, $rev_a, $rev_b, $gs, $url_b, $editor) = @_;
6a8d999e	291	my $path = $gs->path;
9f7ad147 JN	292	my $pool = SVN::Pool->new;
9f7ad147 JN	293
d2fd119c MS	294	my $old_url = $self->url;
d2fd119c MS	295	my $full_url = add_path_to_url( $self->url, $path );
9f7ad147 JN	296	my ($ra, $reparented);
9f7ad147 JN	297
3747c015	298	if ($old_url =~ m#^svn(\+\w+)?://# \|\|
9f7ad147	299	($full_url =~ m#^https?://# &&
9c27a57b	300	canonicalize_url($full_url) ne $full_url)) {
9f7ad147 JN	301	$_[0] = undef;
	302	$self = undef;
	303	$RA = undef;
	304	$ra = Git::SVN::Ra->new($full_url);
	305	$ra_invalid = 1;
	306	} elsif ($old_url ne $full_url) {
705b49cb MS	307	SVN::_Ra::svn_ra_reparent(
	308	$self->{session},
	309	canonicalize_url($full_url),
	310	$pool
	311	);
b4943dc9	312	$self->url($full_url);
9f7ad147 JN	313	$reparented = 1;
	314	}
	315
	316	$ra \|\|= $self;
9c27a57b	317	$url_b = canonicalize_url($url_b);
9f7ad147 JN	318	my $reporter = $ra->do_switch($rev_b, '', 1, $url_b, $editor, $pool);
	319	my @lock = (::compare_svn_version('1.2.0') >= 0) ? (undef) : ();
	320	$reporter->set_path('', $rev_a, 0, @lock, $pool);
	321	$reporter->finish_report($pool);
	322
	323	if ($reparented) {
	324	SVN::_Ra::svn_ra_reparent($self->{session}, $old_url, $pool);
b4943dc9	325	$self->url($old_url);
9f7ad147 JN	326	}
	327
	328	$pool->clear;
	329	$editor->{git_commit_ok};
	330	}
	331
	332	sub longest_common_path {
	333	my ($gsv, $globs) = @_;
	334	my %common;
	335	my $common_max = scalar @$gsv;
	336
	337	foreach my $gs (@$gsv) {
6a8d999e	338	my @tmp = split m#/#, $gs->path;
9f7ad147 JN	339	my $p = '';
	340	foreach (@tmp) {
	341	$p .= length($p) ? "/$_" : $_;
	342	$common{$p} \|\|= 0;
	343	$common{$p}++;
	344	}
	345	}
	346	$globs \|\|= [];
	347	$common_max += scalar @$globs;
	348	foreach my $glob (@$globs) {
	349	my @tmp = split m#/#, $glob->{path}->{left};
	350	my $p = '';
	351	foreach (@tmp) {
	352	$p .= length($p) ? "/$_" : $_;
	353	$common{$p} \|\|= 0;
	354	$common{$p}++;
	355	}
	356	}
	357
	358	my $longest_path = '';
	359	foreach (sort {length $b <=> length $a} keys %common) {
	360	if ($common{$_} == $common_max) {
	361	$longest_path = $_;
	362	last;
	363	}
	364	}
	365	$longest_path;
	366	}
	367
	368	sub gs_fetch_loop_common {
	369	my ($self, $base, $head, $gsv, $globs) = @_;
	370	return if ($base > $head);
	371	my $inc = $_log_window_size;
	372	my ($min, $max) = ($base, $head < $base + $inc ? $head : $base + $inc);
	373	my $longest_path = longest_common_path($gsv, $globs);
b4943dc9	374	my $ra_url = $self->url;
9f7ad147 JN	375	my $find_trailing_edge;
	376	while (1) {
	377	my %revs;
	378	my $err;
	379	my $err_handler = $SVN::Error::handler;
	380	$SVN::Error::handler = sub {
	381	($err) = @_;
	382	skip_unknown_revs($err);
	383	};
	384	sub _cb {
	385	my ($paths, $r, $author, $date, $log) = @_;
	386	[ $paths,
	387	{ author => $author, date => $date, log => $log } ];
	388	}
	389	$self->get_log([$longest_path], $min, $max, 0, 1, 1,
	390	sub { $revs{$_[1]} = _cb(@_) });
	391	if ($err) {
	392	print "Checked through r$max\r";
	393	} else {
	394	$find_trailing_edge = 1;
	395	}
	396	if ($err and $find_trailing_edge) {
	397	print STDERR "Path '$longest_path' ",
	398	"was probably deleted:\n",
	399	$err->expanded_message,
	400	"\nWill attempt to follow ",
	401	"revisions r$min .. r$max ",
	402	"committed before the deletion\n";
	403	my $hi = $max;
	404	while (--$hi >= $min) {
	405	my $ok;
	406	$self->get_log([$longest_path], $min, $hi,
	407	0, 1, 1, sub {
	408	$ok = $_[1];
	409	$revs{$_[1]} = _cb(@_) });
	410	if ($ok) {
	411	print STDERR "r$min .. r$ok OK\n";
	412	last;
	413	}
	414	}
	415	$find_trailing_edge = 0;
	416	}
	417	$SVN::Error::handler = $err_handler;
	418
f3045919	419	my %exists = map { $_->path => $_ } @$gsv;
9f7ad147 JN	420	foreach my $r (sort {$a <=> $b} keys %revs) {
	421	my ($paths, $logged) = @{$revs{$r}};
	422
	423	foreach my $gs ($self->match_globs(\%exists, $paths,
	424	$globs, $r)) {
	425	if ($gs->rev_map_max >= $r) {
	426	next;
	427	}
	428	next unless $gs->match_paths($paths, $r);
	429	$gs->{logged_rev_props} = $logged;
	430	if (my $last_commit = $gs->last_commit) {
	431	$gs->assert_index_clean($last_commit);
	432	}
	433	my $log_entry = $gs->do_fetch($paths, $r);
	434	if ($log_entry) {
	435	$gs->do_git_commit($log_entry);
	436	}
	437	$Git::SVN::INDEX_FILES{$gs->{index}} = 1;
	438	}
	439	foreach my $g (@$globs) {
	440	my $k = "svn-remote.$g->{remote}." .
	441	"$g->{t}-maxRev";
	442	Git::SVN::tmp_config($k, $r);
	443	}
	444	if ($ra_invalid) {
	445	$_[0] = undef;
	446	$self = undef;
	447	$RA = undef;
	448	$self = Git::SVN::Ra->new($ra_url);
	449	$ra_invalid = undef;
	450	}
	451	}
	452	# pre-fill the .rev_db since it'll eventually get filled in
	453	# with '0' x40 if something new gets committed
	454	foreach my $gs (@$gsv) {
	455	next if $gs->rev_map_max >= $max;
	456	next if defined $gs->rev_map_get($max);
	457	$gs->rev_map_set($max, 0 x40);
	458	}
	459	foreach my $g (@$globs) {
	460	my $k = "svn-remote.$g->{remote}.$g->{t}-maxRev";
	461	Git::SVN::tmp_config($k, $max);
	462	}
	463	last if $max >= $head;
	464	$min = $max + 1;
	465	$max += $inc;
	466	$max = $head if ($max > $head);
	467	}
	468	Git::SVN::gc();
	469	}
	470
	471	sub get_dir_globbed {
	472	my ($self, $left, $depth, $r) = @_;
	473
	474	my @x = eval { $self->get_dir($left, $r) };
	475	return unless scalar @x == 3;
	476	my $dirents = $x[0];
	477	my @finalents;
	478	foreach my $de (keys %$dirents) {
	479	next if $dirents->{$de}->{kind} != $SVN::Node::dir;
	480	if ($depth > 1) {
	481	my @args = ("$left/$de", $depth - 1, $r);
	482	foreach my $dir ($self->get_dir_globbed(@args)) {
	483	push @finalents, "$de/$dir";
484	}
485	} else {
486	push @finalents, $de;
487	}
488	}
489	@finalents;
490	}
491
492	# return value: 0 -- don't ignore, 1 -- ignore
493	sub is_ref_ignored {
494	my ($g, $p) = @_;
495	my $refname = $g->{ref}->full_path($p);
496	return 1 if defined($g->{ignore_refs_regex}) &&
497	$refname =~ m!$g->{ignore_refs_regex}!;
498	return 0 unless defined($_ignore_refs_regex);
499	return 1 if $refname =~ m!$_ignore_refs_regex!o;
500	return 0;
501	}
502
503	sub match_globs {
504	my ($self, $exists, $paths, $globs, $r) = @_;
505
506	sub get_dir_check {
507	my ($self, $exists, $g, $r) = @_;
508
509	my @dirs = $self->get_dir_globbed($g->{path}->{left},
510	$g->{path}->{depth},
511	$r);
512
513	foreach my $de (@dirs) {
514	my $p = $g->{path}->full_path($de);
515	next if $exists->{$p};
516	next if (length $g->{path}->{right} &&
517	($self->check_path($p, $r) !=
518	$SVN::Node::dir));
519	next unless $p =~ /$g->{path}->{regex}/;
b4943dc9	520	$exists->{$p} = Git::SVN->init($self->url, $p, undef,
9f7ad147 JN	521	$g->{ref}->full_path($de), 1);
	522	}
	523	}
	524	foreach my $g (@$globs) {
	525	if (my $path = $paths->{"/$g->{path}->{left}"}) {
	526	if ($path->{action} =~ /^[AR]$/) {
	527	get_dir_check($self, $exists, $g, $r);
	528	}
	529	}
	530	foreach (keys %$paths) {
	531	if (/$g->{path}->{left_regex}/ &&
	532	!/$g->{path}->{regex}/) {
	533	next if $paths->{$_}->{action} !~ /^[AR]$/;
	534	get_dir_check($self, $exists, $g, $r);
	535	}
	536	next unless /$g->{path}->{regex}/;
	537	my $p = $1;
	538	my $pathname = $g->{path}->full_path($p);
	539	next if is_ref_ignored($g, $p);
	540	next if $exists->{$pathname};
	541	next if ($self->check_path($pathname, $r) !=
	542	$SVN::Node::dir);
	543	$exists->{$pathname} = Git::SVN->init(
b4943dc9	544	$self->url, $pathname, undef,
9f7ad147 JN	545	$g->{ref}->full_path($p), 1);
	546	}
	547	my $c = '';
	548	foreach (split m#/#, $g->{path}->{left}) {
	549	$c .= "/$_";
	550	next unless ($paths->{$c} &&
	551	($paths->{$c}->{action} =~ /^[AR]$/));
	552	get_dir_check($self, $exists, $g, $r);
	553	}
	554	}
	555	values %$exists;
	556	}
	557
	558	sub minimize_url {
	559	my ($self) = @_;
b4943dc9	560	return $self->url if ($self->url eq $self->{repos_root});
9f7ad147 JN	561	my $url = $self->{repos_root};
	562	my @components = split(m!/!, $self->{svn_path});
	563	my $c = '';
	564	do {
d2fd119c	565	$url = add_path_to_url($url, $c);
9f7ad147 JN	566	eval {
	567	my $ra = (ref $self)->new($url);
	568	my $latest = $ra->get_latest_revnum;
	569	$ra->get_log("", $latest, 0, 1, 0, 1, sub {});
	570	};
	571	} while ($@ && ($c = shift @components));
9c27a57b MS	572
9c27a57b MS	573	return canonicalize_url($url);
9f7ad147 JN	574	}
	575
	576	sub can_do_switch {
	577	my $self = shift;
	578	unless (defined $can_do_switch) {
	579	my $pool = SVN::Pool->new;
	580	my $rep = eval {
b4943dc9	581	$self->do_switch(1, '', 0, $self->url,
9f7ad147 JN	582	SVN::Delta::Editor->new, $pool);
	583	};
	584	if ($@) {
	585	$can_do_switch = 0;
	586	} else {
	587	$rep->abort_report($pool);
	588	$can_do_switch = 1;
	589	}
	590	$pool->clear;
	591	}
	592	$can_do_switch;
	593	}
	594
	595	sub skip_unknown_revs {
	596	my ($err) = @_;
	597	my $errno = $err->apr_err();
	598	# Maybe the branch we're tracking didn't
	599	# exist when the repo started, so it's
	600	# not an error if it doesn't, just continue
	601	#
	602	# Wonderfully consistent library, eh?
	603	# 160013 - svn:// and file://
	604	# 175002 - http(s)://
	605	# 175007 - http(s):// (this repo required authorization, too...)
	606	# More codes may be discovered later...
	607	if ($errno == 175007 \|\| $errno == 175002 \|\| $errno == 160013) {
	608	my $err_key = $err->expanded_message;
	609	# revision numbers change every time, filter them out
	610	$err_key =~ s/\d+/\0/g;
	611	$err_key = "$errno\0$err_key";
	612	unless ($ignored_err{$err_key}) {
	613	warn "W: Ignoring error from SVN, path probably ",
	614	"does not exist: ($errno): ",
	615	$err->expanded_message,"\n";
	616	warn "W: Do not be alarmed at the above message ",
	617	"git-svn is just searching aggressively for ",
	618	"old history.\n",
	619	"This may take a while on large repositories\n";
	620	$ignored_err{$err_key} = 1;
	621	}
	622	return;
	623	}
	624	die "Error from SVN, ($errno): ", $err->expanded_message,"\n";
	625	}
	626
	627	1;
	628	__END__
	629
d301f181 JN	630	=head1 NAME
d301f181 JN	631
9f7ad147 JN	632	Git::SVN::Ra - Subversion remote access functions for git-svn
	633
	634	=head1 SYNOPSIS
	635
	636	use Git::SVN::Ra;
	637
	638	my $ra = Git::SVN::Ra->new($branchurl);
	639	my ($dirents, $fetched_revnum, $props) =
	640	$ra->get_dir('.', $SVN::Core::INVALID_REVNUM);
	641
	642	=head1 DESCRIPTION
	643
	644	This is a wrapper around the L<SVN::Ra> module for use by B<git-svn>.
	645	It fills in some default parameters (such as the authentication
	646	scheme), smooths over incompatibilities between libsvn versions, adds
	647	caching, and implements some functions specific to B<git-svn>.
	648
	649	Do not use it unless you are developing git-svn. The interface will
	650	change as git-svn evolves.
	651
	652	=head1 DEPENDENCIES
	653
	654	Subversion perl bindings,
	655	L<Git::SVN>.
	656
	657	C<Git::SVN::Ra> has not been tested using callers other than
	658	B<git-svn> itself.
	659
	660	=head1 SEE ALSO
	661
	662	L<SVN::Ra>.
	663
	664	=head1 INCOMPATIBILITIES
	665
	666	None reported.
	667
	668	=head1 BUGS
	669
	670	None.