use strict;
use vars qw/ $AUTHOR $VERSION
$sha1 $sha1_short $_revision $_repository
- $_q $_authors %users/;
+ $_q $_authors $_authors_prog %users/;
$AUTHOR = 'Eric Wong <normalperson@yhbt.net>';
$VERSION = '@@GIT_VERSION@@';
use IO::File qw//;
use File::Basename qw/dirname basename/;
use File::Path qw/mkpath/;
+use File::Spec;
use Getopt::Long qw/:config gnu_getopt no_ignore_case auto_abbrev/;
use IPC::Open3;
use Git;
# 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 $package ( qw(SVN::Git::Editor SVN::Git::Fetcher
Git::SVN::Migration Git::SVN::Log Git::SVN),
__PACKAGE__) {
my ($_stdin, $_help, $_edit,
$_message, $_file,
$_template, $_shared,
- $_version, $_fetch_all, $_no_rebase,
+ $_version, $_fetch_all, $_no_rebase, $_fetch_parent,
$_merge, $_strategy, $_dry_run, $_local,
$_prefix, $_no_checkout, $_url, $_verbose,
- $_git_format, $_commit_url);
+ $_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, $_stdlayout);
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,
'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,
+ '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,
+ '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, } ],
"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 ",
version() if $_version;
usage(1) unless defined $cmd;
load_authors() if $_authors;
+if (defined $_authors_prog) {
+ $_authors_prog = "'" . File::Spec->rel2abs($_authors_prog) . "'";
+}
unless ($cmd =~ /^(?:clone|init|multi-init|commit-diff)$/) {
Git::SVN::Migration::migration_check();
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 $i (keys %icv) {
command_noisy('config', "$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 {
$path = basename($url) if !defined $path || !length $path;
cmd_init($url, $path);
Git::SVN::fetch_all($Git::SVN::default_repo_id);
+ command_oneline('config', 'svn.authorsfile', $_authors) if $_authors;
}
sub cmd_init {
}
my ($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) {
+ 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());
}
}
$head ||= 'HEAD';
my @refs;
my ($url, $rev, $uuid, $gs) = working_head_info($head, \@refs);
- $url = defined $_commit_url ? $_commit_url : $gs->full_url;
- my $last_rev = $_revision if defined $_revision;
- if ($url) {
- print "Committing to $url ...\n";
- }
unless ($gs) {
die "Unable to determine upstream SVN information from ",
"$head history.\nPerhaps the repository is empty.";
}
+
+ if (defined $_commit_url) {
+ $url = $_commit_url;
+ } else {
+ $url = eval { command_oneline('config', '--get',
+ "svn-remote.$gs->{repo_id}.commiturl") };
+ if (!$url) {
+ $url = $gs->full_url
+ }
+ }
+
+ my $last_rev = $_revision if defined $_revision;
+ if ($url) {
+ print "Committing to $url ...\n";
+ }
my ($linear_refs, $parents) = linearize_history($gs, \@refs);
if ($_no_rebase && scalar(@$linear_refs) > 1) {
warn "Attempting to commit more than one change while ",
unlink $gs->{index};
}
+sub cmd_branch {
+ my ($branch_name, $head) = @_;
+
+ unless (defined $branch_name && length $branch_name) {
+ die(($_tag ? "tag" : "branch") . " name required\n");
+ }
+ $head ||= 'HEAD';
+
+ my ($src, $rev, undef, $gs) = working_head_info($head);
+
+ 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 $ctx = SVN::Client->new(
+ auth => Git::SVN::Ra::_auth_providers(),
+ log_msg => sub {
+ ${ $_[0] } = defined $_message
+ ? $_message
+ : 'Create ' . ($_tag ? 'tag ' : 'branch ' )
+ . $branch_name;
+ },
+ );
+
+ eval {
+ $ctx->ls($dst, 'HEAD', 0);
+ } and die "branch ${branch_name} already exists\n";
+
+ print "Copying ${src} at r${rev} to ${dst}...\n";
+ $ctx->copy($src, $rev, $dst)
+ unless $_dry_run;
+
+ $gs->fetch_all;
+}
+
sub cmd_find_rev {
my $revision_or_hash = shift or die "SVN or git revision required ",
"as a command-line argument\n";
$gs->prop_walk($gs->{path}, $r, sub {
my ($gs, $path, $props) = @_;
# $path is of the form /path/to/dir/
- my $ignore = '.' . $path . '.gitignore';
+ $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: $!");
}
}
+sub escape_uri_only {
+ my ($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 "$path: (Not a versioned resource)\n\n";
- return;
+ print STDERR "svn: '$path' is not under version control\n";
+ exit 1;
}
my ($url, $rev, $uuid, $gs) = working_head_info('HEAD');
# canonicalize_path() will return "" to make libsvn 1.5.x happy,
$path = "." if $path eq "";
- my $full_url = $url . ($path eq "." ? "" : "/$path");
+ my $full_url = $url . ($fullpath eq "" ? "" : "/$fullpath");
if ($_url) {
- print $full_url, "\n";
+ print escape_url($full_url), "\n";
return;
}
my $result = "Path: $path\n";
$result .= "Name: " . basename($path) . "\n" if $file_type ne "dir";
- $result .= "URL: " . $full_url . "\n";
+ $result .= "URL: " . escape_url($full_url) . "\n";
eval {
my $repos_root = $gs->repos_root;
Git::SVN::remove_username($repos_root);
- $result .= "Repository Root: $repos_root\n";
+ $result .= "Repository Root: " . escape_url($repos_root) . "\n";
};
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";
$result .= "Node Kind: " .
}
my ($lc_author, $lc_rev, $lc_date_utc);
- my @args = Git::SVN::Log::git_svn_log_cmd($rev, $rev, "--", $path);
+ my @args = Git::SVN::Log::git_svn_log_cmd($rev, $rev, "--", $fullpath);
my $log = command_output_pipe(@args);
my $esc_color = qr/(?:\033\[(?:(?:\d+;)*\d*)?m)*/;
while (<$log>) {
system($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 $commit_msg;
\%log_entry;
}
command(qw/cat-file commit/, shift)))[-1]);
}
+sub cmt_sha2rev_batch {
+ my %s2r;
+ my ($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, $refs) = @_;
my @args = ('log', '--no-color', '--first-parent', '--pretty=medium');
use vars qw/$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/;
my $prefix = '';
if ($rwr) {
$z = $rwr;
+ remove_username($z);
} elsif (defined $svm) {
$z = $svm->{source};
$prefix = $svm->{replace};
}
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) {
$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})";
+ 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";
+ print " = $commit ($self->{ref_id})\n" unless $::_q > 1;
if (--$_gc_nr == 0) {
$_gc_nr = $_gc_period;
gc();
if (my $path = $paths->{"/$self->{path}"}) {
return ($path->{action} eq 'D') ? 0 : 1;
}
- $self->{path_regex} ||= qr/^\/\Q$self->{path}\E\//;
+ my $repos_root = $self->ra->{repos_root};
+ my $extended_path = $self->{url} . '/' . $self->{path};
+ $extended_path =~ s#^\Q$repos_root\E(/|$)##;
+ $self->{path_regex} ||= qr/^\/\Q$extended_path\E\//;
if (grep /$self->{path_regex}/, keys %$paths) {
return 1;
}
print STDERR "Found possible branch point: ",
"$new_url => ", $self->full_url, ", $r\n";
$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: $ref_id\n";
- my ($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);
- }
+ my $gs = $self->other_gs($new_url, $url, $repos_root,
+ $branch_from, $r, $self->{ref_id});
my ($r0, $parent) = $gs->find_rev_before($r, 1);
{
my ($base, $head);
# 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";
\@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, $repos_root,
+ $branch_from, $r, $old_ref_id) = @_;
+ my $gs = Git::SVN->find_by_url($new_url, $repos_root, $branch_from);
+ unless ($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: $ref_id\n";
+ my ($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) = @_;
+ 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: $author\n";
+ }
}
sub check_author {
my ($author) = @_;
if (!defined $author || length $author == 0) {
$author = '(no author)';
- } elsif (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";
+ }
}
$author;
}
sub rebuild {
my ($self) = @_;
my $map_path = $self->map_path;
- return if (-e $map_path && ! -z $map_path);
+ my $partial = (-e $map_path && ! -z $map_path);
return unless ::verify_ref($self->refname.'^0');
- if ($self->use_svm_props || $self->no_metadata) {
+ if (!$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) {
$self->unlink_rev_db_symlink;
return;
}
- print "Rebuilding $map_path ...\n";
+ 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/,
- $self->refname, '--');
+ ($head ? "$head.." : "") . $self->refname,
+ '--');
my $metadata_url = $self->metadata_url;
remove_username($metadata_url);
my $svn_uuid = $self->ra_uuid;
($metadata_url && $url && ($url ne $metadata_url))) {
next;
}
+ if ($partial && $head) {
+ print "Partial-rebuilding $map_path ...\n";
+ print "Currently at $base_rev = $head\n";
+ $head = undef;
+ }
$self->rev_map_set($rev, $c);
print "r$rev = $c\n";
}
command_close_pipe($log, $ctx);
- print "Done rebuilding $map_path\n";
+ 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: $!";
sub rev_map_max {
my ($self, $want_commit) = @_;
$self->rebuild;
+ my ($r, $c) = $self->rev_map_max_norebuild($want_commit);
+ $want_commit ? ($r, $c) : $r;
+}
+
+sub rev_map_max_norebuild {
+ my ($self, $want_commit) = @_;
my $map_path = $self->map_path;
stat $map_path or return $want_commit ? (0, undef) : 0;
sysopen(my $fh, $map_path, O_RDONLY) or croak "open: $!";
use Carp qw/croak/;
use File::Temp qw/tempfile/;
use IO::File qw//;
+use vars qw/$_ignore_regex/;
# file baton members: path, mode_a, mode_b, pool, fh, blob, base
sub new {
- my ($class, $git_svn) = @_;
+ my ($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} = {};
$self;
}
+# this uses the Ra object, so it must be called before do_{switch,update},
+# not inside them (when the Git::SVN::Fetcher object is passed) to
+# do_{switch,update}
+sub _mark_empty_symlinks {
+ my ($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 $path;
sub delete_entry {
my ($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, $ctx);
sub open_file {
my ($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, $ctx) = command_output_pipe(qw/ls-tree
my ($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} = $value;
undef;
sub absent_directory {
my ($self, $path, $pb) = @_;
+ return undef if $self->is_path_ignored($path);
$self->{absent_dir}->{$pb->{path}} ||= [];
push @{$self->{absent_dir}->{$pb->{path}}}, $path;
undef;
sub absent_file {
my ($self, $path, $pb) = @_;
+ return undef if $self->is_path_ignored($path);
$self->{absent_file}->{$pb->{path}} ||= [];
push @{$self->{absent_file}->{$pb->{path}}}, $path;
undef;
sub change_file_prop {
my ($self, $fb, $prop, $value) = @_;
+ return undef if $self->is_path_ignored($fb->{path});
if ($prop eq 'svn:executable') {
if ($fb->{mode_b} != 120000) {
$fb->{mode_b} = defined $value ? 100755 : 100644;
sub apply_textdelta {
my ($self, $fb, $exp) = @_;
- my $fh = Git::temp_acquire('svn_delta');
+ 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 = 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 $self->is_path_ignored($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, $res);
while (<$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 {
$state = 'file_b';
sub url_path {
my ($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);
}
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});
$self->SUPER::change_file_prop($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 $fh = Git::temp_acquire('git_blob');
- if ($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);
}
- my $size = $::_repository->cat_blob($m->{sha1_b}, $fh);
- croak "Failed to read object $m->{sha1_b}" if ($size < 0);
+ 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 $exp = ::md5sum($fh);
seek $fh, 0, 0 or croak $!;
+ return ($fh, $exp);
+}
+sub chg_file {
+ my ($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 $exp);
- Git::temp_release($fh, 1);
+ 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;
}
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;
$ret;
my ($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;
}
$self->get_log([$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,
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 = $err_handler;
use strict;
use warnings;
use POSIX qw/strftime/;
+use Time::Local;
use constant commit_log_separator => ('-' x 72) . "\n";
use vars qw/$TZ $limit $color $pager $non_recursive $verbose $oneline
%rusers $show_commit $incremental/;
}
sub format_svn_date {
- return strftime("%Y-%m-%d %H:%M:%S %z (%a, %d %b %Y)", localtime(shift));
+ # 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 {
'--', $path);
my ($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+/) {
- $sha1 = $1;
- (undef, $rev, undef) = ::cmt_metadata($1);
- $rev = '0' if (!$rev);
+ $rev = $s2r->{$1};
+ $rev = '0' if (!$rev)
}
elsif ($line =~ /^author (.*)/) {
$authors{$rev} = $1;
}
}
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: