X-Git-Url: https://asedeno.scripts.mit.edu/gitweb/?a=blobdiff_plain;f=git-svn.perl;h=9e2faf90aa1676974234882a2f557c17f7bc59f4;hb=27b4070e40a771c41ed581ef1ac98dd43e58ab87;hp=b45c7e3266176336a4d8c6deeaa051c6fd0e9be6;hpb=060610c572b21d00bb09ebbab664c0452c7eac9d;p=git.git

diff --git a/git-svn.perl b/git-svn.perl
index b45c7e326..9e2faf90a 100755
--- a/git-svn.perl
+++ b/git-svn.perl
@@ -186,6 +186,9 @@ my %cmd = (
 		    "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",
+	            {} ],
 );
 
 my $cmd;
@@ -197,8 +200,8 @@ for (my $i = 0; $i < @ARGV; $i++) {
 	}
 };
 
-# make sure we're always running
-unless ($cmd =~ /(?:clone|init|multi-init)$/) {
+# make sure we're always running at the top-level working directory
+unless ($cmd && $cmd =~ /(?:clone|init|multi-init)$/) {
 	unless (-d $ENV{GIT_DIR}) {
 		if ($git_dir_user_set) {
 			die "GIT_DIR=$ENV{GIT_DIR} explicitly set, ",
@@ -396,6 +399,7 @@ sub cmd_set_tree {
 	}
 	$gs->set_tree($_) foreach @revs;
 	print "Done committing ",scalar @revs," revisions to SVN\n";
+	unlink $gs->{index};
 }
 
 sub cmd_dcommit {
@@ -417,7 +421,7 @@ sub cmd_dcommit {
 		warn "Attempting to commit more than one change while ",
 		     "--no-rebase is enabled.\n",
 		     "If these changes depend on each other, re-running ",
-		     "without --no-rebase will be required."
+		     "without --no-rebase may be required."
 	}
 	while (1) {
 		my $d = shift @$linear_refs or last;
@@ -452,6 +456,7 @@ sub cmd_dcommit {
 				                               $parents->{$d};
 			}
 			$_fetch_all ? $gs->fetch_all : $gs->fetch;
+			$last_rev = $cmt_rev;
 			next if $_no_rebase;
 
 			# we always want to rebase against the current HEAD,
@@ -511,9 +516,9 @@ sub cmd_dcommit {
 				$parents = \%p;
 				$linear_refs = \@l;
 			}
-			$last_rev = $cmt_rev;
 		}
 	}
+	unlink $gs->{index};
 }
 
 sub cmd_find_rev {
@@ -1245,7 +1250,8 @@ 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 {
@@ -1281,8 +1287,11 @@ BEGIN {
 	}
 }
 
-my %LOCKFILES;
-END { unlink keys %LOCKFILES if %LOCKFILES }
+my (%LOCKFILES, %INDEX_FILES);
+END {
+	unlink keys %LOCKFILES if %LOCKFILES;
+	unlink keys %INDEX_FILES if %INDEX_FILES;
+}
 
 sub resolve_local_globs {
 	my ($url, $fetch, $glob_spec) = @_;
@@ -1403,10 +1412,9 @@ sub read_all_remotes {
 }
 
 sub init_vars {
-	if (defined $_repack) {
-		$_repack = 1000 if ($_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";
 	}
 }
 
@@ -1753,10 +1761,16 @@ sub svnsync {
 	# see if we have it in our config, first:
 	eval {
 		my $section = "svn-remote.$self->{repo_id}";
-		$svnsync = {
-		  url => tmp_config('--get', "$section.svnsync-url"),
-		  uuid => tmp_config('--get', "$section.svnsync-uuid"),
-		}
+
+		my $url = tmp_config('--get', "$section.svnsync-url");
+		($url) = ($url =~ m{^([a-z\+]+://\S+)$}) or
+		   die "doesn't look right - svn:sync-from-url is '$url'\n";
+
+		my $uuid = tmp_config('--get', "$section.svnsync-uuid");
+		($uuid) = ($uuid =~ m{^([0-9a-f\-]{30,})$}) or
+		   die "doesn't look right - svn:sync-from-uuid is '$uuid'\n";
+
+		$svnsync = { url => $url, uuid => $uuid }
 	};
 	if ($svnsync && $svnsync->{url} && $svnsync->{uuid}) {
 		return $self->{svnsync} = $svnsync;
@@ -1767,11 +1781,11 @@ sub svnsync {
 	my $rp = $self->ra->rev_proplist(0);
 
 	my $url = $rp->{'svn:sync-from-url'} or die $err . "url\n";
-	$url =~ m{^[a-z\+]+://} or
+	($url) = ($url =~ m{^([a-z\+]+://\S+)$}) or
 	           die "doesn't look right - svn:sync-from-url is '$url'\n";
 
 	my $uuid = $rp->{'svn:sync-from-uuid'} or die $err . "uuid\n";
-	$uuid =~ m{^[0-9a-f\-]{30,}$} or
+	($uuid) = ($uuid =~ m{^([0-9a-f\-]{30,})$}) or
 	           die "doesn't look right - svn:sync-from-uuid is '$uuid'\n";
 
 	my $section = "svn-remote.$self->{repo_id}";
@@ -1853,6 +1867,7 @@ sub rel_path {
 sub prop_walk {
 	my ($self, $path, $rev, $sub) = @_;
 
+	$path =~ s#^/##;
 	my ($dirent, undef, $props) = $self->ra->get_dir($path, $rev);
 	$path =~ s#^/*#/#g;
 	my $p = $path;
@@ -1904,7 +1919,7 @@ sub last_rev_commit {
 		($self->{last_rev}, $self->{last_commit}) = (undef, undef);
 		return (undef, undef);
 	}
-	my ($rev, $commit) = $self->rev_map_max;
+	my ($rev, $commit) = $self->rev_map_max(1);
 	($self->{last_rev}, $self->{last_commit}) = ($rev, $commit);
 	return ($rev, $commit);
 }
@@ -2049,18 +2064,16 @@ sub full_url {
 	$self->{url} . (length $self->{path} ? '/' . $self->{path} : '');
 }
 
-sub do_git_commit {
-	my ($self, $log_entry) = @_;
-	my $lr = $self->last_rev;
-	if (defined $lr && $lr >= $log_entry->{revision}) {
-		die "Last fetched revision of ", $self->refname,
-		    " was r$lr, but we are about to fetch: ",
-		    "r$log_entry->{revision}!\n";
-	}
-	if (my $c = $self->rev_map_get($log_entry->{revision})) {
-		croak "$log_entry->{revision} = $c already exists! ",
-		      "Why are we refetching it?\n";
+
+sub set_commit_header_env {
+	my ($log_entry) = @_;
+	my %env;
+	foreach my $ned (qw/NAME EMAIL DATE/) {
+		foreach my $ac (qw/AUTHOR COMMITTER/) {
+			$env{"GIT_${ac}_${ned}"} = $ENV{"GIT_${ac}_${ned}"};
+		}
 	}
+
 	$ENV{GIT_AUTHOR_NAME} = $log_entry->{name};
 	$ENV{GIT_AUTHOR_EMAIL} = $log_entry->{email};
 	$ENV{GIT_AUTHOR_DATE} = $ENV{GIT_COMMITTER_DATE} = $log_entry->{date};
@@ -2071,7 +2084,40 @@ sub do_git_commit {
 	$ENV{GIT_COMMITTER_EMAIL} = (defined $log_entry->{commit_email})
 						? $log_entry->{commit_email}
 						: $log_entry->{email};
+	\%env;
+}
 
+sub restore_commit_header_env {
+	my ($env) = @_;
+	foreach my $ned (qw/NAME EMAIL DATE/) {
+		foreach my $ac (qw/AUTHOR COMMITTER/) {
+			my $k = "GIT_${ac}_${ned}";
+			if (defined $env->{$k}) {
+				$ENV{$k} = $env->{$k};
+			} else {
+				delete $ENV{$k};
+			}
+		}
+	}
+}
+
+sub gc {
+	command_noisy('gc', '--auto');
+};
+
+sub do_git_commit {
+	my ($self, $log_entry) = @_;
+	my $lr = $self->last_rev;
+	if (defined $lr && $lr >= $log_entry->{revision}) {
+		die "Last fetched revision of ", $self->refname,
+		    " was r$lr, but we are about to fetch: ",
+		    "r$log_entry->{revision}!\n";
+	}
+	if (my $c = $self->rev_map_get($log_entry->{revision})) {
+		croak "$log_entry->{revision} = $c already exists! ",
+		      "Why are we refetching it?\n";
+	}
+	my $old_env = set_commit_header_env($log_entry);
 	my $tree = $log_entry->{tree};
 	if (!defined $tree) {
 		$tree = $self->tmp_index_do(sub {
@@ -2086,6 +2132,7 @@ sub do_git_commit {
 	defined(my $pid = open3(my $msg_fh, my $out_fh, '>&STDERR', @exec))
 	                                                           or croak $!;
 	print $msg_fh $log_entry->{log} or croak $!;
+	restore_commit_header_env($old_env);
 	unless ($self->no_metadata) {
 		print $msg_fh "\ngit-svn-id: $log_entry->{metadata}\n"
 		              or croak $!;
@@ -2111,12 +2158,9 @@ sub do_git_commit {
 		                   0, $self->svm_uuid);
 	}
 	print " = $commit ($self->{ref_id})\n";
-	if (defined $_repack && (--$_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;
 }
@@ -2188,7 +2232,12 @@ sub find_parent_branch {
 		# 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, $p) = ($new_url, '');
+		if ($u =~ s#^\Q$url\E(/|$)##) {
+			$p = $u;
+			$u = $url;
+		}
+		$gs = Git::SVN->init($u, $p, $self->{repo_id}, $ref_id, 1);
 	}
 	my ($r0, $parent) = $gs->find_rev_before($r, 1);
 	if (!defined $r0 || !defined $parent) {
@@ -2363,11 +2412,20 @@ sub make_log_entry {
 
 	my ($commit_name, $commit_email) = ($name, $email);
 	if ($_use_log_author) {
-		if ($log_entry{log} =~ /From:\s+(.*?)\s+<(.*)>\s*\n/) {
-			($name, $email) = ($1, $2);
-		} elsif ($log_entry{log} =~
-		                      /Signed-off-by:\s+(.*?)\s+<(.*)>\s*\n/) {
+		my $name_field;
+		if ($log_entry{log} =~ /From:\s+(.*\S)\s*\n/i) {
+			$name_field = $1;
+		} elsif ($log_entry{log} =~ /Signed-off-by:\s+(.*\S)\s*\n/i) {
+			$name_field = $1;
+		}
+		if (!defined $name_field) {
+			#
+		} elsif ($name_field =~ /(.*?)\s+<(.*)>/) {
 			($name, $email) = ($1, $2);
+		} elsif ($name_field =~ /(.*)@/) {
+			($name, $email) = ($1, $name_field);
+		} else {
+			($name, $email) = ($name_field, 'unknown');
 		}
 	}
 	if (defined $headrev && $self->use_svm_props) {
@@ -2534,11 +2592,16 @@ sub rebuild {
 #     * 4 bytes for the integer representing an SVN revision number
 #     * 20 bytes representing the sha1 of a git commit
 #   - No empty padding records like the old format
+#     (except the last record, which can be overwritten)
 #   - new records are written append-only since SVN revision numbers
 #     increase monotonically
 #   - lookups on SVN revision number are done via a binary search
-#   - Piping the file to xxd(1) -c24 is a good way of dumping it for
-#     viewing or editing, should the need ever arise.
+#   - Piping the file to xxd -c24 is a good way of dumping it for
+#     viewing or editing (piped back through xxd -r), should the need
+#     ever arise.
+#   - The last record can be padding revision with an all-zero sha1
+#     This is used to optimize fetch performance when using multiple
+#     "fetch" directives in .git/config
 #
 # These files are disposable unless noMetadata or useSvmProps is set
 
@@ -2548,16 +2611,32 @@ sub _rev_map_set {
 	my $size = (stat($fh))[7];
 	($size % 24) == 0 or croak "inconsistent size: $size";
 
+	my $wr_offset = 0;
 	if ($size > 0) {
 		sysseek($fh, -24, SEEK_END) or croak "seek: $!";
 		my $read = sysread($fh, my $buf, 24) or croak "read: $!";
 		$read == 24 or croak "read only $read bytes (!= 24)";
 		my ($last_rev, $last_commit) = unpack(rev_map_fmt, $buf);
-		if ($last_rev >= $rev) {
-			croak "last_rev is higher!: $last_rev >= $rev";
+		if ($last_commit eq ('0' x40)) {
+			if ($size >= 48) {
+				sysseek($fh, -48, SEEK_END) or croak "seek: $!";
+				$read = sysread($fh, $buf, 24) or
+				    croak "read: $!";
+				$read == 24 or
+				    croak "read only $read bytes (!= 24)";
+				($last_rev, $last_commit) =
+				    unpack(rev_map_fmt, $buf);
+				if ($last_commit eq ('0' x40)) {
+					croak "inconsistent .rev_map\n";
+				}
+			}
+			if ($last_rev >= $rev) {
+				croak "last_rev is higher!: $last_rev >= $rev";
+			}
+			$wr_offset = -24;
 		}
 	}
-	sysseek($fh, 0, SEEK_END) or croak "seek: $!";
+	sysseek($fh, $wr_offset, SEEK_END) or croak "seek: $!";
 	syswrite($fh, pack(rev_map_fmt, $rev, $commit), 24) == 24 or
 	  croak "write: $!";
 }
@@ -2599,7 +2678,7 @@ sub rev_map_set {
 					    "$db => $db_lock ($!)\n";
 	}
 
-	sysopen(my $fh, $db_lock, O_RDWR | O_APPEND | O_CREAT)
+	sysopen(my $fh, $db_lock, O_RDWR | O_CREAT)
 	     or croak "Couldn't open $db_lock: $!\n";
 	_rev_map_set($fh, $rev, $commit);
 	if ($sync) {
@@ -2622,25 +2701,40 @@ sub rev_map_set {
 	}
 }
 
+# If want_commit, this will return an array of (rev, commit) where
+# commit _must_ be a valid commit in the archive.
+# Otherwise, it'll return the max revision (whether or not the
+# commit is valid or just a 0x40 placeholder).
 sub rev_map_max {
-	my ($self) = @_;
+	my ($self, $want_commit) = @_;
 	$self->rebuild;
 	my $map_path = $self->map_path;
-	stat $map_path or return wantarray ? (0, undef) : 0;
+	stat $map_path or return $want_commit ? (0, undef) : 0;
 	sysopen(my $fh, $map_path, O_RDONLY) or croak "open: $!";
 	my $size = (stat($fh))[7];
 	($size % 24) == 0 or croak "inconsistent size: $size";
 
 	if ($size == 0) {
 		close $fh or croak "close: $!";
-		return wantarray ? (0, undef) : 0;
+		return $want_commit ? (0, undef) : 0;
 	}
 
-	sysseek($fh, -24, SEEK_END);
+	sysseek($fh, -24, SEEK_END) or croak "seek: $!";
 	sysread($fh, my $buf, 24) == 24 or croak "read: $!";
-	close $fh or croak "close: $!";
 	my ($r, $c) = unpack(rev_map_fmt, $buf);
-	wantarray ? ($r, $c) : $r;
+	if ($want_commit && $c eq ('0' x40)) {
+		if ($size < 48) {
+			return $want_commit ? (0, undef) : 0;
+		}
+		sysseek($fh, -48, SEEK_END) or croak "seek: $!";
+		sysread($fh, $buf, 24) == 24 or croak "read: $!";
+		($r, $c) = unpack(rev_map_fmt, $buf);
+		if ($c eq ('0'x40)) {
+			croak "Penultimate record is all-zeroes in $map_path";
+		}
+	}
+	close $fh or croak "close: $!";
+	$want_commit ? ($r, $c) : $r;
 }
 
 sub rev_map_get {
@@ -2672,7 +2766,7 @@ sub rev_map_get {
 			$u = $i - 24;
 		} else { # $r == $rev
 			close($fh) or croak "close: $!";
-			return $c;
+			return $c eq ('0' x 40) ? undef : $c;
 		}
 	}
 	close($fh) or croak "close: $!";
@@ -2997,6 +3091,20 @@ sub add_file {
 
 sub add_directory {
 	my ($self, $path, $cp_path, $cp_rev) = @_;
+	my $gpath = $self->git_path($path);
+	if ($gpath eq '') {
+		my ($ls, $ctx) = command_output_pipe(qw/ls-tree
+		                                     -r --name-only -z/,
+				                     $self->{c});
+		local $/ = "\0";
+		while (<$ls>) {
+			chomp;
+			$self->{gii}->remove($_);
+			print "\tD\t$_\n" unless $::_q;
+		}
+		command_close_pipe($ls, $ctx);
+		$self->{empty}->{$path} = 0;
+	}
 	my ($dir, $file) = ($path =~ m#^(.*?)/?([^/]+)$#);
 	delete $self->{empty}->{$dir};
 	$self->{empty}->{$path} = 1;
@@ -3087,9 +3195,15 @@ sub close_file {
 		}
 		sysseek($fh, 0, 0) or croak $!;
 		if ($fb->{mode_b} == 120000) {
-			sysread($fh, my $buf, 5) == 5 or croak $!;
-			$buf eq 'link ' or die "$path has mode 120000",
-			                       "but is not a link\n";
+			eval {
+				sysread($fh, my $buf, 5) == 5 or croak $!;
+				$buf eq 'link ' or die "$path has mode 120000",
+						       " but is not a link";
+			};
+			if ($@) {
+				warn "$@\n";
+				sysseek($fh, 0, 0) or croak $!;
+			}
 		}
 		defined(my $pid = open my $out,'-|') or die "Can't fork: $!\n";
 		if (!$pid) {
@@ -3529,6 +3643,7 @@ sub _auth_providers () {
 	  SVN::Client::get_ssl_client_cert_file_provider(),
 	  SVN::Client::get_ssl_client_cert_prompt_provider(
 	    \&Git::SVN::Prompt::ssl_client_cert, 2),
+	  SVN::Client::get_ssl_client_cert_pw_file_provider(),
 	  SVN::Client::get_ssl_client_cert_pw_prompt_provider(
 	    \&Git::SVN::Prompt::ssl_client_cert_pw, 2),
 	  SVN::Client::get_username_provider(),
@@ -3849,6 +3964,7 @@ sub gs_fetch_loop_common {
 				if ($log_entry) {
 					$gs->do_git_commit($log_entry);
 				}
+				$INDEX_FILES{$gs->{index}} = 1;
 			}
 			foreach my $g (@$globs) {
 				my $k = "svn-remote.$g->{remote}." .
@@ -3863,6 +3979,13 @@ sub gs_fetch_loop_common {
 				$ra_invalid = undef;
 			}
 		}
+		# pre-fill the .rev_db since it'll eventually get filled in
+		# with '0' x40 if something new gets committed
+		foreach my $gs (@$gsv) {
+			next if $gs->rev_map_max >= $max;
+			next if defined $gs->rev_map_get($max);
+			$gs->rev_map_set($max, 0 x40);
+		}
 		foreach my $g (@$globs) {
 			my $k = "svn-remote.$g->{remote}.$g->{t}-maxRev";
 			Git::SVN::tmp_config($k, $max);
@@ -3872,6 +3995,7 @@ sub gs_fetch_loop_common {
 		$max += $inc;
 		$max = $head if ($max > $head);
 	}
+	Git::SVN::gc();
 }
 
 sub match_globs {
@@ -3979,6 +4103,10 @@ sub skip_unknown_revs {
 			warn "W: Ignoring error from SVN, path probably ",
 			     "does not exist: ($errno): ",
 			     $err->expanded_message,"\n";
+			warn "W: Do not be alarmed at the above message ",
+			     "git-svn is just searching aggressively for ",
+			     "old history.\n",
+			     "This may take a while on large repositories\n";
 			$ignored_err{$err_key} = 1;
 		}
 		return;
@@ -4037,39 +4165,7 @@ sub cmt_showable {
 }
 
 sub log_use_color {
-	return 1 if $color;
-	my ($dc, $dcvar);
-	$dcvar = 'color.diff';
-	$dc = `git-config --get $dcvar`;
-	if ($dc eq '') {
-		# nothing at all; fallback to "diff.color"
-		$dcvar = 'diff.color';
-		$dc = `git-config --get $dcvar`;
-	}
-	chomp($dc);
-	if ($dc eq 'auto') {
-		my $pc;
-		$pc = `git-config --get color.pager`;
-		if ($pc eq '') {
-			# does not have it -- fallback to pager.color
-			$pc = `git-config --bool --get pager.color`;
-		}
-		else {
-			$pc = `git-config --bool --get color.pager`;
-			if ($?) {
-				$pc = 'false';
-			}
-		}
-		chomp($pc);
-		if (-t *STDOUT || (defined $pager && $pc eq 'true')) {
-			return ($ENV{TERM} && $ENV{TERM} ne 'dumb');
-		}
-		return 0;
-	}
-	return 0 if $dc eq 'never';
-	return 1 if $dc eq 'always';
-	chomp($dc = `git-config --bool --get $dcvar`);
-	return ($dc eq 'true');
+	return $color || Git->repository->get_colorbool('color.diff');
 }
 
 sub git_svn_log_cmd {
@@ -4128,6 +4224,7 @@ sub config_pager {
 	} elsif (length $pager == 0 || $pager eq 'cat') {
 		$pager = undef;
 	}
+	$ENV{GIT_PAGER_IN_USE} = defined($pager);
 }
 
 sub run_pager {
@@ -4355,6 +4452,24 @@ out:
 	print commit_log_separator unless $incremental || $oneline;
 }
 
+sub cmd_blame {
+	my $path = shift;
+
+	config_pager();
+	run_pager();
+
+	my ($fh, $ctx) = command_output_pipe('blame', @_, $path);
+	while (my $line = <$fh>) {
+		if ($line =~ /^\^?([[:xdigit:]]+)\s/) {
+			my (undef, $rev, undef) = ::cmt_metadata($1);
+			$rev = sprintf('%-10s', $rev);
+			$line =~ s/^\^?[[:xdigit:]]+(\s)/$rev$1/;
+		}
+		print $line;
+	}
+	command_close_pipe($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.