Merge branch 'ar/batch-cat'

* ar/batch-cat:
  change quoting in test t1006-cat-file.sh
  builtin-cat-file.c: use parse_options()
  git-svn: Speed up fetch
  Git.pm: Add hash_and_insert_object and cat_blob
  Git.pm: Add command_bidi_pipe and command_close_bidi_pipe
  git-hash-object: Add --stdin-paths option
  Add more tests for git hash-object
  Move git-hash-object tests from t5303 to t1007
  git-cat-file: Add --batch option
  git-cat-file: Add --batch-check option
  git-cat-file: Make option parsing a little more flexible
  git-cat-file: Small refactor of cmd_cat_file
  Add tests for git cat-file

Documentation/git-cat-file.txt

@@ -9,12 +9,16 @@ git-cat-file - Provide content or type/size information for repository objects
 SYNOPSIS
 --------
 'git-cat-file' [-t | -s | -e | -p | <type>] <object>
+'git-cat-file' [--batch | --batch-check] < <list-of-objects>
 
 DESCRIPTION
 -----------
-Provides content or type of objects in the repository. The type
-is required unless '-t' or '-p' is used to find the object type,
-or '-s' is used to find the object size.
+In the first form, provides content or type of objects in the repository. The
+type is required unless '-t' or '-p' is used to find the object type, or '-s'
+is used to find the object size.
+
+In the second form, a list of object (separated by LFs) is provided on stdin,
+and the SHA1, type, and size of each object is printed on stdout.
 
 OPTIONS
 -------
@@ -46,6 +50,14 @@ OPTIONS
 	or to ask for a "blob" with <object> being a tag object that
 	points at it.
 
+--batch::
+	Print the SHA1, type, size, and contents of each object provided on
+	stdin. May not be combined with any other options or arguments.
+
+--batch-check::
+	Print the SHA1, type, and size of each object provided on stdin. May not be
+	combined with any other options or arguments.
+
 OUTPUT
 ------
 If '-t' is specified, one of the <type>.
@@ -56,9 +68,30 @@ If '-e' is specified, no output.
 
 If '-p' is specified, the contents of <object> are pretty-printed.
 
-Otherwise the raw (though uncompressed) contents of the <object> will
-be returned.
+If <type> is specified, the raw (though uncompressed) contents of the <object>
+will be returned.
+
+If '--batch' is specified, output of the following form is printed for each
+object specified on stdin:
+
+------------
+<sha1> SP <type> SP <size> LF
+<contents> LF
+------------
+
+If '--batch-check' is specified, output of the following form is printed for
+each object specified fon stdin:
+
+------------
+<sha1> SP <type> SP <size> LF
+------------
+
+For both '--batch' and '--batch-check', output of the following form is printed
+for each object specified on stdin that does not exist in the repository:
 
+------------
+<object> SP missing LF
+------------
 
 Author
 ------

Documentation/git-hash-object.txt

@@ -8,7 +8,7 @@ git-hash-object - Compute object ID and optionally creates a blob from a file
 
 SYNOPSIS
 --------
-'git-hash-object' [-t <type>] [-w] [--stdin] [--] <file>...
+'git-hash-object' [-t <type>] [-w] [--stdin | --stdin-paths] [--] <file>...
 
 DESCRIPTION
 -----------
@@ -32,6 +32,9 @@ OPTIONS
 --stdin::
 	Read the object from standard input instead of from a file.
 
+--stdin-paths::
+	Read file names from stdin instead of from the command-line.
+
 Author
 ------
 Written by Junio C Hamano <junkio@cox.net>

builtin-cat-file.c

@@ -8,6 +8,10 @@
 #include "tag.h"
 #include "tree.h"
 #include "builtin.h"
+#include "parse-options.h"
+
+#define BATCH 1
+#define BATCH_CHECK 2
 
 static void pprint_tag(const unsigned char *sha1, const char *buf, unsigned long size)
 {
@@ -76,31 +80,16 @@ static void pprint_tag(const unsigned char *sha1, const char *buf, unsigned long
 		write_or_die(1, cp, endp - cp);
 }
 
-int cmd_cat_file(int argc, const char **argv, const char *prefix)
+static int cat_one_file(int opt, const char *exp_type, const char *obj_name)
 {
 	unsigned char sha1[20];
 	enum object_type type;
 	void *buf;
 	unsigned long size;
-	int opt;
-	const char *exp_type, *obj_name;
-
-	git_config(git_default_config);
-	if (argc != 3)
-		usage("git-cat-file [-t|-s|-e|-p|<type>] <sha1>");
-	exp_type = argv[1];
-	obj_name = argv[2];
 
 	if (get_sha1(obj_name, sha1))
 		die("Not a valid object name %s", obj_name);
 
-	opt = 0;
-	if ( exp_type[0] == '-' ) {
-		opt = exp_type[1];
-		if ( !opt || exp_type[2] )
-			opt = -1; /* Not a single character option */
-	}
-
 	buf = NULL;
 	switch (opt) {
 	case 't':
@@ -157,3 +146,108 @@ int cmd_cat_file(int argc, const char **argv, const char *prefix)
 	write_or_die(1, buf, size);
 	return 0;
 }
+
+static int batch_one_object(const char *obj_name, int print_contents)
+{
+	unsigned char sha1[20];
+	enum object_type type;
+	unsigned long size;
+	void *contents = contents;
+
+	if (!obj_name)
+	   return 1;
+
+	if (get_sha1(obj_name, sha1)) {
+		printf("%s missing\n", obj_name);
+		return 0;
+	}
+
+	if (print_contents == BATCH)
+		contents = read_sha1_file(sha1, &type, &size);
+	else
+		type = sha1_object_info(sha1, &size);
+
+	if (type <= 0)
+		return 1;
+
+	printf("%s %s %lu\n", sha1_to_hex(sha1), typename(type), size);
+	fflush(stdout);
+
+	if (print_contents == BATCH) {
+		write_or_die(1, contents, size);
+		printf("\n");
+		fflush(stdout);
+	}
+
+	return 0;
+}
+
+static int batch_objects(int print_contents)
+{
+	struct strbuf buf;
+
+	strbuf_init(&buf, 0);
+	while (strbuf_getline(&buf, stdin, '\n') != EOF) {
+		int error = batch_one_object(buf.buf, print_contents);
+		if (error)
+			return error;
+	}
+
+	return 0;
+}
+
+static const char * const cat_file_usage[] = {
+	"git-cat-file [-t|-s|-e|-p|<type>] <sha1>",
+	"git-cat-file [--batch|--batch-check] < <list_of_sha1s>",
+	NULL
+};
+
+int cmd_cat_file(int argc, const char **argv, const char *prefix)
+{
+	int opt = 0, batch = 0;
+	const char *exp_type = NULL, *obj_name = NULL;
+
+	const struct option options[] = {
+		OPT_GROUP("<type> can be one of: blob, tree, commit, tag"),
+		OPT_SET_INT('t', NULL, &opt, "show object type", 't'),
+		OPT_SET_INT('s', NULL, &opt, "show object size", 's'),
+		OPT_SET_INT('e', NULL, &opt,
+			    "exit with zero when there's no error", 'e'),
+		OPT_SET_INT('p', NULL, &opt, "pretty-print object's content", 'p'),
+		OPT_SET_INT(0, "batch", &batch,
+			    "show info and content of objects feeded on stdin", BATCH),
+		OPT_SET_INT(0, "batch-check", &batch,
+			    "show info about objects feeded on stdin",
+			    BATCH_CHECK),
+		OPT_END()
+	};
+
+	git_config(git_default_config);
+
+	if (argc != 3 && argc != 2)
+		usage_with_options(cat_file_usage, options);
+
+	argc = parse_options(argc, argv, options, cat_file_usage, 0);
+
+	if (opt) {
+		if (argc == 1)
+			obj_name = argv[0];
+		else
+			usage_with_options(cat_file_usage, options);
+	}
+	if (!opt && !batch) {
+		if (argc == 2) {
+			exp_type = argv[0];
+			obj_name = argv[1];
+		} else
+			usage_with_options(cat_file_usage, options);
+	}
+	if (batch && (opt || argc)) {
+		usage_with_options(cat_file_usage, options);
+	}
+
+	if (batch)
+		return batch_objects(batch);
+
+	return cat_one_file(opt, exp_type, obj_name);
+}

git-svn.perl

@@ -4,7 +4,7 @@
 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@@';
@@ -222,6 +222,7 @@ BEGIN
 		}
 		$ENV{GIT_DIR} = $git_dir;
 	}
+	$_repository = Git->repository(Repository => $ENV{GIT_DIR});
 }
 
 my %opts = %{$cmd{$cmd}->[2]} if (defined $cmd);
@@ -303,6 +304,7 @@ sub do_git_init_db {
 			}
 		}
 		command_noisy(@init_db);
+		$_repository = Git->repository(Repository => ".git");
 	}
 	my $set;
 	my $pfx = "svn-remote.$Git::SVN::default_repo_id";
@@ -319,6 +321,7 @@ sub init_subdir {
 	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 {
@@ -3030,6 +3033,7 @@ package SVN::Git::Fetcher;
 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
@@ -3185,14 +3189,9 @@ sub apply_textdelta {
 	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}" unless $size;
 
 		if (defined $exp) {
 			seek $base, 0, 0 or croak $!;
@@ -3233,14 +3232,18 @@ sub close_file {
 				sysseek($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 $!;
 	} else {
@@ -3566,13 +3569,8 @@ sub chg_file {
 	} elsif ($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}" unless $size;
 	$fh->flush == 0 or croak $!;
 	seek $fh, 0, 0 or croak $!;