diff options
Diffstat (limited to 'git-svn.perl')
| -rwxr-xr-x | git-svn.perl | 8796 |
1 files changed, 5874 insertions, 2922 deletions
diff --git a/git-svn.perl b/git-svn.perl index d0bd0bdeb..b67fef0bf 100755 --- a/git-svn.perl +++ b/git-svn.perl @@ -1,189 +1,352 @@ #!/usr/bin/env perl # Copyright (C) 2006, Eric Wong <normalperson@yhbt.net> # License: GPL v2 or later +use 5.008; use warnings; use strict; use vars qw/ $AUTHOR $VERSION - $SVN_URL $SVN_INFO $SVN_WC $SVN_UUID - $GIT_SVN_INDEX $GIT_SVN - $GIT_DIR $GIT_SVN_DIR $REVDB/; + $sha1 $sha1_short $_revision $_repository + $_q $_authors $_authors_prog %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; +# From which subdir have we been invoked? +my $cmd_dir_prefix = eval { + command_oneline([qw/rev-parse --show-prefix/], STDERR => 0) +} || ''; -my $LC_ALL = $ENV{LC_ALL}; -my $TZ = $ENV{TZ}; -# make sure the svn binary gives consistent output between locales and TZs: +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; +$Git::SVN::_minimize_url = 'unset'; + +if (! exists $ENV{SVN_SSH} && exists $ENV{GIT_SSH}) { + $ENV{SVN_SSH} = $ENV{GIT_SSH}; +} + +if (exists $ENV{SVN_SSH} && $^O eq 'msys') { + $ENV{SVN_SSH} =~ s/\\/\\\\/g; + $ENV{SVN_SSH} =~ s/(.*)/"$1"/; +} + +$Git::SVN::Log::TZ = $ENV{TZ}; $ENV{TZ} = 'UTC'; -$ENV{LC_ALL} = 'C'; $| = 1; # unbuffer STDOUT -sub fatal (@) { print STDERR $@; exit 1 } -# If SVN:: library support is added, please make the dependencies -# optional and preserve the capability to use the command-line client. -# use eval { require SVN::... } to make it lazy load -# We don't use any modules not in the standard Perl distribution: +sub fatal (@) { print STDERR "@_\n"; exit 1 } +sub _req_svn { + require SVN::Core; # use()-ing this causes segfaults for me... *shrug* + require SVN::Ra; + require SVN::Delta; + if ($SVN::Core::VERSION lt '1.1.0') { + fatal "Need SVN::Core 1.1.0 or better (got $SVN::Core::VERSION)"; + } +} +my $can_compress = eval { require Compress::Zlib; 1}; +push @Git::SVN::Ra::ISA, 'SVN::Ra'; +push @SVN::Git::Editor::ISA, 'SVN::Delta::Editor'; +push @SVN::Git::Fetcher::ISA, 'SVN::Delta::Editor'; use Carp qw/croak/; +use Digest::MD5; use IO::File qw//; use File::Basename qw/dirname basename/; use File::Path qw/mkpath/; -use Getopt::Long qw/:config gnu_getopt no_ignore_case auto_abbrev pass_through/; -use File::Spec qw//; -use File::Copy qw/copy/; -use POSIX qw/strftime/; +use File::Spec; +use File::Find; +use Getopt::Long qw/:config gnu_getopt no_ignore_case auto_abbrev/; use IPC::Open3; -use Memoize; -memoize('revisions_eq'); -memoize('cmt_metadata'); -memoize('get_commit_time'); - -my ($SVN, $_use_lib); - -sub nag_lib { - print STDERR <<EOF; -! Please consider installing the SVN Perl libraries (version 1.1.0 or -! newer). You will generally get better performance and fewer bugs, -! especially if you: -! 1) have a case-insensitive filesystem -! 2) replace symlinks with files (and vice-versa) in commits - -EOF -} - -$_use_lib = 1 unless $ENV{GIT_SVN_NO_LIB}; -libsvn_load(); -nag_lib() unless $_use_lib; - -my $_optimize_commits = 1 unless $ENV{GIT_SVN_NO_OPTIMIZE_COMMITS}; -my $sha1 = qr/[a-f\d]{40}/; -my $sha1_short = qr/[a-f\d]{4,40}/; -my $_esc_color = qr/(?:\033\[(?:(?:\d+;)*\d*)?m)*/; -my ($_revision,$_stdin,$_no_ignore_ext,$_no_stop_copy,$_help,$_rmdir,$_edit, - $_find_copies_harder, $_l, $_cp_similarity, $_cp_remote, - $_repack, $_repack_nr, $_repack_flags, $_q, - $_message, $_file, $_follow_parent, $_no_metadata, - $_template, $_shared, $_no_default_regex, $_no_graft_copy, - $_limit, $_verbose, $_incremental, $_oneline, $_l_fmt, $_show_commit, - $_version, $_upgrade, $_authors, $_branch_all_refs, @_opt_m, - $_merge, $_strategy, $_dry_run, $_ignore_nodate, $_non_recursive, - $_username, $_config_dir, $_no_auth_cache, $_xfer_delta, - $_pager, $_color); -my (@_branch_from, %tree_map, %users, %rusers, %equiv); -my ($_svn_co_url_revs, $_svn_pg_peg_revs); -my @repo_path_split_cache; - -my %fc_opts = ( 'no-ignore-externals' => \$_no_ignore_ext, - 'branch|b=s' => \@_branch_from, - 'follow-parent|follow' => \$_follow_parent, - 'branch-all-refs|B' => \$_branch_all_refs, +use Git; +use Memoize; # core since 5.8.0, Jul 2002 + +BEGIN { + # import functions from Git into our packages, en masse + no strict 'refs'; + foreach (qw/command command_oneline command_noisy command_output_pipe + command_input_pipe command_close_pipe + command_bidi_pipe command_close_bidi_pipe/) { + for my $package ( qw(SVN::Git::Editor SVN::Git::Fetcher + Git::SVN::Migration Git::SVN::Log Git::SVN), + __PACKAGE__) { + *{"${package}::$_"} = \&{"Git::$_"}; + } + } + Memoize::memoize 'Git::config'; + Memoize::memoize 'Git::config_bool'; +} + +my ($SVN); + +$sha1 = qr/[a-f\d]{40}/; +$sha1_short = qr/[a-f\d]{4,40}/; +my ($_stdin, $_help, $_edit, + $_message, $_file, $_branch_dest, + $_template, $_shared, + $_version, $_fetch_all, $_no_rebase, $_fetch_parent, + $_merge, $_strategy, $_dry_run, $_local, + $_prefix, $_no_checkout, $_url, $_verbose, + $_git_format, $_commit_url, $_tag, $_merge_info, $_interactive); +$Git::SVN::_follow_parent = 1; +$SVN::Git::Fetcher::_placeholder_filename = ".gitignore"; +$_q ||= 0; +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, + 'ignore-paths=s' => \$SVN::Git::Fetcher::_ignore_regex, + 'ignore-refs=s' => \$Git::SVN::Ra::_ignore_refs_regex ); +my %fc_opts = ( 'follow-parent|follow!' => \$Git::SVN::_follow_parent, 'authors-file|A=s' => \$_authors, - 'repack:i' => \$_repack, - 'no-metadata' => \$_no_metadata, - 'quiet|q' => \$_q, - 'username=s' => \$_username, - 'config-dir=s' => \$_config_dir, - 'no-auth-cache' => \$_no_auth_cache, - 'ignore-nodate' => \$_ignore_nodate, - 'repack-flags|repack-args|repack-opts=s' => \$_repack_flags); - -my ($_trunk, $_tags, $_branches); -my %multi_opts = ( 'trunk|T=s' => \$_trunk, - 'tags|t=s' => \$_tags, - 'branches|b=s' => \$_branches ); -my %init_opts = ( 'template=s' => \$_template, 'shared' => \$_shared ); + 'authors-prog=s' => \$_authors_prog, + 'repack:i' => \$Git::SVN::_repack, + 'noMetadata' => \$Git::SVN::_no_metadata, + 'useSvmProps' => \$Git::SVN::_use_svm_props, + 'useSvnsyncProps' => \$Git::SVN::_use_svnsync_props, + 'log-window-size=i' => \$Git::SVN::Ra::_log_window_size, + 'no-checkout' => \$_no_checkout, + 'quiet|q+' => \$_q, + 'repack-flags|repack-args|repack-opts=s' => + \$Git::SVN::_repack_flags, + 'use-log-author' => \$Git::SVN::_use_log_author, + 'add-author-from' => \$Git::SVN::_add_author_from, + 'localtime' => \$Git::SVN::_localtime, + %remote_opts ); + +my ($_trunk, @_tags, @_branches, $_stdlayout); +my %icv; +my %init_opts = ( 'template=s' => \$_template, 'shared:s' => \$_shared, + 'trunk|T=s' => \$_trunk, 'tags|t=s@' => \@_tags, + 'branches|b=s@' => \@_branches, 'prefix=s' => \$_prefix, + 'stdlayout|s' => \$_stdlayout, + 'minimize-url|m!' => \$Git::SVN::_minimize_url, + 'no-metadata' => sub { $icv{noMetadata} = 1 }, + 'use-svm-props' => sub { $icv{useSvmProps} = 1 }, + 'use-svnsync-props' => sub { $icv{useSvnsyncProps} = 1 }, + 'rewrite-root=s' => sub { $icv{rewriteRoot} = $_[1] }, + 'rewrite-uuid=s' => sub { $icv{rewriteUUID} = $_[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 => [ \&fetch, "Download new revisions from SVN", - { 'revision|r=s' => \$_revision, %fc_opts } ], - init => [ \&init, "Initialize a repo for tracking" . + fetch => [ \&cmd_fetch, "Download new revisions from SVN", + { 'revision|r=s' => \$_revision, + 'fetch-all|all' => \$_fetch_all, + 'parent|p' => \$_fetch_parent, + %fc_opts } ], + clone => [ \&cmd_clone, "Initialize and fetch revisions", + { 'revision|r=s' => \$_revision, + 'preserve-empty-dirs' => + \$SVN::Git::Fetcher::_preserve_empty_dirs, + 'placeholder-filename=s' => + \$SVN::Git::Fetcher::_placeholder_filename, + %fc_opts, %init_opts } ], + init => [ \&cmd_init, "Initialize a repo for tracking" . " (requires URL argument)", \%init_opts ], - commit => [ \&commit, "Commit git revisions to SVN", - { 'stdin|' => \$_stdin, %cmt_opts, %fc_opts, } ], - 'show-ignore' => [ \&show_ignore, "Show svn:ignore listings", - { 'revision|r=i' => \$_revision } ], - rebuild => [ \&rebuild, "Rebuild git-svn metadata (after git clone)", - { 'no-ignore-externals' => \$_no_ignore_ext, - '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' => [ \&multi_init, - 'Initialize multiple trees (like git-svnimport)', - { %multi_opts, %init_opts, - 'revision|r=i' => \$_revision, - 'username=s' => \$_username, - 'config-dir=s' => \$_config_dir, - 'no-auth-cache' => \$_no_auth_cache, + '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, + 'commit-url=s' => \$_commit_url, + 'revision|r=i' => \$_revision, + 'no-rebase' => \$_no_rebase, + 'mergeinfo=s' => \$_merge_info, + 'interactive|i' => \$_interactive, + %cmt_opts, %fc_opts } ], + branch => [ \&cmd_branch, + 'Create a branch in the SVN repository', + { 'message|m=s' => \$_message, + 'destination|d=s' => \$_branch_dest, + 'dry-run|n' => \$_dry_run, + 'tag|t' => \$_tag, + 'username=s' => \$Git::SVN::Prompt::_username, + 'commit-url=s' => \$_commit_url } ], + tag => [ sub { $_tag = 1; cmd_branch(@_) }, + 'Create a tag in the SVN repository', + { 'message|m=s' => \$_message, + 'destination|d=s' => \$_branch_dest, + 'dry-run|n' => \$_dry_run, + 'username=s' => \$Git::SVN::Prompt::_username, + 'commit-url=s' => \$_commit_url } ], + 'set-tree' => [ \&cmd_set_tree, + "Set an SVN repository to a git tree-ish", + { 'stdin' => \$_stdin, %cmt_opts, %fc_opts, } ], + 'create-ignore' => [ \&cmd_create_ignore, + 'Create a .gitignore per svn:ignore', + { 'revision|r=i' => \$_revision + } ], + 'mkdirs' => [ \&cmd_mkdirs , + "recreate empty directories after a checkout", + { 'revision|r=i' => \$_revision } ], + 'propget' => [ \&cmd_propget, + 'Print the value of a property on a file or directory', + { 'revision|r=i' => \$_revision } ], + 'proplist' => [ \&cmd_proplist, + 'List all properties of a file or directory', + { 'revision|r=i' => \$_revision } ], + 'show-ignore' => [ \&cmd_show_ignore, "Show svn:ignore listings", + { 'revision|r=i' => \$_revision } ], - 'multi-fetch' => [ \&multi_fetch, - 'Fetch multiple trees (like git-svnimport)', - \%fc_opts ], - 'log' => [ \&show_log, 'Show commit logs', - { 'limit=i' => \$_limit, + 'show-externals' => [ \&cmd_show_externals, "Show svn:externals listings", + { 'revision|r=i' => \$_revision + } ], + '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, - 'verbose|v' => \$_verbose, - 'incremental' => \$_incremental, - 'oneline' => \$_oneline, - 'show-commit' => \$_show_commit, - 'non-recursive' => \$_non_recursive, + 'verbose|v' => \$Git::SVN::Log::verbose, + 'incremental' => \$Git::SVN::Log::incremental, + 'oneline' => \$Git::SVN::Log::oneline, + 'show-commit' => \$Git::SVN::Log::show_commit, + 'non-recursive' => \$Git::SVN::Log::non_recursive, 'authors-file|A=s' => \$_authors, - 'color' => \$_color, - 'pager=s' => \$_pager, + 'color' => \$Git::SVN::Log::color, + 'pager=s' => \$Git::SVN::Log::pager } ], - 'commit-diff' => [ \&commit_diff, 'Commit a diff between two trees', - { 'message|m=s' => \$_message, - 'file|F=s' => \$_file, - 'revision|r=s' => \$_revision, - %cmt_opts } ], - dcommit => [ \&dcommit, 'Commit several diffs to merge with upstream', + 'find-rev' => [ \&cmd_find_rev, + "Translate between SVN revision numbers and tree-ish", + {} ], + '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, 'dry-run|n' => \$_dry_run, + %fc_opts } ], + 'commit-diff' => [ \&cmd_commit_diff, + 'Commit a diff between two trees', + { 'message|m=s' => \$_message, + 'file|F=s' => \$_file, + 'revision|r=s' => \$_revision, %cmt_opts } ], + 'info' => [ \&cmd_info, + "Show info about the latest SVN revision + on the current branch", + { 'url' => \$_url, } ], + 'blame' => [ \&Git::SVN::Log::cmd_blame, + "Show what revision and author last modified each line of a file", + { 'git-format' => \$_git_format } ], + 'reset' => [ \&cmd_reset, + "Undo fetches back to the specified SVN revision", + { 'revision|r=s' => \$_revision, + 'parent|p' => \$_fetch_parent } ], + 'gc' => [ \&cmd_gc, + "Compress unhandled.log files in .git/svn and remove " . + "index files in .git/svn", + {} ], ); +use Term::ReadLine; +package FakeTerm; +sub new { + my ($class, $reason) = @_; + return bless \$reason, shift; +} +sub readline { + my $self = shift; + die "Cannot use readline on FakeTerm: $$self"; +} +package main; + +my $term = eval { + $ENV{"GIT_SVN_NOTTY"} + ? new Term::ReadLine 'git-svn', \*STDIN, \*STDOUT + : new Term::ReadLine 'git-svn'; +}; +if ($@) { + $term = new FakeTerm "$@: going non-interactive"; +} + my $cmd; for (my $i = 0; $i < @ARGV; $i++) { if (defined $cmd{$ARGV[$i]}) { $cmd = $ARGV[$i]; splice @ARGV, $i, 1; last; + } elsif ($ARGV[$i] eq 'help') { + $cmd = $ARGV[$i+1]; + usage(0); } }; +# make sure we're always running at the top-level working directory +unless ($cmd && $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}; + my $cdup = undef; + git_cmd_try { + $cdup = command_oneline(qw/rev-parse --show-cdup/); + $git_dir = '.' unless ($cdup); + chomp $cdup if ($cdup); + $cdup = "." unless ($cdup && length $cdup); + } "Already at toplevel, but $git_dir not found\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; + } + $_repository = Git->repository(Repository => $ENV{GIT_DIR}); +} + 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); -exit 1 if (!$rv && $cmd ne 'log'); +read_git_config(\%opts); +if ($cmd && ($cmd eq 'log' || $cmd eq 'blame')) { + Getopt::Long::Configure('pass_through'); +} +my $rv = GetOptions(%opts, '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 && $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; -svn_compat_check() unless $_use_lib; -migration_check() unless $cmd =~ /^(?:init|rebuild|multi-init|commit-diff)$/; -$cmd{$cmd}->[0]->(@ARGV); +if (defined $_authors_prog) { + $_authors_prog = "'" . File::Spec->rel2abs($_authors_prog) . "'"; +} + +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 ###################### @@ -192,14 +355,17 @@ sub usage { my $fd = $exit ? \*STDERR : \*STDOUT; print $fd <<""; git-svn - bidirectional operations between a single Subversion tree and git -Usage: $0 <command> [options] [arguments]\n +Usage: git svn <command> [options] [arguments]\n print $fd "Available commands:\n" unless $cmd; 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]}) { + foreach (sort keys %{$cmd{$_}->[2]}) { + # mixed-case options are for .git/config only + next if /[A-Z]/ && /^[a-z]+$/i; # prints out arguments as they should be passed: my $x = s#[:=]s$## ? '<arg>' : s#[:=]i$## ? '<num>' : ''; print $fd ' ' x 21, join(', ', map { length $_ > 1 ? @@ -217,256 +383,152 @@ information. } sub version { - print "git-svn version $VERSION\n"; + ::_req_svn(); + print "git-svn version $VERSION (svn $SVN::Core::VERSION)\n"; exit 0; } -sub rebuild { - if (quiet_run(qw/git-rev-parse --verify/,"refs/remotes/$GIT_SVN^0")) { - copy_remote_ref(); - } - $SVN_URL = shift or undef; - my $newest_rev = 0; - if ($_upgrade) { - sys('git-update-ref',"refs/remotes/$GIT_SVN","$GIT_SVN-HEAD"); - } else { - check_upgrade_needed(); - } +sub ask { + my ($prompt, %arg) = @_; + my $valid_re = $arg{valid_re}; + my $default = $arg{default}; + my $resp; + my $i = 0; - my $pid = open(my $rev_list,'-|'); - defined $pid or croak $!; - if ($pid == 0) { - exec("git-rev-list","refs/remotes/$GIT_SVN") or croak $!; + if ( !( defined($term->IN) + && defined( fileno($term->IN) ) + && defined( $term->OUT ) + && defined( fileno($term->OUT) ) ) ){ + return defined($default) ? $default : undef; } - my $latest; - while (<$rev_list>) { - chomp; - my $c = $_; - croak "Non-SHA1: $c\n" unless $c =~ /^$sha1$/o; - my @commit = grep(/^git-svn-id: /,`git-cat-file commit $c`); - next if (!@commit); # skip merges - my ($url, $rev, $uuid) = extract_metadata($commit[$#commit]); - if (!defined $rev || !$uuid) { - croak "Unable to extract revision or UUID from ", - "$c, $commit[$#commit]\n"; - } - - # if we merged or otherwise started elsewhere, this is - # how we break out of it - next if (defined $SVN_UUID && ($uuid ne $SVN_UUID)); - next if (defined $SVN_URL && defined $url && ($url ne $SVN_URL)); - unless (defined $latest) { - if (!$SVN_URL && !$url) { - croak "SVN repository location required: $url\n"; - } - $SVN_URL ||= $url; - $SVN_UUID ||= $uuid; - setup_git_svn(); - $latest = $rev; + while ($i++ < 10) { + $resp = $term->readline($prompt); + if (!defined $resp) { # EOF + print "\n"; + return defined $default ? $default : undef; } - revdb_set($REVDB, $rev, $c); - print "r$rev = $c\n"; - $newest_rev = $rev if ($rev > $newest_rev); - } - close $rev_list or croak $?; - - goto out if $_use_lib; - if (!chdir $SVN_WC) { - svn_cmd_checkout($SVN_URL, $latest, $SVN_WC); - chdir $SVN_WC or croak $!; - } - - $pid = fork; - defined $pid or croak $!; - if ($pid == 0) { - my @svn_up = qw(svn up); - push @svn_up, '--ignore-externals' unless $_no_ignore_ext; - sys(@svn_up,"-r$newest_rev"); - $ENV{GIT_INDEX_FILE} = $GIT_SVN_INDEX; - index_changes(); - exec('git-write-tree') or croak $!; - } - waitpid $pid, 0; - croak $? if $?; -out: - if ($_upgrade) { - print STDERR <<""; -Keeping deprecated refs/head/$GIT_SVN-HEAD for now. Please remove it -when you have upgraded your tools and habits to use refs/remotes/$GIT_SVN - - } -} - -sub init { - my $url = shift or die "SVN repository location required " . - "as a command-line argument\n"; - $url =~ s!/+$!!; # strip trailing slash - - if (my $repo_path = shift) { - unless (-d $repo_path) { - mkpath([$repo_path]); + if ($resp eq '' and defined $default) { + return $default; + } + if (!defined $valid_re or $resp =~ /$valid_re/) { + return $resp; } - $GIT_DIR = $ENV{GIT_DIR} = $repo_path . "/.git"; - init_vars(); - } - - $SVN_URL = $url; - unless (-d $GIT_DIR) { - my @init_db = ('git-init-db'); - push @init_db, "--template=$_template" if defined $_template; - push @init_db, "--shared" if defined $_shared; - sys(@init_db); - } - setup_git_svn(); -} - -sub fetch { - check_upgrade_needed(); - $SVN_URL ||= file_to_s("$GIT_SVN_DIR/info/url"); - my $ret = $_use_lib ? fetch_lib(@_) : fetch_cmd(@_); - if ($ret->{commit} && quiet_run(qw(git-rev-parse --verify - refs/heads/master^0))) { - sys(qw(git-update-ref refs/heads/master),$ret->{commit}); } - return $ret; + return undef; } -sub fetch_cmd { - my (@parents) = @_; - my @log_args = -d $SVN_WC ? ($SVN_WC) : ($SVN_URL); - unless ($_revision) { - $_revision = -d $SVN_WC ? 'BASE:HEAD' : '0:HEAD'; - } - push @log_args, "-r$_revision"; - push @log_args, '--stop-on-copy' unless $_no_stop_copy; - - my $svn_log = svn_log_raw(@log_args); - - my $base = next_log_entry($svn_log) or croak "No base revision!\n"; - # don't need last_revision from grab_base_rev() because - # user could've specified a different revision to skip (they - # didn't want to import certain revisions into git for whatever - # reason, so trust $base->{revision} instead. - my (undef, $last_commit) = svn_grab_base_rev(); - unless (-d $SVN_WC) { - svn_cmd_checkout($SVN_URL,$base->{revision},$SVN_WC); - chdir $SVN_WC or croak $!; - read_uuid(); - $last_commit = git_commit($base, @parents); - assert_tree($last_commit); - } else { - chdir $SVN_WC or croak $!; - read_uuid(); - # looks like a user manually cp'd and svn switch'ed - unless ($last_commit) { - sys(qw/svn revert -R ./); - assert_svn_wc_clean($base->{revision}); - $last_commit = git_commit($base, @parents); - assert_tree($last_commit); - } - } - my @svn_up = qw(svn up); - push @svn_up, '--ignore-externals' unless $_no_ignore_ext; - my $last = $base; - while (my $log_msg = next_log_entry($svn_log)) { - if ($last->{revision} >= $log_msg->{revision}) { - croak "Out of order: last >= current: ", - "$last->{revision} >= $log_msg->{revision}\n"; - } - # Revert is needed for cases like: - # https://svn.musicpd.org/Jamming/trunk (r166:167), but - # I can't seem to reproduce something like that on a test... - sys(qw/svn revert -R ./); - assert_svn_wc_clean($last->{revision}); - sys(@svn_up,"-r$log_msg->{revision}"); - $last_commit = git_commit($log_msg, $last_commit, @parents); - $last = $log_msg; - } - close $svn_log->{fh}; - $last->{commit} = $last_commit; - return $last; -} - -sub fetch_lib { - my (@parents) = @_; - $SVN_URL ||= file_to_s("$GIT_SVN_DIR/info/url"); - $SVN ||= libsvn_connect($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 } - } - my $index = set_index($GIT_SVN_INDEX); - - # 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); - read_uuid(); - if (defined $last_commit) { - unless (-e $GIT_SVN_INDEX) { - sys(qw/git-read-tree/, $last_commit); - } - chomp (my $x = `git-write-tree`); - my ($y) = (`git-cat-file commit $last_commit` - =~ /^tree ($sha1)/m); - if ($y ne $x) { - unlink $GIT_SVN_INDEX or croak $!; - sys(qw/git-read-tree/, $last_commit); - } - chomp ($x = `git-write-tree`); - if ($y ne $x) { - print STDERR "trees ($last_commit) $y != $x\n", - "Something is seriously wrong...\n"; +sub do_git_init_db { + unless (-d $ENV{GIT_DIR}) { + my @init_db = ('init'); + push @init_db, "--template=$_template" if defined $_template; + if (defined $_shared) { + if ($_shared =~ /[a-z]/) { + push @init_db, "--shared=$_shared"; + } else { + push @init_db, "--shared"; + } } - } - 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. - libsvn_get_log(libsvn_dup_ra($SVN), [''], - $min, $max, 0, 1, 1, - sub { - my $log_msg; - if ($last_commit) { - $log_msg = libsvn_fetch( - $last_commit, @_); - $last_commit = git_commit( - $log_msg, - $last_commit, - @parents); - } else { - $log_msg = libsvn_new_tree(@_); - $last_commit = git_commit( - $log_msg, @parents); - } - }); - exit 0; + command_noisy(@init_db); + $_repository = Git->repository(Repository => ".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; + } + my $ignore_paths_regex = \$SVN::Git::Fetcher::_ignore_regex; + command_noisy('config', "$pfx.ignore-paths", $$ignore_paths_regex) + if defined $$ignore_paths_regex; + my $ignore_refs_regex = \$Git::SVN::Ra::_ignore_refs_regex; + command_noisy('config', "$pfx.ignore-refs", $$ignore_refs_regex) + if defined $$ignore_refs_regex; + + if (defined $SVN::Git::Fetcher::_preserve_empty_dirs) { + my $fname = \$SVN::Git::Fetcher::_placeholder_filename; + command_noisy('config', "$pfx.preserve-empty-dirs", 'true'); + command_noisy('config', "$pfx.placeholder-filename", $$fname); + } +} + +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'; + $_repository = Git->repository(Repository => $ENV{GIT_DIR}); +} + +sub cmd_clone { + my ($url, $path) = @_; + if (!defined $path && + (defined $_trunk || @_branches || @_tags || + defined $_stdlayout) && + $url !~ m#^[a-z\+]+://#) { + $path = $url; + } + $path = basename($url) if !defined $path || !length $path; + my $authors_absolute = $_authors ? File::Spec->rel2abs($_authors) : ""; + cmd_init($url, $path); + command_oneline('config', 'svn.authorsfile', $authors_absolute) + if $_authors; + Git::SVN::fetch_all($Git::SVN::default_repo_id); +} + +sub cmd_init { + if (defined $_stdlayout) { + $_trunk = 'trunk' if (!defined $_trunk); + @_tags = 'tags' if (! @_tags); + @_branches = 'branches' if (! @_branches); + } + if (defined $_trunk || @_branches || @_tags) { + return cmd_multi_init(@_); + } + my $url = shift or die "SVN repository location required ", + "as a command-line argument\n"; + $url = canonicalize_url($url); + init_subdir(@_); + do_git_init_db(); + + if ($Git::SVN::_minimize_url eq 'unset') { + $Git::SVN::_minimize_url = 0; + } + + Git::SVN->init($url); +} + +sub cmd_fetch { + if (grep /^\d+=./, @_) { + die "'<rev>=<commit>' fetch arguments are ", + "no longer supported.\n"; + } + my ($remote) = @_; + if (@_ > 1) { + die "Usage: $0 fetch [--all] [--parent] [svn-remote]\n"; + } + $Git::SVN::no_reuse_existing = undef; + if ($_fetch_parent) { + my ($url, $rev, $uuid, $gs) = working_head_info('HEAD'); + unless ($gs) { + die "Unable to determine upstream SVN information from ", + "working tree history\n"; } - 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); + # just fetch, don't checkout. + $_no_checkout = 'true'; + $_fetch_all ? $gs->fetch_all : $gs->fetch; + } elsif ($_fetch_all) { + cmd_multi_fetch(); + } else { + $remote ||= $Git::SVN::default_repo_id; + Git::SVN::fetch_all($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 = (); @@ -478,1586 +540,2478 @@ sub commit { } my @revs; foreach my $c (@commits) { - chomp(my @tmp = safe_qx('git-rev-parse',$c)); + my @tmp = command('rev-parse',$c); if (scalar @tmp == 1) { push @revs, $tmp[0]; } elsif (scalar @tmp > 1) { - push @revs, reverse (safe_qx('git-rev-list',@tmp)); + push @revs, reverse(command('rev-list',@tmp)); } else { - die "Failed to rev-parse $c\n"; + fatal "Failed to rev-parse $c"; } } - chomp @revs; - $_use_lib ? commit_lib(@revs) : commit_cmd(@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}"; + } + $gs->set_tree($_) foreach @revs; print "Done committing ",scalar @revs," revisions to SVN\n"; + unlink $gs->{index}; +} + +sub split_merge_info_range { + my ($range) = @_; + if ($range =~ /(\d+)-(\d+)/) { + return (int($1), int($2)); + } else { + return (int($range), int($range)); + } } -sub commit_cmd { - my (@revs) = @_; +sub combine_ranges { + my ($in) = @_; - chdir $SVN_WC or croak "Unable to chdir $SVN_WC: $!\n"; - my $info = svn_info('.'); - my $fetched = fetch(); - if ($info->{Revision} != $fetched->{revision}) { - print STDERR "There are new revisions that were fetched ", - "and need to be merged (or acknowledged) ", - "before committing.\n"; - exit 1; + my @fnums = (); + my @arr = split(/,/, $in); + for my $element (@arr) { + my ($start, $end) = split_merge_info_range($element); + push @fnums, $start; } - $info = svn_info('.'); - read_uuid($info); - my $last = $fetched; - foreach my $c (@revs) { - my $mods = svn_checkout_tree($last, $c); - if (scalar @$mods == 0) { - print "Skipping, no changes detected\n"; + + my @sorted = @arr [ sort { + $fnums[$a] <=> $fnums[$b] + } 0..$#arr ]; + + my @return = (); + my $last = -1; + my $first = -1; + for my $element (@sorted) { + my ($start, $end) = split_merge_info_range($element); + + if ($last == -1) { + $first = $start; + $last = $end; + next; + } + if ($start <= $last+1) { + if ($end > $last) { + $last = $end; + } next; } - $last = svn_commit_tree($last, $c); + if ($first == $last) { + push @return, "$first"; + } else { + push @return, "$first-$last"; + } + $first = $start; + $last = $end; } + + if ($first != -1) { + if ($first == $last) { + push @return, "$first"; + } else { + push @return, "$first-$last"; + } + } + + return join(',', @return); } -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: $fetched->{revision}\n"; - exit 1; +sub merge_revs_into_hash { + my ($hash, $minfo) = @_; + my @lines = split(' ', $minfo); + + for my $line (@lines) { + my ($branchpath, $revs) = split(/:/, $line); + + if (exists($hash->{$branchpath})) { + # Merge the two revision sets + my $combined = "$hash->{$branchpath},$revs"; + $hash->{$branchpath} = combine_ranges($combined); + } else { + # Just do range combining for consolidation + $hash->{$branchpath} = combine_ranges($revs); + } } - read_uuid(); - my @lock = $SVN::Core::VERSION ge '1.2.0' ? (undef, 0) : (); - my $commit_msg = "$GIT_SVN_DIR/.svn-commit.tmp.$$"; - - my $repo; - set_svn_commit_env(); - foreach my $c (@revs) { - my $log_msg = get_commit_message($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 $ed = SVN::Git::Editor->new( - { r => $r_last, - ra => libsvn_dup_ra($SVN), - c => $c, - svn_path => $SVN->{svn_path}, - }, - $SVN->get_commit_editor( - $log_msg->{msg}, - sub { - libsvn_commit_cb( - @_, $c, - $log_msg->{msg}, - $r_last, - $cmt_last) - }, - @lock) - ); - my $mods = libsvn_checkout_tree($cmt_last, $c, $ed); - if (@$mods == 0) { - print "No changes\nr$r_last = $cmt_last\n"; - $ed->abort_edit; - } else { - $ed->close_edit; - } - exit 0; +} + +sub merge_merge_info { + my ($mergeinfo_one, $mergeinfo_two) = @_; + my %result_hash = (); + + merge_revs_into_hash(\%result_hash, $mergeinfo_one); + merge_revs_into_hash(\%result_hash, $mergeinfo_two); + + my $result = ''; + # Sort below is for consistency's sake + for my $branchname (sort keys(%result_hash)) { + my $revlist = $result_hash{$branchname}; + $result .= "$branchname:$revlist\n" + } + return $result; +} + +sub populate_merge_info { + my ($d, $gs, $uuid, $linear_refs, $rewritten_parent) = @_; + + my %parentshash; + read_commit_parents(\%parentshash, $d); + my @parents = @{$parentshash{$d}}; + if ($#parents > 0) { + # Merge commit + my $all_parents_ok = 1; + my $aggregate_mergeinfo = ''; + my $rooturl = $gs->repos_root; + + if (defined($rewritten_parent)) { + # Replace first parent with newly-rewritten version + shift @parents; + unshift @parents, $rewritten_parent; } - 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; + + foreach my $parent (@parents) { + my ($branchurl, $svnrev, $paruuid) = + cmt_metadata($parent); + + unless (defined($svnrev)) { + # Should have been caught be preflight check + fatal "merge commit $d has ancestor $parent, but that change " + ."does not have git-svn metadata!"; } - } - close $fh or exit 1; - if (! defined $r_new && ! defined $cmt_new) { - unless ($no) { - die "Failed to parse revision information\n"; + unless ($branchurl =~ /^$rooturl(.*)/) { + fatal "commit $parent git-svn metadata changed mid-run!"; } - } else { - ($r_last, $cmt_last) = ($r_new, $cmt_new); + my $branchpath = $1; + + my $ra = Git::SVN::Ra->new($branchurl); + my (undef, undef, $props) = + $ra->get_dir(canonicalize_path("."), $svnrev); + my $par_mergeinfo = $props->{'svn:mergeinfo'}; + unless (defined $par_mergeinfo) { + $par_mergeinfo = ''; + } + # Merge previous mergeinfo values + $aggregate_mergeinfo = + merge_merge_info($aggregate_mergeinfo, + $par_mergeinfo, 0); + + next if $parent eq $parents[0]; # Skip first parent + # Add new changes being placed in tree by merge + my @cmd = (qw/rev-list --reverse/, + $parent, qw/--not/); + foreach my $par (@parents) { + unless ($par eq $parent) { + push @cmd, $par; + } + } + my @revsin = (); + my ($revlist, $ctx) = command_output_pipe(@cmd); + while (<$revlist>) { + my $irev = $_; + chomp $irev; + my (undef, $csvnrev, undef) = + cmt_metadata($irev); + unless (defined $csvnrev) { + # A child is missing SVN annotations... + # this might be OK, or might not be. + warn "W:child $irev is merged into revision " + ."$d but does not have git-svn metadata. " + ."This means git-svn cannot determine the " + ."svn revision numbers to place into the " + ."svn:mergeinfo property. You must ensure " + ."a branch is entirely committed to " + ."SVN before merging it in order for " + ."svn:mergeinfo population to function " + ."properly"; + } + push @revsin, $csvnrev; + } + command_close_pipe($revlist, $ctx); + + last unless $all_parents_ok; + + # We now have a list of all SVN revnos which are + # merged by this particular parent. Integrate them. + next if $#revsin == -1; + my $newmergeinfo = "$branchpath:" . join(',', @revsin); + $aggregate_mergeinfo = + merge_merge_info($aggregate_mergeinfo, + $newmergeinfo, 1); + } + if ($all_parents_ok and $aggregate_mergeinfo) { + return $aggregate_mergeinfo; } } - $ENV{LC_ALL} = 'C'; - unlink $commit_msg; + + return undef; } -sub dcommit { - my $gs = "refs/remotes/$GIT_SVN"; - chomp(my @refs = safe_qx(qw/git-rev-list --no-merges/, "$gs..HEAD")); - my $last_rev; - foreach my $d (reverse @refs) { - if (quiet_run('git-rev-parse','--verify',"$d~1") != 0) { - 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"; +sub cmd_dcommit { + my $head = shift; + command_noisy(qw/update-index --refresh/); + git_cmd_try { command_oneline(qw/diff-index --quiet HEAD/) } + 'Cannot dcommit with a dirty index. Commit your changes first, ' + . "or stash them with `git stash'.\n"; + $head ||= 'HEAD'; + + my $old_head; + if ($head ne 'HEAD') { + $old_head = eval { + command_oneline([qw/symbolic-ref -q HEAD/]) + }; + if ($old_head) { + $old_head =~ s{^refs/heads/}{}; + } else { + $old_head = eval { command_oneline(qw/rev-parse HEAD/) }; + } + command(['checkout', $head], STDERR => 0); + } + + my @refs; + my ($url, $rev, $uuid, $gs) = working_head_info('HEAD', \@refs); + unless ($gs) { + die "Unable to determine upstream SVN information from ", + "$head history.\nPerhaps the repository is empty."; + } + + if (defined $_commit_url) { + $url = $_commit_url; + } else { + $url = eval { command_oneline('config', '--get', + "svn-remote.$gs->{repo_id}.commiturl") }; + if (!$url) { + $url = $gs->full_pushurl } + } + + my $last_rev = $_revision if defined $_revision; + if ($url) { + print "Committing to $url ...\n"; + } + my ($linear_refs, $parents) = linearize_history($gs, \@refs); + if ($_no_rebase && scalar(@$linear_refs) > 1) { + warn "Attempting to commit more than one change while ", + "--no-rebase is enabled.\n", + "If these changes depend on each other, re-running ", + "without --no-rebase may be required." + } + + if (defined $_interactive){ + my $ask_default = "y"; + foreach my $d (@$linear_refs){ + my ($fh, $ctx) = command_output_pipe(qw(show --summary), "$d"); + while (<$fh>){ + print $_; + } + command_close_pipe($fh, $ctx); + $_ = ask("Commit this patch to SVN? ([y]es (default)|[n]o|[q]uit|[a]ll): ", + valid_re => qr/^(?:yes|y|no|n|quit|q|all|a)/i, + default => $ask_default); + die "Commit this patch reply required" unless defined $_; + if (/^[nq]/i) { + exit(0); + } elsif (/^a/i) { + last; + } + } + } + + my $expect_url = $url; + + my $push_merge_info = eval { + command_oneline(qw/config --get svn.pushmergeinfo/) + }; + if (not defined($push_merge_info) + or $push_merge_info eq "false" + or $push_merge_info eq "no" + or $push_merge_info eq "never") { + $push_merge_info = 0; + } + + unless (defined($_merge_info) || ! $push_merge_info) { + # Preflight check of changes to ensure no issues with mergeinfo + # This includes check for uncommitted-to-SVN parents + # (other than the first parent, which we will handle), + # information from different SVN repos, and paths + # which are not underneath this repository root. + my $rooturl = $gs->repos_root; + foreach my $d (@$linear_refs) { + my %parentshash; + read_commit_parents(\%parentshash, $d); + my @realparents = @{$parentshash{$d}}; + if ($#realparents > 0) { + # Merge commit + shift @realparents; # Remove/ignore first parent + foreach my $parent (@realparents) { + my ($branchurl, $svnrev, $paruuid) = cmt_metadata($parent); + unless (defined $paruuid) { + # A parent is missing SVN annotations... + # abort the whole operation. + fatal "$parent is merged into revision $d, " + ."but does not have git-svn metadata. " + ."Either dcommit the branch or use a " + ."local cherry-pick, FF merge, or rebase " + ."instead of an explicit merge commit."; + } + + unless ($paruuid eq $uuid) { + # Parent has SVN metadata from different repository + fatal "merge parent $parent for change $d has " + ."git-svn uuid $paruuid, while current change " + ."has uuid $uuid!"; + } + + unless ($branchurl =~ /^$rooturl(.*)/) { + # This branch is very strange indeed. + fatal "merge parent $parent for $d is on branch " + ."$branchurl, which is not under the " + ."git-svn root $rooturl!"; + } + } + } + } + } + + my $rewritten_parent; + Git::SVN::remove_username($expect_url); + if (defined($_merge_info)) { + $_merge_info =~ tr{ }{\n}; + } + while (1) { + my $d = shift @$linear_refs or last; 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"; } } 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 - } - } - return if $_dry_run; - fetch(); - my @diff = safe_qx(qw/git-diff-tree HEAD/, $gs); - 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; - } else { - print "No changes between current HEAD and $gs\n", - "Hard resetting to the latest $gs\n"; - @finish = qw/reset --mixed/; - } - sys('git', @finish, $gs); -} + my $cmt_rev; -sub show_ignore { - $SVN_URL ||= file_to_s("$GIT_SVN_DIR/info/url"); - $_use_lib ? show_ignore_lib() : show_ignore_cmd(); -} + unless (defined($_merge_info) || ! $push_merge_info) { + $_merge_info = populate_merge_info($d, $gs, + $uuid, + $linear_refs, + $rewritten_parent); + } -sub show_ignore_cmd { - require File::Find or die $!; - if (defined $_revision) { - die "-r/--revision option doesn't work unless the Perl SVN ", - "libraries are used\n"; + my %ed_opts = ( r => $last_rev, + log => get_commit_entry($d)->{log}, + ra => Git::SVN::Ra->new($url), + config => SVN::Core::config_get_config( + $Git::SVN::Ra::config_dir + ), + tree_a => "$d~1", + tree_b => $d, + editor_cb => sub { + print "Committed r$_[0]\n"; + $cmt_rev = $_[0]; + }, + mergeinfo => $_merge_info, + svn_path => ''); + if (!SVN::Git::Editor->new(\%ed_opts)->apply_diff) { + print "No changes\n$d~1 == $d\n"; + } elsif ($parents->{$d} && @{$parents->{$d}}) { + $gs->{inject_parents_dcommit}->{$cmt_rev} = + $parents->{$d}; + } + $_fetch_all ? $gs->fetch_all : $gs->fetch; + $last_rev = $cmt_rev; + next if $_no_rebase; + + # we always want to rebase against the current HEAD, + # not any head that was passed to us + my @diff = command('diff-tree', $d, + $gs->refname, '--'); + my @finish; + if (@diff) { + @finish = rebase_cmd(); + print STDERR "W: $d and ", $gs->refname, + " differ, using @finish:\n", + join("\n", @diff), "\n"; + } else { + print "No changes between current HEAD and ", + $gs->refname, + "\nResetting to the latest ", + $gs->refname, "\n"; + @finish = qw/reset --mixed/; + } + command_noisy(@finish, $gs->refname); + + $rewritten_parent = command_oneline(qw/rev-parse HEAD/); + + if (@diff) { + @refs = (); + my ($url_, $rev_, $uuid_, $gs_) = + working_head_info('HEAD', \@refs); + my ($linear_refs_, $parents_) = + linearize_history($gs_, \@refs); + if (scalar(@$linear_refs) != + scalar(@$linear_refs_)) { + fatal "# of revisions changed ", + "\nbefore:\n", + join("\n", @$linear_refs), + "\n\nafter:\n", + join("\n", @$linear_refs_), "\n", + 'If you are attempting to commit ', + "merges, try running:\n\t", + 'git rebase --interactive', + '--preserve-merges ', + $gs->refname, + "\nBefore dcommitting"; + } + if ($url_ ne $expect_url) { + if ($url_ eq $gs->metadata_url) { + print + "Accepting rewritten URL:", + " $url_\n"; + } else { + fatal + "URL mismatch after rebase:", + " $url_ != $expect_url"; + } + } + if ($uuid_ ne $uuid) { + fatal "uuid mismatch after rebase: ", + "$uuid_ != $uuid"; + } + # remap parents + my (%p, @l, $i); + for ($i = 0; $i < scalar @$linear_refs; $i++) { + my $new = $linear_refs_->[$i] or next; + $p{$new} = + $parents->{$linear_refs->[$i]}; + push @l, $new; + } + $parents = \%p; + $linear_refs = \@l; + } + } } - chdir $SVN_WC or croak $!; - my %ign; - File::Find::find({wanted=>sub{if(lstat $_ && -d _ && -d "$_/.svn"){ - s#^\./##; - @{$ign{$_}} = svn_propget_base('svn:ignore', $_); - }}, no_chdir=>1},'.'); - print "\n# /\n"; - foreach (@{$ign{'.'}}) { print '/',$_ if /\S/ } - delete $ign{'.'}; - foreach my $i (sort keys %ign) { - print "\n# ",$i,"\n"; - foreach (@{$ign{$i}}) { print '/',$i,'/',$_ if /\S/ } + if ($old_head) { + my $new_head = command_oneline(qw/rev-parse HEAD/); + my $new_is_symbolic = eval { + command_oneline(qw/symbolic-ref -q HEAD/); + }; + if ($new_is_symbolic) { + print "dcommitted the branch ", $head, "\n"; + } else { + print "dcommitted on a detached HEAD because you gave ", + "a revision argument.\n", + "The rewritten commit is: ", $new_head, "\n"; + } + command(['checkout', $old_head], STDERR => 0); } -} -sub show_ignore_lib { - my $repo; - $SVN ||= libsvn_connect($SVN_URL); - my $r = defined $_revision ? $_revision : $SVN->get_latest_revnum; - libsvn_traverse_ignore(\*STDOUT, $SVN->{svn_path}, $r); + unlink $gs->{index}; } -sub graft_branches { - my $gr_file = "$GIT_DIR/info/grafts"; - my ($grafts, $comments) = read_grafts($gr_file); - my $gr_sha1; +sub cmd_branch { + my ($branch_name, $head) = @_; - if (%$grafts) { - # temporarily disable our grafts file to make this idempotent - chomp($gr_sha1 = safe_qx(qw/git-hash-object -w/,$gr_file)); - rename $gr_file, "$gr_file~$gr_sha1" or croak $!; + unless (defined $branch_name && length $branch_name) { + die(($_tag ? "tag" : "branch") . " name required\n"); } + $head ||= 'HEAD'; - 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 ); - } - foreach my $u (keys %$l_map) { - if (@re) { - foreach my $p (keys %{$l_map->{$u}}) { - graft_merge_msg($grafts,$l_map,$u,$p,@re); + my (undef, $rev, undef, $gs) = working_head_info($head); + my $src = $gs->full_pushurl; + + my $remote = Git::SVN::read_all_remotes()->{$gs->{repo_id}}; + my $allglobs = $remote->{ $_tag ? 'tags' : 'branches' }; + my $glob; + if ($#{$allglobs} == 0) { + $glob = $allglobs->[0]; + } else { + unless(defined $_branch_dest) { + die "Multiple ", + $_tag ? "tag" : "branch", + " paths defined for Subversion repository.\n", + "You must specify where you want to create the ", + $_tag ? "tag" : "branch", + " with the --destination argument.\n"; + } + foreach my $g (@{$allglobs}) { + # SVN::Git::Editor could probably be moved to Git.pm.. + my $re = SVN::Git::Editor::glob2pat($g->{path}->{left}); + if ($_branch_dest =~ /$re/) { + $glob = $g; + last; } } - unless ($_no_graft_copy) { - if ($_use_lib) { - graft_file_copy_lib($grafts,$l_map,$u); - } else { - graft_file_copy_cmd($grafts,$l_map,$u); + unless (defined $glob) { + my $dest_re = qr/\b\Q$_branch_dest\E\b/; + foreach my $g (@{$allglobs}) { + $g->{path}->{left} =~ /$dest_re/ or next; + if (defined $glob) { + die "Ambiguous destination: ", + $_branch_dest, "\nmatches both '", + $glob->{path}->{left}, "' and '", + $g->{path}->{left}, "'\n"; + } + $glob = $g; + } + unless (defined $glob) { + die "Unknown ", + $_tag ? "tag" : "branch", + " destination $_branch_dest\n"; } } } - graft_tree_joins($grafts); + my ($lft, $rgt) = @{ $glob->{path} }{qw/left right/}; + my $url; + if (defined $_commit_url) { + $url = $_commit_url; + } else { + $url = eval { command_oneline('config', '--get', + "svn-remote.$gs->{repo_id}.commiturl") }; + if (!$url) { + $url = $remote->{pushurl} || $remote->{url}; + } + } + my $dst = join '/', $url, $lft, $branch_name, ($rgt || ()); - write_grafts($grafts, $comments, $gr_file); - unlink "$gr_file~$gr_sha1" if $gr_sha1; -} + if ($dst =~ /^https:/ && $src =~ /^http:/) { + $src=~s/^http:/https:/; + } -sub multi_init { - my $url = shift; - $_trunk ||= 'trunk'; - $_trunk =~ s#/+$##; - $url =~ s#/+$## if $url; - if ($_trunk !~ m#^[a-z\+]+://#) { - $_trunk = '/' . $_trunk if ($_trunk !~ m#^/#); - unless ($url) { - print STDERR "E: '$_trunk' is not a complete URL ", - "and a separate URL is not specified\n"; - exit 1; + ::_req_svn(); + + my $ctx = SVN::Client->new( + auth => Git::SVN::Ra::_auth_providers(), + log_msg => sub { + ${ $_[0] } = defined $_message + ? $_message + : 'Create ' . ($_tag ? 'tag ' : 'branch ' ) + . $branch_name; + }, + ); + + eval { + $ctx->ls($dst, 'HEAD', 0); + } and die "branch ${branch_name} already exists\n"; + + print "Copying ${src} at r${rev} to ${dst}...\n"; + $ctx->copy($src, $rev, $dst) + unless $_dry_run; + + $gs->fetch_all; +} + +sub cmd_find_rev { + my $revision_or_hash = shift or die "SVN or git revision required ", + "as a command-line argument\n"; + my $result; + if ($revision_or_hash =~ /^r\d+$/) { + my $head = shift; + $head ||= 'HEAD'; + my @refs; + my (undef, undef, $uuid, $gs) = working_head_info($head, \@refs); + unless ($gs) { + die "Unable to determine upstream SVN information from ", + "$head history\n"; } - $_trunk = $url . $_trunk; + my $desired_revision = substr($revision_or_hash, 1); + $result = $gs->rev_map_get($desired_revision, $uuid); + } else { + my (undef, $rev, undef) = cmt_metadata($revision_or_hash); + $result = $rev; + } + print "$result\n" if $result; +} + +sub auto_create_empty_directories { + my ($gs) = @_; + my $var = eval { command_oneline('config', '--get', '--bool', + "svn-remote.$gs->{repo_id}.automkdirs") }; + # By default, create empty directories by consulting the unhandled log, + # but allow setting it to 'false' to skip it. + return !($var && $var eq 'false'); +} + +sub cmd_rebase { + command_noisy(qw/update-index --refresh/); + my ($url, $rev, $uuid, $gs) = working_head_info('HEAD'); + unless ($gs) { + die "Unable to determine upstream SVN information from ", + "working tree history\n"; + } + if ($_dry_run) { + print "Remote Branch: " . $gs->refname . "\n"; + print "SVN URL: " . $url . "\n"; + return; + } + if (command(qw/diff-index HEAD --/)) { + print STDERR "Cannot rebase with uncommited changes:\n"; + command_noisy('status'); + exit 1; } - my $ch_id; - if ($GIT_SVN eq 'git-svn') { - $ch_id = 1; - $GIT_SVN = $ENV{GIT_SVN_ID} = 'trunk'; + unless ($_local) { + # rebase will checkout for us, so no need to do it explicitly + $_no_checkout = 'true'; + $_fetch_all ? $gs->fetch_all : $gs->fetch; } - init_vars(); - unless (-d $GIT_SVN_DIR) { - print "GIT_SVN_ID set to 'trunk' for $_trunk\n" if $ch_id; - init($_trunk); - sys('git-repo-config', 'svn.trunk', $_trunk); + command_noisy(rebase_cmd(), $gs->refname); + if (auto_create_empty_directories($gs)) { + $gs->mkemptydirs; } - complete_url_ls_init($url, $_branches, '--branches/-b', ''); - complete_url_ls_init($url, $_tags, '--tags/-t', '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_show_ignore { + my ($url, $rev, $uuid, $gs) = working_head_info('HEAD'); + $gs ||= Git::SVN->new; + my $r = (defined $_revision ? $_revision : $gs->ra->get_latest_revnum); + $gs->prop_walk($gs->{path}, $r, sub { + my ($gs, $path, $props) = @_; + print STDOUT "\n# $path\n"; + my $s = $props->{'svn:ignore'} or return; + $s =~ s/[\r\n]+/\n/g; + $s =~ s/^\n+//; + chomp $s; + $s =~ s#^#$path#gm; + print STDOUT "$s\n"; + }); +} + +sub cmd_show_externals { + my ($url, $rev, $uuid, $gs) = working_head_info('HEAD'); + $gs ||= Git::SVN->new; + my $r = (defined $_revision ? $_revision : $gs->ra->get_latest_revnum); + $gs->prop_walk($gs->{path}, $r, sub { + my ($gs, $path, $props) = @_; + print STDOUT "\n# $path\n"; + my $s = $props->{'svn:externals'} or return; + $s =~ s/[\r\n]+/\n/g; + chomp $s; + $s =~ s#^#$path#gm; + print STDOUT "$s\n"; + }); +} + +sub cmd_create_ignore { + my ($url, $rev, $uuid, $gs) = working_head_info('HEAD'); + $gs ||= Git::SVN->new; + my $r = (defined $_revision ? $_revision : $gs->ra->get_latest_revnum); + $gs->prop_walk($gs->{path}, $r, sub { + my ($gs, $path, $props) = @_; + # $path is of the form /path/to/dir/ + $path = '.' . $path; + # SVN can have attributes on empty directories, + # which git won't track + mkpath([$path]) unless -d $path; + my $ignore = $path . '.gitignore'; + my $s = $props->{'svn:ignore'} or return; + open(GITIGNORE, '>', $ignore) + or fatal("Failed to open `$ignore' for writing: $!"); + $s =~ s/[\r\n]+/\n/g; + $s =~ s/^\n+//; + chomp $s; + # Prefix all patterns so that the ignore doesn't apply + # to sub-directories. + $s =~ s#^#/#gm; + print GITIGNORE "$s\n"; + close(GITIGNORE) + or fatal("Failed to close `$ignore': $!"); + command_noisy('add', '-f', $ignore); + }); +} + +sub cmd_mkdirs { + my ($url, $rev, $uuid, $gs) = working_head_info('HEAD'); + $gs ||= Git::SVN->new; + $gs->mkemptydirs($_revision); +} + +sub canonicalize_path { + my ($path) = @_; + my $dot_slash_added = 0; + if (substr($path, 0, 1) ne "/") { + $path = "./" . $path; + $dot_slash_added = 1; } - rec_fetch('', "$GIT_DIR/svn", @_); + # File::Spec->canonpath doesn't collapse x/../y into y (for a + # good reason), so let's do this manually. + $path =~ s#/+#/#g; + $path =~ s#/\.(?:/|$)#/#g; + $path =~ s#/[^/]+/\.\.##g; + $path =~ s#/$##g; + $path =~ s#^\./## if $dot_slash_added; + $path =~ s#^/##; + $path =~ s#^\.$##; + return $path; } -sub show_log { - my (@args) = @_; - my ($r_min, $r_max); - my $r_last = -1; # prevent dupes - rload_authors() if $_authors; - if (defined $TZ) { - $ENV{TZ} = $TZ; - } else { - delete $ENV{TZ}; +sub canonicalize_url { + my ($url) = @_; + $url =~ s#^([^:]+://[^/]*/)(.*)$#$1 . canonicalize_path($2)#e; + return $url; +} + +# get_svnprops(PATH) +# ------------------ +# Helper for cmd_propget and cmd_proplist below. +sub get_svnprops { + my $path = shift; + my ($url, $rev, $uuid, $gs) = working_head_info('HEAD'); + $gs ||= Git::SVN->new; + + # prefix THE PATH by the sub-directory from which the user + # invoked us. + $path = $cmd_dir_prefix . $path; + fatal("No such file or directory: $path") unless -e $path; + my $is_dir = -d $path ? 1 : 0; + $path = $gs->{path} . '/' . $path; + + # canonicalize the path (otherwise libsvn will abort or fail to + # find the file) + $path = canonicalize_path($path); + + my $r = (defined $_revision ? $_revision : $gs->ra->get_latest_revnum); + my $props; + if ($is_dir) { + (undef, undef, $props) = $gs->ra->get_dir($path, $r); } - if (defined $_revision) { - if ($_revision =~ /^(\d+):(\d+)$/) { - ($r_min, $r_max) = ($1, $2); - } elsif ($_revision =~ /^\d+$/) { - $r_min = $r_max = $_revision; - } else { - print STDERR "-r$_revision is not supported, use ", - "standard \'git log\' arguments instead\n"; - exit 1; - } + else { + (undef, $props) = $gs->ra->get_file($path, $r, undef); } + return $props; +} - config_pager(); - my $pid = open(my $log,'-|'); - defined $pid or croak $!; - if (!$pid) { - exec(git_svn_log_cmd($r_min,$r_max), @args) or croak $!; +# cmd_propget (PROP, PATH) +# ------------------------ +# Print the SVN property PROP for PATH. +sub cmd_propget { + my ($prop, $path) = @_; + $path = '.' if not defined $path; + usage(1) if not defined $prop; + my $props = get_svnprops($path); + if (not defined $props->{$prop}) { + fatal("`$path' does not have a `$prop' SVN property."); } - run_pager(); - my (@k, $c, $d); + print $props->{$prop} . "\n"; +} - while (<$log>) { - if (/^${_esc_color}commit ($sha1_short)/o) { - my $cmt = $1; - if ($c && cmt_showable($c) && $c->{r} != $r_last) { - $r_last = $c->{r}; - process_commit($c, $r_min, $r_max, \@k) or - goto out; - } - $d = undef; - $c = { c => $cmt }; - } elsif (/^${_esc_color}author (.+) (\d+) ([\-\+]?\d+)$/) { - get_author_info($c, $1, $2, $3); - } elsif (/^${_esc_color}(?:tree|parent|committer) /) { - # ignore - } elsif (/^${_esc_color}:\d{6} \d{6} $sha1_short/o) { - push @{$c->{raw}}, $_; - } elsif (/^${_esc_color}[ACRMDT]\t/) { - # we could add $SVN->{svn_path} here, but that requires - # remote access at the moment (repo_path_split)... - s#^(${_esc_color})([ACRMDT])\t#$1 $2 #; - push @{$c->{changed}}, $_; - } elsif (/^${_esc_color}diff /) { - $d = 1; - push @{$c->{diff}}, $_; - } elsif ($d) { - push @{$c->{diff}}, $_; - } elsif (/^${_esc_color} (git-svn-id:.+)$/) { - ($c->{url}, $c->{r}, undef) = extract_metadata($1); - } elsif (s/^${_esc_color} //) { - push @{$c->{l}}, $_; +# cmd_proplist (PATH) +# ------------------- +# Print the list of SVN properties for PATH. +sub cmd_proplist { + my $path = shift; + $path = '.' if not defined $path; + my $props = get_svnprops($path); + print "Properties on '$path':\n"; + foreach (sort keys %{$props}) { + print " $_\n"; + } +} + +sub cmd_multi_init { + my $url = shift; + unless (defined $_trunk || @_branches || @_tags) { + usage(1); + } + + $_prefix = '' unless defined $_prefix; + if (defined $url) { + $url = canonicalize_url($url); + init_subdir(@_); + } + do_git_init_db(); + if (defined $_trunk) { + $_trunk =~ s#^/+##; + my $trunk_ref = 'refs/remotes/' . $_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, $trunk_path) = + complete_svn_url($url, $_trunk); + $gs_trunk = Git::SVN->init($trunk_url, $trunk_path, + undef, $trunk_ref); } } - if ($c && defined $c->{r} && $c->{r} != $r_last) { - $r_last = $c->{r}; - process_commit($c, $r_min, $r_max, \@k); + return unless @_branches || @_tags; + my $ra = $url ? Git::SVN::Ra->new($url) : undef; + foreach my $path (@_branches) { + complete_url_ls_init($ra, $path, '--branches/-b', $_prefix); } - if (@k) { - my $swap = $r_max; - $r_max = $r_min; - $r_min = $swap; - process_commit($_, $r_min, $r_max) foreach reverse @k; + foreach my $path (@_tags) { + complete_url_ls_init($ra, $path, '--tags/-t', $_prefix.'tags/'); } -out: - close $log; - print '-' x72,"\n" unless $_incremental || $_oneline; } -sub commit_diff_usage { - print STDERR "Usage: $0 commit-diff <tree-ish> <tree-ish> [<URL>]\n"; - exit 1 +sub cmd_multi_fetch { + $Git::SVN::no_reuse_existing = undef; + 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); + } + } } -sub commit_diff { - if (!$_use_lib) { - print STDERR "commit-diff must be used with SVN libraries\n"; - exit 1; - } - 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"; +# this command is special because it requires no metadata +sub cmd_commit_diff { + my ($ta, $tb, $url) = @_; + my $usage = "Usage: $0 commit-diff -r<revision> ". + "<tree-ish> <tree-ish> [<URL>]"; + fatal($usage) if (!defined $ta || !defined $tb); + my $svn_path = ''; + if (!defined $url) { + my $gs = eval { Git::SVN->new }; + if (!$gs) { + fatal("Needed URL or usable git-svn --id in ", + "the command-line\n", $usage); } + $url = $gs->{url}; + $svn_path = $gs->{path}; + } + unless (defined $_revision) { + fatal("-r|--revision is a required argument\n", $usage); } 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; + fatal("Both --message/-m and --file/-F specified ", + "for the commit message.\n", + "I have no idea what you mean"); } if (defined $_file) { $_message = file_to_s($_file); } else { - $_message ||= get_commit_message($tb, - "$GIT_DIR/.svn-commit.tmp.$$")->{msg}; + $_message ||= get_commit_entry($tb)->{log}; } - $SVN ||= libsvn_connect($SVN_URL); + my $ra ||= Git::SVN::Ra->new($url); + my $r = $_revision; if ($r eq 'HEAD') { - $r = $SVN->get_latest_revnum; + $r = $ra->get_latest_revnum; } elsif ($r !~ /^\d+$/) { die "revision argument: $r not understood by git-svn\n"; } - my @lock = $SVN::Core::VERSION ge '1.2.0' ? (undef, 0) : (); - my $rev_committed; - my $ed = SVN::Git::Editor->new({ r => $r, - ra => libsvn_dup_ra($SVN), - c => $tb, - svn_path => $SVN->{svn_path} - }, - $SVN->get_commit_editor($_message, - sub { - $rev_committed = $_[0]; - print "Committed $_[0]\n"; - }, @lock) - ); + my %ed_opts = ( r => $r, + 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 == $tb\n"; + } +} + +sub escape_uri_only { + my ($uri) = @_; + my @tmp; + foreach (split m{/}, $uri) { + s/([^~\w.%+-]|%(?![a-fA-F0-9]{2}))/sprintf("%%%02X",ord($1))/eg; + push @tmp, $_; + } + join('/', @tmp); +} + +sub escape_url { + my ($url) = @_; + if ($url =~ m#^([^:]+)://([^/]*)(.*)$#) { + my ($scheme, $domain, $uri) = ($1, $2, escape_uri_only($3)); + $url = "$scheme://$domain$uri"; + } + $url; +} + +sub cmd_info { + my $path = canonicalize_path(defined($_[0]) ? $_[0] : "."); + my $fullpath = canonicalize_path($cmd_dir_prefix . $path); + if (exists $_[1]) { + die "Too many arguments specified\n"; + } + + my ($file_type, $diff_status) = find_file_type_and_diff_status($path); + + if (!$file_type && !$diff_status) { + print STDERR "svn: '$path' is not under version control\n"; + exit 1; + } + + my ($url, $rev, $uuid, $gs) = working_head_info('HEAD'); + unless ($gs) { + die "Unable to determine upstream SVN information from ", + "working tree history\n"; + } + + # canonicalize_path() will return "" to make libsvn 1.5.x happy, + $path = "." if $path eq ""; + + my $full_url = $url . ($fullpath eq "" ? "" : "/$fullpath"); + + if ($_url) { + print escape_url($full_url), "\n"; + return; + } + + my $result = "Path: $path\n"; + $result .= "Name: " . basename($path) . "\n" if $file_type ne "dir"; + $result .= "URL: " . escape_url($full_url) . "\n"; + eval { - my $mods = libsvn_checkout_tree($ta, $tb, $ed); - if (@$mods == 0) { - print "No changes\n$ta == $tb\n"; - $ed->abort_edit; - } else { - $ed->close_edit; - } + my $repos_root = $gs->repos_root; + Git::SVN::remove_username($repos_root); + $result .= "Repository Root: " . escape_url($repos_root) . "\n"; }; - fatal "$@\n" if $@; - $_message = $_file = undef; - return $rev_committed; -} + if ($@) { + $result .= "Repository Root: (offline)\n"; + } + ::_req_svn(); + $result .= "Repository UUID: $uuid\n" unless $diff_status eq "A" && + ($SVN::Core::VERSION le '1.5.4' || $file_type ne "dir"); + $result .= "Revision: " . ($diff_status eq "A" ? 0 : $rev) . "\n"; -########################### utility functions ######################### + $result .= "Node Kind: " . + ($file_type eq "dir" ? "directory" : "file") . "\n"; -sub cmt_showable { - my ($c) = @_; - return 1 if defined $c->{r}; - if ($c->{l} && $c->{l}->[-1] eq "...\n" && - $c->{a_raw} =~ /\@([a-f\d\-]+)>$/) { - my @msg = safe_qx(qw/git-cat-file commit/, $c->{c}); - shift @msg while ($msg[0] ne "\n"); - shift @msg; - @{$c->{l}} = grep !/^git-svn-id: /, @msg; + my $schedule = $diff_status eq "A" + ? "add" + : ($diff_status eq "D" ? "delete" : "normal"); + $result .= "Schedule: $schedule\n"; - (undef, $c->{r}, undef) = extract_metadata( - (grep(/^git-svn-id: /, @msg))[-1]); + if ($diff_status eq "A") { + print $result, "\n"; + return; } - return defined $c->{r}; -} -sub log_use_color { - return 1 if $_color; - my $dc; - chomp($dc = `git-repo-config --get diff.color`); - if ($dc eq 'auto') { - if (-t *STDOUT || (defined $_pager && - `git-repo-config --bool --get pager.color` !~ /^false/)) { - return ($ENV{TERM} && $ENV{TERM} ne 'dumb'); + my ($lc_author, $lc_rev, $lc_date_utc); + my @args = Git::SVN::Log::git_svn_log_cmd($rev, $rev, "--", $fullpath); + my $log = command_output_pipe(@args); + my $esc_color = qr/(?:\033\[(?:(?:\d+;)*\d*)?m)*/; + while (<$log>) { + if (/^${esc_color}author (.+) <[^>]+> (\d+) ([\-\+]?\d+)$/o) { + $lc_author = $1; + $lc_date_utc = Git::SVN::Log::parse_git_date($2, $3); + } elsif (/^${esc_color} (git-svn-id:.+)$/o) { + (undef, $lc_rev, undef) = ::extract_metadata($1); } - return 0; } - return 0 if $dc eq 'never'; - return 1 if $dc eq 'always'; - chomp($dc = `git-repo-config --bool --get diff.color`); - $dc eq 'true'; -} + close $log; -sub git_svn_log_cmd { - my ($r_min, $r_max) = @_; - my @cmd = (qw/git-log --abbrev-commit --pretty=raw - --default/, "refs/remotes/$GIT_SVN"); - push @cmd, '-r' unless $_non_recursive; - push @cmd, qw/--raw --name-status/ if $_verbose; - push @cmd, '--color' if log_use_color(); - return @cmd unless defined $r_max; - if ($r_max == $r_min) { - push @cmd, '--max-count=1'; - if (my $c = revdb_get($REVDB, $r_max)) { - push @cmd, $c; - } - } else { - my ($c_min, $c_max); - $c_max = revdb_get($REVDB, $r_max); - $c_min = revdb_get($REVDB, $r_min); - if (defined $c_min && defined $c_max) { - if ($r_max > $r_max) { - push @cmd, "$c_min..$c_max"; + Git::SVN::Log::set_local_timezone(); + + $result .= "Last Changed Author: $lc_author\n"; + $result .= "Last Changed Rev: $lc_rev\n"; + $result .= "Last Changed Date: " . + Git::SVN::Log::format_svn_date($lc_date_utc) . "\n"; + + if ($file_type ne "dir") { + my $text_last_updated_date = + ($diff_status eq "D" ? $lc_date_utc : (stat $path)[9]); + $result .= + "Text Last Updated: " . + Git::SVN::Log::format_svn_date($text_last_updated_date) . + "\n"; + my $checksum; + if ($diff_status eq "D") { + my ($fh, $ctx) = + command_output_pipe(qw(cat-file blob), "HEAD:$path"); + if ($file_type eq "link") { + my $file_name = <$fh>; + $checksum = md5sum("link $file_name"); } else { - push @cmd, "$c_max..$c_min"; + $checksum = md5sum($fh); } - } elsif ($r_max > $r_min) { - push @cmd, $c_max; + command_close_pipe($fh, $ctx); + } elsif ($file_type eq "link") { + my $file_name = + command(qw(cat-file blob), "HEAD:$path"); + $checksum = + md5sum("link " . $file_name); } else { - push @cmd, $c_min; + open FILE, "<", $path or die $!; + $checksum = md5sum(\*FILE); + close FILE or die $!; } + $result .= "Checksum: " . $checksum . "\n"; } - return @cmd; + + print $result, "\n"; } -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) { - $_repack = undef; - $GIT_SVN = $ENV{GIT_SVN_ID} = $id; - init_vars(); - fetch(@_); - exit 0; +sub cmd_reset { + my $target = shift || $_revision or die "SVN revision required\n"; + $target = $1 if $target =~ /^r(\d+)$/; + $target =~ /^\d+$/ or die "Numeric SVN revision expected\n"; + my ($url, $rev, $uuid, $gs) = working_head_info('HEAD'); + unless ($gs) { + die "Unable to determine upstream SVN information from ". + "history\n"; } - while (<$fh>) { - print $_; - check_repack() if (/^r\d+ = $sha1/); + my ($r, $c) = $gs->find_rev_before($target, not $_fetch_parent); + die "Cannot find SVN revision $target\n" unless defined($c); + $gs->rev_map_set($r, $c, 'reset', $uuid); + print "r$r = $c ($gs->{ref_id})\n"; +} + +sub cmd_gc { + if (!$can_compress) { + warn "Compress::Zlib could not be found; unhandled.log " . + "files will not be compressed.\n"; } - close $fh or croak $?; + find({ wanted => \&gc_directory, no_chdir => 1}, "$ENV{GIT_DIR}/svn"); } -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, $_; +########################### utility functions ######################### + +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; +} + +sub post_fetch_checkout { + return if $_no_checkout; + my $gs = $Git::SVN::_head or return; + return if verify_ref('refs/heads/master^0'); + + # look for "trunk" ref if it exists + my $remote = Git::SVN::read_all_remotes()->{$gs->{repo_id}}; + my $fetch = $remote->{fetch}; + if ($fetch) { + foreach my $p (keys %$fetch) { + basename($fetch->{$p}) eq 'trunk' or next; + $gs = Git::SVN->new($fetch->{$p}, $gs->{repo_id}, $p); + last; } } - foreach (@dir) { - my $x = $_; - $x =~ s!^\Q$GIT_DIR\E/svn/!!; - rec_fetch($x, $_); + + 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')); + + return if $ENV{GIT_DIR} !~ m#^(?:.*/)?\.git$#; + my $index = $ENV{GIT_INDEX_FILE} || "$ENV{GIT_DIR}/index"; + return if -f $index; + + return if command_oneline(qw/rev-parse --is-inside-work-tree/) eq 'false'; + 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", $gs->last_rev, "\n"; + if (auto_create_empty_directories($gs)) { + $gs->mkemptydirs($gs->last_rev); + } +} + +sub complete_svn_url { + my ($url, $path) = @_; + $path =~ s#/+$##; + if ($path !~ m#^[a-z\+]+://#) { + if (!defined $url || $url !~ m#^[a-z\+]+://#) { + fatal("E: '$path' is not a complete URL ", + "and a separate URL is not specified"); + } + return ($url, $path); } + return ($path, ''); } sub complete_url_ls_init { - my ($url, $var, $switch, $pfx) = @_; - unless ($var) { + my ($ra, $repo_path, $switch, $pfx) = @_; + unless ($repo_path) { print STDERR "W: $switch not specified\n"; return; } - $var =~ s#/+$##; - if ($var !~ m#^[a-z\+]+://#) { - $var = '/' . $var if ($var !~ m#^/#); - unless ($url) { - print STDERR "E: '$var' is not a complete URL ", - "and a separate URL is not specified\n"; - exit 1; - } - $var = $url . $var; - } - chomp(my @ls = $_use_lib ? libsvn_ls_fullurl($var) - : safe_qx(qw/svn ls --non-interactive/, $var)); - my $old = $GIT_SVN; - defined(my $pid = fork) or croak $!; - if (!$pid) { - foreach my $u (map { "$var/$_" } (grep m!/$!, @ls)) { - $u =~ s#/+$##; - if ($u !~ m!\Q$var\E/(.+)$!) { - print STDERR "W: Unrecognized URL: $u\n"; - die "This should never happen\n"; - } - # don't try to init already existing refs - my $id = $pfx.$1; - $GIT_SVN = $ENV{GIT_SVN_ID} = $id; - init_vars(); - unless (-d $GIT_SVN_DIR) { - print "init $u => $id\n"; - init($u); - } + $repo_path =~ s#/+$##; + if ($repo_path =~ m#^[a-z\+]+://#) { + $ra = Git::SVN::Ra->new($repo_path); + $repo_path = ''; + } else { + $repo_path =~ s#^/+##; + unless ($ra) { + fatal("E: '$repo_path' is not a complete URL ", + "and a separate URL is not specified"); } - exit 0; } - waitpid $pid, 0; - croak $? if $?; + 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 $remote_path = "$gs->{path}/$repo_path"; + $remote_path =~ s{%([0-9A-F]{2})}{chr hex($1)}ieg; + $remote_path =~ s#/+#/#g; + $remote_path =~ s#^/##g; + $remote_path .= "/*" if $remote_path !~ /\*/; my ($n) = ($switch =~ /^--(\w+)/); - sys('git-repo-config', "svn.$n", $var); + if (length $pfx && $pfx !~ m#/$#) { + die "--prefix='$pfx' must have a trailing slash '/'\n"; + } + command_noisy('config', + '--add', + "svn-remote.$gs->{repo_id}.$n", + "$remote_path:refs/remotes/$pfx*" . + ('/*' x (($remote_path =~ tr/*/*/) - 1)) ); } -sub 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}++; - } +sub verify_ref { + my ($ref) = @_; + eval { command_oneline([ 'rev-parse', '--verify', $ref ], + { STDERR => 0 }); }; +} + +sub get_tree_from_treeish { + my ($treeish) = @_; + # $treeish can be a symbolic ref, too: + my $type = command_oneline(qw/cat-file -t/, $treeish); + my $expected; + while ($type eq 'tag') { + ($treeish, $type) = command(qw/cat-file tag/, $treeish); } - foreach (sort {length $b <=> length $a} keys %common) { - if ($common{$_} == @$paths) { - return $_; - } + if ($type eq 'commit') { + $expected = (grep /^tree /, command(qw/cat-file commit/, + $treeish))[0]; + ($expected) = ($expected =~ /^tree ($sha1)$/o); + die "Unable to get tree from $treeish\n" unless $expected; + } elsif ($type eq 'tree') { + $expected = $treeish; + } else { + die "$treeish is a $type, expected tree, tag or commit\n"; } - return ''; + return $expected; } -# 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 $grafts = shift; - map_tree_joins() if (@_branch_from && !%tree_map); - return unless %tree_map; +sub get_commit_entry { + my ($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 $!; - git_svn_each(sub { - my $i = shift; - defined(my $pid = open my $fh, '-|') or croak $!; - if (!$pid) { - exec qw/git-rev-list --pretty=raw/, - "refs/remotes/$i" 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; + my $author; + my $saw_from = 0; + my $msgbuf = ""; + while (<$msg_fh>) { + if (!$in_msg) { + $in_msg = 1 if (/^\s*$/); + $author = $1 if (/^author (.*>)/); + } elsif (/^git-svn-id: /) { + # skip this for now, we regenerate the + # correct one on re-fetch anyways + # TODO: set *:merge properties or like... + } else { + if (/^From:/ || /^Signed-off-by:/) { + $saw_from = 1; + } + $msgbuf .= $_; + } } - while (<$fh>) { - next unless /^commit ($sha1)$/o; - my $c = $1; - my ($t) = (<$fh> =~ /^tree ($sha1)$/o); - next unless $tree_map{$t}; + $msgbuf =~ s/\s+$//s; + if ($Git::SVN::_add_author_from && defined($author) + && !$saw_from) { + $msgbuf .= "\n\nFrom: $author"; + } + print $log_fh $msgbuf or croak $!; + command_close_pipe($msg_fh, $ctx); + } + close $log_fh or croak $!; - my $l; - do { - $l = readline $fh; - } until ($l =~ /^committer (?:.+) (\d+) ([\-\+]?\d+)$/); + if ($_edit || ($type eq 'tree')) { + chomp(my $editor = command_oneline(qw(var GIT_EDITOR))); + system('sh', '-c', $editor.' "$@"', $editor, $commit_editmsg); + } + rename $commit_editmsg, $commit_msg or croak $!; + { + require Encode; + # SVN requires messages to be UTF-8 when entering the repo + local $/; + open $log_fh, '<', $commit_msg or croak $!; + binmode $log_fh; + chomp($log_entry{log} = <$log_fh>); + + my $enc = Git::config('i18n.commitencoding') || 'UTF-8'; + my $msg = $log_entry{log}; + + eval { $msg = Encode::decode($enc, $msg, 1) }; + if ($@) { + die "Could not decode as $enc:\n", $msg, + "\nPerhaps you need to set i18n.commitencoding\n"; + } - my ($s, $tz) = ($1, $2); - if ($tz =~ s/^\+//) { - $s += tz_to_s_offset($tz); - } elsif ($tz =~ s/^\-//) { - $s -= tz_to_s_offset($tz); - } + eval { $msg = Encode::encode('UTF-8', $msg, 1) }; + die "Could not encode as UTF-8:\n$msg\n" if $@; - my ($url_a, $r_a, $uuid_a) = cmt_metadata($c); + $log_entry{log} = $msg; - foreach my $p (@{$tree_map{$t}}) { - next if $p eq $c; - my $mb = eval { - safe_qx('git-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 ? - } - } - close $fh or croak $?; - }); + close $log_fh or croak $!; + } + unlink $commit_msg; + \%log_entry; } -# this isn't funky-filename safe, but good enough for now... -sub graft_file_copy_cmd { - my ($grafts, $l_map, $u) = @_; - my $paths = $l_map->{$u}; - my $pfx = common_prefix([keys %$paths]); - $SVN_URL ||= $u.$pfx; - my $pid = open my $fh, '-|'; - defined $pid or croak $!; - unless ($pid) { - my @exec = qw/svn log -v/; - push @exec, "-r$_revision" if defined $_revision; - exec @exec, $u.$pfx or croak $!; - } - my ($r, $mp) = (undef, undef); - while (<$fh>) { - chomp; - if (/^\-{72}$/) { - $mp = $r = undef; - } elsif (/^r(\d+) \| /) { - $r = $1 unless defined $r; - } elsif (/^Changed paths:/) { - $mp = 1; - } elsif ($mp && m#^ [AR] /(\S.*?) \(from /(\S+?):(\d+)\)$#) { - my ($p1, $p0, $r0) = ($1, $2, $3); - my $c = find_graft_path_commit($paths, $p1, $r); - next unless $c; - find_graft_path_parents($grafts, $paths, $c, $p0, $r0); - } - } -} - -sub graft_file_copy_lib { - my ($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); - $SVN = libsvn_connect($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) { - my $pool = SVN::Pool->new; - libsvn_get_log(libsvn_dup_ra($SVN), [$path], - $min, $max, 0, 2, 1, - sub { - libsvn_graft_file_copies($grafts, $tree_paths, - $path, @_); - }, $pool); - $pool->clear; - last if ($max >= $head); - $min = $max + 1; - $max += $inc; - $max = $head if ($max > $head); - } - $SVN::Error::handler = $eh; +sub s_to_file { + my ($str, $file, $mode) = @_; + open my $fd,'>',$file or croak $!; + print $fd $str,"\n" or croak $!; + close $fd or croak $!; + chmod ($mode &~ umask, $file) if (defined $mode); } -sub process_merge_msg_matches { - my ($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, $_; +sub file_to_s { + my $file = shift; + open my $fd,'<',$file or croak "$!: file: $file\n"; + local $/; + my $ret = <$fd>; + close $fd or croak $!; + $ret =~ s/\s*$//s; + return $ret; +} + +# '<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"; + my $log = $cmd eq 'log'; + while (<$authors>) { + chomp; + next unless /^(.+?|\(no author\))\s*=\s*(.+?)\s*<(.+)>\s*$/; + my ($user, $name, $email) = ($1, $2, $3); + if ($log) { + $Git::SVN::Log::rusers{"$name <$email>"} = $user; } else { - push @weak, $_; + $users{$user} = [$name, $email]; } } - 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; + close $authors or croak $!; +} + +# convert GetOpt::Long specs for use by git-config +sub read_git_config { + 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-zA-Z\-]+)/); + $key =~ s/-//g; + my $arg = 'git config'; + $arg .= ' --int' if ($o =~ /[:=]i$/); + $arg .= ' --bool' if ($o !~ /[:=][sfi]$/); + if (ref $v eq 'ARRAY') { + chomp(my @tmp = `$arg --get-all svn.$key`); + @$v = @tmp if @tmp; + } else { + chomp(my $tmp = `$arg --get svn.$key`); + if ($tmp && !($arg =~ / --bool/ && $tmp eq 'false')) { + $$v = $tmp; } } } - 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; + delete @$opts{@config_only} if @config_only; +} + +sub extract_metadata { + my $id = shift or return (undef, undef, undef); + my ($url, $rev, $uuid) = ($id =~ /^\s*git-svn-id:\s+(.*)\@(\d+) + \s([a-f\d\-]+)$/ix); + if (!defined $rev || !$uuid || !$url) { + # some of the original repositories I made had + # identifiers like this: + ($rev, $uuid) = ($id =~/^\s*git-svn-id:\s(\d+)\@([a-f\d\-]+)/i); } + return ($url, $rev, $uuid); +} + +sub cmt_metadata { + return extract_metadata((grep(/^git-svn-id: /, + command(qw/cat-file commit/, shift)))[-1]); } -sub graft_merge_msg { - my ($grafts, $l_map, $u, $p, @re) = @_; +sub cmt_sha2rev_batch { + my %s2r; + my ($pid, $in, $out, $ctx) = command_bidi_pipe(qw/cat-file --batch/); + my $list = shift; + + foreach my $sha (@{$list}) { + my $first = 1; + my $size = 0; + print $out $sha, "\n"; + + while (my $line = <$in>) { + if ($first && $line =~ /^[[:xdigit:]]{40}\smissing$/) { + last; + } elsif ($first && + $line =~ /^[[:xdigit:]]{40}\scommit\s(\d+)$/) { + $first = 0; + $size = $1; + next; + } elsif ($line =~ /^(git-svn-id: )/) { + my (undef, $rev, undef) = + extract_metadata($line); + $s2r{$sha} = $rev; + } - my $x = $l_map->{$u}->{$p}; - my $rl = rev_list_raw($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); + $size -= length($line); + last if ($size == 0); } } + + command_close_bidi_pipe($pid, $in, $out, $ctx); + + return \%s2r; } -sub read_uuid { - return if $SVN_UUID; - if ($_use_lib) { - my $pool = SVN::Pool->new; - $SVN_UUID = $SVN->get_uuid($pool); - $pool->clear; - } else { - my $info = shift || svn_info('.'); - $SVN_UUID = $info->{'Repository UUID'} or - croak "Repository UUID unreadable\n"; +sub working_head_info { + my ($head, $refs) = @_; + my @args = qw/log --no-color --no-decorate --first-parent + --pretty=medium/; + my ($fh, $ctx) = command_output_pipe(@args, $head); + my $hash; + my %max; + while (<$fh>) { + if ( m{^commit ($::sha1)$} ) { + unshift @$refs, $hash if $hash and $refs; + $hash = $1; + next; + } + next unless s{^\s*(git-svn-id:)}{$1}; + my ($url, $rev, $uuid) = extract_metadata($_); + if (defined $url && defined $rev) { + next if $max{$url} and $max{$url} < $rev; + if (my $gs = Git::SVN->find_by_url($url)) { + my $c = $gs->rev_map_get($rev, $uuid); + if ($c && $c eq $hash) { + close $fh; # break the pipe + return ($url, $rev, $uuid, $gs); + } else { + $max{$url} ||= $gs->rev_map_max; + } + } + } } + command_close_pipe($fh, $ctx); + (undef, undef, undef, undef); } -sub quiet_run { - my $pid = fork; - defined $pid or croak $!; - if (!$pid) { - open my $null, '>', '/dev/null' or croak $!; - open STDERR, '>&', $null or croak $!; - open STDOUT, '>&', $null or croak $!; - exec @_ or croak $!; - } - waitpid $pid, 0; - return $?; +sub read_commit_parents { + my ($parents, $c) = @_; + chomp(my $p = command_oneline(qw/rev-list --parents -1/, $c)); + $p =~ s/^($c)\s*// or die "rev-list --parents -1 $c failed!\n"; + @{$parents->{$c}} = split(/ /, $p); } -sub repo_path_split { - my $full_url = shift; - $full_url =~ s#/+$##; +sub linearize_history { + my ($gs, $refs) = @_; + my %parents; + foreach my $c (@$refs) { + read_commit_parents(\%parents, $c); + } + + my @linear_refs; + my %skip = (); + my $last_svn_commit = $gs->last_commit; + foreach my $c (reverse @$refs) { + next if $c eq $last_svn_commit; + last if $skip{$c}; + + unshift @linear_refs, $c; + $skip{$c} = 1; + + # we only want the first parent to diff against for linear + # history, we save the rest to inject when we finalize the + # svn commit + my $fp_a = verify_ref("$c~1"); + my $fp_b = shift @{$parents{$c}} if $parents{$c}; + if (!$fp_a || !$fp_b) { + die "Commit $c\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"; + } + if ($fp_a ne $fp_b) { + die "$c~1 = $fp_a, however parsing commit $c ", + "revealed that:\n$c~1 = $fp_b\nBUG!\n"; + } - foreach (@repo_path_split_cache) { - if ($full_url =~ s#$_##) { - my $u = $1; - $full_url =~ s#^/+##; - return ($u, $full_url); + foreach my $p (@{$parents{$c}}) { + $skip{$p} = 1; } } - if ($_use_lib) { - my $tmp = libsvn_connect($full_url); - return ($tmp->{repos_root}, $tmp->{svn_path}); - } else { - my ($url, $path) = ($full_url =~ m!^([a-z\+]+://[^/]*)(.*)$!i); - $path =~ s#^/+##; - my @paths = split(m#/+#, $path); - while (quiet_run(qw/svn ls --non-interactive/, $url)) { - my $n = shift @paths || last; - $url .= "/$n"; - } - push @repo_path_split_cache, qr/^(\Q$url\E)/; - $path = join('/',@paths); - return ($url, $path); - } + (\@linear_refs, \%parents); } -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 find_file_type_and_diff_status { + my ($path) = @_; + return ('dir', '') if $path eq ''; -} + my $diff_output = + command_oneline(qw(diff --cached --name-status --), $path) || ""; + my $diff_status = (split(' ', $diff_output))[0] || ""; -sub assert_svn_wc_clean { - return if $_use_lib; - my ($svn_rev) = @_; - croak "$svn_rev is not an integer!\n" unless ($svn_rev =~ /^\d+$/); - my $lcr = svn_info('.')->{'Last Changed Rev'}; - if ($svn_rev != $lcr) { - print STDERR "Checking for copy-tree ... "; - my @diff = grep(/^Index: /,(safe_qx(qw(svn diff), - "-r$lcr:$svn_rev"))); - if (@diff) { - croak "Nope! Expected r$svn_rev, got r$lcr\n"; - } else { - print STDERR "OK!\n"; - } - } - my @status = grep(!/^Performing status on external/,(`svn status`)); - @status = grep(!/^\s*$/,@status); - @status = grep(!/^X/,@status) if $_no_ignore_ext; - if (scalar @status) { - print STDERR "Tree ($SVN_WC) is not clean:\n"; - print STDERR $_ foreach @status; - croak; + my $ls_tree = command_oneline(qw(ls-tree HEAD), $path) || ""; + + return (undef, undef) if !$diff_status && !$ls_tree; + + if ($diff_status eq "A") { + return ("link", $diff_status) if -l $path; + return ("dir", $diff_status) if -d $path; + return ("file", $diff_status); } + + my $mode = (split(' ', $ls_tree))[0] || ""; + + return ("link", $diff_status) if $mode eq "120000"; + return ("dir", $diff_status) if $mode eq "040000"; + return ("file", $diff_status); } -sub get_tree_from_treeish { - my ($treeish) = @_; - croak "Not a sha1: $treeish\n" unless $treeish =~ /^$sha1$/o; - chomp(my $type = `git-cat-file -t $treeish`); - my $expected; - while ($type eq 'tag') { - chomp(($treeish, $type) = `git-cat-file tag $treeish`); - } - if ($type eq 'commit') { - $expected = (grep /^tree /,`git-cat-file commit $treeish`)[0]; - ($expected) = ($expected =~ /^tree ($sha1)$/); - die "Unable to get tree from $treeish\n" unless $expected; - } elsif ($type eq 'tree') { - $expected = $treeish; +sub md5sum { + my $arg = shift; + my $ref = ref $arg; + my $md5 = Digest::MD5->new(); + if ($ref eq 'GLOB' || $ref eq 'IO::File' || $ref eq 'File::Temp') { + $md5->addfile($arg) or croak $!; + } elsif ($ref eq 'SCALAR') { + $md5->add($$arg) or croak $!; + } elsif (!$ref) { + $md5->add($arg) or croak $!; } else { - die "$treeish is a $type, expected tree, tag or commit\n"; + ::fatal "Can't provide MD5 hash for unknown ref type: '", $ref, "'"; } - return $expected; + return $md5->hexdigest(); } -sub assert_tree { - return if $_use_lib; - my ($treeish) = @_; - my $expected = get_tree_from_treeish($treeish); +sub gc_directory { + if ($can_compress && -f $_ && basename($_) eq "unhandled.log") { + my $out_filename = $_ . ".gz"; + open my $in_fh, "<", $_ or die "Unable to open $_: $!\n"; + binmode $in_fh; + my $gz = Compress::Zlib::gzopen($out_filename, "ab") or + die "Unable to open $out_filename: $!\n"; - my $tmpindex = $GIT_SVN_INDEX.'.assert-tmp'; - if (-e $tmpindex) { - unlink $tmpindex or croak $!; - } - my $old_index = set_index($tmpindex); - index_changes(1); - chomp(my $tree = `git-write-tree`); - restore_index($old_index); - if ($tree ne $expected) { - croak "Tree mismatch, Got: $tree, Expected: $expected\n"; + my $res; + while ($res = sysread($in_fh, my $str, 1024)) { + $gz->gzwrite($str) or + die "Unable to write: ".$gz->gzerror()."!\n"; + } + unlink $_ or die "unlink $File::Find::name: $!\n"; + } elsif (-f $_ && basename($_) eq "index") { + unlink $_ or die "unlink $_: $!\n"; } - unlink $tmpindex; } -sub parse_diff_tree { - my $diff_fh = shift; - local $/ = "\0"; - my $state = 'meta'; - my @mods; - while (<$diff_fh>) { - chomp $_; # this gets rid of the trailing "\0" - if ($state eq 'meta' && /^:(\d{6})\s(\d{6})\s - $sha1\s($sha1)\s([MTCRAD])\d*$/xo) { - push @mods, { mode_a => $1, mode_b => $2, - sha1_b => $3, chg => $4 }; - if ($4 =~ /^(?:C|R)$/) { - $state = 'file_a'; +package Git::SVN; +use strict; +use warnings; +use Fcntl qw/:DEFAULT :seek/; +use constant rev_map_fmt => 'NH40'; +use vars qw/$default_repo_id $default_ref_id $_no_metadata $_follow_parent + $_repack $_repack_flags $_use_svm_props $_head + $_use_svnsync_props $no_reuse_existing $_minimize_url + $_use_log_author $_add_author_from $_localtime/; +use Carp qw/croak/; +use File::Path qw/mkpath/; +use File::Copy qw/copy/; +use IPC::Open3; +use Memoize; # core since 5.8.0, Jul 2002 +use Memoize::Storable; + +my ($_gc_nr, $_gc_period); + +# properties that we do not log: +my %SKIP_PROP; +BEGIN { + %SKIP_PROP = map { $_ => 1 } qw/svn:wc:ra_dav:version-url + svn:special svn:executable + svn:entry:committed-rev + 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 + no strict 'refs'; + for my $option (qw/follow_parent no_metadata use_svm_props + use_svnsync_props/) { + my $key = $option; + $key =~ tr/_//d; + my $prop = "-$option"; + *$option = sub { + my ($self) = @_; + return $self->{$prop} if exists $self->{$prop}; + my $k = "svn-remote.$self->{repo_id}.$key"; + eval { command_oneline(qw/config --get/, $k) }; + if ($@) { + $self->{$prop} = ${"Git::SVN::_$option"}; } else { - $state = 'file_b'; + my $v = command_oneline(qw/config --bool/,$k); + $self->{$prop} = $v eq 'false' ? 0 : 1; } - } elsif ($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"; + return $self->{$prop}; } } - close $diff_fh or croak $?; +} - return \@mods; + +my (%LOCKFILES, %INDEX_FILES); +END { + unlink keys %LOCKFILES if %LOCKFILES; + unlink keys %INDEX_FILES if %INDEX_FILES; } -sub svn_check_prop_executable { - my $m = shift; - return if -l $m->{file_b}; - if ($m->{mode_b} =~ /755$/) { - chmod((0755 &~ umask),$m->{file_b}) or croak $!; - if ($m->{mode_a} !~ /755$/) { - sys(qw(svn propset svn:executable 1), $m->{file_b}); +sub resolve_local_globs { + my ($url, $fetch, $glob_spec) = @_; + return unless defined $glob_spec; + my $ref = $glob_spec->{ref}; + my $path = $glob_spec->{path}; + foreach (command(qw#for-each-ref --format=%(refname) refs/#)) { + next unless m#^$ref->{regex}$#; + my $p = $1; + my $pathname = desanitize_refname($path->full_path($p)); + my $refname = desanitize_refname($ref->full_path($p)); + if (my $existing = $fetch->{$pathname}) { + if ($existing ne $refname) { + die "Refspec conflict:\n", + "existing: $existing\n", + " globbed: $refname\n"; + } + my $u = (::cmt_metadata("$refname"))[0]; + $u =~ s!^\Q$url\E(/|$)!! or die + "$refname: '$url' not found in '$u'\n"; + if ($pathname ne $u) { + warn "W: Refspec glob conflict ", + "(ref: $refname):\n", + "expected path: $pathname\n", + " real path: $u\n", + "Continuing ahead with $u\n"; + next; + } + } else { + $fetch->{$pathname} = $refname; } - -x $m->{file_b} or croak "$m->{file_b} is not executable!\n"; - } elsif ($m->{mode_b} !~ /755$/ && $m->{mode_a} =~ /755$/) { - sys(qw(svn propdel svn:executable), $m->{file_b}); - chmod((0644 &~ umask),$m->{file_b}) or croak $!; - -x $m->{file_b} and croak "$m->{file_b} is executable!\n"; } } -sub svn_ensure_parent_path { - my $dir_b = dirname(shift); - svn_ensure_parent_path($dir_b) if ($dir_b ne File::Spec->curdir); - mkpath([$dir_b]) unless (-d $dir_b); - sys(qw(svn add -N), $dir_b) unless (-d "$dir_b/.svn"); -} +sub 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; + + # ignore errors, $head revision may not even exist anymore + eval { $ra->get_log("", $head, 0, 1, 0, 1, sub { $head = $_[1] }) }; + warn "W: $@\n" if $@; + + 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; + } + } -sub precommit_check { - my $mods = shift; - my (%rm_file, %rmdir_check, %added_check); + if ($fetch) { + foreach my $p (sort keys %$fetch) { + my $gs = Git::SVN->new($fetch->{$p}, $repo_id, $p); + my $lr = $gs->rev_map_max; + if (defined $lr) { + $base = $lr if ($lr < $base); + } + push @gs, $gs; + } + } - my %o = ( D => 0, R => 1, C => 2, A => 3, M => 3, T => 3 ); - foreach my $m (sort { $o{$a->{chg}} <=> $o{$b->{chg}} } @$mods) { - if ($m->{chg} eq 'R') { - if (-d $m->{file_b}) { - err_dir_to_file("$m->{file_a} => $m->{file_b}"); - } - # dir/$file => dir/file/$file - my $dirname = dirname($m->{file_b}); - while ($dirname ne File::Spec->curdir) { - if ($dirname ne $m->{file_a}) { - $dirname = dirname($dirname); - next; - } - err_file_to_dir("$m->{file_a} => $m->{file_b}"); + ($base, $head) = parse_revision_argument($base, $head); + $ra->gs_fetch_loop_common($base, $head, \@gs, \@globs); +} + +sub read_all_remotes { + my $r = {}; + my $use_svm_props = eval { command_oneline(qw/config --bool + svn.useSvmProps/) }; + $use_svm_props = $use_svm_props eq 'true' if $use_svm_props; + my $svn_refspec = qr{\s*(.*?)\s*:\s*(.+?)\s*}; + foreach (grep { s/^svn-remote\.// } command(qw/config -l/)) { + if (m!^(.+)\.fetch=$svn_refspec$!) { + my ($remote, $local_ref, $remote_ref) = ($1, $2, $3); + die("svn-remote.$remote: remote ref '$remote_ref' " + . "must start with 'refs/'\n") + unless $remote_ref =~ m{^refs/}; + $local_ref = uri_decode($local_ref); + $r->{$remote}->{fetch}->{$local_ref} = $remote_ref; + $r->{$remote}->{svm} = {} if $use_svm_props; + } elsif (m!^(.+)\.usesvmprops=\s*(.*)\s*$!) { + $r->{$1}->{svm} = {}; + } elsif (m!^(.+)\.url=\s*(.*)\s*$!) { + $r->{$1}->{url} = $2; + } elsif (m!^(.+)\.pushurl=\s*(.*)\s*$!) { + $r->{$1}->{pushurl} = $2; + } elsif (m!^(.+)\.ignore-refs=\s*(.*)\s*$!) { + $r->{$1}->{ignore_refs_regex} = $2; + } elsif (m!^(.+)\.(branches|tags)=$svn_refspec$!) { + my ($remote, $t, $local_ref, $remote_ref) = + ($1, $2, $3, $4); + die("svn-remote.$remote: remote ref '$remote_ref' ($t) " + . "must start with 'refs/'\n") + unless $remote_ref =~ m{^refs/}; + $local_ref = uri_decode($local_ref); + my $rs = { + t => $t, + remote => $remote, + path => Git::SVN::GlobSpec->new($local_ref, 1), + ref => Git::SVN::GlobSpec->new($remote_ref, 0) }; + if (length($rs->{ref}->{right}) != 0) { + die "The '*' glob character must be the last ", + "character of '$remote_ref'\n"; } - # baz/zzz => baz (baz is a file) - $dirname = dirname($m->{file_a}); - while ($dirname ne File::Spec->curdir) { - if ($dirname ne $m->{file_b}) { - $dirname = dirname($dirname); - next; - } - err_dir_to_file("$m->{file_a} => $m->{file_b}"); - } - } - if ($m->{chg} =~ /^(D|R)$/) { - my $t = $1 eq 'D' ? 'file_b' : 'file_a'; - $rm_file{ $m->{$t} } = 1; - my $dirname = dirname( $m->{$t} ); - my $basename = basename( $m->{$t} ); - $rmdir_check{$dirname}->{$basename} = 1; - } elsif ($m->{chg} =~ /^(?:A|C)$/) { - if (-d $m->{file_b}) { - err_dir_to_file($m->{file_b}); - } - my $dirname = dirname( $m->{file_b} ); - my $basename = basename( $m->{file_b} ); - $added_check{$dirname}->{$basename} = 1; - while ($dirname ne File::Spec->curdir) { - if ($rm_file{$dirname}) { - err_file_to_dir($m->{file_b}); + push @{ $r->{$remote}->{$t} }, $rs; + } + } + + map { + if (defined $r->{$_}->{svm}) { + my $svm; + eval { + my $section = "svn-remote.$_"; + $svm = { + source => tmp_config('--get', + "$section.svm-source"), + replace => tmp_config('--get', + "$section.svm-replace"), } - $dirname = dirname $dirname; + }; + $r->{$_}->{svm} = $svm; + } + } keys %$r; + + foreach my $remote (keys %$r) { + foreach ( grep { defined $_ } + map { $r->{$remote}->{$_} } qw(branches tags) ) { + foreach my $rs ( @$_ ) { + $rs->{ignore_refs_regex} = + $r->{$remote}->{ignore_refs_regex}; } } } - return (\%rmdir_check, \%added_check); - sub err_dir_to_file { - my $file = shift; - print STDERR "Node change from directory to file ", - "is not supported by Subversion: ",$file,"\n"; - exit 1; - } - sub err_file_to_dir { - my $file = shift; - print STDERR "Node change from file to directory ", - "is not supported by Subversion: ",$file,"\n"; - exit 1; - } + $r; } +sub init_vars { + $_gc_nr = $_gc_period = 1000; + if (defined $_repack || defined $_repack_flags) { + warn "Repack options are obsolete; they have no effect.\n"; + } +} -sub get_diff { - my ($from, $treeish) = @_; - assert_tree($from); - print "diff-tree $from $treeish\n"; - my $pid = open my $diff_fh, '-|'; - defined $pid or croak $!; - if ($pid == 0) { - my @diff_tree = qw(git-diff-tree -z -r); - if ($_cp_similarity) { - push @diff_tree, "-C$_cp_similarity"; - } else { - push @diff_tree, '-C'; +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} = $_; } - push @diff_tree, '--find-copies-harder' if $_find_copies_harder; - push @diff_tree, "-l$_l" if defined $_l; - exec(@diff_tree, $from, $treeish) or croak $!; } - return parse_diff_tree($diff_fh); } -sub svn_checkout_tree { - my ($from, $treeish) = @_; - my $mods = get_diff($from->{commit}, $treeish); - return $mods unless (scalar @$mods); - my ($rm, $add) = precommit_check($mods); +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; +} - my %o = ( D => 1, R => 0, C => -1, A => 3, M => 3, T => 3 ); - foreach my $m (sort { $o{$a->{chg}} <=> $o{$b->{chg}} } @$mods) { - if ($m->{chg} eq 'C') { - svn_ensure_parent_path( $m->{file_b} ); - sys(qw(svn cp), $m->{file_a}, $m->{file_b}); - apply_mod_line_blob($m); - svn_check_prop_executable($m); - } elsif ($m->{chg} eq 'D') { - sys(qw(svn rm --force), $m->{file_b}); - } elsif ($m->{chg} eq 'R') { - svn_ensure_parent_path( $m->{file_b} ); - sys(qw(svn mv --force), $m->{file_a}, $m->{file_b}); - apply_mod_line_blob($m); - svn_check_prop_executable($m); - } elsif ($m->{chg} eq 'M') { - apply_mod_line_blob($m); - svn_check_prop_executable($m); - } elsif ($m->{chg} eq 'T') { - svn_check_prop_executable($m); - apply_mod_line_blob($m); - if ($m->{mode_a} =~ /^120/ && $m->{mode_b} !~ /^120/) { - sys(qw(svn propdel svn:special), $m->{file_b}); - } else { - sys(qw(svn propset svn:special *),$m->{file_b}); +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} = $existing; + } elsif ($_minimize_url) { + 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"; } - } elsif ($m->{chg} eq 'A') { - svn_ensure_parent_path( $m->{file_b} ); - apply_mod_line_blob($m); - sys(qw(svn add), $m->{file_b}); - svn_check_prop_executable($m); - } else { - croak "Invalid chg: $m->{chg}\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 (!$no_write && defined $xpath) { + die "svn-remote.$xrepo_id.fetch already set to track ", + "$xpath:", $self->refname, "\n"; + } + unless ($no_write) { + command_noisy('config', + "svn-remote.$self->{repo_id}.url", $url); + $self->{path} =~ s{^/}{}; + $self->{path} =~ s{%([0-9A-F]{2})}{chr hex($1)}ieg; + command_noisy('config', '--add', + "svn-remote.$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 $full_url; + remove_username($full_url); + remove_username($repos_root) if defined $repos_root; + 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; + remove_username($u); + next if defined $repos_root && $repos_root ne $u; + + my $fetch = $remotes->{$repo_id}->{fetch} || {}; + foreach my $t (qw/branches tags/) { + foreach my $globspec (@{$remotes->{$repo_id}->{$t}}) { + resolve_local_globs($u, $fetch, $globspec); + } + } + my $p = $path; + my $rwr = rewrite_root({repo_id => $repo_id}); + my $svm = $remotes->{$repo_id}->{svm} + if defined $remotes->{$repo_id}->{svm}; + unless (defined $p) { + $p = $full_url; + my $z = $u; + my $prefix = ''; + if ($rwr) { + $z = $rwr; + remove_username($z); + } elsif (defined $svm) { + $z = $svm->{source}; + $prefix = $svm->{replace}; + $prefix =~ s#^\Q$u\E(?:/|$)##; + $prefix =~ s#/$##; + } + $p =~ s#^\Q$z\E(?:/|$)#$prefix# or next; + } + foreach my $f (keys %$fetch) { + next if $f ne $p; + return Git::SVN->new($fetch->{$f}, $repo_id, $f); + } + } + undef; +} - assert_tree($treeish); - if ($_rmdir) { # remove empty directories - handle_rmdir($rm, $add); +sub init { + my ($class, $url, $path, $repo_id, $ref_id, $no_write) = @_; + my $self = _new($class, $repo_id, $ref_id, $path); + if (defined $url) { + $self->init_remote_config($url, $no_write); } - assert_tree($treeish); - return $mods; + $self; } -sub libsvn_checkout_tree { - my ($from, $treeish, $ed) = @_; - my $mods = get_diff($from, $treeish); - return $mods unless (scalar @$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) { - my $f = $m->{chg}; - if (defined $o{$f}) { - $ed->$f($m, $_q); - } else { - croak "Invalid change type: $f\n"; +sub find_ref { + my ($ref_id) = @_; + foreach (command(qw/config -l/)) { + next unless m!^svn-remote\.(.+)\.fetch= + \s*(.*?)\s*:\s*(.+?)\s*$!x; + my ($repo_id, $path, $ref) = ($1, $2, $3); + if ($ref eq $ref_id) { + $path = '' if ($path =~ m#^\./?#); + return ($repo_id, $path); } } - $ed->rmdirs($_q) if $_rmdir; - return $mods; + (undef, undef, undef); } -# svn ls doesn't work with respect to the current working tree, but what's -# in the repository. There's not even an option for it... *sigh* -# (added files don't show up and removed files remain in the ls listing) -sub svn_ls_current { - my ($dir, $rm, $add) = @_; - chomp(my @ls = safe_qx('svn','ls',$dir)); - my @ret = (); - foreach (@ls) { - s#/$##; # trailing slashes are evil - push @ret, $_ unless $rm->{$dir}->{$_}; - } - if (exists $add->{$dir}) { - push @ret, keys %{$add->{$dir}}; +sub new { + 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 $repo_id) { + die "Could not find a \"svn-remote.*.fetch\" key ", + "in the repository configuration matching: ", + "$ref_id\n"; + } } - return \@ret; + 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", + ":$ref_id\$") or + die "Failed to read \"svn-remote.$repo_id.fetch\" ", + "\":$ref_id\$\" in config\n"; + ($self->{path}, undef) = split(/\s*:\s*/, $fetch); + } + $self->{path} =~ s{/+}{/}g; + $self->{path} =~ s{\A/}{}; + $self->{path} =~ s{/\z}{}; + $self->{url} = command_oneline('config', '--get', + "svn-remote.$repo_id.url") or + die "Failed to read \"svn-remote.$repo_id.url\" in config\n"; + $self->{pushurl} = eval { command_oneline('config', '--get', + "svn-remote.$repo_id.pushurl") }; + $self->rebuild; + $self; } -sub handle_rmdir { - my ($rm, $add) = @_; - - foreach my $dir (sort {length $b <=> length $a} keys %$rm) { - my $ls = svn_ls_current($dir, $rm, $add); - next if (scalar @$ls); - sys(qw(svn rm --force),$dir); +sub refname { + my ($refname) = $_[0]->{ref_id} ; - my $dn = dirname $dir; - $rm->{ $dn }->{ basename $dir } = 1; - $ls = svn_ls_current($dn, $rm, $add); - while (scalar @$ls == 0 && $dn ne File::Spec->curdir) { - sys(qw(svn rm --force),$dn); - $dir = basename $dn; - $dn = dirname $dn; - $rm->{ $dn }->{ $dir } = 1; - $ls = svn_ls_current($dn, $rm, $add); - } + # It cannot end with a slash /, we'll throw up on this because + # SVN can't have directories with a slash in their name, either: + if ($refname =~ m{/$}) { + die "ref: '$refname' ends with a trailing slash, this is ", + "not permitted by git nor Subversion\n"; } + + # It cannot have ASCII control character space, tilde ~, caret ^, + # colon :, question-mark ?, asterisk *, space, or open bracket [ + # anywhere. + # + # Additionally, % must be escaped because it is used for escaping + # and we want our escaped refname to be reversible + $refname =~ s{([ \%~\^:\?\*\[\t])}{uc sprintf('%%%02x',ord($1))}eg; + + # no slash-separated component can begin with a dot . + # /.* becomes /%2E* + $refname =~ s{/\.}{/%2E}g; + + # It cannot have two consecutive dots .. anywhere + # .. becomes %2E%2E + $refname =~ s{\.\.}{%2E%2E}g; + + # trailing dots and .lock are not allowed + # .$ becomes %2E and .lock becomes %2Elock + $refname =~ s{\.(?=$|lock$)}{%2E}; + + # the sequence @{ is used to access the reflog + # @{ becomes %40{ + $refname =~ s{\@\{}{%40\{}g; + + return $refname; } -sub get_commit_message { - my ($commit, $commit_msg) = (@_); - my %log_msg = ( msg => '' ); - open my $msg, '>', $commit_msg or croak $!; +sub desanitize_refname { + my ($refname) = @_; + $refname =~ s{%(?:([0-9A-F]{2}))}{chr hex($1)}eg; + return $refname; +} - chomp(my $type = `git-cat-file -t $commit`); - if ($type eq 'commit' || $type eq 'tag') { - my $pid = open my $msg_fh, '-|'; - defined $pid or croak $!; +sub svm_uuid { + my ($self) = @_; + return $self->{svm}->{uuid} if $self->svm; + $self->ra; + unless ($self->{svm}) { + die "SVM UUID not cached, and reading remotely failed\n"; + } + $self->{svm}->{uuid}; +} - if ($pid == 0) { - exec('git-cat-file', $type, $commit) or croak $!; +sub svm { + my ($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"), } - my $in_msg = 0; - while (<$msg_fh>) { - if (!$in_msg) { - $in_msg = 1 if (/^\s*$/); - } elsif (/^git-svn-id: /) { - # skip this, we regenerate the correct one - # on re-fetch anyways - } else { - print $msg $_ or croak $!; - } + }; + if ($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); + + $uuid =~ m{^[0-9a-f\-]{30,}$}i + 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; } - close $msg_fh or croak $?; + $path =~ s#/?[^/]+$##; + } + 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"; } - close $msg or croak $!; + Git::SVN::Ra->new($self->{url}); +} - if ($_edit || ($type eq 'tree')) { - my $editor = $ENV{VISUAL} || $ENV{EDITOR} || 'vi'; - system($editor, $commit_msg); +sub svnsync { + my ($self) = @_; + return $self->{svnsync} if $self->{svnsync}; + + if ($self->no_metadata) { + die "Can't have both 'noMetadata' and ", + "'useSvnsyncProps' options set!\n"; + } + if ($self->rewrite_root) { + die "Can't have both 'useSvnsyncProps' and 'rewriteRoot' ", + "options set!\n"; + } + if ($self->rewrite_uuid) { + die "Can't have both 'useSvnsyncProps' and 'rewriteUUID' ", + "options set!\n"; } - # file_to_s removes all trailing newlines, so just use chomp() here: - open $msg, '<', $commit_msg or croak $!; - { local $/; chomp($log_msg{msg} = <$msg>); } - close $msg or croak $!; + my $svnsync; + # see if we have it in our config, first: + eval { + my $section = "svn-remote.$self->{repo_id}"; + + my $url = tmp_config('--get', "$section.svnsync-url"); + ($url) = ($url =~ m{^([a-z\+]+://\S+)$}) or + die "doesn't look right - svn:sync-from-url is '$url'\n"; + + my $uuid = tmp_config('--get', "$section.svnsync-uuid"); + ($uuid) = ($uuid =~ m{^([0-9a-f\-]{30,})$}i) or + die "doesn't look right - svn:sync-from-uuid is '$uuid'\n"; + + $svnsync = { url => $url, uuid => $uuid } + }; + if ($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) = ($url =~ m{^([a-z\+]+://\S+)$}) or + die "doesn't look right - svn:sync-from-url is '$url'\n"; - return \%log_msg; + my $uuid = $rp->{'svn:sync-from-uuid'} or die $err . "uuid\n"; + ($uuid) = ($uuid =~ m{^([0-9a-f\-]{30,})$}i) or + die "doesn't look right - svn:sync-from-uuid is '$uuid'\n"; + + my $section = "svn-remote.$self->{repo_id}"; + tmp_config('--add', "$section.svnsync-uuid", $uuid); + tmp_config('--add', "$section.svnsync-url", $url); + return $self->{svnsync} = { url => $url, uuid => $uuid }; } -sub set_svn_commit_env { - if (defined $LC_ALL) { - $ENV{LC_ALL} = $LC_ALL; - } else { - delete $ENV{LC_ALL}; +# this allows us to memoize our SVN::Ra UUID locally and avoid a +# remote lookup (useful for 'git svn log'). +sub ra_uuid { + my ($self) = @_; + unless ($self->{ra_uuid}) { + my $key = "svn-remote.$self->{repo_id}.uuid"; + my $uuid = eval { tmp_config('--get', $key) }; + if (!$@ && $uuid && $uuid =~ /^([a-f\d\-]{30,})$/i) { + $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}); + } } + $self->{ra_uuid}; } -sub svn_commit_tree { - my ($last, $commit) = @_; - my $commit_msg = "$GIT_SVN_DIR/.svn-commit.tmp.$$"; - my $log_msg = get_commit_message($commit, $commit_msg); - my ($oneline) = ($log_msg->{msg} =~ /([^\n\r]+)/); - print "Committing $commit: $oneline\n"; +sub _set_repos_root { + my ($self, $repos_root) = @_; + my $k = "svn-remote.$self->{repo_id}.reposRoot"; + $repos_root ||= $self->ra->{repos_root}; + tmp_config($k, $repos_root); + $repos_root; +} - set_svn_commit_env(); - my @ci_output = safe_qx(qw(svn commit -F),$commit_msg); - $ENV{LC_ALL} = 'C'; - unlink $commit_msg; - my ($committed) = ($ci_output[$#ci_output] =~ /(\d+)/); - if (!defined $committed) { - my $out = join("\n",@ci_output); - print STDERR "W: Trouble parsing \`svn commit' output:\n\n", - $out, "\n\nAssuming English locale..."; - ($committed) = ($out =~ /^Committed revision \d+\./sm); - defined $committed or die " FAILED!\n", - "Commit output failed to parse committed revision!\n", - print STDERR " OK\n"; - } - - my @svn_up = qw(svn up); - push @svn_up, '--ignore-externals' unless $_no_ignore_ext; - if ($_optimize_commits && ($committed == ($last->{revision} + 1))) { - push @svn_up, "-r$committed"; - sys(@svn_up); - my $info = svn_info('.'); - my $date = $info->{'Last Changed Date'} or die "Missing date\n"; - if ($info->{'Last Changed Rev'} != $committed) { - croak "$info->{'Last Changed Rev'} != $committed\n" - } - my ($Y,$m,$d,$H,$M,$S,$tz) = ($date =~ - /(\d{4})\-(\d\d)\-(\d\d)\s - (\d\d)\:(\d\d)\:(\d\d)\s([\-\+]\d+)/x) - or croak "Failed to parse date: $date\n"; - $log_msg->{date} = "$tz $Y-$m-$d $H:$M:$S"; - $log_msg->{author} = $info->{'Last Changed Author'}; - $log_msg->{revision} = $committed; - $log_msg->{msg} .= "\n"; - $log_msg->{parents} = [ $last->{commit} ]; - $log_msg->{commit} = git_commit($log_msg, $commit); - return $log_msg; - } - # resync immediately - push @svn_up, "-r$last->{revision}"; - sys(@svn_up); - return fetch("$committed=$commit"); -} - -sub rev_list_raw { - my (@args) = @_; - my $pid = open my $fh, '-|'; - defined $pid or croak $!; - if (!$pid) { - exec(qw/git-rev-list --pretty=raw/, @args) or croak $!; +sub repos_root { + my ($self) = @_; + my $k = "svn-remote.$self->{repo_id}.reposRoot"; + eval { tmp_config('--get', $k) } || $self->_set_repos_root; +} + +sub ra { + my ($self) = shift; + my $ra = Git::SVN::Ra->new($self->{url}); + $self->_set_repos_root($ra->{repos_root}); + 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; + } + $ra; +} + +# prop_walk(PATH, REV, SUB) +# ------------------------- +# Recursively traverse PATH at revision REV and invoke SUB for each +# directory that contains a SVN property. SUB will be invoked as +# follows: &SUB(gs, path, props); where `gs' is this instance of +# Git::SVN, `path' the path to the directory where the properties +# `props' were found. The `path' will be relative to point of checkout, +# that is, if url://repo/trunk is the current Git branch, and that +# directory contains a sub-directory `d', SUB will be invoked with `/d/' +# as `path' (note the trailing `/'). +sub prop_walk { + my ($self, $path, $rev, $sub) = @_; + + $path =~ s#^/##; + my ($dirent, undef, $props) = $self->ra->get_dir($path, $rev); + $path =~ s#^/*#/#g; + my $p = $path; + # Strip the irrelevant part of the path. + $p =~ s#^/+\Q$self->{path}\E(/|$)#/#; + # Ensure the path is terminated by a `/'. + $p =~ s#/*$#/#; + + # The properties contain all the internal SVN stuff nobody + # (usually) cares about. + my $interesting_props = 0; + foreach (keys %{$props}) { + # If it doesn't start with `svn:', it must be a + # user-defined property. + ++$interesting_props and next if $_ !~ /^svn:/; + # FIXME: Fragile, if SVN adds new public properties, + # this needs to be updated. + ++$interesting_props if /^svn:(?:ignore|keywords|executable + |eol-style|mime-type + |externals|needs-lock)$/x; + } + &$sub($self, $p, $props) if $interesting_props; + + foreach (sort keys %$dirent) { + next if $dirent->{$_}->{kind} != $SVN::Node::dir; + $self->prop_walk($self->{path} . $p . $_, $rev, $sub); } - return { fh => $fh, 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} .= $_; +sub last_rev { ($_[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) = @_; + if (defined $self->{last_rev} && defined $self->{last_commit}) { + return ($self->{last_rev}, $self->{last_commit}); + } + my $c = ::verify_ref($self->refname.'^0'); + 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, $c); } } - return ($x != $rl->{t}) ? $x : undef; + my $map_path = $self->map_path; + unless (-e $map_path) { + ($self->{last_rev}, $self->{last_commit}) = (undef, undef); + return (undef, undef); + } + my ($rev, $commit) = $self->rev_map_max(1); + ($self->{last_rev}, $self->{last_commit}) = ($rev, $commit); + return ($rev, $commit); } -# read the entire log into a temporary file (which is removed ASAP) -# and store the file handle + parser state -sub svn_log_raw { - my (@log_args) = @_; - my $log_fh = IO::File->new_tmpfile or croak $!; - my $pid = fork; - defined $pid or croak $!; - if (!$pid) { - open STDOUT, '>&', $log_fh or croak $!; - exec (qw(svn log), @log_args) or croak $! +sub get_fetch_range { + my ($self, $min, $max) = @_; + $max ||= $self->ra->get_latest_revnum; + $min ||= $self->rev_map_max; + (++$min, $max); +} + +sub tmp_config { + my (@args) = @_; + my $old_def_config = "$ENV{GIT_DIR}/svn/config"; + my $config = "$ENV{GIT_DIR}/svn/.metadata"; + if (! -f $config && -f $old_def_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}; } - waitpid $pid, 0; - croak $? if $?; - seek $log_fh, 0, 0 or croak $!; - return { state => 'sep', fh => $log_fh }; + 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}; + $@ = undef; + my @ret = eval { + my ($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]; } -sub next_log_entry { - my $log = shift; # retval of svn_log_raw() - my $ret = undef; - my $fh = $log->{fh}; +sub assert_index_clean { + my ($self, $treeish) = @_; - while (<$fh>) { - chomp; - if (/^\-{72}$/) { - if ($log->{state} eq 'msg') { - if ($ret->{lines}) { - $ret->{msg} .= $_."\n"; - unless(--$ret->{lines}) { - $log->{state} = 'sep'; - } - } else { - croak "Log parse error at: $_\n", - $ret->{revision}, - "\n"; - } - next; - } - if ($log->{state} ne 'sep') { - croak "Log parse error at: $_\n", - "state: $log->{state}\n", - $ret->{revision}, - "\n"; - } - $log->{state} = 'rev'; + $self->tmp_index_do(sub { + command_noisy('read-tree', $treeish) unless -e $self->{index}; + my $x = command_oneline('write-tree'); + my ($y) = (command(qw/cat-file commit/, $treeish) =~ + /^tree ($::sha1)/mo); + return if $y eq $x; - # if we have an empty log message, put something there: - if ($ret) { - $ret->{msg} ||= "\n"; - delete $ret->{lines}; - return $ret; - } - next; + 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 != $x\n", + "Something is seriously wrong..."; } - if ($log->{state} eq 'rev' && s/^r(\d+)\s*\|\s*//) { - my $rev = $1; - my ($author, $date, $lines) = split(/\s*\|\s*/, $_, 3); - ($lines) = ($lines =~ /(\d+)/); - $date = '1970-01-01 00:00:00 +0000' - if ($_ignore_nodate && $date eq '(no date)'); - my ($Y,$m,$d,$H,$M,$S,$tz) = ($date =~ - /(\d{4})\-(\d\d)\-(\d\d)\s - (\d\d)\:(\d\d)\:(\d\d)\s([\-\+]\d+)/x) - or croak "Failed to parse date: $date\n"; - $ret = { revision => $rev, - date => "$tz $Y-$m-$d $H:$M:$S", - author => $author, - lines => $lines, - msg => '' }; - if (defined $_authors && ! defined $users{$author}) { - die "Author: $author not defined in ", - "$_authors file\n"; - } - $log->{state} = 'msg_start'; - next; + }); +} + +sub get_commit_parents { + my ($self, $log_entry) = @_; + my (%seen, @ret, @tmp); + # 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, $commit; } - # skip the first blank line of the message: - if ($log->{state} eq 'msg_start' && /^$/) { - $log->{state} = 'msg'; - } elsif ($log->{state} eq 'msg') { - if ($ret->{lines}) { - $ret->{msg} .= $_."\n"; - unless (--$ret->{lines}) { - $log->{state} = 'sep'; - } - } else { - croak "Log parse error at: $_\n", - $ret->{revision},"\n"; - } + } + if (my $cur = ::verify_ref($self->refname.'^0')) { + push @tmp, $cur; + } + if (my $ipd = $self->{inject_parents_dcommit}) { + if (my $commit = delete $ipd->{$log_entry->{revision}}) { + push @tmp, @$commit; } } - return $ret; + push @tmp, $_ foreach (@{$log_entry->{parents}}, @tmp); + while (my $p = shift @tmp) { + next if $seen{$p}; + $seen{$p} = 1; + push @ret, $p; + } + @ret; } -sub svn_info { - my $url = shift || $SVN_URL; - - my $pid = open my $info_fh, '-|'; - defined $pid or croak $!; - - if ($pid == 0) { - exec(qw(svn info),$url) or croak $!; +sub rewrite_root { + my ($self) = @_; + 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; +} - my $ret = {}; - # only single-lines seem to exist in svn info output - while (<$info_fh>) { - chomp $_; - if (m#^([^:]+)\s*:\s*(\S.*)$#) { - $ret->{$1} = $2; - push @{$ret->{-order}}, $1; +sub rewrite_uuid { + my ($self) = @_; + return $self->{-rewrite_uuid} if exists $self->{-rewrite_uuid}; + my $k = "svn-remote.$self->{repo_id}.rewriteUUID"; + my $rwid = eval { command_oneline(qw/config --get/, $k) }; + if ($rwid) { + $rwid =~ s#/+$##; + if ($rwid !~ m#^[a-f0-9]{8}-(?:[a-f0-9]{4}-){3}[a-f0-9]{12}$#) { + die "$rwid is not a valid UUID (key: $k)\n"; } } - close $info_fh or croak $?; - return $ret; + $self->{-rewrite_uuid} = $rwid; } -sub sys { system(@_) == 0 or croak $? } - -sub do_update_index { - my ($z_cmd, $cmd, $no_text_base) = @_; - - my $z = open my $p, '-|'; - defined $z or croak $!; - unless ($z) { exec @$z_cmd or croak $! } - - my $pid = open my $ui, '|-'; - defined $pid or croak $!; - unless ($pid) { - exec('git-update-index',"--$cmd",'-z','--stdin') or croak $!; - } - local $/ = "\0"; - while (my $x = <$p>) { - chomp $x; - if (!$no_text_base && lstat $x && ! -l _ && - svn_propget_base('svn:keywords', $x)) { - my $mode = -x _ ? 0755 : 0644; - my ($v,$d,$f) = File::Spec->splitpath($x); - my $tb = File::Spec->catfile($d, '.svn', 'tmp', - 'text-base',"$f.svn-base"); - $tb =~ s#^/##; - unless (-f $tb) { - $tb = File::Spec->catfile($d, '.svn', - 'text-base',"$f.svn-base"); - $tb =~ s#^/##; - } - my @s = stat($x); - unlink $x or croak $!; - copy($tb, $x); - chmod(($mode &~ umask), $x) or croak $!; - utime $s[8], $s[9], $x; - } - print $ui $x,"\0"; - } - close $ui or croak $?; -} - -sub index_changes { - return if $_use_lib; - - if (!-f "$GIT_SVN_DIR/info/exclude") { - open my $fd, '>>', "$GIT_SVN_DIR/info/exclude" or croak $!; - print $fd '.svn',"\n"; - close $fd or croak $!; - } - my $no_text_base = shift; - do_update_index([qw/git-diff-files --name-only -z/], - 'remove', - $no_text_base); - do_update_index([qw/git-ls-files -z --others/, - "--exclude-from=$GIT_SVN_DIR/info/exclude"], - 'add', - $no_text_base); +sub metadata_url { + my ($self) = @_; + ($self->rewrite_root || $self->{url}) . + (length $self->{path} ? '/' . $self->{path} : ''); } -sub s_to_file { - my ($str, $file, $mode) = @_; - open my $fd,'>',$file or croak $!; - print $fd $str,"\n" or croak $!; - close $fd or croak $!; - chmod ($mode &~ umask, $file) if (defined $mode); +sub full_url { + my ($self) = @_; + $self->{url} . (length $self->{path} ? '/' . $self->{path} : ''); } -sub file_to_s { - my $file = shift; - open my $fd,'<',$file or croak "$!: file: $file\n"; - local $/; - my $ret = <$fd>; - close $fd or croak $!; - $ret =~ s/\s*$//s; - return $ret; +sub full_pushurl { + my ($self) = @_; + if ($self->{pushurl}) { + return $self->{pushurl} . (length $self->{path} ? '/' . + $self->{path} : ''); + } else { + return $self->full_url; + } } -sub assert_revision_unknown { - my $r = shift; - if (my $c = revdb_get($REVDB, $r)) { - croak "$r = $c already exists! Why are we refetching it?"; +sub set_commit_header_env { + my ($log_entry) = @_; + my %env; + foreach my $ned (qw/NAME EMAIL DATE/) { + foreach my $ac (qw/AUTHOR COMMITTER/) { + $env{"GIT_${ac}_${ned}"} = $ENV{"GIT_${ac}_${ned}"}; + } } + + $ENV{GIT_AUTHOR_NAME} = $log_entry->{name}; + $ENV{GIT_AUTHOR_EMAIL} = $log_entry->{email}; + $ENV{GIT_AUTHOR_DATE} = $ENV{GIT_COMMITTER_DATE} = $log_entry->{date}; + + $ENV{GIT_COMMITTER_NAME} = (defined $log_entry->{commit_name}) + ? $log_entry->{commit_name} + : $log_entry->{name}; + $ENV{GIT_COMMITTER_EMAIL} = (defined $log_entry->{commit_email}) + ? $log_entry->{commit_email} + : $log_entry->{email}; + \%env; } -sub trees_eq { - my ($x, $y) = @_; - my @x = safe_qx('git-cat-file','commit',$x); - my @y = safe_qx('git-cat-file','commit',$y); - if (($y[0] ne $x[0]) || $x[0] !~ /^tree $sha1\n$/ - || $y[0] !~ /^tree $sha1\n$/) { - print STDERR "Trees not equal: $y[0] != $x[0]\n"; - return 0 +sub restore_commit_header_env { + my ($env) = @_; + foreach my $ned (qw/NAME EMAIL DATE/) { + foreach my $ac (qw/AUTHOR COMMITTER/) { + my $k = "GIT_${ac}_${ned}"; + if (defined $env->{$k}) { + $ENV{$k} = $env->{$k}; + } else { + delete $ENV{$k}; + } + } } - return 1; } -sub git_commit { - my ($log_msg, @parents) = @_; - assert_revision_unknown($log_msg->{revision}); - map_tree_joins() if (@_branch_from && !%tree_map); +sub gc { + command_noisy('gc', '--auto'); +}; - my (@tmp_parents, @exec_parents, %seen_parent); - if (my $lparents = $log_msg->{parents}) { - @tmp_parents = @$lparents +sub do_git_commit { + 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"; } - # 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_msg->{revision}) { - push @tmp_parents, $2; - } - } else { - push @tmp_parents, $p if $p =~ /$sha1_short/o; - } + if (my $c = $self->rev_map_get($log_entry->{revision})) { + croak "$log_entry->{revision} = $c already exists! ", + "Why are we refetching it?\n"; } - my $tree = $log_msg->{tree}; + my $old_env = set_commit_header_env($log_entry); + my $tree = $log_entry->{tree}; if (!defined $tree) { - my $index = set_index($GIT_SVN_INDEX); - index_changes(); - chomp($tree = `git-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 $cur = eval { file_to_s("$GIT_DIR/refs/remotes/$GIT_SVN") }) { - 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 { - safe_qx('git-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_msg->{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; + $tree = $self->tmp_index_do(sub { + command_oneline('write-tree') }); } + die "Tree is not a valid sha1: $tree\n" if $tree !~ /^$::sha1$/o; - set_commit_env($log_msg); - my @exec = ('git-commit-tree', $tree); - push @exec, '-p', $_ foreach @exec_parents; + my @exec = ('git', 'commit-tree', $tree); + foreach ($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_msg->{msg} or croak $!; - unless ($_no_metadata) { - print $msg_fh "\ngit-svn-id: $SVN_URL\@$log_msg->{revision}", - " $SVN_UUID\n" or croak $!; + or croak $!; + binmode $msg_fh; + + # we always get UTF-8 from SVN, but we may want our commits in + # a different encoding. + if (my $enc = Git::config('i18n.commitencoding')) { + require Encode; + Encode::from_to($log_entry->{log}, 'UTF-8', $enc); + } + print $msg_fh $log_entry->{log} or croak $!; + restore_commit_header_env($old_env); + 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 $!; @@ -2065,675 +3019,1298 @@ sub git_commit { close $out_fh or croak $!; waitpid $pid, 0; croak $? if $?; - if ($commit !~ /^$sha1$/o) { + if ($commit !~ /^$::sha1$/o) { die "Failed to commit, invalid sha1: $commit\n"; } - sys('git-update-ref',"refs/remotes/$GIT_SVN",$commit); - revdb_set($REVDB, $log_msg->{revision}, $commit); - # this output is read via pipe, do not change: - print "r$log_msg->{revision} = $commit\n"; - check_repack(); + $self->rev_map_set($log_entry->{revision}, $commit, 1); + + $self->{last_rev} = $log_entry->{revision}; + $self->{last_commit} = $commit; + print "r$log_entry->{revision}" unless $::_q > 1; + if (defined $log_entry->{svm_revision}) { + print " (\@$log_entry->{svm_revision})" unless $::_q > 1; + $self->rev_map_set($log_entry->{svm_revision}, $commit, + 0, $self->svm_uuid); + } + print " = $commit ($self->{ref_id})\n" unless $::_q > 1; + if (--$_gc_nr == 0) { + $_gc_nr = $_gc_period; + gc(); + } return $commit; } -sub check_repack { - if ($_repack && (--$_repack_nr == 0)) { - $_repack_nr = $_repack; - sys("git repack $_repack_flags"); +sub match_paths { + my ($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) == + $SVN::Node::dir) { + return 1; + } } + return 0; } -sub set_commit_env { - my ($log_msg) = @_; - my $author = $log_msg->{author}; - if (!defined $author || length $author == 0) { - $author = '(no author)'; +sub find_parent_branch { + my ($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 = $_[0] }); + $SVN::Error::handler = $err_handler; } - my ($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_msg->{date}; -} + return undef unless defined $paths; -sub apply_mod_line_blob { - my $m = shift; - if ($m->{mode_b} =~ /^120/) { - blob_to_symlink($m->{sha1_b}, $m->{file_b}); - } else { - blob_to_file($m->{sha1_b}, $m->{file_b}); + # look for a parent from another branch: + my @b_path_components = split m#/#, $self->{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 = $url . $branch_from; + print STDERR "Found possible branch point: ", + "$new_url => ", $self->full_url, ", $r\n" + unless $::_q > 1; + $branch_from =~ s#^/##; + my $gs = $self->other_gs($new_url, $url, + $branch_from, $r, $self->{ref_id}); + my ($r0, $parent) = $gs->find_rev_before($r, 1); + { + my ($base, $head); + if (!defined $r0 || !defined $parent) { + ($base, $head) = parse_revision_argument(0, $r); + } else { + if ($r0 < $r) { + $gs->ra->get_log([$gs->{path}], $r0 + 1, $r, 1, + 0, 1, sub { $base = $_[1] - 1 }); + } + } + if (defined $base && $base <= $r) { + $gs->fetch($base, $r); + } + ($r0, $parent) = $gs->find_rev_before($r, 1); + } + if (defined $r0 && defined $parent) { + print STDERR "Found branch parent: ($self->{ref_id}) $parent\n" + unless $::_q > 1; + my $ed; + if ($self->ra->can_do_switch) { + $self->assert_index_clean($parent); + print STDERR "Following parent with do_switch\n" + unless $::_q > 1; + # 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_rev} = $r0; + $self->{last_commit} = $parent; + $ed = SVN::Git::Fetcher->new($self, $gs->{path}); + $gs->ra->gs_do_switch($r0, $rev, $gs, + $self->full_url, $ed) + or die "SVN connection failed somewhere...\n"; + } elsif ($self->ra->trees_match($new_url, $r0, + $self->full_url, $rev)) { + print STDERR "Trees match:\n", + " $new_url\@$r0\n", + " ${\$self->full_url}\@$rev\n", + "Following parent with no changes\n" + unless $::_q > 1; + $self->tmp_index_do(sub { + command_noisy('read-tree', $parent); + }); + $self->{last_commit} = $parent; + } else { + print STDERR "Following parent with do_update\n" + unless $::_q > 1; + $ed = SVN::Git::Fetcher->new($self); + $self->ra->gs_do_update($rev, $rev, $self, $ed) + or die "SVN connection failed somewhere...\n"; + } + print STDERR "Successfully followed parent\n" unless $::_q > 1; + return $self->make_log_entry($rev, [$parent], $ed); } + return undef; } -sub blob_to_symlink { - my ($blob, $link) = @_; - defined $link or croak "\$link not defined!\n"; - croak "Not a sha1: $blob\n" unless $blob =~ /^$sha1$/o; - if (-l $link || -f _) { - unlink $link or croak $!; +sub do_fetch { + my ($self, $paths, $rev) = @_; + my $ed; + my ($last_rev, @parents); + 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} = $lc; + @parents = ($lc); + } else { + $last_rev = $rev; + if (my $log_entry = $self->find_parent_branch($paths, $rev)) { + return $log_entry; + } + $ed = SVN::Git::Fetcher->new($self); } - - my $dest = `git-cat-file blob $blob`; # no newline, so no chomp - symlink $dest, $link or croak $!; + unless ($self->ra->gs_do_update($last_rev, $rev, $self, $ed)) { + die "SVN connection failed somewhere...\n"; + } + $self->make_log_entry($rev, \@parents, $ed); } -sub blob_to_file { - my ($blob, $file) = @_; - defined $file or croak "\$file not defined!\n"; - croak "Not a sha1: $blob\n" unless $blob =~ /^$sha1$/o; - if (-l $file || -f _) { - unlink $file or croak $!; - } +sub mkemptydirs { + my ($self, $r) = @_; - open my $blob_fh, '>', $file or croak "$!: $file\n"; - my $pid = fork; - defined $pid or croak $!; + sub scan { + my ($r, $empty_dirs, $line) = @_; + if (defined $r && $line =~ /^r(\d+)$/) { + return 0 if $1 > $r; + } elsif ($line =~ /^ \+empty_dir: (.+)$/) { + $empty_dirs->{$1} = 1; + } elsif ($line =~ /^ \-empty_dir: (.+)$/) { + my @d = grep {m[^\Q$1\E(/|$)]} (keys %$empty_dirs); + delete @$empty_dirs{@d}; + } + 1; # continue + }; - if ($pid == 0) { - open STDOUT, '>&', $blob_fh or croak $!; - exec('git-cat-file','blob',$blob) or croak $!; + my %empty_dirs = (); + my $gz_file = "$self->{dir}/unhandled.log.gz"; + if (-f $gz_file) { + if (!$can_compress) { + warn "Compress::Zlib could not be found; ", + "empty directories in $gz_file will not be read\n"; + } else { + my $gz = Compress::Zlib::gzopen($gz_file, "rb") or + die "Unable to open $gz_file: $!\n"; + my $line; + while ($gz->gzreadline($line) > 0) { + scan($r, \%empty_dirs, $line) or last; + } + $gz->gzclose; + } } - waitpid $pid, 0; - croak $? if $?; - close $blob_fh or croak $!; -} + if (open my $fh, '<', "$self->{dir}/unhandled.log") { + binmode $fh or croak "binmode: $!"; + while (<$fh>) { + scan($r, \%empty_dirs, $_) or last; + } + close $fh; + } -sub safe_qx { - my $pid = open my $child, '-|'; - defined $pid or croak $!; - if ($pid == 0) { - exec(@_) or croak $!; + my $strip = qr/\A\Q$self->{path}\E(?:\/|$)/; + foreach my $d (sort keys %empty_dirs) { + $d = uri_decode($d); + $d =~ s/$strip//; + next unless length($d); + next if -d $d; + if (-e $d) { + warn "$d exists but is not a directory\n"; + } else { + print "creating empty directory: $d\n"; + mkpath([$d]); + } } - my @ret = (<$child>); - close $child or croak $?; - die $? if $?; # just in case close didn't error out - return wantarray ? @ret : join('',@ret); } -sub svn_compat_check { - if ($_follow_parent) { - print STDERR 'E: --follow-parent functionality is only ', - "available when SVN libraries are used\n"; - exit 1; - } - my @co_help = safe_qx(qw(svn co -h)); - unless (grep /ignore-externals/,@co_help) { - print STDERR "W: Installed svn version does not support ", - "--ignore-externals\n"; - $_no_ignore_ext = 1; - } - if (grep /usage: checkout URL\[\@REV\]/,@co_help) { - $_svn_co_url_revs = 1; +sub get_untracked { + my ($self, $ed) = @_; + my @out; + my $h = $ed->{empty}; + foreach (sort keys %$h) { + my $act = $h->{$_} ? '+empty_dir' : '-empty_dir'; + push @out, " $act: " . uri_encode($_); + warn "W: $act: $_\n"; + } + foreach my $t (qw/dir_prop file_prop/) { + $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 $SKIP_PROP{$prop}; + my $v = $h->{$path}->{$prop}; + my $t_ppath_prop = "$t: " . + uri_encode($ppath) . ' ' . + uri_encode($prop); + if (defined $v) { + push @out, " +$t_ppath_prop " . + uri_encode($v); + } else { + push @out, " -$t_ppath_prop"; + } + } + } } - if (grep /\[TARGET\[\@REV\]\.\.\.\]/, `svn propget -h`) { - $_svn_pg_peg_revs = 1; + foreach my $t (qw/absent_file absent_directory/) { + $h = $ed->{$t} or next; + foreach my $parent (sort keys %$h) { + foreach my $path (sort @{$h->{$parent}}) { + push @out, " $t: " . + uri_encode("$parent/$path"); + warn "W: $t: $parent/$path ", + "Insufficient permissions?\n"; + } + } } + \@out; +} - # I really, really hope nobody hits this... - unless (grep /stop-on-copy/, (safe_qx(qw(svn log -h)))) { - print STDERR <<''; -W: The installed svn version does not support the --stop-on-copy flag in - the log command. - Lets hope the directory you're tracking is not a branch or tag - and was never moved within the repository... +# parse_svn_date(DATE) +# -------------------- +# Given a date (in UTC) from Subversion, return a string in the format +# "<TZ Offset> <local date/time>" that Git will use. +# +# By default the parsed date will be in UTC; if $Git::SVN::_localtime +# is true we'll convert it to the local timezone instead. +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"; + my $parsed_date; # Set next. + + if ($Git::SVN::_localtime) { + # Translate the Subversion datetime to an epoch time. + # Begin by switching ourselves to $date's timezone, UTC. + my $old_env_TZ = $ENV{TZ}; + $ENV{TZ} = 'UTC'; + + my $epoch_in_UTC = + POSIX::strftime('%s', $S, $M, $H, $d, $m - 1, $Y - 1900); + + # Determine our local timezone (including DST) at the + # time of $epoch_in_UTC. $Git::SVN::Log::TZ stored the + # value of TZ, if any, at the time we were run. + if (defined $Git::SVN::Log::TZ) { + $ENV{TZ} = $Git::SVN::Log::TZ; + } else { + delete $ENV{TZ}; + } - $_no_stop_copy = 1; - } -} + my $our_TZ = + POSIX::strftime('%Z', $S, $M, $H, $d, $m - 1, $Y - 1900); + + # This converts $epoch_in_UTC into our local timezone. + my ($sec, $min, $hour, $mday, $mon, $year, + $wday, $yday, $isdst) = localtime($epoch_in_UTC); + + $parsed_date = sprintf('%s %04d-%02d-%02d %02d:%02d:%02d', + $our_TZ, $year + 1900, $mon + 1, + $mday, $hour, $min, $sec); -# *sigh*, new versions of svn won't honor -r<rev> without URL@<rev>, -# (and they won't honor URL@<rev> without -r<rev>, too!) -sub svn_cmd_checkout { - my ($url, $rev, $dir) = @_; - my @cmd = ('svn','co', "-r$rev"); - push @cmd, '--ignore-externals' unless $_no_ignore_ext; - $url .= "\@$rev" if $_svn_co_url_revs; - sys(@cmd, $url, $dir); + # Reset us to the timezone in effect when we entered + # this routine. + if (defined $old_env_TZ) { + $ENV{TZ} = $old_env_TZ; + } else { + delete $ENV{TZ}; + } + } else { + $parsed_date = "+0000 $Y-$m-$d $H:$M:$S"; + } + + return $parsed_date; +} + +sub other_gs { + my ($self, $new_url, $url, + $branch_from, $r, $old_ref_id) = @_; + my $gs = Git::SVN->find_by_url($new_url, $url, $branch_from); + unless ($gs) { + my $ref_id = $old_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); + my ($u, $p, $repo_id) = ($new_url, '', $ref_id); + if ($u =~ s#^\Q$url\E(/|$)##) { + $p = $u; + $u = $url; + $repo_id = $self->{repo_id}; + } + while (1) { + # It is possible to tag two different subdirectories at + # the same revision. If the url for an existing ref + # does not match, we must either find a ref with a + # matching url or create a new ref by growing a tail. + $gs = Git::SVN->init($u, $p, $repo_id, $ref_id, 1); + my (undef, $max_commit) = $gs->rev_map_max(1); + last if (!$max_commit); + my ($url) = ::cmt_metadata($max_commit); + last if ($url eq $gs->metadata_url); + $ref_id .= '-'; + } + print STDERR "Initializing parent: $ref_id\n" unless $::_q > 1; + } + $gs } -sub check_upgrade_needed { - if (!-r $REVDB) { - -d $GIT_SVN_DIR or mkpath([$GIT_SVN_DIR]); - open my $fh, '>>',$REVDB or croak $!; - close $fh; +sub call_authors_prog { + my ($orig_author) = @_; + $orig_author = command_oneline('rev-parse', '--sq-quote', $orig_author); + my $author = `$::_authors_prog $orig_author`; + if ($? != 0) { + die "$::_authors_prog failed with exit code $?\n" } - my $old = eval { - my $pid = open my $child, '-|'; - defined $pid or croak $!; - if ($pid == 0) { - close STDERR; - exec('git-rev-parse',"$GIT_SVN-HEAD") or croak $!; - } - my @ret = (<$child>); - close $child or croak $?; - die $? if $?; # just in case close didn't error out - return wantarray ? @ret : join('',@ret); - }; - return unless $old; - my $head = eval { safe_qx('git-rev-parse',"refs/remotes/$GIT_SVN") }; - if ($@ || !$head) { - print STDERR "Please run: $0 rebuild --upgrade\n"; - exit 1; + if ($author =~ /^\s*(.+?)\s*<(.*)>\s*$/) { + my ($name, $email) = ($1, $2); + $email = undef if length $2 == 0; + return [$name, $email]; + } else { + die "Author: $orig_author: $::_authors_prog returned " + . "invalid author format: $author\n"; } } -# 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 $pid = open my $pipe, '-|'; - defined $pid or croak $!; - if ($pid == 0) { - exec(qw(git-rev-list --topo-order --pretty=raw), $br) - or croak $!; - } - while (<$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; +sub check_author { + my ($author) = @_; + if (!defined $author || length $author == 0) { + $author = '(no author)'; + } + if (!defined $::users{$author}) { + if (defined $::_authors_prog) { + $::users{$author} = call_authors_prog($author); + } elsif (defined $::_authors) { + die "Author: $author not defined in $::_authors file\n"; + } + } + $author; +} + +sub find_extra_svk_parents { + my ($self, $ed, $tickets, $parents) = @_; + # aha! svk:merge property changed... + my @tickets = split "\n", $tickets; + my @known_parents; + for my $ticket ( @tickets ) { + my ($uuid, $path, $rev) = split /:/, $ticket; + if ( $uuid eq $self->ra_uuid ) { + my $url = $self->{url}; + my $repos_root = $url; + my $branch_from = $path; + $branch_from =~ s{^/}{}; + my $gs = $self->other_gs($repos_root."/".$branch_from, + $url, + $branch_from, + $rev, + $self->{ref_id}); + if ( my $commit = $gs->rev_map_get($rev, $uuid) ) { + # wahey! we found it, but it might be + # an old one (!) + push @known_parents, [ $rev, $commit ]; } } - close $pipe; # we could be breaking the pipe early + } + # Ordering matters; highest-numbered commit merge tickets + # first, as they may account for later merge ticket additions + # or changes. + @known_parents = map {$_->[1]} sort {$b->[0] <=> $a->[0]} @known_parents; + for my $parent ( @known_parents ) { + my @cmd = ('rev-list', $parent, map { "^$_" } @$parents ); + my ($msg_fh, $ctx) = command_output_pipe(@cmd); + my $new; + while ( <$msg_fh> ) { + $new=1;last; + } + command_close_pipe($msg_fh, $ctx); + if ( $new ) { + print STDERR + "Found merge parent (svk:merge ticket): $parent\n"; + push @$parents, $parent; + } } } -sub load_all_refs { - if (@_branch_from) { - print STDERR '--branch|-b parameters are ignored when ', - "--branch-all-refs|-B is passed\n"; +sub lookup_svn_merge { + my $uuid = shift; + my $url = shift; + my $merge = shift; + + my ($source, $revs) = split ":", $merge; + my $path = $source; + $path =~ s{^/}{}; + my $gs = Git::SVN->find_by_url($url.$source, $url, $path); + if ( !$gs ) { + warn "Couldn't find revmap for $url$source\n"; + return; } + my @ranges = split ",", $revs; + my ($tip, $tip_commit); + my @merged_commit_ranges; + # find the tip + for my $range ( @ranges ) { + my ($bottom, $top) = split "-", $range; + $top ||= $bottom; + my $bottom_commit = $gs->find_rev_after( $bottom, 1, $top ); + my $top_commit = $gs->find_rev_before( $top, 1, $bottom ); + + unless ($top_commit and $bottom_commit) { + warn "W:unknown path/rev in svn:mergeinfo " + ."dirprop: $source:$range\n"; + next; + } - # don't worry about rev-list on non-commit objects/tags, - # it shouldn't blow up if a ref is a blob or tree... - chomp(@_branch_from = `git-rev-parse --symbolic --all`); -} + if (scalar(command('rev-parse', "$bottom_commit^@"))) { + push @merged_commit_ranges, + "$bottom_commit^..$top_commit"; + } else { + push @merged_commit_ranges, "$top_commit"; + } -# '<svn username> = real-name <email address>' mapping based on git-svnimport: -sub load_authors { - open my $authors, '<', $_authors or die "Can't open $_authors $!\n"; - while (<$authors>) { - chomp; - next unless /^(\S+?|\(no author\))\s*=\s*(.+?)\s*<(.+)>\s*$/; - my ($user, $name, $email) = ($1, $2, $3); - $users{$user} = [$name, $email]; + if ( !defined $tip or $top > $tip ) { + $tip = $top; + $tip_commit = $top_commit; + } } - close $authors or croak $!; + return ($tip_commit, @merged_commit_ranges); } -sub rload_authors { - open my $authors, '<', $_authors or die "Can't open $_authors $!\n"; - while (<$authors>) { +sub _rev_list { + my ($msg_fh, $ctx) = command_output_pipe( + "rev-list", @_, + ); + my @rv; + while ( <$msg_fh> ) { chomp; - next unless /^(\S+?)\s*=\s*(.+?)\s*<(.+)>\s*$/; - my ($user, $name, $email) = ($1, $2, $3); - $rusers{"$name <$email>"} = $user; + push @rv, $_; } - close $authors or croak $!; + command_close_pipe($msg_fh, $ctx); + @rv; } -sub svn_propget_base { - my ($p, $f) = @_; - $f .= '@BASE' if $_svn_pg_peg_revs; - return safe_qx(qw/svn propget/, $p, $f); -} - -sub git_svn_each { - my $sub = shift; - foreach (`git-rev-parse --symbolic --all`) { - next unless s#^refs/remotes/##; - chomp $_; - next unless -f "$GIT_DIR/svn/$_/info/url"; - &$sub($_); +sub check_cherry_pick { + my $base = shift; + my $tip = shift; + my $parents = shift; + my @ranges = @_; + my %commits = map { $_ => 1 } + _rev_list("--no-merges", $tip, "--not", $base, @$parents, "--"); + for my $range ( @ranges ) { + delete @commits{_rev_list($range, "--")}; + } + for my $commit (keys %commits) { + if (has_no_changes($commit)) { + delete $commits{$commit}; + } } + return (keys %commits); } -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 has_no_changes { + my $commit = shift; -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"; + my @revs = split / /, command_oneline( + qw(rev-list --parents -1 -m), $commit); - foreach my $x (`git-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 $REVDB); - print "Done upgrading.\n"; + # Commits with no parents, e.g. the start of a partial branch, + # have changes by definition. + return 1 if (@revs < 2); + + # Commits with multiple parents, e.g a merge, have no changes + # by definition. + return 0 if (@revs > 2); + + return (command_oneline("rev-parse", "$commit^{tree}") eq + command_oneline("rev-parse", "$commit~1^{tree}")); } -sub find_rev_before { - my ($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); +# The GIT_DIR environment variable is not always set until after the command +# line arguments are processed, so we can't memoize in a BEGIN block. +{ + my $memoized = 0; + + sub memoize_svn_mergeinfo_functions { + return if $memoized; + $memoized = 1; + + my $cache_path = "$ENV{GIT_DIR}/svn/.caches/"; + mkpath([$cache_path]) unless -d $cache_path; + + tie my %lookup_svn_merge_cache => 'Memoize::Storable', + "$cache_path/lookup_svn_merge.db", 'nstore'; + memoize 'lookup_svn_merge', + SCALAR_CACHE => 'FAULT', + LIST_CACHE => ['HASH' => \%lookup_svn_merge_cache], + ; + + tie my %check_cherry_pick_cache => 'Memoize::Storable', + "$cache_path/check_cherry_pick.db", 'nstore'; + memoize 'check_cherry_pick', + SCALAR_CACHE => 'FAULT', + LIST_CACHE => ['HASH' => \%check_cherry_pick_cache], + ; + + tie my %has_no_changes_cache => 'Memoize::Storable', + "$cache_path/has_no_changes.db", 'nstore'; + memoize 'has_no_changes', + SCALAR_CACHE => ['HASH' => \%has_no_changes_cache], + LIST_CACHE => 'FAULT', + ; + } + + sub unmemoize_svn_mergeinfo_functions { + return if not $memoized; + $memoized = 0; + + Memoize::unmemoize 'lookup_svn_merge'; + Memoize::unmemoize 'check_cherry_pick'; + Memoize::unmemoize 'has_no_changes'; + } + + Memoize::memoize 'Git::SVN::repos_root'; +} + +END { + # Force cache writeout explicitly instead of waiting for + # global destruction to avoid segfault in Storable: + # http://rt.cpan.org/Public/Bug/Display.html?id=36087 + unmemoize_svn_mergeinfo_functions(); +} + +sub parents_exclude { + my $parents = shift; + my @commits = @_; + return unless @commits; + + my @excluded; + my $excluded; + do { + my @cmd = ('rev-list', "-1", @commits, "--not", @$parents ); + $excluded = command_oneline(@cmd); + if ( $excluded ) { + my @new; + my $found; + for my $commit ( @commits ) { + if ( $commit eq $excluded ) { + push @excluded, $commit; + $found++; + last; + } + else { + push @new, $commit; + } + } + die "saw commit '$excluded' in rev-list output, " + ."but we didn't ask for that commit (wanted: @commits --not @$parents)" + unless $found; + @commits = @new; } - --$r; } - return (undef, undef); + while ($excluded and @commits); + + return @excluded; } -sub init_vars { - $GIT_SVN ||= $ENV{GIT_SVN_ID} || '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; - $SVN_WC = "$GIT_SVN_DIR/tree"; - %tree_map = (); -} - -# convert GetOpt::Long specs for use by git-repo-config -sub read_repo_config { - return unless -d $GIT_DIR; - my $opts = shift; - foreach my $o (keys %$opts) { - my $v = $opts->{$o}; - my ($key) = ($o =~ /^([a-z\-]+)/); - $key =~ s/-//g; - my $arg = 'git-repo-config'; - $arg .= ' --int' if ($o =~ /[:=]i$/); - $arg .= ' --bool' if ($o !~ /[:=][sfi]$/); - if (ref $v eq 'ARRAY') { - chomp(my @tmp = `$arg --get-all svn.$key`); - @$v = @tmp if @tmp; + +# note: this function should only be called if the various dirprops +# have actually changed +sub find_extra_svn_parents { + my ($self, $ed, $mergeinfo, $parents) = @_; + # aha! svk:merge property changed... + + memoize_svn_mergeinfo_functions(); + + # We first search for merged tips which are not in our + # history. Then, we figure out which git revisions are in + # that tip, but not this revision. If all of those revisions + # are now marked as merge, we can add the tip as a parent. + my @merges = split "\n", $mergeinfo; + my @merge_tips; + my $url = $self->{url}; + my $uuid = $self->ra_uuid; + my %ranges; + for my $merge ( @merges ) { + my ($tip_commit, @ranges) = + lookup_svn_merge( $uuid, $url, $merge ); + unless (!$tip_commit or + grep { $_ eq $tip_commit } @$parents ) { + push @merge_tips, $tip_commit; + $ranges{$tip_commit} = \@ranges; } else { - chomp(my $tmp = `$arg --get svn.$key`); - if ($tmp && !($arg =~ / --bool / && $tmp eq 'false')) { - $$v = $tmp; - } + push @merge_tips, undef; } } -} -sub set_default_vals { - if (defined $_repack) { - $_repack = 1000 if ($_repack <= 0); - $_repack_nr = $_repack; - $_repack_flags ||= '-d'; + my %excluded = map { $_ => 1 } + parents_exclude($parents, grep { defined } @merge_tips); + + # check merge tips for new parents + my @new_parents; + for my $merge_tip ( @merge_tips ) { + my $spec = shift @merges; + next unless $merge_tip and $excluded{$merge_tip}; + + my $ranges = $ranges{$merge_tip}; + + # check out 'new' tips + my $merge_base; + eval { + $merge_base = command_oneline( + "merge-base", + @$parents, $merge_tip, + ); + }; + if ($@) { + die "An error occurred during merge-base" + unless $@->isa("Git::Error::Command"); + + warn "W: Cannot find common ancestor between ". + "@$parents and $merge_tip. Ignoring merge info.\n"; + next; + } + + # double check that there are no missing non-merge commits + my (@incomplete) = check_cherry_pick( + $merge_base, $merge_tip, + $parents, + @$ranges, + ); + + if ( @incomplete ) { + warn "W:svn cherry-pick ignored ($spec) - missing " + .@incomplete." commit(s) (eg $incomplete[0])\n"; + } else { + warn + "Found merge parent (svn:mergeinfo prop): ", + $merge_tip, "\n"; + push @new_parents, $merge_tip; + } } -} -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; + # cater for merges which merge commits from multiple branches + if ( @new_parents > 1 ) { + for ( my $i = 0; $i <= $#new_parents; $i++ ) { + for ( my $j = 0; $j <= $#new_parents; $j++ ) { + next if $i == $j; + next unless $new_parents[$i]; + next unless $new_parents[$j]; + my $revs = command_oneline( + "rev-list", "-1", + "$new_parents[$i]..$new_parents[$j]", + ); + if ( !$revs ) { + undef($new_parents[$j]); } - } else { - push @tmp, $_; } } - close $fh or croak $!; - @{$comments->{'END'}} = @tmp if @tmp; } - return ($grafts, $comments); + push @$parents, grep { defined } @new_parents; } -sub write_grafts { - my ($grafts, $comments, $gr_file) = @_; +sub make_log_entry { + my ($self, $rev, $parents, $ed) = @_; + my $untracked = $self->get_untracked($ed); - open my $fh, '>', $gr_file or croak $!; - foreach my $c (sort keys %$grafts) { - if ($comments->{$c}) { - print $fh $_ foreach @{$comments->{$c}}; + my @parents = @$parents; + my $ps = $ed->{path_strip} || ""; + for my $path ( grep { m/$ps/ } %{$ed->{dir_prop}} ) { + my $props = $ed->{dir_prop}{$path}; + if ( $props->{"svk:merge"} ) { + $self->find_extra_svk_parents + ($ed, $props->{"svk:merge"}, \@parents); } - my $p = $grafts->{$c}; - my %x; # real parents - delete $p->{$c}; # commits are not self-reproducing... - my $pid = open my $ch, '-|'; - defined $pid or croak $!; - if (!$pid) { - exec(qw/git-cat-file commit/, $c) or croak $!; + if ( $props->{"svn:mergeinfo"} ) { + $self->find_extra_svn_parents + ($ed, + $props->{"svn:mergeinfo"}, + \@parents); } - while (<$ch>) { - if (/^parent ($sha1)/) { - $x{$1} = $p->{$1} = 1; + } + + open my $un, '>>', "$self->{dir}/unhandled.log" or croak $!; + 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 { - 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 { safe_qx('git-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; - } + print $un " rev_prop: ", uri_encode($_), ' ', + uri_encode($v), "\n"; } } - - # 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"; + } else { + map { $log_entry{$_} = $logged->{$_} } keys %$logged; + } + close $un or croak $!; + + $log_entry{date} = parse_svn_date($log_entry{date}); + $log_entry{log} .= "\n"; + my $author = $log_entry{author} = check_author($log_entry{author}); + my ($name, $email) = defined $::users{$author} ? @{$::users{$author}} + : ($author, undef); + + my ($commit_name, $commit_email) = ($name, $email); + if ($_use_log_author) { + my $name_field; + if ($log_entry{log} =~ /From:\s+(.*\S)\s*\n/i) { + $name_field = $1; + } elsif ($log_entry{log} =~ /Signed-off-by:\s+(.*\S)\s*\n/i) { + $name_field = $1; + } + if (!defined $name_field) { + if (!defined $email) { + $email = $name; + } + } elsif ($name_field =~ /(.*?)\s+<(.*)>/) { + ($name, $email) = ($1, $2); + } elsif ($name_field =~ /(.*)@/) { + ($name, $email) = ($1, $name_field); + } else { + ($name, $email) = ($name_field, $name_field); + } } - if ($comments->{'END'}) { - print $fh $_ foreach @{$comments->{'END'}}; + if (defined $headrev && $self->use_svm_props) { + if ($self->rewrite_root) { + die "Can't have both 'useSvmProps' and 'rewriteRoot' ", + "options set!\n"; + } + if ($self->rewrite_uuid) { + die "Can't have both 'useSvmProps' and 'rewriteUUID' ", + "options set!\n"; + } + my ($uuid, $r) = $headrev =~ m{^([a-f\d\-]{30,}):(\d+)$}i; + # we don't want "SVM: initializing mirror for junk" ... + return undef if $r == 0; + my $svm = $self->svm; + 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"; + $commit_email ||= "$author\@$uuid"; + } elsif ($self->use_svnsync_props) { + my $full_url = $self->svnsync->{url}; + $full_url .= "/$self->{path}" if length $self->{path}; + remove_username($full_url); + my $uuid = $self->svnsync->{uuid}; + $log_entry{metadata} = "$full_url\@$rev $uuid"; + $email ||= "$author\@$uuid"; + $commit_email ||= "$author\@$uuid"; + } else { + my $url = $self->metadata_url; + remove_username($url); + my $uuid = $self->rewrite_uuid || $self->ra->get_uuid; + $log_entry{metadata} = "$url\@$rev " . $uuid; + $email ||= "$author\@" . $uuid; + $commit_email ||= "$author\@" . $uuid; } - close $fh or croak $!; + $log_entry{name} = $name; + $log_entry{email} = $email; + $log_entry{commit_name} = $commit_name; + $log_entry{commit_email} = $commit_email; + \%log_entry; } -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, $_; - } +sub fetch { + my ($self, $min_rev, $max_rev, @parents) = @_; + my ($last_rev, $last_commit) = $self->last_rev_commit; + 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) = @_; + $self->{inject_parents} = { $rev => $tree }; + $self->fetch(undef, undef); +} + +sub set_tree { + my ($self, $tree) = (shift, shift); + my $log_entry = ::get_commit_entry($tree); + unless ($self->{last_rev}) { + ::fatal("Must have an existing revision to commit"); } - foreach (@dir) { - my $x = $_; - $x =~ s!^\Q$GIT_DIR\E/svn/!!o; - read_url_paths_all($l_map, $x, $_); + 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"; } } -# 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; +sub rebuild_from_rev_db { + my ($self, $path) = @_; + my $r = -1; + open my $fh, '<', $path or croak "open: $!"; + binmode $fh or croak "binmode: $!"; + while (<$fh>) { + length($_) == 41 or croak "inconsistent size in ($_) != 41"; + chomp($_); + ++$r; + next if $_ eq ('0' x 40); + $self->rev_map_set($r, $_); + print "r$r = $_\n"; + } + close $fh or croak "close: $!"; + unlink $path or croak "unlink: $!"; } -sub extract_metadata { - my $id = shift or return (undef, undef, undef); - my ($url, $rev, $uuid) = ($id =~ /^git-svn-id:\s(\S+?)\@(\d+) - \s([a-f\d\-]+)$/x); - if (!defined $rev || !$uuid || !$url) { - # some of the original repositories I made had - # identifiers like this: - ($rev, $uuid) = ($id =~/^git-svn-id:\s(\d+)\@([a-f\d\-]+)/); +sub rebuild { + my ($self) = @_; + my $map_path = $self->map_path; + my $partial = (-e $map_path && ! -z $map_path); + return unless ::verify_ref($self->refname.'^0'); + if (!$partial && ($self->use_svm_props || $self->no_metadata)) { + my $rev_db = $self->rev_db_path; + $self->rebuild_from_rev_db($rev_db); + if ($self->use_svm_props) { + my $svm_rev_db = $self->rev_db_path($self->svm_uuid); + $self->rebuild_from_rev_db($svm_rev_db); + } + $self->unlink_rev_db_symlink; + return; } - return ($url, $rev, $uuid); -} + print "Rebuilding $map_path ...\n" if (!$partial); + my ($base_rev, $head) = ($partial ? $self->rev_map_max_norebuild(1) : + (undef, undef)); + my ($log, $ctx) = + command_output_pipe(qw/rev-list --pretty=raw --no-color --reverse/, + ($head ? "$head.." : "") . $self->refname, + '--'); + my $metadata_url = $self->metadata_url; + remove_username($metadata_url); + my $svn_uuid = $self->rewrite_uuid || $self->ra_uuid; + my $c; + while (<$log>) { + if ( m{^commit ($::sha1)$} ) { + $c = $1; + next; + } + next unless s{^\s*(git-svn-id:)}{$1}; + my ($url, $rev, $uuid) = ::extract_metadata($_); + remove_username($url); -sub cmt_metadata { - return extract_metadata((grep(/^git-svn-id: /, - safe_qx(qw/git-cat-file commit/, shift)))[-1]); + # 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 (($uuid ne $svn_uuid) || + ($metadata_url && $url && ($url ne $metadata_url))) { + next; + } + if ($partial && $head) { + print "Partial-rebuilding $map_path ...\n"; + print "Currently at $base_rev = $head\n"; + $head = undef; + } + + $self->rev_map_set($rev, $c); + print "r$rev = $c\n"; + } + command_close_pipe($log, $ctx); + print "Done rebuilding $map_path\n" if (!$partial || !$head); + my $rev_db_path = $self->rev_db_path; + if (-f $self->rev_db_path) { + unlink $self->rev_db_path or croak "unlink: $!"; + } + $self->unlink_rev_db_symlink; } -sub get_commit_time { - my $cmt = shift; - defined(my $pid = open my $fh, '-|') or croak $!; - if (!$pid) { - exec qw/git-rev-list --pretty=raw -n1/, $cmt or croak $!; +# rev_map: +# 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... +# +# This is the replacement for the rev_db format, which was too big +# and inefficient for large repositories with a lot of sparse history +# (mainly tags) +# +# The format is this: +# - 24 bytes for every record, +# * 4 bytes for the integer representing an SVN revision number +# * 20 bytes representing the sha1 of a git commit +# - No empty padding records like the old format +# (except the last record, which can be overwritten) +# - new records are written append-only since SVN revision numbers +# increase monotonically +# - lookups on SVN revision number are done via a binary search +# - Piping the file to xxd -c24 is a good way of dumping it for +# viewing or editing (piped back through xxd -r), should the need +# ever arise. +# - The last record can be padding revision with an all-zero sha1 +# This is used to optimize fetch performance when using multiple +# "fetch" directives in .git/config +# +# These files are disposable unless noMetadata or useSvmProps is set + +sub _rev_map_set { + my ($fh, $rev, $commit) = @_; + + binmode $fh or croak "binmode: $!"; + my $size = (stat($fh))[7]; + ($size % 24) == 0 or croak "inconsistent size: $size"; + + my $wr_offset = 0; + if ($size > 0) { + sysseek($fh, -24, SEEK_END) or croak "seek: $!"; + my $read = sysread($fh, my $buf, 24) or croak "read: $!"; + $read == 24 or croak "read only $read bytes (!= 24)"; + my ($last_rev, $last_commit) = unpack(rev_map_fmt, $buf); + if ($last_commit eq ('0' x40)) { + if ($size >= 48) { + sysseek($fh, -48, SEEK_END) or croak "seek: $!"; + $read = sysread($fh, $buf, 24) or + croak "read: $!"; + $read == 24 or + croak "read only $read bytes (!= 24)"; + ($last_rev, $last_commit) = + unpack(rev_map_fmt, $buf); + if ($last_commit eq ('0' x40)) { + croak "inconsistent .rev_map\n"; + } + } + if ($last_rev >= $rev) { + croak "last_rev is higher!: $last_rev >= $rev"; + } + $wr_offset = -24; + } } - 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); + sysseek($fh, $wr_offset, SEEK_END) or croak "seek: $!"; + syswrite($fh, pack(rev_map_fmt, $rev, $commit), 24) == 24 or + croak "write: $!"; +} + +sub _rev_map_reset { + my ($fh, $rev, $commit) = @_; + my $c = _rev_map_get($fh, $rev); + $c eq $commit or die "_rev_map_reset(@_) commit $c does not match!\n"; + my $offset = sysseek($fh, 0, SEEK_CUR) or croak "seek: $!"; + truncate $fh, $offset or croak "truncate: $!"; +} + +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_map_set { + my ($self, $rev, $commit, $update_ref, $uuid) = @_; + defined $commit or die "missing arg3\n"; + length $commit == 40 or die "arg3 must be a full SHA1 hexsum\n"; + my $db = $self->map_path($uuid); + my $db_lock = "$db.lock"; + my $sig; + $update_ref ||= 0; + 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_map_set(@_): ", + "Failed to copy: ", + "$db => $db_lock ($!)\n"; + } else { + rename $db, $db_lock or die "rev_map_set(@_): ", + "Failed to rename: ", + "$db => $db_lock ($!)\n"; + } + + sysopen(my $fh, $db_lock, O_RDWR | O_CREAT) + or croak "Couldn't open $db_lock: $!\n"; + $update_ref eq 'reset' ? _rev_map_reset($fh, $rev, $commit) : + _rev_map_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; + my $note = ""; + $note = " ($update_ref)" if ($update_ref !~ /^\d*$/); + command_noisy('update-ref', '-m', "r$rev$note", + $self->refname, $commit); + } + rename $db_lock, $db or die "rev_map_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 $sig; + } +} + +# If want_commit, this will return an array of (rev, commit) where +# commit _must_ be a valid commit in the archive. +# Otherwise, it'll return the max revision (whether or not the +# commit is valid or just a 0x40 placeholder). +sub rev_map_max { + my ($self, $want_commit) = @_; + $self->rebuild; + my ($r, $c) = $self->rev_map_max_norebuild($want_commit); + $want_commit ? ($r, $c) : $r; +} + +sub rev_map_max_norebuild { + my ($self, $want_commit) = @_; + my $map_path = $self->map_path; + stat $map_path or return $want_commit ? (0, undef) : 0; + sysopen(my $fh, $map_path, O_RDONLY) or croak "open: $!"; + binmode $fh or croak "binmode: $!"; + my $size = (stat($fh))[7]; + ($size % 24) == 0 or croak "inconsistent size: $size"; + + if ($size == 0) { + close $fh or croak "close: $!"; + return $want_commit ? (0, undef) : 0; + } + + sysseek($fh, -24, SEEK_END) or croak "seek: $!"; + sysread($fh, my $buf, 24) == 24 or croak "read: $!"; + my ($r, $c) = unpack(rev_map_fmt, $buf); + if ($want_commit && $c eq ('0' x40)) { + if ($size < 48) { + return $want_commit ? (0, undef) : 0; + } + sysseek($fh, -48, SEEK_END) or croak "seek: $!"; + sysread($fh, $buf, 24) == 24 or croak "read: $!"; + ($r, $c) = unpack(rev_map_fmt, $buf); + if ($c eq ('0'x40)) { + croak "Penultimate record is all-zeroes in $map_path"; } - close $fh; - return $s; } - die "Can't get commit time for commit: $cmt\n"; + close $fh or croak "close: $!"; + $want_commit ? ($r, $c) : $r; } -sub tz_to_s_offset { - my ($tz) = @_; - $tz =~ s/(\d\d)$//; - return ($1 * 60) + ($tz * 3600); +sub rev_map_get { + my ($self, $rev, $uuid) = @_; + my $map_path = $self->map_path($uuid); + return undef unless -e $map_path; + + sysopen(my $fh, $map_path, O_RDONLY) or croak "open: $!"; + my $c = _rev_map_get($fh, $rev); + close($fh) or croak "close: $!"; + $c } -# adapted from pager.c -sub config_pager { - $_pager ||= $ENV{GIT_PAGER} || $ENV{PAGER}; - if (!defined $_pager) { - $_pager = 'less'; - } elsif (length $_pager == 0 || $_pager eq 'cat') { - $_pager = undef; +sub _rev_map_get { + my ($fh, $rev) = @_; + + binmode $fh or croak "binmode: $!"; + my $size = (stat($fh))[7]; + ($size % 24) == 0 or croak "inconsistent size: $size"; + + if ($size == 0) { + return undef; } + + my ($l, $u) = (0, $size - 24); + my ($r, $c, $buf); + + while ($l <= $u) { + my $i = int(($l/24 + $u/24) / 2) * 24; + sysseek($fh, $i, SEEK_SET) or croak "seek: $!"; + sysread($fh, my $buf, 24) == 24 or croak "read: $!"; + my ($r, $c) = unpack(rev_map_fmt, $buf); + + if ($r < $rev) { + $l = $i + 24; + } elsif ($r > $rev) { + $u = $i - 24; + } else { # $r == $rev + return $c eq ('0' x 40) ? undef : $c; + } + } + undef; } -sub run_pager { - return unless -t *STDOUT; - pipe my $rfd, my $wfd or return; - defined(my $pid = fork) or croak $!; - if (!$pid) { - open STDOUT, '>&', $wfd or croak $!; - return; +# Finds the first svn revision that exists on (if $eq_ok is true) or +# before $rev for the current branch. It will not search any lower +# than $min_rev. Returns the git commit hash and svn revision number +# if found, else (undef, undef). +sub find_rev_before { + my ($self, $rev, $eq_ok, $min_rev) = @_; + --$rev unless $eq_ok; + $min_rev ||= 1; + my $max_rev = $self->rev_map_max; + $rev = $max_rev if ($rev > $max_rev); + while ($rev >= $min_rev) { + if (my $c = $self->rev_map_get($rev)) { + return ($rev, $c); + } + --$rev; } - open STDIN, '<&', $rfd or croak $!; - $ENV{LESS} ||= 'FRSX'; - exec $_pager or croak "Can't run pager: $! ($_pager)\n"; + return (undef, undef); } -sub get_author_info { - my ($dest, $author, $t, $tz) = @_; - $author =~ s/(?:^\s*|\s*$)//g; - $dest->{a_raw} = $author; - my $_a; - if ($_authors) { - $_a = $rusers{$author} || undef; +# Finds the first svn revision that exists on (if $eq_ok is true) or +# after $rev for the current branch. It will not search any higher +# than $max_rev. Returns the git commit hash and svn revision number +# if found, else (undef, undef). +sub find_rev_after { + my ($self, $rev, $eq_ok, $max_rev) = @_; + ++$rev unless $eq_ok; + $max_rev ||= $self->rev_map_max; + while ($rev <= $max_rev) { + if (my $c = $self->rev_map_get($rev)) { + return ($rev, $c); + } + ++$rev; } - if (!$_a) { - ($_a) = ($author =~ /<([^>]+)\@[^>]+>$/); + 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; } - $dest->{t} = $t; - $dest->{tz} = $tz; - $dest->{a} = $_a; - # Date::Parse isn't in the standard Perl distro :( - if ($tz =~ s/^\+//) { - $t += tz_to_s_offset($tz); - } elsif ($tz =~ s/^\-//) { - $t -= tz_to_s_offset($tz); + unless (defined $ref_id && length $ref_id) { + $_prefix = '' unless defined($_prefix); + $_[2] = $ref_id = + "refs/remotes/$_prefix$Git::SVN::default_ref_id"; } - $dest->{t_utc} = $t; -} + $_[1] = $repo_id; + my $dir = "$ENV{GIT_DIR}/svn/$ref_id"; -sub process_commit { - my ($c, $r_min, $r_max, $defer) = @_; - if (defined $r_min && defined $r_max) { - if ($r_min == $c->{r} && $r_min == $r_max) { - show_commit($c); - return 0; - } - return 1 if $r_min == $r_max; - if ($r_min < $r_max) { - # we need to reverse the print order - return 0 if (defined $_limit && --$_limit < 0); - push @$defer, $c; - return 1; - } - if ($r_min != $r_max) { - return 1 if ($r_min < $c->{r}); - return 1 if ($r_max > $c->{r}); + # Older repos imported by us used $GIT_DIR/svn/foo instead of + # $GIT_DIR/svn/refs/remotes/foo when tracking refs/remotes/foo + if ($ref_id =~ m{^refs/remotes/(.*)}) { + my $old_dir = "$ENV{GIT_DIR}/svn/$1"; + if (-d $old_dir && ! -d $dir) { + $dir = $old_dir; } } - return 0 if (defined $_limit && --$_limit < 0); - show_commit($c); - return 1; + + $_[3] = $path = '' unless (defined $path); + mkpath([$dir]); + bless { + ref_id => $ref_id, dir => $dir, index => "$dir/index", + path => $path, config => "$ENV{GIT_DIR}/svn/config", + map_root => "$dir/.rev_map", repo_id => $repo_id }, $class; } -sub show_commit { - my $c = shift; - if ($_oneline) { - my $x = "\n"; - if (my $l = $c->{l}) { - while ($l->[0] =~ /^\s*$/) { shift @$l } - $x = $l->[0]; - } - $_l_fmt ||= 'A' . length($c->{r}); - print 'r',pack($_l_fmt, $c->{r}),' | '; - print "$c->{c} | " if $_show_commit; - print $x; - } else { - show_commit_normal($c); +# for read-only access of old .rev_db formats +sub unlink_rev_db_symlink { + my ($self) = @_; + my $link = $self->rev_db_path; + $link =~ s/\.[\w-]+$// or croak "missing UUID at the end of $link"; + if (-l $link) { + unlink $link or croak "unlink: $link failed!"; } } -sub show_commit_changed_paths { - my ($c) = @_; - return unless $c->{changed}; - print "Changed paths:\n", @{$c->{changed}}; +sub rev_db_path { + my ($self, $uuid) = @_; + my $db_path = $self->map_path($uuid); + $db_path =~ s{/\.rev_map\.}{/\.rev_db\.} + or croak "map_path: $db_path does not contain '/.rev_map.' !"; + $db_path; } -sub show_commit_normal { - my ($c) = @_; - print '-' x72, "\nr$c->{r} | "; - print "$c->{c} | " if $_show_commit; - print "$c->{a} | ", strftime("%Y-%m-%d %H:%M:%S %z (%a, %d %b %Y)", - localtime($c->{t_utc})), ' | '; - my $nr_line = 0; +# the new replacement for .rev_db +sub map_path { + my ($self, $uuid) = @_; + $uuid ||= $self->ra_uuid; + "$self->{map_root}.$uuid"; +} - if (my $l = $c->{l}) { - while ($l->[$#$l] eq "\n" && $#$l > 0 - && $l->[($#$l - 1)] eq "\n") { - pop @$l; - } - $nr_line = scalar @$l; - if (!$nr_line) { - print "1 line\n\n\n"; - } else { - if ($nr_line == 1) { - $nr_line = '1 line'; - } else { - $nr_line .= ' lines'; - } - print $nr_line, "\n"; - show_commit_changed_paths($c); - print "\n"; - print $_ foreach @$l; - } - } else { - print "1 line\n"; - show_commit_changed_paths($c); - print "\n"; +sub uri_encode { + my ($f) = @_; + $f =~ s#([^a-zA-Z0-9\*!\:_\./\-])#uc sprintf("%%%02x",ord($1))#eg; + $f +} - } - foreach my $x (qw/raw diff/) { - if ($c->{$x}) { - print "\n"; - print $_ foreach @{$c->{$x}} - } - } +sub uri_decode { + my ($f) = @_; + $f =~ s#%([0-9a-fA-F]{2})#chr(hex($1))#eg; + $f } -sub libsvn_load { - return unless $_use_lib; - $_use_lib = eval { - require SVN::Core; - if ($SVN::Core::VERSION lt '1.1.0') { - die "Need SVN::Core 1.1.0 or better ", - "(got $SVN::Core::VERSION) ", - "Falling back to command-line svn\n"; - } - require SVN::Ra; - require SVN::Delta; - push @SVN::Git::Editor::ISA, 'SVN::Delta::Editor'; - push @SVN::Git::Fetcher::ISA, 'SVN::Delta::Editor'; - *SVN::Git::Fetcher::process_rm = *process_rm; - *SVN::Git::Fetcher::safe_qx = *safe_qx; - my $kill_stupid_warnings = $SVN::Node::none.$SVN::Node::file. - $SVN::Node::dir.$SVN::Node::unknown. - $SVN::Node::none.$SVN::Node::file. - $SVN::Node::dir.$SVN::Node::unknown. - $SVN::Auth::SSL::CNMISMATCH. - $SVN::Auth::SSL::NOTYETVALID. - $SVN::Auth::SSL::EXPIRED. - $SVN::Auth::SSL::UNKNOWNCA. - $SVN::Auth::SSL::OTHER; - 1; - }; +sub remove_username { + $_[0] =~ s{^([^:]*://)[^@]+@}{$1}; } -sub _simple_prompt { +package Git::SVN::Prompt; +use strict; +use warnings; +require SVN::Core; +use vars qw/$_no_auth_cache $_username/; + +sub simple { my ($cred, $realm, $default_username, $may_save, $pool) = @_; $may_save = undef if $_no_auth_cache; $default_username = $_username if defined $_username; if (defined $default_username && length $default_username) { if (defined $realm && length $realm) { - print "Authentication realm: $realm\n"; + print STDERR "Authentication realm: $realm\n"; + STDERR->flush; } $cred->username($default_username); } else { - _username_prompt($cred, $realm, $may_save, $pool); + username($cred, $realm, $may_save, $pool); } $cred->password(_read_password("Password for '" . $cred->username . "': ", $realm)); @@ -2741,39 +4318,49 @@ sub _simple_prompt { $SVN::_Core::SVN_NO_ERROR; } -sub _ssl_server_trust_prompt { +sub ssl_server_trust { my ($cred, $realm, $failures, $cert_info, $may_save, $pool) = @_; $may_save = undef if $_no_auth_cache; - print "Error validating server certificate for '$realm':\n"; - if ($failures & $SVN::Auth::SSL::UNKNOWNCA) { - print " - The certificate is not issued by a trusted ", - "authority. Use the\n", - " fingerprint to validate the certificate manually!\n"; - } - if ($failures & $SVN::Auth::SSL::CNMISMATCH) { - print " - The certificate hostname does not match.\n"; - } - if ($failures & $SVN::Auth::SSL::NOTYETVALID) { - print " - The certificate is not yet valid.\n"; - } - if ($failures & $SVN::Auth::SSL::EXPIRED) { - print " - The certificate has expired.\n"; - } - if ($failures & $SVN::Auth::SSL::OTHER) { - print " - The certificate has an unknown error.\n"; - } - printf( "Certificate information:\n". + print STDERR "Error validating server certificate for '$realm':\n"; + { + no warnings 'once'; + # All variables SVN::Auth::SSL::* are used only once, + # so we're shutting up Perl warnings about this. + if ($failures & $SVN::Auth::SSL::UNKNOWNCA) { + print STDERR " - The certificate is not issued ", + "by a trusted authority. Use the\n", + " fingerprint to validate ", + "the certificate manually!\n"; + } + if ($failures & $SVN::Auth::SSL::CNMISMATCH) { + print STDERR " - The certificate hostname ", + "does not match.\n"; + } + if ($failures & $SVN::Auth::SSL::NOTYETVALID) { + print STDERR " - The certificate is not yet valid.\n"; + } + if ($failures & $SVN::Auth::SSL::EXPIRED) { + print STDERR " - The certificate has expired.\n"; + } + if ($failures & $SVN::Auth::SSL::OTHER) { + print STDERR " - The certificate has ", + "an unknown error.\n"; + } + } # no warnings 'once' + printf STDERR + "Certificate information:\n". " - Hostname: %s\n". " - Valid: from %s until %s\n". " - Issuer: %s\n". " - Fingerprint: %s\n", map $cert_info->$_, qw(hostname valid_from valid_until - issuer_dname fingerprint) ); + issuer_dname fingerprint); my $choice; prompt: - print $may_save ? + print STDERR $may_save ? "(R)eject, accept (t)emporarily or accept (p)ermanently? " : "(R)eject or accept (t)emporarily? "; + STDERR->flush; $choice = lc(substr(<STDIN> || 'R', 0, 1)); if ($choice =~ /^t$/i) { $cred->may_save(undef); @@ -2788,17 +4375,18 @@ prompt: $SVN::_Core::SVN_NO_ERROR; } -sub _ssl_client_cert_prompt { +sub ssl_client_cert { my ($cred, $realm, $may_save, $pool) = @_; $may_save = undef if $_no_auth_cache; - print "Client certificate filename: "; + print STDERR "Client certificate filename: "; + STDERR->flush; chomp(my $filename = <STDIN>); $cred->cert_file($filename); $cred->may_save($may_save); $SVN::_Core::SVN_NO_ERROR; } -sub _ssl_client_cert_pw_prompt { +sub ssl_client_cert_pw { my ($cred, $realm, $may_save, $pool) = @_; $may_save = undef if $_no_auth_cache; $cred->password(_read_password("Password: ", $realm)); @@ -2806,17 +4394,18 @@ sub _ssl_client_cert_pw_prompt { $SVN::_Core::SVN_NO_ERROR; } -sub _username_prompt { +sub username { my ($cred, $realm, $may_save, $pool) = @_; $may_save = undef if $_no_auth_cache; if (defined $realm && length $realm) { - print "Authentication realm: $realm\n"; + print STDERR "Authentication realm: $realm\n"; } my $username; if (defined $_username) { $username = $_username; } else { - print "Username: "; + print STDERR "Username: "; + STDERR->flush; chomp($username = <STDIN>); } $cred->username($username); @@ -2826,762 +4415,677 @@ sub _username_prompt { sub _read_password { my ($prompt, $realm) = @_; - print $prompt; - require Term::ReadKey; - Term::ReadKey::ReadMode('noecho'); my $password = ''; - while (defined(my $key = Term::ReadKey::ReadKey(0))) { - last if $key =~ /[\012\015]/; # \n\r - $password .= $key; - } - Term::ReadKey::ReadMode('restore'); - print "\n"; - $password; -} - -sub libsvn_connect { - my ($url) = @_; - SVN::_Core::svn_config_ensure($_config_dir, undef); - my ($baton, $callbacks) = SVN::Core::auth_open_helper([ - SVN::Client::get_simple_provider(), - SVN::Client::get_ssl_server_trust_file_provider(), - SVN::Client::get_simple_prompt_provider( - \&_simple_prompt, 2), - SVN::Client::get_ssl_client_cert_prompt_provider( - \&_ssl_client_cert_prompt, 2), - SVN::Client::get_ssl_client_cert_pw_prompt_provider( - \&_ssl_client_cert_pw_prompt, 2), - SVN::Client::get_username_provider(), - SVN::Client::get_ssl_server_trust_prompt_provider( - \&_ssl_server_trust_prompt), - SVN::Client::get_username_prompt_provider( - \&_username_prompt, 2), - ]); - my $config = SVN::Core::config_get_config($_config_dir); - my $ra = SVN::Ra->new(url => $url, auth => $baton, - config => $config, - pool => SVN::Pool->new, - auth_provider_callbacks => $callbacks); - - my $df = $ENV{GIT_SVN_DELTA_FETCH}; - if (defined $df) { - $_xfer_delta = $df; + if (exists $ENV{GIT_ASKPASS}) { + open(PH, "-|", $ENV{GIT_ASKPASS}, $prompt); + $password = <PH>; + $password =~ s/[\012\015]//; # \n\r + close(PH); } else { - $_xfer_delta = ($url =~ m#^file://#) ? undef : 1; + print STDERR $prompt; + STDERR->flush; + require Term::ReadKey; + Term::ReadKey::ReadMode('noecho'); + while (defined(my $key = Term::ReadKey::ReadKey(0))) { + last if $key =~ /[\012\015]/; # \n\r + $password .= $key; + } + Term::ReadKey::ReadMode('restore'); + print STDERR "\n"; + STDERR->flush; } - $ra->{svn_path} = $url; - $ra->{repos_root} = $ra->get_repos_root; - $ra->{svn_path} =~ s#^\Q$ra->{repos_root}\E/*##; - push @repo_path_split_cache, qr/^(\Q$ra->{repos_root}\E)/; - return $ra; -} - -sub libsvn_dup_ra { - my ($ra) = @_; - SVN::Ra->new(map { $_ => $ra->{$_} } qw/config url - auth auth_provider_callbacks repos_root svn_path/); + $password; } -sub libsvn_get_file { - my ($gui, $f, $rev, $chg) = @_; - $f =~ s#^/##; - print "\t$chg\t$f\n" unless $_q; - - my ($hash, $pid, $in, $out); - my $pool = SVN::Pool->new; - defined($pid = open3($in, $out, '>&STDERR', - qw/git-hash-object -w --stdin/)) or croak $!; - # redirect STDOUT for SVN 1.1.x compatibility - open my $stdout, '>&', \*STDOUT or croak $!; - open STDOUT, '>&', $in or croak $!; - my ($r, $props) = $SVN->get_file($f, $rev, \*STDOUT, $pool); - $in->flush == 0 or croak $!; - open STDOUT, '>&', $stdout or croak $!; - close $in or croak $!; - close $stdout or croak $!; - $pool->clear; - chomp($hash = do { local $/; <$out> }); - close $out or croak $!; - waitpid $pid, 0; - $hash =~ /^$sha1$/o or die "not a sha1: $hash\n"; +package SVN::Git::Fetcher; +use vars qw/@ISA $_ignore_regex $_preserve_empty_dirs $_placeholder_filename + @deleted_gpath %added_placeholder $repo_id/; +use strict; +use warnings; +use Carp qw/croak/; +use File::Basename qw/dirname/; +use IO::File qw//; - my $mode = exists $props->{'svn:executable'} ? '100755' : '100644'; - if (exists $props->{'svn:special'}) { - $mode = '120000'; - my $link = `git-cat-file blob $hash`; - $link =~ s/^link // or die "svn:special file with contents: <", - $link, "> is not understood\n"; - defined($pid = open3($in, $out, '>&STDERR', - qw/git-hash-object -w --stdin/)) or croak $!; - print $in $link; - $in->flush == 0 or croak $!; - close $in or croak $!; - chomp($hash = do { local $/; <$out> }); - close $out or croak $!; - waitpid $pid, 0; - $hash =~ /^$sha1$/o or die "not a sha1: $hash\n"; - } - print $gui $mode,' ',$hash,"\t",$f,"\0" or croak $!; -} - -sub libsvn_log_entry { - my ($rev, $author, $date, $msg, $parents) = @_; - my ($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 $_authors && ! defined $users{$author}) { - die "Author: $author not defined in $_authors file\n"; - } - $msg = '' if ($rev == 0 && !defined $msg); - return { revision => $rev, date => "+0000 $Y-$m-$d $H:$M:$S", - author => $author, msg => $msg."\n", parents => $parents || [] } +# file baton members: path, mode_a, mode_b, pool, fh, blob, base +sub new { + my ($class, $git_svn, $switch_path) = @_; + my $self = SVN::Delta::Editor->new; + bless $self, $class; + if (exists $git_svn->{last_commit}) { + $self->{c} = $git_svn->{last_commit}; + $self->{empty_symlinks} = + _mark_empty_symlinks($git_svn, $switch_path); + } + + # 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 + $repo_id = $git_svn->{repo_id}; + my $k = "svn-remote.$repo_id.ignore-paths"; + my $v = eval { command_oneline('config', '--get', $k) }; + $self->{ignore_regex} = $v; + + $k = "svn-remote.$repo_id.preserve-empty-dirs"; + $v = eval { command_oneline('config', '--get', '--bool', $k) }; + if ($v && $v eq 'true') { + $_preserve_empty_dirs = 1; + $k = "svn-remote.$repo_id.placeholder-filename"; + $v = eval { command_oneline('config', '--get', $k) }; + $_placeholder_filename = $v; + } + + # Load the list of placeholder files added during previous invocations. + $k = "svn-remote.$repo_id.added-placeholder"; + $v = eval { command_oneline('config', '--get-all', $k) }; + if ($_preserve_empty_dirs && $v) { + # command() prints errors to stderr, so we only call it if + # command_oneline() succeeded. + my @v = command('config', '--get-all', $k); + $added_placeholder{ dirname($_) } = $_ foreach @v; + } + + $self->{empty} = {}; + $self->{dir_prop} = {}; + $self->{file_prop} = {}; + $self->{absent_dir} = {}; + $self->{absent_file} = {}; + $self->{gii} = $git_svn->tmp_index_do(sub { Git::IndexInfo->new }); + $self->{pathnameencoding} = Git::config('svn.pathnameencoding'); + $self; } -sub process_rm { - my ($gui, $last_commit, $f, $q) = @_; - # remove entire directories. - if (safe_qx('git-ls-tree',$last_commit,'--',$f) =~ /^040000 tree/) { - defined(my $pid = open my $ls, '-|') or croak $!; - if (!$pid) { - exec(qw/git-ls-tree -r --name-only -z/, - $last_commit,'--',$f) or croak $!; +# this uses the Ra object, so it must be called before do_{switch,update}, +# not inside them (when the Git::SVN::Fetcher object is passed) to +# do_{switch,update} +sub _mark_empty_symlinks { + my ($git_svn, $switch_path) = @_; + my $bool = Git::config_bool('svn.brokenSymlinkWorkaround'); + return {} if (!defined($bool)) || (defined($bool) && ! $bool); + + my %ret; + my ($rev, $cmt) = $git_svn->last_rev_commit; + return {} unless ($rev && $cmt); + + # allow the warning to be printed for each revision we fetch to + # ensure the user sees it. The user can also disable the workaround + # on the repository even while git svn is running and the next + # revision fetched will skip this expensive function. + my $printed_warning; + chomp(my $empty_blob = `git hash-object -t blob --stdin < /dev/null`); + my ($ls, $ctx) = command_output_pipe(qw/ls-tree -r -z/, $cmt); + local $/ = "\0"; + my $pfx = defined($switch_path) ? $switch_path : $git_svn->{path}; + $pfx .= '/' if length($pfx); + while (<$ls>) { + chomp; + s/\A100644 blob $empty_blob\t//o or next; + unless ($printed_warning) { + print STDERR "Scanning for empty symlinks, ", + "this may take a while if you have ", + "many empty files\n", + "You may disable this with `", + "git config svn.brokenSymlinkWorkaround ", + "false'.\n", + "This may be done in a different ", + "terminal without restarting ", + "git svn\n"; + $printed_warning = 1; } - local $/ = "\0"; - while (<$ls>) { - print $gui '0 ',0 x 40,"\t",$_ or croak $!; - print "\tD\t$_\n" unless $q; + my $path = $_; + my (undef, $props) = + $git_svn->ra->get_file($pfx.$path, $rev, undef); + if ($props->{'svn:special'}) { + $ret{$path} = 1; } - print "\tD\t$f/\n" unless $q; - close $ls or croak $?; - } else { - print $gui '0 ',0 x 40,"\t",$f,"\0" or croak $!; - print "\tD\t$f\n" unless $q; } + command_close_pipe($ls, $ctx); + \%ret; } -sub libsvn_fetch { - $_xfer_delta ? libsvn_fetch_delta(@_) : libsvn_fetch_full(@_); +# returns true if a given path is inside a ".git" directory +sub in_dot_git { + $_[0] =~ m{(?:^|/)\.git(?:/|$)}; } -sub libsvn_fetch_delta { - my ($last_commit, $paths, $rev, $author, $date, $msg) = @_; - my $pool = SVN::Pool->new; - my $ed = SVN::Git::Fetcher->new({ c => $last_commit, q => $_q }); - my $reporter = $SVN->do_update($rev, '', 1, $ed, $pool); - my @lock = $SVN::Core::VERSION ge '1.2.0' ? (undef) : (); - my (undef, $last_rev, undef) = cmt_metadata($last_commit); - $reporter->set_path('', $last_rev, 0, @lock, $pool); - $reporter->finish_report($pool); - $pool->clear; - unless ($ed->{git_commit_ok}) { - die "SVN connection failed somewhere...\n"; - } - libsvn_log_entry($rev, $author, $date, $msg, [$last_commit]); -} - -sub libsvn_fetch_full { - my ($last_commit, $paths, $rev, $author, $date, $msg) = @_; - open my $gui, '| git-update-index -z --index-info' or croak $!; - my %amr; - my $p = $SVN->{svn_path}; - foreach my $f (keys %$paths) { - my $m = $paths->{$f}->action(); - if (length $p) { - $f =~ s#^/\Q$p\E/##; - next if $f =~ m#^/#; - } else { - $f =~ s#^/##; - } - if ($m =~ /^[DR]$/) { - process_rm($gui, $last_commit, $f, $_q); - next if $m eq 'D'; - # 'R' can be file replacements, too, right? - } - my $pool = SVN::Pool->new; - my $t = $SVN->check_path($f, $rev, $pool); - if ($t == $SVN::Node::file) { - if ($m =~ /^[AMR]$/) { - $amr{$f} = $m; - } else { - die "Unrecognized action: $m, ($f r$rev)\n"; - } - } elsif ($t == $SVN::Node::dir && $m =~ /^[AR]$/) { - my @traversed = (); - libsvn_traverse($gui, '', $f, $rev, \@traversed); - foreach (@traversed) { - $amr{$_} = $m; - } - } - $pool->clear; - } - foreach (keys %amr) { - libsvn_get_file($gui, $_, $rev, $amr{$_}); - } - close $gui or croak $?; - return libsvn_log_entry($rev, $author, $date, $msg, [$last_commit]); +# return value: 0 -- don't ignore, 1 -- ignore +sub is_path_ignored { + my ($self, $path) = @_; + return 1 if in_dot_git($path); + return 1 if defined($self->{ignore_regex}) && + $path =~ m!$self->{ignore_regex}!; + return 0 unless defined($_ignore_regex); + return 1 if $path =~ m!$_ignore_regex!o; + return 0; } -sub svn_grab_base_rev { - defined(my $pid = open my $fh, '-|') or croak $!; - if (!$pid) { - open my $null, '>', '/dev/null' or croak $!; - open STDERR, '>&', $null or croak $!; - exec qw/git-rev-parse --verify/,"refs/remotes/$GIT_SVN^0" - or croak $!; - } - chomp(my $c = do { local $/; <$fh> }); - close $fh; - 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, $c); - } - return (undef, undef); +sub set_path_strip { + my ($self, $path) = @_; + $self->{path_strip} = qr/^\Q$path\E(\/|$)/ if length $path; } -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: $_revision not understood by git-svn\n", - "Try using the command-line svn client instead\n"; +sub open_root { + { path => '' }; } -sub libsvn_traverse { - my ($gui, $pfx, $path, $rev, $files) = @_; - my $cwd = length $pfx ? "$pfx/$path" : $path; - my $pool = SVN::Pool->new; - $cwd =~ s#^\Q$SVN->{svn_path}\E##; - my ($dirent, $r, $props) = $SVN->get_dir($cwd, $rev, $pool); - foreach my $d (keys %$dirent) { - my $t = $dirent->{$d}->kind; - if ($t == $SVN::Node::dir) { - libsvn_traverse($gui, $cwd, $d, $rev, $files); - } elsif ($t == $SVN::Node::file) { - my $file = "$cwd/$d"; - if (defined $files) { - push @$files, $file; - } else { - libsvn_get_file($gui, $file, $rev, 'A'); - } - } - } - $pool->clear; +sub open_directory { + my ($self, $path, $pb, $rev) = @_; + { path => $path }; } -sub libsvn_traverse_ignore { - my ($fh, $path, $r) = @_; - $path =~ s#^/+##g; - my $pool = SVN::Pool->new; - my ($dirent, undef, $props) = $SVN->get_dir($path, $r, $pool); - 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, "$path/$_", $r); +sub git_path { + my ($self, $path) = @_; + if (my $enc = $self->{pathnameencoding}) { + require Encode; + Encode::from_to($path, 'UTF-8', $enc); } - $pool->clear; -} - -sub revisions_eq { - my ($path, $r0, $r1) = @_; - return 1 if $r0 == $r1; - my $nr = 0; - if ($_use_lib) { - # should be OK to use Pool here (r1 - r0) should be small - my $pool = SVN::Pool->new; - libsvn_get_log($SVN, [$path], $r0, $r1, - 0, 0, 1, sub {$nr++}, $pool); - $pool->clear; - } else { - my ($url, undef) = repo_path_split($SVN_URL); - my $svn_log = svn_log_raw("$url/$path","-r$r0:$r1"); - while (next_log_entry($svn_log)) { $nr++ } - close $svn_log->{fh}; + if ($self->{path_strip}) { + $path =~ s!$self->{path_strip}!! or + die "Failed to strip path '$path' ($self->{path_strip})\n"; } - return 0 if ($nr > 1); - return 1; + $path; } -sub libsvn_find_parent_branch { - my ($paths, $rev, $author, $date, $msg) = @_; - 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"; - sys(qw/git-read-tree/, $parent); - # I can't seem to get do_switch() to work correctly with - # the SWIG interface (TypeError when passing switch_url...), - # so we'll unconditionally bypass the delta interface here - # for now - return libsvn_fetch_full($parent, $paths, $rev, - $author, $date, $msg); - } - print STDERR "Nope, branch point not imported or unknown\n"; - return undef; -} +sub delete_entry { + my ($self, $path, $rev, $pb) = @_; + return undef if $self->is_path_ignored($path); -sub libsvn_get_log { - my ($ra, @args) = @_; - $args[4]-- if $args[4] && $_xfer_delta && ! $_follow_parent; - if ($SVN::Core::VERSION le '1.2.0') { - splice(@args, 3, 1); - } - $ra->get_log(@args); -} + my $gpath = $self->git_path($path); + return undef if ($gpath eq ''); -sub libsvn_new_tree { - if (my $log_entry = libsvn_find_parent_branch(@_)) { - return $log_entry; - } - my ($paths, $rev, $author, $date, $msg) = @_; - if ($_xfer_delta) { - my $pool = SVN::Pool->new; - my $ed = SVN::Git::Fetcher->new({q => $_q}); - my $reporter = $SVN->do_update($rev, '', 1, $ed, $pool); - my @lock = $SVN::Core::VERSION ge '1.2.0' ? (undef) : (); - $reporter->set_path('', $rev, 1, @lock, $pool); - $reporter->finish_report($pool); - $pool->clear; - unless ($ed->{git_commit_ok}) { - die "SVN connection failed somewhere...\n"; + # remove entire directories. + my ($tree) = (command('ls-tree', '-z', $self->{c}, "./$gpath") + =~ /\A040000 tree ([a-f\d]{40})\t\Q$gpath\E\0/); + if ($tree) { + my ($ls, $ctx) = command_output_pipe(qw/ls-tree + -r --name-only -z/, + $tree); + local $/ = "\0"; + while (<$ls>) { + chomp; + my $rmpath = "$gpath/$_"; + $self->{gii}->remove($rmpath); + print "\tD\t$rmpath\n" unless $::_q; } + print "\tD\t$gpath/\n" unless $::_q; + command_close_pipe($ls, $ctx); } else { - open my $gui, '| git-update-index -z --index-info' or croak $!; - libsvn_traverse($gui, '', $SVN->{svn_path}, $rev); - close $gui or croak $?; - } - return libsvn_log_entry($rev, $author, $date, $msg); -} - -sub find_graft_path_commit { - my ($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; - } + $self->{gii}->remove($gpath); + print "\tD\t$gpath\n" unless $::_q; } + # Don't add to @deleted_gpath if we're deleting a placeholder file. + push @deleted_gpath, $gpath unless $added_placeholder{dirname($path)}; + $self->{empty}->{$path} = 0; + undef; } -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, $r0); - } -} +sub open_file { + my ($self, $path, $pb, $rev) = @_; + my ($mode, $blob); -sub set_index { - my $old = $ENV{GIT_INDEX_FILE}; - $ENV{GIT_INDEX_FILE} = shift; - return $old; -} + goto out if $self->is_path_ignored($path); -sub restore_index { - my ($old) = @_; - if (defined $old) { - $ENV{GIT_INDEX_FILE} = $old; - } else { - delete $ENV{GIT_INDEX_FILE}; + my $gpath = $self->git_path($path); + ($mode, $blob) = (command('ls-tree', '-z', $self->{c}, "./$gpath") + =~ /\A(\d{6}) blob ([a-f\d]{40})\t\Q$gpath\E\0/); + unless (defined $mode && defined $blob) { + die "$path was not found in commit $self->{c} (r$rev)\n"; } -} - -sub libsvn_commit_cb { - my ($rev, $date, $committer, $c, $msg, $r_last, $cmt_last) = @_; - if ($_optimize_commits && $rev == ($r_last + 1)) { - my $log = libsvn_log_entry($rev,$committer,$date,$msg); - $log->{tree} = get_tree_from_treeish($c); - my $cmt = git_commit($log, $cmt_last, $c); - my @diff = safe_qx('git-diff-tree', $cmt, $c); - if (@diff) { - print STDERR "Trees differ: $cmt $c\n", - join('',@diff),"\n"; - exit 1; - } - } else { - fetch("$rev=$c"); + if ($mode eq '100644' && $self->{empty_symlinks}->{$path}) { + $mode = '120000'; } +out: + { path => $path, mode_a => $mode, mode_b => $mode, blob => $blob, + pool => SVN::Pool->new, action => 'M' }; } -sub libsvn_ls_fullurl { - my $fullurl = shift; - my $ra = libsvn_connect($fullurl); - my @ret; - my $pool = SVN::Pool->new; - my $r = defined $_revision ? $_revision : $ra->get_latest_revnum; - my ($dirent, undef, undef) = $ra->get_dir('', $r, $pool); - foreach my $d (keys %$dirent) { - if ($dirent->{$d}->kind == $SVN::Node::dir) { - push @ret, "$d/"; # add '/' for compat with cli svn +sub add_file { + my ($self, $path, $pb, $cp_path, $cp_rev) = @_; + my $mode; + + if (!$self->is_path_ignored($path)) { + my ($dir, $file) = ($path =~ m#^(.*?)/?([^/]+)$#); + delete $self->{empty}->{$dir}; + $mode = '100644'; + + if ($added_placeholder{$dir}) { + # Remove our placeholder file, if we created one. + delete_entry($self, $added_placeholder{$dir}) + unless $path eq $added_placeholder{$dir}; + delete $added_placeholder{$dir} } } - $pool->clear; - return @ret; -} - -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 $!; + { path => $path, mode_a => $mode, mode_b => $mode, + pool => SVN::Pool->new, action => 'A' }; } -sub revdb_get { - my ($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}$/); +sub add_directory { + my ($self, $path, $cp_path, $cp_rev) = @_; + goto out if $self->is_path_ignored($path); + my $gpath = $self->git_path($path); + if ($gpath eq '') { + my ($ls, $ctx) = command_output_pipe(qw/ls-tree + -r --name-only -z/, + $self->{c}); + local $/ = "\0"; + while (<$ls>) { + chomp; + $self->{gii}->remove($_); + print "\tD\t$_\n" unless $::_q; + push @deleted_gpath, $gpath; } + command_close_pipe($ls, $ctx); + $self->{empty}->{$path} = 0; } - close $fh or croak $!; - return $ret; -} + my ($dir, $file) = ($path =~ m#^(.*?)/?([^/]+)$#); + delete $self->{empty}->{$dir}; + $self->{empty}->{$path} = 1; -sub copy_remote_ref { - my $origin = $_cp_remote ? $_cp_remote : 'origin'; - my $ref = "refs/remotes/$GIT_SVN"; - if (safe_qx('git-ls-remote', $origin, $ref)) { - sys(qw/git fetch/, $origin, "$ref:$ref"); - } elsif ($_cp_remote && !$_upgrade) { - die "Unable to find remote reference: ", - "refs/remotes/$GIT_SVN on $origin\n"; + if ($added_placeholder{$dir}) { + # Remove our placeholder file, if we created one. + delete_entry($self, $added_placeholder{$dir}); + delete $added_placeholder{$dir} } -} -package SVN::Git::Fetcher; -use vars qw/@ISA/; -use strict; -use warnings; -use Carp qw/croak/; -use IO::File qw//; -# 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; - open my $gui, '| git-update-index -z --index-info' or croak $!; - $self->{gui} = $gui; - $self->{c} = $git_svn->{c} if exists $git_svn->{c}; - $self->{q} = $git_svn->{q}; - require Digest::MD5; - $self; +out: + { path => $path }; } -sub delete_entry { - my ($self, $path, $rev, $pb) = @_; - process_rm($self->{gui}, $self->{c}, $path, $self->{q}); +sub change_dir_prop { + my ($self, $db, $prop, $value) = @_; + return undef if $self->is_path_ignored($db->{path}); + $self->{dir_prop}->{$db->{path}} ||= {}; + $self->{dir_prop}->{$db->{path}}->{$prop} = $value; undef; } -sub open_file { - my ($self, $path, $pb, $rev) = @_; - my ($mode, $blob) = (safe_qx('git-ls-tree',$self->{c},'--',$path) - =~ /^(\d{6}) blob ([a-f\d]{40})\t/); - { path => $path, mode_a => $mode, mode_b => $mode, blob => $blob, - pool => SVN::Pool->new, action => 'M' }; +sub absent_directory { + my ($self, $path, $pb) = @_; + return undef if $self->is_path_ignored($path); + $self->{absent_dir}->{$pb->{path}} ||= []; + push @{$self->{absent_dir}->{$pb->{path}}}, $path; + undef; } -sub add_file { - my ($self, $path, $pb, $cp_path, $cp_rev) = @_; - { path => $path, mode_a => 100644, mode_b => 100644, - pool => SVN::Pool->new, action => 'A' }; +sub absent_file { + my ($self, $path, $pb) = @_; + return undef if $self->is_path_ignored($path); + $self->{absent_file}->{$pb->{path}} ||= []; + push @{$self->{absent_file}->{$pb->{path}}}, $path; + undef; } sub change_file_prop { my ($self, $fb, $prop, $value) = @_; + return undef if $self->is_path_ignored($fb->{path}); if ($prop eq 'svn:executable') { if ($fb->{mode_b} != 120000) { $fb->{mode_b} = defined $value ? 100755 : 100644; } } elsif ($prop eq 'svn:special') { $fb->{mode_b} = defined $value ? 120000 : 100644; + } else { + $self->{file_prop}->{$fb->{path}} ||= {}; + $self->{file_prop}->{$fb->{path}}->{$prop} = $value; } undef; } sub apply_textdelta { my ($self, $fb, $exp) = @_; - my $fh = IO::File->new_tmpfile; - $fh->autoflush(1); + return undef if $self->is_path_ignored($fb->{path}); + my $fh = $::_repository->temp_acquire('svn_delta'); # $fh gets auto-closed() by SVN::TxDelta::apply(), # (but $base does not,) so dup() it for reading in close_file open my $dup, '<&', $fh or croak $!; - my $base = IO::File->new_tmpfile; - $base->autoflush(1); + my $base = $::_repository->temp_acquire('git_blob'); + if ($fb->{blob}) { - defined (my $pid = fork) or croak $!; - if (!$pid) { - open STDOUT, '>&', $base or croak $!; - print STDOUT 'link ' if ($fb->{mode_a} == 120000); - exec qw/git-cat-file blob/, $fb->{blob} or croak $!; + my ($base_is_link, $size); + + if ($fb->{mode_a} eq '120000' && + ! $self->{empty_symlinks}->{$fb->{path}}) { + print $base 'link ' or die "print $!\n"; + $base_is_link = 1; } - waitpid $pid, 0; - croak $? if $?; + retry: + $size = $::_repository->cat_blob($fb->{blob}, $base); + die "Failed to read object $fb->{blob}" if ($size < 0); if (defined $exp) { seek $base, 0, 0 or croak $!; - my $md5 = Digest::MD5->new; - $md5->addfile($base); - my $got = $md5->hexdigest; - die "Checksum mismatch: $fb->{path} $fb->{blob}\n", - "expected: $exp\n", - " got: $got\n" if ($got ne $exp); + my $got = ::md5sum($base); + if ($got ne $exp) { + my $err = "Checksum mismatch: ". + "$fb->{path} $fb->{blob}\n" . + "expected: $exp\n" . + " got: $got\n"; + if ($base_is_link) { + warn $err, + "Retrying... (possibly ", + "a bad symlink from SVN)\n"; + $::_repository->temp_reset($base); + $base_is_link = 0; + goto retry; + } + die $err; + } } } seek $base, 0, 0 or croak $!; - $fb->{fh} = $dup; + $fb->{fh} = $fh; $fb->{base} = $base; - [ SVN::TxDelta::apply($base, $fh, undef, $fb->{path}, $fb->{pool}) ]; + [ SVN::TxDelta::apply($base, $dup, undef, $fb->{path}, $fb->{pool}) ]; } sub close_file { my ($self, $fb, $exp) = @_; + return undef if $self->is_path_ignored($fb->{path}); + 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; - $md5->addfile($fh); - my $got = $md5->hexdigest; - die "Checksum mismatch: $path\n", - "expected: $exp\n got: $got\n" if ($got ne $exp); - seek($fh, 0, 0) or croak $!; + if (defined $exp) { + seek($fh, 0, 0) or croak $!; + my $got = ::md5sum($fh); + if ($got ne $exp) { + die "Checksum mismatch: $path\n", + "expected: $exp\n got: $got\n"; + } + } if ($fb->{mode_b} == 120000) { - read($fh, my $buf, 5) == 5 or croak $!; - $buf eq 'link ' or die "$path has mode 120000", - "but is not a link\n"; - } - defined(my $pid = open my $out,'-|') or die "Can't fork: $!\n"; - if (!$pid) { - open STDIN, '<&', $fh or croak $!; - exec qw/git-hash-object -w --stdin/ or croak $!; - } - chomp($hash = do { local $/; <$out> }); - close $out or croak $!; - close $fh or croak $!; + sysseek($fh, 0, 0) or croak $!; + my $rd = sysread($fh, my $buf, 5); + + if (!defined $rd) { + croak "sysread: $!\n"; + } elsif ($rd == 0) { + warn "$path has mode 120000", + " but it points to nothing\n", + "converting to an empty file with mode", + " 100644\n"; + $fb->{mode_b} = '100644'; + } elsif ($buf ne 'link ') { + warn "$path has mode 120000", + " but is not a link\n"; + } else { + my $tmp_fh = $::_repository->temp_acquire( + 'svn_hash'); + my $res; + while ($res = sysread($fh, my $str, 1024)) { + my $out = syswrite($tmp_fh, $str, $res); + defined($out) && $out == $res + or croak("write ", + Git::temp_path($tmp_fh), + ": $!\n"); + } + defined $res or croak $!; + + ($fh, $tmp_fh) = ($tmp_fh, $fh); + Git::temp_release($tmp_fh, 1); + } + } + + $hash = $::_repository->hash_and_insert_object( + Git::temp_path($fh)); $hash =~ /^[a-f\d]{40}$/ or die "not a sha1: $hash\n"; - close $fb->{base} or croak $!; + + Git::temp_release($fb->{base}, 1); + Git::temp_release($fh, 1); } else { $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; - close $self->{gui}; + $self->{nr} = $self->{gii}->{nr}; + delete $self->{gii}; $self->SUPER::abort_edit(@_); } sub close_edit { my $self = shift; - close $self->{gui} or croak $!; + + if ($_preserve_empty_dirs) { + my @empty_dirs; + + # Any entry flagged as empty that also has an associated + # dir_prop represents a newly created empty directory. + foreach my $i (keys %{$self->{empty}}) { + push @empty_dirs, $i if exists $self->{dir_prop}->{$i}; + } + + # Search for directories that have become empty due subsequent + # file deletes. + push @empty_dirs, $self->find_empty_directories(); + + # Finally, add a placeholder file to each empty directory. + $self->add_placeholder_file($_) foreach (@empty_dirs); + + $self->stash_placeholder_list(); + } + $self->{git_commit_ok} = 1; + $self->{nr} = $self->{gii}->{nr}; + delete $self->{gii}; $self->SUPER::close_edit(@_); } +sub find_empty_directories { + my ($self) = @_; + my @empty_dirs; + my %dirs = map { dirname($_) => 1 } @deleted_gpath; + + foreach my $dir (sort keys %dirs) { + next if $dir eq "."; + + # If there have been any additions to this directory, there is + # no reason to check if it is empty. + my $skip_added = 0; + foreach my $t (qw/dir_prop file_prop/) { + foreach my $path (keys %{ $self->{$t} }) { + if (exists $self->{$t}->{dirname($path)}) { + $skip_added = 1; + last; + } + } + last if $skip_added; + } + next if $skip_added; + + # Use `git ls-tree` to get the filenames of this directory + # that existed prior to this particular commit. + my $ls = command('ls-tree', '-z', '--name-only', + $self->{c}, "$dir/"); + my %files = map { $_ => 1 } split(/\0/, $ls); + + # Remove the filenames that were deleted during this commit. + delete $files{$_} foreach (@deleted_gpath); + + # Report the directory if there are no filenames left. + push @empty_dirs, $dir unless (scalar %files); + } + @empty_dirs; +} + +sub add_placeholder_file { + my ($self, $dir) = @_; + my $path = "$dir/$_placeholder_filename"; + my $gpath = $self->git_path($path); + + my $fh = $::_repository->temp_acquire($gpath); + my $hash = $::_repository->hash_and_insert_object(Git::temp_path($fh)); + Git::temp_release($fh, 1); + $self->{gii}->update('100644', $hash, $gpath) or croak $!; + + # The directory should no longer be considered empty. + delete $self->{empty}->{$dir} if exists $self->{empty}->{$dir}; + + # Keep track of any placeholder files we create. + $added_placeholder{$dir} = $path; +} + +sub stash_placeholder_list { + my ($self) = @_; + my $k = "svn-remote.$repo_id.added-placeholder"; + my $v = eval { command_oneline('config', '--get-all', $k) }; + command_noisy('config', '--unset-all', $k) if $v; + foreach (values %added_placeholder) { + command_noisy('config', '--add', $k, $_); + } +} + 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; 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, $class; - foreach (qw/svn_path c r ra /) { - die "$_ 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}/" : ''; + $self->{config} = $opts->{config}; + $self->{mergeinfo} = $opts->{mergeinfo}; 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_a => $3, sha1_b => $4, + chg => $5 }; + if ($5 =~ /^(?:C|R)$/) { + $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) = @_; + if (my $enc = $self->{pathnameencoding}) { + require Encode; + Encode::from_to($path, $enc, 'UTF-8'); + } + $self->{path_prefix}.(defined $path ? $path : ''); } sub url_path { my ($self, $path) = @_; - $self->{ra}->{url} . '/' . $self->repo_path($path); + if ($self->{url} =~ m#^https?://#) { + $path =~ s!([^~a-zA-Z0-9_./-])!uc sprintf("%%%02x",ord($1))!eg; + } + $self->{url} . '/' . $self->repo_path($path); } sub rmdirs { - my ($self, $q) = @_; + my ($self) = @_; my $rm = $self->{rm}; delete $rm->{''}; # we never delete the url we're tracking return unless %$rm; @@ -3599,10 +5103,8 @@ sub rmdirs { delete $rm->{''}; # we never delete the url we're tracking return unless %$rm; - defined(my $pid = open my $fh,'-|') or croak $!; - if (!$pid) { - exec qw/git-ls-tree --name-only -r -z/, $self->{c} or croak $!; - } + my ($fh, $ctx) = command_output_pipe(qw/ls-tree --name-only -r -z/, + $self->{tree_b}); local $/ = "\0"; while (<$fh>) { chomp; @@ -3615,13 +5117,13 @@ sub rmdirs { return; } } - close $fh; + command_close_pipe($fh, $ctx); my ($r, $p, $bat) = ($self->{r}, $self->{pool}, $self->{bat}); foreach my $d (sort { $b =~ tr#/#/# <=> $a =~ tr#/#/# } keys %$rm) { $self->close_directory($bat->{$d}, $p); my ($dn) = ($d =~ m#^(.*?)/?(?:[^/]+)$#); - print "\tD+\t/$d/\n" unless $q; + print "\tD+\t$d/\n" unless $::_q; $self->SUPER::delete_entry($d, $r, $bat->{$dn}, $p); delete $bat->{$d}; } @@ -3629,28 +5131,34 @@ sub rmdirs { sub open_or_add_dir { my ($self, $full_path, $baton) = @_; - my $p = SVN::Pool->new; - my $t = $self->{ra}->check_path($full_path, $self->{r}, $p); - $p->clear; - if ($t == $SVN::Node::none) { - return $self->add_directory($full_path, $baton, - undef, -1, $self->{pool}); - } elsif ($t == $SVN::Node::dir) { - return $self->open_directory($full_path, $baton, - $self->{r}, $self->{pool}); - } - print STDERR "$full_path already exists in repository at ", - "r$self->{r} and it is not a directory (", - ($t == $SVN::Node::file ? 'file' : 'unknown'),"/$t)\n"; + my $t = $self->{types}->{$full_path}; + if (!defined $t) { + die "$full_path not known in r$self->{r} or we have a bug!\n"; + } + { + no warnings 'once'; + # SVN::Node::none and SVN::Node::file are used only once, + # so we're shutting up Perl's warnings about them. + if ($t == $SVN::Node::none) { + return $self->add_directory($full_path, $baton, + undef, -1, $self->{pool}); + } elsif ($t == $SVN::Node::dir) { + return $self->open_directory($full_path, $baton, + $self->{r}, $self->{pool}); + } # no warnings 'once' + print STDERR "$full_path already exists in repository at ", + "r$self->{r} and it is not a directory (", + ($t == $SVN::Node::file ? 'file' : 'unknown'),"/$t)\n"; + } # no warnings 'once' exit 1; } 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) { @@ -3661,24 +5169,76 @@ sub ensure_path { return $bat->{$c}; } +# Subroutine to convert a globbing pattern to a regular expression. +# From perl cookbook. +sub glob2pat { + my $globstr = shift; + my %patmap = ('*' => '.*', '?' => '.', '[' => '[', ']' => ']'); + $globstr =~ s{(.)} { $patmap{$1} || "\Q$1" }ge; + return '^' . $globstr . '$'; +} + +sub check_autoprop { + my ($self, $pattern, $properties, $file, $fbat) = @_; + # Convert the globbing pattern to a regular expression. + my $regex = glob2pat($pattern); + # Check if the pattern matches the file name. + if($file =~ m/($regex)/) { + # Parse the list of properties to set. + my @props = split(/;/, $properties); + foreach my $prop (@props) { + # Parse 'name=value' syntax and set the property. + if ($prop =~ /([^=]+)=(.*)/) { + my ($n,$v) = ($1,$2); + for ($n, $v) { + s/^\s+//; s/\s+$//; + } + $self->change_file_prop($fbat, $n, $v); + } + } + } +} + +sub apply_autoprops { + my ($self, $file, $fbat) = @_; + my $conf_t = ${$self->{config}}{'config'}; + no warnings 'once'; + # Check [miscellany]/enable-auto-props in svn configuration. + if (SVN::_Core::svn_config_get_bool( + $conf_t, + $SVN::_Core::SVN_CONFIG_SECTION_MISCELLANY, + $SVN::_Core::SVN_CONFIG_OPTION_ENABLE_AUTO_PROPS, + 0)) { + # Auto-props are enabled. Enumerate them to look for matches. + my $callback = sub { + $self->check_autoprop($_[0], $_[1], $file, $fbat); + }; + SVN::_Core::svn_config_enumerate( + $conf_t, + $SVN::_Core::SVN_CONFIG_SECTION_AUTO_PROPS, + $callback); + } +} + sub A { - my ($self, $m, $q) = @_; + my ($self, $m) = @_; my ($dir, $file) = split_path($m->{file_b}); my $pbat = $self->ensure_path($dir); my $fbat = $self->add_file($self->repo_path($m->{file_b}), $pbat, undef, -1); - print "\tA\t$m->{file_b}\n" unless $q; + print "\tA\t$m->{file_b}\n" unless $::_q; + $self->apply_autoprops($file, $fbat); $self->chg_file($fbat, $m); $self->close_file($fbat,undef,$self->{pool}); } sub C { - my ($self, $m, $q) = @_; + my ($self, $m) = @_; my ($dir, $file) = split_path($m->{file_b}); my $pbat = $self->ensure_path($dir); my $fbat = $self->add_file($self->repo_path($m->{file_b}), $pbat, $self->url_path($m->{file_a}), $self->{r}); - print "\tC\t$m->{file_a} => $m->{file_b}\n" unless $q; + print "\tC\t$m->{file_a} => $m->{file_b}\n" unless $::_q; $self->chg_file($fbat, $m); $self->close_file($fbat,undef,$self->{pool}); } @@ -3692,12 +5252,13 @@ sub delete_entry { } sub R { - my ($self, $m, $q) = @_; + my ($self, $m) = @_; my ($dir, $file) = split_path($m->{file_b}); my $pbat = $self->ensure_path($dir); my $fbat = $self->add_file($self->repo_path($m->{file_b}), $pbat, $self->url_path($m->{file_a}), $self->{r}); - print "\tR\t$m->{file_a} => $m->{file_b}\n" unless $q; + print "\tR\t$m->{file_a} => $m->{file_b}\n" unless $::_q; + $self->apply_autoprops($file, $fbat); $self->chg_file($fbat, $m); $self->close_file($fbat,undef,$self->{pool}); @@ -3707,12 +5268,12 @@ sub R { } sub M { - my ($self, $m, $q) = @_; + my ($self, $m) = @_; my ($dir, $file) = split_path($m->{file_b}); my $pbat = $self->ensure_path($dir); my $fbat = $self->open_file($self->repo_path($m->{file_b}), $pbat,$self->{r},$self->{pool}); - print "\t$m->{chg}\t$m->{file_b}\n" unless $q; + print "\t$m->{chg}\t$m->{file_b}\n" unless $::_q; $self->chg_file($fbat, $m); $self->close_file($fbat,undef,$self->{pool}); } @@ -3724,49 +5285,65 @@ sub change_file_prop { $self->SUPER::change_file_prop($fbat, $pname, $pval, $self->{pool}); } -sub chg_file { - my ($self, $fbat, $m) = @_; - if ($m->{mode_b} =~ /755$/ && $m->{mode_a} !~ /755$/) { - $self->change_file_prop($fbat,'svn:executable','*'); - } elsif ($m->{mode_b} !~ /755$/ && $m->{mode_a} =~ /755$/) { - $self->change_file_prop($fbat,'svn:executable',undef); - } - my $fh = IO::File->new_tmpfile or croak $!; - if ($m->{mode_b} =~ /^120/) { +sub change_dir_prop { + my ($self, $pbat, $pname, $pval) = @_; + $self->SUPER::change_dir_prop($pbat, $pname, $pval, $self->{pool}); +} + +sub _chg_file_get_blob ($$$$) { + my ($self, $fbat, $m, $which) = @_; + my $fh = $::_repository->temp_acquire("git_blob_$which"); + if ($m->{"mode_$which"} =~ /^120/) { print $fh 'link ' or croak $!; $self->change_file_prop($fbat,'svn:special','*'); - } elsif ($m->{mode_a} =~ /^120/ && $m->{mode_b} !~ /^120/) { + } elsif ($m->{mode_a} =~ /^120/ && $m->{"mode_$which"} !~ /^120/) { $self->change_file_prop($fbat,'svn:special',undef); } - defined(my $pid = fork) or croak $!; - if (!$pid) { - open STDOUT, '>&', $fh or croak $!; - exec qw/git-cat-file blob/, $m->{sha1_b} or croak $!; - } - waitpid $pid, 0; - croak $? if $?; + my $blob = $m->{"sha1_$which"}; + return ($fh,) if ($blob =~ /^0{40}$/); + my $size = $::_repository->cat_blob($blob, $fh); + croak "Failed to read object $blob" if ($size < 0); $fh->flush == 0 or croak $!; seek $fh, 0, 0 or croak $!; - my $md5 = Digest::MD5->new; - $md5->addfile($fh) or croak $!; + my $exp = ::md5sum($fh); seek $fh, 0, 0 or croak $!; + return ($fh, $exp); +} - my $exp = $md5->hexdigest; +sub chg_file { + my ($self, $fbat, $m) = @_; + if ($m->{mode_b} =~ /755$/ && $m->{mode_a} !~ /755$/) { + $self->change_file_prop($fbat,'svn:executable','*'); + } elsif ($m->{mode_b} !~ /755$/ && $m->{mode_a} =~ /755$/) { + $self->change_file_prop($fbat,'svn:executable',undef); + } + my ($fh_a, $exp_a) = _chg_file_get_blob $self, $fbat, $m, 'a'; + my ($fh_b, $exp_b) = _chg_file_get_blob $self, $fbat, $m, 'b'; my $pool = SVN::Pool->new; - my $atd = $self->apply_textdelta($fbat, undef, $pool); - my $got = SVN::TxDelta::send_stream($fh, @$atd, $pool); - die "Checksum mismatch\nexpected: $exp\ngot: $got\n" if ($got ne $exp); + my $atd = $self->apply_textdelta($fbat, $exp_a, $pool); + if (-s $fh_a) { + my $txstream = SVN::TxDelta::new ($fh_a, $fh_b, $pool); + my $res = SVN::TxDelta::send_txstream($txstream, @$atd, $pool); + if (defined $res) { + die "Unexpected result from send_txstream: $res\n", + "(SVN::Core::VERSION: $SVN::Core::VERSION)\n"; + } + } else { + my $got = SVN::TxDelta::send_stream($fh_b, @$atd, $pool); + die "Checksum mismatch\nexpected: $exp_b\ngot: $got\n" + if ($got ne $exp_b); + } + Git::temp_release($fh_b, 1); + Git::temp_release($fh_a, 1); $pool->clear; - - close $fh or croak $!; } sub D { - my ($self, $m, $q) = @_; + my ($self, $m) = @_; my ($dir, $file) = split_path($m->{file_b}); my $pbat = $self->ensure_path($dir); - print "\tD\t$m->{file_b}\n" unless $q; + print "\tD\t$m->{file_b}\n" unless $::_q; $self->delete_entry($m->{file_b}, $pbat); } @@ -3774,8 +5351,10 @@ sub close_edit { my ($self) = @_; my ($p,$bat) = ($self->{pool}, $self->{bat}); foreach (sort { $b =~ tr#/#/# <=> $a =~ tr#/#/# } keys %$bat) { + next if $_ eq ''; $self->close_directory($bat->{$_}, $p); } + $self->close_directory($bat->{''}, $p); $self->SUPER::close_edit($p); $p->clear; } @@ -3783,22 +5362,1394 @@ sub close_edit { sub abort_edit { my ($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) = @_; + 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) { + my $f = $m->{chg}; + if (defined $o{$f}) { + $self->$f($m); + } else { + fatal("Invalid change type: $f"); + } + } + + if (defined($self->{mergeinfo})) { + $self->change_dir_prop($self->{bat}{''}, "svn:mergeinfo", + $self->{mergeinfo}); + } + $self->rmdirs if $_rmdir; + if (@$mods == 0) { + $self->abort_edit; + } else { + $self->close_edit; + } + return scalar @$mods; +} + +package Git::SVN::Ra; +use vars qw/@ISA $config_dir $_ignore_refs_regex $_log_window_size/; +use strict; +use warnings; +my ($ra_invalid, $can_do_switch, %ignored_err, $RA); + +BEGIN { + # enforce temporary pool usage for some simple functions + no strict 'refs'; + for my $f (qw/rev_proplist get_latest_revnum get_uuid get_repos_root + get_file/) { + my $SUPER = "SUPER::$f"; + *$f = sub { + my $self = shift; + my $pool = SVN::Pool->new; + my @ret = $self->$SUPER(@_,$pool); + $pool->clear; + wantarray ? @ret : $ret[0]; + }; + } +} + +sub _auth_providers () { + [ + SVN::Client::get_simple_provider(), + SVN::Client::get_ssl_server_trust_file_provider(), + SVN::Client::get_simple_prompt_provider( + \&Git::SVN::Prompt::simple, 2), + SVN::Client::get_ssl_client_cert_file_provider(), + SVN::Client::get_ssl_client_cert_prompt_provider( + \&Git::SVN::Prompt::ssl_client_cert, 2), + SVN::Client::get_ssl_client_cert_pw_file_provider(), + SVN::Client::get_ssl_client_cert_pw_prompt_provider( + \&Git::SVN::Prompt::ssl_client_cert_pw, 2), + SVN::Client::get_username_provider(), + SVN::Client::get_ssl_server_trust_prompt_provider( + \&Git::SVN::Prompt::ssl_server_trust), + SVN::Client::get_username_prompt_provider( + \&Git::SVN::Prompt::username, 2) + ] +} + +sub escape_uri_only { + my ($uri) = @_; + my @tmp; + foreach (split m{/}, $uri) { + s/([^~\w.%+-]|%(?![a-fA-F0-9]{2}))/sprintf("%%%02X",ord($1))/eg; + push @tmp, $_; + } + join('/', @tmp); +} + +sub escape_url { + my ($url) = @_; + if ($url =~ m#^(https?)://([^/]+)(.*)$#) { + my ($scheme, $domain, $uri) = ($1, $2, escape_uri_only($3)); + $url = "$scheme://$domain$uri"; + } + $url; +} + +sub new { + my ($class, $url) = @_; + $url =~ s!/+$!!; + return $RA if ($RA && $RA->{url} eq $url); + + ::_req_svn(); + + SVN::_Core::svn_config_ensure($config_dir, undef); + my ($baton, $callbacks) = SVN::Core::auth_open_helper(_auth_providers); + my $config = SVN::Core::config_get_config($config_dir); + $RA = undef; + my $dont_store_passwords = 1; + my $conf_t = ${$config}{'config'}; + { + no warnings 'once'; + # The usage of $SVN::_Core::SVN_CONFIG_* variables + # produces warnings that variables are used only once. + # I had not found the better way to shut them up, so + # the warnings of type 'once' are disabled in this block. + if (SVN::_Core::svn_config_get_bool($conf_t, + $SVN::_Core::SVN_CONFIG_SECTION_AUTH, + $SVN::_Core::SVN_CONFIG_OPTION_STORE_PASSWORDS, + 1) == 0) { + SVN::_Core::svn_auth_set_parameter($baton, + $SVN::_Core::SVN_AUTH_PARAM_DONT_STORE_PASSWORDS, + bless (\$dont_store_passwords, "_p_void")); + } + if (SVN::_Core::svn_config_get_bool($conf_t, + $SVN::_Core::SVN_CONFIG_SECTION_AUTH, + $SVN::_Core::SVN_CONFIG_OPTION_STORE_AUTH_CREDS, + 1) == 0) { + $Git::SVN::Prompt::_no_auth_cache = 1; + } + } # no warnings 'once' + my $self = SVN::Ra->new(url => escape_url($url), auth => $baton, + config => $config, + pool => SVN::Pool->new, + auth_provider_callbacks => $callbacks); + $self->{url} = $url; + $self->{svn_path} = $url; + $self->{repos_root} = $self->get_repos_root; + $self->{svn_path} =~ s#^\Q$self->{repos_root}\E(/|$)##; + $self->{cache} = { check_path => { r => 0, data => {} }, + get_dir => { r => 0, data => {} } }; + $RA = bless $self, $class; +} + +sub check_path { + my ($self, $path, $r) = @_; + my $cache = $self->{cache}->{check_path}; + if ($r == $cache->{r} && exists $cache->{data}->{$path}) { + return $cache->{data}->{$path}; + } + my $pool = SVN::Pool->new; + my $t = $self->SUPER::check_path($path, $r, $pool); + $pool->clear; + if ($r != $cache->{r}) { + %{$cache->{data}} = (); + $cache->{r} = $r; + } + $cache->{data}->{$path} = $t; +} + +sub get_dir { + my ($self, $dir, $r) = @_; + my $cache = $self->{cache}->{get_dir}; + if ($r == $cache->{r}) { + if (my $x = $cache->{data}->{$dir}) { + return wantarray ? @$x : $x->[0]; + } + } + my $pool = SVN::Pool->new; + my ($d, undef, $props) = $self->SUPER::get_dir($dir, $r, $pool); + my %dirents = map { $_ => { kind => $d->{$_}->kind } } keys %$d; + $pool->clear; + if ($r != $cache->{r}) { + %{$cache->{data}} = (); + $cache->{r} = $r; + } + $cache->{data}->{$dir} = [ \%dirents, $r, $props ]; + wantarray ? (\%dirents, $r, $props) : \%dirents; +} + +sub DESTROY { + # do not call the real DESTROY since we store ourselves in $RA +} + +# get_log(paths, start, end, limit, +# discover_changed_paths, strict_node_history, receiver) +sub get_log { + my ($self, @args) = @_; + my $pool = SVN::Pool->new; + + # svn_log_changed_path_t objects passed to get_log are likely to be + # overwritten even if only the refs are copied to an external variable, + # so we should dup the structures in their entirety. Using an + # externally passed pool (instead of our temporary and quickly cleared + # pool in Git::SVN::Ra) does not help matters at all... + my $receiver = pop @args; + my $prefix = "/".$self->{svn_path}; + $prefix =~ s#/+($)##; + my $prefix_regex = qr#^\Q$prefix\E#; + push(@args, sub { + my ($paths) = $_[0]; + return &$receiver(@_) unless $paths; + $_[0] = (); + foreach my $p (keys %$paths) { + my $i = $paths->{$p}; + # Make path relative to our url, not repos_root + $p =~ s/$prefix_regex//; + my %s = map { $_ => $i->$_; } + qw/copyfrom_path copyfrom_rev action/; + if ($s{'copyfrom_path'}) { + $s{'copyfrom_path'} =~ s/$prefix_regex//; + } + $_[0]{$p} = \%s; + } + &$receiver(@_); + }); + + + # the limit parameter was not supported in SVN 1.1.x, so we + # drop it. Therefore, the receiver callback passed to it + # is made aware of this limitation by being wrapped if + # the limit passed to is being wrapped. + if ($SVN::Core::VERSION le '1.2.0') { + my $limit = splice(@args, 3, 1); + if ($limit > 0) { + my $receiver = pop @args; + push(@args, sub { &$receiver(@_) if (--$limit >= 0) }); + } + } + my $ret = $self->SUPER::get_log(@args, $pool); + $pool->clear; + $ret; +} + +sub trees_match { + my ($self, $url1, $rev1, $url2, $rev2) = @_; + my $ctx = SVN::Client->new(auth => _auth_providers); + my $out = IO::File->new_tmpfile; + + # older SVN (1.1.x) doesn't take $pool as the last parameter for + # $ctx->diff(), so we'll create a default one + my $pool = SVN::Pool->new_default_sub; + + $ra_invalid = 1; # this will open a new SVN::Ra connection to $url1 + $ctx->diff([], $url1, $rev1, $url2, $rev2, 1, 1, 0, $out, $out); + $out->flush; + my $ret = (($out->stat)[7] == 0); + close $out or croak $!; + + $ret; +} + +sub get_commit_editor { + my ($self, $log, $cb, $pool) = @_; + my @lock = $SVN::Core::VERSION ge '1.2.0' ? (undef, 0) : (); + $self->SUPER::get_commit_editor($log, $cb, @lock, $pool); +} + +sub gs_do_update { + my ($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; + $editor->set_path_strip($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) : (); + + # 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, $gs, $url_b, $editor) = @_; + my $path = $gs->{path}; + my $pool = SVN::Pool->new; + + my $full_url = $self->{url}; + my $old_url = $full_url; + $full_url .= '/' . $path if length $path; + my ($ra, $reparented); + + if ($old_url =~ m#^svn(\+ssh)?://# || + ($full_url =~ m#^https?://# && + escape_url($full_url) ne $full_url)) { + $_[0] = undef; + $self = undef; + $RA = undef; + $ra = Git::SVN::Ra->new($full_url); + $ra_invalid = 1; + } elsif ($old_url ne $full_url) { + SVN::_Ra::svn_ra_reparent($self->{session}, $full_url, $pool); + $self->{url} = $full_url; + $reparented = 1; + } + + $ra ||= $self; + $url_b = escape_url($url_b); + 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('', $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; + $editor->{git_commit_ok}; +} + +sub longest_common_path { + my ($gsv, $globs) = @_; + 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; + } + } + $longest_path; +} + +sub gs_fetch_loop_common { + my ($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 $longest_path = longest_common_path($gsv, $globs); + my $ra_url = $self->{url}; + my $find_trailing_edge; + 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) = @_; + [ $paths, + { author => $author, date => $date, log => $log } ]; + } + $self->get_log([$longest_path], $min, $max, 0, 1, 1, + sub { $revs{$_[1]} = _cb(@_) }); + if ($err) { + print "Checked through r$max\r"; + } else { + $find_trailing_edge = 1; + } + if ($err and $find_trailing_edge) { + print STDERR "Path '$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; + } + } + $find_trailing_edge = 0; + } + $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_map_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); + } + $INDEX_FILES{$gs->{index}} = 1; + } + foreach my $g (@$globs) { + my $k = "svn-remote.$g->{remote}." . + "$g->{t}-maxRev"; + Git::SVN::tmp_config($k, $r); + } + if ($ra_invalid) { + $_[0] = undef; + $self = undef; + $RA = undef; + $self = Git::SVN::Ra->new($ra_url); + $ra_invalid = undef; + } + } + # 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 $gs->rev_map_max >= $max; + next if defined $gs->rev_map_get($max); + $gs->rev_map_set($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 > $head); + } + Git::SVN::gc(); +} + +sub get_dir_globbed { + my ($self, $left, $depth, $r) = @_; + + my @x = eval { $self->get_dir($left, $r) }; + return unless scalar @x == 3; + my $dirents = $x[0]; + my @finalents; + foreach my $de (keys %$dirents) { + next if $dirents->{$de}->{kind} != $SVN::Node::dir; + if ($depth > 1) { + my @args = ("$left/$de", $depth - 1, $r); + foreach my $dir ($self->get_dir_globbed(@args)) { + push @finalents, "$de/$dir"; + } + } else { + push @finalents, $de; + } + } + @finalents; +} + +# return value: 0 -- don't ignore, 1 -- ignore +sub is_ref_ignored { + my ($g, $p) = @_; + my $refname = $g->{ref}->full_path($p); + return 1 if defined($g->{ignore_refs_regex}) && + $refname =~ m!$g->{ignore_refs_regex}!; + return 0 unless defined($_ignore_refs_regex); + return 1 if $refname =~ m!$_ignore_refs_regex!o; + return 0; +} + +sub match_globs { + my ($self, $exists, $paths, $globs, $r) = @_; + + sub get_dir_check { + my ($self, $exists, $g, $r) = @_; + + my @dirs = $self->get_dir_globbed($g->{path}->{left}, + $g->{path}->{depth}, + $r); + + foreach my $de (@dirs) { + 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)); + next unless $p =~ /$g->{path}->{regex}/; + $exists->{$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 is_ref_ignored($g, $p); + next if $exists->{$pathname}; + next if ($self->check_path($pathname, $r) != + $SVN::Node::dir); + $exists->{$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 { + my $ra = (ref $self)->new($url); + my $latest = $ra->get_latest_revnum; + $ra->get_log("", $latest, 0, 1, 0, 1, sub {}); + }; + } while ($@ && ($c = shift @components)); + $url; +} + +sub can_do_switch { + my $self = shift; + unless (defined $can_do_switch) { + my $pool = SVN::Pool->new; + my $rep = eval { + $self->do_switch(1, '', 0, $self->{url}, + SVN::Delta::Editor->new, $pool); + }; + if ($@) { + $can_do_switch = 0; + } else { + $rep->abort_report($pool); + $can_do_switch = 1; + } + $pool->clear; + } + $can_do_switch; +} + +sub skip_unknown_revs { + my ($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) { + my $err_key = $err->expanded_message; + # revision numbers change every time, filter them out + $err_key =~ s/\d+/\0/g; + $err_key = "$errno\0$err_key"; + unless ($ignored_err{$err_key}) { + warn "W: Ignoring error from SVN, path probably ", + "does not exist: ($errno): ", + $err->expanded_message,"\n"; + warn "W: Do not be alarmed at the above message ", + "git-svn is just searching aggressively for ", + "old history.\n", + "This may take a while on large repositories\n"; + $ignored_err{$err_key} = 1; + } + return; + } + die "Error from SVN, ($errno): ", $err->expanded_message,"\n"; +} + +package Git::SVN::Log; +use strict; +use warnings; +use POSIX qw/strftime/; +use Time::Local; +use constant commit_log_separator => ('-' x 72) . "\n"; +use vars qw/$TZ $limit $color $pager $non_recursive $verbose $oneline + %rusers $show_commit $incremental/; +my $l_fmt; + +sub cmt_showable { + my ($c) = @_; + return 1 if defined $c->{r}; + + # big commit message got truncated by the 16k pretty buffer in rev-list + if ($c->{l} && $c->{l}->[-1] eq "...\n" && + $c->{a_raw} =~ /\@([a-f\d\-]+)>$/) { + @{$c->{l}} = (); + my @log = command(qw/cat-file commit/, $c->{c}); + + # shift off the headers + shift @log while ($log[0] ne ''); + shift @log; + + # TODO: make $c->{l} not have a trailing newline in the future + @{$c->{l}} = map { "$_\n" } grep !/^git-svn-id: /, @log; + + (undef, $c->{r}, undef) = ::extract_metadata( + (grep(/^git-svn-id: /, @log))[-1]); + } + return defined $c->{r}; +} + +sub log_use_color { + return $color || Git->repository->get_colorbool('color.diff'); +} + +sub git_svn_log_cmd { + my ($r_min, $r_max, @args) = @_; + my $head = 'HEAD'; + my (@files, @log_opts); + foreach my $x (@args) { + if ($x eq '--' || @files) { + push @files, $x; + } else { + if (::verify_ref("$x^0")) { + $head = $x; + } else { + push @log_opts, $x; + } + } + } + + my ($url, $rev, $uuid, $gs) = ::working_head_info($head); + $gs ||= Git::SVN->_new; + my @cmd = (qw/log --abbrev-commit --pretty=raw --default/, + $gs->refname); + push @cmd, '-r' unless $non_recursive; + push @cmd, qw/--raw --name-status/ if $verbose; + push @cmd, '--color' if log_use_color(); + push @cmd, @log_opts; + if (defined $r_max && $r_max == $r_min) { + push @cmd, '--max-count=1'; + if (my $c = $gs->rev_map_get($r_max)) { + push @cmd, $c; + } + } elsif (defined $r_max) { + if ($r_max < $r_min) { + ($r_min, $r_max) = ($r_max, $r_min); + } + my (undef, $c_max) = $gs->find_rev_before($r_max, 1, $r_min); + my (undef, $c_min) = $gs->find_rev_after($r_min, 1, $r_max); + # If there are no commits in the range, both $c_max and $c_min + # will be undefined. If there is at least 1 commit in the + # range, both will be defined. + return () if !defined $c_min || !defined $c_max; + if ($c_min eq $c_max) { + push @cmd, '--max-count=1', $c_min; + } else { + push @cmd, '--boundary', "$c_min..$c_max"; + } + } + return (@cmd, @files); +} + +# adapted from pager.c +sub config_pager { + if (! -t *STDOUT) { + $ENV{GIT_PAGER_IN_USE} = 'false'; + $pager = undef; + return; + } + chomp($pager = command_oneline(qw(var GIT_PAGER))); + if ($pager eq 'cat') { + $pager = undef; + } + $ENV{GIT_PAGER_IN_USE} = defined($pager); +} + +sub run_pager { + return unless defined $pager; + pipe my ($rfd, $wfd) or return; + defined(my $pid = fork) or ::fatal "Can't fork: $!"; + if (!$pid) { + open STDOUT, '>&', $wfd or + ::fatal "Can't redirect to stdout: $!"; + return; + } + open STDIN, '<&', $rfd or ::fatal "Can't redirect stdin: $!"; + $ENV{LESS} ||= 'FRSX'; + exec $pager or ::fatal "Can't run pager: $! ($pager)"; +} + +sub format_svn_date { + # some systmes don't handle or mishandle %z, so be creative. + my $t = shift || time; + my $gm = timelocal(gmtime($t)); + my $sign = qw( + + - )[ $t <=> $gm ]; + my $gmoff = sprintf("%s%02d%02d", $sign, (gmtime(abs($t - $gm)))[2,1]); + return strftime("%Y-%m-%d %H:%M:%S $gmoff (%a, %d %b %Y)", localtime($t)); +} + +sub parse_git_date { + my ($t, $tz) = @_; + # Date::Parse isn't in the standard Perl distro :( + if ($tz =~ s/^\+//) { + $t += tz_to_s_offset($tz); + } elsif ($tz =~ s/^\-//) { + $t -= tz_to_s_offset($tz); + } + return $t; +} + +sub set_local_timezone { + if (defined $TZ) { + $ENV{TZ} = $TZ; + } else { + delete $ENV{TZ}; + } +} + +sub tz_to_s_offset { + my ($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) { + $au = $rusers{$author} || undef; + } + if (!$au) { + ($au) = ($author =~ /<([^>]+)\@[^>]+>$/); + } + $dest->{t} = $t; + $dest->{tz} = $tz; + $dest->{a} = $au; + $dest->{t_utc} = parse_git_date($t, $tz); +} + +sub process_commit { + my ($c, $r_min, $r_max, $defer) = @_; + if (defined $r_min && defined $r_max) { + if ($r_min == $c->{r} && $r_min == $r_max) { + show_commit($c); + return 0; + } + return 1 if $r_min == $r_max; + if ($r_min < $r_max) { + # we need to reverse the print order + return 0 if (defined $limit && --$limit < 0); + push @$defer, $c; + return 1; + } + if ($r_min != $r_max) { + return 1 if ($r_min < $c->{r}); + return 1 if ($r_max > $c->{r}); + } + } + return 0 if (defined $limit && --$limit < 0); + show_commit($c); + return 1; +} + +sub show_commit { + my $c = shift; + if ($oneline) { + my $x = "\n"; + if (my $l = $c->{l}) { + while ($l->[0] =~ /^\s*$/) { shift @$l } + $x = $l->[0]; + } + $l_fmt ||= 'A' . length($c->{r}); + print 'r',pack($l_fmt, $c->{r}),' | '; + print "$c->{c} | " if $show_commit; + print $x; + } else { + show_commit_normal($c); + } +} + +sub show_commit_changed_paths { + my ($c) = @_; + return unless $c->{changed}; + print "Changed paths:\n", @{$c->{changed}}; +} + +sub show_commit_normal { + my ($c) = @_; + print commit_log_separator, "r$c->{r} | "; + print "$c->{c} | " if $show_commit; + print "$c->{a} | ", format_svn_date($c->{t_utc}), ' | '; + my $nr_line = 0; + + if (my $l = $c->{l}) { + while ($l->[$#$l] eq "\n" && $#$l > 0 + && $l->[($#$l - 1)] eq "\n") { + pop @$l; + } + $nr_line = scalar @$l; + if (!$nr_line) { + print "1 line\n\n\n"; + } else { + if ($nr_line == 1) { + $nr_line = '1 line'; + } else { + $nr_line .= ' lines'; + } + print $nr_line, "\n"; + show_commit_changed_paths($c); + print "\n"; + print $_ foreach @$l; + } + } else { + print "1 line\n"; + show_commit_changed_paths($c); + print "\n"; + + } + foreach my $x (qw/raw stat diff/) { + if ($c->{$x}) { + print "\n"; + print $_ foreach @{$c->{$x}} + } + } +} + +sub cmd_show_log { + my (@args) = @_; + my ($r_min, $r_max); + my $r_last = -1; # prevent dupes + set_local_timezone(); + if (defined $::_revision) { + if ($::_revision =~ /^(\d+):(\d+)$/) { + ($r_min, $r_max) = ($1, $2); + } elsif ($::_revision =~ /^\d+$/) { + $r_min = $r_max = $::_revision; + } else { + ::fatal "-r$::_revision is not supported, use ", + "standard 'git log' arguments instead"; + } + } + + config_pager(); + @args = git_svn_log_cmd($r_min, $r_max, @args); + if (!@args) { + print commit_log_separator unless $incremental || $oneline; + return; + } + my $log = command_output_pipe(@args); + run_pager(); + my (@k, $c, $d, $stat); + my $esc_color = qr/(?:\033\[(?:(?:\d+;)*\d*)?m)*/; + while (<$log>) { + if (/^${esc_color}commit (?:- )?($::sha1_short)/o) { + my $cmt = $1; + if ($c && cmt_showable($c) && $c->{r} != $r_last) { + $r_last = $c->{r}; + process_commit($c, $r_min, $r_max, \@k) or + goto out; + } + $d = undef; + $c = { c => $cmt }; + } elsif (/^${esc_color}author (.+) (\d+) ([\-\+]?\d+)$/o) { + get_author_info($c, $1, $2, $3); + } elsif (/^${esc_color}(?:tree|parent|committer) /o) { + # ignore + } elsif (/^${esc_color}:\d{6} \d{6} $::sha1_short/o) { + push @{$c->{raw}}, $_; + } elsif (/^${esc_color}[ACRMDT]\t/) { + # we could add $SVN->{svn_path} here, but that requires + # remote access at the moment (repo_path_split)... + s#^(${esc_color})([ACRMDT])\t#$1 $2 #o; + push @{$c->{changed}}, $_; + } elsif (/^${esc_color}diff /o) { + $d = 1; + push @{$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) { + push @{$c->{l}}, $_; + } + } + if ($c && defined $c->{r} && $c->{r} != $r_last) { + $r_last = $c->{r}; + process_commit($c, $r_min, $r_max, \@k); + } + if (@k) { + ($r_min, $r_max) = ($r_max, $r_min); + process_commit($_, $r_min, $r_max) foreach reverse @k; + } +out: + close $log; + print commit_log_separator unless $incremental || $oneline; +} + +sub cmd_blame { + my $path = pop; + + config_pager(); + run_pager(); + + my ($fh, $ctx, $rev); + + if ($_git_format) { + ($fh, $ctx) = command_output_pipe('blame', @_, $path); + while (my $line = <$fh>) { + if ($line =~ /^\^?([[:xdigit:]]+)\s/) { + # Uncommitted edits show up as a rev ID of + # all zeros, which we can't look up with + # cmt_metadata + if ($1 !~ /^0+$/) { + (undef, $rev, undef) = + ::cmt_metadata($1); + $rev = '0' if (!$rev); + } else { + $rev = '0'; + } + $rev = sprintf('%-10s', $rev); + $line =~ s/^\^?[[:xdigit:]]+(\s)/$rev$1/; + } + print $line; + } + } else { + ($fh, $ctx) = command_output_pipe('blame', '-p', @_, 'HEAD', + '--', $path); + my ($sha1); + my %authors; + my @buffer; + my %dsha; #distinct sha keys + + while (my $line = <$fh>) { + push @buffer, $line; + if ($line =~ /^([[:xdigit:]]{40})\s\d+\s\d+/) { + $dsha{$1} = 1; + } + } + + my $s2r = ::cmt_sha2rev_batch([keys %dsha]); + + foreach my $line (@buffer) { + if ($line =~ /^([[:xdigit:]]{40})\s\d+\s\d+/) { + $rev = $s2r->{$1}; + $rev = '0' if (!$rev) + } + elsif ($line =~ /^author (.*)/) { + $authors{$rev} = $1; + $authors{$rev} =~ s/\s/_/g; + } + elsif ($line =~ /^\t(.*)$/) { + printf("%6s %10s %s\n", $rev, $authors{$rev}, $1); + } + } + } + command_close_pipe($fh, $ctx); +} + +package Git::SVN::Migration; +# these version numbers do NOT correspond to actual version numbers +# of git nor git-svn. They are just relative. +# +# v0 layout: .git/$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) +# +# v5 layout: .rev_db.$UUID => .rev_map.$UUID +# - newer, more-efficient format that uses 24-bytes per record +# with no filler space. +# - use xxd -c24 < .rev_map.$UUID to view and debug +# - This is a one-way migration, repositories updated to the +# new format will not be able to use old git-svn without +# rebuilding the .rev_db. Rebuilding the rev_db is not +# possible if noMetadata or useSvmProps are set; but should +# be no problem for users that use the (sensible) defaults. +use strict; +use warnings; +use Carp qw/croak/; +use File::Path qw/mkpath/; +use File::Basename qw/dirname basename/; +use vars qw/$_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 $ra->{repos_root}) || + ($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} || $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}:". + "$x->{ref_id}"); + command_noisy(qw/config --unset/, + "$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_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, $pattern_ok) = @_; + my $re = $glob; + $re =~ s!/+$!!g; # no need for trailing slashes + my (@left, @right, @patterns); + my $state = "left"; + my $die_msg = "Only one set of wildcard directories " . + "(e.g. '*' or '*/*/*') is supported: '$glob'\n"; + for my $part (split(m|/|, $glob)) { + if ($part =~ /\*/ && $part ne "*") { + die "Invalid pattern in '$glob': $part\n"; + } elsif ($pattern_ok && $part =~ /[{}]/ && + $part !~ /^\{[^{}]+\}/) { + die "Invalid pattern in '$glob': $part\n"; + } + if ($part eq "*") { + die $die_msg if $state eq "right"; + $state = "pattern"; + push(@patterns, "[^/]*"); + } elsif ($pattern_ok && $part =~ /^\{(.*)\}$/) { + die $die_msg if $state eq "right"; + $state = "pattern"; + my $p = quotemeta($1); + $p =~ s/\\,/|/g; + push(@patterns, "(?:$p)"); + } else { + if ($state eq "left") { + push(@left, $part); + } else { + push(@right, $part); + $state = "right"; + } + } + } + my $depth = @patterns; + if ($depth == 0) { + die "One '*' is needed in glob: '$glob'\n"; + } + my $left = join('/', @left); + my $right = join('/', @right); + $re = join('/', @patterns); + $re = join('\/', + grep(length, quotemeta($left), "($re)", quotemeta($right))); + my $left_re = qr/^\/\Q$left\E(\/|$)/; + bless { left => $left, right => $right, left_regex => $left_re, + regex => qr/$re/, glob => $glob, depth => $depth }, $class; +} + +sub full_path { + my ($self, $path) = @_; + return (length $self->{left} ? "$self->{left}/" : '') . + $path . (length $self->{right} ? "/$self->{right}" : ''); +} + __END__ Data structures: -$svn_log hashref (as returned by svn_log_raw) -{ - fh => file handle of the log file, - state => state of the log file parser (sep/msg/rev/msg_start...) -} -$log_msg hashref as returned by next_log_entry($svn_log) +$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() { - msg => 'whitespace-formatted log entry + log => 'whitespace-formatted log entry ', # trailing newline is preserved revision => '8', # integer date => '2004-02-24T17:01:44.108345Z', # commit date @@ -3806,6 +6757,7 @@ $log_msg hashref as returned by next_log_entry($svn_log) }; +# this is generated by generate_diff(); @mods = array of diff-index line hashes, each element represents one line of diff-index output |