[thirdparty/git.git] / perl / Git.pm

=head1 NAME

Git - Perl interface to the Git version control system

=cut


package Git;

use strict;


BEGIN {

our ($VERSION, @ISA, @EXPORT, @EXPORT_OK);

# Totally unstable API.
$VERSION = '0.01';


=head1 SYNOPSIS

  use Git;

  my $version = Git::command_oneline('version');

  Git::command_noisy('update-server-info');

  my $repo = Git->repository (Directory => '/srv/git/cogito.git');


  my @revs = $repo->command('rev-list', '--since=last monday', '--all');

  my $fh = $repo->command_pipe('rev-list', '--since=last monday', '--all');
  my $lastrev = <$fh>; chomp $lastrev;
  close $fh; # You may want to test rev-list exit status here

  my $lastrev = $repo->command_oneline('rev-list', '--all');

=cut


require Exporter;

@ISA = qw(Exporter);

@EXPORT = qw();

# Methods which can be called as standalone functions as well:
@EXPORT_OK = qw(command command_oneline command_pipe command_noisy
                exec_path hash_object);


=head1 DESCRIPTION

This module provides Perl scripts easy way to interface the Git version control
system. The modules have an easy and well-tested way to call arbitrary Git
commands; in the future, the interface will also provide specialized methods
for doing easily operations which are not totally trivial to do over
the generic command interface.

While some commands can be executed outside of any context (e.g. 'version'
or 'init-db'), most operations require a repository context, which in practice
means getting an instance of the Git object using the repository() constructor.
(In the future, we will also get a new_repository() constructor.) All commands
called as methods of the object are then executed in the context of the
repository.

TODO: In the future, we might also do

	my $subdir = $repo->subdir('Documentation');
	# Gets called in the subdirectory context:
	$subdir->command('status');

	my $remoterepo = $repo->remote_repository (Name => 'cogito', Branch => 'master');
	$remoterepo ||= Git->remote_repository ('http://git.or.cz/cogito.git/');
	my @refs = $remoterepo->refs();

So far, all functions just die if anything goes wrong. If you don't want that,
make appropriate provisions to catch the possible deaths. Better error recovery
mechanisms will be provided in the future.

Currently, the module merely wraps calls to external Git tools. In the future,
it will provide a much faster way to interact with Git by linking directly
to libgit. This should be completely opaque to the user, though (performance
increate nonwithstanding).

=cut


use Carp qw(carp croak);

require XSLoader;
XSLoader::load('Git', $VERSION);

}


=head1 CONSTRUCTORS

=over 4

=item repository ( OPTIONS )

=item repository ( DIRECTORY )

=item repository ()

Construct a new repository object.
C<OPTIONS> are passed in a hash like fashion, using key and value pairs.
Possible options are:

B<Repository> - Path to the Git repository.

B<WorkingCopy> - Path to the associated working copy; not strictly required
as many commands will happily crunch on a bare repository.

B<Directory> - Path to the Git working directory in its usual setup. This
is just for convenient setting of both C<Repository> and C<WorkingCopy>
at once: If the directory as a C<.git> subdirectory, C<Repository> is pointed
to the subdirectory and the directory is assumed to be the working copy.
If the directory does not have the subdirectory, C<WorkingCopy> is left
undefined and C<Repository> is pointed to the directory itself.

You should not use both C<Directory> and either of C<Repository> and
C<WorkingCopy> - the results of that are undefined.

Alternatively, a directory path may be passed as a single scalar argument
to the constructor; it is equivalent to setting only the C<Directory> option
field.

Calling the constructor with no options whatsoever is equivalent to
calling it with C<< Directory => '.' >>.

=cut

sub repository {
	my $class = shift;
	my @args = @_;
	my %opts = ();
	my $self;

	if (defined $args[0]) {
		if ($#args % 2 != 1) {
			# Not a hash.
			$#args == 0 or croak "bad usage";
			%opts = (Directory => $args[0]);
		} else {
			%opts = @args;
		}

		if ($opts{Directory}) {
			-d $opts{Directory} or croak "Directory not found: $!";
			if (-d $opts{Directory}."/.git") {
				# TODO: Might make this more clever
				$opts{WorkingCopy} = $opts{Directory};
				$opts{Repository} = $opts{Directory}."/.git";
			} else {
				$opts{Repository} = $opts{Directory};
			}
			delete $opts{Directory};
		}
	}

	$self = { opts => \%opts };
	bless $self, $class;
}


=back

=head1 METHODS

=over 4

=item command ( COMMAND [, ARGUMENTS... ] )

Execute the given Git C<COMMAND> (specify it without the 'git-'
prefix), optionally with the specified extra C<ARGUMENTS>.

The method can be called without any instance or on a specified Git repository
(in that case the command will be run in the repository context).

In scalar context, it returns all the command output in a single string
(verbatim).

In array context, it returns an array containing lines printed to the
command's stdout (without trailing newlines).

In both cases, the command's stdin and stderr are the same as the caller's.

=cut

sub command {
	my $fh = command_pipe(@_);

	if (not defined wantarray) {
		_cmd_close($fh);

	} elsif (not wantarray) {
		local $/;
		my $text = <$fh>;
		_cmd_close($fh);
		return $text;

	} else {
		my @lines = <$fh>;
		_cmd_close($fh);
		chomp @lines;
		return @lines;
	}
}


=item command_oneline ( COMMAND [, ARGUMENTS... ] )

Execute the given C<COMMAND> in the same way as command()
does but always return a scalar string containing the first line
of the command's standard output.

=cut

sub command_oneline {
	my $fh = command_pipe(@_);

	my $line = <$fh>;
	_cmd_close($fh);

	chomp $line;
	return $line;
}


=item command_pipe ( COMMAND [, ARGUMENTS... ] )

Execute the given C<COMMAND> in the same way as command()
does but return a pipe filehandle from which the command output can be
read.

=cut

sub command_pipe {
	my ($self, $cmd, @args) = _maybe_self(@_);

	$cmd =~ /^[a-z0-9A-Z_-]+$/ or croak "bad command: $cmd";

	my $pid = open(my $fh, "-|");
	if (not defined $pid) {
		croak "open failed: $!";
	} elsif ($pid == 0) {
		_cmd_exec($self, $cmd, @args);
	}
	return $fh;
}


=item command_noisy ( COMMAND [, ARGUMENTS... ] )

Execute the given C<COMMAND> in the same way as command() does but do not
capture the command output - the standard output is not redirected and goes
to the standard output of the caller application.

While the method is called command_noisy(), you might want to as well use
it for the most silent Git commands which you know will never pollute your
stdout but you want to avoid the overhead of the pipe setup when calling them.

The function returns only after the command has finished running.

=cut

sub command_noisy {
	my ($self, $cmd, @args) = _maybe_self(@_);

	$cmd =~ /^[a-z0-9A-Z_-]+$/ or croak "bad command: $cmd";

	my $pid = fork;
	if (not defined $pid) {
		croak "fork failed: $!";
	} elsif ($pid == 0) {
		_cmd_exec($self, $cmd, @args);
	}
	if (waitpid($pid, 0) > 0 and $? != 0) {
		croak "exit status: $?";
	}
}


=item exec_path ()

Return path to the git sub-command executables (the same as
C<git --exec-path>). Useful mostly only internally.

Implementation of this function is very fast; no external command calls
are involved.

=cut

# Implemented in Git.xs.


=item hash_object ( FILENAME [, TYPE ] )

=item hash_object ( FILEHANDLE [, TYPE ] )

Compute the SHA1 object id of the given C<FILENAME> (or data waiting in
C<FILEHANDLE>) considering it is of the C<TYPE> object type (C<blob>
(default), C<commit>, C<tree>).

In case of C<FILEHANDLE> passed instead of file name, all the data
available are read and hashed, and the filehandle is automatically
closed. The file handle should be freshly opened - if you have already
read anything from the file handle, the results are undefined (since
this function works directly with the file descriptor and internal
PerlIO buffering might have messed things up).

The method can be called without any instance or on a specified Git repository,
it makes zero difference.

The function returns the SHA1 hash.

Implementation of this function is very fast; no external command calls
are involved.

=cut

# Implemented in Git.xs.


=back

=head1 TODO

This is still fairly crude.
We need some good way to report errors back except just dying.

=head1 COPYRIGHT

Copyright 2006 by Petr Baudis E<lt>pasky@suse.czE<gt>.

This module is free software; it may be used, copied, modified
and distributed under the terms of the GNU General Public Licence,
either version 2, or (at your option) any later version.

=cut


# Take raw method argument list and return ($obj, @args) in case
# the method was called upon an instance and (undef, @args) if
# it was called directly.
sub _maybe_self {
	# This breaks inheritance. Oh well.
	ref $_[0] eq 'Git' ? @_ : (undef, @_);
}

# When already in the subprocess, set up the appropriate state
# for the given repository and execute the git command.
sub _cmd_exec {
	my ($self, @args) = @_;
	if ($self) {
		$self->{opts}->{Repository} and $ENV{'GIT_DIR'} = $self->{opts}->{Repository};
		$self->{opts}->{WorkingCopy} and chdir($self->{opts}->{WorkingCopy});
	}
	xs__execv_git_cmd(@args);
	croak "exec failed: $!";
}

# Execute the given Git command ($_[0]) with arguments ($_[1..])
# by searching for it at proper places.
# _execv_git_cmd(), implemented in Git.xs.

# Close pipe to a subprocess.
sub _cmd_close {
	my ($fh) = @_;
	if (not close $fh) {
		if ($!) {
			# It's just close, no point in fatalities
			carp "error closing pipe: $!";
		} elsif ($? >> 8) {
			croak "exit status: ".($? >> 8);
		}
		# else we might e.g. closed a live stream; the command
		# dying of SIGPIPE would drive us here.
	}
}


# Trickery for .xs routines: In order to avoid having some horrid
# C code trying to do stuff with undefs and hashes, we gate all
# xs calls through the following and in case we are being ran upon
# an instance call a C part of the gate which will set up the
# environment properly.
sub _call_gate {
	my $xsfunc = shift;
	my ($self, @args) = _maybe_self(@_);

	if (defined $self) {
		# XXX: We ignore the WorkingCopy! To properly support
		# that will require heavy changes in libgit.

		# XXX: And we ignore everything else as well. libgit
		# at least needs to be extended to let us specify
		# the $GIT_DIR instead of looking it up in environment.
		#xs_call_gate($self->{opts}->{Repository});
	}

	&$xsfunc(@args);
}

sub AUTOLOAD {
	my $xsname;
	our $AUTOLOAD;
	($xsname = $AUTOLOAD) =~ s/.*:://;
	croak "&Git::$xsname not defined" if $xsname =~ /^xs_/;
	$xsname = 'xs_'.$xsname;
	_call_gate(\&$xsname, @_);
}

sub DESTROY { }


1; # Famous last words
Commit	Line	Data
b1edc53d PB	1	=head1 NAME
	2
	3	Git - Perl interface to the Git version control system
	4
	5	=cut
	6
	7
	8	package Git;
	9
	10	use strict;
	11
	12
	13	BEGIN {
	14
	15	our ($VERSION, @ISA, @EXPORT, @EXPORT_OK);
	16
	17	# Totally unstable API.
	18	$VERSION = '0.01';
	19
	20
	21	=head1 SYNOPSIS
	22
	23	use Git;
	24
	25	my $version = Git::command_oneline('version');
	26
	27	Git::command_noisy('update-server-info');
	28
	29	my $repo = Git->repository (Directory => '/srv/git/cogito.git');
	30
	31
	32	my @revs = $repo->command('rev-list', '--since=last monday', '--all');
	33
	34	my $fh = $repo->command_pipe('rev-list', '--since=last monday', '--all');
	35	my $lastrev = <$fh>; chomp $lastrev;
	36	close $fh; # You may want to test rev-list exit status here
	37
	38	my $lastrev = $repo->command_oneline('rev-list', '--all');
	39
	40	=cut
	41
	42
	43	require Exporter;
	44
	45	@ISA = qw(Exporter);
	46
	47	@EXPORT = qw();
	48
	49	# Methods which can be called as standalone functions as well:
	50	@EXPORT_OK = qw(command command_oneline command_pipe command_noisy
eca1f6fd	51	exec_path hash_object);
b1edc53d PB	52
	53
	54	=head1 DESCRIPTION
	55
	56	This module provides Perl scripts easy way to interface the Git version control
	57	system. The modules have an easy and well-tested way to call arbitrary Git
	58	commands; in the future, the interface will also provide specialized methods
	59	for doing easily operations which are not totally trivial to do over
	60	the generic command interface.
	61
	62	While some commands can be executed outside of any context (e.g. 'version'
	63	or 'init-db'), most operations require a repository context, which in practice
	64	means getting an instance of the Git object using the repository() constructor.
	65	(In the future, we will also get a new_repository() constructor.) All commands
	66	called as methods of the object are then executed in the context of the
	67	repository.
	68
	69	TODO: In the future, we might also do
	70
	71	my $subdir = $repo->subdir('Documentation');
	72	# Gets called in the subdirectory context:
	73	$subdir->command('status');
	74
	75	my $remoterepo = $repo->remote_repository (Name => 'cogito', Branch => 'master');
	76	$remoterepo \|\|= Git->remote_repository ('http://git.or.cz/cogito.git/');
	77	my @refs = $remoterepo->refs();
	78
	79	So far, all functions just die if anything goes wrong. If you don't want that,
	80	make appropriate provisions to catch the possible deaths. Better error recovery
	81	mechanisms will be provided in the future.
	82
	83	Currently, the module merely wraps calls to external Git tools. In the future,
	84	it will provide a much faster way to interact with Git by linking directly
	85	to libgit. This should be completely opaque to the user, though (performance
	86	increate nonwithstanding).
	87
	88	=cut
	89
	90
	91	use Carp qw(carp croak);
	92
	93	require XSLoader;
	94	XSLoader::load('Git', $VERSION);
	95
	96	}
	97
	98
	99	=head1 CONSTRUCTORS
	100
	101	=over 4
	102
	103	=item repository ( OPTIONS )
	104
	105	=item repository ( DIRECTORY )
	106
	107	=item repository ()
	108
	109	Construct a new repository object.
	110	C<OPTIONS> are passed in a hash like fashion, using key and value pairs.
	111	Possible options are:
	112
	113	B<Repository> - Path to the Git repository.
	114
	115	B<WorkingCopy> - Path to the associated working copy; not strictly required
116	as many commands will happily crunch on a bare repository.
117
118	B<Directory> - Path to the Git working directory in its usual setup. This
119	is just for convenient setting of both C<Repository> and C<WorkingCopy>
120	at once: If the directory as a C<.git> subdirectory, C<Repository> is pointed
121	to the subdirectory and the directory is assumed to be the working copy.
122	If the directory does not have the subdirectory, C<WorkingCopy> is left
123	undefined and C<Repository> is pointed to the directory itself.
124
b1edc53d PB	125	You should not use both C<Directory> and either of C<Repository> and
	126	C<WorkingCopy> - the results of that are undefined.
	127
	128	Alternatively, a directory path may be passed as a single scalar argument
	129	to the constructor; it is equivalent to setting only the C<Directory> option
	130	field.
	131
	132	Calling the constructor with no options whatsoever is equivalent to
	133	calling it with C<< Directory => '.' >>.
	134
	135	=cut
	136
	137	sub repository {
	138	my $class = shift;
	139	my @args = @_;
	140	my %opts = ();
	141	my $self;
	142
	143	if (defined $args[0]) {
	144	if ($#args % 2 != 1) {
	145	# Not a hash.
	146	$#args == 0 or croak "bad usage";
	147	%opts = (Directory => $args[0]);
	148	} else {
	149	%opts = @args;
	150	}
	151
	152	if ($opts{Directory}) {
	153	-d $opts{Directory} or croak "Directory not found: $!";
	154	if (-d $opts{Directory}."/.git") {
	155	# TODO: Might make this more clever
	156	$opts{WorkingCopy} = $opts{Directory};
	157	$opts{Repository} = $opts{Directory}."/.git";
	158	} else {
	159	$opts{Repository} = $opts{Directory};
	160	}
	161	delete $opts{Directory};
	162	}
	163	}
	164
	165	$self = { opts => \%opts };
	166	bless $self, $class;
	167	}
	168
	169
	170	=back
	171
	172	=head1 METHODS
	173
	174	=over 4
	175
	176	=item command ( COMMAND [, ARGUMENTS... ] )
	177
	178	Execute the given Git C<COMMAND> (specify it without the 'git-'
	179	prefix), optionally with the specified extra C<ARGUMENTS>.
	180
	181	The method can be called without any instance or on a specified Git repository
	182	(in that case the command will be run in the repository context).
	183
	184	In scalar context, it returns all the command output in a single string
	185	(verbatim).
	186
	187	In array context, it returns an array containing lines printed to the
	188	command's stdout (without trailing newlines).
189
190	In both cases, the command's stdin and stderr are the same as the caller's.
191
192	=cut
193
194	sub command {
195	my $fh = command_pipe(@_);
196
197	if (not defined wantarray) {
198	_cmd_close($fh);
199
200	} elsif (not wantarray) {
201	local $/;
202	my $text = <$fh>;
203	_cmd_close($fh);
204	return $text;
205
206	} else {
207	my @lines = <$fh>;
208	_cmd_close($fh);
209	chomp @lines;
210	return @lines;
211	}
212	}
213
214
215	=item command_oneline ( COMMAND [, ARGUMENTS... ] )
216
217	Execute the given C<COMMAND> in the same way as command()
218	does but always return a scalar string containing the first line
219	of the command's standard output.
220
221	=cut
222
223	sub command_oneline {
224	my $fh = command_pipe(@_);
225
226	my $line = <$fh>;
227	_cmd_close($fh);
228
229	chomp $line;
230	return $line;
231	}
232
233
234	=item command_pipe ( COMMAND [, ARGUMENTS... ] )
235
236	Execute the given C<COMMAND> in the same way as command()
237	does but return a pipe filehandle from which the command output can be
238	read.
239
240	=cut
241
242	sub command_pipe {
243	my ($self, $cmd, @args) = _maybe_self(@_);
244
245	$cmd =~ /^[a-z0-9A-Z_-]+$/ or croak "bad command: $cmd";
246
247	my $pid = open(my $fh, "-\|");
248	if (not defined $pid) {
249	croak "open failed: $!";
250	} elsif ($pid == 0) {
251	_cmd_exec($self, $cmd, @args);
252	}
253	return $fh;
254	}
255
256
257	=item command_noisy ( COMMAND [, ARGUMENTS... ] )
258
259	Execute the given C<COMMAND> in the same way as command() does but do not
260	capture the command output - the standard output is not redirected and goes
261	to the standard output of the caller application.
262
263	While the method is called command_noisy(), you might want to as well use
264	it for the most silent Git commands which you know will never pollute your
265	stdout but you want to avoid the overhead of the pipe setup when calling them.
266
267	The function returns only after the command has finished running.
268
269	=cut
270
271	sub command_noisy {
272	my ($self, $cmd, @args) = _maybe_self(@_);
273
274	$cmd =~ /^[a-z0-9A-Z_-]+$/ or croak "bad command: $cmd";
275
276	my $pid = fork;
277	if (not defined $pid) {
278	croak "fork failed: $!";
279	} elsif ($pid == 0) {
280	_cmd_exec($self, $cmd, @args);
281	}
282	if (waitpid($pid, 0) > 0 and $? != 0) {
283	croak "exit status: $?";
284	}
285	}
286
287
eca1f6fd PB	288	=item exec_path ()
	289
	290	Return path to the git sub-command executables (the same as
	291	C<git --exec-path>). Useful mostly only internally.
	292
	293	Implementation of this function is very fast; no external command calls
	294	are involved.
	295
	296	=cut
	297
	298	# Implemented in Git.xs.
	299
	300
b1edc53d PB	301	=item hash_object ( FILENAME [, TYPE ] )
	302
	303	=item hash_object ( FILEHANDLE [, TYPE ] )
	304
	305	Compute the SHA1 object id of the given C<FILENAME> (or data waiting in
	306	C<FILEHANDLE>) considering it is of the C<TYPE> object type (C<blob>
	307	(default), C<commit>, C<tree>).
	308
	309	In case of C<FILEHANDLE> passed instead of file name, all the data
	310	available are read and hashed, and the filehandle is automatically
	311	closed. The file handle should be freshly opened - if you have already
	312	read anything from the file handle, the results are undefined (since
	313	this function works directly with the file descriptor and internal
	314	PerlIO buffering might have messed things up).
	315
	316	The method can be called without any instance or on a specified Git repository,
	317	it makes zero difference.
	318
	319	The function returns the SHA1 hash.
	320
	321	Implementation of this function is very fast; no external command calls
	322	are involved.
	323
	324	=cut
	325
	326	# Implemented in Git.xs.
	327
	328
	329	=back
	330
	331	=head1 TODO
	332
	333	This is still fairly crude.
	334	We need some good way to report errors back except just dying.
	335
	336	=head1 COPYRIGHT
	337
	338	Copyright 2006 by Petr Baudis E<lt>pasky@suse.czE<gt>.
	339
	340	This module is free software; it may be used, copied, modified
	341	and distributed under the terms of the GNU General Public Licence,
	342	either version 2, or (at your option) any later version.
	343
	344	=cut
	345
	346
	347	# Take raw method argument list and return ($obj, @args) in case
	348	# the method was called upon an instance and (undef, @args) if
	349	# it was called directly.
	350	sub _maybe_self {
	351	# This breaks inheritance. Oh well.
	352	ref $_[0] eq 'Git' ? @_ : (undef, @_);
	353	}
	354
	355	# When already in the subprocess, set up the appropriate state
	356	# for the given repository and execute the git command.
	357	sub _cmd_exec {
	358	my ($self, @args) = @_;
	359	if ($self) {
	360	$self->{opts}->{Repository} and $ENV{'GIT_DIR'} = $self->{opts}->{Repository};
	361	$self->{opts}->{WorkingCopy} and chdir($self->{opts}->{WorkingCopy});
	362	}
8062f81c PB	363	xs__execv_git_cmd(@args);
8062f81c PB	364	croak "exec failed: $!";
b1edc53d PB	365	}
b1edc53d PB	366
8062f81c PB	367	# Execute the given Git command ($_[0]) with arguments ($_[1..])
	368	# by searching for it at proper places.
	369	# _execv_git_cmd(), implemented in Git.xs.
	370
b1edc53d PB	371	# Close pipe to a subprocess.
	372	sub _cmd_close {
	373	my ($fh) = @_;
	374	if (not close $fh) {
	375	if ($!) {
	376	# It's just close, no point in fatalities
	377	carp "error closing pipe: $!";
	378	} elsif ($? >> 8) {
	379	croak "exit status: ".($? >> 8);
	380	}
	381	# else we might e.g. closed a live stream; the command
	382	# dying of SIGPIPE would drive us here.
	383	}
	384	}
	385
	386
	387	# Trickery for .xs routines: In order to avoid having some horrid
	388	# C code trying to do stuff with undefs and hashes, we gate all
	389	# xs calls through the following and in case we are being ran upon
	390	# an instance call a C part of the gate which will set up the
	391	# environment properly.
	392	sub _call_gate {
	393	my $xsfunc = shift;
	394	my ($self, @args) = _maybe_self(@_);
	395
	396	if (defined $self) {
	397	# XXX: We ignore the WorkingCopy! To properly support
	398	# that will require heavy changes in libgit.
	399
	400	# XXX: And we ignore everything else as well. libgit
	401	# at least needs to be extended to let us specify
	402	# the $GIT_DIR instead of looking it up in environment.
	403	#xs_call_gate($self->{opts}->{Repository});
	404	}
	405
	406	&$xsfunc(@args);
	407	}
	408
	409	sub AUTOLOAD {
	410	my $xsname;
	411	our $AUTOLOAD;
	412	($xsname = $AUTOLOAD) =~ s/.*:://;
	413	croak "&Git::$xsname not defined" if $xsname =~ /^xs_/;
	414	$xsname = 'xs_'.$xsname;
	415	_call_gate(\&$xsname, @_);
	416	}
	417
	418	sub DESTROY { }
	419
	420
	421	1; # Famous last words