use warnings;
use strict;
use vars qw/ $AUTHOR $VERSION
- $SVN_URL
- $GIT_SVN_INDEX $GIT_SVN
- $GIT_DIR $GIT_SVN_DIR $REVDB
- $_follow_parent $sha1 $sha1_short $_revision
- $_cp_remote $_upgrade $_rmdir $_q $_cp_similarity
- $_find_copies_harder $_l/;
+ $sha1 $sha1_short $_revision
+ $_q $_authors %users/;
$AUTHOR = 'Eric Wong <normalperson@yhbt.net>';
$VERSION = '@@GIT_VERSION@@';
-use Cwd qw/abs_path/;
-$GIT_DIR = abs_path($ENV{GIT_DIR} || '.git');
-$ENV{GIT_DIR} = $GIT_DIR;
+my $git_dir_user_set = 1 if defined $ENV{GIT_DIR};
+$ENV{GIT_DIR} ||= '.git';
+$Git::SVN::default_repo_id = 'svn';
+$Git::SVN::default_ref_id = $ENV{GIT_SVN_ID} || 'git-svn';
+$Git::SVN::Ra::_log_window_size = 100;
-my $LC_ALL = $ENV{LC_ALL};
$Git::SVN::Log::TZ = $ENV{TZ};
-# make sure the svn binary gives consistent output between locales and TZs:
$ENV{TZ} = 'UTC';
-$ENV{LC_ALL} = 'C';
$| = 1; # unbuffer STDOUT
-# properties that we do not log:
-my %SKIP = ( 'svn:wc:ra_dav:version-url' => 1,
- 'svn:special' => 1,
- 'svn:executable' => 1,
- 'svn:entry:committed-rev' => 1,
- 'svn:entry:last-author' => 1,
- 'svn:entry:uuid' => 1,
- 'svn:entry:committed-date' => 1,
-);
-
sub fatal (@) { print STDERR @_; exit 1 }
require SVN::Core; # use()-ing this causes segfaults for me... *shrug*
require SVN::Ra;
use File::Path qw/mkpath/;
use Getopt::Long qw/:config gnu_getopt no_ignore_case auto_abbrev pass_through/;
use IPC::Open3;
-use Memoize;
use Git;
-memoize('revisions_eq');
-memoize('cmt_metadata');
-memoize('get_commit_time');
BEGIN {
my $s;
foreach (qw/command command_oneline command_noisy command_output_pipe
command_input_pipe command_close_pipe/) {
$s .= "*SVN::Git::Editor::$_ = *SVN::Git::Fetcher::$_ = ".
+ "*Git::SVN::Migration::$_ = ".
"*Git::SVN::Log::$_ = *Git::SVN::$_ = *$_ = *Git::$_; ";
}
eval $s;
my ($SVN);
-my $_optimize_commits = 1 unless $ENV{GIT_SVN_NO_OPTIMIZE_COMMITS};
$sha1 = qr/[a-f\d]{40}/;
$sha1_short = qr/[a-f\d]{4,40}/;
my ($_stdin, $_help, $_edit,
- $_repack, $_repack_nr, $_repack_flags,
- $_message, $_file, $_no_metadata,
- $_template, $_shared, $_no_default_regex, $_no_graft_copy,
- $_version, $_upgrade, $_authors, $_branch_all_refs, @_opt_m,
- $_merge, $_strategy, $_dry_run,
- $_prefix);
-my (@_branch_from, %tree_map, %users);
-my @repo_path_split_cache;
-
-my %fc_opts = ( 'branch|b=s' => \@_branch_from,
- 'follow-parent|follow' => \$_follow_parent,
- 'branch-all-refs|B' => \$_branch_all_refs,
+ $_message, $_file,
+ $_template, $_shared,
+ $_version, $_fetch_all,
+ $_merge, $_strategy, $_dry_run, $_local,
+ $_prefix, $_no_checkout, $_verbose);
+$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 );
+my %fc_opts = ( 'follow-parent|follow!' => \$Git::SVN::_follow_parent,
'authors-file|A=s' => \$_authors,
- 'repack:i' => \$_repack,
- 'no-metadata' => \$_no_metadata,
+ 'repack:i' => \$Git::SVN::_repack,
+ 'noMetadata' => \$Git::SVN::_no_metadata,
+ 'useSvmProps' => \$Git::SVN::_use_svm_props,
+ 'useSvnsyncProps' => \$Git::SVN::_use_svnsync_props,
+ 'log-window-size=i' => \$Git::SVN::Ra::_log_window_size,
+ 'no-checkout' => \$_no_checkout,
'quiet|q' => \$_q,
- 'username=s' => \$Git::SVN::Prompt::_username,
- 'config-dir=s' => \$Git::SVN::Ra::config_dir,
- 'no-auth-cache' => \$Git::SVN::Prompt::_no_auth_cache,
- 'repack-flags|repack-args|repack-opts=s' => \$_repack_flags);
+ 'repack-flags|repack-args|repack-opts=s' =>
+ \$Git::SVN::_repack_flags,
+ %remote_opts );
my ($_trunk, $_tags, $_branches);
-my %multi_opts = ( 'trunk|T=s' => \$_trunk,
- 'tags|t=s' => \$_tags,
- 'branches|b=s' => \$_branches );
-my %init_opts = ( 'template=s' => \$_template, 'shared' => \$_shared );
+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,
+ 'no-metadata' => sub { $icv{noMetadata} = 1 },
+ 'use-svm-props' => sub { $icv{useSvmProps} = 1 },
+ 'use-svnsync-props' => sub { $icv{useSvnsyncProps} = 1 },
+ 'rewrite-root=s' => sub { $icv{rewriteRoot} = $_[1] },
+ %remote_opts );
my %cmt_opts = ( 'edit|e' => \$_edit,
- 'rmdir' => \$_rmdir,
- 'find-copies-harder' => \$_find_copies_harder,
- 'l=i' => \$_l,
- 'copy-similarity|C=i'=> \$_cp_similarity
+ 'rmdir' => \$SVN::Git::Editor::_rmdir,
+ 'find-copies-harder' => \$SVN::Git::Editor::_find_copies_harder,
+ 'l=i' => \$SVN::Git::Editor::_rename_limit,
+ 'copy-similarity|C=i'=> \$SVN::Git::Editor::_cp_similarity
);
my %cmd = (
fetch => [ \&cmd_fetch, "Download new revisions from SVN",
- { 'revision|r=s' => \$_revision, %fc_opts } ],
+ { 'revision|r=s' => \$_revision,
+ 'fetch-all|all' => \$_fetch_all,
+ %fc_opts } ],
+ clone => [ \&cmd_clone, "Initialize and fetch revisions",
+ { 'revision|r=s' => \$_revision,
+ %fc_opts, %init_opts } ],
init => [ \&cmd_init, "Initialize a repo for tracking" .
" (requires URL argument)",
\%init_opts ],
- dcommit => [ \&dcommit, 'Commit several diffs to merge with upstream',
+ 'multi-init' => [ \&cmd_multi_init,
+ "Deprecated alias for ".
+ "'$0 init -T<trunk> -b<branches> -t<tags>'",
+ \%init_opts ],
+ dcommit => [ \&cmd_dcommit,
+ 'Commit several diffs to merge with upstream',
{ 'merge|m|M' => \$_merge,
'strategy|s=s' => \$_strategy,
+ 'verbose|v' => \$_verbose,
'dry-run|n' => \$_dry_run,
+ 'fetch-all|all' => \$_fetch_all,
%cmt_opts, %fc_opts } ],
- 'set-tree' => [ \&commit, "Set an SVN repository to a git tree-ish",
- { 'stdin|' => \$_stdin, %cmt_opts, %fc_opts, } ],
+ 'set-tree' => [ \&cmd_set_tree,
+ "Set an SVN repository to a git tree-ish",
+ { 'stdin|' => \$_stdin, %cmt_opts, %fc_opts, } ],
'show-ignore' => [ \&cmd_show_ignore, "Show svn:ignore listings",
{ 'revision|r=i' => \$_revision } ],
- rebuild => [ \&cmd_rebuild, "Rebuild git-svn metadata (after git clone)",
- { 'copy-remote|remote=s' => \$_cp_remote,
- 'upgrade' => \$_upgrade } ],
- 'graft-branches' => [ \&graft_branches,
- 'Detect merges/branches from already imported history',
- { 'merge-rx|m' => \@_opt_m,
- 'branch|b=s' => \@_branch_from,
- 'branch-all-refs|B' => \$_branch_all_refs,
- 'no-default-regex' => \$_no_default_regex,
- 'no-graft-copy' => \$_no_graft_copy } ],
- 'multi-init' => [ \&cmd_multi_init,
- 'Initialize multiple trees (like git-svnimport)',
- { %multi_opts, %init_opts,
- 'revision|r=i' => \$_revision,
- 'username=s' => \$Git::SVN::Prompt::_username,
- 'config-dir=s' => \$Git::SVN::Ra::config_dir,
- 'no-auth-cache' => \$Git::SVN::Prompt::_no_auth_cache,
- 'prefix=s' => \$_prefix,
- } ],
- 'multi-fetch' => [ \&multi_fetch,
- 'Fetch multiple trees (like git-svnimport)',
- \%fc_opts ],
+ 'multi-fetch' => [ \&cmd_multi_fetch,
+ "Deprecated alias for $0 fetch --all",
+ { 'revision|r=s' => \$_revision, %fc_opts } ],
+ 'migrate' => [ sub { },
+ # no-op, we automatically run this anyways,
+ 'Migrate configuration/metadata/layout from
+ previous versions of git-svn',
+ { 'minimize' => \$Git::SVN::Migration::_minimize,
+ %remote_opts } ],
'log' => [ \&Git::SVN::Log::cmd_show_log, 'Show commit logs',
{ 'limit=i' => \$Git::SVN::Log::limit,
'revision|r=s' => \$_revision,
'color' => \$Git::SVN::Log::color,
'pager=s' => \$Git::SVN::Log::pager,
} ],
+ 'rebase' => [ \&cmd_rebase, "Fetch and rebase your working directory",
+ { 'merge|m|M' => \$_merge,
+ 'verbose|v' => \$_verbose,
+ 'strategy|s=s' => \$_strategy,
+ 'local|l' => \$_local,
+ 'fetch-all|all' => \$_fetch_all,
+ %fc_opts } ],
'commit-diff' => [ \&cmd_commit_diff,
'Commit a diff between two trees',
{ 'message|m=s' => \$_message,
my %opts = %{$cmd{$cmd}->[2]} if (defined $cmd);
read_repo_config(\%opts);
-my $rv = GetOptions(%opts, 'help|H|h' => \$_help,
- 'version|V' => \$_version,
- 'id|i=s' => \$GIT_SVN);
+my $rv = GetOptions(%opts, 'help|H|h' => \$_help, 'version|V' => \$_version,
+ 'minimize-connections' => \$Git::SVN::Migration::_minimize,
+ 'id|i=s' => \$Git::SVN::default_ref_id,
+ 'svn-remote|remote|R=s' => sub {
+ $Git::SVN::no_reuse_existing = 1;
+ $Git::SVN::default_repo_id = $_[1] });
exit 1 if (!$rv && $cmd ne 'log');
-set_default_vals();
usage(0) if $_help;
version() if $_version;
usage(1) unless defined $cmd;
-init_vars();
load_authors() if $_authors;
-load_all_refs() if $_branch_all_refs;
-migration_check() unless $cmd =~ /^(?:init|rebuild|multi-init|commit-diff)$/;
-$cmd{$cmd}->[0]->(@ARGV);
+
+# make sure we're always running
+unless ($cmd =~ /(?:clone|init|multi-init)$/) {
+ unless (-d $ENV{GIT_DIR}) {
+ if ($git_dir_user_set) {
+ die "GIT_DIR=$ENV{GIT_DIR} explicitly set, ",
+ "but it is not a directory\n";
+ }
+ my $git_dir = delete $ENV{GIT_DIR};
+ chomp(my $cdup = command_oneline(qw/rev-parse --show-cdup/));
+ unless (length $cdup) {
+ die "Already at toplevel, but $git_dir ",
+ "not found '$cdup'\n";
+ }
+ chdir $cdup or die "Unable to chdir up to '$cdup'\n";
+ unless (-d $git_dir) {
+ die "$git_dir still not found after going to ",
+ "'$cdup'\n";
+ }
+ $ENV{GIT_DIR} = $git_dir;
+ }
+}
+unless ($cmd =~ /^(?:clone|init|multi-init|commit-diff)$/) {
+ Git::SVN::Migration::migration_check();
+}
+Git::SVN::init_vars();
+eval {
+ Git::SVN::verify_remotes_sanity();
+ $cmd{$cmd}->[0]->(@ARGV);
+};
+fatal $@ if $@;
+post_fetch_checkout();
exit 0;
####################### primary functions ######################
foreach (sort keys %cmd) {
next if $cmd && $cmd ne $_;
+ next if /^multi-/; # don't show deprecated commands
print $fd ' ',pack('A17',$_),$cmd{$_}->[1],"\n";
foreach (keys %{$cmd{$_}->[2]}) {
# prints out arguments as they should be passed:
exit 0;
}
-sub cmd_rebuild {
- my $url = shift;
- my $gs = $url ? Git::SVN->init(undef, $url)
- : eval { Git::SVN->new };
- $gs ||= Git::SVN->_new;
- if (!verify_ref($gs->refname.'^0')) {
- $gs->copy_remote_ref;
- }
- if ($_upgrade) {
- command_noisy('update-ref',$gs->refname, $gs->{id}.'-HEAD');
- } else {
- $gs->check_upgrade_needed;
- }
-
- my ($rev_list, $ctx) = command_output_pipe("rev-list", $gs->refname);
- my $latest;
- my $svn_uuid;
- while (<$rev_list>) {
- chomp;
- my $c = $_;
- fatal "Non-SHA1: $c\n" unless $c =~ /^$sha1$/o;
- my ($url, $rev, $uuid) = cmt_metadata($c);
-
- # ignore merges (from set-tree)
- next if (!defined $rev || !$uuid);
-
- # if we merged or otherwise started elsewhere, this is
- # how we break out of it
- if ((defined $svn_uuid && ($uuid ne $svn_uuid)) ||
- ($gs->{url} && $url && ($url ne $gs->{url}))) {
- next;
- }
-
- unless (defined $latest) {
- if (!$gs->{url} && !$url) {
- fatal "SVN repository location required\n";
- }
- $gs = Git::SVN->init(undef, $url);
- $latest = $rev;
- }
- $gs->rev_db_set($rev, $c);
- print "r$rev = $c\n";
- }
- command_close_pipe($rev_list, $ctx);
-}
-
sub do_git_init_db {
unless (-d $ENV{GIT_DIR}) {
my @init_db = ('init');
push @init_db, "--template=$_template" if defined $_template;
- push @init_db, "--shared" if defined $_shared;
+ if (defined $_shared) {
+ if ($_shared =~ /[a-z]/) {
+ push @init_db, "--shared=$_shared";
+ } else {
+ push @init_db, "--shared";
+ }
+ }
command_noisy(@init_db);
}
-}
-
-sub cmd_init {
- my $url = shift or die "SVN repository location required " .
- "as a command-line argument\n";
- if (my $repo_path = shift) {
- unless (-d $repo_path) {
- mkpath([$repo_path]);
- }
- chdir $repo_path or croak $!;
- $ENV{GIT_DIR} = $repo_path . "/.git";
+ my $set;
+ my $pfx = "svn-remote.$Git::SVN::default_repo_id";
+ foreach my $i (keys %icv) {
+ die "'$set' and '$i' cannot both be set\n" if $set;
+ next unless defined $icv{$i};
+ command_noisy('config', "$pfx.$i", $icv{$i});
+ $set = $i;
}
- do_git_init_db();
-
- Git::SVN->init(undef, $url);
}
-sub cmd_fetch {
- fetch_child_id($GIT_SVN, @_);
+sub init_subdir {
+ my $repo_path = shift or return;
+ mkpath([$repo_path]) unless -d $repo_path;
+ chdir $repo_path or die "Couldn't chdir to $repo_path: $!\n";
+ $ENV{GIT_DIR} = '.git';
}
-sub fetch {
- check_upgrade_needed();
- $SVN_URL ||= file_to_s("$GIT_SVN_DIR/info/url");
- my $ret = fetch_lib(@_);
- if ($ret->{commit} && !verify_ref('refs/heads/master^0')) {
- command_noisy(qw(update-ref refs/heads/master),$ret->{commit});
+sub cmd_clone {
+ my ($url, $path) = @_;
+ if (!defined $path &&
+ (defined $_trunk || defined $_branches || defined $_tags) &&
+ $url !~ m#^[a-z\+]+://#) {
+ $path = $url;
}
- return $ret;
+ $path = basename($url) if !defined $path || !length $path;
+ cmd_init($url, $path);
+ Git::SVN::fetch_all($Git::SVN::default_repo_id);
}
-sub fetch_lib {
- my (@parents) = @_;
- $SVN_URL ||= file_to_s("$GIT_SVN_DIR/info/url");
- $SVN ||= Git::SVN::Ra->new($SVN_URL);
- my ($last_rev, $last_commit) = svn_grab_base_rev();
- my ($base, $head) = libsvn_parse_revision($last_rev);
- if ($base > $head) {
- return { revision => $last_rev, commit => $last_commit }
+sub cmd_init {
+ if (defined $_trunk || defined $_branches || defined $_tags) {
+ return cmd_multi_init(@_);
}
- my $index = set_index($GIT_SVN_INDEX);
+ my $url = shift or die "SVN repository location required ",
+ "as a command-line argument\n";
+ init_subdir(@_);
+ do_git_init_db();
- # limit ourselves and also fork() since get_log won't release memory
- # after processing a revision and SVN stuff seems to leak
- my $inc = 1000;
- my ($min, $max) = ($base, $head < $base+$inc ? $head : $base+$inc);
- if (defined $last_commit) {
- unless (-e $GIT_SVN_INDEX) {
- command_noisy('read-tree', $last_commit);
- }
- my $x = command_oneline('write-tree');
- my ($y) = (command(qw/cat-file commit/, $last_commit)
- =~ /^tree ($sha1)/m);
- if ($y ne $x) {
- unlink $GIT_SVN_INDEX or croak $!;
- command_noisy('read-tree', $last_commit);
- }
- $x = command_oneline('write-tree');
- if ($y ne $x) {
- print STDERR "trees ($last_commit) $y != $x\n",
- "Something is seriously wrong...\n";
- }
+ Git::SVN->init($url);
+}
+
+sub cmd_fetch {
+ if (grep /^\d+=./, @_) {
+ die "'<rev>=<commit>' fetch arguments are ",
+ "no longer supported.\n";
}
- while (1) {
- # fork, because using SVN::Pool with get_log() still doesn't
- # seem to help enough to keep memory usage down.
- defined(my $pid = fork) or croak $!;
- if (!$pid) {
- $SVN::Error::handler = \&libsvn_skip_unknown_revs;
-
- # Yes I'm perfectly aware that the fourth argument
- # below is the limit revisions number. Unfortunately
- # performance sucks with it enabled, so it's much
- # faster to fetch revision ranges instead of relying
- # on the limiter.
- $SVN->dup->get_log([''], $min, $max, 0, 1, 1,
- sub {
- my $log_entry;
- if ($last_commit) {
- $log_entry = libsvn_fetch(
- $last_commit, @_);
- $last_commit = git_commit(
- $log_entry,
- $last_commit,
- @parents);
- } else {
- $log_entry = libsvn_new_tree(@_);
- $last_commit = git_commit(
- $log_entry, @parents);
- }
- });
- exit 0;
- }
- waitpid $pid, 0;
- croak $? if $?;
- ($last_rev, $last_commit) = svn_grab_base_rev();
- last if ($max >= $head);
- $min = $max + 1;
- $max += $inc;
- $max = $head if ($max > $head);
- $SVN = Git::SVN::Ra->new($SVN_URL);
+ my ($remote) = @_;
+ if (@_ > 1) {
+ die "Usage: $0 fetch [--all] [svn-remote]\n";
+ }
+ $remote ||= $Git::SVN::default_repo_id;
+ if ($_fetch_all) {
+ cmd_multi_fetch();
+ } else {
+ Git::SVN::fetch_all($remote, Git::SVN::read_all_remotes());
}
- restore_index($index);
- return { revision => $last_rev, commit => $last_commit };
}
-sub commit {
+sub cmd_set_tree {
my (@commits) = @_;
- check_upgrade_needed();
if ($_stdin || !@commits) {
print "Reading from stdin...\n";
@commits = ();
} elsif (scalar @tmp > 1) {
push @revs, reverse(command('rev-list',@tmp));
} else {
- die "Failed to rev-parse $c\n";
+ fatal "Failed to rev-parse $c\n";
}
}
- commit_lib(@revs);
+ my $gs = Git::SVN->new;
+ my ($r_last, $cmt_last) = $gs->last_rev_commit;
+ $gs->fetch;
+ if (defined $gs->{last_rev} && $r_last != $gs->{last_rev}) {
+ fatal "There are new revisions that were fetched ",
+ "and need to be merged (or acknowledged) ",
+ "before committing.\nlast rev: $r_last\n",
+ " current: $gs->{last_rev}\n";
+ }
+ $gs->set_tree($_) foreach @revs;
print "Done committing ",scalar @revs," revisions to SVN\n";
}
-sub commit_lib {
- my (@revs) = @_;
- my ($r_last, $cmt_last) = svn_grab_base_rev();
- defined $r_last or die "Must have an existing revision to commit\n";
- my $fetched = fetch();
- if ($r_last != $fetched->{revision}) {
- print STDERR "There are new revisions that were fetched ",
- "and need to be merged (or acknowledged) ",
- "before committing.\n",
- "last rev: $r_last\n",
- " current: $fetched->{revision}\n";
- exit 1;
- }
- my $commit_msg = "$GIT_SVN_DIR/.svn-commit.tmp.$$";
-
- my $repo;
- set_svn_commit_env();
- foreach my $c (@revs) {
- my $log_entry = get_commit_entry($c, $commit_msg);
-
- # fork for each commit because there's a memory leak I
- # can't track down... (it's probably in the SVN code)
- defined(my $pid = open my $fh, '-|') or croak $!;
- if (!$pid) {
- my $pool = SVN::Pool->new;
- my $ed = SVN::Git::Editor->new(
- { r => $r_last,
- ra => $SVN->dup,
- svn_path => $SVN->{svn_path},
- },
- $SVN->get_commit_editor(
- $log_entry->{log},
- sub {
- libsvn_commit_cb(
- @_, $c,
- $log_entry->{log},
- $r_last,
- $cmt_last)
- }, $pool)
- );
- my $mods = $ed->apply_diff($cmt_last, $c);
- if (@$mods == 0) {
- print "No changes\nr$r_last = $cmt_last\n";
- }
- $pool->clear;
- exit 0;
- }
- my ($r_new, $cmt_new, $no);
- while (<$fh>) {
- print $_;
- chomp;
- if (/^r(\d+) = ($sha1)$/o) {
- ($r_new, $cmt_new) = ($1, $2);
- } elsif ($_ eq 'No changes') {
- $no = 1;
- }
- }
- close $fh or exit 1;
- if (! defined $r_new && ! defined $cmt_new) {
- unless ($no) {
- die "Failed to parse revision information\n";
- }
- } else {
- ($r_last, $cmt_last) = ($r_new, $cmt_new);
- }
+sub cmd_dcommit {
+ my $head = shift;
+ $head ||= 'HEAD';
+ my @refs;
+ my ($url, $rev, $uuid) = working_head_info($head, \@refs);
+ my $c = $refs[-1];
+ unless (defined $url && defined $rev && defined $uuid) {
+ die "Unable to determine upstream SVN information from ",
+ "$head history\n";
}
- $ENV{LC_ALL} = 'C';
- unlink $commit_msg;
-}
-
-sub dcommit {
- my $head = shift || 'HEAD';
- my $gs = "refs/remotes/$GIT_SVN";
- my @refs = command(qw/rev-list --no-merges/, "$gs..$head");
+ my $gs = Git::SVN->find_by_url($url);
my $last_rev;
- foreach my $d (reverse @refs) {
+ foreach my $d (@refs) {
if (!verify_ref("$d~1")) {
- die "Commit $d\n",
- "has no parent commit, and therefore ",
- "nothing to diff against.\n",
- "You should be working from a repository ",
- "originally created by git-svn\n";
+ fatal "Commit $d\n",
+ "has no parent commit, and therefore ",
+ "nothing to diff against.\n",
+ "You should be working from a repository ",
+ "originally created by git-svn\n";
}
unless (defined $last_rev) {
(undef, $last_rev, undef) = cmt_metadata("$d~1");
unless (defined $last_rev) {
- die "Unable to extract revision information ",
- "from commit $d~1\n";
+ fatal "Unable to extract revision information ",
+ "from commit $d~1\n";
}
}
if ($_dry_run) {
print "diff-tree $d~1 $d\n";
} else {
- if (my $r = commit_diff("$d~1", $d, undef, $last_rev)) {
- $last_rev = $r;
- } # else: no changes, same $last_rev
+ my %ed_opts = ( r => $last_rev,
+ log => get_commit_entry($d)->{log},
+ ra => Git::SVN::Ra->new($url),
+ tree_a => "$d~1",
+ tree_b => $d,
+ editor_cb => sub {
+ print "Committed r$_[0]\n";
+ $last_rev = $_[0]; },
+ svn_path => '');
+ if (!SVN::Git::Editor->new(\%ed_opts)->apply_diff) {
+ print "No changes\n$d~1 == $d\n";
+ }
}
}
return if $_dry_run;
- fetch();
- my @diff = command('diff-tree', 'HEAD', $gs, '--');
+ unless ($gs) {
+ warn "Could not determine fetch information for $url\n",
+ "Will not attempt to fetch and rebase commits.\n",
+ "This probably means you have useSvmProps and should\n",
+ "now resync your SVN::Mirror repository.\n";
+ return;
+ }
+ $_fetch_all ? $gs->fetch_all : $gs->fetch;
+ # we always want to rebase against the current HEAD, not any
+ # head that was passed to us
+ my @diff = command('diff-tree', 'HEAD', $gs->refname, '--');
my @finish;
if (@diff) {
- @finish = qw/rebase/;
- push @finish, qw/--merge/ if $_merge;
- push @finish, "--strategy=$_strategy" if $_strategy;
- print STDERR "W: HEAD and $gs differ, using @finish:\n", @diff;
+ @finish = rebase_cmd();
+ print STDERR "W: HEAD and ", $gs->refname, " differ, ",
+ "using @finish:\n", "@diff";
} else {
- print "No changes between current HEAD and $gs\n",
- "Resetting to the latest $gs\n";
+ print "No changes between current HEAD and ",
+ $gs->refname, "\nResetting to the latest ",
+ $gs->refname, "\n";
@finish = qw/reset --mixed/;
}
- command_noisy(@finish, $gs);
-}
-
-sub cmd_show_ignore {
- my $gs = Git::SVN->new;
- my $r = (defined $_revision ? $_revision : $gs->ra->get_latest_revnum);
- $gs->traverse_ignore(\*STDOUT, '', $r);
+ command_noisy(@finish, $gs->refname);
}
-sub graft_branches {
- my $gr_file = "$GIT_DIR/info/grafts";
- my ($grafts, $comments) = read_grafts($gr_file);
- my $gr_sha1;
-
- if (%$grafts) {
- # temporarily disable our grafts file to make this idempotent
- chomp($gr_sha1 = command(qw/hash-object -w/,$gr_file));
- rename $gr_file, "$gr_file~$gr_sha1" or croak $!;
+sub cmd_rebase {
+ command_noisy(qw/update-index --refresh/);
+ my $url = (working_head_info('HEAD'))[0];
+ if (!defined $url) {
+ die "Unable to determine upstream SVN information from ",
+ "working tree history\n";
}
- my $l_map = read_url_paths();
- my @re = map { qr/$_/is } @_opt_m if @_opt_m;
- unless ($_no_default_regex) {
- push @re, (qr/\b(?:merge|merging|merged)\s+with\s+([\w\.\-]+)/i,
- qr/\b(?:merge|merging|merged)\s+([\w\.\-]+)/i,
- qr/\b(?:from|of)\s+([\w\.\-]+)/i );
+ my $gs = Git::SVN->find_by_url($url);
+ if (command(qw/diff-index HEAD --/)) {
+ print STDERR "Cannot rebase with uncommited changes:\n";
+ command_noisy('status');
+ exit 1;
}
- foreach my $u (keys %$l_map) {
- if (@re) {
- foreach my $p (keys %{$l_map->{$u}}) {
- graft_merge_msg($grafts,$l_map,$u,$p,@re);
- }
- }
- unless ($_no_graft_copy) {
- graft_file_copy_lib($grafts,$l_map,$u);
- }
+ unless ($_local) {
+ $_fetch_all ? $gs->fetch_all : $gs->fetch;
}
- graft_tree_joins($grafts);
+ command_noisy(rebase_cmd(), $gs->refname);
+}
- write_grafts($grafts, $comments, $gr_file);
- unlink "$gr_file~$gr_sha1" if $gr_sha1;
+sub cmd_show_ignore {
+ my $url = (::working_head_info('HEAD'))[0];
+ my $gs = Git::SVN->find_by_url($url) || Git::SVN->new;
+ my $r = (defined $_revision ? $_revision : $gs->ra->get_latest_revnum);
+ $gs->traverse_ignore(\*STDOUT, $gs->{path}, $r);
}
sub cmd_multi_init {
unless (defined $_trunk || defined $_branches || defined $_tags) {
usage(1);
}
- do_git_init_db();
$_prefix = '' unless defined $_prefix;
+ if (defined $url) {
+ $url =~ s#/+$##;
+ init_subdir(@_);
+ }
+ do_git_init_db();
if (defined $_trunk) {
- my $gs_trunk = eval { Git::SVN->new($_prefix . 'trunk') };
+ my $trunk_ref = $_prefix . 'trunk';
+ # try both old-style and new-style lookups:
+ my $gs_trunk = eval { Git::SVN->new($trunk_ref) };
unless ($gs_trunk) {
- my $trunk_url = complete_svn_url($url, $_trunk);
- $gs_trunk = Git::SVN->init($_prefix . 'trunk',
- $trunk_url);
- command_noisy('config', 'svn.trunk', $trunk_url);
+ my ($trunk_url, $trunk_path) =
+ complete_svn_url($url, $_trunk);
+ $gs_trunk = Git::SVN->init($trunk_url, $trunk_path,
+ undef, $trunk_ref);
}
}
+ return unless defined $_branches || defined $_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/');
}
-sub multi_fetch {
- # try to do trunk first, since branches/tags
- # may be descended from it.
- if (-e "$GIT_DIR/svn/trunk/info/url") {
- fetch_child_id('trunk', @_);
+sub cmd_multi_fetch {
+ my $remotes = Git::SVN::read_all_remotes();
+ foreach my $repo_id (sort keys %$remotes) {
+ if ($remotes->{$repo_id}->{url}) {
+ Git::SVN::fetch_all($repo_id, $remotes);
+ }
}
- rec_fetch('', "$GIT_DIR/svn", @_);
}
# this command is special because it requires no metadata
my $usage = "Usage: $0 commit-diff -r<revision> ".
"<tree-ish> <tree-ish> [<URL>]\n";
fatal($usage) if (!defined $ta || !defined $tb);
+ my $svn_path;
if (!defined $url) {
my $gs = eval { Git::SVN->new };
if (!$gs) {
"the command-line\n", $usage);
}
$url = $gs->{url};
+ $svn_path = $gs->{path};
}
unless (defined $_revision) {
fatal("-r|--revision is a required argument\n", $usage);
$_message ||= get_commit_entry($tb)->{log};
}
my $ra ||= Git::SVN::Ra->new($url);
+ $svn_path ||= $ra->{svn_path};
my $r = $_revision;
if ($r eq 'HEAD') {
$r = $ra->get_latest_revnum;
} elsif ($r !~ /^\d+$/) {
die "revision argument: $r not understood by git-svn\n";
}
- my $pool = SVN::Pool->new;
my %ed_opts = ( r => $r,
- ra => $ra->dup,
- svn_path => $ra->{svn_path} );
- my $ed = SVN::Git::Editor->new(\%ed_opts,
- $ra->get_commit_editor($_message,
- sub { print "Committed r$_[0]\n" }),
- $pool);
- my $mods = $ed->apply_diff($ta, $tb);
- if (@$mods == 0) {
+ log => $_message,
+ ra => $ra,
+ tree_a => $ta,
+ tree_b => $tb,
+ editor_cb => sub { print "Committed r$_[0]\n" },
+ svn_path => $svn_path );
+ if (!SVN::Git::Editor->new(\%ed_opts)->apply_diff) {
print "No changes\n$ta == $tb\n";
}
- $pool->clear;
}
-sub commit_diff_usage {
- print STDERR "Usage: $0 commit-diff <tree-ish> <tree-ish> [<URL>]\n";
- exit 1
-}
+########################### utility functions #########################
-sub commit_diff {
- my $ta = shift or commit_diff_usage();
- my $tb = shift or commit_diff_usage();
- if (!eval { $SVN_URL = shift || file_to_s("$GIT_SVN_DIR/info/url") }) {
- print STDERR "Needed URL or usable git-svn id command-line\n";
- commit_diff_usage();
- }
- my $r = shift;
- unless (defined $r) {
- if (defined $_revision) {
- $r = $_revision
- } else {
- die "-r|--revision is a required argument\n";
- }
- }
- if (defined $_message && defined $_file) {
- print STDERR "Both --message/-m and --file/-F specified ",
- "for the commit message.\n",
- "I have no idea what you mean\n";
- exit 1;
- }
- if (defined $_file) {
- $_message = file_to_s($_file);
- } else {
- $_message ||= get_commit_entry($tb,
- "$GIT_DIR/.svn-commit.tmp.$$")->{log};
- }
- $SVN ||= Git::SVN::Ra->new($SVN_URL);
- if ($r eq 'HEAD') {
- $r = $SVN->get_latest_revnum;
- } elsif ($r !~ /^\d+$/) {
- die "revision argument: $r not understood by git-svn\n";
- }
- my $rev_committed;
- my $pool = SVN::Pool->new;
- my $ed = SVN::Git::Editor->new({ r => $r,
- ra => $SVN->dup,
- svn_path => $SVN->{svn_path}
- },
- $SVN->get_commit_editor($_message,
- sub {
- $rev_committed = $_[0];
- print "Committed $_[0]\n";
- },
- $pool)
- );
- eval {
- my $mods = $ed->apply_diff($ta, $tb);
- if (@$mods == 0) {
- print "No changes\n$ta == $tb\n";
- }
- };
- $pool->clear;
- fatal "$@\n" if $@;
- $_message = $_file = undef;
- return $rev_committed;
+sub rebase_cmd {
+ my @cmd = qw/rebase/;
+ push @cmd, '-v' if $_verbose;
+ push @cmd, qw/--merge/ if $_merge;
+ push @cmd, "--strategy=$_strategy" if $_strategy;
+ @cmd;
}
-########################### utility functions #########################
+sub post_fetch_checkout {
+ return if $_no_checkout;
+ my $gs = $Git::SVN::_head or return;
+ return if verify_ref('refs/heads/master^0');
-sub fetch_child_id {
- my $id = shift;
- print "Fetching $id\n";
- my $ref = "$GIT_DIR/refs/remotes/$id";
- defined(my $pid = open my $fh, '-|') or croak $!;
- if (!$pid) {
- $GIT_SVN = $ENV{GIT_SVN_ID} = $id;
- init_vars();
- fetch(@_);
- exit 0;
- }
- while (<$fh>) {
- print $_;
- check_repack() if (/^r\d+ = $sha1/o);
- }
- close $fh or croak $?;
-}
+ my $valid_head = verify_ref('HEAD^0');
+ command_noisy(qw(update-ref refs/heads/master), $gs->refname);
+ return if ($valid_head || !verify_ref('HEAD^0'));
-sub rec_fetch {
- my ($pfx, $p, @args) = @_;
- my @dir;
- foreach (sort <$p/*>) {
- if (-r "$_/info/url") {
- $pfx .= '/' if $pfx && $pfx !~ m!/$!;
- my $id = $pfx . basename $_;
- next if $id eq 'trunk';
- fetch_child_id($id, @args);
- } elsif (-d $_) {
- push @dir, $_;
- }
- }
- foreach (@dir) {
- my $x = $_;
- $x =~ s!^\Q$GIT_DIR\E/svn/!!;
- rec_fetch($x, $_);
- }
+ return if $ENV{GIT_DIR} !~ m#^(?:.*/)?\.git$#;
+ my $index = $ENV{GIT_INDEX_FILE} || "$ENV{GIT_DIR}/index";
+ return if -f $index;
+
+ chomp(my $bare = `git config --bool --get core.bare`);
+ return if $bare eq 'true';
+ return if command_oneline(qw/rev-parse --is-inside-git-dir/) eq 'true';
+ command_noisy(qw/read-tree -m -u -v HEAD HEAD/);
+ print STDERR "Checked out HEAD:\n ",
+ $gs->full_url, " r", $gs->last_rev, "\n";
}
sub complete_svn_url {
my ($url, $path) = @_;
$path =~ s#/+$##;
- $url =~ s#/+$## if $url;
if ($path !~ m#^[a-z\+]+://#) {
- $path = '/' . $path if ($path !~ m#^/#);
if (!defined $url || $url !~ m#^[a-z\+]+://#) {
fatal("E: '$path' is not a complete URL ",
"and a separate URL is not specified\n");
}
- $path = $url . $path;
+ return ($url, $path);
}
- return $path;
+ return ($path, '');
}
sub complete_url_ls_init {
- my ($ra, $path, $switch, $pfx) = @_;
- unless ($path) {
+ my ($ra, $repo_path, $switch, $pfx) = @_;
+ unless ($repo_path) {
print STDERR "W: $switch not specified\n";
return;
}
- $path =~ s#/+$##;
- if ($path =~ m#^[a-z\+]+://#) {
- $ra = Git::SVN::Ra->new($path);
- $path = '';
+ $repo_path =~ s#/+$##;
+ if ($repo_path =~ m#^[a-z\+]+://#) {
+ $ra = Git::SVN::Ra->new($repo_path);
+ $repo_path = '';
} else {
- $path =~ s#^/+##;
+ $repo_path =~ s#^/+##;
unless ($ra) {
- fatal("E: '$path' is not a complete URL ",
+ fatal("E: '$repo_path' is not a complete URL ",
"and a separate URL is not specified\n");
}
}
- my $r = defined $_revision ? $_revision : $ra->get_latest_revnum;
- my ($dirent, undef, undef) = $ra->get_dir($path, $r);
- my $url = $ra->{url} . (length $path ? "/$path" : '');
- foreach my $d (sort keys %$dirent) {
- next if ($dirent->{$d}->kind != $SVN::Node::dir);
- my $u = "$url/$d";
- my $id = "$pfx$d";
- my $gs = eval { Git::SVN->new($id) };
- # don't try to init already existing refs
- unless ($gs) {
- print "init $u => $id\n";
- Git::SVN->init($id, $u);
- }
+ my $url = $ra->{url};
+ my $gs = Git::SVN->init($url, undef, undef, undef, 1);
+ my $k = "svn-remote.$gs->{repo_id}.url";
+ my $orig_url = eval { command_oneline(qw/config --get/, $k) };
+ if ($orig_url && ($orig_url ne $gs->{url})) {
+ die "$k already set: $orig_url\n",
+ "wanted to set to: $gs->{url}\n";
}
+ command_oneline('config', $k, $gs->{url}) unless $orig_url;
+ my $remote_path = "$ra->{svn_path}/$repo_path/*";
+ $remote_path =~ s#/+#/#g;
+ $remote_path =~ s#^/##g;
my ($n) = ($switch =~ /^--(\w+)/);
- command_noisy('config', "svn.$n", $url);
-}
-
-sub common_prefix {
- my $paths = shift;
- my %common;
- foreach (@$paths) {
- my @tmp = split m#/#, $_;
- my $p = '';
- while (my $x = shift @tmp) {
- $p .= "/$x";
- $common{$p} ||= 0;
- $common{$p}++;
- }
- }
- foreach (sort {length $b <=> length $a} keys %common) {
- if ($common{$_} == @$paths) {
- return $_;
- }
- }
- return '';
-}
-
-# grafts set here are 'stronger' in that they're based on actual tree
-# matches, and won't be deleted from merge-base checking in write_grafts()
-sub graft_tree_joins {
- my $grafts = shift;
- map_tree_joins() if (@_branch_from && !%tree_map);
- return unless %tree_map;
-
- git_svn_each(sub {
- my $i = shift;
- my @args = (qw/rev-list --pretty=raw/, "refs/remotes/$i");
- my ($fh, $ctx) = command_output_pipe(@args);
- while (<$fh>) {
- next unless /^commit ($sha1)$/o;
- my $c = $1;
- my ($t) = (<$fh> =~ /^tree ($sha1)$/o);
- next unless $tree_map{$t};
-
- my $l;
- do {
- $l = readline $fh;
- } until ($l =~ /^committer (?:.+) (\d+) ([\-\+]?\d+)$/);
-
- my ($s, $tz) = ($1, $2);
- if ($tz =~ s/^\+//) {
- $s += tz_to_s_offset($tz);
- } elsif ($tz =~ s/^\-//) {
- $s -= tz_to_s_offset($tz);
- }
-
- my ($url_a, $r_a, $uuid_a) = cmt_metadata($c);
-
- foreach my $p (@{$tree_map{$t}}) {
- next if $p eq $c;
- my $mb = eval { command('merge-base', $c, $p) };
- next unless ($@ || $?);
- if (defined $r_a) {
- # see if SVN says it's a relative
- my ($url_b, $r_b, $uuid_b) =
- cmt_metadata($p);
- next if (defined $url_b &&
- defined $url_a &&
- ($url_a eq $url_b) &&
- ($uuid_a eq $uuid_b));
- if ($uuid_a eq $uuid_b) {
- if ($r_b < $r_a) {
- $grafts->{$c}->{$p} = 2;
- next;
- } elsif ($r_b > $r_a) {
- $grafts->{$p}->{$c} = 2;
- next;
- }
- }
- }
- my $ct = get_commit_time($p);
- if ($ct < $s) {
- $grafts->{$c}->{$p} = 2;
- } elsif ($ct > $s) {
- $grafts->{$p}->{$c} = 2;
- }
- # what should we do when $ct == $s ?
- }
- }
- command_close_pipe($fh, $ctx);
- });
-}
-
-sub graft_file_copy_lib {
- my ($grafts, $l_map, $u) = @_;
- my $tree_paths = $l_map->{$u};
- my $pfx = common_prefix([keys %$tree_paths]);
- my ($repo, $path) = repo_path_split($u.$pfx);
- $SVN = Git::SVN::Ra->new($repo);
-
- my ($base, $head) = libsvn_parse_revision();
- my $inc = 1000;
- my ($min, $max) = ($base, $head < $base+$inc ? $head : $base+$inc);
- my $eh = $SVN::Error::handler;
- $SVN::Error::handler = \&libsvn_skip_unknown_revs;
- while (1) {
- $SVN->dup->get_log([$path], $min, $max, 0, 2, 1,
- sub {
- libsvn_graft_file_copies($grafts, $tree_paths,
- $path, @_);
- });
- last if ($max >= $head);
- $min = $max + 1;
- $max += $inc;
- $max = $head if ($max > $head);
- }
- $SVN::Error::handler = $eh;
-}
-
-sub process_merge_msg_matches {
- my ($grafts, $l_map, $u, $p, $c, @matches) = @_;
- my (@strong, @weak);
- foreach (@matches) {
- # merging with ourselves is not interesting
- next if $_ eq $p;
- if ($l_map->{$u}->{$_}) {
- push @strong, $_;
- } else {
- push @weak, $_;
- }
- }
- foreach my $w (@weak) {
- last if @strong;
- # no exact match, use branch name as regexp.
- my $re = qr/\Q$w\E/i;
- foreach (keys %{$l_map->{$u}}) {
- if (/$re/) {
- push @strong, $l_map->{$u}->{$_};
- last;
- }
- }
- last if @strong;
- $w = basename($w);
- $re = qr/\Q$w\E/i;
- foreach (keys %{$l_map->{$u}}) {
- if (/$re/) {
- push @strong, $l_map->{$u}->{$_};
- last;
- }
- }
- }
- my ($rev) = ($c->{m} =~ /^git-svn-id:\s(?:\S+?)\@(\d+)
- \s(?:[a-f\d\-]+)$/xsm);
- unless (defined $rev) {
- ($rev) = ($c->{m} =~/^git-svn-id:\s(\d+)
- \@(?:[a-f\d\-]+)/xsm);
- return unless defined $rev;
- }
- foreach my $m (@strong) {
- my ($r0, $s0) = find_rev_before($rev, $m, 1);
- $grafts->{$c->{c}}->{$s0} = 1 if defined $s0;
- }
-}
-
-sub graft_merge_msg {
- my ($grafts, $l_map, $u, $p, @re) = @_;
-
- my $x = $l_map->{$u}->{$p};
- my $rl = rev_list_raw("refs/remotes/$x");
- while (my $c = next_rev_list_entry($rl)) {
- foreach my $re (@re) {
- my (@br) = ($c->{m} =~ /$re/g);
- next unless @br;
- process_merge_msg_matches($grafts,$l_map,$u,$p,$c,@br);
- }
+ if (length $pfx && $pfx !~ m#/$#) {
+ die "--prefix='$pfx' must have a trailing slash '/'\n";
}
+ command_noisy('config', "svn-remote.$gs->{repo_id}.$n",
+ "$remote_path:refs/remotes/$pfx*");
}
sub verify_ref {
{ STDERR => 0 }); };
}
-sub repo_path_split {
- my $full_url = shift;
- $full_url =~ s#/+$##;
-
- foreach (@repo_path_split_cache) {
- if ($full_url =~ s#$_##) {
- my $u = $1;
- $full_url =~ s#^/+##;
- return ($u, $full_url);
- }
- }
- my $tmp = Git::SVN::Ra->new($full_url);
- return ($tmp->{repos_root}, $tmp->{svn_path});
-}
-
-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([$GIT_SVN_DIR]);
- mkpath(["$GIT_SVN_DIR/info"]);
- open my $fh, '>>',$REVDB or croak $!;
- close $fh;
- s_to_file($SVN_URL,"$GIT_SVN_DIR/info/url");
-
-}
-
sub get_tree_from_treeish {
my ($treeish) = @_;
# $treeish can be a symbolic ref, too:
return $expected;
}
-sub get_diff {
- my ($from, $treeish) = @_;
- print "diff-tree $from $treeish\n";
- my @diff_tree = qw(diff-tree -z -r);
- if ($_cp_similarity) {
- push @diff_tree, "-C$_cp_similarity";
- } else {
- push @diff_tree, '-C';
- }
- push @diff_tree, '--find-copies-harder' if $_find_copies_harder;
- push @diff_tree, "-l$_l" if defined $_l;
- push @diff_tree, $from, $treeish;
- my ($diff_fh, $ctx) = command_output_pipe(@diff_tree);
- 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 ($4 =~ /^(?:C|R)$/) {
- $state = 'file_a';
+sub get_commit_entry {
+ my ($treeish) = shift;
+ my %log_entry = ( log => '', tree => get_tree_from_treeish($treeish) );
+ my $commit_editmsg = "$ENV{GIT_DIR}/COMMIT_EDITMSG";
+ my $commit_msg = "$ENV{GIT_DIR}/COMMIT_MSG";
+ open my $log_fh, '>', $commit_editmsg or croak $!;
+
+ my $type = command_oneline(qw/cat-file -t/, $treeish);
+ if ($type eq 'commit' || $type eq 'tag') {
+ my ($msg_fh, $ctx) = command_output_pipe('cat-file',
+ $type, $treeish);
+ my $in_msg = 0;
+ while (<$msg_fh>) {
+ if (!$in_msg) {
+ $in_msg = 1 if (/^\s*$/);
+ } elsif (/^git-svn-id: /) {
+ # skip this for now, we regenerate the
+ # correct one on re-fetch anyways
+ # TODO: set *:merge properties or like...
} 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 $_\n";
- }
- }
- command_close_pipe($diff_fh, $ctx);
- return \@mods;
-}
-
-sub get_commit_entry {
- my ($treeish) = shift;
- my %log_entry = ( log => '', tree => get_tree_from_treeish($treeish) );
- my $commit_editmsg = "$ENV{GIT_DIR}/COMMIT_EDITMSG";
- my $commit_msg = "$ENV{GIT_DIR}/COMMIT_MSG";
- open my $log_fh, '>', $commit_editmsg or croak $!;
-
- my $type = command_oneline(qw/cat-file -t/, $treeish);
- if ($type eq 'commit' || $type eq 'tag') {
- my ($msg_fh, $ctx) = command_output_pipe('cat-file',
- $type, $treeish);
- my $in_msg = 0;
- while (<$msg_fh>) {
- if (!$in_msg) {
- $in_msg = 1 if (/^\s*$/);
- } elsif (/^git-svn-id: /) {
- # skip this for now, we regenerate the
- # correct one on re-fetch anyways
- # TODO: set *:merge properties or like...
- } else {
- print $log_fh $_ or croak $!;
+ print $log_fh $_ or croak $!;
}
}
command_close_pipe($msg_fh, $ctx);
\%log_entry;
}
-sub set_svn_commit_env {
- if (defined $LC_ALL) {
- $ENV{LC_ALL} = $LC_ALL;
- } else {
- delete $ENV{LC_ALL};
- }
-}
-
-sub rev_list_raw {
- my ($fh, $c) = command_output_pipe(qw/rev-list --pretty=raw/, @_);
- return { fh => $fh, ctx => $c, t => { } };
-}
-
-sub next_rev_list_entry {
- my $rl = shift;
- my $fh = $rl->{fh};
- my $x = $rl->{t};
- while (<$fh>) {
- if (/^commit ($sha1)$/o) {
- if ($x->{c}) {
- $rl->{t} = { c => $1 };
- return $x;
- } else {
- $x->{c} = $1;
- }
- } elsif (/^parent ($sha1)$/o) {
- $x->{p}->{$1} = 1;
- } elsif (s/^ //) {
- $x->{m} ||= '';
- $x->{m} .= $_;
- }
- }
- command_close_pipe($fh, $rl->{ctx});
- return ($x != $rl->{t}) ? $x : undef;
-}
-
sub s_to_file {
my ($str, $file, $mode) = @_;
open my $fd,'>',$file or croak $!;
return $ret;
}
-sub assert_revision_unknown {
- my $r = shift;
- if (my $c = revdb_get($REVDB, $r)) {
- croak "$r = $c already exists! Why are we refetching it?";
- }
-}
-
-sub git_commit {
- my ($log_entry, @parents) = @_;
- assert_revision_unknown($log_entry->{revision});
- map_tree_joins() if (@_branch_from && !%tree_map);
-
- my (@tmp_parents, @exec_parents, %seen_parent);
- if (my $lparents = $log_entry->{parents}) {
- @tmp_parents = @$lparents
- }
- # commit parents can be conditionally bound to a particular
- # svn revision via: "svn_revno=commit_sha1", filter them out here:
- foreach my $p (@parents) {
- next unless defined $p;
- if ($p =~ /^(\d+)=($sha1_short)$/o) {
- if ($1 == $log_entry->{revision}) {
- push @tmp_parents, $2;
- }
- } else {
- push @tmp_parents, $p if $p =~ /$sha1_short/o;
- }
- }
- my $tree = $log_entry->{tree};
- if (!defined $tree) {
- my $index = set_index($GIT_SVN_INDEX);
- $tree = command_oneline('write-tree');
- croak $? if $?;
- restore_index($index);
- }
- # just in case we clobber the existing ref, we still want that ref
- # as our parent:
- if (my $cur = verify_ref("refs/remotes/$GIT_SVN^0")) {
- chomp $cur;
- push @tmp_parents, $cur;
- }
-
- if (exists $tree_map{$tree}) {
- foreach my $p (@{$tree_map{$tree}}) {
- my $skip;
- foreach (@tmp_parents) {
- # see if a common parent is found
- my $mb = eval { command('merge-base', $_, $p) };
- next if ($@ || $?);
- $skip = 1;
- last;
- }
- next if $skip;
- my ($url_p, $r_p, $uuid_p) = cmt_metadata($p);
- next if (($SVN->uuid eq $uuid_p) &&
- ($log_entry->{revision} > $r_p));
- next if (defined $url_p && defined $SVN_URL &&
- ($SVN->uuid eq $uuid_p) &&
- ($url_p eq $SVN_URL));
- push @tmp_parents, $p;
- }
- }
- foreach (@tmp_parents) {
- next if $seen_parent{$_};
- $seen_parent{$_} = 1;
- push @exec_parents, $_;
- # MAXPARENT is defined to 16 in commit-tree.c:
- last if @exec_parents > 16;
- }
-
- set_commit_env($log_entry);
- my @exec = ('git-commit-tree', $tree);
- push @exec, '-p', $_ foreach @exec_parents;
- defined(my $pid = open3(my $msg_fh, my $out_fh, '>&STDERR', @exec))
- or croak $!;
- print $msg_fh $log_entry->{log} or croak $!;
- unless ($_no_metadata) {
- print $msg_fh "\ngit-svn-id: $SVN_URL\@$log_entry->{revision} ",
- $SVN->uuid,"\n" or croak $!;
- }
- $msg_fh->flush == 0 or croak $!;
- close $msg_fh or croak $!;
- chomp(my $commit = do { local $/; <$out_fh> });
- close $out_fh or croak $!;
- waitpid $pid, 0;
- croak $? if $?;
- if ($commit !~ /^$sha1$/o) {
- die "Failed to commit, invalid sha1: $commit\n";
- }
- command_noisy('update-ref',"refs/remotes/$GIT_SVN",$commit);
- revdb_set($REVDB, $log_entry->{revision}, $commit);
-
- # this output is read via pipe, do not change:
- print "r$log_entry->{revision} = $commit\n";
- return $commit;
-}
-
-sub check_repack {
- if ($_repack && (--$_repack_nr == 0)) {
- $_repack_nr = $_repack;
- # repack doesn't use any arguments with spaces in them, does it?
- command_noisy('repack', split(/\s+/, $_repack_flags));
- }
-}
-
-sub set_commit_env {
- my ($log_entry) = @_;
- my $author = $log_entry->{author};
- if (!defined $author || length $author == 0) {
- $author = '(no author)';
- }
- my ($name,$email) = defined $users{$author} ? @{$users{$author}}
- : ($author,$author . '@' . $SVN->uuid);
- $ENV{GIT_AUTHOR_NAME} = $ENV{GIT_COMMITTER_NAME} = $name;
- $ENV{GIT_AUTHOR_EMAIL} = $ENV{GIT_COMMITTER_EMAIL} = $email;
- $ENV{GIT_AUTHOR_DATE} = $ENV{GIT_COMMITTER_DATE} = $log_entry->{date};
-}
-
-sub check_upgrade_needed {
- if (!-r $REVDB) {
- -d $GIT_SVN_DIR or mkpath([$GIT_SVN_DIR]);
- open my $fh, '>>',$REVDB or croak $!;
- close $fh;
- }
- return unless eval {
- command([qw/rev-parse --verify/,"$GIT_SVN-HEAD^0"],
- {STDERR => 0});
- };
- my $head = eval { command('rev-parse',"refs/remotes/$GIT_SVN") };
- if ($@ || !$head) {
- print STDERR "Please run: $0 rebuild --upgrade\n";
- exit 1;
- }
-}
-
-# fills %tree_map with a reverse mapping of trees to commits. Useful
-# for finding parents to commit on.
-sub map_tree_joins {
- my %seen;
- foreach my $br (@_branch_from) {
- my $pipe = command_output_pipe(qw/rev-list
- --topo-order --pretty=raw/, $br);
- while (<$pipe>) {
- if (/^commit ($sha1)$/o) {
- my $commit = $1;
-
- # if we've seen a commit,
- # we've seen its parents
- last if $seen{$commit};
- my ($tree) = (<$pipe> =~ /^tree ($sha1)$/o);
- unless (defined $tree) {
- die "Failed to parse commit $commit\n";
- }
- push @{$tree_map{$tree}}, $commit;
- $seen{$commit} = 1;
- }
- }
- close $pipe;
- }
-}
-
-sub load_all_refs {
- if (@_branch_from) {
- print STDERR '--branch|-b parameters are ignored when ',
- "--branch-all-refs|-B is passed\n";
- }
-
- # don't worry about rev-list on non-commit objects/tags,
- # it shouldn't blow up if a ref is a blob or tree...
- @_branch_from = command(qw/rev-parse --symbolic --all/);
-}
-
# '<svn username> = real-name <email address>' mapping based on git-svnimport:
sub load_authors {
open my $authors, '<', $_authors or die "Can't open $_authors $!\n";
close $authors or croak $!;
}
-sub git_svn_each {
- my $sub = shift;
- foreach (command(qw/rev-parse --symbolic --all/)) {
- next unless s#^refs/remotes/##;
- chomp $_;
- next unless -f "$GIT_DIR/svn/$_/info/url";
- &$sub($_);
- }
-}
-
-sub migrate_revdb {
- git_svn_each(sub {
- my $id = shift;
- defined(my $pid = fork) or croak $!;
- if (!$pid) {
- $GIT_SVN = $ENV{GIT_SVN_ID} = $id;
- init_vars();
- exit 0 if -r $REVDB;
- print "Upgrading svn => git mapping...\n";
- -d $GIT_SVN_DIR or mkpath([$GIT_SVN_DIR]);
- open my $fh, '>>',$REVDB or croak $!;
- close $fh;
- rebuild();
- print "Done upgrading. You may now delete the ",
- "deprecated $GIT_SVN_DIR/revs directory\n";
- exit 0;
- }
- waitpid $pid, 0;
- croak $? if $?;
- });
-}
-
-sub migration_check {
- migrate_revdb() unless (-e $REVDB);
- return if (-d "$GIT_DIR/svn" || !-d $GIT_DIR);
- print "Upgrading repository...\n";
- unless (-d "$GIT_DIR/svn") {
- mkdir "$GIT_DIR/svn" or croak $!;
- }
- print "Data from a previous version of git-svn exists, but\n\t",
- "$GIT_SVN_DIR\n\t(required for this version ",
- "($VERSION) of git-svn) does not.\n";
-
- foreach my $x (command(qw/rev-parse --symbolic --all/)) {
- next unless $x =~ s#^refs/remotes/##;
- chomp $x;
- next unless -f "$GIT_DIR/$x/info/url";
- my $u = eval { file_to_s("$GIT_DIR/$x/info/url") };
- next unless $u;
- my $dn = dirname("$GIT_DIR/svn/$x");
- mkpath([$dn]) unless -d $dn;
- rename "$GIT_DIR/$x", "$GIT_DIR/svn/$x" or croak "$!: $x";
- }
- migrate_revdb() if (-d $GIT_SVN_DIR && !-w $REVDB);
- print "Done upgrading.\n";
-}
-
-sub find_rev_before {
- my ($r, $id, $eq_ok) = @_;
- my $f = "$GIT_DIR/svn/$id/.rev_db";
- return (undef,undef) unless -r $f;
- --$r unless $eq_ok;
- while ($r > 0) {
- if (my $c = revdb_get($f, $r)) {
- return ($r, $c);
- }
- --$r;
- }
- return (undef, undef);
-}
-
-sub init_vars {
- $GIT_SVN ||= $ENV{GIT_SVN_ID} || 'git-svn';
- $Git::SVN::default = $GIT_SVN;
- $GIT_SVN_DIR = "$GIT_DIR/svn/$GIT_SVN";
- $REVDB = "$GIT_SVN_DIR/.rev_db";
- $GIT_SVN_INDEX = "$GIT_SVN_DIR/index";
- $SVN_URL = undef;
- %tree_map = ();
-}
-
# convert GetOpt::Long specs for use by git-config
sub read_repo_config {
- return unless -d $GIT_DIR;
+ return unless -d $ENV{GIT_DIR};
my $opts = shift;
+ my @config_only;
foreach my $o (keys %$opts) {
+ # if we have mixedCase and a long option-only, then
+ # it's a config-only variable that we don't need for
+ # the command-line.
+ push @config_only, $o if ($o =~ /[A-Z]/ && $o =~ /^[a-z]+$/i);
my $v = $opts->{$o};
- my ($key) = ($o =~ /^([a-z\-]+)/);
+ my ($key) = ($o =~ /^([a-zA-Z\-]+)/);
$key =~ s/-//g;
my $arg = 'git-config';
$arg .= ' --int' if ($o =~ /[:=]i$/);
}
}
}
-}
-
-sub set_default_vals {
- if (defined $_repack) {
- $_repack = 1000 if ($_repack <= 0);
- $_repack_nr = $_repack;
- $_repack_flags ||= '-d';
- }
-}
-
-sub read_grafts {
- my $gr_file = shift;
- my ($grafts, $comments) = ({}, {});
- if (open my $fh, '<', $gr_file) {
- my @tmp;
- while (<$fh>) {
- if (/^($sha1)\s+/) {
- my $c = $1;
- if (@tmp) {
- @{$comments->{$c}} = @tmp;
- @tmp = ();
- }
- foreach my $p (split /\s+/, $_) {
- $grafts->{$c}->{$p} = 1;
- }
- } else {
- push @tmp, $_;
- }
- }
- close $fh or croak $!;
- @{$comments->{'END'}} = @tmp if @tmp;
- }
- return ($grafts, $comments);
-}
-
-sub write_grafts {
- my ($grafts, $comments, $gr_file) = @_;
-
- open my $fh, '>', $gr_file or croak $!;
- foreach my $c (sort keys %$grafts) {
- if ($comments->{$c}) {
- print $fh $_ foreach @{$comments->{$c}};
- }
- my $p = $grafts->{$c};
- my %x; # real parents
- delete $p->{$c}; # commits are not self-reproducing...
- my $ch = command_output_pipe(qw/cat-file commit/, $c);
- while (<$ch>) {
- if (/^parent ($sha1)/) {
- $x{$1} = $p->{$1} = 1;
- } else {
- last unless /^\S/;
- }
- }
- close $ch; # breaking the pipe
-
- # if real parents are the only ones in the grafts, drop it
- next if join(' ',sort keys %$p) eq join(' ',sort keys %x);
-
- my (@ip, @jp, $mb);
- my %del = %x;
- @ip = @jp = keys %$p;
- foreach my $i (@ip) {
- next if $del{$i} || $p->{$i} == 2;
- foreach my $j (@jp) {
- next if $i eq $j || $del{$j} || $p->{$j} == 2;
- $mb = eval { command('merge-base', $i, $j) };
- next unless $mb;
- chomp $mb;
- next if $x{$mb};
- if ($mb eq $j) {
- delete $p->{$i};
- $del{$i} = 1;
- } elsif ($mb eq $i) {
- delete $p->{$j};
- $del{$j} = 1;
- }
- }
- }
-
- # if real parents are the only ones in the grafts, drop it
- next if join(' ',sort keys %$p) eq join(' ',sort keys %x);
-
- print $fh $c, ' ', join(' ', sort keys %$p),"\n";
- }
- if ($comments->{'END'}) {
- print $fh $_ foreach @{$comments->{'END'}};
- }
- close $fh or croak $!;
-}
-
-sub read_url_paths_all {
- my ($l_map, $pfx, $p) = @_;
- my @dir;
- foreach (<$p/*>) {
- if (-r "$_/info/url") {
- $pfx .= '/' if $pfx && $pfx !~ m!/$!;
- my $id = $pfx . basename $_;
- my $url = file_to_s("$_/info/url");
- my ($u, $p) = repo_path_split($url);
- $l_map->{$u}->{$p} = $id;
- } elsif (-d $_) {
- push @dir, $_;
- }
- }
- foreach (@dir) {
- my $x = $_;
- $x =~ s!^\Q$GIT_DIR\E/svn/!!o;
- read_url_paths_all($l_map, $x, $_);
- }
-}
-
-# this one only gets ids that have been imported, not new ones
-sub read_url_paths {
- my $l_map = {};
- git_svn_each(sub { my $x = shift;
- my $url = file_to_s("$GIT_DIR/svn/$x/info/url");
- my ($u, $p) = repo_path_split($url);
- $l_map->{$u}->{$p} = $x;
- });
- return $l_map;
+ delete @$opts{@config_only} if @config_only;
}
sub extract_metadata {
command(qw/cat-file commit/, shift)))[-1]);
}
-sub get_commit_time {
- my $cmt = shift;
- my $fh = command_output_pipe(qw/rev-list --pretty=raw -n1/, $cmt);
+sub working_head_info {
+ my ($head, $refs) = @_;
+ my ($url, $rev, $uuid);
+ my ($fh, $ctx) = command_output_pipe('rev-list', $head);
while (<$fh>) {
- /^committer\s(?:.+) (\d+) ([\-\+]?\d+)$/ or next;
- my ($s, $tz) = ($1, $2);
- if ($tz =~ s/^\+//) {
- $s += tz_to_s_offset($tz);
- } elsif ($tz =~ s/^\-//) {
- $s -= tz_to_s_offset($tz);
- }
- close $fh;
- return $s;
+ chomp;
+ ($url, $rev, $uuid) = cmt_metadata($_);
+ last if (defined $url && defined $rev && defined $uuid);
+ unshift @$refs, $_ if $refs;
}
- die "Can't get commit time for commit: $cmt\n";
-}
-
-sub tz_to_s_offset {
- my ($tz) = @_;
- $tz =~ s/(\d\d)$//;
- return ($1 * 60) + ($tz * 3600);
+ close $fh; # break the pipe
+ ($url, $rev, $uuid);
}
package Git::SVN;
use strict;
use warnings;
-use vars qw/$default/;
+use vars qw/$default_repo_id $default_ref_id $_no_metadata $_follow_parent
+ $_repack $_repack_flags $_use_svm_props $_head
+ $_use_svnsync_props $no_reuse_existing/;
use Carp qw/croak/;
use File::Path qw/mkpath/;
+use File::Copy qw/copy/;
use IPC::Open3;
+my $_repack_nr;
# properties that we do not log:
my %SKIP_PROP;
BEGIN {
svn:entry:last-author
svn:entry:uuid
svn:entry:committed-date/;
+
+ # some options are read globally, but can be overridden locally
+ # per [svn-remote "..."] section. Command-line options will *NOT*
+ # override options set in an [svn-remote "..."] section
+ my $e;
+ foreach (qw/follow_parent no_metadata use_svm_props
+ use_svnsync_props/) {
+ my $key = $_;
+ $key =~ tr/_//d;
+ $e .= "sub $_ {
+ my (\$self) = \@_;
+ return \$self->{-$_} if exists \$self->{-$_};
+ my \$k = \"svn-remote.\$self->{repo_id}\.$key\";
+ eval { command_oneline(qw/config --get/, \$k) };
+ if (\$@) {
+ \$self->{-$_} = \$Git::SVN::_$_;
+ } else {
+ my \$v = command_oneline(qw/config --bool/,\$k);
+ \$self->{-$_} = \$v eq 'false' ? 0 : 1;
+ }
+ return \$self->{-$_} }\n";
+ }
+ $e .= "1;\n";
+ eval $e or die $@;
+}
+
+my %LOCKFILES;
+END { unlink keys %LOCKFILES if %LOCKFILES }
+
+sub resolve_local_globs {
+ my ($url, $fetch, $glob_spec) = @_;
+ return unless defined $glob_spec;
+ my $ref = $glob_spec->{ref};
+ my $path = $glob_spec->{path};
+ foreach (command(qw#for-each-ref --format=%(refname) refs/remotes#)) {
+ next unless m#^refs/remotes/$ref->{regex}$#;
+ my $p = $1;
+ my $pathname = $path->full_path($p);
+ my $refname = $ref->full_path($p);
+ if (my $existing = $fetch->{$pathname}) {
+ if ($existing ne $refname) {
+ die "Refspec conflict:\n",
+ "existing: refs/remotes/$existing\n",
+ " globbed: refs/remotes/$refname\n";
+ }
+ my $u = (::cmt_metadata("refs/remotes/$refname"))[0];
+ $u =~ s!^\Q$url\E(/|$)!! or die
+ "refs/remotes/$refname: '$url' not found in '$u'\n";
+ if ($pathname ne $u) {
+ warn "W: Refspec glob conflict ",
+ "(ref: refs/remotes/$refname):\n",
+ "expected path: $pathname\n",
+ " real path: $u\n",
+ "Continuing ahead with $u\n";
+ next;
+ }
+ } else {
+ $fetch->{$pathname} = $refname;
+ }
+ }
+}
+
+sub parse_revision_argument {
+ my ($base, $head) = @_;
+ if (!defined $::_revision || $::_revision eq 'BASE:HEAD') {
+ return ($base, $head);
+ }
+ return ($1, $2) if ($::_revision =~ /^(\d+):(\d+)$/);
+ return ($::_revision, $::_revision) if ($::_revision =~ /^\d+$/);
+ return ($head, $head) if ($::_revision eq 'HEAD');
+ return ($base, $1) if ($::_revision =~ /^BASE:(\d+)$/);
+ return ($1, $head) if ($::_revision =~ /^(\d+):HEAD$/);
+ die "revision argument: $::_revision not understood by git-svn\n";
+}
+
+sub fetch_all {
+ my ($repo_id, $remotes) = @_;
+ if (ref $repo_id) {
+ my $gs = $repo_id;
+ $repo_id = undef;
+ $repo_id = $gs->{repo_id};
+ }
+ $remotes ||= read_all_remotes();
+ my $remote = $remotes->{$repo_id} or
+ die "[svn-remote \"$repo_id\"] unknown\n";
+ my $fetch = $remote->{fetch};
+ my $url = $remote->{url} or die "svn-remote.$repo_id.url not defined\n";
+ my (@gs, @globs);
+ my $ra = Git::SVN::Ra->new($url);
+ my $uuid = $ra->get_uuid;
+ my $head = $ra->get_latest_revnum;
+ 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};
+ my $max_rev = eval { tmp_config(qw/--int --get/,
+ "svn-remote.$repo_id.${t}-maxRev") };
+ if (defined $max_rev && ($max_rev < $base)) {
+ $base = $max_rev;
+ } elsif (!defined $max_rev) {
+ $base = 0;
+ }
+ }
+
+ if ($fetch) {
+ foreach my $p (sort keys %$fetch) {
+ my $gs = Git::SVN->new($fetch->{$p}, $repo_id, $p);
+ my $lr = $gs->rev_db_max;
+ if (defined $lr) {
+ $base = $lr if ($lr < $base);
+ }
+ push @gs, $gs;
+ }
+ }
+
+ ($base, $head) = parse_revision_argument($base, $head);
+ $ra->gs_fetch_loop_common($base, $head, \@gs, \@globs);
+}
+
+sub read_all_remotes {
+ my $r = {};
+ foreach (grep { s/^svn-remote\.// } command(qw/config -l/)) {
+ if (m!^(.+)\.fetch=\s*(.*)\s*:\s*refs/remotes/(.+)\s*$!) {
+ $r->{$1}->{fetch}->{$2} = $3;
+ } elsif (m!^(.+)\.url=\s*(.*)\s*$!) {
+ $r->{$1}->{url} = $2;
+ } elsif (m!^(.+)\.(branches|tags)=
+ (.*):refs/remotes/(.+)\s*$/!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($g) };
+ if (length($rs->{ref}->{right}) != 0) {
+ die "The '*' glob character must be the last ",
+ "character of '$g'\n";
+ }
+ }
+ }
+ $r;
+}
+
+sub init_vars {
+ if (defined $_repack) {
+ $_repack = 1000 if ($_repack <= 0);
+ $_repack_nr = $_repack;
+ $_repack_flags ||= '-d';
+ }
+}
+
+sub verify_remotes_sanity {
+ return unless -d $ENV{GIT_DIR};
+ my %seen;
+ foreach (command(qw/config -l/)) {
+ if (m!^svn-remote\.(?:.+)\.fetch=.*:refs/remotes/(\S+)\s*$!) {
+ if ($seen{$1}) {
+ die "Remote ref refs/remote/$1 is tracked by",
+ "\n \"$_\"\nand\n \"$seen{$1}\"\n",
+ "Please resolve this ambiguity in ",
+ "your git configuration file before ",
+ "continuing\n";
+ }
+ $seen{$1} = $_;
+ }
+ }
+}
+
+# we allow more chars than remotes2config.sh...
+sub sanitize_remote_name {
+ my ($name) = @_;
+ $name =~ tr{A-Za-z0-9:,/+-}{.}c;
+ $name;
+}
+
+sub find_existing_remote {
+ my ($url, $remotes) = @_;
+ return undef if $no_reuse_existing;
+ my $existing;
+ foreach my $repo_id (keys %$remotes) {
+ my $u = $remotes->{$repo_id}->{url} or next;
+ next if $u ne $url;
+ $existing = $repo_id;
+ last;
+ }
+ $existing;
+}
+
+sub init_remote_config {
+ my ($self, $url, $no_write) = @_;
+ $url =~ s!/+$!!; # strip trailing slash
+ my $r = read_all_remotes();
+ my $existing = find_existing_remote($url, $r);
+ if ($existing) {
+ unless ($no_write) {
+ print STDERR "Using existing ",
+ "[svn-remote \"$existing\"]\n";
+ }
+ $self->{repo_id} = $existing;
+ } else {
+ my $min_url = Git::SVN::Ra->new($url)->minimize_url;
+ $existing = find_existing_remote($min_url, $r);
+ if ($existing) {
+ unless ($no_write) {
+ print STDERR "Using existing ",
+ "[svn-remote \"$existing\"]\n";
+ }
+ $self->{repo_id} = $existing;
+ }
+ if ($min_url ne $url) {
+ unless ($no_write) {
+ print STDERR "Using higher level of URL: ",
+ "$url => $min_url\n";
+ }
+ my $old_path = $self->{path};
+ $self->{path} = $url;
+ $self->{path} =~ s!^\Q$min_url\E(/|$)!!;
+ if (length $old_path) {
+ $self->{path} .= "/$old_path";
+ }
+ $url = $min_url;
+ }
+ }
+ my $orig_url;
+ if (!$existing) {
+ # verify that we aren't overwriting anything:
+ $orig_url = eval {
+ command_oneline('config', '--get',
+ "svn-remote.$self->{repo_id}.url")
+ };
+ if ($orig_url && ($orig_url ne $url)) {
+ die "svn-remote.$self->{repo_id}.url already set: ",
+ "$orig_url\nwanted to set to: $url\n";
+ }
+ }
+ my ($xrepo_id, $xpath) = find_ref($self->refname);
+ if (defined $xpath) {
+ die "svn-remote.$xrepo_id.fetch already set to track ",
+ "$xpath:refs/remotes/", $self->refname, "\n";
+ }
+ unless ($no_write) {
+ command_noisy('config',
+ "svn-remote.$self->{repo_id}.url", $url);
+ command_noisy('config', '--add',
+ "svn-remote.$self->{repo_id}.fetch",
+ "$self->{path}:".$self->refname);
+ }
+ $self->{url} = $url;
+}
+
+sub find_by_url { # repos_root and, path are optional
+ my ($class, $full_url, $repos_root, $path) = @_;
+ return undef unless defined $full_url;
+ my $remotes = read_all_remotes();
+ if (defined $full_url && defined $repos_root && !defined $path) {
+ $path = $full_url;
+ $path =~ s#^\Q$repos_root\E(?:/|$)##;
+ }
+ foreach my $repo_id (keys %$remotes) {
+ my $u = $remotes->{$repo_id}->{url} or next;
+ 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}->{$_});
+ }
+ my $p = $path;
+ unless (defined $p) {
+ $p = $full_url;
+ $p =~ s#^\Q$u\E(?:/|$)## or next;
+ }
+ foreach my $f (keys %$fetch) {
+ next if $f ne $p;
+ return Git::SVN->new($fetch->{$f}, $repo_id, $f);
+ }
+ }
+ undef;
}
sub init {
- my ($class, $id, $url) = @_;
- my $self = _new($class, $id);
- mkpath(["$self->{dir}/info"]);
+ my ($class, $url, $path, $repo_id, $ref_id, $no_write) = @_;
+ my $self = _new($class, $repo_id, $ref_id, $path);
if (defined $url) {
- $url =~ s!/+$!!; # strip trailing slash
- ::s_to_file($url, "$self->{dir}/info/url");
+ $self->init_remote_config($url, $no_write);
}
- $self->{url} = $url;
- open my $fh, '>>', $self->{db_path} or croak $!;
- close $fh or croak $!;
$self;
}
+sub find_ref {
+ my ($ref_id) = @_;
+ foreach (command(qw/config -l/)) {
+ next unless m!^svn-remote\.(.+)\.fetch=
+ \s*(.*)\s*:\s*refs/remotes/(.+)\s*$!x;
+ my ($repo_id, $path, $ref) = ($1, $2, $3);
+ if ($ref eq $ref_id) {
+ $path = '' if ($path =~ m#^\./?#);
+ return ($repo_id, $path);
+ }
+ }
+ (undef, undef, undef);
+}
+
sub new {
- my ($class, $id) = @_;
- my $self = _new($class, $id);
- $self->{url} = ::file_to_s("$self->{dir}/info/url");
+ my ($class, $ref_id, $repo_id, $path) = @_;
+ if (defined $ref_id && !defined $repo_id && !defined $path) {
+ ($repo_id, $path) = find_ref($ref_id);
+ if (!defined $repo_id) {
+ die "Could not find a \"svn-remote.*.fetch\" key ",
+ "in the repository configuration matching: ",
+ "refs/remotes/$ref_id\n";
+ }
+ }
+ my $self = _new($class, $repo_id, $ref_id, $path);
+ if (!defined $self->{path} || !length $self->{path}) {
+ my $fetch = command_oneline('config', '--get',
+ "svn-remote.$repo_id.fetch",
+ ":refs/remotes/$ref_id\$") or
+ die "Failed to read \"svn-remote.$repo_id.fetch\" ",
+ "\":refs/remotes/$ref_id\$\" in config\n";
+ ($self->{path}, undef) = split(/\s*:\s*/, $fetch);
+ }
+ $self->{url} = command_oneline('config', '--get',
+ "svn-remote.$repo_id.url") or
+ die "Failed to read \"svn-remote.$repo_id.url\" in config\n";
+ $self->rebuild;
$self;
}
-sub refname { "refs/remotes/$_[0]->{id}" }
+sub refname { "refs/remotes/$_[0]->{ref_id}" }
+
+sub svm_uuid {
+ my ($self) = @_;
+ return $self->{svm}->{uuid} if $self->svm;
+ $self->ra;
+ unless ($self->{svm}) {
+ die "SVM UUID not cached, and reading remotely failed\n";
+ }
+ $self->{svm}->{uuid};
+}
+
+sub svm {
+ my ($self) = @_;
+ return $self->{svm} if $self->{svm};
+ my $svm;
+ # see if we have it in our config, first:
+ eval {
+ my $section = "svn-remote.$self->{repo_id}";
+ $svm = {
+ source => tmp_config('--get', "$section.svm-source"),
+ uuid => tmp_config('--get', "$section.svm-uuid"),
+ replace => tmp_config('--get', "$section.svm-replace"),
+ }
+ };
+ if ($svm && $svm->{source} && $svm->{uuid} && $svm->{replace}) {
+ $self->{svm} = $svm;
+ }
+ $self->{svm};
+}
+
+sub _set_svm_vars {
+ my ($self, $ra) = @_;
+ return $ra if $self->svm;
+
+ my @err = ( "useSvmProps set, but failed to read SVM properties\n",
+ "(svm:source, svm:uuid) ",
+ "from the following URLs:\n" );
+ sub read_svm_props {
+ my ($self, $ra, $path, $r) = @_;
+ my $props = ($ra->get_dir($path, $r))[2];
+ my $src = $props->{'svm:source'};
+ my $uuid = $props->{'svm:uuid'};
+ return undef if (!$src || !$uuid);
+
+ chomp($src, $uuid);
+
+ $uuid =~ m{^[0-9a-f\-]{30,}$}
+ or die "doesn't look right - svm:uuid is '$uuid'\n";
+
+ # the '!' is used to mark the repos_root!/relative/path
+ $src =~ s{/?!/?}{/};
+ $src =~ s{/+$}{}; # no trailing slashes please
+ # username is of no interest
+ $src =~ s{(^[a-z\+]*://)[^/@]*@}{$1};
+
+ my $replace = $ra->{url};
+ $replace .= "/$path" if length $path;
+
+ my $section = "svn-remote.$self->{repo_id}";
+ tmp_config("$section.svm-source", $src);
+ tmp_config("$section.svm-replace", $replace);
+ tmp_config("$section.svm-uuid", $uuid);
+ $self->{svm} = {
+ source => $src,
+ uuid => $uuid,
+ replace => $replace
+ };
+ }
+
+ my $r = $ra->get_latest_revnum;
+ my $path = $self->{path};
+ my %tried;
+ while (length $path) {
+ unless ($tried{"$self->{url}/$path"}) {
+ return $ra if $self->read_svm_props($ra, $path, $r);
+ $tried{"$self->{url}/$path"} = 1;
+ }
+ $path =~ s#/?[^/]+$##;
+ }
+ die "Path: '$path' should be ''\n" if $path ne '';
+ return $ra if $self->read_svm_props($ra, $path, $r);
+ $tried{"$self->{url}/$path"} = 1;
+
+ if ($ra->{repos_root} eq $self->{url}) {
+ die @err, (map { " $_\n" } keys %tried), "\n";
+ }
+
+ # nope, make sure we're connected to the repository root:
+ my $ok;
+ my @tried_b;
+ $path = $ra->{svn_path};
+ $ra = Git::SVN::Ra->new($ra->{repos_root});
+ while (length $path) {
+ unless ($tried{"$ra->{url}/$path"}) {
+ $ok = $self->read_svm_props($ra, $path, $r);
+ last if $ok;
+ $tried{"$ra->{url}/$path"} = 1;
+ }
+ $path =~ s#/?[^/]+$##;
+ }
+ die "Path: '$path' should be ''\n" if $path ne '';
+ $ok ||= $self->read_svm_props($ra, $path, $r);
+ $tried{"$ra->{url}/$path"} = 1;
+ if (!$ok) {
+ die @err, (map { " $_\n" } keys %tried), "\n";
+ }
+ Git::SVN::Ra->new($self->{url});
+}
+
+sub svnsync {
+ my ($self) = @_;
+ return $self->{svnsync} if $self->{svnsync};
+
+ if ($self->no_metadata) {
+ die "Can't have both 'noMetadata' and ",
+ "'useSvnsyncProps' options set!\n";
+ }
+ if ($self->rewrite_root) {
+ die "Can't have both 'useSvnsyncProps' and 'rewriteRoot' ",
+ "options set!\n";
+ }
+
+ my $svnsync;
+ # see if we have it in our config, first:
+ eval {
+ my $section = "svn-remote.$self->{repo_id}";
+ $svnsync = {
+ url => tmp_config('--get', "$section.svnsync-url"),
+ uuid => tmp_config('--get', "$section.svnsync-uuid"),
+ }
+ };
+ if ($svnsync && $svnsync->{url} && $svnsync->{uuid}) {
+ return $self->{svnsync} = $svnsync;
+ }
+
+ my $err = "useSvnsyncProps set, but failed to read " .
+ "svnsync property: svn:sync-from-";
+ my $rp = $self->ra->rev_proplist(0);
+
+ my $url = $rp->{'svn:sync-from-url'} or die $err . "url\n";
+ $url =~ m{^[a-z\+]+://} or
+ die "doesn't look right - svn:sync-from-url is '$url'\n";
+
+ my $uuid = $rp->{'svn:sync-from-uuid'} or die $err . "uuid\n";
+ $uuid =~ m{^[0-9a-f\-]{30,}$} or
+ die "doesn't look right - svn:sync-from-uuid is '$uuid'\n";
+
+ my $section = "svn-remote.$self->{repo_id}";
+ tmp_config('--add', "$section.svnsync-uuid", $uuid);
+ tmp_config('--add', "$section.svnsync-url", $url);
+ return $self->{svnsync} = { url => $url, uuid => $uuid };
+}
+
+# this allows us to memoize our SVN::Ra UUID locally and avoid a
+# remote lookup (useful for 'git svn log').
+sub ra_uuid {
+ my ($self) = @_;
+ unless ($self->{ra_uuid}) {
+ my $key = "svn-remote.$self->{repo_id}.uuid";
+ my $uuid = eval { tmp_config('--get', $key) };
+ if (!$@ && $uuid && $uuid =~ /^([a-f\d\-]{30,})$/) {
+ $self->{ra_uuid} = $uuid;
+ } else {
+ die "ra_uuid called without URL\n" unless $self->{url};
+ $self->{ra_uuid} = $self->ra->get_uuid;
+ tmp_config('--add', $key, $self->{ra_uuid});
+ }
+ }
+ $self->{ra_uuid};
+}
sub ra {
my ($self) = shift;
- $self->{ra} ||= Git::SVN::Ra->new($self->{url});
+ my $ra = Git::SVN::Ra->new($self->{url});
+ if ($self->use_svm_props && !$self->{svm}) {
+ if ($self->no_metadata) {
+ die "Can't have both 'noMetadata' and ",
+ "'useSvmProps' options set!\n";
+ } elsif ($self->use_svnsync_props) {
+ die "Can't have both 'useSvnsyncProps' and ",
+ "'useSvmProps' options set!\n";
+ }
+ $ra = $self->_set_svm_vars($ra);
+ $self->{-want_revprops} = 1;
+ }
+ $ra;
}
-sub copy_remote_ref {
+sub rel_path {
my ($self) = @_;
- my $origin = $::_cp_remote ? $::_cp_remote : 'origin';
- my $ref = $self->refname;
- if (command('ls-remote', $origin, $ref)) {
- command_noisy('fetch', $origin, "$ref:$ref");
- } elsif ($::_cp_remote && !$::_upgrade) {
- die "Unable to find remote reference: $ref on $origin\n";
- }
+ my $repos_root = $self->ra->{repos_root};
+ return $self->{path} if ($self->{url} eq $repos_root);
+ die "BUG: rel_path failed! repos_root: $repos_root, Ra URL: ",
+ $self->ra->{url}, " path: $self->{path}, URL: $self->{url}\n";
}
sub traverse_ignore {
my ($self, $fh, $path, $r) = @_;
$path =~ s#^/+##g;
- my ($dirent, undef, $props) = $self->ra->get_dir($path, $r);
+ my $ra = $self->ra;
+ my ($dirent, undef, $props) = $ra->get_dir($path, $r);
my $p = $path;
- $p =~ s#^\Q$self->{ra}->{svn_path}\E/##;
+ $p =~ s#^\Q$self->{path}\E(/|$)##;
print $fh length $p ? "\n# $p\n" : "\n# /\n";
if (my $s = $props->{'svn:ignore'}) {
$s =~ s/[\r\n]+/\n/g;
}
}
+sub last_rev { ($_[0]->last_rev_commit)[0] }
+sub last_commit { ($_[0]->last_rev_commit)[1] }
+
# returns the newest SVN revision number and newest commit SHA1
sub last_rev_commit {
my ($self) = @_;
return ($self->{last_rev}, $self->{last_commit});
}
my $c = ::verify_ref($self->refname.'^0');
- if (defined $c && length $c) {
+ if ($c && !$self->use_svm_props && !$self->no_metadata) {
my $rev = (::cmt_metadata($c))[1];
if (defined $rev) {
($self->{last_rev}, $self->{last_commit}) = ($rev, $c);
return ($rev, $c);
}
}
+ my $db_path = $self->db_path;
+ unless (-e $db_path) {
+ ($self->{last_rev}, $self->{last_commit}) = (undef, undef);
+ return (undef, undef);
+ }
my $offset = -41; # from tail
my $rl;
- open my $fh, '<', $self->{db_path} or
- croak "$self->{db_path} not readable: $!\n";
- seek $fh, $offset, 2;
- $rl = readline $fh;
- defined $rl or return (undef, undef);
+ open my $fh, '<', $db_path or croak "$db_path not readable: $!\n";
+ sysseek($fh, $offset, 2); # don't care for errors
+ sysread($fh, $rl, 41) == 41 or return (undef, undef);
chomp $rl;
- while ($c ne $rl && tell $fh != 0) {
+ while (('0' x40) eq $rl && sysseek($fh, 0, 1) != 0) {
$offset -= 41;
- seek $fh, $offset, 2;
- $rl = readline $fh;
- defined $rl or return (undef, undef);
+ sysseek($fh, $offset, 2); # don't care for errors
+ sysread($fh, $rl, 41) == 41 or return (undef, undef);
chomp $rl;
}
- my $rev = tell $fh;
- croak $! if ($rev < 0);
+ if ($c && $c ne $rl) {
+ die "$db_path and ", $self->refname,
+ " inconsistent!:\n$c != $rl\n";
+ }
+ my $rev = sysseek($fh, 0, 1) or croak $!;
$rev = ($rev - 41) / 41;
close $fh or croak $!;
($self->{last_rev}, $self->{last_commit}) = ($rev, $c);
return ($rev, $c);
}
-sub parse_revision {
- my ($self, $base) = @_;
- my $head = $self->ra->get_latest_revnum;
- if (!defined $::_revision || $::_revision eq 'BASE:HEAD') {
- return ($base + 1, $head) if (defined $base);
- return (0, $head);
- }
- return ($1, $2) if ($::_revision =~ /^(\d+):(\d+)$/);
- return ($::_revision, $::_revision) if ($::_revision =~ /^\d+$/);
- if ($::_revision =~ /^BASE:(\d+)$/) {
- return ($base + 1, $1) if (defined $base);
- return (0, $head);
+sub get_fetch_range {
+ my ($self, $min, $max) = @_;
+ $max ||= $self->ra->get_latest_revnum;
+ $min ||= $self->rev_db_max;
+ (++$min, $max);
+}
+
+sub tmp_config {
+ my (@args) = @_;
+ my $old_def_config = "$ENV{GIT_DIR}/svn/config";
+ my $config = "$ENV{GIT_DIR}/svn/.metadata";
+ if (-e $old_def_config && ! -e $config) {
+ rename $old_def_config, $config or
+ die "Failed rename $old_def_config => $config: $!\n";
+ }
+ my $old_config = $ENV{GIT_CONFIG};
+ $ENV{GIT_CONFIG} = $config;
+ $@ = undef;
+ my @ret = eval {
+ unless (-f $config) {
+ mkfile($config);
+ open my $fh, '>', $config or
+ die "Can't open $config: $!\n";
+ print $fh "; This file is used internally by ",
+ "git-svn\n" or die
+ "Couldn't write to $config: $!\n";
+ print $fh "; You should not have to edit it\n" or
+ die "Couldn't write to $config: $!\n";
+ close $fh or die "Couldn't close $config: $!\n";
+ }
+ command('config', @args);
+ };
+ my $err = $@;
+ if (defined $old_config) {
+ $ENV{GIT_CONFIG} = $old_config;
+ } else {
+ delete $ENV{GIT_CONFIG};
}
- return ($1, $head) if ($::_revision =~ /^(\d+):HEAD$/);
- die "revision argument: $::_revision not understood by git-svn\n",
- "Try using the command-line svn client instead\n";
+ die $err if $err;
+ wantarray ? @ret : $ret[0];
}
sub tmp_index_do {
my ($self, $sub) = @_;
my $old_index = $ENV{GIT_INDEX_FILE};
$ENV{GIT_INDEX_FILE} = $self->{index};
- my @ret = &$sub;
- if ($old_index) {
+ $@ = undef;
+ my @ret = eval {
+ my ($dir, $base) = ($self->{index} =~ m#^(.*?)/?([^/]+)$#);
+ mkpath([$dir]) unless -d $dir;
+ &$sub;
+ };
+ my $err = $@;
+ if (defined $old_index) {
$ENV{GIT_INDEX_FILE} = $old_index;
} else {
delete $ENV{GIT_INDEX_FILE};
}
+ die $err if $err;
wantarray ? @ret : $ret[0];
}
my $x = command_oneline('write-tree');
my ($y) = (command(qw/cat-file commit/, $treeish) =~
/^tree ($::sha1)/mo);
- if ($y ne $x) {
- unlink $self->{index} or croak $!;
- command_noisy('read-tree', $treeish);
- }
+ return if $y eq $x;
+
+ warn "Index mismatch: $y != $x\nrereading $treeish\n";
+ unlink $self->{index} or die "unlink $self->{index}: $!\n";
+ command_noisy('read-tree', $treeish);
$x = command_oneline('write-tree');
if ($y ne $x) {
::fatal "trees ($treeish) $y != $x\n",
}
sub get_commit_parents {
- my ($self, $log_entry, @parents) = @_;
+ my ($self, $log_entry) = @_;
my (%seen, @ret, @tmp);
- # commit parents can be conditionally bound to a particular
- # svn revision via: "svn_revno=commit_sha1", filter them out here:
- foreach my $p (@parents) {
- next unless defined $p;
- if ($p =~ /^(\d+)=($::sha1_short)$/o) {
- push @tmp, $2 if $1 == $log_entry->{revision};
- } else {
- push @tmp, $p if $p =~ /^$::sha1_short$/o;
+ # legacy support for 'set-tree'; this is only used by set_tree_cb:
+ if (my $ip = $self->{inject_parents}) {
+ if (my $commit = delete $ip->{$log_entry->{revision}}) {
+ push @tmp, $commit;
}
}
if (my $cur = ::verify_ref($self->refname.'^0')) {
@ret;
}
-sub check_upgrade_needed {
+sub rewrite_root {
my ($self) = @_;
- if (!-r $self->{db_path}) {
- -d $self->{dir} or mkpath([$self->{dir}]);
- open my $fh, '>>', $self->{db_path} or croak $!;
- close $fh;
- }
- return unless ::verify_ref($self->{id}.'-HEAD^0');
- my $head = ::verify_ref($self->refname.'^0');
- if ($@ || !$head) {
- ::fatal("Please run: $0 rebuild --upgrade\n");
+ return $self->{-rewrite_root} if exists $self->{-rewrite_root};
+ my $k = "svn-remote.$self->{repo_id}.rewriteRoot";
+ my $rwr = eval { command_oneline(qw/config --get/, $k) };
+ if ($rwr) {
+ $rwr =~ s#/+$##;
+ if ($rwr !~ m#^[a-z\+]+://#) {
+ die "$rwr is not a valid URL (key: $k)\n";
+ }
}
+ $self->{-rewrite_root} = $rwr;
+}
+
+sub metadata_url {
+ my ($self) = @_;
+ ($self->rewrite_root || $self->{url}) .
+ (length $self->{path} ? '/' . $self->{path} : '');
+}
+
+sub full_url {
+ my ($self) = @_;
+ $self->{url} . (length $self->{path} ? '/' . $self->{path} : '');
}
sub do_git_commit {
- my ($self, $log_entry, @parents) = @_;
+ my ($self, $log_entry) = @_;
+ my $lr = $self->last_rev;
+ if (defined $lr && $lr >= $log_entry->{revision}) {
+ die "Last fetched revision of ", $self->refname,
+ " was r$lr, but we are about to fetch: ",
+ "r$log_entry->{revision}!\n";
+ }
if (my $c = $self->rev_db_get($log_entry->{revision})) {
croak "$log_entry->{revision} = $c already exists! ",
"Why are we refetching it?\n";
}
- my ($name, $email) = ::author_name_email($log_entry->{author},
- $self->ra);
- $ENV{GIT_AUTHOR_NAME} = $ENV{GIT_COMMITTER_NAME} = $name;
- $ENV{GIT_AUTHOR_EMAIL} = $ENV{GIT_COMMITTER_EMAIL} = $email;
+ $ENV{GIT_AUTHOR_NAME} = $ENV{GIT_COMMITTER_NAME} = $log_entry->{name};
+ $ENV{GIT_AUTHOR_EMAIL} = $ENV{GIT_COMMITTER_EMAIL} =
+ $log_entry->{email};
$ENV{GIT_AUTHOR_DATE} = $ENV{GIT_COMMITTER_DATE} = $log_entry->{date};
my $tree = $log_entry->{tree};
die "Tree is not a valid sha1: $tree\n" if $tree !~ /^$::sha1$/o;
my @exec = ('git-commit-tree', $tree);
- foreach ($self->get_commit_parents($log_entry, @parents)) {
+ foreach ($self->get_commit_parents($log_entry)) {
push @exec, '-p', $_;
}
defined(my $pid = open3(my $msg_fh, my $out_fh, '>&STDERR', @exec))
or croak $!;
print $msg_fh $log_entry->{log} or croak $!;
- print $msg_fh "\ngit-svn-id: ", $self->ra->{url}, '@',
- $log_entry->{revision}, ' ',
- $self->ra->uuid, "\n" or croak $!;
+ unless ($self->no_metadata) {
+ print $msg_fh "\ngit-svn-id: $log_entry->{metadata}\n"
+ or croak $!;
+ }
$msg_fh->flush == 0 or croak $!;
close $msg_fh or croak $!;
chomp(my $commit = do { local $/; <$out_fh> });
die "Failed to commit, invalid sha1: $commit\n";
}
- command_noisy('update-ref',$self->refname, $commit);
- $self->rev_db_set($log_entry->{revision}, $commit);
+ $self->rev_db_set($log_entry->{revision}, $commit, 1);
$self->{last_rev} = $log_entry->{revision};
$self->{last_commit} = $commit;
- print "r$log_entry->{revision} = $commit\n";
+ print "r$log_entry->{revision}";
+ if (defined $log_entry->{svm_revision}) {
+ print " (\@$log_entry->{svm_revision})";
+ $self->rev_db_set($log_entry->{svm_revision}, $commit,
+ 0, $self->svm_uuid);
+ }
+ print " = $commit ($self->{ref_id})\n";
+ if (defined $_repack && (--$_repack_nr == 0)) {
+ $_repack_nr = $_repack;
+ # repack doesn't use any arguments with spaces in them, does it?
+ print "Running git repack $_repack_flags ...\n";
+ command_noisy('repack', split(/\s+/, $_repack_flags));
+ print "Done repacking\n";
+ }
return $commit;
}
+sub match_paths {
+ my ($self, $paths, $r) = @_;
+ return 1 if $self->{path} eq '';
+ if (my $path = $paths->{"/$self->{path}"}) {
+ return ($path->{action} eq 'D') ? 0 : 1;
+ }
+ $self->{path_regex} ||= qr/^\/\Q$self->{path}\E\//;
+ if (grep /$self->{path_regex}/, keys %$paths) {
+ return 1;
+ }
+ my $c = '';
+ foreach (split m#/#, $self->{path}) {
+ $c .= "/$_";
+ next unless ($paths->{$c} &&
+ ($paths->{$c}->{action} =~ /^[AR]$/));
+ if ($self->ra->check_path($self->{path}, $r) ==
+ $SVN::Node::dir) {
+ return 1;
+ }
+ }
+ return 0;
+}
+
+sub find_parent_branch {
+ my ($self, $paths, $rev) = @_;
+ return undef unless $self->follow_parent;
+ 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]) });
+ $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 @a_path_components;
+ my $i;
+ while (@b_path_components) {
+ $i = $paths->{'/'.join('/', @b_path_components)};
+ last if $i && defined $i->{copyfrom_path};
+ unshift(@a_path_components, pop(@b_path_components));
+ }
+ return undef unless defined $i && defined $i->{copyfrom_path};
+ my $branch_from = $i->{copyfrom_path};
+ if (@a_path_components) {
+ print STDERR "branch_from: $branch_from => ";
+ $branch_from .= '/'.join('/', @a_path_components);
+ print STDERR $branch_from, "\n";
+ }
+ my $r = $i->{copyfrom_rev};
+ my $repos_root = $self->ra->{repos_root};
+ my $url = $self->ra->{url};
+ my $new_url = $repos_root . $branch_from;
+ print STDERR "Found possible branch point: ",
+ "$new_url => ", $self->full_url, ", $r\n";
+ $branch_from =~ s#^/##;
+ my $gs = Git::SVN->find_by_url($new_url, $repos_root, $branch_from);
+ unless ($gs) {
+ my $ref_id = $self->{ref_id};
+ $ref_id =~ s/\@\d+$//;
+ $ref_id .= "\@$r";
+ # just grow a tail if we're not unique enough :x
+ $ref_id .= '-' while find_ref($ref_id);
+ print STDERR "Initializing parent: $ref_id\n";
+ $gs = Git::SVN->init($new_url, '', $ref_id, $ref_id, 1);
+ }
+ my ($r0, $parent) = $gs->find_rev_before($r, 1);
+ if (!defined $r0 || !defined $parent) {
+ $gs->fetch(0, $r);
+ ($r0, $parent) = $gs->last_rev_commit;
+ }
+ if (defined $r0 && defined $parent) {
+ print STDERR "Found branch parent: ($self->{ref_id}) $parent\n";
+ my $ed;
+ if ($self->ra->can_do_switch) {
+ $self->assert_index_clean($parent);
+ print STDERR "Following parent with do_switch\n";
+ # do_switch works with svn/trunk >= r22312, but that
+ # is not included with SVN 1.4.3 (the latest version
+ # at the moment), so we can't rely on it
+ $self->{last_commit} = $parent;
+ $ed = SVN::Git::Fetcher->new($self);
+ $gs->ra->gs_do_switch($r0, $rev, $gs,
+ $self->full_url, $ed)
+ or die "SVN connection failed somewhere...\n";
+ } else {
+ print STDERR "Following parent with do_update\n";
+ $ed = SVN::Git::Fetcher->new($self);
+ $self->ra->gs_do_update($rev, $rev, $self, $ed)
+ or die "SVN connection failed somewhere...\n";
+ }
+ print STDERR "Successfully followed parent\n";
+ return $self->make_log_entry($rev, [$parent], $ed);
+ }
+ return undef;
+}
+
sub do_fetch {
- my ($self, $paths, $rev) = @_; #, $author, $date, $log) = @_;
- my $ed = SVN::Git::Fetcher->new($self);
+ my ($self, $paths, $rev) = @_;
+ my $ed;
my ($last_rev, @parents);
- if ($self->{last_commit}) {
+ if (my $lc = $self->last_commit) {
+ # we can have a branch that was deleted, then re-added
+ # under the same name but copied from another path, in
+ # which case we'll have multiple parents (we don't
+ # want to break the original ref, nor lose copypath info):
+ if (my $log_entry = $self->find_parent_branch($paths, $rev)) {
+ push @{$log_entry->{parents}}, $lc;
+ return $log_entry;
+ }
+ $ed = SVN::Git::Fetcher->new($self);
$last_rev = $self->{last_rev};
- $ed->{c} = $self->{last_commit};
- @parents = ($self->{last_commit});
+ $ed->{c} = $lc;
+ @parents = ($lc);
} else {
$last_rev = $rev;
+ if (my $log_entry = $self->find_parent_branch($paths, $rev)) {
+ return $log_entry;
+ }
+ $ed = SVN::Git::Fetcher->new($self);
}
- unless ($self->ra->do_update($last_rev, $rev, '', 1, $ed)) {
+ unless ($self->ra->gs_do_update($last_rev, $rev, $self, $ed)) {
die "SVN connection failed somewhere...\n";
}
$self->make_log_entry($rev, \@parents, $ed);
}
-sub write_untracked {
- my ($self, $rev, $fh, $untracked) = @_;
- my $h;
- print $fh "r$rev\n" or croak $!;
- $h = $untracked->{empty};
+sub get_untracked {
+ my ($self, $ed) = @_;
+ my @out;
+ my $h = $ed->{empty};
foreach (sort keys %$h) {
my $act = $h->{$_} ? '+empty_dir' : '-empty_dir';
- print $fh " $act: ", uri_encode($_), "\n" or croak $!;
+ push @out, " $act: " . uri_encode($_);
warn "W: $act: $_\n";
}
foreach my $t (qw/dir_prop file_prop/) {
- $h = $untracked->{$t} or next;
+ $h = $ed->{$t} or next;
foreach my $path (sort keys %$h) {
my $ppath = $path eq '' ? '.' : $path;
foreach my $prop (sort keys %{$h->{$path}}) {
- next if $SKIP{$prop};
+ next if $SKIP_PROP{$prop};
my $v = $h->{$path}->{$prop};
+ my $t_ppath_prop = "$t: " .
+ uri_encode($ppath) . ' ' .
+ uri_encode($prop);
if (defined $v) {
- print $fh " +$t: ",
- uri_encode($ppath), ' ',
- uri_encode($prop), ' ',
- uri_encode($v), "\n"
- or croak $!;
+ push @out, " +$t_ppath_prop " .
+ uri_encode($v);
} else {
- print $fh " -$t: ",
- uri_encode($ppath), ' ',
- uri_encode($prop), "\n"
- or croak $!;
+ push @out, " -$t_ppath_prop";
}
}
}
}
foreach my $t (qw/absent_file absent_directory/) {
- $h = $untracked->{$t} or next;
+ $h = $ed->{$t} or next;
foreach my $parent (sort keys %$h) {
foreach my $path (sort @{$h->{$parent}}) {
- print $fh " $t: ",
- uri_encode("$parent/$path"), "\n"
- or croak $!;
+ push @out, " $t: " .
+ uri_encode("$parent/$path");
warn "W: $t: $parent/$path ",
"Insufficient permissions?\n";
}
}
}
+ \@out;
+}
+
+sub parse_svn_date {
+ my $date = shift || return '+0000 1970-01-01 00:00:00';
+ my ($Y,$m,$d,$H,$M,$S) = ($date =~ /^(\d{4})\-(\d\d)\-(\d\d)T
+ (\d\d)\:(\d\d)\:(\d\d).\d+Z$/x) or
+ croak "Unable to parse date: $date\n";
+ "+0000 $Y-$m-$d $H:$M:$S";
+}
+
+sub check_author {
+ my ($author) = @_;
+ if (!defined $author || length $author == 0) {
+ $author = '(no author)';
+ }
+ if (defined $::_authors && ! defined $::users{$author}) {
+ die "Author: $author not defined in $::_authors file\n";
+ }
+ $author;
}
sub make_log_entry {
- my ($self, $rev, $parents, $untracked) = @_;
- my $rp = $self->ra->rev_proplist($rev);
- my %log_entry = ( parents => $parents || [], revision => $rev,
- revprops => $rp, log => '');
+ my ($self, $rev, $parents, $ed) = @_;
+ my $untracked = $self->get_untracked($ed);
+
open my $un, '>>', "$self->{dir}/unhandled.log" or croak $!;
- $self->write_untracked($rev, $un, $untracked);
- foreach (sort keys %$rp) {
- my $v = $rp->{$_};
- if (/^svn:(author|date|log)$/) {
- $log_entry{$1} = $v;
- } else {
- print $un " rev_prop: ", uri_encode($_), ' ',
- uri_encode($v), "\n";
+ print $un "r$rev\n" or croak $!;
+ print $un $_, "\n" foreach @$untracked;
+ my %log_entry = ( parents => $parents || [], revision => $rev,
+ log => '');
+
+ my $headrev;
+ my $logged = delete $self->{logged_rev_props};
+ if (!$logged || $self->{-want_revprops}) {
+ my $rp = $self->ra->rev_proplist($rev);
+ foreach (sort keys %$rp) {
+ my $v = $rp->{$_};
+ if (/^svn:(author|date|log)$/) {
+ $log_entry{$1} = $v;
+ } elsif ($_ eq 'svm:headrev') {
+ $headrev = $v;
+ } else {
+ print $un " rev_prop: ", uri_encode($_), ' ',
+ uri_encode($v), "\n";
+ }
}
+ } else {
+ map { $log_entry{$_} = $logged->{$_} } keys %$logged;
}
close $un or croak $!;
+
$log_entry{date} = parse_svn_date($log_entry{date});
- $log_entry{author} = check_author($log_entry{author});
$log_entry{log} .= "\n";
+ my $author = $log_entry{author} = check_author($log_entry{author});
+ my ($name, $email) = defined $::users{$author} ? @{$::users{$author}}
+ : ($author, undef);
+ if (defined $headrev && $self->use_svm_props) {
+ if ($self->rewrite_root) {
+ die "Can't have both 'useSvmProps' and 'rewriteRoot' ",
+ "options set!\n";
+ }
+ my ($uuid, $r) = $headrev =~ m{^([a-f\d\-]{30,}):(\d+)$};
+ # we don't want "SVM: initializing mirror for junk" ...
+ return undef if $r == 0;
+ my $svm = $self->svm;
+ if ($uuid ne $svm->{uuid}) {
+ die "UUID mismatch on SVM path:\n",
+ "expected: $svm->{uuid}\n",
+ " got: $uuid\n";
+ }
+ my $full_url = $self->full_url;
+ $full_url =~ s#^\Q$svm->{replace}\E(/|$)#$svm->{source}$1# or
+ die "Failed to replace '$svm->{replace}' with ",
+ "'$svm->{source}' in $full_url\n";
+ # throw away username for storing in records
+ remove_username($full_url);
+ $log_entry{metadata} = "$full_url\@$r $uuid";
+ $log_entry{svm_revision} = $r;
+ $email ||= "$author\@$uuid"
+ } elsif ($self->use_svnsync_props) {
+ my $full_url = $self->svnsync->{url};
+ $full_url .= "/$self->{path}" if length $self->{path};
+ my $uuid = $self->svnsync->{uuid};
+ $log_entry{metadata} = "$full_url\@$rev $uuid";
+ $email ||= "$author\@$uuid"
+ } else {
+ $log_entry{metadata} = $self->metadata_url. "\@$rev " .
+ $self->ra->get_uuid;
+ $email ||= "$author\@" . $self->ra->get_uuid;
+ }
+ $log_entry{name} = $name;
+ $log_entry{email} = $email;
\%log_entry;
}
sub fetch {
- my ($self, @parents) = @_;
+ my ($self, $min_rev, $max_rev, @parents) = @_;
my ($last_rev, $last_commit) = $self->last_rev_commit;
- my ($base, $head) = $self->parse_revision($last_rev);
- return if ($base > $head);
- if (defined $last_commit) {
- $self->assert_index_clean($last_commit);
- }
- my $inc = 1000;
- my ($min, $max) = ($base, $head < $base + $inc ? $head : $base + $inc);
- my $err_handler = $SVN::Error::handler;
- $SVN::Error::handler = \&skip_unknown_revs;
- while (1) {
- my @revs;
- $self->ra->get_log([''], $min, $max, 0, 1, 1, sub {
- my ($paths, $rev, $author, $date, $log) = @_;
- push @revs, $rev });
- foreach (@revs) {
- my $log_entry = $self->do_fetch(undef, $_);
- $self->do_git_commit($log_entry, @parents);
- }
- last if $max >= $head;
- $min = $max + 1;
- $max += $inc;
- $max = $head if ($max > $head);
- }
- $SVN::Error::handler = $err_handler;
+ my ($base, $head) = $self->get_fetch_range($min_rev, $max_rev);
+ $self->ra->gs_fetch_loop_common($base, $head, [$self]);
}
sub set_tree_cb {
my ($self, $log_entry, $tree, $rev, $date, $author) = @_;
- # TODO: enable and test optimized commits:
- if (0 && $rev == ($self->{last_rev} + 1)) {
- $log_entry->{revision} = $rev;
- $log_entry->{author} = $author;
- $self->do_git_commit($log_entry, "$rev=$tree");
- } else {
- $self->fetch("$rev=$tree");
- }
+ $self->{inject_parents} = { $rev => $tree };
+ $self->fetch(undef, undef);
}
sub set_tree {
my ($self, $tree) = (shift, shift);
- my $log_entry = get_commit_entry($tree);
+ my $log_entry = ::get_commit_entry($tree);
unless ($self->{last_rev}) {
fatal("Must have an existing revision to commit\n");
}
- my $pool = SVN::Pool->new;
- my $ed = SVN::Git::Editor->new({ r => $self->{last_rev},
- ra => $self->ra->dup,
- svn_path => $self->ra->{svn_path}
- },
- $self->ra->get_commit_editor(
- $log_entry->{log}, sub {
- $self->set_tree_cb($log_entry,
- $tree, @_);
- }),
- $pool);
- my $mods = $ed->apply_diff($self->{last_commit}, $tree);
- if (@$mods == 0) {
+ my %ed_opts = ( r => $self->{last_rev},
+ log => $log_entry->{log},
+ ra => $self->ra,
+ tree_a => $self->{last_commit},
+ tree_b => $tree,
+ editor_cb => sub {
+ $self->set_tree_cb($log_entry, $tree, @_) },
+ svn_path => $self->{path} );
+ if (!SVN::Git::Editor->new(\%ed_opts)->apply_diff) {
print "No changes\nr$self->{last_rev} = $tree\n";
}
- $pool->clear;
}
-sub skip_unknown_revs {
- my ($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 || $errno == 160013) {
+sub rebuild {
+ my ($self) = @_;
+ my $db_path = $self->db_path;
+ return if (-e $db_path && ! -z $db_path);
+ return unless ::verify_ref($self->refname.'^0');
+ if (-f $self->{db_root}) {
+ rename $self->{db_root}, $db_path or die
+ "rename $self->{db_root} => $db_path failed: $!\n";
+ my ($dir, $base) = ($db_path =~ m#^(.*?)/?([^/]+)$#);
+ symlink $base, $self->{db_root} or die
+ "symlink $base => $self->{db_root} failed: $!\n";
return;
}
- croak "Error from SVN, ($errno): ", $err->expanded_message,"\n";
+ print "Rebuilding $db_path ...\n";
+ my ($rev_list, $ctx) = command_output_pipe("rev-list", $self->refname);
+ my $latest;
+ my $full_url = $self->full_url;
+ remove_username($full_url);
+ my $svn_uuid;
+ while (<$rev_list>) {
+ chomp;
+ my $c = $_;
+ die "Non-SHA1: $c\n" unless $c =~ /^$::sha1$/o;
+ my ($url, $rev, $uuid) = ::cmt_metadata($c);
+ remove_username($url);
+
+ # ignore merges (from set-tree)
+ next if (!defined $rev || !$uuid);
+
+ # if we merged or otherwise started elsewhere, this is
+ # how we break out of it
+ if ((defined $svn_uuid && ($uuid ne $svn_uuid)) ||
+ ($full_url && $url && ($url ne $full_url))) {
+ next;
+ }
+ $latest ||= $rev;
+ $svn_uuid ||= $uuid;
+
+ $self->rev_db_set($rev, $c);
+ print "r$rev = $c\n";
+ }
+ command_close_pipe($rev_list, $ctx);
+ print "Done rebuilding $db_path\n";
}
# rev_db:
# to a revision: (41 * rev) is the byte offset.
# A record of 40 0s denotes an empty revision.
# And yes, it's still pretty fast (faster than Tie::File).
+# These files are disposable unless noMetadata or useSvmProps is set
-sub rev_db_set {
- my ($self, $rev, $commit) = @_;
- length $commit == 40 or croak "arg3 must be a full SHA1 hexsum\n";
- open my $fh, '+<', $self->{db_path} or croak $!;
+sub _rev_db_set {
+ my ($fh, $rev, $commit) = @_;
my $offset = $rev * 41;
# assume that append is the common case:
seek $fh, 0, 2 or croak $!;
my $pos = tell $fh;
if ($pos < $offset) {
- print $fh (('0' x 40),"\n") x (($offset - $pos) / 41)
- or croak $!;
+ for (1 .. (($offset - $pos) / 41)) {
+ print $fh (('0' x 40),"\n") or croak $!;
+ }
}
seek $fh, $offset, 0 or croak $!;
print $fh $commit,"\n" or croak $!;
+}
+
+sub mkfile {
+ my ($path) = @_;
+ unless (-e $path) {
+ my ($dir, $base) = ($path =~ m#^(.*?)/?([^/]+)$#);
+ mkpath([$dir]) unless -d $dir;
+ open my $fh, '>>', $path or die "Couldn't create $path: $!\n";
+ close $fh or die "Couldn't close (create) $path: $!\n";
+ }
+}
+
+sub rev_db_set {
+ my ($self, $rev, $commit, $update_ref, $uuid) = @_;
+ length $commit == 40 or die "arg3 must be a full SHA1 hexsum\n";
+ my $db = $self->db_path($uuid);
+ my $db_lock = "$db.lock";
+ my $sig;
+ if ($update_ref) {
+ $SIG{INT} = $SIG{HUP} = $SIG{TERM} = $SIG{ALRM} = $SIG{PIPE} =
+ $SIG{USR1} = $SIG{USR2} = sub { $sig = $_[0] };
+ }
+ mkfile($db);
+
+ $LOCKFILES{$db_lock} = 1;
+ my $sync;
+ # both of these options make our .rev_db file very, very important
+ # and we can't afford to lose it because rebuild() won't work
+ if ($self->use_svm_props || $self->no_metadata) {
+ $sync = 1;
+ copy($db, $db_lock) or die "rev_db_set(@_): ",
+ "Failed to copy: ",
+ "$db => $db_lock ($!)\n";
+ } else {
+ rename $db, $db_lock or die "rev_db_set(@_): ",
+ "Failed to rename: ",
+ "$db => $db_lock ($!)\n";
+ }
+ open my $fh, '+<', $db_lock or die "Couldn't open $db_lock: $!\n";
+ _rev_db_set($fh, $rev, $commit);
+ if ($sync) {
+ $fh->flush or die "Couldn't flush $db_lock: $!\n";
+ $fh->sync or die "Couldn't sync $db_lock: $!\n";
+ }
close $fh or croak $!;
+ if ($update_ref) {
+ $_head = $self;
+ command_noisy('update-ref', '-m', "r$rev",
+ $self->refname, $commit);
+ }
+ rename $db_lock, $db or die "rev_db_set(@_): ", "Failed to rename: ",
+ "$db_lock => $db ($!)\n";
+ delete $LOCKFILES{$db_lock};
+ if ($update_ref) {
+ $SIG{INT} = $SIG{HUP} = $SIG{TERM} = $SIG{ALRM} = $SIG{PIPE} =
+ $SIG{USR1} = $SIG{USR2} = 'DEFAULT';
+ kill $sig, $$ if defined $sig;
+ }
+}
+
+sub rev_db_max {
+ my ($self) = @_;
+ $self->rebuild;
+ my $db_path = $self->db_path;
+ my @stat = stat $db_path or return 0;
+ ($stat[7] % 41) == 0 or die "$db_path inconsistent size: $stat[7]\n";
+ my $max = $stat[7] / 41;
+ (($max > 0) ? $max - 1 : 0);
+}
+
+sub rev_db_get {
+ my ($self, $rev, $uuid) = @_;
+ my $ret;
+ my $offset = $rev * 41;
+ my $db_path = $self->db_path($uuid);
+ return undef unless -e $db_path;
+ open my $fh, '<', $db_path or croak $!;
+ if (sysseek($fh, $offset, 0) == $offset) {
+ my $read = sysread($fh, $ret, 40);
+ $ret = undef if ($read != 40 || $ret eq ('0'x40));
+ }
+ close $fh or croak $!;
+ $ret;
+}
+
+sub find_rev_before {
+ my ($self, $rev, $eq_ok) = @_;
+ --$rev unless $eq_ok;
+ while ($rev > 0) {
+ if (my $c = $self->rev_db_get($rev)) {
+ return ($rev, $c);
+ }
+ --$rev;
+ }
+ return (undef, undef);
+}
+
+sub _new {
+ my ($class, $repo_id, $ref_id, $path) = @_;
+ unless (defined $repo_id && length $repo_id) {
+ $repo_id = $Git::SVN::default_repo_id;
+ }
+ unless (defined $ref_id && length $ref_id) {
+ $_[2] = $ref_id = $Git::SVN::default_ref_id;
+ }
+ $_[1] = $repo_id = sanitize_remote_name($repo_id);
+ my $dir = "$ENV{GIT_DIR}/svn/$ref_id";
+ $_[3] = $path = '' unless (defined $path);
+ mkpath(["$ENV{GIT_DIR}/svn"]);
+ bless {
+ ref_id => $ref_id, dir => $dir, index => "$dir/index",
+ path => $path, config => "$ENV{GIT_DIR}/svn/config",
+ db_root => "$dir/.rev_db", repo_id => $repo_id }, $class;
}
-sub rev_db_get {
- my ($self, $rev) = @_;
- my $ret;
- my $offset = $rev * 41;
- open my $fh, '<', $self->{db_path} or croak $!;
- if (seek $fh, $offset, 0) {
- $ret = readline $fh;
- if (defined $ret) {
- chomp $ret;
- $ret = undef if ($ret =~ /^0{40}$/);
- }
- }
- close $fh or croak $!;
- $ret;
+sub db_path {
+ my ($self, $uuid) = @_;
+ $uuid ||= $self->ra_uuid;
+ "$self->{db_root}.$uuid";
}
-sub _new {
- my ($class, $id) = @_;
- $id ||= $Git::SVN::default;
- my $dir = "$ENV{GIT_DIR}/svn/$id";
- bless { id => $id, dir => $dir, index => "$dir/index",
- db_path => "$dir/.rev_db" }, $class;
+sub uri_encode {
+ my ($f) = @_;
+ $f =~ s#([^a-zA-Z0-9\*!\:_\./\-])#uc sprintf("%%%02x",ord($1))#eg;
+ $f
}
+sub remove_username {
+ $_[0] =~ s{^([^:]*://)[^@]+@}{$1};
+}
package Git::SVN::Prompt;
use strict;
package main;
-sub uri_encode {
- my ($f) = @_;
- $f =~ s#([^a-zA-Z0-9\*!\:_\./\-])#uc sprintf("%%%02x",ord($1))#eg;
- $f
-}
-
-sub uri_decode {
- my ($f) = @_;
- $f =~ tr/+/ /;
- $f =~ s/%([A-F0-9]{2})/chr hex($1)/ge;
- $f
-}
-
-sub libsvn_log_entry {
- my ($rev, $author, $date, $log, $parents, $untracked) = @_;
- my ($Y,$m,$d,$H,$M,$S) = ($date =~ /^(\d{4})\-(\d\d)\-(\d\d)T
- (\d\d)\:(\d\d)\:(\d\d).\d+Z$/x)
- or die "Unable to parse date: $date\n";
- if (defined $author && length $author > 0 &&
- defined $_authors && ! defined $users{$author}) {
- die "Author: $author not defined in $_authors file\n";
- }
- $log = '' if ($rev == 0 && !defined $log);
-
- open my $un, '>>', "$GIT_SVN_DIR/unhandled.log" or croak $!;
- my $h;
- print $un "r$rev\n" or croak $!;
- $h = $untracked->{empty};
- foreach (sort keys %$h) {
- my $act = $h->{$_} ? '+empty_dir' : '-empty_dir';
- print $un " $act: ", uri_encode($_), "\n" or croak $!;
- warn "W: $act: $_\n";
- }
- foreach my $t (qw/dir_prop file_prop/) {
- $h = $untracked->{$t} or next;
- foreach my $path (sort keys %$h) {
- my $ppath = $path eq '' ? '.' : $path;
- foreach my $prop (sort keys %{$h->{$path}}) {
- next if $SKIP{$prop};
- my $v = $h->{$path}->{$prop};
- if (defined $v) {
- print $un " +$t: ",
- uri_encode($ppath), ' ',
- uri_encode($prop), ' ',
- uri_encode($v), "\n"
- or croak $!;
- } else {
- print $un " -$t: ",
- uri_encode($ppath), ' ',
- uri_encode($prop), "\n"
- or croak $!;
- }
- }
- }
- }
- foreach my $t (qw/absent_file absent_directory/) {
- $h = $untracked->{$t} or next;
- foreach my $parent (sort keys %$h) {
- foreach my $path (sort @{$h->{$parent}}) {
- print $un " $t: ",
- uri_encode("$parent/$path"), "\n"
- or croak $!;
- warn "W: $t: $parent/$path ",
- "Insufficient permissions?\n";
- }
- }
- }
-
- # revprops (make this optional? it's an extra network trip...)
- my $rp = $SVN->rev_proplist($rev);
- foreach (sort keys %$rp) {
- next if /^svn:(?:author|date|log)$/;
- print $un " rev_prop: ", uri_encode($_), ' ',
- uri_encode($rp->{$_}), "\n";
- }
- close $un or croak $!;
-
- { revision => $rev, date => "+0000 $Y-$m-$d $H:$M:$S",
- author => $author, log => $log."\n", parents => $parents || [],
- revprops => $rp }
-}
-
-sub libsvn_fetch {
- my ($last_commit, $paths, $rev, $author, $date, $log) = @_;
- my $ed = SVN::Git::Fetcher->new({ c => $last_commit, q => $_q });
- my (undef, $last_rev, undef) = cmt_metadata($last_commit);
- unless ($SVN->gs_do_update($last_rev, $rev, '', 1, $ed)) {
- die "SVN connection failed somewhere...\n";
- }
- libsvn_log_entry($rev, $author, $date, $log, [$last_commit], $ed);
-}
-
-sub svn_grab_base_rev {
- my $c = eval { command_oneline([qw/rev-parse --verify/,
- "refs/remotes/$GIT_SVN^0"],
- { STDERR => 0 }) };
- if (defined $c && length $c) {
- my ($url, $rev, $uuid) = cmt_metadata($c);
- return ($rev, $c) if defined $rev;
- }
- if ($_no_metadata) {
- my $offset = -41; # from tail
- my $rl;
- open my $fh, '<', $REVDB or
- die "--no-metadata specified and $REVDB not readable\n";
- seek $fh, $offset, 2;
- $rl = readline $fh;
- defined $rl or return (undef, undef);
- chomp $rl;
- while ($c ne $rl && tell $fh != 0) {
- $offset -= 41;
- seek $fh, $offset, 2;
- $rl = readline $fh;
- defined $rl or return (undef, undef);
- chomp $rl;
- }
- my $rev = tell $fh;
- croak $! if ($rev < -1);
- $rev = ($rev - 41) / 41;
- close $fh or croak $!;
- return ($rev, $c);
- }
- return (undef, undef);
-}
-
-sub libsvn_parse_revision {
- my $base = shift;
- my $head = $SVN->get_latest_revnum();
- if (!defined $_revision || $_revision eq 'BASE:HEAD') {
- return ($base + 1, $head) if (defined $base);
- return (0, $head);
- }
- return ($1, $2) if ($_revision =~ /^(\d+):(\d+)$/);
- return ($_revision, $_revision) if ($_revision =~ /^\d+$/);
- if ($_revision =~ /^BASE:(\d+)$/) {
- return ($base + 1, $1) if (defined $base);
- return (0, $head);
- }
- return ($1, $head) if ($_revision =~ /^(\d+):HEAD$/);
- die "revision argument: $_revision not understood by git-svn\n",
- "Try using the command-line svn client instead\n";
-}
-
-sub libsvn_traverse_ignore {
- my ($fh, $path, $r) = @_;
- $path =~ s#^/+##g;
- my ($dirent, undef, $props) = $SVN->get_dir($path, $r);
- my $p = $path;
- $p =~ s#^\Q$SVN->{svn_path}\E/##;
- print $fh length $p ? "\n# $p\n" : "\n# /\n";
- if (my $s = $props->{'svn:ignore'}) {
- $s =~ s/[\r\n]+/\n/g;
- chomp $s;
- if (length $p == 0) {
- $s =~ s#\n#\n/$p#g;
- print $fh "/$s\n";
- } else {
- $s =~ s#\n#\n/$p/#g;
- print $fh "/$p/$s\n";
- }
- }
- foreach (sort keys %$dirent) {
- next if $dirent->{$_}->kind != $SVN::Node::dir;
- libsvn_traverse_ignore($fh, "$path/$_", $r);
- }
-}
-
-sub revisions_eq {
- my ($path, $r0, $r1) = @_;
- return 1 if $r0 == $r1;
- my $nr = 0;
- # should be OK to use Pool here (r1 - r0) should be small
- $SVN->get_log([$path], $r0, $r1, 0, 0, 1, sub {$nr++});
- return 0 if ($nr > 1);
- return 1;
-}
-
-sub libsvn_find_parent_branch {
- my ($paths, $rev, $author, $date, $log) = @_;
- my $svn_path = '/'.$SVN->{svn_path};
-
- # look for a parent from another branch:
- my $i = $paths->{$svn_path} or return;
- my $branch_from = $i->copyfrom_path or return;
- my $r = $i->copyfrom_rev;
- print STDERR "Found possible branch point: ",
- "$branch_from => $svn_path, $r\n";
- $branch_from =~ s#^/##;
- my $l_map = {};
- read_url_paths_all($l_map, '', "$GIT_DIR/svn");
- my $url = $SVN->{repos_root};
- defined $l_map->{$url} or return;
- my $id = $l_map->{$url}->{$branch_from};
- if (!defined $id && $_follow_parent) {
- print STDERR "Following parent: $branch_from\@$r\n";
- # auto create a new branch and follow it
- $id = basename($branch_from);
- $id .= '@'.$r if -r "$GIT_DIR/svn/$id";
- while (-r "$GIT_DIR/svn/$id") {
- # just grow a tail if we're not unique enough :x
- $id .= '-';
- }
- }
- return unless defined $id;
-
- my ($r0, $parent) = find_rev_before($r,$id,1);
- if ($_follow_parent && (!defined $r0 || !defined $parent)) {
- defined(my $pid = fork) or croak $!;
- if (!$pid) {
- $GIT_SVN = $ENV{GIT_SVN_ID} = $id;
- init_vars();
- $SVN_URL = "$url/$branch_from";
- $SVN = undef;
- setup_git_svn();
- # we can't assume SVN_URL exists at r+1:
- $_revision = "0:$r";
- fetch_lib();
- exit 0;
- }
- waitpid $pid, 0;
- croak $? if $?;
- ($r0, $parent) = find_rev_before($r,$id,1);
- }
- return unless (defined $r0 && defined $parent);
- if (revisions_eq($branch_from, $r0, $r)) {
- unlink $GIT_SVN_INDEX;
- print STDERR "Found branch parent: ($GIT_SVN) $parent\n";
- command_noisy('read-tree', $parent);
- unless ($SVN->can_do_switch) {
- return _libsvn_new_tree($paths, $rev, $author, $date,
- $log, [$parent]);
- }
- # do_switch works with svn/trunk >= r22312, but that is not
- # included with SVN 1.4.2 (the latest version at the moment),
- # so we can't rely on it.
- my $ra = Git::SVN::Ra->new("$url/$branch_from");
- my $ed = SVN::Git::Fetcher->new({c => $parent, q => $_q });
- $ra->gs_do_switch($r0, $rev, '', 1, $SVN->{url}, $ed) or
- die "SVN connection failed somewhere...\n";
- return libsvn_log_entry($rev, $author, $date, $log, [$parent]);
- }
- print STDERR "Nope, branch point not imported or unknown\n";
- return undef;
-}
-
-sub libsvn_new_tree {
- if (my $log_entry = libsvn_find_parent_branch(@_)) {
- return $log_entry;
- }
- my ($paths, $rev, $author, $date, $log) = @_; # $pool is last
- _libsvn_new_tree($paths, $rev, $author, $date, $log, []);
-}
-
-sub _libsvn_new_tree {
- my ($paths, $rev, $author, $date, $log, $parents) = @_;
- my $ed = SVN::Git::Fetcher->new({q => $_q});
- unless ($SVN->gs_do_update($rev, $rev, '', 1, $ed)) {
- die "SVN connection failed somewhere...\n";
- }
- libsvn_log_entry($rev, $author, $date, $log, $parents, $ed);
-}
-
-sub find_graft_path_commit {
- my ($tree_paths, $p1, $r1) = @_;
- foreach my $x (keys %$tree_paths) {
- next unless ($p1 =~ /^\Q$x\E/);
- my $i = $tree_paths->{$x};
- my ($r0, $parent) = find_rev_before($r1,$i,1);
- return $parent if (defined $r0 && $r0 == $r1);
- print STDERR "r$r1 of $i not imported\n";
- next;
- }
- return undef;
-}
-
-sub find_graft_path_parents {
- my ($grafts, $tree_paths, $c, $p0, $r0) = @_;
- foreach my $x (keys %$tree_paths) {
- next unless ($p0 =~ /^\Q$x\E/);
- my $i = $tree_paths->{$x};
- my ($r, $parent) = find_rev_before($r0, $i, 1);
- if (defined $r && defined $parent && revisions_eq($x,$r,$r0)) {
- my ($url_b, undef, $uuid_b) = cmt_metadata($c);
- my ($url_a, undef, $uuid_a) = cmt_metadata($parent);
- next if ($url_a && $url_b && $url_a eq $url_b &&
- $uuid_b eq $uuid_a);
- $grafts->{$c}->{$parent} = 1;
- }
- }
-}
-
-sub libsvn_graft_file_copies {
- my ($grafts, $tree_paths, $path, $paths, $rev) = @_;
- foreach (keys %$paths) {
- my $i = $paths->{$_};
- my ($m, $p0, $r0) = ($i->action, $i->copyfrom_path,
- $i->copyfrom_rev);
- next unless (defined $p0 && defined $r0);
-
- my $p1 = $_;
- $p1 =~ s#^/##;
- $p0 =~ s#^/##;
- my $c = find_graft_path_commit($tree_paths, $p1, $rev);
- next unless $c;
- find_graft_path_parents($grafts, $tree_paths, $c, $p0, $r0);
- }
-}
-
-sub set_index {
- my $old = $ENV{GIT_INDEX_FILE};
- $ENV{GIT_INDEX_FILE} = shift;
- return $old;
-}
-
-sub restore_index {
- my ($old) = @_;
- if (defined $old) {
- $ENV{GIT_INDEX_FILE} = $old;
- } else {
- delete $ENV{GIT_INDEX_FILE};
- }
-}
-
-sub libsvn_commit_cb {
- my ($rev, $date, $committer, $c, $log, $r_last, $cmt_last) = @_;
- if ($_optimize_commits && $rev == ($r_last + 1)) {
- my $log = libsvn_log_entry($rev,$committer,$date,$log);
- $log->{tree} = get_tree_from_treeish($c);
- my $cmt = git_commit($log, $cmt_last, $c);
- my @diff = command('diff-tree', $cmt, $c);
- if (@diff) {
- print STDERR "Trees differ: $cmt $c\n",
- join('',@diff),"\n";
- exit 1;
- }
- } else {
- fetch("$rev=$c");
- }
-}
-
-sub libsvn_skip_unknown_revs {
- my $err = shift;
- 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 || $errno == 160013) {
- return;
- }
- croak "Error from SVN, ($errno): ", $err->expanded_message,"\n";
-};
-
-# Tie::File seems to be prone to offset errors if revisions get sparse,
-# it's not that fast, either. Tie::File is also not in Perl 5.6. So
-# one of my favorite modules is out :< Next up would be one of the DBM
-# modules, but I'm not sure which is most portable... So I'll just
-# go with something that's plain-text, but still capable of
-# being randomly accessed. So here's my ultra-simple fixed-width
-# database. All records are 40 characters + "\n", so it's easy to seek
-# to a revision: (41 * rev) is the byte offset.
-# A record of 40 0s denotes an empty revision.
-# And yes, it's still pretty fast (faster than Tie::File).
-sub revdb_set {
- my ($file, $rev, $commit) = @_;
- length $commit == 40 or croak "arg3 must be a full SHA1 hexsum\n";
- open my $fh, '+<', $file or croak $!;
- my $offset = $rev * 41;
- # assume that append is the common case:
- seek $fh, 0, 2 or croak $!;
- my $pos = tell $fh;
- if ($pos < $offset) {
- print $fh (('0' x 40),"\n") x (($offset - $pos) / 41);
- }
- seek $fh, $offset, 0 or croak $!;
- print $fh $commit,"\n";
- close $fh or croak $!;
-}
-
-sub revdb_get {
- my ($file, $rev) = @_;
- my $ret;
- my $offset = $rev * 41;
- open my $fh, '<', $file or croak $!;
- seek $fh, $offset, 0;
- if (tell $fh == $offset) {
- $ret = readline $fh;
- if (defined $ret) {
- chomp $ret;
- $ret = undef if ($ret =~ /^0{40}$/);
- }
- }
- close $fh or croak $!;
- return $ret;
-}
-
{
my $kill_stupid_warnings = $SVN::Node::none.$SVN::Node::file.
$SVN::Node::dir.$SVN::Node::unknown.
use warnings;
use Carp qw/croak/;
use IO::File qw//;
+use Digest::MD5;
# file baton members: path, mode_a, mode_b, pool, fh, blob, base
sub new {
my ($class, $git_svn) = @_;
my $self = SVN::Delta::Editor->new;
bless $self, $class;
- $self->{c} = $git_svn->{c} if exists $git_svn->{c};
- $self->{q} = $git_svn->{q};
+ $self->{c} = $git_svn->{last_commit} if exists $git_svn->{last_commit};
$self->{empty} = {};
$self->{dir_prop} = {};
$self->{file_prop} = {};
$self->{absent_dir} = {};
$self->{absent_file} = {};
- ($self->{gui}, $self->{ctx}) = command_input_pipe(
- qw/update-index -z --index-info/);
- require Digest::MD5;
+ $self->{gii} = $git_svn->tmp_index_do(sub { Git::IndexInfo->new });
$self;
}
+sub set_path_strip {
+ my ($self, $path) = @_;
+ $self->{path_strip} = qr/^\Q$path\E(\/|$)/ if length $path;
+}
+
sub open_root {
{ path => '' };
}
{ path => $path };
}
+sub git_path {
+ my ($self, $path) = @_;
+ if ($self->{path_strip}) {
+ $path =~ s!$self->{path_strip}!! or
+ die "Failed to strip path '$path' ($self->{path_strip})\n";
+ }
+ $path;
+}
+
sub delete_entry {
my ($self, $path, $rev, $pb) = @_;
- my $gui = $self->{gui};
+
+ my $gpath = $self->git_path($path);
+ return undef if ($gpath eq '');
# remove entire directories.
- if (command('ls-tree', $self->{c}, '--', $path) =~ /^040000 tree/) {
+ if (command('ls-tree', $self->{c}, '--', $gpath) =~ /^040000 tree/) {
my ($ls, $ctx) = command_output_pipe(qw/ls-tree
-r --name-only -z/,
- $self->{c}, '--', $path);
+ $self->{c}, '--', $gpath);
local $/ = "\0";
while (<$ls>) {
- print $gui '0 ',0 x 40,"\t",$_ or croak $!;
- print "\tD\t$_\n" unless $self->{q};
+ chomp;
+ $self->{gii}->remove($_);
+ print "\tD\t$_\n" unless $::_q;
}
- print "\tD\t$path/\n" unless $self->{q};
+ print "\tD\t$gpath/\n" unless $::_q;
command_close_pipe($ls, $ctx);
$self->{empty}->{$path} = 0
} else {
- print $gui '0 ',0 x 40,"\t",$path,"\0" or croak $!;
- print "\tD\t$path\n" unless $self->{q};
+ $self->{gii}->remove($gpath);
+ print "\tD\t$gpath\n" unless $::_q;
}
undef;
}
sub open_file {
my ($self, $path, $pb, $rev) = @_;
- my ($mode, $blob) = (command('ls-tree', $self->{c}, '--',$path)
+ my $gpath = $self->git_path($path);
+ my ($mode, $blob) = (command('ls-tree', $self->{c}, '--', $gpath)
=~ /^(\d{6}) blob ([a-f\d]{40})\t/);
unless (defined $mode && defined $blob) {
die "$path was not found in commit $self->{c} (r$rev)\n";
sub close_file {
my ($self, $fb, $exp) = @_;
my $hash;
- my $path = $fb->{path};
+ my $path = $self->git_path($fb->{path});
if (my $fh = $fb->{fh}) {
seek($fh, 0, 0) or croak $!;
my $md5 = Digest::MD5->new;
$hash = $fb->{blob} or die "no blob information\n";
}
$fb->{pool}->clear;
- my $gui = $self->{gui};
- print $gui "$fb->{mode_b} $hash\t$path\0" or croak $!;
- print "\t$fb->{action}\t$path\n" if $fb->{action} && ! $self->{q};
+ $self->{gii}->update($fb->{mode_b}, $hash, $path) or croak $!;
+ print "\t$fb->{action}\t$path\n" if $fb->{action} && ! $::_q;
undef;
}
sub abort_edit {
my $self = shift;
- eval { command_close_pipe($self->{gui}, $self->{ctx}) };
+ $self->{nr} = $self->{gii}->{nr};
+ delete $self->{gii};
$self->SUPER::abort_edit(@_);
}
sub close_edit {
my $self = shift;
- command_close_pipe($self->{gui}, $self->{ctx});
$self->{git_commit_ok} = 1;
+ $self->{nr} = $self->{gii}->{nr};
+ delete $self->{gii};
$self->SUPER::close_edit(@_);
}
package SVN::Git::Editor;
-use vars qw/@ISA/;
+use vars qw/@ISA $_rmdir $_cp_similarity $_find_copies_harder $_rename_limit/;
use strict;
use warnings;
use Carp qw/croak/;
use IO::File;
+use Digest::MD5;
sub new {
- my $class = shift;
- my $git_svn = shift;
- my $self = SVN::Delta::Editor->new(@_);
+ my ($class, $opts) = @_;
+ foreach (qw/svn_path r ra tree_a tree_b log editor_cb/) {
+ die "$_ required!\n" unless (defined $opts->{$_});
+ }
+
+ my $pool = SVN::Pool->new;
+ my $mods = generate_diff($opts->{tree_a}, $opts->{tree_b});
+ my $types = check_diff_paths($opts->{ra}, $opts->{svn_path},
+ $opts->{r}, $mods);
+
+ # $opts->{ra} functions should not be used after this:
+ my @ce = $opts->{ra}->get_commit_editor($opts->{log},
+ $opts->{editor_cb}, $pool);
+ my $self = SVN::Delta::Editor->new(@ce, $pool);
bless $self, $class;
- foreach (qw/svn_path r ra/) {
- die "$_ required!\n" unless (defined $git_svn->{$_});
- $self->{$_} = $git_svn->{$_};
+ foreach (qw/svn_path r tree_a tree_b/) {
+ $self->{$_} = $opts->{$_};
}
- $self->{pool} = SVN::Pool->new;
+ $self->{url} = $opts->{ra}->{url};
+ $self->{mods} = $mods;
+ $self->{types} = $types;
+ $self->{pool} = $pool;
$self->{bat} = { '' => $self->open_root($self->{r}, $self->{pool}) };
$self->{rm} = { };
- require Digest::MD5;
+ $self->{path_prefix} = length $self->{svn_path} ?
+ "$self->{svn_path}/" : '';
return $self;
}
+sub generate_diff {
+ my ($tree_a, $tree_b) = @_;
+ my @diff_tree = qw(diff-tree -z -r);
+ if ($_cp_similarity) {
+ push @diff_tree, "-C$_cp_similarity";
+ } else {
+ push @diff_tree, '-C';
+ }
+ push @diff_tree, '--find-copies-harder' if $_find_copies_harder;
+ push @diff_tree, "-l$_rename_limit" if defined $_rename_limit;
+ push @diff_tree, $tree_a, $tree_b;
+ my ($diff_fh, $ctx) = command_output_pipe(@diff_tree);
+ 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 $_\n";
+ }
+ }
+ command_close_pipe($diff_fh, $ctx);
+ \@mods;
+}
+
+sub check_diff_paths {
+ my ($ra, $pfx, $rev, $mods) = @_;
+ my %types;
+ $pfx .= '/' if length $pfx;
+
+ sub type_diff_paths {
+ my ($ra, $types, $path, $rev) = @_;
+ my @p = split m#/+#, $path;
+ my $c = shift @p;
+ unless (defined $types->{$c}) {
+ $types->{$c} = $ra->check_path($c, $rev);
+ }
+ while (@p) {
+ $c .= '/' . shift @p;
+ next if defined $types->{$c};
+ $types->{$c} = $ra->check_path($c, $rev);
+ }
+ }
+
+ foreach my $m (@$mods) {
+ foreach my $f (qw/file_a file_b/) {
+ next unless defined $m->{$f};
+ my ($dir) = ($m->{$f} =~ m#^(.*?)/?(?:[^/]+)$#);
+ if (length $pfx.$dir && ! defined $types{$dir}) {
+ type_diff_paths($ra, \%types, $pfx.$dir, $rev);
+ }
+ }
+ }
+ \%types;
+}
+
sub split_path {
return ($_[0] =~ m#^(.*?)/?([^/]+)$#);
}
sub repo_path {
- (defined $_[1] && length $_[1]) ? $_[1] : ''
+ my ($self, $path) = @_;
+ $self->{path_prefix}.(defined $path ? $path : '');
}
sub url_path {
my ($self, $path) = @_;
- $self->{ra}->{url} . '/' . $self->repo_path($path);
+ $self->{url} . '/' . $self->repo_path($path);
}
sub rmdirs {
- my ($self, $tree_b) = @_;
+ my ($self) = @_;
my $rm = $self->{rm};
delete $rm->{''}; # we never delete the url we're tracking
return unless %$rm;
delete $rm->{''}; # we never delete the url we're tracking
return unless %$rm;
- my ($fh, $ctx) = command_output_pipe(
- qw/ls-tree --name-only -r -z/, $tree_b);
+ my ($fh, $ctx) = command_output_pipe(qw/ls-tree --name-only -r -z/,
+ $self->{tree_b});
local $/ = "\0";
while (<$fh>) {
chomp;
sub open_or_add_dir {
my ($self, $full_path, $baton) = @_;
- my $t = $self->{ra}->check_path($full_path, $self->{r});
+ my $t = $self->{types}->{$full_path};
+ if (!defined $t) {
+ die "$full_path not known in r$self->{r} or we have a bug!\n";
+ }
if ($t == $SVN::Node::none) {
return $self->add_directory($full_path, $baton,
undef, -1, $self->{pool});
sub ensure_path {
my ($self, $path) = @_;
my $bat = $self->{bat};
- $path = $self->repo_path($path);
- return $bat->{''} unless (length $path);
- my @p = split m#/+#, $path;
+ my $repo_path = $self->repo_path($path);
+ return $bat->{''} unless (length $repo_path);
+ my @p = split m#/+#, $repo_path;
my $c = shift @p;
$bat->{$c} ||= $self->open_or_add_dir($c, $bat->{''});
while (@p) {
sub abort_edit {
my ($self) = @_;
$self->SUPER::abort_edit($self->{pool});
+}
+
+sub DESTROY {
+ my $self = shift;
+ $self->SUPER::DESTROY(@_);
$self->{pool}->clear;
}
# this drives the editor
sub apply_diff {
- my ($self, $tree_a, $tree_b) = @_;
- my @diff_tree = qw(diff-tree -z -r);
- if ($::_cp_similarity) {
- push @diff_tree, "-C$::_cp_similarity";
- } else {
- push @diff_tree, '-C';
- }
- push @diff_tree, '--find-copies-harder' if $::_find_copies_harder;
- push @diff_tree, "-l$::_l" if defined $::_l;
- push @diff_tree, $tree_a, $tree_b;
- my ($diff_fh, $ctx) = command_output_pipe(@diff_tree);
- my $nl = $/;
- 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 $_\n";
- }
- }
- command_close_pipe($diff_fh, $ctx);
- $/ = $nl;
-
+ my ($self) = @_;
+ my $mods = $self->{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) {
+ foreach my $m (sort { $o{$a->{chg}} <=> $o{$b->{chg}} } @$mods) {
my $f = $m->{chg};
if (defined $o{$f}) {
$self->$f($m);
fatal("Invalid change type: $f\n");
}
}
- $self->rmdirs($tree_b) if $::_rmdir;
- if (@mods == 0) {
+ $self->rmdirs if $_rmdir;
+ if (@$mods == 0) {
$self->abort_edit;
} else {
$self->close_edit;
}
- \@mods;
+ return scalar @$mods;
}
package Git::SVN::Ra;
-use vars qw/@ISA $config_dir/;
+use vars qw/@ISA $config_dir $_log_window_size/;
use strict;
use warnings;
my ($can_do_switch);
+my $RA;
BEGIN {
# enforce temporary pool usage for some simple functions
my $e;
- foreach (qw/get_latest_revnum rev_proplist get_file
- check_path get_dir get_uuid get_repos_root/) {
+ foreach (qw/get_latest_revnum get_uuid get_repos_root/) {
$e .= "sub $_ {
my \$self = shift;
my \$pool = SVN::Pool->new;
\$pool->clear;
wantarray ? \@ret : \$ret[0]; }\n";
}
- eval $e;
+
+ # get_dir needs $pool held in cache for dirents to work,
+ # check_path is cacheable and rev_proplist is close enough
+ # for our purposes.
+ foreach (qw/check_path get_dir rev_proplist/) {
+ $e .= "my \%${_}_cache; my \$${_}_rev = 0; sub $_ {
+ my \$self = shift;
+ my \$r = pop;
+ my \$k = join(\"\\0\", \@_);
+ if (my \$x = \$${_}_cache{\$r}->{\$k}) {
+ return wantarray ? \@\$x : \$x->[0];
+ }
+ my \$pool = SVN::Pool->new;
+ my \@ret = \$self->SUPER::$_(\@_, \$r, \$pool);
+ if (\$r != \$${_}_rev) {
+ \%${_}_cache = ( pool => [] );
+ \$${_}_rev = \$r;
+ }
+ \$${_}_cache{\$r}->{\$k} = \\\@ret;
+ push \@{\$${_}_cache{pool}}, \$pool;
+ wantarray ? \@ret : \$ret[0]; }\n";
+ }
+ $e .= "\n1;";
+ eval $e or die $@;
}
sub new {
my ($class, $url) = @_;
+ $url =~ s!/+$!!;
+ return $RA if ($RA && $RA->{url} eq $url);
+ $RA->{pool}->clear if $RA;
+
SVN::_Core::svn_config_ensure($config_dir, undef);
my ($baton, $callbacks) = SVN::Core::auth_open_helper([
SVN::Client::get_simple_provider(),
auth_provider_callbacks => $callbacks);
$self->{svn_path} = $url;
$self->{repos_root} = $self->get_repos_root;
- $self->{svn_path} =~ s#^\Q$self->{repos_root}\E/*##;
- bless $self, $class;
+ $self->{svn_path} =~ s#^\Q$self->{repos_root}\E(/|$)##;
+ $RA = bless $self, $class;
}
sub DESTROY {
- my $self = shift;
- $self->{pool}->clear if $self->{pool};
- $self->SUPER::DESTROY(@_);
-}
-
-sub dup {
- my ($self) = @_;
- my $dup = SVN::Ra->new(pool => SVN::Pool->new,
- map { $_ => $self->{$_} } qw/config url
- auth auth_provider_callbacks repos_root svn_path/);
- bless $dup, ref $self;
+ # do not call the real DESTROY since we store ourselves in $RA
}
sub get_log {
my ($self, @args) = @_;
my $pool = SVN::Pool->new;
- $args[4]-- if $args[4] && ! $::_follow_parent;
splice(@args, 3, 1) if ($SVN::Core::VERSION le '1.2.0');
my $ret = $self->SUPER::get_log(@args, $pool);
$pool->clear;
$self->SUPER::get_commit_editor($log, $cb, @lock, $pool);
}
-sub uuid {
- my ($self) = @_;
- $self->{uuid} ||= $self->get_uuid;
-}
-
sub gs_do_update {
- my ($self, $rev_a, $rev_b, $path, $recurse, $editor) = @_;
+ my ($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;
- my $reporter = $self->do_update($rev_b, $path, $recurse,
- $editor, $pool);
+ $editor->set_path_strip($path);
+ my (@pc) = split m#/#, $path;
+ my $reporter = $self->do_update($rev_b, (@pc ? shift @pc : ''),
+ 1, $editor, $pool);
my @lock = $SVN::Core::VERSION ge '1.2.0' ? (undef) : ();
- my $new = ($rev_a == $rev_b);
- $reporter->set_path($path, $rev_a, $new, @lock, $pool);
+
+ # 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, $path, $recurse, $url_b, $editor) = @_;
+ my ($self, $rev_a, $rev_b, $gs, $url_b, $editor) = @_;
+ my $path = $gs->{path};
my $pool = SVN::Pool->new;
- my $reporter = $self->do_switch($rev_b, $path, $recurse,
- $url_b, $editor, $pool);
+
+ my $full_url = $self->{url};
+ my $old_url = $full_url;
+ $full_url .= "/$path" if length $path;
+ my ($ra, $reparented);
+ if ($old_url ne $full_url) {
+ if ($old_url !~ m#^svn(\+ssh)?://#) {
+ SVN::_Ra::svn_ra_reparent($self->{session}, $full_url,
+ $pool);
+ $self->{url} = $full_url;
+ $reparented = 1;
+ } else {
+ $ra = Git::SVN::Ra->new($full_url);
+ }
+ }
+ $ra ||= $self;
+ my $reporter = $ra->do_switch($rev_b, '', 1, $url_b, $editor, $pool);
my @lock = $SVN::Core::VERSION ge '1.2.0' ? (undef) : ();
- $reporter->set_path($path, $rev_a, 0, @lock, $pool);
+ $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;
$editor->{git_commit_ok};
}
+sub gs_fetch_loop_common {
+ my ($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 %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;
+ }
+ }
+ 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, $log) = @_;
+ [ dup_changed_paths($paths),
+ { author => $author, date => $date, log => $log } ];
+ }
+ $self->get_log([$longest_path], $min, $max, 0, 1, 1,
+ sub { $revs{$_[1]} = _cb(@_) });
+ if ($err && $max >= $head) {
+ print STDERR "Path '$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;
+ }
+ }
+ }
+ $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_db_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);
+ }
+ }
+ foreach my $g (@$globs) {
+ my $k = "svn-remote.$g->{remote}." .
+ "$g->{t}-maxRev";
+ Git::SVN::tmp_config($k, $r);
+ }
+ }
+ # 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 defined $gs->rev_db_get($max);
+ $gs->rev_db_set($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 > $head);
+ }
+}
+
+sub match_globs {
+ my ($self, $exists, $paths, $globs, $r) = @_;
+
+ sub get_dir_check {
+ my ($self, $exists, $g, $r) = @_;
+ my @x = eval { $self->get_dir($g->{path}->{left}, $r) };
+ return unless scalar @x == 3;
+ my $dirents = $x[0];
+ foreach my $de (keys %$dirents) {
+ next if $dirents->{$de}->kind != $SVN::Node::dir;
+ 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));
+ $exists->{$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 $exists->{$pathname};
+ $exists->{$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 {
+ $url .= "/$c" if length $c;
+ eval { (ref $self)->new($url)->get_latest_revnum };
+ } while ($@ && ($c = shift @components));
+ $url;
+}
+
sub can_do_switch {
my $self = shift;
unless (defined $can_do_switch) {
$can_do_switch;
}
+sub skip_unknown_revs {
+ my ($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 || $errno == 160013) {
+ warn "W: Ignoring error from SVN, path probably ",
+ "does not exist: ($errno): ",
+ $err->expanded_message,"\n";
+ return;
+ }
+ die "Error from SVN, ($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;
}
sub git_svn_log_cmd {
- my ($r_min, $r_max) = @_;
- my $gs = Git::SVN->_new;
+ my ($r_min, $r_max, @args) = @_;
+ my $head = 'HEAD';
+ foreach my $x (@args) {
+ last if $x eq '--';
+ next unless ::verify_ref("$x^0");
+ $head = $x;
+ last;
+ }
+
+ my $url = (::working_head_info($head))[0];
+ my $gs = Git::SVN->find_by_url($url) || Git::SVN->_new;
my @cmd = (qw/log --abbrev-commit --pretty=raw --default/,
$gs->refname);
push @cmd, '-r' unless $non_recursive;
exec $pager or ::fatal "Can't run pager: $! ($pager)\n";
}
+sub tz_to_s_offset {
+ my ($tz) = @_;
+ $tz =~ s/(\d\d)$//;
+ return ($1 * 60) + ($tz * 3600);
+}
+
sub get_author_info {
my ($dest, $author, $t, $tz) = @_;
$author =~ s/(?:^\s*|\s*$)//g;
$dest->{a_raw} = $author;
my $au;
- if ($_authors) {
+ if ($::_authors) {
$au = $rusers{$author} || undef;
}
if (!$au) {
$dest->{a} = $au;
# Date::Parse isn't in the standard Perl distro :(
if ($tz =~ s/^\+//) {
- $t += ::tz_to_s_offset($tz);
+ $t += tz_to_s_offset($tz);
} elsif ($tz =~ s/^\-//) {
- $t -= ::tz_to_s_offset($tz);
+ $t -= tz_to_s_offset($tz);
}
$dest->{t_utc} = $t;
}
print "\n";
}
- foreach my $x (qw/raw diff/) {
+ foreach my $x (qw/raw stat diff/) {
if ($c->{$x}) {
print "\n";
print $_ foreach @{$c->{$x}}
}
config_pager();
- @args = (git_svn_log_cmd($r_min, $r_max), @args);
+ @args = (git_svn_log_cmd($r_min, $r_max, @args), @args);
my $log = command_output_pipe(@args);
run_pager();
- my (@k, $c, $d);
+ my (@k, $c, $d, $stat);
my $esc_color = qr/(?:\033\[(?:(?:\d+;)*\d*)?m)*/;
while (<$log>) {
if (/^${esc_color}commit ($::sha1_short)/o) {
push @{$c->{diff}}, $_;
} elsif ($d) {
push @{$c->{diff}}, $_;
+ } elsif (/^\ .+\ \|\s*\d+\ $esc_color[\+\-]*
+ $esc_color*[\+\-]*$esc_color$/x) {
+ $stat = 1;
+ push @{$c->{stat}}, $_;
+ } elsif ($stat && /^ \d+ files changed, \d+ insertions/) {
+ push @{$c->{stat}}, $_;
+ $stat = undef;
} elsif (/^${esc_color} (git-svn-id:.+)$/o) {
($c->{url}, $c->{r}, undef) = ::extract_metadata($1);
} elsif (s/^${esc_color} //o) {
print '-' x72,"\n" unless $incremental || $oneline;
}
+package Git::SVN::Migration;
+# these version numbers do NOT correspond to actual version numbers
+# of git nor git-svn. They are just relative.
+#
+# v0 layout: .git/$id/info/url, refs/heads/$id-HEAD
+#
+# v1 layout: .git/$id/info/url, refs/remotes/$id
+#
+# v2 layout: .git/svn/$id/info/url, refs/remotes/$id
+#
+# v3 layout: .git/svn/$id, refs/remotes/$id
+# - info/url may remain for backwards compatibility
+# - this is what we migrate up to this layout automatically,
+# - this will be used by git svn init on single branches
+# v3.1 layout (auto migrated):
+# - .rev_db => .rev_db.$UUID, .rev_db will remain as a symlink
+# for backwards compatibility
+#
+# v4 layout: .git/svn/$repo_id/$id, refs/remotes/$repo_id/$id
+# - this is only created for newly multi-init-ed
+# repositories. Similar in spirit to the
+# --use-separate-remotes option in git-clone (now default)
+# - we do not automatically migrate to this (following
+# the example set by core git)
+use strict;
+use warnings;
+use Carp qw/croak/;
+use File::Path qw/mkpath/;
+use File::Basename qw/dirname basename/;
+use vars qw/$_minimize/;
+
+sub migrate_from_v0 {
+ my $git_dir = $ENV{GIT_DIR};
+ return undef unless -d $git_dir;
+ my ($fh, $ctx) = command_output_pipe(qw/rev-parse --symbolic --all/);
+ my $migrated = 0;
+ while (<$fh>) {
+ chomp;
+ my ($id, $orig_ref) = ($_, $_);
+ next unless $id =~ s#^refs/heads/(.+)-HEAD$#$1#;
+ next unless -f "$git_dir/$id/info/url";
+ my $new_ref = "refs/remotes/$id";
+ if (::verify_ref("$new_ref^0")) {
+ print STDERR "W: $orig_ref is probably an old ",
+ "branch used by an ancient version of ",
+ "git-svn.\n",
+ "However, $new_ref also exists.\n",
+ "We will not be able ",
+ "to use this branch until this ",
+ "ambiguity is resolved.\n";
+ next;
+ }
+ print STDERR "Migrating from v0 layout...\n" if !$migrated;
+ print STDERR "Renaming ref: $orig_ref => $new_ref\n";
+ command_noisy('update-ref', $new_ref, $orig_ref);
+ command_noisy('update-ref', '-d', $orig_ref, $orig_ref);
+ $migrated++;
+ }
+ command_close_pipe($fh, $ctx);
+ print STDERR "Done migrating from v0 layout...\n" if $migrated;
+ $migrated;
+}
+
+sub migrate_from_v1 {
+ my $git_dir = $ENV{GIT_DIR};
+ my $migrated = 0;
+ return $migrated unless -d $git_dir;
+ my $svn_dir = "$git_dir/svn";
+
+ # just in case somebody used 'svn' as their $id at some point...
+ return $migrated if -d $svn_dir && ! -f "$svn_dir/info/url";
+
+ print STDERR "Migrating from a git-svn v1 layout...\n";
+ mkpath([$svn_dir]);
+ print STDERR "Data from a previous version of git-svn exists, but\n\t",
+ "$svn_dir\n\t(required for this version ",
+ "($::VERSION) of git-svn) does not. exist\n";
+ my ($fh, $ctx) = command_output_pipe(qw/rev-parse --symbolic --all/);
+ while (<$fh>) {
+ my $x = $_;
+ next unless $x =~ s#^refs/remotes/##;
+ chomp $x;
+ next unless -f "$git_dir/$x/info/url";
+ my $u = eval { ::file_to_s("$git_dir/$x/info/url") };
+ next unless $u;
+ my $dn = dirname("$git_dir/svn/$x");
+ mkpath([$dn]) unless -d $dn;
+ if ($x eq 'svn') { # they used 'svn' as GIT_SVN_ID:
+ mkpath(["$git_dir/svn/svn"]);
+ print STDERR " - $git_dir/$x/info => ",
+ "$git_dir/svn/$x/info\n";
+ rename "$git_dir/$x/info", "$git_dir/svn/$x/info" or
+ croak "$!: $x";
+ # don't worry too much about these, they probably
+ # don't exist with repos this old (save for index,
+ # and we can easily regenerate that)
+ foreach my $f (qw/unhandled.log index .rev_db/) {
+ rename "$git_dir/$x/$f", "$git_dir/svn/$x/$f";
+ }
+ } else {
+ print STDERR " - $git_dir/$x => $git_dir/svn/$x\n";
+ rename "$git_dir/$x", "$git_dir/svn/$x" or
+ croak "$!: $x";
+ }
+ $migrated++;
+ }
+ command_close_pipe($fh, $ctx);
+ print STDERR "Done migrating from a git-svn v1 layout\n";
+ $migrated;
+}
+
+sub read_old_urls {
+ my ($l_map, $pfx, $path) = @_;
+ my @dir;
+ foreach (<$path/*>) {
+ if (-r "$_/info/url") {
+ $pfx .= '/' if $pfx && $pfx !~ m!/$!;
+ my $ref_id = $pfx . basename $_;
+ my $url = ::file_to_s("$_/info/url");
+ $l_map->{$ref_id} = $url;
+ } elsif (-d $_) {
+ push @dir, $_;
+ }
+ }
+ foreach (@dir) {
+ my $x = $_;
+ $x =~ s!^\Q$ENV{GIT_DIR}\E/svn/!!o;
+ read_old_urls($l_map, $x, $_);
+ }
+}
+
+sub migrate_from_v2 {
+ my @cfg = command(qw/config -l/);
+ return if grep /^svn-remote\..+\.url=/, @cfg;
+ my %l_map;
+ read_old_urls(\%l_map, '', "$ENV{GIT_DIR}/svn");
+ my $migrated = 0;
+
+ foreach my $ref_id (sort keys %l_map) {
+ eval { Git::SVN->init($l_map{$ref_id}, '', undef, $ref_id) };
+ if ($@) {
+ Git::SVN->init($l_map{$ref_id}, '', $ref_id, $ref_id);
+ }
+ $migrated++;
+ }
+ $migrated;
+}
+
+sub minimize_connections {
+ my $r = Git::SVN::read_all_remotes();
+ my $new_urls = {};
+ my $root_repos = {};
+ foreach my $repo_id (keys %$r) {
+ my $url = $r->{$repo_id}->{url} or next;
+ my $fetch = $r->{$repo_id}->{fetch} or next;
+ my $ra = Git::SVN::Ra->new($url);
+
+ # skip existing cases where we already connect to the root
+ if (($ra->{url} eq $ra->{repos_root}) ||
+ (Git::SVN::sanitize_remote_name($ra->{repos_root}) eq
+ $repo_id)) {
+ $root_repos->{$ra->{url}} = $repo_id;
+ next;
+ }
+
+ my $root_ra = Git::SVN::Ra->new($ra->{repos_root});
+ my $root_path = $ra->{url};
+ $root_path =~ s#^\Q$ra->{repos_root}\E(/|$)##;
+ foreach my $path (keys %$fetch) {
+ my $ref_id = $fetch->{$path};
+ my $gs = Git::SVN->new($ref_id, $repo_id, $path);
+
+ # make sure we can read when connecting to
+ # a higher level of a repository
+ my ($last_rev, undef) = $gs->last_rev_commit;
+ if (!defined $last_rev) {
+ $last_rev = eval {
+ $root_ra->get_latest_revnum;
+ };
+ next if $@;
+ }
+ my $new = $root_path;
+ $new .= length $path ? "/$path" : '';
+ eval {
+ $root_ra->get_log([$new], $last_rev, $last_rev,
+ 0, 0, 1, sub { });
+ };
+ next if $@;
+ $new_urls->{$ra->{repos_root}}->{$new} =
+ { ref_id => $ref_id,
+ old_repo_id => $repo_id,
+ old_path => $path };
+ }
+ }
+
+ my @emptied;
+ foreach my $url (keys %$new_urls) {
+ # see if we can re-use an existing [svn-remote "repo_id"]
+ # instead of creating a(n ugly) new section:
+ my $repo_id = $root_repos->{$url} ||
+ Git::SVN::sanitize_remote_name($url);
+
+ my $fetch = $new_urls->{$url};
+ foreach my $path (keys %$fetch) {
+ my $x = $fetch->{$path};
+ Git::SVN->init($url, $path, $repo_id, $x->{ref_id});
+ my $pfx = "svn-remote.$x->{old_repo_id}";
+
+ my $old_fetch = quotemeta("$x->{old_path}:".
+ "refs/remotes/$x->{ref_id}");
+ command_noisy(qw/config --unset/,
+ "$pfx.fetch", '^'. $old_fetch . '$');
+ delete $r->{$x->{old_repo_id}}->
+ {fetch}->{$x->{old_path}};
+ if (!keys %{$r->{$x->{old_repo_id}}->{fetch}}) {
+ command_noisy(qw/config --unset/,
+ "$pfx.url");
+ push @emptied, $x->{old_repo_id}
+ }
+ }
+ }
+ if (@emptied) {
+ my $file = $ENV{GIT_CONFIG} || $ENV{GIT_CONFIG_LOCAL} ||
+ "$ENV{GIT_DIR}/config";
+ print STDERR <<EOF;
+The following [svn-remote] sections in your config file ($file) are empty
+and can be safely removed:
+EOF
+ print STDERR "[svn-remote \"$_\"]\n" foreach @emptied;
+ }
+}
+
+sub migration_check {
+ migrate_from_v0();
+ migrate_from_v1();
+ migrate_from_v2();
+ minimize_connections() if $_minimize;
+}
+
+package Git::IndexInfo;
+use strict;
+use warnings;
+use Git qw/command_input_pipe command_close_pipe/;
+
+sub new {
+ my ($class) = @_;
+ my ($gui, $ctx) = command_input_pipe(qw/update-index -z --index-info/);
+ bless { gui => $gui, ctx => $ctx, nr => 0}, $class;
+}
+
+sub remove {
+ my ($self, $path) = @_;
+ if (print { $self->{gui} } '0 ', 0 x 40, "\t", $path, "\0") {
+ return ++$self->{nr};
+ }
+ undef;
+}
+
+sub update {
+ my ($self, $mode, $hash, $path) = @_;
+ if (print { $self->{gui} } $mode, ' ', $hash, "\t", $path, "\0") {
+ return ++$self->{nr};
+ }
+ undef;
+}
+
+sub DESTROY {
+ my ($self) = @_;
+ command_close_pipe($self->{gui}, $self->{ctx});
+}
+
+package Git::SVN::GlobSpec;
+use strict;
+use warnings;
+
+sub new {
+ my ($class, $glob) = @_;
+ my $re = $glob;
+ $re =~ s!/+$!!g; # no need for trailing slashes
+ my $nr = ($re =~ s!^(.*)\*(.*)$!\(\[^/\]+\)!g);
+ my ($left, $right) = ($1, $2);
+ if ($nr > 1) {
+ die "Only one '*' wildcard expansion ",
+ "is supported (got $nr): '$glob'\n";
+ } elsif ($nr == 0) {
+ die "One '*' is needed for glob: '$glob'\n";
+ }
+ $re = quotemeta($left) . $re . quotemeta($right);
+ if (length $left && !($left =~ s!/+$!!g)) {
+ die "Missing trailing '/' on left side of: '$glob' ($left)\n";
+ }
+ if (length $right && !($right =~ s!^/+!!g)) {
+ die "Missing leading '/' on right side of: '$glob' ($right)\n";
+ }
+ my $left_re = qr/^\/\Q$left\E(\/|$)/;
+ bless { left => $left, right => $right, left_regex => $left_re,
+ regex => qr/$re/, glob => $glob }, $class;
+}
+
+sub full_path {
+ my ($self, $path) = @_;
+ return (length $self->{left} ? "$self->{left}/" : '') .
+ $path . (length $self->{right} ? "/$self->{right}" : '');
+}
+
__END__
Data structures:
+
+$remotes = { # returned by read_all_remotes()
+ 'svn' => {
+ # svn-remote.svn.url=https://svn.musicpd.org
+ url => 'https://svn.musicpd.org',
+ # svn-remote.svn.fetch=mpd/trunk:trunk
+ fetch => {
+ 'mpd/trunk' => 'trunk',
+ },
+ # svn-remote.svn.tags=mpd/tags/*:tags/*
+ tags => {
+ path => {
+ left => 'mpd/tags',
+ right => '',
+ regex => qr!mpd/tags/([^/]+)$!,
+ glob => 'tags/*',
+ },
+ ref => {
+ left => 'tags',
+ right => '',
+ regex => qr!tags/([^/]+)$!,
+ glob => 'tags/*',
+ },
+ }
+ }
+};
+
$log_entry hashref as returned by libsvn_log_entry()
{
log => 'whitespace-formatted log entry
author => 'committer name'
};
+
+# this is generated by generate_diff();
@mods = array of diff-index line hashes, each element represents one line
of diff-index output