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

diff --git a/Documentation/git-cat-file.txt b/Documentation/git-cat-file.txt
index df42cb10f24825623ffe32579f0cfbcda6f0337b..f6c394c48240314298dd67716c6d96e6d9704c11 100644 (file)
--- a/Documentation/git-cat-file.txt
+++ b/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
 ------

diff --git a/Documentation/git-hash-object.txt b/Documentation/git-hash-object.txt
index 33030c022f1b86a8dba281ff04537c1a40cb6782..99a21434b53a40a1b317e9d3da1728ca22d76b53 100644 (file)
--- a/Documentation/git-hash-object.txt
+++ b/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>

diff --git a/builtin-cat-file.c b/builtin-cat-file.c
index f132d583d3e2a2ac0fe696b66723c846902d0a19..5ef15a4fa9eac952db105376ec6a10b706b3cbb2 100644 (file)
--- a/builtin-cat-file.c
+++ b/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);
+}

diff --git a/git-svn.perl b/git-svn.perl
index 0e61897b9ecc255d3d22d016b46c90d3a30e9f38..37976f25057ac5d3c91a13ab8564a4cb40f59f79 100755 (executable)
--- a/git-svn.perl
+++ b/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>';
 $VERSION = '@@GIT_VERSION@@';
@@ -222,6 +222,7 @@ unless ($cmd && $cmd =~ /(?:clone|init|multi-init)$/) {
                }
                $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 @@ use vars qw/@ISA/;
 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 $!;
 

diff --git a/hash-object.c b/hash-object.c
index 61e7160b361f60e6d673ab64aa3d22c1a783d057..0a7ac2fe2adf820a171898b9e51b245c063018cc 100644 (file)
--- a/hash-object.c
+++ b/hash-object.c
@@ -6,6 +6,7 @@
  */
 #include "cache.h"
 #include "blob.h"
+#include "quote.h"
 
 static void hash_object(const char *path, enum object_type type, int write_object)
 {
@@ -20,6 +21,7 @@ static void hash_object(const char *path, enum object_type type, int write_objec
                    ? "Unable to add %s to database"
                    : "Unable to hash %s", path);
        printf("%s\n", sha1_to_hex(sha1));
+       maybe_flush_or_die(stdout, "hash to stdout");
 }
 
 static void hash_stdin(const char *type, int write_object)
@@ -30,8 +32,27 @@ static void hash_stdin(const char *type, int write_object)
        printf("%s\n", sha1_to_hex(sha1));
 }
 
+static void hash_stdin_paths(const char *type, int write_objects)
+{
+       struct strbuf buf, nbuf;
+
+       strbuf_init(&buf, 0);
+       strbuf_init(&nbuf, 0);
+       while (strbuf_getline(&buf, stdin, '\n') != EOF) {
+               if (buf.buf[0] == '"') {
+                       strbuf_reset(&nbuf);
+                       if (unquote_c_style(&nbuf, buf.buf, NULL))
+                               die("line is badly quoted");
+                       strbuf_swap(&buf, &nbuf);
+               }
+               hash_object(buf.buf, type_from_string(type), write_objects);
+       }
+       strbuf_release(&buf);
+       strbuf_release(&nbuf);
+}
+
 static const char hash_object_usage[] =
-"git-hash-object [-t <type>] [-w] [--stdin] <file>...";
+"git-hash-object [ [-t <type>] [-w] [--stdin] <file>... | --stdin-paths < <list-of-paths> ]";
 
 int main(int argc, char **argv)
 {
@@ -42,6 +63,7 @@ int main(int argc, char **argv)
        int prefix_length = -1;
        int no_more_flags = 0;
        int hashstdin = 0;
+       int stdin_paths = 0;
 
        git_config(git_default_config);
 
@@ -65,7 +87,19 @@ int main(int argc, char **argv)
                        }
                        else if (!strcmp(argv[i], "--help"))
                                usage(hash_object_usage);
+                       else if (!strcmp(argv[i], "--stdin-paths")) {
+                               if (hashstdin) {
+                                       error("Can't use --stdin-paths with --stdin");
+                                       usage(hash_object_usage);
+                               }
+                               stdin_paths = 1;
+
+                       }
                        else if (!strcmp(argv[i], "--stdin")) {
+                               if (stdin_paths) {
+                                       error("Can't use %s with --stdin-paths", argv[i]);
+                                       usage(hash_object_usage);
+                               }
                                if (hashstdin)
                                        die("Multiple --stdin arguments are not supported");
                                hashstdin = 1;
@@ -76,6 +110,11 @@ int main(int argc, char **argv)
                else {
                        const char *arg = argv[i];
 
+                       if (stdin_paths) {
+                               error("Can't specify files (such as \"%s\") with --stdin-paths", arg);
+                               usage(hash_object_usage);
+                       }
+
                        if (hashstdin) {
                                hash_stdin(type, write_object);
                                hashstdin = 0;
@@ -87,6 +126,10 @@ int main(int argc, char **argv)
                        no_more_flags = 1;
                }
        }
+
+       if (stdin_paths)
+               hash_stdin_paths(type, write_object);
+
        if (hashstdin)
                hash_stdin(type, write_object);
        return 0;

diff --git a/perl/Git.pm b/perl/Git.pm
index 2e7f896baec00d644903af5d967b6c781ee3503a..6ba8ee5c0d209704fdf1c9d58f63579d3a7e0836 100644 (file)
--- a/perl/Git.pm
+++ b/perl/Git.pm
@@ -39,6 +39,10 @@ $VERSION = '0.01';
   my $lastrev = $repo->command_oneline( [ 'rev-list', '--all' ],
                                         STDERR => 0 );
 
+  my $sha1 = $repo->hash_and_insert_object('file.txt');
+  my $tempfile = tempfile();
+  my $size = $repo->cat_blob($sha1, $tempfile);
+
 =cut
 
 
@@ -51,6 +55,7 @@ require Exporter;
 # Methods which can be called as standalone functions as well:
 @EXPORT_OK = qw(command command_oneline command_noisy
                 command_output_pipe command_input_pipe command_close_pipe
+                command_bidi_pipe command_close_bidi_pipe
                 version exec_path hash_object git_cmd_try);
 
 
@@ -92,6 +97,7 @@ increate nonwithstanding).
 use Carp qw(carp croak); # but croak is bad - throw instead
 use Error qw(:try);
 use Cwd qw(abs_path);
+use IPC::Open2 qw(open2);
 
 }
 
@@ -216,7 +222,6 @@ sub repository {
        bless $self, $class;
 }
 
-
 =back
 
 =head1 METHODS
@@ -375,6 +380,60 @@ sub command_close_pipe {
        _cmd_close($fh, $ctx);
 }
 
+=item command_bidi_pipe ( COMMAND [, ARGUMENTS... ] )
+
+Execute the given C<COMMAND> in the same way as command_output_pipe()
+does but return both an input pipe filehandle and an output pipe filehandle.
+
+The function will return return C<($pid, $pipe_in, $pipe_out, $ctx)>.
+See C<command_close_bidi_pipe()> for details.
+
+=cut
+
+sub command_bidi_pipe {
+       my ($pid, $in, $out);
+       $pid = open2($in, $out, 'git', @_);
+       return ($pid, $in, $out, join(' ', @_));
+}
+
+=item command_close_bidi_pipe ( PID, PIPE_IN, PIPE_OUT [, CTX] )
+
+Close the C<PIPE_IN> and C<PIPE_OUT> as returned from C<command_bidi_pipe()>,
+checking whether the command finished successfully. The optional C<CTX>
+argument is required if you want to see the command name in the error message,
+and it is the fourth value returned by C<command_bidi_pipe()>.  The call idiom
+is:
+
+       my ($pid, $in, $out, $ctx) = $r->command_bidi_pipe('cat-file --batch-check');
+       print "000000000\n" $out;
+       while (<$in>) { ... }
+       $r->command_close_bidi_pipe($pid, $in, $out, $ctx);
+
+Note that you should not rely on whatever actually is in C<CTX>;
+currently it is simply the command name but in future the context might
+have more complicated structure.
+
+=cut
+
+sub command_close_bidi_pipe {
+       my ($pid, $in, $out, $ctx) = @_;
+       foreach my $fh ($in, $out) {
+               unless (close $fh) {
+                       if ($!) {
+                               carp "error closing pipe: $!";
+                       } elsif ($? >> 8) {
+                               throw Git::Error::Command($ctx, $? >>8);
+                       }
+               }
+       }
+
+       waitpid $pid, 0;
+
+       if ($? >> 8) {
+               throw Git::Error::Command($ctx, $? >>8);
+       }
+}
+
 
 =item command_noisy ( COMMAND [, ARGUMENTS... ] )
 
@@ -678,6 +737,147 @@ sub hash_object {
 }
 
 
+=item hash_and_insert_object ( FILENAME )
+
+Compute the SHA1 object id of the given C<FILENAME> and add the object to the
+object database.
+
+The function returns the SHA1 hash.
+
+=cut
+
+# TODO: Support for passing FILEHANDLE instead of FILENAME
+sub hash_and_insert_object {
+       my ($self, $filename) = @_;
+
+       carp "Bad filename \"$filename\"" if $filename =~ /[\r\n]/;
+
+       $self->_open_hash_and_insert_object_if_needed();
+       my ($in, $out) = ($self->{hash_object_in}, $self->{hash_object_out});
+
+       unless (print $out $filename, "\n") {
+               $self->_close_hash_and_insert_object();
+               throw Error::Simple("out pipe went bad");
+       }
+
+       chomp(my $hash = <$in>);
+       unless (defined($hash)) {
+               $self->_close_hash_and_insert_object();
+               throw Error::Simple("in pipe went bad");
+       }
+
+       return $hash;
+}
+
+sub _open_hash_and_insert_object_if_needed {
+       my ($self) = @_;
+
+       return if defined($self->{hash_object_pid});
+
+       ($self->{hash_object_pid}, $self->{hash_object_in},
+        $self->{hash_object_out}, $self->{hash_object_ctx}) =
+               command_bidi_pipe(qw(hash-object -w --stdin-paths));
+}
+
+sub _close_hash_and_insert_object {
+       my ($self) = @_;
+
+       return unless defined($self->{hash_object_pid});
+
+       my @vars = map { 'hash_object_' . $_ } qw(pid in out ctx);
+
+       command_close_bidi_pipe($self->{@vars});
+       delete $self->{@vars};
+}
+
+=item cat_blob ( SHA1, FILEHANDLE )
+
+Prints the contents of the blob identified by C<SHA1> to C<FILEHANDLE> and
+returns the number of bytes printed.
+
+=cut
+
+sub cat_blob {
+       my ($self, $sha1, $fh) = @_;
+
+       $self->_open_cat_blob_if_needed();
+       my ($in, $out) = ($self->{cat_blob_in}, $self->{cat_blob_out});
+
+       unless (print $out $sha1, "\n") {
+               $self->_close_cat_blob();
+               throw Error::Simple("out pipe went bad");
+       }
+
+       my $description = <$in>;
+       if ($description =~ / missing$/) {
+               carp "$sha1 doesn't exist in the repository";
+               return 0;
+       }
+
+       if ($description !~ /^[0-9a-fA-F]{40} \S+ (\d+)$/) {
+               carp "Unexpected result returned from git cat-file";
+               return 0;
+       }
+
+       my $size = $1;
+
+       my $blob;
+       my $bytesRead = 0;
+
+       while (1) {
+               my $bytesLeft = $size - $bytesRead;
+               last unless $bytesLeft;
+
+               my $bytesToRead = $bytesLeft < 1024 ? $bytesLeft : 1024;
+               my $read = read($in, $blob, $bytesToRead, $bytesRead);
+               unless (defined($read)) {
+                       $self->_close_cat_blob();
+                       throw Error::Simple("in pipe went bad");
+               }
+
+               $bytesRead += $read;
+       }
+
+       # Skip past the trailing newline.
+       my $newline;
+       my $read = read($in, $newline, 1);
+       unless (defined($read)) {
+               $self->_close_cat_blob();
+               throw Error::Simple("in pipe went bad");
+       }
+       unless ($read == 1 && $newline eq "\n") {
+               $self->_close_cat_blob();
+               throw Error::Simple("didn't find newline after blob");
+       }
+
+       unless (print $fh $blob) {
+               $self->_close_cat_blob();
+               throw Error::Simple("couldn't write to passed in filehandle");
+       }
+
+       return $size;
+}
+
+sub _open_cat_blob_if_needed {
+       my ($self) = @_;
+
+       return if defined($self->{cat_blob_pid});
+
+       ($self->{cat_blob_pid}, $self->{cat_blob_in},
+        $self->{cat_blob_out}, $self->{cat_blob_ctx}) =
+               command_bidi_pipe(qw(cat-file --batch));
+}
+
+sub _close_cat_blob {
+       my ($self) = @_;
+
+       return unless defined($self->{cat_blob_pid});
+
+       my @vars = map { 'cat_blob_' . $_ } qw(pid in out ctx);
+
+       command_close_bidi_pipe($self->{@vars});
+       delete $self->{@vars};
+}
 
 =back
 
@@ -895,7 +1095,11 @@ sub _cmd_close {
 }
 
 
-sub DESTROY { }
+sub DESTROY {
+       my ($self) = @_;
+       $self->_close_hash_and_insert_object();
+       $self->_close_cat_blob();
+}
 
 
 # Pipe implementation for ActiveState Perl.

diff --git a/t/t1006-cat-file.sh b/t/t1006-cat-file.sh
new file mode 100755 (executable)
index 0000000..cb1fbe5
--- /dev/null
+++ b/t/t1006-cat-file.sh
@@ -0,0 +1,226 @@
+#!/bin/sh
+
+test_description='git cat-file'
+
+. ./test-lib.sh
+
+echo_without_newline () {
+    printf '%s' "$*"
+}
+
+strlen () {
+    echo_without_newline "$1" | wc -c | sed -e 's/^ *//'
+}
+
+maybe_remove_timestamp () {
+    if test -z "$2"; then
+        echo_without_newline "$1"
+    else
+       echo_without_newline "$(printf '%s\n' "$1" | sed -e 's/ [0-9][0-9]* [-+][0-9][0-9][0-9][0-9]$//')"
+    fi
+}
+
+run_tests () {
+    type=$1
+    sha1=$2
+    size=$3
+    content=$4
+    pretty_content=$5
+    no_ts=$6
+
+    batch_output="$sha1 $type $size
+$content"
+
+    test_expect_success "$type exists" '
+       git cat-file -e $sha1
+    '
+
+    test_expect_success "Type of $type is correct" '
+        test $type = "$(git cat-file -t $sha1)"
+    '
+
+    test_expect_success "Size of $type is correct" '
+        test $size = "$(git cat-file -s $sha1)"
+    '
+
+    test -z "$content" ||
+    test_expect_success "Content of $type is correct" '
+       expect="$(maybe_remove_timestamp "$content" $no_ts)"
+       actual="$(maybe_remove_timestamp "$(git cat-file $type $sha1)" $no_ts)"
+
+        if test "z$expect" = "z$actual"
+       then
+               : happy
+       else
+               echo "Oops: expected $expect"
+               echo "but got $actual"
+               false
+        fi
+    '
+
+    test_expect_success "Pretty content of $type is correct" '
+       expect="$(maybe_remove_timestamp "$pretty_content" $no_ts)"
+       actual="$(maybe_remove_timestamp "$(git cat-file -p $sha1)" $no_ts)"
+        if test "z$expect" = "z$actual"
+       then
+               : happy
+       else
+               echo "Oops: expected $expect"
+               echo "but got $actual"
+               false
+        fi
+    '
+
+    test -z "$content" ||
+    test_expect_success "--batch output of $type is correct" '
+       expect="$(maybe_remove_timestamp "$batch_output" $no_ts)"
+       actual="$(maybe_remove_timestamp "$(echo $sha1 | git cat-file --batch)" no_ts)"
+        if test "z$expect" = "z$actual"
+       then
+               : happy
+       else
+               echo "Oops: expected $expect"
+               echo "but got $actual"
+               false
+        fi
+    '
+
+    test_expect_success "--batch-check output of $type is correct" '
+       expect="$sha1 $type $size"
+       actual="$(echo_without_newline $sha1 | git cat-file --batch-check)"
+        if test "z$expect" = "z$actual"
+       then
+               : happy
+       else
+               echo "Oops: expected $expect"
+               echo "but got $actual"
+               false
+        fi
+    '
+}
+
+hello_content="Hello World"
+hello_size=$(strlen "$hello_content")
+hello_sha1=$(echo_without_newline "$hello_content" | git hash-object --stdin)
+
+test_expect_success "setup" '
+       echo_without_newline "$hello_content" > hello &&
+       git update-index --add hello
+'
+
+run_tests 'blob' $hello_sha1 $hello_size "$hello_content" "$hello_content"
+
+tree_sha1=$(git write-tree)
+tree_size=33
+tree_pretty_content="100644 blob $hello_sha1   hello"
+
+run_tests 'tree' $tree_sha1 $tree_size "" "$tree_pretty_content"
+
+commit_message="Intial commit"
+commit_sha1=$(echo_without_newline "$commit_message" | git commit-tree $tree_sha1)
+commit_size=176
+commit_content="tree $tree_sha1
+author $GIT_AUTHOR_NAME <$GIT_AUTHOR_EMAIL> 0000000000 +0000
+committer $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> 0000000000 +0000
+
+$commit_message"
+
+run_tests 'commit' $commit_sha1 $commit_size "$commit_content" "$commit_content" 1
+
+tag_header_without_timestamp="object $hello_sha1
+type blob
+tag hellotag
+tagger $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL>"
+tag_description="This is a tag"
+tag_content="$tag_header_without_timestamp 0000000000 +0000
+
+$tag_description"
+tag_pretty_content="$tag_header_without_timestamp Thu Jan 1 00:00:00 1970 +0000
+
+$tag_description"
+
+tag_sha1=$(echo_without_newline "$tag_content" | git mktag)
+tag_size=$(strlen "$tag_content")
+
+run_tests 'tag' $tag_sha1 $tag_size "$tag_content" "$tag_pretty_content" 1
+
+test_expect_success \
+    "Reach a blob from a tag pointing to it" \
+    "test '$hello_content' = \"\$(git cat-file blob $tag_sha1)\""
+
+for batch in batch batch-check
+do
+    for opt in t s e p
+    do
+       test_expect_success "Passing -$opt with --$batch fails" '
+           test_must_fail git cat-file --$batch -$opt $hello_sha1
+       '
+
+       test_expect_success "Passing --$batch with -$opt fails" '
+           test_must_fail git cat-file -$opt --$batch $hello_sha1
+       '
+    done
+
+    test_expect_success "Passing <type> with --$batch fails" '
+       test_must_fail git cat-file --$batch blob $hello_sha1
+    '
+
+    test_expect_success "Passing --$batch with <type> fails" '
+       test_must_fail git cat-file blob --$batch $hello_sha1
+    '
+
+    test_expect_success "Passing sha1 with --$batch fails" '
+       test_must_fail git cat-file --$batch $hello_sha1
+    '
+done
+
+test_expect_success "--batch-check for a non-existent object" '
+    test "deadbeef missing" = \
+    "$(echo_without_newline deadbeef | git cat-file --batch-check)"
+'
+
+test_expect_success "--batch-check for an emtpy line" '
+    test " missing" = "$(echo | git cat-file --batch-check)"
+'
+
+batch_input="$hello_sha1
+$commit_sha1
+$tag_sha1
+deadbeef
+
+"
+
+batch_output="$hello_sha1 blob $hello_size
+$hello_content
+$commit_sha1 commit $commit_size
+$commit_content
+$tag_sha1 tag $tag_size
+$tag_content
+deadbeef missing
+ missing"
+
+test_expect_success '--batch with multiple sha1s gives correct format' '
+       test "$(maybe_remove_timestamp "$batch_output" 1)" = "$(maybe_remove_timestamp "$(echo_without_newline "$batch_input" | git cat-file --batch)" 1)"
+'
+
+batch_check_input="$hello_sha1
+$tree_sha1
+$commit_sha1
+$tag_sha1
+deadbeef
+
+"
+
+batch_check_output="$hello_sha1 blob $hello_size
+$tree_sha1 tree $tree_size
+$commit_sha1 commit $commit_size
+$tag_sha1 tag $tag_size
+deadbeef missing
+ missing"
+
+test_expect_success "--batch-check with multiple sha1s gives correct format" '
+    test "$batch_check_output" = \
+    "$(echo_without_newline "$batch_check_input" | git cat-file --batch-check)"
+'
+
+test_done

diff --git a/t/t1007-hash-object.sh b/t/t1007-hash-object.sh
new file mode 100755 (executable)
index 0000000..0526295
--- /dev/null
+++ b/t/t1007-hash-object.sh
@@ -0,0 +1,133 @@
+#!/bin/sh
+
+test_description=git-hash-object
+
+. ./test-lib.sh
+
+echo_without_newline() {
+       printf '%s' "$*"
+}
+
+test_blob_does_not_exist() {
+       test_expect_success 'blob does not exist in database' "
+               test_must_fail git cat-file blob $1
+       "
+}
+
+test_blob_exists() {
+       test_expect_success 'blob exists in database' "
+               git cat-file blob $1
+       "
+}
+
+hello_content="Hello World"
+hello_sha1=5e1c309dae7f45e0f39b1bf3ac3cd9db12e7d689
+
+example_content="This is an example"
+example_sha1=ddd3f836d3e3fbb7ae289aa9ae83536f76956399
+
+setup_repo() {
+       echo_without_newline "$hello_content" > hello
+       echo_without_newline "$example_content" > example
+}
+
+test_repo=test
+push_repo() {
+       test_create_repo $test_repo
+       cd $test_repo
+
+       setup_repo
+}
+
+pop_repo() {
+       cd ..
+       rm -rf $test_repo
+}
+
+setup_repo
+
+# Argument checking
+
+test_expect_success "multiple '--stdin's are rejected" '
+       test_must_fail git hash-object --stdin --stdin < example
+'
+
+test_expect_success "Can't use --stdin and --stdin-paths together" '
+       test_must_fail git hash-object --stdin --stdin-paths &&
+       test_must_fail git hash-object --stdin-paths --stdin
+'
+
+test_expect_success "Can't pass filenames as arguments with --stdin-paths" '
+       test_must_fail git hash-object --stdin-paths hello < example
+'
+
+# Behavior
+
+push_repo
+
+test_expect_success 'hash a file' '
+       test $hello_sha1 = $(git hash-object hello)
+'
+
+test_blob_does_not_exist $hello_sha1
+
+test_expect_success 'hash from stdin' '
+       test $example_sha1 = $(git hash-object --stdin < example)
+'
+
+test_blob_does_not_exist $example_sha1
+
+test_expect_success 'hash a file and write to database' '
+       test $hello_sha1 = $(git hash-object -w hello)
+'
+
+test_blob_exists $hello_sha1
+
+test_expect_success 'git hash-object --stdin file1 <file0 first operates on file0, then file1' '
+       echo foo > file1 &&
+       obname0=$(echo bar | git hash-object --stdin) &&
+       obname1=$(git hash-object file1) &&
+       obname0new=$(echo bar | git hash-object --stdin file1 | sed -n -e 1p) &&
+       obname1new=$(echo bar | git hash-object --stdin file1 | sed -n -e 2p) &&
+       test "$obname0" = "$obname0new" &&
+       test "$obname1" = "$obname1new"
+'
+
+pop_repo
+
+for args in "-w --stdin" "--stdin -w"; do
+       push_repo
+
+       test_expect_success "hash from stdin and write to database ($args)" '
+               test $example_sha1 = $(git hash-object $args < example)
+       '
+
+       test_blob_exists $example_sha1
+
+       pop_repo
+done
+
+filenames="hello
+example"
+
+sha1s="$hello_sha1
+$example_sha1"
+
+test_expect_success "hash two files with names on stdin" '
+       test "$sha1s" = "$(echo_without_newline "$filenames" | git hash-object --stdin-paths)"
+'
+
+for args in "-w --stdin-paths" "--stdin-paths -w"; do
+       push_repo
+
+       test_expect_success "hash two files with names on stdin and write to database ($args)" '
+               test "$sha1s" = "$(echo_without_newline "$filenames" | git hash-object $args)"
+       '
+
+       test_blob_exists $hello_sha1
+       test_blob_exists $example_sha1
+
+       pop_repo
+done
+
+test_done

diff --git a/t/t5303-hash-object.sh b/t/t5303-hash-object.sh
deleted file mode 100755 (executable)
index 543c078..0000000
--- a/t/t5303-hash-object.sh
+++ /dev/null
@@ -1,35 +0,0 @@
-#!/bin/sh
-
-test_description=git-hash-object
-
-. ./test-lib.sh
-
-test_expect_success \
-    'git hash-object -w --stdin saves the object' \
-    'obname=$(echo foo | git hash-object -w --stdin) &&
-    obpath=$(echo $obname | sed -e "s/\(..\)/\1\//") &&
-    test -r .git/objects/"$obpath" &&
-    rm -f .git/objects/"$obpath"'
-    
-test_expect_success \
-    'git hash-object --stdin -w saves the object' \
-    'obname=$(echo foo | git hash-object --stdin -w) &&
-    obpath=$(echo $obname | sed -e "s/\(..\)/\1\//") &&
-    test -r .git/objects/"$obpath" &&
-    rm -f .git/objects/"$obpath"'    
-
-test_expect_success \
-    'git hash-object --stdin file1 <file0 first operates on file0, then file1' \
-    'echo foo > file1 &&
-    obname0=$(echo bar | git hash-object --stdin) &&
-    obname1=$(git hash-object file1) &&
-    obname0new=$(echo bar | git hash-object --stdin file1 | sed -n -e 1p) &&
-    obname1new=$(echo bar | git hash-object --stdin file1 | sed -n -e 2p) &&
-    test "$obname0" = "$obname0new" &&
-    test "$obname1" = "$obname1new"'
-
-test_expect_success \
-    'git hash-object refuses multiple --stdin arguments' \
-    '! git hash-object --stdin --stdin < file1'
-
-test_done