$_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 Time::Local;
use Memoize; # core since 5.8.0, Jul 2002
-use Memoize::Storable;
use POSIX qw(:signal_h);
+use Time::Local;
use Git qw(
command
command_noisy
command_output_pipe
command_close_pipe
+ get_tz_offset
+);
+use Git::SVN::Utils qw(
+ fatal
+ can_compress
+ join_paths
+ canonicalize_path
+ canonicalize_url
+ add_path_to_url
);
-use Git::SVN::Utils qw(fatal can_compress);
-
-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 $default_repo_id = 'svn';
} elsif (m!^(.+)\.usesvmprops=\s*(.*)\s*$!) {
$r->{$1}->{svm} = {};
} elsif (m!^(.+)\.url=\s*(.*)\s*$!) {
- $r->{$1}->{url} = $2;
+ $r->{$1}->{url} = canonicalize_url($2);
} elsif (m!^(.+)\.pushurl=\s*(.*)\s*$!) {
- $r->{$1}->{pushurl} = $2;
+ $r->{$1}->{pushurl} = canonicalize_url($2);
} elsif (m!^(.+)\.ignore-refs=\s*(.*)\s*$!) {
$r->{$1}->{ignore_refs_regex} = $2;
} elsif (m!^(.+)\.(branches|tags)=$svn_refspec$!) {
sub init_remote_config {
my ($self, $url, $no_write) = @_;
- $url =~ s!/+$!!; # strip trailing slash
+ $url = canonicalize_url($url);
my $r = read_all_remotes();
my $existing = find_existing_remote($url, $r);
if ($existing) {
print STDERR "Using higher level of URL: ",
"$url => $min_url\n";
}
- my $old_path = $self->{path};
- $self->{path} = $url;
- $self->{path} =~ s!^\Q$min_url\E(/|$)!!;
- if (length $old_path) {
- $self->{path} .= "/$old_path";
- }
+ my $old_path = $self->path;
+ $url =~ s!^\Q$min_url\E(/|$)!!;
+ $url = join_paths($url, $old_path);
+ $self->path($url);
$url = $min_url;
}
}
unless ($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;
+ my $path = $self->path;
+ $path =~ s{^/}{};
+ $path =~ s{%([0-9A-F]{2})}{chr hex($1)}ieg;
+ $self->path($path);
command_noisy('config', '--add',
"svn-remote.$self->{repo_id}.fetch",
- "$self->{path}:".$self->refname);
+ $self->path.":".$self->refname);
}
- $self->{url} = $url;
+ $self->url($url);
}
sub find_by_url { # repos_root and, path are optional
my ($class, $full_url, $repos_root, $path) = @_;
+ $full_url = canonicalize_url($full_url);
+
return undef unless defined $full_url;
remove_username($full_url);
remove_username($repos_root) if defined $repos_root;
}
$p =~ s#^\Q$z\E(?:/|$)#$prefix# or next;
}
+
+ # remote fetch paths are not URI escaped. Decode ours
+ # so they match
+ $p = uri_decode($p);
+
foreach my $f (keys %$fetch) {
next if $f ne $p;
return Git::SVN->new($fetch->{$f}, $repo_id, $f);
}
}
my $self = _new($class, $repo_id, $ref_id, $path);
- if (!defined $self->{path} || !length $self->{path}) {
+ if (!defined $self->path || !length $self->path) {
my $fetch = command_oneline('config', '--get',
"svn-remote.$repo_id.fetch",
":$ref_id\$") or
die "Failed to read \"svn-remote.$repo_id.fetch\" ",
"\":$ref_id\$\" in config\n";
- ($self->{path}, undef) = split(/\s*:\s*/, $fetch);
+ my($path) = split(/\s*:\s*/, $fetch);
+ $self->path($path);
}
- $self->{path} =~ s{/+}{/}g;
- $self->{path} =~ s{\A/}{};
- $self->{path} =~ s{/\z}{};
- $self->{url} = command_oneline('config', '--get',
- "svn-remote.$repo_id.url") or
+ {
+ my $path = $self->path;
+ $path =~ s{\A/}{};
+ $path =~ s{/\z}{};
+ $self->path($path);
+ }
+ my $url = command_oneline('config', '--get',
+ "svn-remote.$repo_id.url") or
die "Failed to read \"svn-remote.$repo_id.url\" in config\n";
+ $self->url($url);
$self->{pushurl} = eval { command_oneline('config', '--get',
"svn-remote.$repo_id.pushurl") };
$self->rebuild;
# It cannot end with a slash /, we'll throw up on this because
# SVN can't have directories with a slash in their name, either:
if ($refname =~ m{/$}) {
- die "ref: '$refname' ends with a trailing slash, this is ",
- "not permitted by git nor Subversion\n";
+ die "ref: '$refname' ends with a trailing slash; this is ",
+ "not permitted by git or Subversion\n";
}
# It cannot have ASCII control character space, tilde ~, caret ^,
#
# Additionally, % must be escaped because it is used for escaping
# and we want our escaped refname to be reversible
- $refname =~ s{([ \%~\^:\?\*\[\t])}{uc sprintf('%%%02x',ord($1))}eg;
+ $refname =~ s{([ \%~\^:\?\*\[\t])}{sprintf('%%%02X',ord($1))}eg;
# no slash-separated component can begin with a dot .
# /.* becomes /%2E*
# username is of no interest
$src =~ s{(^[a-z\+]*://)[^/@]*@}{$1};
- my $replace = $ra->{url};
- $replace .= "/$path" if length $path;
+ my $replace = add_path_to_url($ra->url, $path);
my $section = "svn-remote.$self->{repo_id}";
tmp_config("$section.svm-source", $src);
}
my $r = $ra->get_latest_revnum;
- my $path = $self->{path};
+ my $path = $self->path;
my %tried;
while (length $path) {
- unless ($tried{"$self->{url}/$path"}) {
+ my $try = add_path_to_url($self->url, $path);
+ unless ($tried{$try}) {
return $ra if $self->read_svm_props($ra, $path, $r);
- $tried{"$self->{url}/$path"} = 1;
+ $tried{$try} = 1;
}
$path =~ s#/?[^/]+$##;
}
die "Path: '$path' should be ''\n" if $path ne '';
return $ra if $self->read_svm_props($ra, $path, $r);
- $tried{"$self->{url}/$path"} = 1;
+ $tried{ add_path_to_url($self->url, $path) } = 1;
- if ($ra->{repos_root} eq $self->{url}) {
+ if ($ra->{repos_root} eq $self->url) {
die @err, (map { " $_\n" } keys %tried), "\n";
}
$path = $ra->{svn_path};
$ra = Git::SVN::Ra->new($ra->{repos_root});
while (length $path) {
- unless ($tried{"$ra->{url}/$path"}) {
+ my $try = add_path_to_url($ra->url, $path);
+ unless ($tried{$try}) {
$ok = $self->read_svm_props($ra, $path, $r);
last if $ok;
- $tried{"$ra->{url}/$path"} = 1;
+ $tried{$try} = 1;
}
$path =~ s#/?[^/]+$##;
}
die "Path: '$path' should be ''\n" if $path ne '';
$ok ||= $self->read_svm_props($ra, $path, $r);
- $tried{"$ra->{url}/$path"} = 1;
+ $tried{ add_path_to_url($ra->url, $path) } = 1;
if (!$ok) {
die @err, (map { " $_\n" } keys %tried), "\n";
}
- Git::SVN::Ra->new($self->{url});
+ Git::SVN::Ra->new($self->url);
}
sub svnsync {
if (!$@ && $uuid && $uuid =~ /^([a-f\d\-]{30,})$/i) {
$self->{ra_uuid} = $uuid;
} else {
- die "ra_uuid called without URL\n" unless $self->{url};
+ die "ra_uuid called without URL\n" unless $self->url;
$self->{ra_uuid} = $self->ra->get_uuid;
tmp_config('--add', $key, $self->{ra_uuid});
}
sub ra {
my ($self) = shift;
- my $ra = Git::SVN::Ra->new($self->{url});
+ 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) {
$path =~ s#^/*#/#g;
my $p = $path;
# Strip the irrelevant part of the path.
- $p =~ s#^/+\Q$self->{path}\E(/|$)#/#;
+ $p =~ s#^/+\Q@{[$self->path]}\E(/|$)#/#;
# Ensure the path is terminated by a `/'.
$p =~ s#/*$#/#;
foreach (sort keys %$dirent) {
next if $dirent->{$_}->{kind} != $SVN::Node::dir;
- $self->prop_walk($self->{path} . $p . $_, $rev, $sub);
+ $self->prop_walk($self->path . $p . $_, $rev, $sub);
}
}
sub metadata_url {
my ($self) = @_;
- ($self->rewrite_root || $self->{url}) .
- (length $self->{path} ? '/' . $self->{path} : '');
+ my $url = $self->rewrite_root || $self->url;
+ return canonicalize_url( add_path_to_url( $url, $self->path ) );
}
sub full_url {
my ($self) = @_;
- $self->{url} . (length $self->{path} ? '/' . $self->{path} : '');
+ return canonicalize_url( add_path_to_url( $self->url, $self->path ) );
}
sub full_pushurl {
my ($self) = @_;
if ($self->{pushurl}) {
- return $self->{pushurl} . (length $self->{path} ? '/' .
- $self->{path} : '');
+ return canonicalize_url( add_path_to_url( $self->{pushurl}, $self->path ) );
} else {
return $self->full_url;
}
sub match_paths {
my ($self, $paths, $r) = @_;
- return 1 if $self->{path} eq '';
- if (my $path = $paths->{"/$self->{path}"}) {
+ return 1 if $self->path eq '';
+ if (my $path = $paths->{"/".$self->path}) {
return ($path->{action} eq 'D') ? 0 : 1;
}
- $self->{path_regex} ||= qr/^\/\Q$self->{path}\E\//;
+ $self->{path_regex} ||= qr{^/\Q@{[$self->path]}\E/};
if (grep /$self->{path_regex}/, keys %$paths) {
return 1;
}
my $c = '';
- foreach (split m#/#, $self->{path}) {
+ foreach (split m#/#, $self->path) {
$c .= "/$_";
next unless ($paths->{$c} &&
($paths->{$c}->{action} =~ /^[AR]$/));
- if ($self->ra->check_path($self->{path}, $r) ==
+ if ($self->ra->check_path($self->path, $r) ==
$SVN::Node::dir) {
return 1;
}
unless (defined $paths) {
my $err_handler = $SVN::Error::handler;
$SVN::Error::handler = \&Git::SVN::Ra::skip_unknown_revs;
- $self->ra->get_log([$self->{path}], $rev, $rev, 0, 1, 1,
+ $self->ra->get_log([$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->{path};
+ my @b_path_components = split m#/#, $self->path;
my @a_path_components;
my $i;
while (@b_path_components) {
}
my $r = $i->{copyfrom_rev};
my $repos_root = $self->ra->{repos_root};
- my $url = $self->ra->{url};
- my $new_url = $url . $branch_from;
+ my $url = $self->ra->url;
+ my $new_url = canonicalize_url( add_path_to_url( $url, $branch_from ) );
print STDERR "Found possible branch point: ",
"$new_url => ", $self->full_url, ", $r\n"
unless $::_q > 1;
($base, $head) = parse_revision_argument(0, $r);
} else {
if ($r0 < $r) {
- $gs->ra->get_log([$gs->{path}], $r0 + 1, $r, 1,
+ $gs->ra->get_log([$gs->path], $r0 + 1, $r, 1,
0, 1, sub { $base = $_[1] - 1 });
}
}
# at the moment), so we can't rely on it
$self->{last_rev} = $r0;
$self->{last_commit} = $parent;
- $ed = Git::SVN::Fetcher->new($self, $gs->{path});
+ $ed = Git::SVN::Fetcher->new($self, $gs->path);
$gs->ra->gs_do_switch($r0, $rev, $gs,
$self->full_url, $ed)
or die "SVN connection failed somewhere...\n";
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;
}
# we can have a branch that was deleted, then re-added
# under the same name but copied from another path, in
# which case we'll have multiple parents (we don't
- # want to break the original ref, nor lose copypath info):
+ # want to break the original ref or lose copypath info):
if (my $log_entry = $self->find_parent_branch($paths, $rev)) {
push @{$log_entry->{parents}}, $lc;
return $log_entry;
unless ($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()) {
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;
}
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;
}
- my $strip = qr/\A\Q$self->{path}\E(?:\/|$)/;
- foreach my $d (sort keys %empty_dirs) {
+ collect_paths(\%paths_table, \@empty_dirs);
+ my $strip = qr/\A\Q@{[$self->path]}\E(?:\/|$)/;
+ foreach my $d (sort @empty_dirs) {
$d = uri_decode($d);
$d =~ s/$strip//;
next unless length($d);
\@out;
}
-sub get_tz {
- # 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 ];
- return sprintf("%s%02d%02d", $sign, (gmtime(abs($t - $gm)))[2,1]);
-}
-
# parse_svn_date(DATE)
# --------------------
# Given a date (in UTC) from Subversion, return a string in the format
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.
$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
delete $ENV{TZ};
}
- my $our_TZ = get_tz();
+ my $our_TZ = get_tz_offset();
# This converts $epoch_in_UTC into our local timezone.
my ($sec, $min, $hour, $mday, $mon, $year,
}
sub find_extra_svk_parents {
- my ($self, $ed, $tickets, $parents) = @_;
+ my ($self, $tickets, $parents) = @_;
# aha! svk:merge property changed...
my @tickets = split "\n", $tickets;
my @known_parents;
for my $ticket ( @tickets ) {
my ($uuid, $path, $rev) = split /:/, $ticket;
if ( $uuid eq $self->ra_uuid ) {
- my $url = $self->{url};
- my $repos_root = $url;
+ my $repos_root = $self->url;
my $branch_from = $path;
$branch_from =~ s{^/}{};
- my $gs = $self->other_gs($repos_root."/".$branch_from,
- $url,
+ my $gs = $self->other_gs(add_path_to_url( $repos_root, $branch_from ),
+ $repos_root,
$branch_from,
$rev,
$self->{ref_id});
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);
my @merged_commit_ranges;
# find the tip
for my $range ( @ranges ) {
+ if ($range =~ /[*]$/) {
+ warn "W: Ignoring partial merge in svn:mergeinfo "
+ ."dirprop: $source:$range\n";
+ next;
+ }
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 "
+ warn "W: unknown path/rev in svn:mergeinfo "
."dirprop: $source:$range\n";
next;
}
@rv;
}
-sub check_cherry_pick {
+sub check_cherry_pick2 {
my $base = shift;
my $tip = shift;
my $parents = shift;
delete $commits{$commit};
}
}
- return (keys %commits);
+ my @k = (keys %commits);
+ return (scalar @k, $k[0]);
}
sub has_no_changes {
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';
mkpath([$cache_path]) unless -d $cache_path;
my %lookup_svn_merge_cache;
- my %check_cherry_pick_cache;
+ my %check_cherry_pick2_cache;
my %has_no_changes_cache;
tie_for_persistent_memoization(\%lookup_svn_merge_cache,
LIST_CACHE => ['HASH' => \%lookup_svn_merge_cache],
;
- tie_for_persistent_memoization(\%check_cherry_pick_cache,
- "$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,
$memoized = 0;
Memoize::unmemoize 'lookup_svn_merge';
- Memoize::unmemoize 'check_cherry_pick';
+ Memoize::unmemoize 'check_cherry_pick2';
Memoize::unmemoize 'has_no_changes';
}
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";
if ( $commit eq $excluded ) {
push @excluded, $commit;
$found++;
- last;
}
else {
push @new, $commit;
return @excluded;
}
+# Compute what's new in svn:mergeinfo.
+sub mergeinfo_changes {
+ my ($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();
# 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 $url = $self->url;
my $uuid = $self->ra_uuid;
- my %ranges;
+ 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;
- $ranges{$tip_commit} = \@ranges;
+ push @all_ranges, @ranges;
} else {
push @merge_tips, undef;
}
# 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 $ranges = $ranges{$merge_tip};
+ my $spec = "$merge:$mergeinfo->{$merge}";
# check out 'new' tips
my $merge_base;
}
# double check that there are no missing non-merge commits
- my (@incomplete) = check_cherry_pick(
+ my ($ninc, $ifirst) = check_cherry_pick2(
$merge_base, $merge_tip,
$parents,
- @$ranges,
+ @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, $merge_tip;
}
}
}
sub make_log_entry {
- my ($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 $!;
$email ||= "$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};
+ my $full_url = canonicalize_url(
+ add_path_to_url( $self->svnsync->{url}, $self->path )
+ );
remove_username($full_url);
my $uuid = $self->svnsync->{uuid};
$log_entry{metadata} = "$full_url\@$rev $uuid";
tree_b => $tree,
editor_cb => sub {
$self->set_tree_cb($log_entry, $tree, @_) },
- svn_path => $self->{path} );
+ svn_path => $self->path );
if (!Git::SVN::Editor->new(\%ed_opts)->apply_diff) {
print "No changes\nr$self->{last_rev} = $tree\n";
}
unlink $path or croak "unlink: $!";
}
+#define a global associate map to record rebuild status
+my %rebuild_status;
+#define a global associate map to record rebuild verify status
+my %rebuild_verify_status;
+
sub rebuild {
my ($self) = @_;
my $map_path = $self->map_path;
my $partial = (-e $map_path && ! -z $map_path);
- return unless ::verify_ref($self->refname.'^0');
+ my $verify_key = $self->refname.'^0';
+ if (!$rebuild_verify_status{$verify_key}) {
+ my $verify_result = ::verify_ref($verify_key);
+ if ($verify_result) {
+ $rebuild_verify_status{$verify_key} = 1;
+ }
+ }
+ if (!$rebuild_verify_status{$verify_key}) {
+ return;
+ }
if (!$partial && ($self->use_svm_props || $self->no_metadata)) {
my $rev_db = $self->rev_db_path;
$self->rebuild_from_rev_db($rev_db);
print "Rebuilding $map_path ...\n" if (!$partial);
my ($base_rev, $head) = ($partial ? $self->rev_map_max_norebuild(1) :
(undef, undef));
+ my $key_value = ($head ? "$head.." : "") . $self->refname;
+ if (exists $rebuild_status{$key_value}) {
+ 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: $!";
+ }
+ $self->unlink_rev_db_symlink;
+ return;
+ }
my ($log, $ctx) =
- command_output_pipe(qw/rev-list --pretty=raw --reverse/,
- ($head ? "$head.." : "") . $self->refname,
+ command_output_pipe(qw/rev-list --pretty=raw --reverse/,
+ $key_value,
'--');
+ $rebuild_status{$key_value} = 1;
my $metadata_url = $self->metadata_url;
remove_username($metadata_url);
my $svn_uuid = $self->rewrite_uuid || $self->ra_uuid;
# both of these options make our .rev_db file very, very important
# and we can't afford to lose it because rebuild() won't work
if ($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 {
# 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;
$_[3] = $path = '' unless (defined $path);
mkpath([$dir]);
- bless {
+ my $obj = bless {
ref_id => $ref_id, dir => $dir, index => "$dir/index",
- path => $path, config => "$ENV{GIT_DIR}/svn/config",
+ config => "$ENV{GIT_DIR}/svn/config",
map_root => "$dir/.rev_map", repo_id => $repo_id }, $class;
+
+ # Ensure it gets canonicalized
+ $obj->path($path);
+
+ return $obj;
+}
+
+sub path {
+ my $self = shift;
+
+ if (@_) {
+ my $path = shift;
+ $self->{_path} = canonicalize_path($path);
+ return;
+ }
+
+ return $self->{_path};
+}
+
+sub url {
+ my $self = shift;
+
+ if (@_) {
+ my $url = shift;
+ $self->{url} = canonicalize_url($url);
+ return;
+ }
+
+ return $self->{url};
}
# for read-only access of old .rev_db formats
sub uri_encode {
my ($f) = @_;
- $f =~ s#([^a-zA-Z0-9\*!\:_\./\-])#uc sprintf("%%%02x",ord($1))#eg;
+ $f =~ s#([^a-zA-Z0-9\*!\:_\./\-])#sprintf("%%%02X",ord($1))#eg;
$f
}