use warnings;
use strict;
use vars qw/ $AUTHOR $VERSION
- $sha1 $sha1_short $_revision
+ $sha1 $sha1_short $_revision $_repository
$_q $_authors %users/;
$AUTHOR = 'Eric Wong <normalperson@yhbt.net>';
$VERSION = '@@GIT_VERSION@@';
$_template, $_shared,
$_version, $_fetch_all, $_no_rebase,
$_merge, $_strategy, $_dry_run, $_local,
- $_prefix, $_no_checkout, $_url, $_verbose);
+ $_prefix, $_no_checkout, $_url, $_verbose,
+ $_git_format);
$Git::SVN::_follow_parent = 1;
my %remote_opts = ( 'username=s' => \$Git::SVN::Prompt::_username,
'config-dir=s' => \$Git::SVN::Ra::config_dir,
'repack-flags|repack-args|repack-opts=s' =>
\$Git::SVN::_repack_flags,
'use-log-author' => \$Git::SVN::_use_log_author,
+ 'add-author-from' => \$Git::SVN::_add_author_from,
%remote_opts );
my ($_trunk, $_tags, $_branches, $_stdlayout);
'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',
"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 } ],
);
my $cmd;
}
$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 && $cmd eq 'log');
+Getopt::Long::Configure('pass_through') if ($cmd && ($cmd eq 'log' || $cmd eq 'blame'));
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,
}
}
command_noisy(@init_db);
+ $_repository = Git->repository(Repository => ".git");
}
my $set;
my $pfx = "svn-remote.$Git::SVN::default_repo_id";
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 {
$head ||= 'HEAD';
my @refs;
my ($url, $rev, $uuid, $gs) = working_head_info($head, \@refs);
- print "Committing to $url ...\n";
+ if ($url) {
+ print "Committing to $url ...\n";
+ }
unless ($gs) {
die "Unable to determine upstream SVN information from ",
- "$head history\n";
+ "$head history.\nPerhaps the repository is empty.";
}
my $last_rev;
my ($linear_refs, $parents) = linearize_history($gs, \@refs);
}
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 $head = shift;
die "Unable to determine upstream SVN information from ",
"working tree history\n";
}
+ if ($_dry_run) {
+ print "Remote Branch: " . $gs->refname . "\n";
+ print "SVN URL: " . $url . "\n";
+ return;
+ }
if (command(qw/diff-index HEAD --/)) {
print STDERR "Cannot rebase with uncommited changes:\n";
command_noisy('status');
print GITIGNORE "$s\n";
close(GITIGNORE)
or fatal("Failed to close `$ignore': $!");
- command_noisy('add', $ignore);
+ command_noisy('add', '-f', $ignore);
});
}
my $usage = "Usage: $0 commit-diff -r<revision> ".
"<tree-ish> <tree-ish> [<URL>]";
fatal($usage) if (!defined $ta || !defined $tb);
- my $svn_path;
+ my $svn_path = '';
if (!defined $url) {
my $gs = eval { Git::SVN->new };
if (!$gs) {
$_message ||= get_commit_entry($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;
"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 $remote_path = "$ra->{svn_path}/$repo_path";
$remote_path =~ s#/+#/#g;
$remote_path =~ s#^/##g;
+ $remote_path .= "/*" if $remote_path !~ /\*/;
my ($n) = ($switch =~ /^--(\w+)/);
if (length $pfx && $pfx !~ m#/$#) {
die "--prefix='$pfx' must have a trailing slash '/'\n";
my ($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 $!;
sub working_head_info {
my ($head, $refs) = @_;
- my @args = ('log', '--no-color', '--first-parent');
+ my @args = ('log', '--no-color', '--first-parent', '--pretty=medium');
my ($fh, $ctx) = command_output_pipe(@args, $head);
my $hash;
my %max;
use vars qw/$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/;
+ $_use_log_author $_add_author_from/;
use Carp qw/croak/;
use File::Path qw/mkpath/;
use File::Copy qw/copy/;
use IPC::Open3;
-my $_repack_nr;
+my ($_gc_nr, $_gc_period);
+
# properties that we do not log:
my %SKIP_PROP;
BEGIN {
}
sub init_vars {
- $_repack = 1000 unless (defined $_repack && $_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";
+ }
}
sub verify_remotes_sanity {
$remotes->{$repo_id}->{$_});
}
my $p = $path;
+ my $rwr = rewrite_root({repo_id => $repo_id});
unless (defined $p) {
$p = $full_url;
- $p =~ s#^\Q$u\E(?:/|$)## or next;
+ my $z = $u;
+ if ($rwr) {
+ $z = $rwr;
+ }
+ $p =~ s#^\Q$z\E(?:/|$)## or next;
}
foreach my $f (keys %$fetch) {
next if $f ne $p;
foreach (sort keys %$dirent) {
next if $dirent->{$_}->{kind} != $SVN::Node::dir;
- $self->prop_walk($path . '/' . $_, $rev, $sub);
+ $self->prop_walk($self->{path} . $p . $_, $rev, $sub);
}
}
}
}
+sub gc {
+ command_noisy('gc', '--auto');
+};
+
sub do_git_commit {
my ($self, $log_entry) = @_;
my $lr = $self->last_rev;
0, $self->svm_uuid);
}
print " = $commit ($self->{ref_id})\n";
- if ($_repack && (--$_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+/, $_repack_flags));
- print "Done repacking\n";
+ if (--$_gc_nr == 0) {
+ $_gc_nr = $_gc_period;
+ gc();
}
return $commit;
}
# 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, $ref_id, 1);
+ my ($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, $ref_id, 1);
}
my ($r0, $parent) = $gs->find_rev_before($r, 1);
if (!defined $r0 || !defined $parent) {
my ($author) = @_;
if (!defined $author || length $author == 0) {
$author = '(no author)';
- }
- if (defined $::_authors && ! defined $::users{$author}) {
+ } elsif (defined $::_authors && ! defined $::users{$author}) {
die "Author: $author not defined in $::_authors file\n";
}
$author;
$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, 'unknown');
+ ($name, $email) = ($name_field, $name_field);
}
}
if (defined $headrev && $self->use_svm_props) {
my ($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($_);
sub _rev_map_set {
my ($fh, $rev, $commit) = @_;
+ binmode $fh or croak "binmode: $!";
my $size = (stat($fh))[7];
($size % 24) == 0 or croak "inconsistent size: $size";
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";
return undef unless -e $map_path;
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";
use strict;
use warnings;
use Carp qw/croak/;
+use File::Temp qw/tempfile/;
use IO::File qw//;
# file baton members: path, mode_a, mode_b, pool, fh, blob, base
my $base = IO::File->new_tmpfile;
$base->autoflush(1);
if ($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 $!;
- }
- waitpid $pid, 0;
- croak $? if $?;
+ print $base 'link ' if ($fb->{mode_a} == 120000);
+ my $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 $!;
sysseek($fh, 0, 0) or croak $!;
}
}
- 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 $!;
+
+ my ($tmp_fh, $tmp_filename) = File::Temp::tempfile(UNLINK => 1);
+ my $result;
+ while ($result = sysread($fh, my $string, 1024)) {
+ syswrite($tmp_fh, $string, $result);
}
- chomp($hash = do { local $/; <$out> });
- close $out or croak $!;
+ defined $result or croak $!;
+ close $tmp_fh or croak $!;
+
close $fh or croak $!;
+
+ $hash = $::_repository->hash_and_insert_object($tmp_filename);
$hash =~ /^[a-f\d]{40}$/ or die "not a sha1: $hash\n";
close $fb->{base} or croak $!;
} else {
} elsif ($m->{mode_a} =~ /^120/ && $m->{mode_b} !~ /^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 $size = $::_repository->cat_blob($m->{sha1_b}, $fh);
+ croak "Failed to read object $m->{sha1_b}" if ($size < 0);
$fh->flush == 0 or croak $!;
seek $fh, 0, 0 or croak $!;
my ($uri) = @_;
my @tmp;
foreach (split m{/}, $uri) {
- s/([^\w.-])/sprintf("%%%02X",ord($1))/eg;
+ s/([^\w.%+-]|%(?![a-fA-F0-9]{2}))/sprintf("%%%02X",ord($1))/eg;
push @tmp, $_;
}
join('/', @tmp);
$max += $inc;
$max = $head if ($max > $head);
}
+ Git::SVN::gc();
}
sub match_globs {
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;
+ while (my $line = <$fh>) {
+ if ($line =~ /^([[:xdigit:]]{40})\s\d+\s\d+/) {
+ $sha1 = $1;
+ (undef, $rev, undef) = ::cmt_metadata($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;
# these version numbers do NOT correspond to actual version numbers
# of git nor git-svn. They are just relative.