diff options
Diffstat (limited to 'git-svn.perl')
| -rwxr-xr-x | git-svn.perl | 3200 |
1 files changed, 2549 insertions, 651 deletions
diff --git a/git-svn.perl b/git-svn.perl index ee7ef693fa..650c9e5f02 100755 --- a/git-svn.perl +++ b/git-svn.perl @@ -4,35 +4,54 @@ use warnings; use strict; use vars qw/ $AUTHOR $VERSION - $sha1 $sha1_short $_revision - $_q $_authors %users/; + $sha1 $sha1_short $_revision $_repository + $_q $_authors $_authors_prog %users/; $AUTHOR = 'Eric Wong <normalperson@yhbt.net>'; $VERSION = '@@GIT_VERSION@@'; +# From which subdir have we been invoked? +my $cmd_dir_prefix = eval { + command_oneline([qw/rev-parse --show-prefix/], STDERR => 0) +} || ''; + 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}) { + if (exists $ENV{GIT_SSH}) { + $ENV{SVN_SSH} = $ENV{GIT_SSH}; + if ($^O eq 'msys') { + $ENV{SVN_SSH} =~ s/\\/\\\\/g; + } + } +} $Git::SVN::Log::TZ = $ENV{TZ}; $ENV{TZ} = 'UTC'; $| = 1; # unbuffer STDOUT -sub fatal (@) { print STDERR @_; exit 1 } +sub fatal (@) { print STDERR "@_\n"; exit 1 } require SVN::Core; # use()-ing this causes segfaults for me... *shrug* require SVN::Ra; require SVN::Delta; if ($SVN::Core::VERSION lt '1.1.0') { - fatal "Need SVN::Core 1.1.0 or better (got $SVN::Core::VERSION)\n"; + 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 File::Spec; +use File::Find; use Getopt::Long qw/:config gnu_getopt no_ignore_case auto_abbrev/; use IPC::Open3; use Git; @@ -41,7 +60,8 @@ 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_input_pipe command_close_pipe + command_bidi_pipe command_close_bidi_pipe/) { for my $package ( qw(SVN::Git::Editor SVN::Git::Fetcher Git::SVN::Migration Git::SVN::Log Git::SVN), __PACKAGE__) { @@ -55,34 +75,42 @@ my ($SVN); $sha1 = qr/[a-f\d]{40}/; $sha1_short = qr/[a-f\d]{4,40}/; my ($_stdin, $_help, $_edit, - $_message, $_file, + $_message, $_file, $_branch_dest, $_template, $_shared, - $_version, $_fetch_all, $_no_rebase, + $_version, $_fetch_all, $_no_rebase, $_fetch_parent, $_merge, $_strategy, $_dry_run, $_local, - $_prefix, $_no_checkout, $_verbose); + $_prefix, $_no_checkout, $_url, $_verbose, + $_git_format, $_commit_url, $_tag); $Git::SVN::_follow_parent = 1; +$_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 ); + 'no-auth-cache' => \$Git::SVN::Prompt::_no_auth_cache, + 'ignore-paths=s' => \$SVN::Git::Fetcher::_ignore_regex ); my %fc_opts = ( 'follow-parent|follow!' => \$Git::SVN::_follow_parent, 'authors-file|A=s' => \$_authors, + '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, + '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, $_branches); +my ($_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, - 'minimize-url|m' => \$Git::SVN::_minimize_url, + '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 }, @@ -99,6 +127,7 @@ my %cmd = ( 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, @@ -117,13 +146,43 @@ my %cmd = ( '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, %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 } ], + tag => [ sub { $_tag = 1; cmd_branch(@_) }, + 'Create a tag in the SVN repository', + { 'message|m=s' => \$_message, + 'destination|d=s' => \$_branch_dest, + 'dry-run|n' => \$_dry_run } ], 'set-tree' => [ \&cmd_set_tree, "Set an SVN repository to a git tree-ish", - { 'stdin|' => \$_stdin, %cmt_opts, %fc_opts, } ], + { '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 } ], + { 'revision|r=i' => \$_revision + } ], + '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 } ], @@ -143,16 +202,18 @@ my %cmd = ( 'non-recursive' => \$Git::SVN::Log::non_recursive, 'authors-file|A=s' => \$_authors, 'color' => \$Git::SVN::Log::color, - 'pager=s' => \$Git::SVN::Log::pager, + 'pager=s' => \$Git::SVN::Log::pager } ], - 'find-rev' => [ \&cmd_find_rev, "Translate between SVN revision numbers and tree-ish", - { } ], + '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', @@ -160,6 +221,21 @@ my %cmd = ( '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", + {} ], ); my $cmd; @@ -168,13 +244,43 @@ for (my $i = 0; $i < @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 $cmd); -read_repo_config(\%opts); -Getopt::Long::Configure('pass_through') if ($cmd && $cmd eq 'log'); +read_git_config(\%opts); +if ($cmd && ($cmd eq 'log' || $cmd eq 'blame')) { + Getopt::Long::Configure('pass_through'); +} my $rv = GetOptions(%opts, 'help|H|h' => \$_help, 'version|V' => \$_version, 'minimize-connections' => \$Git::SVN::Migration::_minimize, 'id|i=s' => \$Git::SVN::default_ref_id, @@ -187,28 +293,10 @@ usage(0) if $_help; version() if $_version; usage(1) unless defined $cmd; load_authors() if $_authors; - -# make sure we're always running -unless ($cmd =~ /(?:clone|init|multi-init)$/) { - unless (-d $ENV{GIT_DIR}) { - if ($git_dir_user_set) { - die "GIT_DIR=$ENV{GIT_DIR} explicitly set, ", - "but it is not a directory\n"; - } - my $git_dir = delete $ENV{GIT_DIR}; - chomp(my $cdup = command_oneline(qw/rev-parse --show-cdup/)); - unless (length $cdup) { - die "Already at toplevel, but $git_dir ", - "not found '$cdup'\n"; - } - chdir $cdup or die "Unable to chdir up to '$cdup'\n"; - unless (-d $git_dir) { - die "$git_dir still not found after going to ", - "'$cdup'\n"; - } - $ENV{GIT_DIR} = $git_dir; - } +if (defined $_authors_prog) { + $_authors_prog = "'" . File::Spec->rel2abs($_authors_prog) . "'"; } + unless ($cmd =~ /^(?:clone|init|multi-init|commit-diff)$/) { Git::SVN::Migration::migration_check(); } @@ -227,7 +315,7 @@ 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; @@ -235,7 +323,7 @@ Usage: $0 <command> [options] [arguments]\n 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: @@ -271,7 +359,9 @@ sub do_git_init_db { } } command_noisy(@init_db); + $_repository = Git->repository(Repository => ".git"); } + command_noisy('config', 'core.autocrlf', 'false'); my $set; my $pfx = "svn-remote.$Git::SVN::default_repo_id"; foreach my $i (keys %icv) { @@ -280,6 +370,9 @@ sub do_git_init_db { command_noisy('config', "$pfx.$i", $icv{$i}); $set = $i; } + my $ignore_regex = \$SVN::Git::Fetcher::_ignore_regex; + command_noisy('config', "$pfx.ignore-paths", $$ignore_regex) + if defined $$ignore_regex; } sub init_subdir { @@ -287,29 +380,44 @@ sub init_subdir { 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 || defined $_branches || defined $_tags) && + (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 $_trunk || defined $_branches || defined $_tags) { + 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); } @@ -320,12 +428,22 @@ sub cmd_fetch { } my ($remote) = @_; if (@_ > 1) { - die "Usage: $0 fetch [--all] [svn-remote]\n"; + die "Usage: $0 fetch [--all] [--parent] [svn-remote]\n"; } - $remote ||= $Git::SVN::default_repo_id; - if ($_fetch_all) { + $Git::SVN::no_reuse_existing = undef; + if ($_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"; + } + # 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()); } } @@ -349,7 +467,7 @@ sub cmd_set_tree { } elsif (scalar @tmp > 1) { push @revs, reverse(command('rev-list',@tmp)); } else { - fatal "Failed to rev-parse $c\n"; + fatal "Failed to rev-parse $c"; } } my $gs = Git::SVN->new; @@ -359,93 +477,275 @@ sub cmd_set_tree { fatal "There are new revisions that were fetched ", "and need to be merged (or acknowledged) ", "before committing.\nlast rev: $r_last\n", - " current: $gs->{last_rev}\n"; + " current: $gs->{last_rev}"; } $gs->set_tree($_) foreach @revs; print "Done committing ",scalar @revs," revisions to SVN\n"; + unlink $gs->{index}; } sub cmd_dcommit { my $head = shift; + 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); + my ($url, $rev, $uuid, $gs) = working_head_info('HEAD', \@refs); unless ($gs) { die "Unable to determine upstream SVN information from ", - "$head history\n"; + "$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_url + } + } + + my $last_rev = $_revision if defined $_revision; + if ($url) { + print "Committing to $url ...\n"; } - my $last_rev; my ($linear_refs, $parents) = linearize_history($gs, \@refs); - foreach my $d (@$linear_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." + } + my $expect_url = $url; + Git::SVN::remove_username($expect_url); + 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) { fatal "Unable to extract revision information ", - "from commit $d~1\n"; + "from commit $d~1"; } } if ($_dry_run) { print "diff-tree $d~1 $d\n"; } else { + my $cmt_rev; my %ed_opts = ( r => $last_rev, log => get_commit_entry($d)->{log}, - ra => Git::SVN::Ra->new($gs->full_url), + ra => Git::SVN::Ra->new($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"; - $last_rev = $_[0]; }, + $cmt_rev = $_[0]; + }, svn_path => ''); if (!SVN::Git::Editor->new(\%ed_opts)->apply_diff) { print "No changes\n$d~1 == $d\n"; } elsif ($parents->{$d} && @{$parents->{$d}}) { - $gs->{inject_parents_dcommit}->{$last_rev} = + $gs->{inject_parents_dcommit}->{$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, $gs->refname); + if (@diff) { + @refs = (); + my ($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; + } } } - return if $_dry_run; - unless ($gs) { - warn "Could not determine fetch information for $url\n", - "Will not attempt to fetch and rebase commits.\n", - "This probably means you have useSvmProps and should\n", - "now resync your SVN::Mirror repository.\n"; - return; - } - $_fetch_all ? $gs->fetch_all : $gs->fetch; - unless ($_no_rebase) { - # we always want to rebase against the current HEAD, not any - # head that was passed to us - my @diff = command('diff-tree', 'HEAD', $gs->refname, '--'); - my @finish; - if (@diff) { - @finish = rebase_cmd(); - print STDERR "W: HEAD and ", $gs->refname, " differ, ", - "using @finish:\n", "@diff"; + + if ($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 "No changes between current HEAD and ", - $gs->refname, "\nResetting to the latest ", - $gs->refname, "\n"; - @finish = qw/reset --mixed/; + print "dcommitted on a detached HEAD because you gave ", + "a revision argument.\n", + "The rewritten commit is: ", $new_head, "\n"; } - command_noisy(@finish, $gs->refname); + command(['checkout', $old_head], STDERR => 0); } + + unlink $gs->{index}; +} + +sub cmd_branch { + my ($branch_name, $head) = @_; + + unless (defined $branch_name && length $branch_name) { + die(($_tag ? "tag" : "branch") . " name required\n"); + } + $head ||= 'HEAD'; + + my (undef, $rev, undef, $gs) = working_head_info($head); + my $src = $gs->full_url; + + 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 (defined $glob) { + my $dest_re = qr/\b\Q$_branch_dest\E\b/; + foreach my $g (@{$allglobs}) { + $g->{path}->{left} =~ /$dest_re/ or next; + if (defined $glob) { + die "Ambiguous destination: ", + $_branch_dest, "\nmatches both '", + $glob->{path}->{left}, "' and '", + $g->{path}->{left}, "'\n"; + } + $glob = $g; + } + unless (defined $glob) { + die "Unknown ", + $_tag ? "tag" : "branch", + " destination $_branch_dest\n"; + } + } + } + my ($lft, $rgt) = @{ $glob->{path} }{qw/left right/}; + my $dst = join '/', $remote->{url}, $lft, $branch_name, ($rgt || ()); + + 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; + 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, undef, $gs) = working_head_info($head, \@refs); + my (undef, undef, $uuid, $gs) = working_head_info($head, \@refs); unless ($gs) { die "Unable to determine upstream SVN information from ", "$head history\n"; } my $desired_revision = substr($revision_or_hash, 1); - $result = $gs->rev_db_get($desired_revision); + $result = $gs->rev_map_get($desired_revision, $uuid); } else { my (undef, $rev, undef) = cmt_metadata($revision_or_hash); $result = $rev; @@ -460,42 +760,186 @@ sub cmd_rebase { die "Unable to determine upstream SVN information from ", "working tree history\n"; } + if ($_dry_run) { + print "Remote Branch: " . $gs->refname . "\n"; + print "SVN URL: " . $url . "\n"; + return; + } if (command(qw/diff-index HEAD --/)) { print STDERR "Cannot rebase with uncommited changes:\n"; command_noisy('status'); exit 1; } unless ($_local) { + # rebase will checkout for us, so no need to do it explicitly + $_no_checkout = 'true'; $_fetch_all ? $gs->fetch_all : $gs->fetch; } command_noisy(rebase_cmd(), $gs->refname); + $gs->mkemptydirs; } sub cmd_show_ignore { my ($url, $rev, $uuid, $gs) = working_head_info('HEAD'); $gs ||= Git::SVN->new; my $r = (defined $_revision ? $_revision : $gs->ra->get_latest_revnum); - $gs->traverse_ignore(\*STDOUT, $gs->{path}, $r); + $gs->prop_walk($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; + } + # 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 $path; +} + +sub canonicalize_url { + my ($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); + } + else { + (undef, $props) = $gs->ra->get_file($path, $r, undef); + } + return $props; +} + +# cmd_propget (PROP, PATH) +# ------------------------ +# Print the SVN property PROP for PATH. +sub cmd_propget { + my ($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."); + } + print $props->{$prop} . "\n"; +} + +# 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 || defined $_branches || defined $_tags) { + unless (defined $_trunk || @_branches || @_tags) { usage(1); } - # there are currently some bugs that prevent multi-init/multi-fetch - # setups from working well without this. - $Git::SVN::_minimize_url = 1; - $_prefix = '' unless defined $_prefix; if (defined $url) { - $url =~ s#/+$##; + $url = canonicalize_url($url); init_subdir(@_); } do_git_init_db(); if (defined $_trunk) { - my $trunk_ref = $_prefix . 'trunk'; + 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) { @@ -505,13 +949,18 @@ sub cmd_multi_init { undef, $trunk_ref); } } - return unless defined $_branches || defined $_tags; + return unless @_branches || @_tags; my $ra = $url ? Git::SVN::Ra->new($url) : undef; - complete_url_ls_init($ra, $_branches, '--branches/-b', $_prefix); - complete_url_ls_init($ra, $_tags, '--tags/-t', $_prefix . 'tags/'); + foreach my $path (@_branches) { + complete_url_ls_init($ra, $path, '--branches/-b', $_prefix); + } + foreach my $path (@_tags) { + complete_url_ls_init($ra, $path, '--tags/-t', $_prefix.'tags/'); + } } sub cmd_multi_fetch { + $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}) { @@ -524,9 +973,9 @@ sub cmd_multi_fetch { sub cmd_commit_diff { my ($ta, $tb, $url) = @_; my $usage = "Usage: $0 commit-diff -r<revision> ". - "<tree-ish> <tree-ish> [<URL>]\n"; + "<tree-ish> <tree-ish> [<URL>]"; fatal($usage) if (!defined $ta || !defined $tb); - my $svn_path; + my $svn_path = ''; if (!defined $url) { my $gs = eval { Git::SVN->new }; if (!$gs) { @@ -542,7 +991,7 @@ sub cmd_commit_diff { if (defined $_message && defined $_file) { fatal("Both --message/-m and --file/-F specified ", "for the commit message.\n", - "I have no idea what you mean\n"); + "I have no idea what you mean"); } if (defined $_file) { $_message = file_to_s($_file); @@ -550,7 +999,6 @@ sub cmd_commit_diff { $_message ||= get_commit_entry($tb)->{log}; } my $ra ||= Git::SVN::Ra->new($url); - $svn_path ||= $ra->{svn_path}; my $r = $_revision; if ($r eq 'HEAD') { $r = $ra->get_latest_revnum; @@ -569,6 +1017,161 @@ sub cmd_commit_diff { } } +sub escape_uri_only { + my ($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 $repos_root = $gs->repos_root; + Git::SVN::remove_username($repos_root); + $result .= "Repository Root: " . escape_url($repos_root) . "\n"; + }; + if ($@) { + $result .= "Repository Root: (offline)\n"; + } + $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"; + + $result .= "Node Kind: " . + ($file_type eq "dir" ? "directory" : "file") . "\n"; + + my $schedule = $diff_status eq "A" + ? "add" + : ($diff_status eq "D" ? "delete" : "normal"); + $result .= "Schedule: $schedule\n"; + + if ($diff_status eq "A") { + print $result, "\n"; + return; + } + + my ($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); + } + } + close $log; + + 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 { + $checksum = md5sum($fh); + } + 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 { + open FILE, "<", $path or die $!; + $checksum = md5sum(\*FILE); + close FILE or die $!; + } + $result .= "Checksum: " . $checksum . "\n"; + } + + print $result, "\n"; +} + +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"; + } + my ($r, $c) = $gs->find_rev_before($target, not $_fetch_parent); + $gs->rev_map_set($r, $c, 'reset', $uuid); + print "r$r = $c ($gs->{ref_id})\n"; +} + +sub cmd_gc { + if (!$can_compress) { + warn "Compress::Zlib could not be found; unhandled.log " . + "files will not be compressed.\n"; + } + find({ wanted => \&gc_directory, no_chdir => 1}, "$ENV{GIT_DIR}/svn"); +} + ########################### utility functions ######################### sub rebase_cmd { @@ -584,6 +1187,17 @@ sub post_fetch_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; + } + } + 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')); @@ -597,6 +1211,7 @@ sub post_fetch_checkout { command_noisy(qw/read-tree -m -u -v HEAD HEAD/); print STDERR "Checked out HEAD:\n ", $gs->full_url, " r", $gs->last_rev, "\n"; + $gs->mkemptydirs($gs->last_rev); } sub complete_svn_url { @@ -605,7 +1220,7 @@ sub complete_svn_url { 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\n"); + "and a separate URL is not specified"); } return ($url, $path); } @@ -626,7 +1241,7 @@ sub complete_url_ls_init { $repo_path =~ s#^/+##; unless ($ra) { fatal("E: '$repo_path' is not a complete URL ", - "and a separate URL is not specified\n"); + "and a separate URL is not specified"); } } my $url = $ra->{url}; @@ -638,15 +1253,20 @@ sub complete_url_ls_init { "wanted to set to: $gs->{url}\n"; } command_oneline('config', $k, $gs->{url}) unless $orig_url; - my $remote_path = "$ra->{svn_path}/$repo_path/*"; + my $remote_path = "$gs->{path}/$repo_path"; + $remote_path =~ s{%([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+)/); if (length $pfx && $pfx !~ m#/$#) { die "--prefix='$pfx' must have a trailing slash '/'\n"; } - command_noisy('config', "svn-remote.$gs->{repo_id}.$n", - "$remote_path:refs/remotes/$pfx*"); + command_noisy('config', + '--add', + "svn-remote.$gs->{repo_id}.$n", + "$remote_path:refs/remotes/$pfx*" . + ('/*' x (($remote_path =~ tr/*/*/) - 1)) ); } sub verify_ref { @@ -688,30 +1308,63 @@ sub get_commit_entry { 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 { - print $log_fh $_ or croak $!; + if (/^From:/ || /^Signed-off-by:/) { + $saw_from = 1; + } + $msgbuf .= $_; } } + $msgbuf =~ s/\s+$//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 $!; if ($_edit || ($type eq 'tree')) { - my $editor = $ENV{VISUAL} || $ENV{EDITOR} || 'vi'; - # TODO: strip out spaces, comments, like git-commit.sh - system($editor, $commit_editmsg); + chomp(my $editor = command_oneline(qw(var GIT_EDITOR))); + system('sh', '-c', $editor.' "$@"', $editor, $commit_editmsg); } rename $commit_editmsg, $commit_msg or croak $!; - open $log_fh, '<', $commit_msg or croak $!; - { local $/; chomp($log_entry{log} = <$log_fh>); } - close $log_fh 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"; + } + + eval { $msg = Encode::encode('UTF-8', $msg, 1) }; + die "Could not encode as UTF-8:\n$msg\n" if $@; + + $log_entry{log} = $msg; + + close $log_fh or croak $!; + } unlink $commit_msg; \%log_entry; } @@ -752,8 +1405,7 @@ sub load_authors { } # convert GetOpt::Long specs for use by git-config -sub read_repo_config { - return unless -d $ENV{GIT_DIR}; +sub read_git_config { my $opts = shift; my @config_only; foreach my $o (keys %$opts) { @@ -764,7 +1416,7 @@ sub read_repo_config { my $v = $opts->{$o}; my ($key) = ($o =~ /^([a-zA-Z\-]+)/); $key =~ s/-//g; - my $arg = 'git-config'; + my $arg = 'git config'; $arg .= ' --int' if ($o =~ /[:=]i$/); $arg .= ' --bool' if ($o !~ /[:=][sfi]$/); if (ref $v eq 'ARRAY') { @@ -783,11 +1435,11 @@ sub read_repo_config { sub extract_metadata { my $id = shift or return (undef, undef, undef); my ($url, $rev, $uuid) = ($id =~ /^\s*git-svn-id:\s+(.*)\@(\d+) - \s([a-f\d\-]+)$/x); + \s([a-f\d\-]+)$/ix); if (!defined $rev || !$uuid || !$url) { # some of the original repositories I made had # identifiers like this: - ($rev, $uuid) = ($id =~/^\s*git-svn-id:\s(\d+)\@([a-f\d\-]+)/); + ($rev, $uuid) = ($id =~/^\s*git-svn-id:\s(\d+)\@([a-f\d\-]+)/i); } return ($url, $rev, $uuid); } @@ -797,9 +1449,44 @@ sub cmt_metadata { command(qw/cat-file commit/, shift)))[-1]); } +sub cmt_sha2rev_batch { + my %s2r; + my ($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; + } + + $size -= length($line); + last if ($size == 0); + } + } + + command_close_bidi_pipe($pid, $in, $out, $ctx); + + return \%s2r; +} + sub working_head_info { my ($head, $refs) = @_; - my ($fh, $ctx) = command_output_pipe('log', $head); + my @args = ('log', '--no-color', '--first-parent', '--pretty=medium'); + my ($fh, $ctx) = command_output_pipe(@args, $head); my $hash; my %max; while (<$fh>) { @@ -813,12 +1500,12 @@ sub working_head_info { if (defined $url && defined $rev) { next if $max{$url} and $max{$url} < $rev; if (my $gs = Git::SVN->find_by_url($url)) { - my $c = $gs->rev_db_get($rev); + 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_db_max; + $max{$url} ||= $gs->rev_map_max; } } } @@ -829,14 +1516,9 @@ sub working_head_info { sub read_commit_parents { my ($parents, $c) = @_; - my ($fh, $ctx) = command_output_pipe(qw/cat-file commit/, $c); - while (<$fh>) { - chomp; - last if ''; - /^parent ($sha1)/ or next; - push @{$parents->{$c}}, $1; - } - close $fh; # break the pipe + 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(/ /, $p); } sub linearize_history { @@ -880,18 +1562,83 @@ sub linearize_history { (\@linear_refs, \%parents); } +sub find_file_type_and_diff_status { + my ($path) = @_; + return ('dir', '') if $path eq ''; + + my $diff_output = + command_oneline(qw(diff --cached --name-status --), $path) || ""; + my $diff_status = (split(' ', $diff_output))[0] || ""; + + 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 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 { + ::fatal "Can't provide MD5 hash for unknown ref type: '", $ref, "'"; + } + return $md5->hexdigest(); +} + +sub gc_directory { + if ($can_compress && -f $_ && basename($_) eq "unhandled.log") { + my $out_filename = $_ . ".gz"; + open my $in_fh, "<", $_ or die "Unable to open $_: $!\n"; + binmode $in_fh; + my $gz = Compress::Zlib::gzopen($out_filename, "ab") or + die "Unable to open $out_filename: $!\n"; + + my $res; + while ($res = sysread($in_fh, my $str, 1024)) { + $gz->gzwrite($str) or + die "Unable to write: ".$gz->gzerror()."!\n"; + } + unlink $_ or die "unlink $File::Find::name: $!\n"; + } elsif (-f $_ && basename($_) eq "index") { + unlink $_ or die "unlink $_: $!\n"; + } +} + package Git::SVN; use strict; use warnings; +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_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 + +my ($_gc_nr, $_gc_period); -my $_repack_nr; # properties that we do not log: my %SKIP_PROP; BEGIN { @@ -927,31 +1674,35 @@ BEGIN { } } -my %LOCKFILES; -END { unlink keys %LOCKFILES if %LOCKFILES } + +my (%LOCKFILES, %INDEX_FILES); +END { + unlink keys %LOCKFILES if %LOCKFILES; + unlink keys %INDEX_FILES if %INDEX_FILES; +} sub resolve_local_globs { my ($url, $fetch, $glob_spec) = @_; return unless defined $glob_spec; my $ref = $glob_spec->{ref}; my $path = $glob_spec->{path}; - foreach (command(qw#for-each-ref --format=%(refname) refs/remotes#)) { - next unless m#^refs/remotes/$ref->{regex}$#; + 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: refs/remotes/$existing\n", - " globbed: refs/remotes/$refname\n"; + "existing: $existing\n", + " globbed: $refname\n"; } - my $u = (::cmt_metadata("refs/remotes/$refname"))[0]; + my $u = (::cmt_metadata("$refname"))[0]; $u =~ s!^\Q$url\E(/|$)!! or die - "refs/remotes/$refname: '$url' not found in '$u'\n"; + "$refname: '$url' not found in '$u'\n"; if ($pathname ne $u) { warn "W: Refspec glob conflict ", - "(ref: refs/remotes/$refname):\n", + "(ref: $refname):\n", "expected path: $pathname\n", " real path: $u\n", "Continuing ahead with $u\n"; @@ -992,12 +1743,18 @@ sub fetch_all { 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}; + 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)) { @@ -1010,7 +1767,7 @@ sub fetch_all { if ($fetch) { foreach my $p (sort keys %$fetch) { my $gs = Git::SVN->new($fetch->{$p}, $repo_id, $p); - my $lr = $gs->rev_db_max; + my $lr = $gs->rev_map_max; if (defined $lr) { $base = $lr if ($lr < $base); } @@ -1024,35 +1781,64 @@ sub fetch_all { 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=\s*(.*)\s*:\s*refs/remotes/(.+)\s*$!) { + if (m!^(.+)\.fetch=$svn_refspec$!) { my ($remote, $local_ref, $remote_ref) = ($1, $2, $3); - $local_ref =~ s{^/}{}; + die("svn-remote.$remote: remote ref '$remote_ref' " + . "must start with 'refs/'\n") + unless $remote_ref =~ m{^refs/}; $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!^(.+)\.(branches|tags)= - (.*):refs/remotes/(.+)\s*$/!x) { - my ($p, $g) = ($3, $4); - my $rs = $r->{$1}->{$2} = { - t => $2, - remote => $1, - path => Git::SVN::GlobSpec->new($p), - ref => Git::SVN::GlobSpec->new($g) }; + } 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/}; + my $rs = { + t => $t, + remote => $remote, + path => Git::SVN::GlobSpec->new($local_ref), + ref => Git::SVN::GlobSpec->new($remote_ref) }; if (length($rs->{ref}->{right}) != 0) { die "The '*' glob character must be the last ", - "character of '$g'\n"; + "character of '$remote_ref'\n"; } + 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"), + } + }; + $r->{$_}->{svm} = $svm; + } + } keys %$r; + $r; } sub init_vars { - if (defined $_repack) { - $_repack = 1000 if ($_repack <= 0); - $_repack_nr = $_repack; - $_repack_flags ||= '-d'; + $_gc_nr = $_gc_period = 1000; + if (defined $_repack || defined $_repack_flags) { + warn "Repack options are obsolete; they have no effect.\n"; } } @@ -1073,13 +1859,6 @@ sub verify_remotes_sanity { } } -# we allow more chars than remotes2config.sh... -sub sanitize_remote_name { - my ($name) = @_; - $name =~ tr{A-Za-z0-9:,/+-}{.}c; - $name; -} - sub find_existing_remote { my ($url, $remotes) = @_; return undef if $no_reuse_existing; @@ -1141,14 +1920,15 @@ sub init_remote_config { } } my ($xrepo_id, $xpath) = find_ref($self->refname); - if (defined $xpath) { + if (!$no_write && defined $xpath) { die "svn-remote.$xrepo_id.fetch already set to track ", - "$xpath:refs/remotes/", $self->refname, "\n"; + "$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); @@ -1173,14 +1953,29 @@ sub find_by_url { # repos_root and, path are optional next if defined $repos_root && $repos_root ne $u; my $fetch = $remotes->{$repo_id}->{fetch} || {}; - foreach (qw/branches tags/) { - resolve_local_globs($u, $fetch, - $remotes->{$repo_id}->{$_}); + foreach my $t (qw/branches tags/) { + foreach my $globspec (@{$remotes->{$repo_id}->{$t}}) { + resolve_local_globs($u, $fetch, $globspec); + } } my $p = $path; + my $rwr = rewrite_root({repo_id => $repo_id}); + my $svm = $remotes->{$repo_id}->{svm} + if defined $remotes->{$repo_id}->{svm}; unless (defined $p) { $p = $full_url; - $p =~ s#^\Q$u\E(?:/|$)## or next; + 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; @@ -1203,7 +1998,7 @@ sub find_ref { my ($ref_id) = @_; foreach (command(qw/config -l/)) { next unless m!^svn-remote\.(.+)\.fetch= - \s*(.*)\s*:\s*refs/remotes/(.+)\s*$!x; + \s*(.*?)\s*:\s*(.+?)\s*$!x; my ($repo_id, $path, $ref) = ($1, $2, $3); if ($ref eq $ref_id) { $path = '' if ($path =~ m#^\./?#); @@ -1220,16 +2015,16 @@ sub new { if (!defined $repo_id) { die "Could not find a \"svn-remote.*.fetch\" key ", "in the repository configuration matching: ", - "refs/remotes/$ref_id\n"; + "$ref_id\n"; } } my $self = _new($class, $repo_id, $ref_id, $path); if (!defined $self->{path} || !length $self->{path}) { my $fetch = command_oneline('config', '--get', "svn-remote.$repo_id.fetch", - ":refs/remotes/$ref_id\$") or + ":$ref_id\$") or die "Failed to read \"svn-remote.$repo_id.fetch\" ", - "\":refs/remotes/$ref_id\$\" in config\n"; + "\":$ref_id\$\" in config\n"; ($self->{path}, undef) = split(/\s*:\s*/, $fetch); } $self->{url} = command_oneline('config', '--get', @@ -1240,7 +2035,7 @@ sub new { } sub refname { - my ($refname) = "refs/remotes/$_[0]->{ref_id}" ; + my ($refname) = $_[0]->{ref_id} ; # 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: @@ -1319,7 +2114,7 @@ sub _set_svm_vars { chomp($src, $uuid); - $uuid =~ m{^[0-9a-f\-]{30,}$} + $uuid =~ m{^[0-9a-f\-]{30,}$}i or die "doesn't look right - svm:uuid is '$uuid'\n"; # the '!' is used to mark the repos_root!/relative/path @@ -1399,10 +2194,16 @@ sub svnsync { # see if we have it in our config, first: eval { my $section = "svn-remote.$self->{repo_id}"; - $svnsync = { - url => tmp_config('--get', "$section.svnsync-url"), - uuid => tmp_config('--get', "$section.svnsync-uuid"), - } + + 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; @@ -1413,11 +2214,11 @@ sub svnsync { my $rp = $self->ra->rev_proplist(0); my $url = $rp->{'svn:sync-from-url'} or die $err . "url\n"; - $url =~ m{^[a-z\+]+://} or + ($url) = ($url =~ m{^([a-z\+]+://\S+)$}) or die "doesn't look right - svn:sync-from-url is '$url'\n"; my $uuid = $rp->{'svn:sync-from-uuid'} or die $err . "uuid\n"; - $uuid =~ m{^[0-9a-f\-]{30,}$} or + ($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}"; @@ -1433,7 +2234,7 @@ sub ra_uuid { unless ($self->{ra_uuid}) { my $key = "svn-remote.$self->{repo_id}.uuid"; my $uuid = eval { tmp_config('--get', $key) }; - if (!$@ && $uuid && $uuid =~ /^([a-f\d\-]{30,})$/) { + if (!$@ && $uuid && $uuid =~ /^([a-f\d\-]{30,})$/i) { $self->{ra_uuid} = $uuid; } else { die "ra_uuid called without URL\n" unless $self->{url}; @@ -1444,9 +2245,24 @@ sub ra_uuid { $self->{ra_uuid}; } +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; +} + +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 ", @@ -1461,38 +2277,46 @@ sub ra { $ra; } -sub rel_path { - my ($self) = @_; - my $repos_root = $self->ra->{repos_root}; - return $self->{path} if ($self->{url} eq $repos_root); - my $url = $self->{url} . - (length $self->{path} ? "/$self->{path}" : $self->{path}); - $url =~ s!^\Q$repos_root\E(?:/+|$)!!g; - $url; -} - -sub traverse_ignore { - my ($self, $fh, $path, $r) = @_; - $path =~ s#^/+##g; - my $ra = $self->ra; - my ($dirent, undef, $props) = $ra->get_dir($path, $r); +# 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; - $p =~ s#^\Q$self->{path}\E(/|$)##; - print $fh length $p ? "\n# $p\n" : "\n# /\n"; - if (my $s = $props->{'svn:ignore'}) { - $s =~ s/[\r\n]+/\n/g; - 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"; - } - } + # 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->traverse_ignore($fh, "$path/$_", $r); + $self->prop_walk($self->{path} . $p . $_, $rev, $sub); } } @@ -1513,38 +2337,20 @@ sub last_rev_commit { return ($rev, $c); } } - my $db_path = $self->db_path; - unless (-e $db_path) { + my $map_path = $self->map_path; + unless (-e $map_path) { ($self->{last_rev}, $self->{last_commit}) = (undef, undef); return (undef, undef); } - my $offset = -41; # from tail - my $rl; - open my $fh, '<', $db_path or croak "$db_path not readable: $!\n"; - sysseek($fh, $offset, 2); # don't care for errors - sysread($fh, $rl, 41) == 41 or return (undef, undef); - chomp $rl; - while (('0' x40) eq $rl && sysseek($fh, 0, 1) != 0) { - $offset -= 41; - sysseek($fh, $offset, 2); # don't care for errors - sysread($fh, $rl, 41) == 41 or return (undef, undef); - chomp $rl; - } - if ($c && $c ne $rl) { - die "$db_path and ", $self->refname, - " inconsistent!:\n$c != $rl\n"; - } - my $rev = sysseek($fh, 0, 1) or croak $!; - $rev = ($rev - 41) / 41; - close $fh or croak $!; - ($self->{last_rev}, $self->{last_commit}) = ($rev, $c); - return ($rev, $c); + my ($rev, $commit) = $self->rev_map_max(1); + ($self->{last_rev}, $self->{last_commit}) = ($rev, $commit); + return ($rev, $commit); } sub get_fetch_range { my ($self, $min, $max) = @_; $max ||= $self->ra->get_latest_revnum; - $min ||= $self->rev_db_max; + $min ||= $self->rev_map_max; (++$min, $max); } @@ -1619,7 +2425,7 @@ sub assert_index_clean { $x = command_oneline('write-tree'); if ($y ne $x) { ::fatal "trees ($treeish) $y != $x\n", - "Something is seriously wrong...\n"; + "Something is seriously wrong..."; } }); } @@ -1646,12 +2452,6 @@ sub get_commit_parents { next if $seen{$p}; $seen{$p} = 1; push @ret, $p; - # MAXPARENT is defined to 16 in commit-tree.c: - last if @ret >= 16; - } - if (@tmp) { - die "r$log_entry->{revision}: No room for parents:\n\t", - join("\n\t", @tmp), "\n"; } @ret; } @@ -1681,6 +2481,47 @@ sub full_url { $self->{url} . (length $self->{path} ? '/' . $self->{path} : ''); } + +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 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}; + } + } + } +} + +sub gc { + command_noisy('gc', '--auto'); +}; + sub do_git_commit { my ($self, $log_entry) = @_; my $lr = $self->last_rev; @@ -1689,15 +2530,11 @@ sub do_git_commit { " was r$lr, but we are about to fetch: ", "r$log_entry->{revision}!\n"; } - if (my $c = $self->rev_db_get($log_entry->{revision})) { + if (my $c = $self->rev_map_get($log_entry->{revision})) { croak "$log_entry->{revision} = $c already exists! ", "Why are we refetching it?\n"; } - $ENV{GIT_AUTHOR_NAME} = $ENV{GIT_COMMITTER_NAME} = $log_entry->{name}; - $ENV{GIT_AUTHOR_EMAIL} = $ENV{GIT_COMMITTER_EMAIL} = - $log_entry->{email}; - $ENV{GIT_AUTHOR_DATE} = $ENV{GIT_COMMITTER_DATE} = $log_entry->{date}; - + my $old_env = set_commit_header_env($log_entry); my $tree = $log_entry->{tree}; if (!defined $tree) { $tree = $self->tmp_index_do(sub { @@ -1705,13 +2542,22 @@ sub do_git_commit { } die "Tree is not a valid sha1: $tree\n" if $tree !~ /^$::sha1$/o; - my @exec = ('git-commit-tree', $tree); + 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 $!; + 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 $!; @@ -1726,23 +2572,20 @@ sub do_git_commit { die "Failed to commit, invalid sha1: $commit\n"; } - $self->rev_db_set($log_entry->{revision}, $commit, 1); + $self->rev_map_set($log_entry->{revision}, $commit, 1); $self->{last_rev} = $log_entry->{revision}; $self->{last_commit} = $commit; - print "r$log_entry->{revision}"; + print "r$log_entry->{revision}" unless $::_q > 1; if (defined $log_entry->{svm_revision}) { - print " (\@$log_entry->{svm_revision})"; - $self->rev_db_set($log_entry->{svm_revision}, $commit, + 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"; - if (defined $_repack && (--$_repack_nr == 0)) { - $_repack_nr = $_repack; - # repack doesn't use any arguments with spaces in them, does it? - print "Running git repack $_repack_flags ...\n"; - command_noisy('repack', split(/\s+/, $_repack_flags)); - print "Done repacking\n"; + print " = $commit ($self->{ref_id})\n" unless $::_q > 1; + if (--$_gc_nr == 0) { + $_gc_nr = $_gc_period; + gc(); } return $commit; } @@ -1776,15 +2619,14 @@ sub find_parent_branch { unless (defined $paths) { my $err_handler = $SVN::Error::handler; $SVN::Error::handler = \&Git::SVN::Ra::skip_unknown_revs; - $self->ra->get_log([$self->{path}], $rev, $rev, 0, 1, 1, sub { - $paths = - Git::SVN::Ra::dup_changed_paths($_[0]) }); + $self->ra->get_log([$self->{path}], $rev, $rev, 0, 1, 1, + sub { $paths = $_[0] }); $SVN::Error::handler = $err_handler; } return undef unless defined $paths; # look for a parent from another branch: - my @b_path_components = split m#/#, $self->rel_path; + my @b_path_components = split m#/#, $self->{path}; my @a_path_components; my $i; while (@b_path_components) { @@ -1802,49 +2644,65 @@ sub find_parent_branch { my $r = $i->{copyfrom_rev}; my $repos_root = $self->ra->{repos_root}; my $url = $self->ra->{url}; - my $new_url = $repos_root . $branch_from; + my $new_url = $url . $branch_from; print STDERR "Found possible branch point: ", - "$new_url => ", $self->full_url, ", $r\n"; + "$new_url => ", $self->full_url, ", $r\n" + unless $::_q > 1; $branch_from =~ s#^/##; - my $gs = Git::SVN->find_by_url($new_url, $repos_root, $branch_from); - unless ($gs) { - my $ref_id = $self->{ref_id}; - $ref_id =~ s/\@\d+$//; - $ref_id .= "\@$r"; - # just grow a tail if we're not unique enough :x - $ref_id .= '-' while find_ref($ref_id); - print STDERR "Initializing parent: $ref_id\n"; - $gs = Git::SVN->init($new_url, '', $ref_id, $ref_id, 1); - } + my $gs = $self->other_gs($new_url, $url, + $branch_from, $r, $self->{ref_id}); my ($r0, $parent) = $gs->find_rev_before($r, 1); - if (!defined $r0 || !defined $parent) { - my ($base, $head) = parse_revision_argument(0, $r); - if ($base <= $r) { + { + 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->last_rev_commit; + ($r0, $parent) = $gs->find_rev_before($r, 1); } if (defined $r0 && defined $parent) { - print STDERR "Found branch parent: ($self->{ref_id}) $parent\n"; + 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"; + 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); + $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"; + 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"; + print STDERR "Successfully followed parent\n" unless $::_q > 1; return $self->make_log_entry($rev, [$parent], $ed); } return undef; @@ -1880,6 +2738,61 @@ sub do_fetch { $self->make_log_entry($rev, \@parents, $ed); } +sub mkemptydirs { + my ($self, $r) = @_; + + 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 + }; + + 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; + } + } + + if (open my $fh, '<', "$self->{dir}/unhandled.log") { + binmode $fh or croak "binmode: $!"; + while (<$fh>) { + scan($r, \%empty_dirs, $_) or last; + } + close $fh; + } + + my $strip = qr/\A\Q$self->{path}\E(?:\/|$)/; + foreach my $d (sort keys %empty_dirs) { + $d = uri_decode($d); + $d =~ s/$strip//; + next if -d $d; + if (-e _) { + warn "$d exists but is not a directory\n"; + } else { + print "creating empty directory: $d\n"; + mkpath([$d]); + } + } +} + sub get_untracked { my ($self, $ed) = @_; my @out; @@ -1922,12 +2835,100 @@ sub get_untracked { \@out; } +# 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 + (\d\d)\:(\d\d)\:(\d\d)\.\d*Z$/x) or croak "Unable to parse date: $date\n"; - "+0000 $Y-$m-$d $H:$M:$S"; + 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}; + } + + 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); + + # 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); + print STDERR "Initializing parent: $ref_id\n" unless $::_q > 1; + my ($u, $p, $repo_id) = ($new_url, '', $ref_id); + if ($u =~ s#^\Q$url\E(/|$)##) { + $p = $u; + $u = $url; + $repo_id = $self->{repo_id}; + } + $gs = Git::SVN->init($u, $p, $repo_id, $ref_id, 1); + } + $gs +} + +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" + } + 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"; + } } sub check_author { @@ -1935,20 +2936,270 @@ sub check_author { if (!defined $author || length $author == 0) { $author = '(no author)'; } - if (defined $::_authors && ! defined $::users{$author}) { - die "Author: $author not defined in $::_authors file\n"; + 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->rewrite_root || $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 ]; + } + } + } + # 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 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; + } + + push @merged_commit_ranges, + "$bottom_commit^..$top_commit"; + + if ( !defined $tip or $top > $tip ) { + $tip = $top; + $tip_commit = $top_commit; + } + } + return ($tip_commit, @merged_commit_ranges); +} + +sub _rev_list { + my ($msg_fh, $ctx) = command_output_pipe( + "rev-list", @_, + ); + my @rv; + while ( <$msg_fh> ) { + chomp; + push @rv, $_; + } + command_close_pipe($msg_fh, $ctx); + @rv; +} + +sub check_cherry_pick { + my $base = shift; + my $tip = shift; + my @ranges = @_; + my %commits = map { $_ => 1 } + _rev_list("--no-merges", $tip, "--not", $base); + for my $range ( @ranges ) { + delete @commits{_rev_list($range)}; + } + return (keys %commits); +} + +BEGIN { + memoize 'lookup_svn_merge'; + memoize 'check_cherry_pick'; +} + +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; + } + } + while ($excluded and @commits); + + return @excluded; +} + + +# 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... + + # 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->rewrite_root || $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 { + push @merge_tips, undef; + } + } + + 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 = command_oneline( + "merge-base", + @$parents, $merge_tip, + ); + + # double check that there are no missing non-merge commits + my (@incomplete) = check_cherry_pick( + $merge_base, $merge_tip, + @$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; + } + } + + # 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[$i]); + } + } + } + } + push @$parents, grep { defined } @new_parents; +} + sub make_log_entry { my ($self, $rev, $parents, $ed) = @_; my $untracked = $self->get_untracked($ed); + 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); + } + if ( $props->{"svn:mergeinfo"} ) { + $self->find_extra_svn_parents + ($ed, + $props->{"svn:mergeinfo"}, + \@parents); + } + } + 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, + my %log_entry = ( parents => \@parents, revision => $rev, log => ''); my $headrev; @@ -1975,13 +3226,34 @@ sub make_log_entry { $log_entry{log} .= "\n"; my $author = $log_entry{author} = check_author($log_entry{author}); my ($name, $email) = defined $::users{$author} ? @{$::users{$author}} - : ($author, undef); + : ($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 (defined $headrev && $self->use_svm_props) { if ($self->rewrite_root) { die "Can't have both 'useSvmProps' and 'rewriteRoot' ", "options set!\n"; } - my ($uuid, $r) = $headrev =~ m{^([a-f\d\-]{30,}):(\d+)$}; + 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; @@ -1998,23 +3270,28 @@ sub make_log_entry { remove_username($full_url); $log_entry{metadata} = "$full_url\@$r $uuid"; $log_entry{svm_revision} = $r; - $email ||= "$author\@$uuid" + $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" + $email ||= "$author\@$uuid"; + $commit_email ||= "$author\@$uuid"; } else { my $url = $self->metadata_url; remove_username($url); $log_entry{metadata} = "$url\@$rev " . $self->ra->get_uuid; $email ||= "$author\@" . $self->ra->get_uuid; + $commit_email ||= "$author\@" . $self->ra->get_uuid; } $log_entry{name} = $name; $log_entry{email} = $email; + $log_entry{commit_name} = $commit_name; + $log_entry{commit_email} = $commit_email; \%log_entry; } @@ -2035,7 +3312,7 @@ 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\n"); + ::fatal("Must have an existing revision to commit"); } my %ed_opts = ( r => $self->{last_rev}, log => $log_entry->{log}, @@ -2050,25 +3327,48 @@ sub set_tree { } } +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 rebuild { my ($self) = @_; - my $db_path = $self->db_path; - return if (-e $db_path && ! -z $db_path); + my $map_path = $self->map_path; + my $partial = (-e $map_path && ! -z $map_path); return unless ::verify_ref($self->refname.'^0'); - if (-f $self->{db_root}) { - rename $self->{db_root}, $db_path or die - "rename $self->{db_root} => $db_path failed: $!\n"; - my ($dir, $base) = ($db_path =~ m#^(.*?)/?([^/]+)$#); - symlink $base, $self->{db_root} or die - "symlink $base => $self->{db_root} failed: $!\n"; + 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; } - print "Rebuilding $db_path ...\n"; - my ($log, $ctx) = command_output_pipe("log", $self->refname); - my $latest; - my $full_url = $self->full_url; - remove_username($full_url); - my $svn_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->ra_uuid; my $c; while (<$log>) { if ( m{^commit ($::sha1)$} ) { @@ -2084,46 +3384,99 @@ sub rebuild { # if we merged or otherwise started elsewhere, this is # how we break out of it - if ((defined $svn_uuid && ($uuid ne $svn_uuid)) || - ($full_url && $url && ($url ne $full_url))) { + if (($uuid ne $svn_uuid) || + ($metadata_url && $url && ($url ne $metadata_url))) { next; } - $latest ||= $rev; - $svn_uuid ||= $uuid; + if ($partial && $head) { + print "Partial-rebuilding $map_path ...\n"; + print "Currently at $base_rev = $head\n"; + $head = undef; + } - $self->rev_db_set($rev, $c); + $self->rev_map_set($rev, $c); print "r$rev = $c\n"; } command_close_pipe($log, $ctx); - print "Done rebuilding $db_path\n"; + 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; } -# rev_db: +# 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... 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). +# 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_db_set { +sub _rev_map_set { my ($fh, $rev, $commit) = @_; - my $offset = $rev * 41; - # assume that append is the common case: - seek $fh, 0, 2 or croak $!; - my $pos = tell $fh; - if ($pos < $offset) { - for (1 .. (($offset - $pos) / 41)) { - print $fh (('0' x 40),"\n") or croak $!; + + 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; } } - seek $fh, $offset, 0 or croak $!; - print $fh $commit,"\n" or croak $!; + 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 { @@ -2136,12 +3489,13 @@ sub mkfile { } } -sub rev_db_set { +sub rev_map_set { my ($self, $rev, $commit, $update_ref, $uuid) = @_; length $commit == 40 or die "arg3 must be a full SHA1 hexsum\n"; - my $db = $self->db_path($uuid); + my $db = $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] }; @@ -2154,16 +3508,19 @@ sub rev_db_set { # and we can't afford to lose it because rebuild() won't work if ($self->use_svm_props || $self->no_metadata) { $sync = 1; - copy($db, $db_lock) or die "rev_db_set(@_): ", + copy($db, $db_lock) or die "rev_map_set(@_): ", "Failed to copy: ", "$db => $db_lock ($!)\n"; } else { - rename $db, $db_lock or die "rev_db_set(@_): ", + rename $db, $db_lock or die "rev_map_set(@_): ", "Failed to rename: ", "$db => $db_lock ($!)\n"; } - open my $fh, '+<', $db_lock or die "Couldn't open $db_lock: $!\n"; - _rev_db_set($fh, $rev, $commit); + + 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"; @@ -2171,10 +3528,12 @@ sub rev_db_set { close $fh or croak $!; if ($update_ref) { $_head = $self; - command_noisy('update-ref', '-m', "r$rev", + 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_db_set(@_): ", "Failed to rename: ", + rename $db_lock, $db or die "rev_map_set(@_): ", "Failed to rename: ", "$db_lock => $db ($!)\n"; delete $LOCKFILES{$db_lock}; if ($update_ref) { @@ -2184,36 +3543,103 @@ sub rev_db_set { } } -sub rev_db_max { - my ($self) = @_; +# 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 $db_path = $self->db_path; - my @stat = stat $db_path or return 0; - ($stat[7] % 41) == 0 or die "$db_path inconsistent size: $stat[7]\n"; - my $max = $stat[7] / 41; - (($max > 0) ? $max - 1 : 0); + 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 or croak "close: $!"; + $want_commit ? ($r, $c) : $r; } -sub rev_db_get { +sub rev_map_get { my ($self, $rev, $uuid) = @_; - my $ret; - my $offset = $rev * 41; - my $db_path = $self->db_path($uuid); - return undef unless -e $db_path; - open my $fh, '<', $db_path or croak $!; - if (sysseek($fh, $offset, 0) == $offset) { - my $read = sysread($fh, $ret, 40); - $ret = undef if ($read != 40 || $ret eq ('0'x40)); + 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 +} + +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; } - close $fh or croak $!; - $ret; + + 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; } +# 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) = @_; + my ($self, $rev, $eq_ok, $min_rev) = @_; --$rev unless $eq_ok; - while ($rev > 0) { - if (my $c = $self->rev_db_get($rev)) { + $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; @@ -2221,28 +3647,76 @@ sub find_rev_before { return (undef, 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; + } + return (undef, undef); +} + sub _new { my ($class, $repo_id, $ref_id, $path) = @_; unless (defined $repo_id && length $repo_id) { $repo_id = $Git::SVN::default_repo_id; } unless (defined $ref_id && length $ref_id) { - $_[2] = $ref_id = $Git::SVN::default_ref_id; + $_prefix = '' unless defined($_prefix); + $_[2] = $ref_id = + "refs/remotes/$_prefix$Git::SVN::default_ref_id"; } - $_[1] = $repo_id = sanitize_remote_name($repo_id); + $_[1] = $repo_id; my $dir = "$ENV{GIT_DIR}/svn/$ref_id"; + + # 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; + } + } + $_[3] = $path = '' unless (defined $path); - mkpath(["$ENV{GIT_DIR}/svn"]); + mkpath([$dir]); bless { ref_id => $ref_id, dir => $dir, index => "$dir/index", path => $path, config => "$ENV{GIT_DIR}/svn/config", - db_root => "$dir/.rev_db", repo_id => $repo_id }, $class; + map_root => "$dir/.rev_map", repo_id => $repo_id }, $class; +} + +# 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 db_path { +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; +} + +# the new replacement for .rev_db +sub map_path { my ($self, $uuid) = @_; $uuid ||= $self->ra_uuid; - "$self->{db_root}.$uuid"; + "$self->{map_root}.$uuid"; } sub uri_encode { @@ -2251,6 +3725,12 @@ sub uri_encode { $f } +sub uri_decode { + my ($f) = @_; + $f =~ s#%([0-9a-fA-F]{2})#chr(hex($1))#eg; + $f +} + sub remove_username { $_[0] =~ s{^([^:]*://)[^@]+@}{$1}; } @@ -2284,23 +3764,31 @@ sub ssl_server_trust { my ($cred, $realm, $failures, $cert_info, $may_save, $pool) = @_; $may_save = undef if $_no_auth_cache; print STDERR "Error validating server certificate for '$realm':\n"; - 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'; + # 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". @@ -2384,34 +3872,27 @@ sub _read_password { $password; } -package main; - -{ - 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; -} - package SVN::Git::Fetcher; use vars qw/@ISA/; use strict; use warnings; use Carp qw/croak/; +use File::Temp qw/tempfile/; use IO::File qw//; -use Digest::MD5; +use vars qw/$_ignore_regex/; # file baton members: path, mode_a, mode_b, pool, fh, blob, base sub new { - my ($class, $git_svn) = @_; + my ($class, $git_svn, $switch_path) = @_; my $self = SVN::Delta::Editor->new; bless $self, $class; - $self->{c} = $git_svn->{last_commit} if exists $git_svn->{last_commit}; + if (exists $git_svn->{last_commit}) { + $self->{c} = $git_svn->{last_commit}; + $self->{empty_symlinks} = + _mark_empty_symlinks($git_svn, $switch_path); + } + $self->{ignore_regex} = eval { command_oneline('config', '--get', + "svn-remote.$git_svn->{repo_id}.ignore-paths") }; $self->{empty} = {}; $self->{dir_prop} = {}; $self->{file_prop} = {}; @@ -2421,6 +3902,70 @@ sub new { $self; } +# this uses the Ra object, so it must be called before do_{switch,update}, +# not inside them (when the Git::SVN::Fetcher object is passed) to +# do_{switch,update} +sub _mark_empty_symlinks { + my ($git_svn, $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; + } + my $path = $_; + my (undef, $props) = + $git_svn->ra->get_file($pfx.$path, $rev, undef); + if ($props->{'svn:special'}) { + $ret{$path} = 1; + } + } + command_close_pipe($ls, $ctx); + \%ret; +} + +# returns true if a given path is inside a ".git" directory +sub in_dot_git { + $_[0] =~ m{(?:^|/)\.git(?:/|$)}; +} + +# 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 set_path_strip { my ($self, $path) = @_; $self->{path_strip} = qr/^\Q$path\E(\/|$)/ if length $path; @@ -2446,61 +3991,95 @@ sub git_path { sub delete_entry { my ($self, $path, $rev, $pb) = @_; + return undef if $self->is_path_ignored($path); my $gpath = $self->git_path($path); return undef if ($gpath eq ''); # remove entire directories. - if (command('ls-tree', $self->{c}, '--', $gpath) =~ /^040000 tree/) { + 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/, - $self->{c}, '--', $gpath); + $tree); local $/ = "\0"; while (<$ls>) { chomp; - $self->{gii}->remove($_); - print "\tD\t$_\n" unless $::_q; + 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); - $self->{empty}->{$path} = 0 } else { $self->{gii}->remove($gpath); print "\tD\t$gpath\n" unless $::_q; } + $self->{empty}->{$path} = 0; undef; } sub open_file { my ($self, $path, $pb, $rev) = @_; + my ($mode, $blob); + + goto out if $self->is_path_ignored($path); + my $gpath = $self->git_path($path); - my ($mode, $blob) = (command('ls-tree', $self->{c}, '--', $gpath) - =~ /^(\d{6}) blob ([a-f\d]{40})\t/); + ($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"; } + 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 add_file { my ($self, $path, $pb, $cp_path, $cp_rev) = @_; - my ($dir, $file) = ($path =~ m#^(.*?)/?([^/]+)$#); - delete $self->{empty}->{$dir}; - { path => $path, mode_a => 100644, mode_b => 100644, + my $mode; + + if (!$self->is_path_ignored($path)) { + my ($dir, $file) = ($path =~ m#^(.*?)/?([^/]+)$#); + delete $self->{empty}->{$dir}; + $mode = '100644'; + } + { path => $path, mode_a => $mode, mode_b => $mode, pool => SVN::Pool->new, action => 'A' }; } 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; + } + command_close_pipe($ls, $ctx); + $self->{empty}->{$path} = 0; + } my ($dir, $file) = ($path =~ m#^(.*?)/?([^/]+)$#); delete $self->{empty}->{$dir}; $self->{empty}->{$path} = 1; +out: { path => $path }; } 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; @@ -2508,6 +4087,7 @@ sub change_dir_prop { 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; @@ -2515,6 +4095,7 @@ sub absent_directory { 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; @@ -2522,6 +4103,7 @@ sub absent_file { 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; @@ -2537,70 +4119,105 @@ sub change_file_prop { 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 = $self->git_path($fb->{path}); if (my $fh = $fb->{fh}) { if (defined $exp) { seek($fh, 0, 0) or croak $!; - my $md5 = Digest::MD5->new; - $md5->addfile($fh); - my $got = $md5->hexdigest; + my $got = ::md5sum($fh); if ($got ne $exp) { die "Checksum mismatch: $path\n", "expected: $exp\n got: $got\n"; } } - sysseek($fh, 0, 0) or croak $!; if ($fb->{mode_b} == 120000) { - sysread($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"; } @@ -2631,7 +4248,6 @@ use strict; use warnings; use Carp qw/croak/; use IO::File; -use Digest::MD5; sub new { my ($class, $opts) = @_; @@ -2660,6 +4276,7 @@ sub new { $self->{rm} = { }; $self->{path_prefix} = length $self->{svn_path} ? "$self->{svn_path}/" : ''; + $self->{config} = $opts->{config}; return $self; } @@ -2681,11 +4298,12 @@ sub generate_diff { 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 + ($::sha1)\s($::sha1)\s ([MTCRAD])\d*$/xo) { push @mods, { mode_a => $1, mode_b => $2, - sha1_b => $3, chg => $4 }; - if ($4 =~ /^(?:C|R)$/) { + sha1_a => $3, sha1_b => $4, + chg => $5 }; + if ($5 =~ /^(?:C|R)$/) { $state = 'file_a'; } else { $state = 'file_b'; @@ -2758,7 +4376,7 @@ sub repo_path { sub url_path { my ($self, $path) = @_; if ($self->{url} =~ m#^https?://#) { - $path =~ s/([^a-zA-Z0-9_.-])/uc sprintf("%%%02x",ord($1))/eg; + $path =~ s!([^~a-zA-Z0-9_./-])!uc sprintf("%%%02x",ord($1))!eg; } $self->{url} . '/' . $self->repo_path($path); } @@ -2814,16 +4432,21 @@ sub open_or_add_dir { if (!defined $t) { die "$full_path not known in r$self->{r} or we have a bug!\n"; } - if ($t == $SVN::Node::none) { - return $self->add_directory($full_path, $baton, - undef, -1, $self->{pool}); - } 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"; + { + 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; } @@ -2843,6 +4466,57 @@ 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) = @_; my ($dir, $file) = split_path($m->{file_b}); @@ -2850,6 +4524,7 @@ sub A { my $fbat = $self->add_file($self->repo_path($m->{file_b}), $pbat, undef, -1); 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}); } @@ -2880,6 +4555,7 @@ sub R { 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; + $self->apply_autoprops($file, $fbat); $self->chg_file($fbat, $m); $self->close_file($fbat,undef,$self->{pool}); @@ -2906,42 +4582,53 @@ 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 _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 { @@ -2985,7 +4672,7 @@ sub apply_diff { if (defined $o{$f}) { $self->$f($m); } else { - fatal("Invalid change type: $f\n"); + fatal("Invalid change type: $f"); } } $self->rmdirs if $_rmdir; @@ -3001,12 +4688,13 @@ package Git::SVN::Ra; use vars qw/@ISA $config_dir $_log_window_size/; use strict; use warnings; -my ($can_do_switch, %ignored_err, $RA); +my ($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/) { + for my $f (qw/rev_proplist get_latest_revnum get_uuid get_repos_root + get_file/) { my $SUPER = "SUPER::$f"; *$f = sub { my $self = shift; @@ -3018,34 +4706,82 @@ BEGIN { } } +sub _auth_providers () { + [ + SVN::Client::get_simple_provider(), + SVN::Client::get_ssl_server_trust_file_provider(), + SVN::Client::get_simple_prompt_provider( + \&Git::SVN::Prompt::simple, 2), + SVN::Client::get_ssl_client_cert_file_provider(), + SVN::Client::get_ssl_client_cert_prompt_provider( + \&Git::SVN::Prompt::ssl_client_cert, 2), + SVN::Client::get_ssl_client_cert_pw_file_provider(), + SVN::Client::get_ssl_client_cert_pw_prompt_provider( + \&Git::SVN::Prompt::ssl_client_cert_pw, 2), + SVN::Client::get_username_provider(), + SVN::Client::get_ssl_server_trust_prompt_provider( + \&Git::SVN::Prompt::ssl_server_trust), + SVN::Client::get_username_prompt_provider( + \&Git::SVN::Prompt::username, 2) + ] +} + +sub escape_uri_only { + my ($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 $url); SVN::_Core::svn_config_ensure($config_dir, undef); - my ($baton, $callbacks) = SVN::Core::auth_open_helper([ - SVN::Client::get_simple_provider(), - SVN::Client::get_ssl_server_trust_file_provider(), - SVN::Client::get_simple_prompt_provider( - \&Git::SVN::Prompt::simple, 2), - SVN::Client::get_ssl_client_cert_file_provider(), - SVN::Client::get_ssl_client_cert_prompt_provider( - \&Git::SVN::Prompt::ssl_client_cert, 2), - SVN::Client::get_ssl_client_cert_pw_prompt_provider( - \&Git::SVN::Prompt::ssl_client_cert_pw, 2), - SVN::Client::get_username_provider(), - SVN::Client::get_ssl_server_trust_prompt_provider( - \&Git::SVN::Prompt::ssl_server_trust), - SVN::Client::get_username_prompt_provider( - \&Git::SVN::Prompt::username, 2), - ]); + my ($baton, $callbacks) = SVN::Core::auth_open_helper(_auth_providers); my $config = SVN::Core::config_get_config($config_dir); $RA = undef; - my $self = SVN::Ra->new(url => $url, auth => $baton, + 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(/|$)##; @@ -3094,15 +4830,74 @@ 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 $pool = SVN::Pool->new; - splice(@args, 3, 1) if ($SVN::Core::VERSION le '1.2.0'); + + # 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) : (); @@ -3153,19 +4948,25 @@ sub gs_do_switch { my $full_url = $self->{url}; my $old_url = $full_url; - $full_url .= "/$path" if length $path; + $full_url .= '/' . $path if length $path; my ($ra, $reparented); - if ($old_url ne $full_url) { - if ($old_url !~ m#^svn(\+ssh)?://#) { - SVN::_Ra::svn_ra_reparent($self->{session}, $full_url, - $pool); - $self->{url} = $full_url; - $reparented = 1; - } else { - $ra = Git::SVN::Ra->new($full_url); - } + + 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); @@ -3222,6 +5023,8 @@ sub gs_fetch_loop_common { 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 $err; @@ -3232,12 +5035,17 @@ sub gs_fetch_loop_common { }; sub _cb { my ($paths, $r, $author, $date, $log) = @_; - [ dup_changed_paths($paths), + [ $paths, { author => $author, date => $date, log => $log } ]; } $self->get_log([$longest_path], $min, $max, 0, 1, 1, sub { $revs{$_[1]} = _cb(@_) }); - if ($err && $max >= $head) { + if ($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, @@ -3249,13 +5057,14 @@ sub gs_fetch_loop_common { my $ok; $self->get_log([$longest_path], $min, $hi, 0, 1, 1, sub { - $ok ||= $_[1]; + $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; @@ -3265,7 +5074,7 @@ sub gs_fetch_loop_common { foreach my $gs ($self->match_globs(\%exists, $paths, $globs, $r)) { - if ($gs->rev_db_max >= $r) { + if ($gs->rev_map_max >= $r) { next; } next unless $gs->match_paths($paths, $r); @@ -3277,18 +5086,27 @@ sub gs_fetch_loop_common { if ($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 defined $gs->rev_db_get($max); - $gs->rev_db_set($max, 0 x40); + 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"; @@ -3299,6 +5117,28 @@ sub gs_fetch_loop_common { $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, $de; + } + } + @finalents; } sub match_globs { @@ -3306,11 +5146,12 @@ sub match_globs { sub get_dir_check { my ($self, $exists, $g, $r) = @_; - my @x = eval { $self->get_dir($g->{path}->{left}, $r) }; - return unless scalar @x == 3; - my $dirents = $x[0]; - foreach my $de (keys %$dirents) { - next if $dirents->{$de}->{kind} != $SVN::Node::dir; + + my @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} && @@ -3361,7 +5202,11 @@ sub minimize_url { my $c = ''; do { $url .= "/$c" if length $c; - eval { (ref $self)->new($url)->get_latest_revnum }; + eval { + my $ra = (ref $self)->new($url); + my $latest = $ra->get_latest_revnum; + $ra->get_log("", $latest, 0, 1, 0, 1, sub {}); + }; } while ($@ && ($c = shift @components)); $url; } @@ -3406,6 +5251,10 @@ sub skip_unknown_revs { warn "W: Ignoring error from SVN, path probably ", "does not exist: ($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; @@ -3413,28 +5262,12 @@ sub skip_unknown_revs { die "Error from SVN, ($errno): ", $err->expanded_message,"\n"; } -# svn_log_changed_path_t objects passed to get_log are likely to be -# overwritten even if only the refs are copied to an external variable, -# so we should dup the structures in their entirety. Using an externally -# passed pool (instead of our temporary and quickly cleared pool in -# Git::SVN::Ra) does not help matters at all... -sub dup_changed_paths { - my ($paths) = @_; - return undef unless $paths; - my %ret; - foreach my $p (keys %$paths) { - my $i = $paths->{$p}; - my %s = map { $_ => $i->$_ } - qw/copyfrom_path copyfrom_rev action/; - $ret{$p} = \%s; - } - \%ret; -} - package Git::SVN::Log; use strict; use warnings; 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; @@ -3463,49 +5296,23 @@ sub cmt_showable { } sub log_use_color { - return 1 if $color; - my ($dc, $dcvar); - $dcvar = 'color.diff'; - $dc = `git-config --get $dcvar`; - if ($dc eq '') { - # nothing at all; fallback to "diff.color" - $dcvar = 'diff.color'; - $dc = `git-config --get $dcvar`; - } - chomp($dc); - if ($dc eq 'auto') { - my $pc; - $pc = `git-config --get color.pager`; - if ($pc eq '') { - # does not have it -- fallback to pager.color - $pc = `git-config --bool --get pager.color`; - } - else { - $pc = `git-config --bool --get color.pager`; - if ($?) { - $pc = 'false'; - } - } - chomp($pc); - if (-t *STDOUT || (defined $pager && $pc eq 'true')) { - return ($ENV{TERM} && $ENV{TERM} ne 'dumb'); - } - return 0; - } - return 0 if $dc eq 'never'; - return 1 if $dc eq 'always'; - chomp($dc = `git-config --bool --get $dcvar`); - return ($dc eq 'true'); + 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) { - last if $x eq '--'; - next unless ::verify_ref("$x^0"); - $head = $x; - last; + if ($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); @@ -3515,53 +5322,80 @@ sub git_svn_log_cmd { 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, @log_opts; + if (defined $r_max && $r_max == $r_min) { push @cmd, '--max-count=1'; - if (my $c = $gs->rev_db_get($r_max)) { + if (my $c = $gs->rev_map_get($r_max)) { push @cmd, $c; } - } else { - my ($c_min, $c_max); - $c_max = $gs->rev_db_get($r_max); - $c_min = $gs->rev_db_get($r_min); - if (defined $c_min && defined $c_max) { - if ($r_max > $r_max) { - push @cmd, "$c_min..$c_max"; - } else { - push @cmd, "$c_max..$c_min"; - } - } elsif ($r_max > $r_min) { - push @cmd, $c_max; + } 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, $c_min; + push @cmd, '--boundary', "$c_min..$c_max"; } } - return @cmd; + return (@cmd, @files); } # 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') { + chomp(my $pager = command_oneline(qw(var GIT_PAGER))); + if ($pager eq 'cat') { $pager = undef; } + $ENV{GIT_PAGER_IN_USE} = defined($pager); } sub run_pager { - return unless -t *STDOUT; - pipe my $rfd, my $wfd or return; - defined(my $pid = fork) or ::fatal "Can't fork: $!\n"; + return unless -t *STDOUT && 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: $!\n"; + ::fatal "Can't redirect to stdout: $!"; return; } - open STDIN, '<&', $rfd or ::fatal "Can't redirect stdin: $!\n"; + open STDIN, '<&', $rfd or ::fatal "Can't redirect stdin: $!"; $ENV{LESS} ||= 'FRSX'; - exec $pager or ::fatal "Can't run pager: $! ($pager)\n"; + 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 { @@ -3584,13 +5418,7 @@ sub get_author_info { $dest->{t} = $t; $dest->{tz} = $tz; $dest->{a} = $au; - # Date::Parse isn't in the standard Perl distro :( - if ($tz =~ s/^\+//) { - $t += tz_to_s_offset($tz); - } elsif ($tz =~ s/^\-//) { - $t -= tz_to_s_offset($tz); - } - $dest->{t_utc} = $t; + $dest->{t_utc} = parse_git_date($t, $tz); } sub process_commit { @@ -3642,10 +5470,9 @@ sub show_commit_changed_paths { sub show_commit_normal { my ($c) = @_; - print '-' x72, "\nr$c->{r} | "; + print commit_log_separator, "r$c->{r} | "; print "$c->{c} | " if $show_commit; - print "$c->{a} | ", strftime("%Y-%m-%d %H:%M:%S %z (%a, %d %b %Y)", - localtime($c->{t_utc})), ' | '; + print "$c->{a} | ", format_svn_date($c->{t_utc}), ' | '; my $nr_line = 0; if (my $l = $c->{l}) { @@ -3685,11 +5512,7 @@ sub cmd_show_log { my (@args) = @_; my ($r_min, $r_max); my $r_last = -1; # prevent dupes - if (defined $TZ) { - $ENV{TZ} = $TZ; - } else { - delete $ENV{TZ}; - } + set_local_timezone(); if (defined $::_revision) { if ($::_revision =~ /^(\d+):(\d+)$/) { ($r_min, $r_max) = ($1, $2); @@ -3697,18 +5520,22 @@ sub cmd_show_log { $r_min = $r_max = $::_revision; } else { ::fatal "-r$::_revision is not supported, use ", - "standard \'git log\' arguments instead\n"; + "standard 'git log' arguments instead"; } } config_pager(); - @args = (git_svn_log_cmd($r_min, $r_max, @args), @args); + @args = git_svn_log_cmd($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 ($::sha1_short)/o) { + if (/^${esc_color}commit -?($::sha1_short)/o) { my $cmt = $1; if ($c && cmt_showable($c) && $c->{r} != $r_last) { $r_last = $c->{r}; @@ -3751,14 +5578,73 @@ sub cmd_show_log { process_commit($c, $r_min, $r_max, \@k); } if (@k) { - my $swap = $r_max; - $r_max = $r_min; - $r_min = $swap; + ($r_min, $r_max) = ($r_max, $r_min); process_commit($_, $r_min, $r_max) foreach reverse @k; } out: close $log; - print '-' x72,"\n" unless $incremental || $oneline; + 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, $ctx); } package Git::SVN::Migration; @@ -3785,6 +5671,16 @@ package Git::SVN::Migration; # --use-separate-remotes option in git-clone (now default) # - we do not automatically migrate to this (following # the example set by core git) +# +# v5 layout: .rev_db.$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/; @@ -3837,7 +5733,7 @@ sub migrate_from_v1 { 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 ", - "($::VERSION) of git-svn) does not. exist\n"; + "($::VERSION) of git-svn) does not exist.\n"; my ($fh, $ctx) = command_output_pipe(qw/rev-parse --symbolic --all/); while (<$fh>) { my $x = $_; @@ -3920,8 +5816,7 @@ sub minimize_connections { # skip existing cases where we already connect to the root if (($ra->{url} eq $ra->{repos_root}) || - (Git::SVN::sanitize_remote_name($ra->{repos_root}) eq - $repo_id)) { + ($ra->{repos_root} eq $repo_id)) { $root_repos->{$ra->{url}} = $repo_id; next; } @@ -3960,8 +5855,7 @@ sub minimize_connections { foreach my $url (keys %$new_urls) { # see if we can re-use an existing [svn-remote "repo_id"] # instead of creating a(n ugly) new section: - my $repo_id = $root_repos->{$url} || - Git::SVN::sanitize_remote_name($url); + my $repo_id = $root_repos->{$url} || $url; my $fetch = $new_urls->{$url}; foreach my $path (keys %$fetch) { @@ -3970,7 +5864,7 @@ sub minimize_connections { my $pfx = "svn-remote.$x->{old_repo_id}"; my $old_fetch = quotemeta("$x->{old_path}:". - "refs/remotes/$x->{ref_id}"); + "$x->{ref_id}"); command_noisy(qw/config --unset/, "$pfx.fetch", '^'. $old_fetch . '$'); delete $r->{$x->{old_repo_id}}-> @@ -3983,8 +5877,7 @@ sub minimize_connections { } } if (@emptied) { - my $file = $ENV{GIT_CONFIG} || $ENV{GIT_CONFIG_LOCAL} || - "$ENV{GIT_DIR}/config"; + my $file = $ENV{GIT_CONFIG} || "$ENV{GIT_DIR}/config"; print STDERR <<EOF; The following [svn-remote] sections in your config file ($file) are empty and can be safely removed: @@ -4040,15 +5933,20 @@ sub new { my ($class, $glob) = @_; my $re = $glob; $re =~ s!/+$!!g; # no need for trailing slashes - my $nr = ($re =~ s!^(.*)\*(.*)$!\(\[^/\]+\)!g); - my ($left, $right) = ($1, $2); - if ($nr > 1) { - die "Only one '*' wildcard expansion ", - "is supported (got $nr): '$glob'\n"; - } elsif ($nr == 0) { + $re =~ m!^([^*]*)(\*(?:/\*)*)(.*)$!; + my $temp = $re; + my ($left, $right) = ($1, $3); + $re = $2; + my $depth = $re =~ tr/*/*/; + if ($depth != $temp =~ tr/*/*/) { + die "Only one set of wildcard directories " . + "(e.g. '*' or '*/*/*') is supported: '$glob'\n"; + } + if ($depth == 0) { die "One '*' is needed for glob: '$glob'\n"; } - $re = quotemeta($left) . $re . quotemeta($right); + $re =~ s!\*!\[^/\]*!g; + $re = quotemeta($left) . "($re)" . quotemeta($right); if (length $left && !($left =~ s!/+$!!g)) { die "Missing trailing '/' on left side of: '$glob' ($left)\n"; } @@ -4057,7 +5955,7 @@ sub new { } my $left_re = qr/^\/\Q$left\E(\/|$)/; bless { left => $left, right => $right, left_regex => $left_re, - regex => qr/$re/, glob => $glob }, $class; + regex => qr/$re/, glob => $glob, depth => $depth }, $class; } sub full_path { |