diff options
Diffstat (limited to 'perl/Git/SVN.pm')
| -rw-r--r-- | perl/Git/SVN.pm | 238 |
1 files changed, 169 insertions, 69 deletions
diff --git a/perl/Git/SVN.pm b/perl/Git/SVN.pm index a59564fb34..b2c14e2ff5 100644 --- a/perl/Git/SVN.pm +++ b/perl/Git/SVN.pm @@ -9,11 +9,10 @@ use vars qw/$_no_metadata $_use_log_author $_add_author_from $_localtime/; use Carp qw/croak/; use File::Path qw/mkpath/; -use File::Copy qw/copy/; use IPC::Open3; use Memoize; # core since 5.8.0, Jul 2002 -use Memoize::Storable; use POSIX qw(:signal_h); +use Time::Local; use Git qw( command @@ -32,11 +31,7 @@ use Git::SVN::Utils qw( add_path_to_url ); -my $can_use_yaml; -BEGIN { - $can_use_yaml = eval { require Git::SVN::Memoize::YAML; 1}; -} - +my $memo_backend; our $_follow_parent = 1; our $_minimize_url = 'unset'; our $default_repo_id = 'svn'; @@ -1178,7 +1173,7 @@ sub find_parent_branch { or die "SVN connection failed somewhere...\n"; } print STDERR "Successfully followed parent\n" unless $::_q > 1; - return $self->make_log_entry($rev, [$parent], $ed); + return $self->make_log_entry($rev, [$parent], $ed, $r0, $branch_from); } return undef; } @@ -1210,26 +1205,93 @@ sub do_fetch { unless ($self->ra->gs_do_update($last_rev, $rev, $self, $ed)) { die "SVN connection failed somewhere...\n"; } - $self->make_log_entry($rev, \@parents, $ed); + $self->make_log_entry($rev, \@parents, $ed, $last_rev, $self->path); } sub mkemptydirs { my ($self, $r) = @_; + # add/remove/collect a paths table + # + # Paths are split into a tree of nodes, stored as a hash of hashes. + # + # Each node contains a 'path' entry for the path (if any) associated + # with that node and a 'children' entry for any nodes under that + # location. + # + # Removing a path requires a hash lookup for each component then + # dropping that node (and anything under it), which is substantially + # faster than a grep slice into a single hash of paths for large + # numbers of paths. + # + # For a large (200K) number of empty_dir directives this reduces + # scanning time to 3 seconds vs 10 minutes for grep+delete on a single + # hash of paths. + sub add_path { + my ($paths_table, $path) = @_; + my $node_ref; + + foreach my $x (split('/', $path)) { + if (!exists($paths_table->{$x})) { + $paths_table->{$x} = { children => {} }; + } + + $node_ref = $paths_table->{$x}; + $paths_table = $paths_table->{$x}->{children}; + } + + $node_ref->{path} = $path; + } + + sub remove_path { + my ($paths_table, $path) = @_; + my $nodes_ref; + my $node_name; + + foreach my $x (split('/', $path)) { + if (!exists($paths_table->{$x})) { + return; + } + + $nodes_ref = $paths_table; + $node_name = $x; + + $paths_table = $paths_table->{$x}->{children}; + } + + delete($nodes_ref->{$node_name}); + } + + sub collect_paths { + my ($paths_table, $paths_ref) = @_; + + foreach my $v (values %$paths_table) { + my $p = $v->{path}; + my $c = $v->{children}; + + collect_paths($c, $paths_ref); + + if (defined($p)) { + push(@$paths_ref, $p); + } + } + } + sub scan { - my ($r, $empty_dirs, $line) = @_; + my ($r, $paths_table, $line) = @_; if (defined $r && $line =~ /^r(\d+)$/) { return 0 if $1 > $r; } elsif ($line =~ /^ \+empty_dir: (.+)$/) { - $empty_dirs->{$1} = 1; + add_path($paths_table, $1); } elsif ($line =~ /^ \-empty_dir: (.+)$/) { - my @d = grep {m[^\Q$1\E(/|$)]} (keys %$empty_dirs); - delete @$empty_dirs{@d}; + remove_path($paths_table, $1); } 1; # continue }; - my %empty_dirs = (); + my @empty_dirs; + my %paths_table; + my $gz_file = "$self->{dir}/unhandled.log.gz"; if (-f $gz_file) { if (!can_compress()) { @@ -1240,7 +1302,7 @@ sub mkemptydirs { die "Unable to open $gz_file: $!\n"; my $line; while ($gz->gzreadline($line) > 0) { - scan($r, \%empty_dirs, $line) or last; + scan($r, \%paths_table, $line) or last; } $gz->gzclose; } @@ -1249,13 +1311,14 @@ sub mkemptydirs { if (open my $fh, '<', "$self->{dir}/unhandled.log") { binmode $fh or croak "binmode: $!"; while (<$fh>) { - scan($r, \%empty_dirs, $_) or last; + scan($r, \%paths_table, $_) or last; } close $fh; } + collect_paths(\%paths_table, \@empty_dirs); my $strip = qr/\A\Q@{[$self->path]}\E(?:\/|$)/; - foreach my $d (sort keys %empty_dirs) { + foreach my $d (sort @empty_dirs) { $d = uri_decode($d); $d =~ s/$strip//; next unless length($d); @@ -1321,7 +1384,7 @@ sub get_untracked { 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"; my $parsed_date; # Set next. @@ -1332,7 +1395,7 @@ sub parse_svn_date { $ENV{TZ} = 'UTC'; my $epoch_in_UTC = - POSIX::strftime('%s', $S, $M, $H, $d, $m - 1, $Y - 1900); + Time::Local::timelocal($S, $M, $H, $d, $m - 1, $Y - 1900); # Determine our local timezone (including DST) at the # time of $epoch_in_UTC. $Git::SVN::Log::TZ stored the @@ -1433,7 +1496,7 @@ sub check_author { } sub find_extra_svk_parents { - my ($self, $ed, $tickets, $parents) = @_; + my ($self, $tickets, $parents) = @_; # aha! svk:merge property changed... my @tickets = split "\n", $tickets; my @known_parents; @@ -1478,9 +1541,9 @@ sub find_extra_svk_parents { sub lookup_svn_merge { my $uuid = shift; my $url = shift; - my $merge = shift; + my $source = shift; + my $revs = shift; - my ($source, $revs) = split ":", $merge; my $path = $source; $path =~ s{^/}{}; my $gs = Git::SVN->find_by_url($url.$source, $url, $path); @@ -1537,7 +1600,7 @@ sub _rev_list { @rv; } -sub check_cherry_pick { +sub check_cherry_pick2 { my $base = shift; my $tip = shift; my $parents = shift; @@ -1552,7 +1615,8 @@ sub check_cherry_pick { delete $commits{$commit}; } } - return (keys %commits); + my @k = (keys %commits); + return (scalar @k, $k[0]); } sub has_no_changes { @@ -1577,7 +1641,16 @@ sub tie_for_persistent_memoization { my $hash = shift; my $path = shift; - if ($can_use_yaml) { + unless ($memo_backend) { + if (eval { require Git::SVN::Memoize::YAML; 1}) { + $memo_backend = 1; + } else { + require Memoize::Storable; + $memo_backend = -1; + } + } + + if ($memo_backend > 0) { tie %$hash => 'Git::SVN::Memoize::YAML', "$path.yaml"; } else { tie %$hash => 'Memoize::Storable', "$path.db", 'nstore'; @@ -1597,9 +1670,8 @@ sub tie_for_persistent_memoization { mkpath([$cache_path]) unless -d $cache_path; my %lookup_svn_merge_cache; - my %check_cherry_pick_cache; + my %check_cherry_pick2_cache; my %has_no_changes_cache; - my %_rev_list_cache; tie_for_persistent_memoization(\%lookup_svn_merge_cache, "$cache_path/lookup_svn_merge"); @@ -1608,11 +1680,11 @@ sub tie_for_persistent_memoization { LIST_CACHE => ['HASH' => \%lookup_svn_merge_cache], ; - tie_for_persistent_memoization(\%check_cherry_pick_cache, - "$cache_path/check_cherry_pick"); - memoize 'check_cherry_pick', + tie_for_persistent_memoization(\%check_cherry_pick2_cache, + "$cache_path/check_cherry_pick2"); + memoize 'check_cherry_pick2', SCALAR_CACHE => 'FAULT', - LIST_CACHE => ['HASH' => \%check_cherry_pick_cache], + LIST_CACHE => ['HASH' => \%check_cherry_pick2_cache], ; tie_for_persistent_memoization(\%has_no_changes_cache, @@ -1621,14 +1693,6 @@ sub tie_for_persistent_memoization { SCALAR_CACHE => ['HASH' => \%has_no_changes_cache], LIST_CACHE => 'FAULT', ; - - tie_for_persistent_memoization(\%_rev_list_cache, - "$cache_path/_rev_list"); - memoize '_rev_list', - SCALAR_CACHE => 'FAULT', - LIST_CACHE => ['HASH' => \%_rev_list_cache], - ; - } sub unmemoize_svn_mergeinfo_functions { @@ -1636,9 +1700,8 @@ sub tie_for_persistent_memoization { $memoized = 0; Memoize::unmemoize 'lookup_svn_merge'; - Memoize::unmemoize 'check_cherry_pick'; + Memoize::unmemoize 'check_cherry_pick2'; Memoize::unmemoize 'has_no_changes'; - Memoize::unmemoize '_rev_list'; } sub clear_memoized_mergeinfo_caches { @@ -1648,7 +1711,8 @@ sub tie_for_persistent_memoization { return unless -d $cache_path; for my $cache_file (("$cache_path/lookup_svn_merge", - "$cache_path/check_cherry_pick", + "$cache_path/check_cherry_pick", # old + "$cache_path/check_cherry_pick2", "$cache_path/has_no_changes")) { for my $suffix (qw(yaml db)) { my $file = "$cache_file.$suffix"; @@ -1702,11 +1766,49 @@ sub parents_exclude { return @excluded; } +# Compute what's new in svn:mergeinfo. +sub mergeinfo_changes { + my ($self, $old_path, $old_rev, $path, $rev, $mergeinfo_prop) = @_; + my %minfo = map {split ":", $_ } split "\n", $mergeinfo_prop; + my $old_minfo = {}; + + my $ra = $self->ra; + # Give up if $old_path isn't in the repo. + # This is probably a merge on a subtree. + if ($ra->check_path($old_path, $old_rev) != $SVN::Node::dir) { + warn "W: ignoring svn:mergeinfo on $old_path, ", + "directory didn't exist in r$old_rev\n"; + return {}; + } + my (undef, undef, $props) = $ra->get_dir($old_path, $old_rev); + if (defined $props->{"svn:mergeinfo"}) { + my %omi = map {split ":", $_ } split "\n", + $props->{"svn:mergeinfo"}; + $old_minfo = \%omi; + } + + my %changes = (); + foreach my $p (keys %minfo) { + my $a = $old_minfo->{$p} || ""; + my $b = $minfo{$p}; + # Omit merged branches whose ranges lists are unchanged. + next if $a eq $b; + # Remove any common range list prefix. + ($a ^ $b) =~ /^[\0]*/; + my $common_prefix = rindex $b, ",", $+[0] - 1; + $changes{$p} = substr $b, $common_prefix + 1; + } + print STDERR "Checking svn:mergeinfo changes since r$old_rev: ", + scalar(keys %minfo), " sources, ", + scalar(keys %changes), " changed\n"; + + return \%changes; +} # note: this function should only be called if the various dirprops # have actually changed sub find_extra_svn_parents { - my ($self, $ed, $mergeinfo, $parents) = @_; + my ($self, $mergeinfo, $parents) = @_; # aha! svk:merge property changed... memoize_svn_mergeinfo_functions(); @@ -1715,14 +1817,15 @@ sub find_extra_svn_parents { # 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", $mergeinfo; + my @merges = sort keys %$mergeinfo; my @merge_tips; my $url = $self->url; my $uuid = $self->ra_uuid; my @all_ranges; for my $merge ( @merges ) { my ($tip_commit, @ranges) = - lookup_svn_merge( $uuid, $url, $merge ); + lookup_svn_merge( $uuid, $url, + $merge, $mergeinfo->{$merge} ); unless (!$tip_commit or grep { $_ eq $tip_commit } @$parents ) { push @merge_tips, $tip_commit; @@ -1738,8 +1841,9 @@ sub find_extra_svn_parents { # check merge tips for new parents my @new_parents; for my $merge_tip ( @merge_tips ) { - my $spec = shift @merges; + my $merge = shift @merges; next unless $merge_tip and $excluded{$merge_tip}; + my $spec = "$merge:$mergeinfo->{$merge}"; # check out 'new' tips my $merge_base; @@ -1759,19 +1863,17 @@ sub find_extra_svn_parents { } # double check that there are no missing non-merge commits - my (@incomplete) = check_cherry_pick( + my ($ninc, $ifirst) = check_cherry_pick2( $merge_base, $merge_tip, $parents, @all_ranges, ); - if ( @incomplete ) { - warn "W:svn cherry-pick ignored ($spec) - missing " - .@incomplete." commit(s) (eg $incomplete[0])\n"; + if ($ninc) { + warn "W: svn cherry-pick ignored ($spec) - missing " . + "$ninc commit(s) (eg $ifirst)\n"; } else { - warn - "Found merge parent (svn:mergeinfo prop): ", - $merge_tip, "\n"; + warn "Found merge parent ($spec): ", $merge_tip, "\n"; push @new_parents, $merge_tip; } } @@ -1797,23 +1899,20 @@ sub find_extra_svn_parents { } sub make_log_entry { - my ($self, $rev, $parents, $ed) = @_; + my ($self, $rev, $parents, $ed, $parent_rev, $parent_path) = @_; 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); - } + my $props = $ed->{dir_prop}{$self->path}; + if ( $props->{"svk:merge"} ) { + $self->find_extra_svk_parents($props->{"svk:merge"}, \@parents); + } + if ( $props->{"svn:mergeinfo"} ) { + my $mi_changes = $self->mergeinfo_changes + ($parent_path, $parent_rev, + $self->path, $rev, + $props->{"svn:mergeinfo"}); + $self->find_extra_svn_parents($mi_changes, \@parents); } open my $un, '>>', "$self->{dir}/unhandled.log" or croak $!; @@ -2161,8 +2260,9 @@ sub rev_map_set { # both of these options make our .rev_db file very, very important # and we can't afford to lose it because rebuild() won't work if ($self->use_svm_props || $self->no_metadata) { + require File::Copy; $sync = 1; - copy($db, $db_lock) or die "rev_map_set(@_): ", + File::Copy::copy($db, $db_lock) or die "rev_map_set(@_): ", "Failed to copy: ", "$db => $db_lock ($!)\n"; } else { @@ -2338,7 +2438,7 @@ sub _new { # 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/(.*)}) { + if ($ref_id =~ m{^refs/remotes/(.+)}) { my $old_dir = "$ENV{GIT_DIR}/svn/$1"; if (-d $old_dir && ! -d $dir) { $dir = $old_dir; |