git-svn: add --ignore-paths option for fetching

This will be useful when somebody want to checkout something partially from
repository with some non-standart layout or exclude some files from it.
Example: repository has structure /module-{a,b,c}/{trunk,branches,tags}/...
Modules are interdependent, and you want it to be single repostory (to commit
to all modules simultaneously and view complete history), but do not want
branches and tags be checked out into working copy.
Other use case is excluding some large blobs.

The quirk for now is that user must specify this option every fetch/rebase;
in other case he may get extra files or "file not found" errors. It may be
will be resolved by adding regular expression to .git/config into
[svn-remote ...] to make it persistent.

Signed-off-by: Vitaly "_Vi" Shukela <[email protected]>
Acked-by: Eric Wong <[email protected]>

[ew: replaced 4-space indent with tabs]
[ew: prefixed $ignore_regex with an underscore to be consistent
     with other globals in git-svn]
[ew: rearranged functions to minimize diff and removed prototype
     usage to be consistent with the rest of git-svn (and other
     Perl code in git (and they're ugly to me)]

Author: Vitaly \"_Vi\" Shukela

git-svn.perl

@@ -70,7 +70,8 @@ BEGIN
 $Git::SVN::_follow_parent = 1;
 my %remote_opts = ( 'username=s' => \$Git::SVN::Prompt::_username,
                     'config-dir=s' => \$Git::SVN::Ra::config_dir,
-                    'no-auth-cache' => \$Git::SVN::Prompt::_no_auth_cache );
+                    'no-auth-cache' => \$Git::SVN::Prompt::_no_auth_cache,
+                    'ignore-paths=s' => \$SVN::Git::Fetcher::_ignore_regex );
 my %fc_opts = ( 'follow-parent|follow!' => \$Git::SVN::_follow_parent,
 		'authors-file|A=s' => \$_authors,
 		'repack:i' => \$Git::SVN::_repack,
@@ -3245,6 +3246,7 @@ package SVN::Git::Fetcher;
 use Carp qw/croak/;
 use File::Temp qw/tempfile/;
 use IO::File qw//;
+use vars qw/$_ignore_regex/;
 
 # file baton members: path, mode_a, mode_b, pool, fh, blob, base
 sub new {
@@ -3297,6 +3299,15 @@ sub in_dot_git {
 	$_[0] =~ m{(?:^|/)\.git(?:/|$)};
 }
 
+# return value: 0 -- don't ignore, 1 -- ignore
+sub is_path_ignored {
+	my ($path) = @_;
+	return 1 if in_dot_git($path);
+	return 0 unless defined($_ignore_regex);
+	return 1 if $path =~ m!$_ignore_regex!o;
+	return 0;
+}
+
 sub set_path_strip {
 	my ($self, $path) = @_;
 	$self->{path_strip} = qr/^\Q$path\E(\/|$)/ if length $path;
@@ -3322,7 +3333,7 @@ sub git_path {
 
 sub delete_entry {
 	my ($self, $path, $rev, $pb) = @_;
-	return undef if in_dot_git($path);
+	return undef if is_path_ignored($path);
 
 	my $gpath = $self->git_path($path);
 	return undef if ($gpath eq '');
@@ -3352,7 +3363,7 @@ sub open_file {
 	my ($self, $path, $pb, $rev) = @_;
 	my ($mode, $blob);
 
-	goto out if in_dot_git($path);
+	goto out if is_path_ignored($path);
 
 	my $gpath = $self->git_path($path);
 	($mode, $blob) = (command('ls-tree', $self->{c}, '--', $gpath)
@@ -3372,7 +3383,7 @@ sub add_file {
 	my ($self, $path, $pb, $cp_path, $cp_rev) = @_;
 	my $mode;
 
-	if (!in_dot_git($path)) {
+	if (!is_path_ignored($path)) {
 		my ($dir, $file) = ($path =~ m#^(.*?)/?([^/]+)$#);
 		delete $self->{empty}->{$dir};
 		$mode = '100644';
@@ -3383,7 +3394,7 @@ sub add_file {
 
 sub add_directory {
 	my ($self, $path, $cp_path, $cp_rev) = @_;
-	goto out if in_dot_git($path);
+	goto out if is_path_ignored($path);
 	my $gpath = $self->git_path($path);
 	if ($gpath eq '') {
 		my ($ls, $ctx) = command_output_pipe(qw/ls-tree
@@ -3407,31 +3418,31 @@ sub add_directory {
 
 sub change_dir_prop {
 	my ($self, $db, $prop, $value) = @_;
-	return undef if in_dot_git($db->{path});
+	return undef if is_path_ignored($db->{path});
 	$self->{dir_prop}->{$db->{path}} ||= {};
 	$self->{dir_prop}->{$db->{path}}->{$prop} = $value;
 	undef;
 }
 
 sub absent_directory {
 	my ($self, $path, $pb) = @_;
-	return undef if in_dot_git($pb->{path});
+	return undef if is_path_ignored($path);
 	$self->{absent_dir}->{$pb->{path}} ||= [];
 	push @{$self->{absent_dir}->{$pb->{path}}}, $path;
 	undef;
 }
 
 sub absent_file {
 	my ($self, $path, $pb) = @_;
-	return undef if in_dot_git($pb->{path});
+	return undef if is_path_ignored($path);
 	$self->{absent_file}->{$pb->{path}} ||= [];
 	push @{$self->{absent_file}->{$pb->{path}}}, $path;
 	undef;
 }
 
 sub change_file_prop {
 	my ($self, $fb, $prop, $value) = @_;
-	return undef if in_dot_git($fb->{path});
+	return undef if is_path_ignored($fb->{path});
 	if ($prop eq 'svn:executable') {
 		if ($fb->{mode_b} != 120000) {
 			$fb->{mode_b} = defined $value ? 100755 : 100644;
@@ -3447,7 +3458,7 @@ sub change_file_prop {
 
 sub apply_textdelta {
 	my ($self, $fb, $exp) = @_;
-	return undef if (in_dot_git($fb->{path}));
+	return undef if is_path_ignored($fb->{path});
 	my $fh = $::_repository->temp_acquire('svn_delta');
 	# $fh gets auto-closed() by SVN::TxDelta::apply(),
 	# (but $base does not,) so dup() it for reading in close_file
@@ -3494,7 +3505,7 @@ sub apply_textdelta {
 
 sub close_file {
 	my ($self, $fb, $exp) = @_;
-	return undef if (in_dot_git($fb->{path}));
+	return undef if is_path_ignored($fb->{path});
 
 	my $hash;
 	my $path = $self->git_path($fb->{path});