$Git::SVN::_follow_parent = 1;
my %remote_opts = ( 'username=s' => \$Git::SVN::Prompt::_username,
'config-dir=s' => \$Git::SVN::Ra::config_dir,
- 'no-auth-cache' => \$Git::SVN::Prompt::_no_auth_cache );
+ 'no-auth-cache' => \$Git::SVN::Prompt::_no_auth_cache,
+ 'ignore-paths=s' => \$SVN::Git::Fetcher::_ignore_regex );
my %fc_opts = ( 'follow-parent|follow!' => \$Git::SVN::_follow_parent,
'authors-file|A=s' => \$_authors,
'repack:i' => \$Git::SVN::_repack,
\$Git::SVN::_repack_flags,
'use-log-author' => \$Git::SVN::_use_log_author,
'add-author-from' => \$Git::SVN::_add_author_from,
+ 'localtime' => \$Git::SVN::_localtime,
%remote_opts );
my ($_trunk, $_tags, $_branches, $_stdlayout);
"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";
- }
+ 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 ",
my ($src, $rev, undef, $gs) = working_head_info($head);
- my $remote = Git::SVN::read_all_remotes()->{svn};
+ my $remote = Git::SVN::read_all_remotes()->{$gs->{repo_id}};
my $glob = $remote->{ $_tag ? 'tags' : 'branches' };
my ($lft, $rgt) = @{ $glob->{path} }{qw/left right/};
my $dst = join '/', $remote->{url}, $lft, $branch_name, ($rgt || ());
my ($uri) = @_;
my @tmp;
foreach (split m{/}, $uri) {
- s/([^\w.%+-]|%(?![a-fA-F0-9]{2}))/sprintf("%%%02X",ord($1))/eg;
+ s/([^~\w.%+-]|%(?![a-fA-F0-9]{2}))/sprintf("%%%02X",ord($1))/eg;
push @tmp, $_;
}
join('/', @tmp);
if ($@) {
$result .= "Repository Root: (offline)\n";
}
- $result .= "Repository UUID: $uuid\n" unless $diff_status eq "A";
+ $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";
$result .= "Node Kind: " .
system($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 $!;
+ {
+ # 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>);
+
+ if (my $enc = Git::config('i18n.commitencoding')) {
+ require Encode;
+ Encode::from_to($log_entry{log}, $enc, 'UTF-8');
+ }
+ close $log_fh or croak $!;
+ }
unlink $commit_msg;
\%log_entry;
}
use vars qw/$default_repo_id $default_ref_id $_no_metadata $_follow_parent
$_repack $_repack_flags $_use_svm_props $_head
$_use_svnsync_props $no_reuse_existing $_minimize_url
- $_use_log_author $_add_author_from/;
+ $_use_log_author $_add_author_from $_localtime/;
use Carp qw/croak/;
use File::Path qw/mkpath/;
use File::Copy qw/copy/;
}
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) {
$gs = Git::SVN->init($u, $p, $repo_id, $ref_id, 1);
}
my ($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";
\@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
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 $parsed_date;
}
sub check_author {
use Carp qw/croak/;
use File::Temp qw/tempfile/;
use IO::File qw//;
+use vars qw/$_ignore_regex/;
# file baton members: path, mode_a, mode_b, pool, fh, blob, base
sub new {
my ($class, $git_svn) = @_;
my $self = SVN::Delta::Editor->new;
bless $self, $class;
- $self->{c} = $git_svn->{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);
+ }
$self->{empty} = {};
$self->{dir_prop} = {};
$self->{file_prop} = {};
$self;
}
+# this uses the Ra object, so it must be called before do_{switch,update},
+# not inside them (when the Git::SVN::Fetcher object is passed) to
+# do_{switch,update}
+sub _mark_empty_symlinks {
+ my ($git_svn) = @_;
+ my %ret;
+ my ($rev, $cmt) = $git_svn->last_rev_commit;
+ return {} unless ($rev && $cmt);
+
+ 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 = $git_svn->{path};
+ $pfx .= '/' if length($pfx);
+ while (<$ls>) {
+ chomp;
+ s/\A100644 blob $empty_blob\t//o or next;
+ 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 ($path) = @_;
+ return 1 if in_dot_git($path);
+ 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 $path;
sub delete_entry {
my ($self, $path, $rev, $pb) = @_;
+ return undef if is_path_ignored($path);
my $gpath = $self->git_path($path);
return undef if ($gpath eq '');
sub open_file {
my ($self, $path, $pb, $rev) = @_;
+ my ($mode, $blob);
+
+ goto out if is_path_ignored($path);
+
my $gpath = $self->git_path($path);
- my ($mode, $blob) = (command('ls-tree', $self->{c}, '--', $gpath)
+ ($mode, $blob) = (command('ls-tree', $self->{c}, '--', $gpath)
=~ /^(\d{6}) blob ([a-f\d]{40})\t/);
unless (defined $mode && defined $blob) {
die "$path was not found in commit $self->{c} (r$rev)\n";
}
+ 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 $mode;
+
+ if (!is_path_ignored($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, $cp_rev) = @_;
+ goto out if is_path_ignored($path);
my $gpath = $self->git_path($path);
if ($gpath eq '') {
my ($ls, $ctx) = command_output_pipe(qw/ls-tree
my ($dir, $file) = ($path =~ m#^(.*?)/?([^/]+)$#);
delete $self->{empty}->{$dir};
$self->{empty}->{$path} = 1;
+out:
{ path => $path };
}
sub change_dir_prop {
my ($self, $db, $prop, $value) = @_;
+ return undef if is_path_ignored($db->{path});
$self->{dir_prop}->{$db->{path}} ||= {};
$self->{dir_prop}->{$db->{path}}->{$prop} = $value;
undef;
sub absent_directory {
my ($self, $path, $pb) = @_;
+ return undef if is_path_ignored($path);
$self->{absent_dir}->{$pb->{path}} ||= [];
push @{$self->{absent_dir}->{$pb->{path}}}, $path;
undef;
sub absent_file {
my ($self, $path, $pb) = @_;
+ return undef if is_path_ignored($path);
$self->{absent_file}->{$pb->{path}} ||= [];
push @{$self->{absent_file}->{$pb->{path}}}, $path;
undef;
sub change_file_prop {
my ($self, $fb, $prop, $value) = @_;
+ return undef if is_path_ignored($fb->{path});
if ($prop eq 'svn:executable') {
if ($fb->{mode_b} != 120000) {
$fb->{mode_b} = defined $value ? 100755 : 100644;
sub apply_textdelta {
my ($self, $fb, $exp) = @_;
- my $fh = Git::temp_acquire('svn_delta');
+ return undef if is_path_ignored($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 = Git::temp_acquire('git_blob');
+ my $base = $::_repository->temp_acquire('git_blob');
+
if ($fb->{blob}) {
- print $base 'link ' if ($fb->{mode_a} == 120000);
- my $size = $::_repository->cat_blob($fb->{blob}, $base);
+ my ($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;
+ }
+ 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 $got = ::md5sum($base);
- die "Checksum mismatch: $fb->{path} $fb->{blob}\n",
- "expected: $exp\n",
- " got: $got\n" if ($got ne $exp);
+ if ($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 $!;
sub close_file {
my ($self, $fb, $exp) = @_;
+ return undef if is_path_ignored($fb->{path});
+
my $hash;
my $path = $self->git_path($fb->{path});
if (my $fh = $fb->{fh}) {
}
if ($fb->{mode_b} == 120000) {
sysseek($fh, 0, 0) or croak $!;
- sysread($fh, my $buf, 5) == 5 or croak $!;
+ my $rd = sysread($fh, my $buf, 5);
- unless ($buf eq 'link ') {
+ 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";
+ " but is not a link\n";
} else {
- my $tmp_fh = Git::temp_acquire('svn_hash');
+ my $tmp_fh = $::_repository->temp_acquire(
+ 'svn_hash');
my $res;
while ($res = sysread($fh, my $str, 1024)) {
my $out = syswrite($tmp_fh, $str, $res);
sub url_path {
my ($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);
}
sub _chg_file_get_blob ($$$$) {
my ($self, $fbat, $m, $which) = @_;
- my $fh = Git::temp_acquire("git_blob_$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','*');
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 $self = shift;
my ($uri) = @_;
my @tmp;
foreach (split m{/}, $uri) {
- s/([^\w.%+-]|%(?![a-fA-F0-9]{2}))/sprintf("%%%02X",ord($1))/eg;
+ s/([^~\w.%+-]|%(?![a-fA-F0-9]{2}))/sprintf("%%%02X",ord($1))/eg;
push @tmp, $_;
}
join('/', @tmp);
# 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');
+
+ # 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;
}
}
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: