![[tokkee]](http://tokkee.org/images/avatar.png){kind=avatar}
diff --git a/git-svn.perl b/git-svn.perl
index b1245cbab2ec7303482d7405e594ba666dfc3f58..24bdbf5b813ddd6c7f242189b9bb22fbe7dfff11 100755 (executable)
--- a/git-svn.perl
+++ b/git-svn.perl
$Git::SVN::default_repo_id = 'svn';
$Git::SVN::default_ref_id = $ENV{GIT_SVN_ID} || 'git-svn';
$Git::SVN::Ra::_log_window_size = 100;
+$Git::SVN::_minimize_url = 'unset';
$Git::SVN::Log::TZ = $ENV{TZ};
$ENV{TZ} = 'UTC';
if ($SVN::Core::VERSION lt '1.1.0') {
fatal "Need SVN::Core 1.1.0 or better (got $SVN::Core::VERSION)";
}
+my $can_compress = eval { require Compress::Zlib; 1};
push @Git::SVN::Ra::ISA, 'SVN::Ra';
push @SVN::Git::Editor::ISA, 'SVN::Delta::Editor';
push @SVN::Git::Fetcher::ISA, 'SVN::Delta::Editor';
use File::Basename qw/dirname basename/;
use File::Path qw/mkpath/;
use File::Spec;
+use File::Find;
use Getopt::Long qw/:config gnu_getopt no_ignore_case auto_abbrev/;
use IPC::Open3;
use Git;
$sha1 = qr/[a-f\d]{40}/;
$sha1_short = qr/[a-f\d]{4,40}/;
my ($_stdin, $_help, $_edit,
- $_message, $_file,
+ $_message, $_file, $_branch_dest,
$_template, $_shared,
$_version, $_fetch_all, $_no_rebase, $_fetch_parent,
$_merge, $_strategy, $_dry_run, $_local,
'localtime' => \$Git::SVN::_localtime,
%remote_opts );
-my ($_trunk, $_tags, $_branches, $_stdlayout);
+my ($_trunk, @_tags, @_branches, $_stdlayout);
my %icv;
my %init_opts = ( 'template=s' => \$_template, 'shared:s' => \$_shared,
- 'trunk|T=s' => \$_trunk, 'tags|t=s' => \$_tags,
- 'branches|b=s' => \$_branches, 'prefix=s' => \$_prefix,
+ 'trunk|T=s' => \$_trunk, 'tags|t=s@' => \@_tags,
+ 'branches|b=s@' => \@_branches, 'prefix=s' => \$_prefix,
'stdlayout|s' => \$_stdlayout,
- 'minimize-url|m' => \$Git::SVN::_minimize_url,
+ 'minimize-url|m!' => \$Git::SVN::_minimize_url,
'no-metadata' => sub { $icv{noMetadata} = 1 },
'use-svm-props' => sub { $icv{useSvmProps} = 1 },
'use-svnsync-props' => sub { $icv{useSvnsyncProps} = 1 },
branch => [ \&cmd_branch,
'Create a branch in the SVN repository',
{ 'message|m=s' => \$_message,
+ 'destination|d=s' => \$_branch_dest,
'dry-run|n' => \$_dry_run,
'tag|t' => \$_tag } ],
tag => [ sub { $_tag = 1; cmd_branch(@_) },
'Create a tag in the SVN repository',
{ 'message|m=s' => \$_message,
+ 'destination|d=s' => \$_branch_dest,
'dry-run|n' => \$_dry_run } ],
'set-tree' => [ \&cmd_set_tree,
"Set an SVN repository to a git tree-ish",
"Undo fetches back to the specified SVN revision",
{ 'revision|r=s' => \$_revision,
'parent|p' => \$_fetch_parent } ],
+ 'gc' => [ \&cmd_gc,
+ "Compress unhandled.log files in .git/svn and remove " .
+ "index files in .git/svn",
+ {} ],
);
my $cmd;
sub cmd_clone {
my ($url, $path) = @_;
if (!defined $path &&
- (defined $_trunk || defined $_branches || defined $_tags ||
+ (defined $_trunk || @_branches || @_tags ||
defined $_stdlayout) &&
$url !~ m#^[a-z\+]+://#) {
$path = $url;
sub cmd_init {
if (defined $_stdlayout) {
$_trunk = 'trunk' if (!defined $_trunk);
- $_tags = 'tags' if (!defined $_tags);
- $_branches = 'branches' if (!defined $_branches);
+ @_tags = 'tags' if (! @_tags);
+ @_branches = 'branches' if (! @_branches);
}
- if (defined $_trunk || defined $_branches || defined $_tags) {
+ if (defined $_trunk || @_branches || @_tags) {
return cmd_multi_init(@_);
}
my $url = shift or die "SVN repository location required ",
"as a command-line argument\n";
+ $url = canonicalize_url($url);
init_subdir(@_);
do_git_init_db();
+ if ($Git::SVN::_minimize_url eq 'unset') {
+ $Git::SVN::_minimize_url = 0;
+ }
+
Git::SVN->init($url);
}
my ($src, $rev, undef, $gs) = working_head_info($head);
my $remote = Git::SVN::read_all_remotes()->{$gs->{repo_id}};
- my $glob = $remote->{ $_tag ? 'tags' : 'branches' };
+ my $allglobs = $remote->{ $_tag ? 'tags' : 'branches' };
+ my $glob;
+ if ($#{$allglobs} == 0) {
+ $glob = $allglobs->[0];
+ } else {
+ unless(defined $_branch_dest) {
+ die "Multiple ",
+ $_tag ? "tag" : "branch",
+ " paths defined for Subversion repository.\n",
+ "You must specify where you want to create the ",
+ $_tag ? "tag" : "branch",
+ " with the --destination argument.\n";
+ }
+ foreach my $g (@{$allglobs}) {
+ # SVN::Git::Editor could probably be moved to Git.pm..
+ my $re = SVN::Git::Editor::glob2pat($g->{path}->{left});
+ if ($_branch_dest =~ /$re/) {
+ $glob = $g;
+ last;
+ }
+ }
+ unless (defined $glob) {
+ my $dest_re = qr/\b\Q$_branch_dest\E\b/;
+ foreach my $g (@{$allglobs}) {
+ $g->{path}->{left} =~ /$dest_re/ or next;
+ if (defined $glob) {
+ die "Ambiguous destination: ",
+ $_branch_dest, "\nmatches both '",
+ $glob->{path}->{left}, "' and '",
+ $g->{path}->{left}, "'\n";
+ }
+ $glob = $g;
+ }
+ unless (defined $glob) {
+ die "Unknown ",
+ $_tag ? "tag" : "branch",
+ " destination $_branch_dest\n";
+ }
+ }
+ }
my ($lft, $rgt) = @{ $glob->{path} }{qw/left right/};
my $dst = join '/', $remote->{url}, $lft, $branch_name, ($rgt || ());
return $path;
}
+sub canonicalize_url {
+ my ($url) = @_;
+ $url =~ s#^([^:]+://[^/]*/)(.*)$#$1 . canonicalize_path($2)#e;
+ return $url;
+}
+
# get_svnprops(PATH)
# ------------------
# Helper for cmd_propget and cmd_proplist below.
sub cmd_multi_init {
my $url = shift;
- unless (defined $_trunk || defined $_branches || defined $_tags) {
+ unless (defined $_trunk || @_branches || @_tags) {
usage(1);
}
- # there are currently some bugs that prevent multi-init/multi-fetch
- # setups from working well without this.
- $Git::SVN::_minimize_url = 1;
-
$_prefix = '' unless defined $_prefix;
if (defined $url) {
- $url =~ s#/+$##;
+ $url = canonicalize_url($url);
init_subdir(@_);
}
do_git_init_db();
undef, $trunk_ref);
}
}
- return unless defined $_branches || defined $_tags;
+ return unless @_branches || @_tags;
my $ra = $url ? Git::SVN::Ra->new($url) : undef;
- complete_url_ls_init($ra, $_branches, '--branches/-b', $_prefix);
- complete_url_ls_init($ra, $_tags, '--tags/-t', $_prefix . 'tags/');
+ foreach my $path (@_branches) {
+ complete_url_ls_init($ra, $path, '--branches/-b', $_prefix);
+ }
+ foreach my $path (@_tags) {
+ complete_url_ls_init($ra, $path, '--tags/-t', $_prefix.'tags/');
+ }
}
sub cmd_multi_fetch {
print "r$r = $c ($gs->{ref_id})\n";
}
+sub cmd_gc {
+ if (!$can_compress) {
+ warn "Compress::Zlib could not be found; unhandled.log " .
+ "files will not be compressed.\n";
+ }
+ find({ wanted => \&gc_directory, no_chdir => 1}, "$ENV{GIT_DIR}/svn");
+}
+
########################### utility functions #########################
sub rebase_cmd {
"wanted to set to: $gs->{url}\n";
}
command_oneline('config', $k, $gs->{url}) unless $orig_url;
- my $remote_path = "$ra->{svn_path}/$repo_path";
+ my $remote_path = "$gs->{path}/$repo_path";
$remote_path =~ s#/+#/#g;
$remote_path =~ s#^/##g;
$remote_path .= "/*" if $remote_path !~ /\*/;
die "--prefix='$pfx' must have a trailing slash '/'\n";
}
command_noisy('config',
+ '--add',
"svn-remote.$gs->{repo_id}.$n",
"$remote_path:refs/remotes/$pfx*" .
('/*' x (($remote_path =~ tr/*/*/) - 1)) );
sub extract_metadata {
my $id = shift or return (undef, undef, undef);
my ($url, $rev, $uuid) = ($id =~ /^\s*git-svn-id:\s+(.*)\@(\d+)
- \s([a-f\d\-]+)$/x);
+ \s([a-f\d\-]+)$/ix);
if (!defined $rev || !$uuid || !$url) {
# some of the original repositories I made had
# identifiers like this:
- ($rev, $uuid) = ($id =~/^\s*git-svn-id:\s(\d+)\@([a-f\d\-]+)/);
+ ($rev, $uuid) = ($id =~/^\s*git-svn-id:\s(\d+)\@([a-f\d\-]+)/i);
}
return ($url, $rev, $uuid);
}
return $md5->hexdigest();
}
+sub gc_directory {
+ if ($can_compress && -f $_ && basename($_) eq "unhandled.log") {
+ my $out_filename = $_ . ".gz";
+ open my $in_fh, "<", $_ or die "Unable to open $_: $!\n";
+ binmode $in_fh;
+ my $gz = Compress::Zlib::gzopen($out_filename, "ab") or
+ die "Unable to open $out_filename: $!\n";
+
+ my $res;
+ while ($res = sysread($in_fh, my $str, 1024)) {
+ $gz->gzwrite($str) or
+ die "Unable to write: ".$gz->gzerror()."!\n";
+ }
+ unlink $_ or die "unlink $File::Find::name: $!\n";
+ } elsif (-f $_ && basename($_) eq "index") {
+ unlink $_ or die "unlink $_: $!\n";
+ }
+}
+
package Git::SVN;
use strict;
use warnings;
my $ra = Git::SVN::Ra->new($url);
my $uuid = $ra->get_uuid;
my $head = $ra->get_latest_revnum;
+ $ra->get_log("", $head, 0, 1, 0, 1, sub { $head = $_[1] });
my $base = defined $fetch ? $head : 0;
# read the max revs for wildcard expansion (branches/*, tags/*)
foreach my $t (qw/branches tags/) {
defined $remote->{$t} or next;
- push @globs, $remote->{$t};
+ push @globs, @{$remote->{$t}};
+
my $max_rev = eval { tmp_config(qw/--int --get/,
"svn-remote.$repo_id.${t}-maxRev") };
if (defined $max_rev && ($max_rev < $base)) {
} elsif (m!^(.+)\.(branches|tags)=
(.*):refs/remotes/(.+)\s*$/!x) {
my ($p, $g) = ($3, $4);
- my $rs = $r->{$1}->{$2} = {
- t => $2,
- remote => $1,
- path => Git::SVN::GlobSpec->new($p),
- ref => Git::SVN::GlobSpec->new($g) };
+ my $rs = {
+ t => $2,
+ remote => $1,
+ path => Git::SVN::GlobSpec->new($p),
+ ref => Git::SVN::GlobSpec->new($g) };
if (length($rs->{ref}->{right}) != 0) {
die "The '*' glob character must be the last ",
"character of '$g'\n";
}
+ push @{ $r->{$1}->{$2} }, $rs;
}
}
next if defined $repos_root && $repos_root ne $u;
my $fetch = $remotes->{$repo_id}->{fetch} || {};
- foreach (qw/branches tags/) {
- resolve_local_globs($u, $fetch,
- $remotes->{$repo_id}->{$_});
+ foreach my $t (qw/branches tags/) {
+ foreach my $globspec (@{$remotes->{$repo_id}->{$t}}) {
+ resolve_local_globs($u, $fetch, $globspec);
+ }
}
my $p = $path;
my $rwr = rewrite_root({repo_id => $repo_id});
chomp($src, $uuid);
- $uuid =~ m{^[0-9a-f\-]{30,}$}
+ $uuid =~ m{^[0-9a-f\-]{30,}$}i
or die "doesn't look right - svm:uuid is '$uuid'\n";
# the '!' is used to mark the repos_root!/relative/path
die "doesn't look right - svn:sync-from-url is '$url'\n";
my $uuid = tmp_config('--get', "$section.svnsync-uuid");
- ($uuid) = ($uuid =~ m{^([0-9a-f\-]{30,})$}) or
+ ($uuid) = ($uuid =~ m{^([0-9a-f\-]{30,})$}i) or
die "doesn't look right - svn:sync-from-uuid is '$uuid'\n";
$svnsync = { url => $url, uuid => $uuid }
die "doesn't look right - svn:sync-from-url is '$url'\n";
my $uuid = $rp->{'svn:sync-from-uuid'} or die $err . "uuid\n";
- ($uuid) = ($uuid =~ m{^([0-9a-f\-]{30,})$}) or
+ ($uuid) = ($uuid =~ m{^([0-9a-f\-]{30,})$}i) or
die "doesn't look right - svn:sync-from-uuid is '$uuid'\n";
my $section = "svn-remote.$self->{repo_id}";
unless ($self->{ra_uuid}) {
my $key = "svn-remote.$self->{repo_id}.uuid";
my $uuid = eval { tmp_config('--get', $key) };
- if (!$@ && $uuid && $uuid =~ /^([a-f\d\-]{30,})$/) {
+ if (!$@ && $uuid && $uuid =~ /^([a-f\d\-]{30,})$/i) {
$self->{ra_uuid} = $uuid;
} else {
die "ra_uuid called without URL\n" unless $self->{url};
$ra;
}
-sub rel_path {
- my ($self) = @_;
- my $repos_root = $self->ra->{repos_root};
- return $self->{path} if ($self->{url} eq $repos_root);
- my $url = $self->{url} .
- (length $self->{path} ? "/$self->{path}" : $self->{path});
- $url =~ s!^\Q$repos_root\E(?:/+|$)!!g;
- $url;
-}
-
# prop_walk(PATH, REV, SUB)
# -------------------------
# Recursively traverse PATH at revision REV and invoke SUB for each
if (my $path = $paths->{"/$self->{path}"}) {
return ($path->{action} eq 'D') ? 0 : 1;
}
- my $repos_root = $self->ra->{repos_root};
- my $extended_path = $self->{url} . '/' . $self->{path};
- $extended_path =~ s#^\Q$repos_root\E(/|$)##;
- $self->{path_regex} ||= qr/^\/\Q$extended_path\E\//;
+ $self->{path_regex} ||= qr/^\/\Q$self->{path}\E\//;
if (grep /$self->{path_regex}/, keys %$paths) {
return 1;
}
unless (defined $paths) {
my $err_handler = $SVN::Error::handler;
$SVN::Error::handler = \&Git::SVN::Ra::skip_unknown_revs;
- $self->ra->get_log([$self->{path}], $rev, $rev, 0, 1, 1, sub {
- $paths =
- Git::SVN::Ra::dup_changed_paths($_[0]) });
+ $self->ra->get_log([$self->{path}], $rev, $rev, 0, 1, 1,
+ sub { $paths = $_[0] });
$SVN::Error::handler = $err_handler;
}
return undef unless defined $paths;
# look for a parent from another branch:
- my @b_path_components = split m#/#, $self->rel_path;
+ my @b_path_components = split m#/#, $self->{path};
my @a_path_components;
my $i;
while (@b_path_components) {
my $r = $i->{copyfrom_rev};
my $repos_root = $self->ra->{repos_root};
my $url = $self->ra->{url};
- my $new_url = $repos_root . $branch_from;
+ my $new_url = $url . $branch_from;
print STDERR "Found possible branch point: ",
"$new_url => ", $self->full_url, ", $r\n";
$branch_from =~ s#^/##;
- my $gs = $self->other_gs($new_url, $url, $repos_root,
+ my $gs = $self->other_gs($new_url, $url,
$branch_from, $r, $self->{ref_id});
my ($r0, $parent) = $gs->find_rev_before($r, 1);
{
}
sub other_gs {
- my ($self, $new_url, $url, $repos_root,
+ my ($self, $new_url, $url,
$branch_from, $r, $old_ref_id) = @_;
- my $gs = Git::SVN->find_by_url($new_url, $repos_root, $branch_from);
+ my $gs = Git::SVN->find_by_url($new_url, $url, $branch_from);
unless ($gs) {
my $ref_id = $old_ref_id;
$ref_id =~ s/\@\d+$//;
sub call_authors_prog {
my ($orig_author) = @_;
+ $orig_author = command_oneline('rev-parse', '--sq-quote', $orig_author);
my $author = `$::_authors_prog $orig_author`;
if ($? != 0) {
die "$::_authors_prog failed with exit code $?\n"
die "Can't have both 'useSvmProps' and 'rewriteRoot' ",
"options set!\n";
}
- my ($uuid, $r) = $headrev =~ m{^([a-f\d\-]{30,}):(\d+)$};
+ my ($uuid, $r) = $headrev =~ m{^([a-f\d\-]{30,}):(\d+)$}i;
# we don't want "SVM: initializing mirror for junk" ...
return undef if $r == 0;
my $svm = $self->svm;
sub url_path {
my ($self, $path) = @_;
if ($self->{url} =~ m#^https?://#) {
- $path =~ s/([^~a-zA-Z0-9_.-])/uc sprintf("%%%02x",ord($1))/eg;
+ $path =~ s!([^~a-zA-Z0-9_./-])!uc sprintf("%%%02x",ord($1))!eg;
}
$self->{url} . '/' . $self->repo_path($path);
}
my ($self, @args) = @_;
my $pool = SVN::Pool->new;
+ # svn_log_changed_path_t objects passed to get_log are likely to be
+ # overwritten even if only the refs are copied to an external variable,
+ # so we should dup the structures in their entirety. Using an
+ # externally passed pool (instead of our temporary and quickly cleared
+ # pool in Git::SVN::Ra) does not help matters at all...
+ my $receiver = pop @args;
+ my $prefix = "/".$self->{svn_path};
+ $prefix =~ s#/+($)##;
+ my $prefix_regex = qr#^\Q$prefix\E#;
+ push(@args, sub {
+ my ($paths) = $_[0];
+ return &$receiver(@_) unless $paths;
+ $_[0] = ();
+ foreach my $p (keys %$paths) {
+ my $i = $paths->{$p};
+ # Make path relative to our url, not repos_root
+ $p =~ s/$prefix_regex//;
+ my %s = map { $_ => $i->$_; }
+ qw/copyfrom_path copyfrom_rev action/;
+ if ($s{'copyfrom_path'}) {
+ $s{'copyfrom_path'} =~ s/$prefix_regex//;
+ }
+ $_[0]{$p} = \%s;
+ }
+ &$receiver(@_);
+ });
+
+
# the limit parameter was not supported in SVN 1.1.x, so we
# drop it. Therefore, the receiver callback passed to it
# is made aware of this limitation by being wrapped if
my $full_url = $self->{url};
my $old_url = $full_url;
- $full_url .= '/' . escape_uri_only($path) if length $path;
+ $full_url .= '/' . $path if length $path;
my ($ra, $reparented);
- if ($old_url =~ m#^svn(\+ssh)?://#) {
+ if ($old_url =~ m#^svn(\+ssh)?://# ||
+ ($full_url =~ m#^https?://# &&
+ escape_url($full_url) ne $full_url)) {
$_[0] = undef;
$self = undef;
$RA = undef;
};
sub _cb {
my ($paths, $r, $author, $date, $log) = @_;
- [ dup_changed_paths($paths),
+ [ $paths,
{ author => $author, date => $date, log => $log } ];
}
$self->get_log([$longest_path], $min, $max, 0, 1, 1,
my $c = '';
do {
$url .= "/$c" if length $c;
- eval { (ref $self)->new($url)->get_latest_revnum };
+ eval {
+ my $ra = (ref $self)->new($url);
+ my $latest = $ra->get_latest_revnum;
+ $ra->get_log("", $latest, 0, 1, 0, 1, sub {});
+ };
} while ($@ && ($c = shift @components));
$url;
}
die "Error from SVN, ($errno): ", $err->expanded_message,"\n";
}
-# svn_log_changed_path_t objects passed to get_log are likely to be
-# overwritten even if only the refs are copied to an external variable,
-# so we should dup the structures in their entirety. Using an externally
-# passed pool (instead of our temporary and quickly cleared pool in
-# Git::SVN::Ra) does not help matters at all...
-sub dup_changed_paths {
- my ($paths) = @_;
- return undef unless $paths;
- my %ret;
- foreach my $p (keys %$paths) {
- my $i = $paths->{$p};
- my %s = map { $_ => $i->$_ }
- qw/copyfrom_path copyfrom_rev action/;
- $ret{$p} = \%s;
- }
- \%ret;
-}
-
package Git::SVN::Log;
use strict;
use warnings;