git-svn: handle empty files marked as symlinks in SVN

Broken SVN clients generate empty files with the svn:special set
to '*'.  This attempts to denote a symlink pointing to a file
with an empty path (""), which cannot be generated on a POSIX
system.

Thus, we mimic the behavior of svn(1) and create a zero-byte
file in our tree.

Signed-off-by: Eric Wong <normalperson@yhbt.net>

diff --git a/git-svn.perl b/git-svn.perl
index ad01e182df8abbeac7efa3db0d84d55ab1563e40..1b87a652996ee0961fa64b6484e3401bb65e80ab 100755 (executable)
--- a/git-svn.perl
+++ b/git-svn.perl
@@ -3200,7 +3200,10 @@ sub new {
        my ($class, $git_svn) = @_;
        my $self = SVN::Delta::Editor->new;
        bless $self, $class;
-       $self->{c} = $git_svn->{last_commit} if exists $git_svn->{last_commit};
+       if (exists $git_svn->{last_commit}) {
+               $self->{c} = $git_svn->{last_commit};
+               $self->{empty_symlinks} = _mark_empty_symlinks($git_svn);
+       }
        $self->{empty} = {};
        $self->{dir_prop} = {};
        $self->{file_prop} = {};
@@ -3210,6 +3213,34 @@ sub new {
        $self;
 }
 
+# this uses the Ra object, so it must be called before do_{switch,update},
+# not inside them (when the Git::SVN::Fetcher object is passed) to
+# do_{switch,update}
+sub _mark_empty_symlinks {
+       my ($git_svn) = @_;
+       my %ret;
+       my ($rev, $cmt) = $git_svn->last_rev_commit;
+       return {} unless ($rev && $cmt);
+
+       chomp(my $empty_blob = `git hash-object -t blob --stdin < /dev/null`);
+       my ($ls, $ctx) = command_output_pipe(qw/ls-tree -r -z/, $cmt);
+       local $/ = "\0";
+       my $pfx = $git_svn->{path};
+       $pfx .= '/' if length($pfx);
+       while (<$ls>) {
+               chomp;
+               s/\A100644 blob $empty_blob\t//o or next;
+               my $path = $_;
+               my (undef, $props) =
+                              $git_svn->ra->get_file($pfx.$path, $rev, undef);
+               if ($props->{'svn:special'}) {
+                       $ret{$path} = 1;
+               }
+       }
+       command_close_pipe($ls, $ctx);
+       \%ret;
+}
+
 sub set_path_strip {
        my ($self, $path) = @_;
        $self->{path_strip} = qr/^\Q$path\E(\/|$)/ if length $path;
@@ -3268,6 +3299,9 @@ sub open_file {
        unless (defined $mode && defined $blob) {
                die "$path was not found in commit $self->{c} (r$rev)\n";
        }
+       if ($mode eq '100644' && $self->{empty_symlinks}->{$path}) {
+               $mode = '120000';
+       }
        { path => $path, mode_a => $mode, mode_b => $mode, blob => $blob,
          pool => SVN::Pool->new, action => 'M' };
 }
@@ -3346,7 +3380,10 @@ sub apply_textdelta {
        open my $dup, '<&', $fh or croak $!;
        my $base = $::_repository->temp_acquire('git_blob');
        if ($fb->{blob}) {
-               print $base 'link ' if ($fb->{mode_a} == 120000);
+               if ($fb->{mode_a} eq '120000' &&
+                   ! $self->{empty_symlinks}->{$fb->{path}}) {
+                       print $base 'link ' or die "print $!\n";
+               }
                my $size = $::_repository->cat_blob($fb->{blob}, $base);
                die "Failed to read object $fb->{blob}" if ($size < 0);
 
@@ -3379,11 +3416,19 @@ sub close_file {
                }
                if ($fb->{mode_b} == 120000) {
                        sysseek($fh, 0, 0) or croak $!;
-                       sysread($fh, my $buf, 5) == 5 or croak $!;
+                       my $rd = sysread($fh, my $buf, 5);
 
-                       unless ($buf eq 'link ') {
+                       if (!defined $rd) {
+                               croak "sysread: $!\n";
+                       } elsif ($rd == 0) {
+                               warn "$path has mode 120000",
+                                    " but it points to nothing\n",
+                                    "converting to an empty file with mode",
+                                    " 100644\n";
+                               $fb->{mode_b} = '100644';
+                       } elsif ($buf ne 'link ') {
                                warn "$path has mode 120000",
-                                               " but is not a link\n";
+                                    " but is not a link\n";
                        } else {
                                my $tmp_fh = $::_repository->temp_acquire(
                                        'svn_hash');

diff --git a/t/t9131-git-svn-empty-symlink.sh b/t/t9131-git-svn-empty-symlink.sh
new file mode 100755 (executable)
index 0000000..704a4f8
--- /dev/null
+++ b/t/t9131-git-svn-empty-symlink.sh
@@ -0,0 +1,90 @@
+#!/bin/sh
+
+test_description='test that git handles an svn repository with empty symlinks'
+
+. ./lib-git-svn.sh
+test_expect_success 'load svn dumpfile' '
+       svnadmin load "$rawsvnrepo" <<EOF
+SVN-fs-dump-format-version: 2
+
+UUID: 60780f9a-7df5-43b4-83ab-60e2c0673ef7
+
+Revision-number: 0
+Prop-content-length: 56
+Content-length: 56
+
+K 8
+svn:date
+V 27
+2008-11-26T07:17:27.590577Z
+PROPS-END
+
+Revision-number: 1
+Prop-content-length: 111
+Content-length: 111
+
+K 7
+svn:log
+V 4
+test
+K 10
+svn:author
+V 12
+normalperson
+K 8
+svn:date
+V 27
+2008-11-26T07:18:03.511836Z
+PROPS-END
+
+Node-path: bar
+Node-kind: file
+Node-action: add
+Prop-content-length: 33
+Text-content-length: 0
+Text-content-md5: d41d8cd98f00b204e9800998ecf8427e
+Content-length: 33
+
+K 11
+svn:special
+V 1
+*
+PROPS-END
+
+Revision-number: 2
+Prop-content-length: 121
+Content-length: 121
+
+K 7
+svn:log
+V 13
+bar => doink
+
+K 10
+svn:author
+V 12
+normalperson
+K 8
+svn:date
+V 27
+2008-11-27T03:55:31.601672Z
+PROPS-END
+
+Node-path: bar
+Node-kind: file
+Node-action: change
+Text-content-length: 10
+Text-content-md5: 92ca4fe7a9721f877f765c252dcd66c9
+Content-length: 10
+
+link doink
+
+EOF
+'
+
+test_expect_success 'clone using git svn' 'git svn clone -r1 "$svnrepo" x'
+test_expect_success '"bar" is an empty file' 'test -f x/bar && ! test -s x/bar'
+test_expect_success 'get "bar" => symlink fix from svn' \
+               '(cd x && git svn rebase)'
+test_expect_success '"bar" becomes a symlink' 'test -L x/bar'
+test_done