SCRIPT_PERL = \
git-archimport.perl git-cvsimport.perl git-relink.perl \
git-shortlog.perl git-fmt-merge-msg.perl git-rerere.perl \
+ git-annotate.perl \
git-svnimport.perl git-mv.perl git-cvsexportcommit.perl
SCRIPT_PYTHON = \
--- /dev/null
+git-svn
+git-svn.xml
+git-svn.html
+git-svn.1
--- /dev/null
+all: git-svn
+
+prefix?=$(HOME)
+bindir=$(prefix)/bin
+mandir=$(prefix)/man
+man1=$(mandir)/man1
+INSTALL?=install
+doc_conf=../../Documentation/asciidoc.conf
+-include ../../config.mak
+
+git-svn: git-svn.perl
+ cp $< $@
+ chmod +x $@
+
+install: all
+ $(INSTALL) -d -m755 $(DESTDIR)$(bindir)
+ $(INSTALL) git-svn $(DESTDIR)$(bindir)
+
+install-doc: doc
+ $(INSTALL) git-svn.1 $(DESTDIR)$(man1)
+
+doc: git-svn.1
+git-svn.1 : git-svn.xml
+ xmlto man git-svn.xml
+git-svn.xml : git-svn.txt
+ asciidoc -b docbook -d manpage \
+ -f ../../Documentation/asciidoc.conf $<
+test:
+ cd t && $(SHELL) ./t0000-contrib-git-svn.sh
+
+clean:
+ rm -f git-svn *.xml *.html *.1
+++ /dev/null
-#!/usr/bin/env perl
-use warnings;
-use strict;
-use vars qw/ $AUTHOR $VERSION
- $SVN_URL $SVN_INFO $SVN_WC
- $GIT_SVN_INDEX $GIT_SVN
- $GIT_DIR $REV_DIR/;
-$AUTHOR = 'Eric Wong <normalperson@yhbt.net>';
-$VERSION = '0.9.0';
-$GIT_DIR = $ENV{GIT_DIR} || "$ENV{PWD}/.git";
-$GIT_SVN = $ENV{GIT_SVN_ID} || 'git-svn';
-$GIT_SVN_INDEX = "$GIT_DIR/$GIT_SVN/index";
-$ENV{GIT_DIR} ||= $GIT_DIR;
-$SVN_URL = undef;
-$REV_DIR = "$GIT_DIR/$GIT_SVN/revs";
-$SVN_WC = "$GIT_DIR/$GIT_SVN/tree";
-
-# make sure the svn binary gives consistent output between locales and TZs:
-$ENV{TZ} = 'UTC';
-$ENV{LC_ALL} = 'C';
-
-# If SVN:: library support is added, please make the dependencies
-# optional and preserve the capability to use the command-line client.
-# See what I do with XML::Simple to make the dependency optional.
-use Carp qw/croak/;
-use IO::File qw//;
-use File::Basename qw/dirname basename/;
-use File::Path qw/mkpath/;
-use Getopt::Long qw/:config gnu_getopt no_ignore_case auto_abbrev/;
-use File::Spec qw//;
-my $sha1 = qr/[a-f\d]{40}/;
-my $sha1_short = qr/[a-f\d]{6,40}/;
-my ($_revision,$_stdin,$_no_ignore_ext,$_no_stop_copy,$_help,$_rmdir,$_edit);
-
-GetOptions( 'revision|r=s' => \$_revision,
- 'no-ignore-externals' => \$_no_ignore_ext,
- 'stdin|' => \$_stdin,
- 'edit|e' => \$_edit,
- 'rmdir' => \$_rmdir,
- 'help|H|h' => \$_help,
- 'no-stop-copy' => \$_no_stop_copy );
-my %cmd = (
- fetch => [ \&fetch, "Download new revisions from SVN" ],
- init => [ \&init, "Initialize and fetch (import)"],
- commit => [ \&commit, "Commit git revisions to SVN" ],
- rebuild => [ \&rebuild, "Rebuild git-svn metadata (after git clone)" ],
- help => [ \&usage, "Show help" ],
-);
-my $cmd;
-for (my $i = 0; $i < @ARGV; $i++) {
- if (defined $cmd{$ARGV[$i]}) {
- $cmd = $ARGV[$i];
- splice @ARGV, $i, 1;
- last;
- }
-};
-
-# we may be called as git-svn-(command), or git-svn(command).
-foreach (keys %cmd) {
- if (/git\-svn\-?($_)(?:\.\w+)?$/) {
- $cmd = $1;
- last;
- }
-}
-usage(0) if $_help;
-usage(1) unless (defined $cmd);
-svn_check_ignore_externals();
-$cmd{$cmd}->[0]->(@ARGV);
-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
-Available commands:
-
- foreach (sort keys %cmd) {
- print $fd ' ',pack('A10',$_),$cmd{$_}->[1],"\n";
- }
- print $fd <<"";
-\nGIT_SVN_ID may be set in the environment to an arbitrary identifier if
-you're tracking multiple SVN branches/repositories in one git repository
-and want to keep them separate.
-
- exit $exit;
-}
-
-sub rebuild {
- $SVN_URL = shift or undef;
- my $repo_uuid;
- my $newest_rev = 0;
-
- my $pid = open(my $rev_list,'-|');
- defined $pid or croak $!;
- if ($pid == 0) {
- exec("git-rev-list","$GIT_SVN-HEAD") or croak $!;
- }
- my $first;
- while (<$rev_list>) {
- chomp;
- my $c = $_;
- croak "Non-SHA1: $c\n" unless $c =~ /^$sha1$/o;
- my @commit = grep(/^git-svn-id: /,`git-cat-file commit $c`);
- next if (!@commit); # skip merges
- my $id = $commit[$#commit];
- my ($url, $rev, $uuid) = ($id =~ /^git-svn-id:\s(\S+?)\@(\d+)
- \s([a-f\d\-]+)$/x);
- if (!$rev || !$uuid || !$url) {
- # some of the original repositories I made had
- # indentifiers like this:
- ($rev, $uuid) = ($id =~/^git-svn-id:\s(\d+)
- \@([a-f\d\-]+)/x);
- if (!$rev || !$uuid) {
- croak "Unable to extract revision or UUID from ",
- "$c, $id\n";
- }
- }
- print "r$rev = $c\n";
- unless (defined $first) {
- if (!$SVN_URL && !$url) {
- croak "SVN repository location required: $url\n";
- }
- $SVN_URL ||= $url;
- $repo_uuid = setup_git_svn();
- $first = $rev;
- }
- if ($uuid ne $repo_uuid) {
- croak "Repository UUIDs do not match!\ngot: $uuid\n",
- "expected: $repo_uuid\n";
- }
- assert_revision_eq_or_unknown($rev, $c);
- sys('git-update-ref',"$GIT_SVN/revs/$rev",$c);
- $newest_rev = $rev if ($rev > $newest_rev);
- }
- close $rev_list or croak $?;
- if (!chdir $SVN_WC) {
- my @svn_co = ('svn','co',"-r$first");
- push @svn_co, '--ignore-externals' unless $_no_ignore_ext;
- sys(@svn_co, $SVN_URL, $SVN_WC);
- chdir $SVN_WC or croak $!;
- }
-
- $pid = fork;
- defined $pid or croak $!;
- if ($pid == 0) {
- my @svn_up = qw(svn up);
- push @svn_up, '--ignore-externals' unless $_no_ignore_ext;
- sys(@svn_up,"-r$newest_rev");
- $ENV{GIT_INDEX_FILE} = $GIT_SVN_INDEX;
- git_addremove();
- exec('git-write-tree');
- }
- waitpid $pid, 0;
-}
-
-sub init {
- $SVN_URL = shift or croak "SVN repository location required\n";
- unless (-d $GIT_DIR) {
- sys('git-init-db');
- }
- setup_git_svn();
-}
-
-sub fetch {
- my (@parents) = @_;
- $SVN_URL ||= file_to_s("$GIT_DIR/$GIT_SVN/info/url");
- my @log_args = -d $SVN_WC ? ($SVN_WC) : ($SVN_URL);
- unless ($_revision) {
- $_revision = -d $SVN_WC ? 'BASE:HEAD' : '0:HEAD';
- }
- push @log_args, "-r$_revision";
- push @log_args, '--stop-on-copy' unless $_no_stop_copy;
-
- eval { require XML::Simple or croak $! };
- my $svn_log = $@ ? svn_log_raw(@log_args) : svn_log_xml(@log_args);
- @$svn_log = sort { $a->{revision} <=> $b->{revision} } @$svn_log;
-
- my $base = shift @$svn_log or croak "No base revision!\n";
- my $last_commit = undef;
- unless (-d $SVN_WC) {
- my @svn_co = ('svn','co',"-r$base->{revision}");
- push @svn_co,'--ignore-externals' unless $_no_ignore_ext;
- sys(@svn_co, $SVN_URL, $SVN_WC);
- chdir $SVN_WC or croak $!;
- $last_commit = git_commit($base, @parents);
- unless (-f "$GIT_DIR/refs/heads/master") {
- sys(qw(git-update-ref refs/heads/master),$last_commit);
- }
- assert_svn_wc_clean($base->{revision}, $last_commit);
- } else {
- chdir $SVN_WC or croak $!;
- $last_commit = file_to_s("$REV_DIR/$base->{revision}");
- }
- my @svn_up = qw(svn up);
- push @svn_up, '--ignore-externals' unless $_no_ignore_ext;
- my $last_rev = $base->{revision};
- foreach my $log_msg (@$svn_log) {
- assert_svn_wc_clean($last_rev, $last_commit);
- $last_rev = $log_msg->{revision};
- sys(@svn_up,"-r$last_rev");
- $last_commit = git_commit($log_msg, $last_commit, @parents);
- }
- assert_svn_wc_clean($last_rev, $last_commit);
- return pop @$svn_log;
-}
-
-sub commit {
- my (@commits) = @_;
- if ($_stdin || !@commits) {
- print "Reading from stdin...\n";
- @commits = ();
- while (<STDIN>) {
- if (/^([a-f\d]{6,40})\b/) {
- unshift @commits, $1;
- }
- }
- }
- my @revs;
- foreach (@commits) {
- push @revs, (safe_qx('git-rev-parse',$_));
- }
- chomp @revs;
-
- fetch();
- chdir $SVN_WC or croak $!;
- my $svn_current_rev = svn_info('.')->{'Last Changed Rev'};
- foreach my $c (@revs) {
- print "Committing $c\n";
- svn_checkout_tree($svn_current_rev, $c);
- $svn_current_rev = svn_commit_tree($svn_current_rev, $c);
- }
- print "Done committing ",scalar @revs," revisions to SVN\n";
-
-}
-
-########################### utility functions #########################
-
-sub setup_git_svn {
- defined $SVN_URL or croak "SVN repository location required\n";
- unless (-d $GIT_DIR) {
- croak "GIT_DIR=$GIT_DIR does not exist!\n";
- }
- mkpath(["$GIT_DIR/$GIT_SVN"]);
- mkpath(["$GIT_DIR/$GIT_SVN/info"]);
- mkpath([$REV_DIR]);
- s_to_file($SVN_URL,"$GIT_DIR/$GIT_SVN/info/url");
- my $uuid = svn_info($SVN_URL)->{'Repository UUID'} or
- croak "Repository UUID unreadable\n";
- s_to_file($uuid,"$GIT_DIR/$GIT_SVN/info/uuid");
-
- open my $fd, '>>', "$GIT_DIR/$GIT_SVN/info/exclude" or croak $!;
- print $fd '.svn',"\n";
- close $fd or croak $!;
- return $uuid;
-}
-
-sub assert_svn_wc_clean {
- my ($svn_rev, $commit) = @_;
- croak "$svn_rev is not an integer!\n" unless ($svn_rev =~ /^\d+$/);
- croak "$commit is not a sha1!\n" unless ($commit =~ /^$sha1$/o);
- my $svn_info = svn_info('.');
- if ($svn_rev != $svn_info->{'Last Changed Rev'}) {
- croak "Expected r$svn_rev, got r",
- $svn_info->{'Last Changed Rev'},"\n";
- }
- my @status = grep(!/^Performing status on external/,(`svn status`));
- @status = grep(!/^\s*$/,@status);
- if (scalar @status) {
- print STDERR "Tree ($SVN_WC) is not clean:\n";
- print STDERR $_ foreach @status;
- croak;
- }
- my ($tree_a) = grep(/^tree $sha1$/o,`git-cat-file commit $commit`);
- $tree_a =~ s/^tree //;
- chomp $tree_a;
- chomp(my $tree_b = `GIT_INDEX_FILE=$GIT_SVN_INDEX git-write-tree`);
- if ($tree_a ne $tree_b) {
- croak "$svn_rev != $commit, $tree_a != $tree_b\n";
- }
-}
-
-sub parse_diff_tree {
- my $diff_fh = shift;
- local $/ = "\0";
- my $state = 'meta';
- my @mods;
- while (<$diff_fh>) {
- chomp $_; # this gets rid of the trailing "\0"
- print $_,"\n";
- if ($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 __LINE__,": Empty array\n";
- if ($x->{chg} !~ /^(?:C|R)$/) {
- croak __LINE__,": Error parsing $_, $x->{chg}\n";
- }
- $x->{file_a} = $_;
- $state = 'file_b';
- } elsif ($state eq 'file_b') {
- my $x = $mods[$#mods] or croak __LINE__,": Empty array\n";
- if (exists $x->{file_a} && $x->{chg} !~ /^(?:C|R)$/) {
- croak __LINE__,": Error parsing $_, $x->{chg}\n";
- }
- if (!exists $x->{file_a} && $x->{chg} =~ /^(?:C|R)$/) {
- croak __LINE__,": Error parsing $_, $x->{chg}\n";
- }
- $x->{file_b} = $_;
- $state = 'meta';
- } else {
- croak __LINE__,": Error parsing $_\n";
- }
- }
- close $diff_fh or croak $!;
- return \@mods;
-}
-
-sub svn_check_prop_executable {
- my $m = shift;
- if ($m->{mode_b} =~ /755$/ && $m->{mode_a} !~ /755$/) {
- sys(qw(svn propset svn:executable 1), $m->{file_b});
- } elsif ($m->{mode_b} !~ /755$/ && $m->{mode_a} =~ /755$/) {
- sys(qw(svn propdel svn:executable), $m->{file_b});
- }
-}
-
-sub svn_ensure_parent_path {
- my $dir_b = dirname(shift);
- svn_ensure_parent_path($dir_b) if ($dir_b ne File::Spec->curdir);
- mkpath([$dir_b]) unless (-d $dir_b);
- sys(qw(svn add -N), $dir_b) unless (-d "$dir_b/.svn");
-}
-
-sub svn_checkout_tree {
- my ($svn_rev, $commit) = @_;
- my $from = file_to_s("$REV_DIR/$svn_rev");
- assert_svn_wc_clean($svn_rev,$from);
- print "diff-tree '$from' '$commit'\n";
- my $pid = open my $diff_fh, '-|';
- defined $pid or croak $!;
- if ($pid == 0) {
- exec(qw(git-diff-tree -z -r -C), $from, $commit) or croak $!;
- }
- my $mods = parse_diff_tree($diff_fh);
- unless (@$mods) {
- # git can do empty commits, SVN doesn't allow it...
- return $svn_rev;
- }
- my %rm;
- foreach my $m (@$mods) {
- if ($m->{chg} eq 'C') {
- svn_ensure_parent_path( $m->{file_b} );
- sys(qw(svn cp), $m->{file_a}, $m->{file_b});
- blob_to_file( $m->{sha1_b}, $m->{file_b});
- svn_check_prop_executable($m);
- } elsif ($m->{chg} eq 'D') {
- $rm{dirname $m->{file_b}}->{basename $m->{file_b}} = 1;
- sys(qw(svn rm --force), $m->{file_b});
- } elsif ($m->{chg} eq 'R') {
- svn_ensure_parent_path( $m->{file_b} );
- sys(qw(svn mv --force), $m->{file_a}, $m->{file_b});
- blob_to_file( $m->{sha1_b}, $m->{file_b});
- svn_check_prop_executable($m);
- $rm{dirname $m->{file_a}}->{basename $m->{file_a}} = 1;
- } elsif ($m->{chg} eq 'M') {
- if ($m->{mode_b} =~ /^120/ && $m->{mode_a} =~ /^120/) {
- unlink $m->{file_b} or croak $!;
- blob_to_symlink($m->{sha1_b}, $m->{file_b});
- } else {
- blob_to_file($m->{sha1_b}, $m->{file_b});
- }
- svn_check_prop_executable($m);
- } elsif ($m->{chg} eq 'T') {
- sys(qw(svn rm --force),$m->{file_b});
- if ($m->{mode_b} =~ /^120/ && $m->{mode_a} =~ /^100/) {
- blob_to_symlink($m->{sha1_b}, $m->{file_b});
- } else {
- blob_to_file($m->{sha1_b}, $m->{file_b});
- }
- svn_check_prop_executable($m);
- sys(qw(svn add --force), $m->{file_b});
- } elsif ($m->{chg} eq 'A') {
- svn_ensure_parent_path( $m->{file_b} );
- blob_to_file( $m->{sha1_b}, $m->{file_b});
- if ($m->{mode_b} =~ /755$/) {
- chmod 0755, $m->{file_b};
- }
- sys(qw(svn add --force), $m->{file_b});
- } else {
- croak "Invalid chg: $m->{chg}\n";
- }
- }
- if ($_rmdir) {
- my $old_index = $ENV{GIT_INDEX_FILE};
- $ENV{GIT_INDEX_FILE} = $GIT_SVN_INDEX;
- foreach my $dir (keys %rm) {
- my $files = $rm{$dir};
- my @files;
- foreach (safe_qx('svn','ls',$dir)) {
- chomp;
- push @files, $_ unless $files->{$_};
- }
- sys(qw(svn rm),$dir) unless @files;
- }
- if ($old_index) {
- $ENV{GIT_INDEX_FILE} = $old_index;
- } else {
- delete $ENV{GIT_INDEX_FILE};
- }
- }
-}
-
-sub svn_commit_tree {
- my ($svn_rev, $commit) = @_;
- my $commit_msg = "$GIT_DIR/$GIT_SVN/.svn-commit.tmp.$$";
- open my $msg, '>', $commit_msg or croak $!;
-
- chomp(my $type = `git-cat-file -t $commit`);
- if ($type eq 'commit') {
- my $pid = open my $msg_fh, '-|';
- defined $pid or croak $!;
-
- if ($pid == 0) {
- exec(qw(git-cat-file commit), $commit) or croak $!;
- }
- my $in_msg = 0;
- while (<$msg_fh>) {
- if (!$in_msg) {
- $in_msg = 1 if (/^\s*$/);
- } else {
- print $msg $_ or croak $!;
- }
- }
- close $msg_fh or croak $!;
- }
- close $msg or croak $!;
-
- if ($_edit || ($type eq 'tree')) {
- my $editor = $ENV{VISUAL} || $ENV{EDITOR} || 'vi';
- system($editor, $commit_msg);
- }
- my @ci_output = safe_qx(qw(svn commit -F),$commit_msg);
- my ($committed) = grep(/^Committed revision \d+\./,@ci_output);
- unlink $commit_msg;
- defined $committed or croak
- "Commit output failed to parse committed revision!\n",
- join("\n",@ci_output),"\n";
- my ($rev_committed) = ($committed =~ /^Committed revision (\d+)\./);
-
- # resync immediately
- my @svn_up = (qw(svn up), "-r$svn_rev");
- push @svn_up, '--ignore-externals' unless $_no_ignore_ext;
- sys(@svn_up);
- return fetch("$rev_committed=$commit")->{revision};
-}
-
-sub svn_log_xml {
- my (@log_args) = @_;
- my $log_fh = IO::File->new_tmpfile or croak $!;
-
- my $pid = fork;
- defined $pid or croak $!;
-
- if ($pid == 0) {
- open STDOUT, '>&', $log_fh or croak $!;
- exec (qw(svn log --xml), @log_args) or croak $!
- }
-
- waitpid $pid, 0;
- croak $? if $?;
-
- seek $log_fh, 0, 0;
- my @svn_log;
- my $log = XML::Simple::XMLin( $log_fh,
- ForceArray => ['path','revision','logentry'],
- KeepRoot => 0,
- KeyAttr => { logentry => '+revision',
- paths => '+path' },
- )->{logentry};
- foreach my $r (sort {$a <=> $b} keys %$log) {
- my $log_msg = $log->{$r};
- my ($Y,$m,$d,$H,$M,$S) = ($log_msg->{date} =~
- /(\d{4})\-(\d\d)\-(\d\d)T
- (\d\d)\:(\d\d)\:(\d\d)\.\d+Z$/x)
- or croak "Failed to parse date: ",
- $log->{$r}->{date};
- $log_msg->{date} = "+0000 $Y-$m-$d $H:$M:$S";
-
- # XML::Simple can't handle <msg></msg> as a string:
- if (ref $log_msg->{msg} eq 'HASH') {
- $log_msg->{msg} = "\n";
- } else {
- $log_msg->{msg} .= "\n";
- }
- push @svn_log, $log->{$r};
- }
- return \@svn_log;
-}
-
-sub svn_log_raw {
- my (@log_args) = @_;
- my $pid = open my $log_fh,'-|';
- defined $pid or croak $!;
-
- if ($pid == 0) {
- exec (qw(svn log), @log_args) or croak $!
- }
-
- my @svn_log;
- my $state;
- while (<$log_fh>) {
- chomp;
- if (/^\-{72}$/) {
- $state = 'rev';
-
- # if we have an empty log message, put something there:
- if (@svn_log) {
- $svn_log[$#svn_log]->{msg} ||= "\n";
- }
- next;
- }
- if ($state eq 'rev' && s/^r(\d+)\s*\|\s*//) {
- my $rev = $1;
- my ($author, $date) = split(/\s*\|\s*/, $_, 2);
- my ($Y,$m,$d,$H,$M,$S,$tz) = ($date =~
- /(\d{4})\-(\d\d)\-(\d\d)\s
- (\d\d)\:(\d\d)\:(\d\d)\s([\-\+]\d+)/x)
- or croak "Failed to parse date: $date\n";
- my %log_msg = ( revision => $rev,
- date => "$tz $Y-$m-$d $H:$M:$S",
- author => $author,
- msg => '' );
- push @svn_log, \%log_msg;
- $state = 'msg_start';
- next;
- }
- # skip the first blank line of the message:
- if ($state eq 'msg_start' && /^$/) {
- $state = 'msg';
- } elsif ($state eq 'msg') {
- $svn_log[$#svn_log]->{msg} .= $_."\n";
- }
- }
- close $log_fh or croak $?;
- return \@svn_log;
-}
-
-sub svn_info {
- my $url = shift || $SVN_URL;
-
- my $pid = open my $info_fh, '-|';
- defined $pid or croak $!;
-
- if ($pid == 0) {
- exec(qw(svn info),$url) or croak $!;
- }
-
- my $ret = {};
- # only single-lines seem to exist in svn info output
- while (<$info_fh>) {
- chomp $_;
- if (m#^([^:]+)\s*:\s*(\S*)$#) {
- $ret->{$1} = $2;
- push @{$ret->{-order}}, $1;
- }
- }
- close $info_fh or croak $!;
- return $ret;
-}
-
-sub sys { system(@_) == 0 or croak $? }
-
-sub git_addremove {
- system( "git-diff-files --name-only -z ".
- " | git-update-index --remove -z --stdin; ".
- "git-ls-files -z --others ".
- "'--exclude-from=$GIT_DIR/$GIT_SVN/info/exclude'".
- " | git-update-index --add -z --stdin; "
- ) == 0 or croak $?
-}
-
-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;
-}
-
-sub assert_revision_unknown {
- my $revno = shift;
- if (-f "$REV_DIR/$revno") {
- croak "$REV_DIR/$revno already exists! ",
- "Why are we refetching it?";
- }
-}
-
-sub assert_revision_eq_or_unknown {
- my ($revno, $commit) = @_;
- if (-f "$REV_DIR/$revno") {
- my $current = file_to_s("$REV_DIR/$revno");
- if ($commit ne $current) {
- croak "$REV_DIR/$revno already exists!\n",
- "current: $current\nexpected: $commit\n";
- }
- return;
- }
-}
-
-sub git_commit {
- my ($log_msg, @parents) = @_;
- assert_revision_unknown($log_msg->{revision});
- my $out_fh = IO::File->new_tmpfile or croak $!;
- my $info = svn_info('.');
- my $uuid = $info->{'Repository UUID'};
- defined $uuid or croak "Unable to get Repository UUID\n";
-
- # commit parents can be conditionally bound to a particular
- # svn revision via: "svn_revno=commit_sha1", filter them out here:
- my @exec_parents;
- foreach my $p (@parents) {
- next unless defined $p;
- if ($p =~ /^(\d+)=($sha1_short)$/o) {
- if ($1 == $log_msg->{revision}) {
- push @exec_parents, $2;
- }
- } else {
- push @exec_parents, $p if $p =~ /$sha1_short/o;
- }
- }
-
- my $pid = fork;
- defined $pid or croak $!;
- if ($pid == 0) {
- $ENV{GIT_INDEX_FILE} = $GIT_SVN_INDEX;
- git_addremove();
- chomp(my $tree = `git-write-tree`);
- croak if $?;
- my $msg_fh = IO::File->new_tmpfile or croak $!;
- print $msg_fh $log_msg->{msg}, "\ngit-svn-id: ",
- "$SVN_URL\@$log_msg->{revision}",
- " $uuid\n" or croak $!;
- $msg_fh->flush == 0 or croak $!;
- seek $msg_fh, 0, 0 or croak $!;
-
- $ENV{GIT_AUTHOR_NAME} = $ENV{GIT_COMMITTER_NAME} =
- $log_msg->{author};
- $ENV{GIT_AUTHOR_EMAIL} = $ENV{GIT_COMMITTER_EMAIL} =
- $log_msg->{author}."\@$uuid";
- $ENV{GIT_AUTHOR_DATE} = $ENV{GIT_COMMITTER_DATE} =
- $log_msg->{date};
- my @exec = ('git-commit-tree',$tree);
- push @exec, '-p', $_ foreach @exec_parents;
- open STDIN, '<&', $msg_fh or croak $!;
- open STDOUT, '>&', $out_fh or croak $!;
- exec @exec or croak $!;
- }
- waitpid($pid,0);
- croak if $?;
-
- $out_fh->flush == 0 or croak $!;
- seek $out_fh, 0, 0 or croak $!;
- chomp(my $commit = do { local $/; <$out_fh> });
- if ($commit !~ /^$sha1$/o) {
- croak "Failed to commit, invalid sha1: $commit\n";
- }
- my @update_ref = ('git-update-ref',"refs/heads/$GIT_SVN-HEAD",$commit);
- if (my $primary_parent = shift @exec_parents) {
- push @update_ref, $primary_parent;
- }
- sys(@update_ref);
- sys('git-update-ref',"$GIT_SVN/revs/$log_msg->{revision}",$commit);
- print "r$log_msg->{revision} = $commit\n";
- return $commit;
-}
-
-sub blob_to_symlink {
- my ($blob, $link) = @_;
- defined $link or croak "\$link not defined!\n";
- croak "Not a sha1: $blob\n" unless $blob =~ /^$sha1$/o;
- my $dest = `git-cat-file blob $blob`; # no newline, so no chomp
- symlink $dest, $link or croak $!;
-}
-
-sub blob_to_file {
- my ($blob, $file) = @_;
- defined $file or croak "\$file not defined!\n";
- croak "Not a sha1: $blob\n" unless $blob =~ /^$sha1$/o;
- open my $blob_fh, '>', $file or croak "$!: $file\n";
- my $pid = fork;
- defined $pid or croak $!;
-
- if ($pid == 0) {
- open STDOUT, '>&', $blob_fh or croak $!;
- exec('git-cat-file','blob',$blob);
- }
- waitpid $pid, 0;
- croak $? if $?;
-
- close $blob_fh or croak $!;
-}
-
-sub safe_qx {
- my $pid = open my $child, '-|';
- defined $pid or croak $!;
- if ($pid == 0) {
- exec(@_) or croak $?;
- }
- my @ret = (<$child>);
- close $child or croak $?;
- die $? if $?; # just in case close didn't error out
- return wantarray ? @ret : join('',@ret);
-}
-
-sub svn_check_ignore_externals {
- return if $_no_ignore_ext;
- unless (grep /ignore-externals/,(safe_qx(qw(svn co -h)))) {
- print STDERR "W: Installed svn version does not support ",
- "--ignore-externals\n";
- $_no_ignore_ext = 1;
- }
-}
-__END__
-
-Data structures:
-
-@svn_log = array of log_msg hashes
-
-$log_msg hash
-{
- msg => 'whitespace-formatted log entry
-', # trailing newline is preserved
- revision => '8', # integer
- date => '2004-02-24T17:01:44.108345Z', # commit date
- author => 'committer name'
-};
-
-
-@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,
- chg => change type [MCRAD],
- 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)
-}
-;
--- /dev/null
+#!/usr/bin/env perl
+# Copyright (C) 2006, Eric Wong <normalperson@yhbt.net>
+# License: GPL v2 or later
+use warnings;
+use strict;
+use vars qw/ $AUTHOR $VERSION
+ $SVN_URL $SVN_INFO $SVN_WC
+ $GIT_SVN_INDEX $GIT_SVN
+ $GIT_DIR $REV_DIR/;
+$AUTHOR = 'Eric Wong <normalperson@yhbt.net>';
+$VERSION = '0.9.1';
+$GIT_DIR = $ENV{GIT_DIR} || "$ENV{PWD}/.git";
+$GIT_SVN = $ENV{GIT_SVN_ID} || 'git-svn';
+$GIT_SVN_INDEX = "$GIT_DIR/$GIT_SVN/index";
+$ENV{GIT_DIR} ||= $GIT_DIR;
+$SVN_URL = undef;
+$REV_DIR = "$GIT_DIR/$GIT_SVN/revs";
+$SVN_WC = "$GIT_DIR/$GIT_SVN/tree";
+
+# make sure the svn binary gives consistent output between locales and TZs:
+$ENV{TZ} = 'UTC';
+$ENV{LC_ALL} = 'C';
+
+# If SVN:: library support is added, please make the dependencies
+# optional and preserve the capability to use the command-line client.
+# use eval { require SVN::... } to make it lazy load
+use Carp qw/croak/;
+use IO::File qw//;
+use File::Basename qw/dirname basename/;
+use File::Path qw/mkpath/;
+use Getopt::Long qw/:config gnu_getopt no_ignore_case auto_abbrev/;
+use File::Spec qw//;
+my $sha1 = qr/[a-f\d]{40}/;
+my $sha1_short = qr/[a-f\d]{6,40}/;
+my ($_revision,$_stdin,$_no_ignore_ext,$_no_stop_copy,$_help,$_rmdir,$_edit,
+ $_find_copies_harder, $_l, $_version);
+
+GetOptions( 'revision|r=s' => \$_revision,
+ 'no-ignore-externals' => \$_no_ignore_ext,
+ 'stdin|' => \$_stdin,
+ 'edit|e' => \$_edit,
+ 'rmdir' => \$_rmdir,
+ 'help|H|h' => \$_help,
+ 'find-copies-harder' => \$_find_copies_harder,
+ 'l=i' => \$_l,
+ 'version|V' => \$_version,
+ 'no-stop-on-copy' => \$_no_stop_copy );
+my %cmd = (
+ fetch => [ \&fetch, "Download new revisions from SVN" ],
+ init => [ \&init, "Initialize and fetch (import)"],
+ commit => [ \&commit, "Commit git revisions to SVN" ],
+ rebuild => [ \&rebuild, "Rebuild git-svn metadata (after git clone)" ],
+ help => [ \&usage, "Show help" ],
+);
+my $cmd;
+for (my $i = 0; $i < @ARGV; $i++) {
+ if (defined $cmd{$ARGV[$i]}) {
+ $cmd = $ARGV[$i];
+ splice @ARGV, $i, 1;
+ last;
+ }
+};
+
+# we may be called as git-svn-(command), or git-svn(command).
+foreach (keys %cmd) {
+ if (/git\-svn\-?($_)(?:\.\w+)?$/) {
+ $cmd = $1;
+ last;
+ }
+}
+usage(0) if $_help;
+version() if $_version;
+usage(1) unless (defined $cmd);
+svn_check_ignore_externals();
+$cmd{$cmd}->[0]->(@ARGV);
+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
+Available commands:
+
+ foreach (sort keys %cmd) {
+ print $fd ' ',pack('A10',$_),$cmd{$_}->[1],"\n";
+ }
+ print $fd <<"";
+\nGIT_SVN_ID may be set in the environment to an arbitrary identifier if
+you're tracking multiple SVN branches/repositories in one git repository
+and want to keep them separate.
+
+ exit $exit;
+}
+
+sub version {
+ print "git-svn version $VERSION\n";
+ exit 0;
+}
+
+sub rebuild {
+ $SVN_URL = shift or undef;
+ my $repo_uuid;
+ my $newest_rev = 0;
+
+ my $pid = open(my $rev_list,'-|');
+ defined $pid or croak $!;
+ if ($pid == 0) {
+ exec("git-rev-list","$GIT_SVN-HEAD") or croak $!;
+ }
+ my $first;
+ while (<$rev_list>) {
+ chomp;
+ my $c = $_;
+ croak "Non-SHA1: $c\n" unless $c =~ /^$sha1$/o;
+ my @commit = grep(/^git-svn-id: /,`git-cat-file commit $c`);
+ next if (!@commit); # skip merges
+ my $id = $commit[$#commit];
+ my ($url, $rev, $uuid) = ($id =~ /^git-svn-id:\s(\S+?)\@(\d+)
+ \s([a-f\d\-]+)$/x);
+ if (!$rev || !$uuid || !$url) {
+ # some of the original repositories I made had
+ # indentifiers like this:
+ ($rev, $uuid) = ($id =~/^git-svn-id:\s(\d+)
+ \@([a-f\d\-]+)/x);
+ if (!$rev || !$uuid) {
+ croak "Unable to extract revision or UUID from ",
+ "$c, $id\n";
+ }
+ }
+ print "r$rev = $c\n";
+ unless (defined $first) {
+ if (!$SVN_URL && !$url) {
+ croak "SVN repository location required: $url\n";
+ }
+ $SVN_URL ||= $url;
+ $repo_uuid = setup_git_svn();
+ $first = $rev;
+ }
+ if ($uuid ne $repo_uuid) {
+ croak "Repository UUIDs do not match!\ngot: $uuid\n",
+ "expected: $repo_uuid\n";
+ }
+ assert_revision_eq_or_unknown($rev, $c);
+ sys('git-update-ref',"$GIT_SVN/revs/$rev",$c);
+ $newest_rev = $rev if ($rev > $newest_rev);
+ }
+ close $rev_list or croak $?;
+ if (!chdir $SVN_WC) {
+ my @svn_co = ('svn','co',"-r$first");
+ push @svn_co, '--ignore-externals' unless $_no_ignore_ext;
+ sys(@svn_co, $SVN_URL, $SVN_WC);
+ chdir $SVN_WC or croak $!;
+ }
+
+ $pid = fork;
+ defined $pid or croak $!;
+ if ($pid == 0) {
+ my @svn_up = qw(svn up);
+ push @svn_up, '--ignore-externals' unless $_no_ignore_ext;
+ sys(@svn_up,"-r$newest_rev");
+ $ENV{GIT_INDEX_FILE} = $GIT_SVN_INDEX;
+ git_addremove();
+ exec('git-write-tree');
+ }
+ waitpid $pid, 0;
+}
+
+sub init {
+ $SVN_URL = shift or croak "SVN repository location required\n";
+ unless (-d $GIT_DIR) {
+ sys('git-init-db');
+ }
+ setup_git_svn();
+}
+
+sub fetch {
+ my (@parents) = @_;
+ $SVN_URL ||= file_to_s("$GIT_DIR/$GIT_SVN/info/url");
+ my @log_args = -d $SVN_WC ? ($SVN_WC) : ($SVN_URL);
+ unless ($_revision) {
+ $_revision = -d $SVN_WC ? 'BASE:HEAD' : '0:HEAD';
+ }
+ push @log_args, "-r$_revision";
+ push @log_args, '--stop-on-copy' unless $_no_stop_copy;
+
+ my $svn_log = svn_log_raw(@log_args);
+ @$svn_log = sort { $a->{revision} <=> $b->{revision} } @$svn_log;
+
+ my $base = shift @$svn_log or croak "No base revision!\n";
+ my $last_commit = undef;
+ unless (-d $SVN_WC) {
+ my @svn_co = ('svn','co',"-r$base->{revision}");
+ push @svn_co,'--ignore-externals' unless $_no_ignore_ext;
+ sys(@svn_co, $SVN_URL, $SVN_WC);
+ chdir $SVN_WC or croak $!;
+ $last_commit = git_commit($base, @parents);
+ unless (-f "$GIT_DIR/refs/heads/master") {
+ sys(qw(git-update-ref refs/heads/master),$last_commit);
+ }
+ assert_svn_wc_clean($base->{revision}, $last_commit);
+ } else {
+ chdir $SVN_WC or croak $!;
+ $last_commit = file_to_s("$REV_DIR/$base->{revision}");
+ }
+ my @svn_up = qw(svn up);
+ push @svn_up, '--ignore-externals' unless $_no_ignore_ext;
+ my $last_rev = $base->{revision};
+ foreach my $log_msg (@$svn_log) {
+ assert_svn_wc_clean($last_rev, $last_commit);
+ $last_rev = $log_msg->{revision};
+ sys(@svn_up,"-r$last_rev");
+ $last_commit = git_commit($log_msg, $last_commit, @parents);
+ }
+ assert_svn_wc_clean($last_rev, $last_commit);
+ return pop @$svn_log;
+}
+
+sub commit {
+ my (@commits) = @_;
+ if ($_stdin || !@commits) {
+ print "Reading from stdin...\n";
+ @commits = ();
+ while (<STDIN>) {
+ if (/\b([a-f\d]{6,40})\b/) {
+ unshift @commits, $1;
+ }
+ }
+ }
+ my @revs;
+ foreach my $c (@commits) {
+ chomp(my @tmp = safe_qx('git-rev-parse',$c));
+ if (scalar @tmp == 1) {
+ push @revs, $tmp[0];
+ } elsif (scalar @tmp > 1) {
+ push @revs, reverse (safe_qx('git-rev-list',@tmp));
+ } else {
+ die "Failed to rev-parse $c\n";
+ }
+ }
+ chomp @revs;
+
+ fetch();
+ chdir $SVN_WC or croak $!;
+ my $svn_current_rev = svn_info('.')->{'Last Changed Rev'};
+ foreach my $c (@revs) {
+ print "Committing $c\n";
+ my $mods = svn_checkout_tree($svn_current_rev, $c);
+ if (scalar @$mods == 0) {
+ print "Skipping, no changes detected\n";
+ next;
+ }
+ $svn_current_rev = svn_commit_tree($svn_current_rev, $c);
+ }
+ print "Done committing ",scalar @revs," revisions to SVN\n";
+
+}
+
+########################### utility functions #########################
+
+sub setup_git_svn {
+ defined $SVN_URL or croak "SVN repository location required\n";
+ unless (-d $GIT_DIR) {
+ croak "GIT_DIR=$GIT_DIR does not exist!\n";
+ }
+ mkpath(["$GIT_DIR/$GIT_SVN"]);
+ mkpath(["$GIT_DIR/$GIT_SVN/info"]);
+ mkpath([$REV_DIR]);
+ s_to_file($SVN_URL,"$GIT_DIR/$GIT_SVN/info/url");
+ my $uuid = svn_info($SVN_URL)->{'Repository UUID'} or
+ croak "Repository UUID unreadable\n";
+ s_to_file($uuid,"$GIT_DIR/$GIT_SVN/info/uuid");
+
+ open my $fd, '>>', "$GIT_DIR/$GIT_SVN/info/exclude" or croak $!;
+ print $fd '.svn',"\n";
+ close $fd or croak $!;
+ return $uuid;
+}
+
+sub assert_svn_wc_clean {
+ my ($svn_rev, $treeish) = @_;
+ croak "$svn_rev is not an integer!\n" unless ($svn_rev =~ /^\d+$/);
+ croak "$treeish is not a sha1!\n" unless ($treeish =~ /^$sha1$/o);
+ my $svn_info = svn_info('.');
+ if ($svn_rev != $svn_info->{'Last Changed Rev'}) {
+ croak "Expected r$svn_rev, got r",
+ $svn_info->{'Last Changed Rev'},"\n";
+ }
+ my @status = grep(!/^Performing status on external/,(`svn status`));
+ @status = grep(!/^\s*$/,@status);
+ if (scalar @status) {
+ print STDERR "Tree ($SVN_WC) is not clean:\n";
+ print STDERR $_ foreach @status;
+ croak;
+ }
+ assert_tree($treeish);
+}
+
+sub assert_tree {
+ my ($treeish) = @_;
+ croak "Not a sha1: $treeish\n" unless $treeish =~ /^$sha1$/o;
+ chomp(my $type = `git-cat-file -t $treeish`);
+ my $expected;
+ while ($type eq 'tag') {
+ chomp(($treeish, $type) = `git-cat-file tag $treeish`);
+ }
+ if ($type eq 'commit') {
+ $expected = (grep /^tree /,`git-cat-file commit $treeish`)[0];
+ ($expected) = ($expected =~ /^tree ($sha1)$/);
+ 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";
+ }
+
+ my $old_index = $ENV{GIT_INDEX_FILE};
+ my $tmpindex = $GIT_SVN_INDEX.'.assert-tmp';
+ if (-e $tmpindex) {
+ unlink $tmpindex or croak $!;
+ }
+ $ENV{GIT_INDEX_FILE} = $tmpindex;
+ git_addremove();
+ chomp(my $tree = `git-write-tree`);
+ if ($old_index) {
+ $ENV{GIT_INDEX_FILE} = $old_index;
+ } else {
+ delete $ENV{GIT_INDEX_FILE};
+ }
+ if ($tree ne $expected) {
+ croak "Tree mismatch, Got: $tree, Expected: $expected\n";
+ }
+}
+
+sub parse_diff_tree {
+ my $diff_fh = shift;
+ 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";
+ }
+ }
+ close $diff_fh or croak $!;
+
+ return \@mods;
+}
+
+sub svn_check_prop_executable {
+ my $m = shift;
+ return if -l $m->{file_b};
+ if ($m->{mode_b} =~ /755$/) {
+ chmod((0755 &~ umask),$m->{file_b}) or croak $!;
+ if ($m->{mode_a} !~ /755$/) {
+ sys(qw(svn propset svn:executable 1), $m->{file_b});
+ }
+ -x $m->{file_b} or croak "$m->{file_b} is not executable!\n";
+ } elsif ($m->{mode_b} !~ /755$/ && $m->{mode_a} =~ /755$/) {
+ sys(qw(svn propdel svn:executable), $m->{file_b});
+ chmod((0644 &~ umask),$m->{file_b}) or croak $!;
+ -x $m->{file_b} and croak "$m->{file_b} is executable!\n";
+ }
+}
+
+sub svn_ensure_parent_path {
+ my $dir_b = dirname(shift);
+ svn_ensure_parent_path($dir_b) if ($dir_b ne File::Spec->curdir);
+ mkpath([$dir_b]) unless (-d $dir_b);
+ sys(qw(svn add -N), $dir_b) unless (-d "$dir_b/.svn");
+}
+
+sub precommit_check {
+ my $mods = shift;
+ my (%rm_file, %rmdir_check, %added_check);
+
+ my %o = ( D => 0, R => 1, C => 2, A => 3, M => 3, T => 3 );
+ foreach my $m (sort { $o{$a->{chg}} <=> $o{$b->{chg}} } @$mods) {
+ if ($m->{chg} eq 'R') {
+ if (-d $m->{file_b}) {
+ err_dir_to_file("$m->{file_a} => $m->{file_b}");
+ }
+ # dir/$file => dir/file/$file
+ my $dirname = dirname($m->{file_b});
+ while ($dirname ne File::Spec->curdir) {
+ if ($dirname ne $m->{file_a}) {
+ $dirname = dirname($dirname);
+ next;
+ }
+ err_file_to_dir("$m->{file_a} => $m->{file_b}");
+ }
+ # baz/zzz => baz (baz is a file)
+ $dirname = dirname($m->{file_a});
+ while ($dirname ne File::Spec->curdir) {
+ if ($dirname ne $m->{file_b}) {
+ $dirname = dirname($dirname);
+ next;
+ }
+ err_dir_to_file("$m->{file_a} => $m->{file_b}");
+ }
+ }
+ if ($m->{chg} =~ /^(D|R)$/) {
+ my $t = $1 eq 'D' ? 'file_b' : 'file_a';
+ $rm_file{ $m->{$t} } = 1;
+ my $dirname = dirname( $m->{$t} );
+ my $basename = basename( $m->{$t} );
+ $rmdir_check{$dirname}->{$basename} = 1;
+ } elsif ($m->{chg} =~ /^(?:A|C)$/) {
+ if (-d $m->{file_b}) {
+ err_dir_to_file($m->{file_b});
+ }
+ my $dirname = dirname( $m->{file_b} );
+ my $basename = basename( $m->{file_b} );
+ $added_check{$dirname}->{$basename} = 1;
+ while ($dirname ne File::Spec->curdir) {
+ if ($rm_file{$dirname}) {
+ err_file_to_dir($m->{file_b});
+ }
+ $dirname = dirname $dirname;
+ }
+ }
+ }
+ return (\%rmdir_check, \%added_check);
+
+ sub err_dir_to_file {
+ my $file = shift;
+ print STDERR "Node change from directory to file ",
+ "is not supported by Subversion: ",$file,"\n";
+ exit 1;
+ }
+ sub err_file_to_dir {
+ my $file = shift;
+ print STDERR "Node change from file to directory ",
+ "is not supported by Subversion: ",$file,"\n";
+ exit 1;
+ }
+}
+
+sub svn_checkout_tree {
+ my ($svn_rev, $treeish) = @_;
+ my $from = file_to_s("$REV_DIR/$svn_rev");
+ assert_svn_wc_clean($svn_rev,$from);
+ print "diff-tree '$from' '$treeish'\n";
+ my $pid = open my $diff_fh, '-|';
+ defined $pid or croak $!;
+ if ($pid == 0) {
+ my @diff_tree = qw(git-diff-tree -z -r -C);
+ push @diff_tree, '--find-copies-harder' if $_find_copies_harder;
+ push @diff_tree, "-l$_l" if defined $_l;
+ exec(@diff_tree, $from, $treeish) or croak $!;
+ }
+ my $mods = parse_diff_tree($diff_fh);
+ unless (@$mods) {
+ # git can do empty commits, SVN doesn't allow it...
+ return $mods;
+ }
+ my ($rm, $add) = precommit_check($mods);
+
+ my %o = ( D => 1, R => 0, C => -1, A => 3, M => 3, T => 3 );
+ foreach my $m (sort { $o{$a->{chg}} <=> $o{$b->{chg}} } @$mods) {
+ if ($m->{chg} eq 'C') {
+ svn_ensure_parent_path( $m->{file_b} );
+ sys(qw(svn cp), $m->{file_a}, $m->{file_b});
+ apply_mod_line_blob($m);
+ svn_check_prop_executable($m);
+ } elsif ($m->{chg} eq 'D') {
+ sys(qw(svn rm --force), $m->{file_b});
+ } elsif ($m->{chg} eq 'R') {
+ svn_ensure_parent_path( $m->{file_b} );
+ sys(qw(svn mv --force), $m->{file_a}, $m->{file_b});
+ apply_mod_line_blob($m);
+ svn_check_prop_executable($m);
+ } elsif ($m->{chg} eq 'M') {
+ apply_mod_line_blob($m);
+ svn_check_prop_executable($m);
+ } elsif ($m->{chg} eq 'T') {
+ sys(qw(svn rm --force),$m->{file_b});
+ apply_mod_line_blob($m);
+ sys(qw(svn add --force), $m->{file_b});
+ svn_check_prop_executable($m);
+ } elsif ($m->{chg} eq 'A') {
+ svn_ensure_parent_path( $m->{file_b} );
+ apply_mod_line_blob($m);
+ sys(qw(svn add --force), $m->{file_b});
+ svn_check_prop_executable($m);
+ } else {
+ croak "Invalid chg: $m->{chg}\n";
+ }
+ }
+
+ assert_tree($treeish);
+ if ($_rmdir) { # remove empty directories
+ handle_rmdir($rm, $add);
+ }
+ assert_tree($treeish);
+ return $mods;
+}
+
+# svn ls doesn't work with respect to the current working tree, but what's
+# in the repository. There's not even an option for it... *sigh*
+# (added files don't show up and removed files remain in the ls listing)
+sub svn_ls_current {
+ my ($dir, $rm, $add) = @_;
+ chomp(my @ls = safe_qx('svn','ls',$dir));
+ my @ret = ();
+ foreach (@ls) {
+ s#/$##; # trailing slashes are evil
+ push @ret, $_ unless $rm->{$dir}->{$_};
+ }
+ if (exists $add->{$dir}) {
+ push @ret, keys %{$add->{$dir}};
+ }
+ return \@ret;
+}
+
+sub handle_rmdir {
+ my ($rm, $add) = @_;
+
+ foreach my $dir (sort {length $b <=> length $a} keys %$rm) {
+ my $ls = svn_ls_current($dir, $rm, $add);
+ next if (scalar @$ls);
+ sys(qw(svn rm --force),$dir);
+
+ my $dn = dirname $dir;
+ $rm->{ $dn }->{ basename $dir } = 1;
+ $ls = svn_ls_current($dn, $rm, $add);
+ while (scalar @$ls == 0 && $dn ne File::Spec->curdir) {
+ sys(qw(svn rm --force),$dn);
+ $dir = basename $dn;
+ $dn = dirname $dn;
+ $rm->{ $dn }->{ $dir } = 1;
+ $ls = svn_ls_current($dn, $rm, $add);
+ }
+ }
+}
+
+sub svn_commit_tree {
+ my ($svn_rev, $commit) = @_;
+ my $commit_msg = "$GIT_DIR/$GIT_SVN/.svn-commit.tmp.$$";
+ open my $msg, '>', $commit_msg or croak $!;
+
+ chomp(my $type = `git-cat-file -t $commit`);
+ if ($type eq 'commit') {
+ my $pid = open my $msg_fh, '-|';
+ defined $pid or croak $!;
+
+ if ($pid == 0) {
+ exec(qw(git-cat-file commit), $commit) or croak $!;
+ }
+ my $in_msg = 0;
+ while (<$msg_fh>) {
+ if (!$in_msg) {
+ $in_msg = 1 if (/^\s*$/);
+ } else {
+ print $msg $_ or croak $!;
+ }
+ }
+ close $msg_fh or croak $!;
+ }
+ close $msg or croak $!;
+
+ if ($_edit || ($type eq 'tree')) {
+ my $editor = $ENV{VISUAL} || $ENV{EDITOR} || 'vi';
+ system($editor, $commit_msg);
+ }
+ my @ci_output = safe_qx(qw(svn commit -F),$commit_msg);
+ my ($committed) = grep(/^Committed revision \d+\./,@ci_output);
+ unlink $commit_msg;
+ defined $committed or croak
+ "Commit output failed to parse committed revision!\n",
+ join("\n",@ci_output),"\n";
+ my ($rev_committed) = ($committed =~ /^Committed revision (\d+)\./);
+
+ # resync immediately
+ my @svn_up = (qw(svn up), "-r$svn_rev");
+ push @svn_up, '--ignore-externals' unless $_no_ignore_ext;
+ sys(@svn_up);
+ return fetch("$rev_committed=$commit")->{revision};
+}
+
+sub svn_log_raw {
+ my (@log_args) = @_;
+ my $pid = open my $log_fh,'-|';
+ defined $pid or croak $!;
+
+ if ($pid == 0) {
+ exec (qw(svn log), @log_args) or croak $!
+ }
+
+ my @svn_log;
+ my $state = 'sep';
+ while (<$log_fh>) {
+ chomp;
+ if (/^\-{72}$/) {
+ if ($state eq 'msg') {
+ if ($svn_log[$#svn_log]->{lines}) {
+ $svn_log[$#svn_log]->{msg} .= $_."\n";
+ unless(--$svn_log[$#svn_log]->{lines}) {
+ $state = 'sep';
+ }
+ } else {
+ croak "Log parse error at: $_\n",
+ $svn_log[$#svn_log]->{revision},
+ "\n";
+ }
+ next;
+ }
+ if ($state ne 'sep') {
+ croak "Log parse error at: $_\n",
+ "state: $state\n",
+ $svn_log[$#svn_log]->{revision},
+ "\n";
+ }
+ $state = 'rev';
+
+ # if we have an empty log message, put something there:
+ if (@svn_log) {
+ $svn_log[$#svn_log]->{msg} ||= "\n";
+ delete $svn_log[$#svn_log]->{lines};
+ }
+ next;
+ }
+ if ($state eq 'rev' && s/^r(\d+)\s*\|\s*//) {
+ my $rev = $1;
+ my ($author, $date, $lines) = split(/\s*\|\s*/, $_, 3);
+ ($lines) = ($lines =~ /(\d+)/);
+ my ($Y,$m,$d,$H,$M,$S,$tz) = ($date =~
+ /(\d{4})\-(\d\d)\-(\d\d)\s
+ (\d\d)\:(\d\d)\:(\d\d)\s([\-\+]\d+)/x)
+ or croak "Failed to parse date: $date\n";
+ my %log_msg = ( revision => $rev,
+ date => "$tz $Y-$m-$d $H:$M:$S",
+ author => $author,
+ lines => $lines,
+ msg => '' );
+ push @svn_log, \%log_msg;
+ $state = 'msg_start';
+ next;
+ }
+ # skip the first blank line of the message:
+ if ($state eq 'msg_start' && /^$/) {
+ $state = 'msg';
+ } elsif ($state eq 'msg') {
+ if ($svn_log[$#svn_log]->{lines}) {
+ $svn_log[$#svn_log]->{msg} .= $_."\n";
+ unless (--$svn_log[$#svn_log]->{lines}) {
+ $state = 'sep';
+ }
+ } else {
+ croak "Log parse error at: $_\n",
+ $svn_log[$#svn_log]->{revision},"\n";
+ }
+ }
+ }
+ close $log_fh or croak $?;
+ return \@svn_log;
+}
+
+sub svn_info {
+ my $url = shift || $SVN_URL;
+
+ my $pid = open my $info_fh, '-|';
+ defined $pid or croak $!;
+
+ if ($pid == 0) {
+ exec(qw(svn info),$url) or croak $!;
+ }
+
+ my $ret = {};
+ # only single-lines seem to exist in svn info output
+ while (<$info_fh>) {
+ chomp $_;
+ if (m#^([^:]+)\s*:\s*(\S*)$#) {
+ $ret->{$1} = $2;
+ push @{$ret->{-order}}, $1;
+ }
+ }
+ close $info_fh or croak $!;
+ return $ret;
+}
+
+sub sys { system(@_) == 0 or croak $? }
+
+sub git_addremove {
+ system( "git-diff-files --name-only -z ".
+ " | git-update-index --remove -z --stdin && ".
+ "git-ls-files -z --others ".
+ "'--exclude-from=$GIT_DIR/$GIT_SVN/info/exclude'".
+ " | git-update-index --add -z --stdin"
+ ) == 0 or croak $?
+}
+
+sub s_to_file {
+ my ($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;
+}
+
+sub assert_revision_unknown {
+ my $revno = shift;
+ if (-f "$REV_DIR/$revno") {
+ croak "$REV_DIR/$revno already exists! ",
+ "Why are we refetching it?";
+ }
+}
+
+sub assert_revision_eq_or_unknown {
+ my ($revno, $commit) = @_;
+ if (-f "$REV_DIR/$revno") {
+ my $current = file_to_s("$REV_DIR/$revno");
+ if ($commit ne $current) {
+ croak "$REV_DIR/$revno already exists!\n",
+ "current: $current\nexpected: $commit\n";
+ }
+ return;
+ }
+}
+
+sub git_commit {
+ my ($log_msg, @parents) = @_;
+ assert_revision_unknown($log_msg->{revision});
+ my $out_fh = IO::File->new_tmpfile or croak $!;
+ my $info = svn_info('.');
+ my $uuid = $info->{'Repository UUID'};
+ defined $uuid or croak "Unable to get Repository UUID\n";
+
+ # commit parents can be conditionally bound to a particular
+ # svn revision via: "svn_revno=commit_sha1", filter them out here:
+ my @exec_parents;
+ foreach my $p (@parents) {
+ next unless defined $p;
+ if ($p =~ /^(\d+)=($sha1_short)$/o) {
+ if ($1 == $log_msg->{revision}) {
+ push @exec_parents, $2;
+ }
+ } else {
+ push @exec_parents, $p if $p =~ /$sha1_short/o;
+ }
+ }
+
+ my $pid = fork;
+ defined $pid or croak $!;
+ if ($pid == 0) {
+ $ENV{GIT_INDEX_FILE} = $GIT_SVN_INDEX;
+ git_addremove();
+ chomp(my $tree = `git-write-tree`);
+ croak if $?;
+ my $msg_fh = IO::File->new_tmpfile or croak $!;
+ print $msg_fh $log_msg->{msg}, "\ngit-svn-id: ",
+ "$SVN_URL\@$log_msg->{revision}",
+ " $uuid\n" or croak $!;
+ $msg_fh->flush == 0 or croak $!;
+ seek $msg_fh, 0, 0 or croak $!;
+
+ $ENV{GIT_AUTHOR_NAME} = $ENV{GIT_COMMITTER_NAME} =
+ $log_msg->{author};
+ $ENV{GIT_AUTHOR_EMAIL} = $ENV{GIT_COMMITTER_EMAIL} =
+ $log_msg->{author}."\@$uuid";
+ $ENV{GIT_AUTHOR_DATE} = $ENV{GIT_COMMITTER_DATE} =
+ $log_msg->{date};
+ my @exec = ('git-commit-tree',$tree);
+ push @exec, '-p', $_ foreach @exec_parents;
+ open STDIN, '<&', $msg_fh or croak $!;
+ open STDOUT, '>&', $out_fh or croak $!;
+ exec @exec or croak $!;
+ }
+ waitpid($pid,0);
+ croak if $?;
+
+ $out_fh->flush == 0 or croak $!;
+ seek $out_fh, 0, 0 or croak $!;
+ chomp(my $commit = do { local $/; <$out_fh> });
+ if ($commit !~ /^$sha1$/o) {
+ croak "Failed to commit, invalid sha1: $commit\n";
+ }
+ my @update_ref = ('git-update-ref',"refs/heads/$GIT_SVN-HEAD",$commit);
+ if (my $primary_parent = shift @exec_parents) {
+ push @update_ref, $primary_parent;
+ }
+ sys(@update_ref);
+ sys('git-update-ref',"$GIT_SVN/revs/$log_msg->{revision}",$commit);
+ print "r$log_msg->{revision} = $commit\n";
+ return $commit;
+}
+
+sub apply_mod_line_blob {
+ my $m = shift;
+ if ($m->{mode_b} =~ /^120/) {
+ blob_to_symlink($m->{sha1_b}, $m->{file_b});
+ } else {
+ blob_to_file($m->{sha1_b}, $m->{file_b});
+ }
+}
+
+sub blob_to_symlink {
+ my ($blob, $link) = @_;
+ defined $link or croak "\$link not defined!\n";
+ croak "Not a sha1: $blob\n" unless $blob =~ /^$sha1$/o;
+ if (-l $link || -f _) {
+ unlink $link or croak $!;
+ }
+
+ my $dest = `git-cat-file blob $blob`; # no newline, so no chomp
+ symlink $dest, $link or croak $!;
+}
+
+sub blob_to_file {
+ my ($blob, $file) = @_;
+ defined $file or croak "\$file not defined!\n";
+ croak "Not a sha1: $blob\n" unless $blob =~ /^$sha1$/o;
+ if (-l $file || -f _) {
+ unlink $file or croak $!;
+ }
+
+ open my $blob_fh, '>', $file or croak "$!: $file\n";
+ my $pid = fork;
+ defined $pid or croak $!;
+
+ if ($pid == 0) {
+ open STDOUT, '>&', $blob_fh or croak $!;
+ exec('git-cat-file','blob',$blob);
+ }
+ waitpid $pid, 0;
+ croak $? if $?;
+
+ close $blob_fh or croak $!;
+}
+
+sub safe_qx {
+ my $pid = open my $child, '-|';
+ defined $pid or croak $!;
+ if ($pid == 0) {
+ exec(@_) or croak $?;
+ }
+ my @ret = (<$child>);
+ close $child or croak $?;
+ die $? if $?; # just in case close didn't error out
+ return wantarray ? @ret : join('',@ret);
+}
+
+sub svn_check_ignore_externals {
+ return if $_no_ignore_ext;
+ unless (grep /ignore-externals/,(safe_qx(qw(svn co -h)))) {
+ print STDERR "W: Installed svn version does not support ",
+ "--ignore-externals\n";
+ $_no_ignore_ext = 1;
+ }
+}
+__END__
+
+Data structures:
+
+@svn_log = array of log_msg hashes
+
+$log_msg hash
+{
+ msg => 'whitespace-formatted log entry
+', # trailing newline is preserved
+ revision => '8', # integer
+ date => '2004-02-24T17:01:44.108345Z', # commit date
+ author => 'committer name'
+};
+
+
+@mods = array of diff-index line hashes, each element represents one line
+ of diff-index output
+
+diff-index line ($m hash)
+{
+ mode_a => first column of diff-index output, no leading ':',
+ mode_b => second column of diff-index output,
+ sha1_b => sha1sum of the final blob,
+ chg => change type [MCRAD],
+ file_a => original file name of a file (iff chg is 'C' or 'R')
+ file_b => new/current file name of a file (any chg)
+}
+;
default for objects that are commits, and forced on when committing
tree objects.
+-l<num>::
+--find-copies-harder::
+ Both of these are only used with the 'commit' command.
+
+ They are both passed directly to git-diff-tree see
+ git-diff-tree(1) for more information.
+
COMPATIBILITY OPTIONS
---------------------
--no-ignore-externals::
# Commit only the git commits you want to SVN::
git-svn commit <tree-ish> [<tree-ish_2> ...]
# Commit all the git commits from my-branch that don't exist in SVN::
- git rev-list --pretty=oneline git-svn-HEAD..my-branch | git-svn commit
+ git commit git-svn-HEAD..my-branch
# Something is committed to SVN, pull the latest into your branch::
git-svn fetch && git pull . git-svn-HEAD
svn:keywords can't be ignored in Subversion (at least I don't know of
a way to ignore them).
+Renamed and copied directories are not detected by git and hence not
+tracked when committing to SVN. I do not plan on adding support for
+this as it's quite difficult and time-consuming to get working for all
+the possible corner cases (git doesn't do it, either). Renamed and
+copied files are fully supported if they're similar enough for git to
+detect them.
+
Author
------
Written by Eric Wong <normalperson@yhbt.net>.
--- /dev/null
+#!/bin/sh
+#
+# Copyright (c) 2006 Eric Wong
+#
+
+
+PATH=$PWD/../:$PATH
+test_description='git-svn tests'
+if test -d ../../../t
+then
+ cd ../../../t
+else
+ echo "Must be run in contrib/git-svn/t" >&2
+ exit 1
+fi
+
+. ./test-lib.sh
+
+GIT_DIR=$PWD/.git
+GIT_SVN_DIR=$GIT_DIR/git-svn
+SVN_TREE=$GIT_SVN_DIR/tree
+
+svnadmin >/dev/null 2>&1
+if test $? != 1
+then
+ test_expect_success 'skipping contrib/git-svn test' :
+ test_done
+ exit
+fi
+
+svn >/dev/null 2>&1
+if test $? != 1
+then
+ test_expect_success 'skipping contrib/git-svn test' :
+ test_done
+ exit
+fi
+
+svnrepo=$PWD/svnrepo
+
+set -e
+
+svnadmin create $svnrepo
+svnrepo="file://$svnrepo/test-git-svn"
+
+mkdir import
+
+cd import
+
+echo foo > foo
+ln -s foo foo.link
+mkdir -p dir/a/b/c/d/e
+echo 'deep dir' > dir/a/b/c/d/e/file
+mkdir -p bar
+echo 'zzz' > bar/zzz
+echo '#!/bin/sh' > exec.sh
+chmod +x exec.sh
+svn import -m 'import for git-svn' . $svnrepo >/dev/null
+
+cd ..
+
+rm -rf import
+
+test_expect_success \
+ 'initialize git-svn' \
+ "git-svn init $svnrepo"
+
+test_expect_success \
+ 'import an SVN revision into git' \
+ 'git-svn fetch'
+
+
+name='try a deep --rmdir with a commit'
+git checkout -b mybranch git-svn-HEAD
+mv dir/a/b/c/d/e/file dir/file
+cp dir/file file
+git update-index --add --remove dir/a/b/c/d/e/file dir/file file
+git commit -m "$name"
+
+test_expect_success "$name" \
+ "git-svn commit --find-copies-harder --rmdir git-svn-HEAD..mybranch &&
+ test -d $SVN_TREE/dir && test ! -d $SVN_TREE/dir/a"
+
+
+name='detect node change from file to directory #1'
+mkdir dir/new_file
+mv dir/file dir/new_file/file
+mv dir/new_file dir/file
+git update-index --remove dir/file
+git update-index --add dir/file/file
+git commit -m "$name"
+
+test_expect_code 1 "$name" \
+ 'git-svn commit --find-copies-harder --rmdir git-svn-HEAD..mybranch' \
+ || true
+
+
+name='detect node change from directory to file #1'
+rm -rf dir $GIT_DIR/index
+git checkout -b mybranch2 git-svn-HEAD
+mv bar/zzz zzz
+rm -rf bar
+mv zzz bar
+git update-index --remove -- bar/zzz
+git update-index --add -- bar
+git commit -m "$name"
+
+test_expect_code 1 "$name" \
+ 'git-svn commit --find-copies-harder --rmdir git-svn-HEAD..mybranch2' \
+ || true
+
+
+name='detect node change from file to directory #2'
+rm -f $GIT_DIR/index
+git checkout -b mybranch3 git-svn-HEAD
+rm bar/zzz
+git-update-index --remove bar/zzz
+mkdir bar/zzz
+echo yyy > bar/zzz/yyy
+git-update-index --add bar/zzz/yyy
+git commit -m "$name"
+
+test_expect_code 1 "$name" \
+ 'git-svn commit --find-copies-harder --rmdir git-svn-HEAD..mybranch3' \
+ || true
+
+
+name='detect node change from directory to file #2'
+rm -f $GIT_DIR/index
+git checkout -b mybranch4 git-svn-HEAD
+rm -rf dir
+git update-index --remove -- dir/file
+touch dir
+echo asdf > dir
+git update-index --add -- dir
+git commit -m "$name"
+
+test_expect_code 1 "$name" \
+ 'git-svn commit --find-copies-harder --rmdir git-svn-HEAD..mybranch4' \
+ || true
+
+
+name='remove executable bit from a file'
+rm -f $GIT_DIR/index
+git checkout -b mybranch5 git-svn-HEAD
+chmod -x exec.sh
+git update-index exec.sh
+git commit -m "$name"
+
+test_expect_success "$name" \
+ "git-svn commit --find-copies-harder --rmdir git-svn-HEAD..mybranch5 &&
+ test ! -x $SVN_TREE/exec.sh"
+
+
+name='add executable bit back file'
+chmod +x exec.sh
+git update-index exec.sh
+git commit -m "$name"
+
+test_expect_success "$name" \
+ "git-svn commit --find-copies-harder --rmdir git-svn-HEAD..mybranch5 &&
+ test -x $SVN_TREE/exec.sh"
+
+
+
+name='executable file becomes a symlink to bar/zzz (file)'
+rm exec.sh
+ln -s bar/zzz exec.sh
+git update-index exec.sh
+git commit -m "$name"
+
+test_expect_success "$name" \
+ "git-svn commit --find-copies-harder --rmdir git-svn-HEAD..mybranch5 &&
+ test -L $SVN_TREE/exec.sh"
+
+
+
+name='new symlink is added to a file that was also just made executable'
+chmod +x bar/zzz
+ln -s bar/zzz exec-2.sh
+git update-index --add bar/zzz exec-2.sh
+git commit -m "$name"
+
+test_expect_success "$name" \
+ "git-svn commit --find-copies-harder --rmdir git-svn-HEAD..mybranch5 &&
+ test -x $SVN_TREE/bar/zzz &&
+ test -L $SVN_TREE/exec-2.sh"
+
+
+
+name='modify a symlink to become a file'
+git help > help || true
+rm exec-2.sh
+cp help exec-2.sh
+git update-index exec-2.sh
+git commit -m "$name"
+
+test_expect_success "$name" \
+ "git-svn commit --find-copies-harder --rmdir git-svn-HEAD..mybranch5 &&
+ test -f $SVN_TREE/exec-2.sh &&
+ test ! -L $SVN_TREE/exec-2.sh &&
+ diff -u help $SVN_TREE/exec-2.sh"
+
+
+
+name='test fetch functionality (svn => git) with alternate GIT_SVN_ID'
+GIT_SVN_ID=alt
+export GIT_SVN_ID
+test_expect_success "$name" \
+ "git-svn init $svnrepo && git-svn fetch -v &&
+ git-rev-list --pretty=raw git-svn-HEAD | grep ^tree | uniq > a &&
+ git-rev-list --pretty=raw alt-HEAD | grep ^tree | uniq > b &&
+ diff -u a b"
+
+test_done
+
--- /dev/null
+#!/usr/bin/perl
+# Copyright 2006, Ryan Anderson <ryan@michonline.com>
+#
+# GPL v2 (See COPYING)
+#
+# This file is licensed under the GPL v2, or a later version
+# at the discretion of Linus Torvalds.
+
+use warnings;
+use strict;
+
+my $filename = shift @ARGV;
+
+
+my @stack = (
+ {
+ 'rev' => "HEAD",
+ 'filename' => $filename,
+ },
+);
+
+our (@lineoffsets, @pendinglineoffsets);
+our @filelines = ();
+open(F,"<",$filename)
+ or die "Failed to open filename: $!";
+
+while(<F>) {
+ chomp;
+ push @filelines, $_;
+}
+close(F);
+our $leftover_lines = @filelines;
+our %revs;
+our @revqueue;
+our $head;
+
+my $revsprocessed = 0;
+while (my $bound = pop @stack) {
+ my @revisions = git_rev_list($bound->{'rev'}, $bound->{'filename'});
+ foreach my $revinst (@revisions) {
+ my ($rev, @parents) = @$revinst;
+ $head ||= $rev;
+
+ $revs{$rev}{'filename'} = $bound->{'filename'};
+ if (scalar @parents > 0) {
+ $revs{$rev}{'parents'} = \@parents;
+ next;
+ }
+
+ my $newbound = find_parent_renames($rev, $bound->{'filename'});
+ if ( exists $newbound->{'filename'} && $newbound->{'filename'} ne $bound->{'filename'}) {
+ push @stack, $newbound;
+ $revs{$rev}{'parents'} = [$newbound->{'rev'}];
+ }
+ }
+}
+push @revqueue, $head;
+init_claim($head);
+$revs{$head}{'lineoffsets'} = {};
+handle_rev();
+
+
+my $i = 0;
+foreach my $l (@filelines) {
+ my ($output, $rev, $committer, $date);
+ if (ref $l eq 'ARRAY') {
+ ($output, $rev, $committer, $date) = @$l;
+ if (length($rev) > 8) {
+ $rev = substr($rev,0,8);
+ }
+ } else {
+ $output = $l;
+ ($rev, $committer, $date) = ('unknown', 'unknown', 'unknown');
+ }
+
+ printf("(%8s %10s %10s %d)%s\n", $rev, $committer, $date, $i++, $output);
+}
+
+sub init_claim {
+ my ($rev) = @_;
+ my %revinfo = git_commit_info($rev);
+ for (my $i = 0; $i < @filelines; $i++) {
+ $filelines[$i] = [ $filelines[$i], '', '', '', 1];
+ # line,
+ # rev,
+ # author,
+ # date,
+ # 1 <-- belongs to the original file.
+ }
+ $revs{$rev}{'lines'} = \@filelines;
+}
+
+
+sub handle_rev {
+ my $i = 0;
+ while (my $rev = shift @revqueue) {
+
+ my %revinfo = git_commit_info($rev);
+
+ foreach my $p (@{$revs{$rev}{'parents'}}) {
+
+ git_diff_parse($p, $rev, %revinfo);
+ push @revqueue, $p;
+ }
+
+
+ if (scalar @{$revs{$rev}{parents}} == 0) {
+ # We must be at the initial rev here, so claim everything that is left.
+ for (my $i = 0; $i < @{$revs{$rev}{lines}}; $i++) {
+ if (ref ${$revs{$rev}{lines}}[$i] eq '' || ${$revs{$rev}{lines}}[$i][1] eq '') {
+ claim_line($i, $rev, $revs{$rev}{lines}, %revinfo);
+ }
+ }
+ }
+ }
+}
+
+
+sub git_rev_list {
+ my ($rev, $file) = @_;
+
+ open(P,"-|","git-rev-list","--parents","--remove-empty",$rev,"--",$file)
+ or die "Failed to exec git-rev-list: $!";
+
+ my @revs;
+ while(my $line = <P>) {
+ chomp $line;
+ my ($rev, @parents) = split /\s+/, $line;
+ push @revs, [ $rev, @parents ];
+ }
+ close(P);
+
+ printf("0 revs found for rev %s (%s)\n", $rev, $file) if (@revs == 0);
+ return @revs;
+}
+
+sub find_parent_renames {
+ my ($rev, $file) = @_;
+
+ open(P,"-|","git-diff-tree", "-M50", "-r","--name-status", "-z","$rev")
+ or die "Failed to exec git-diff: $!";
+
+ local $/ = "\0";
+ my %bound;
+ my $junk = <P>;
+ while (my $change = <P>) {
+ chomp $change;
+ my $filename = <P>;
+ chomp $filename;
+
+ if ($change =~ m/^[AMD]$/ ) {
+ next;
+ } elsif ($change =~ m/^R/ ) {
+ my $oldfilename = $filename;
+ $filename = <P>;
+ chomp $filename;
+ if ( $file eq $filename ) {
+ my $parent = git_find_parent($rev, $oldfilename);
+ @bound{'rev','filename'} = ($parent, $oldfilename);
+ last;
+ }
+ }
+ }
+ close(P);
+
+ return \%bound;
+}
+
+
+sub git_find_parent {
+ my ($rev, $filename) = @_;
+
+ open(REVPARENT,"-|","git-rev-list","--remove-empty", "--parents","--max-count=1","$rev","--",$filename)
+ or die "Failed to open git-rev-list to find a single parent: $!";
+
+ my $parentline = <REVPARENT>;
+ chomp $parentline;
+ my ($revfound,$parent) = split m/\s+/, $parentline;
+
+ close(REVPARENT);
+
+ return $parent;
+}
+
+
+# Get a diff between the current revision and a parent.
+# Record the commit information that results.
+sub git_diff_parse {
+ my ($parent, $rev, %revinfo) = @_;
+
+ my ($ri, $pi) = (0,0);
+ open(DIFF,"-|","git-diff-tree","-M","-p",$rev,$parent,"--",
+ $revs{$rev}{'filename'}, $revs{$parent}{'filename'})
+ or die "Failed to call git-diff for annotation: $!";
+
+ my $slines = $revs{$rev}{'lines'};
+ my @plines;
+
+ my $gotheader = 0;
+ my ($remstart, $remlength, $addstart, $addlength);
+ my ($hunk_start, $hunk_index, $hunk_adds);
+ while(<DIFF>) {
+ chomp;
+ if (m/^@@ -(\d+),(\d+) \+(\d+),(\d+)/) {
+ ($remstart, $remlength, $addstart, $addlength) = ($1, $2, $3, $4);
+ # Adjust for 0-based arrays
+ $remstart--;
+ $addstart--;
+ # Reinit hunk tracking.
+ $hunk_start = $remstart;
+ $hunk_index = 0;
+ $gotheader = 1;
+
+ for (my $i = $ri; $i < $remstart; $i++) {
+ $plines[$pi++] = $slines->[$i];
+ $ri++;
+ }
+ next;
+ } elsif (!$gotheader) {
+ next;
+ }
+
+ if (m/^\+(.*)$/) {
+ my $line = $1;
+ $plines[$pi++] = [ $line, '', '', '', 0 ];
+ next;
+
+ } elsif (m/^-(.*)$/) {
+ my $line = $1;
+ if (get_line($slines, $ri) eq $line) {
+ # Found a match, claim
+ claim_line($ri, $rev, $slines, %revinfo);
+ } else {
+ die sprintf("Sync error: %d/%d\n|%s\n|%s\n%s => %s\n",
+ $ri, $hunk_start + $hunk_index,
+ $line,
+ get_line($slines, $ri),
+ $rev, $parent);
+ }
+ $ri++;
+
+ } else {
+ if (substr($_,1) ne get_line($slines,$ri) ) {
+ die sprintf("Line %d (%d) does not match:\n|%s\n|%s\n%s => %s\n",
+ $hunk_start + $hunk_index, $ri,
+ substr($_,1),
+ get_line($slines,$ri),
+ $rev, $parent);
+ }
+ $plines[$pi++] = $slines->[$ri++];
+ }
+ $hunk_index++;
+ }
+ close(DIFF);
+ for (my $i = $ri; $i < @{$slines} ; $i++) {
+ push @plines, $slines->[$ri++];
+ }
+
+ $revs{$parent}{lines} = \@plines;
+ return;
+}
+
+sub get_line {
+ my ($lines, $index) = @_;
+
+ return ref $lines->[$index] ne '' ? $lines->[$index][0] : $lines->[$index];
+}
+
+sub git_cat_file {
+ my ($parent, $filename) = @_;
+ return () unless defined $parent && defined $filename;
+ my $blobline = `git-ls-tree $parent $filename`;
+ my ($mode, $type, $blob, $tfilename) = split(/\s+/, $blobline, 4);
+
+ open(C,"-|","git-cat-file", "blob", $blob)
+ or die "Failed to git-cat-file blob $blob (rev $parent, file $filename): " . $!;
+
+ my @lines;
+ while(<C>) {
+ chomp;
+ push @lines, $_;
+ }
+ close(C);
+
+ return @lines;
+}
+
+
+sub claim_line {
+ my ($floffset, $rev, $lines, %revinfo) = @_;
+ my $oline = get_line($lines, $floffset);
+ @{$lines->[$floffset]} = ( $oline, $rev,
+ $revinfo{'author'}, $revinfo{'author_date'} );
+ #printf("Claiming line %d with rev %s: '%s'\n",
+ # $floffset, $rev, $oline) if 1;
+}
+
+sub git_commit_info {
+ my ($rev) = @_;
+ open(COMMIT, "-|","git-cat-file", "commit", $rev)
+ or die "Failed to call git-cat-file: $!";
+
+ my %info;
+ while(<COMMIT>) {
+ chomp;
+ last if (length $_ == 0);
+
+ if (m/^author (.*) <(.*)> (.*)$/) {
+ $info{'author'} = $1;
+ $info{'author_email'} = $2;
+ $info{'author_date'} = $3;
+ } elsif (m/^committer (.*) <(.*)> (.*)$/) {
+ $info{'committer'} = $1;
+ $info{'committer_email'} = $2;
+ $info{'committer_date'} = $3;
+ }
+ }
+ close(COMMIT);
+
+ return %info;
+}