X-Git-Url: https://git.tokkee.org/?a=blobdiff_plain;ds=inline;f=perl%2FGit.pm;h=2b26b65bfb00c60535919d7b9359a5549f9e9709;hb=c326246accf36bc070b326773df2b9ec1c336037;hp=212337ee5bfe64bb0479eab01beb073f4f007f89;hpb=8062f81c2d9df5e6552bf267b258ffcc5f647f93;p=git.git diff --git a/perl/Git.pm b/perl/Git.pm index 212337ee5..2b26b65bf 100644 --- a/perl/Git.pm +++ b/perl/Git.pm @@ -24,18 +24,20 @@ $VERSION = '0.01'; my $version = Git::command_oneline('version'); - Git::command_noisy('update-server-info'); + git_cmd_try { Git::command_noisy('update-server-info') } + '%s failed w/ code %d'; my $repo = Git->repository (Directory => '/srv/git/cogito.git'); my @revs = $repo->command('rev-list', '--since=last monday', '--all'); - my $fh = $repo->command_pipe('rev-list', '--since=last monday', '--all'); + my ($fh, $c) = $repo->command_output_pipe('rev-list', '--since=last monday', '--all'); my $lastrev = <$fh>; chomp $lastrev; - close $fh; # You may want to test rev-list exit status here + $repo->command_close_pipe($fh, $c); - my $lastrev = $repo->command_oneline('rev-list', '--all'); + my $lastrev = $repo->command_oneline( [ 'rev-list', '--all' ], + STDERR => 0 ); =cut @@ -44,11 +46,12 @@ require Exporter; @ISA = qw(Exporter); -@EXPORT = qw(); +@EXPORT = qw(git_cmd_try); # Methods which can be called as standalone functions as well: -@EXPORT_OK = qw(command command_oneline command_pipe command_noisy - exec_path hash_object); +@EXPORT_OK = qw(command command_oneline command_noisy + command_output_pipe command_input_pipe command_close_pipe + version exec_path hash_object git_cmd_try); =head1 DESCRIPTION @@ -66,20 +69,18 @@ means getting an instance of the Git object using the repository() constructor. called as methods of the object are then executed in the context of the repository. -TODO: In the future, we might also do +Part of the "repository state" is also information about path to the attached +working copy (unless you work with a bare repository). You can also navigate +inside of the working copy using the C method. (Note that +the repository object is self-contained and will not change working directory +of your process.) - my $subdir = $repo->subdir('Documentation'); - # Gets called in the subdirectory context: - $subdir->command('status'); +TODO: In the future, we might also do 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 @@ -88,10 +89,9 @@ increate nonwithstanding). =cut -use Carp qw(carp croak); - -require XSLoader; -XSLoader::load('Git', $VERSION); +use Carp qw(carp croak); # but croak is bad - throw instead +use Error qw(:try); +use Cwd qw(abs_path); } @@ -115,12 +115,17 @@ B - Path to the Git repository. B - Path to the associated working copy; not strictly required as many commands will happily crunch on a bare repository. -B - Path to the Git working directory in its usual setup. This -is just for convenient setting of both C and C -at once: If the directory as a C<.git> subdirectory, C is pointed -to the subdirectory and the directory is assumed to be the working copy. -If the directory does not have the subdirectory, C is left -undefined and C is pointed to the directory itself. +B - Subdirectory in the working copy to work inside. +Just left undefined if you do not want to limit the scope of operations. + +B - Path to the Git working directory in its usual setup. +The C<.git> directory is searched in the directory and all the parent +directories; if found, C is set to the directory containing +it and C to the C<.git> directory itself. If no C<.git> +directory was found, the C is assumed to be a bare repository, +C is set to point at it and C is left undefined. +If the C<$GIT_DIR> environment variable is set, things behave as expected +as well. You should not use both C and either of C and C - the results of that are undefined. @@ -130,7 +135,10 @@ to the constructor; it is equivalent to setting only the C option field. Calling the constructor with no options whatsoever is equivalent to -calling it with C<< Directory => '.' >>. +calling it with C<< Directory => '.' >>. In general, if you are building +a standard porcelain command, simply doing C<< Git->repository() >> should +do the right thing and setup the object to reflect exactly where the user +is right now. =cut @@ -143,23 +151,65 @@ sub repository { if (defined $args[0]) { if ($#args % 2 != 1) { # Not a hash. - $#args == 0 or croak "bad usage"; - %opts = (Directory => $args[0]); + $#args == 0 or throw Error::Simple("bad usage"); + %opts = ( Directory => $args[0] ); } else { %opts = @args; } + } + + if (not defined $opts{Repository} and not defined $opts{WorkingCopy}) { + $opts{Directory} ||= '.'; + } + + if ($opts{Directory}) { + -d $opts{Directory} or throw Error::Simple("Directory not found: $!"); + + my $search = Git->repository(WorkingCopy => $opts{Directory}); + my $dir; + try { + $dir = $search->command_oneline(['rev-parse', '--git-dir'], + STDERR => 0); + } catch Git::Error::Command with { + $dir = undef; + }; + + if ($dir) { + $dir =~ m#^/# or $dir = $opts{Directory} . '/' . $dir; + $opts{Repository} = $dir; + + # If --git-dir went ok, this shouldn't die either. + my $prefix = $search->command_oneline('rev-parse', '--show-prefix'); + $dir = abs_path($opts{Directory}) . '/'; + if ($prefix) { + if (substr($dir, -length($prefix)) ne $prefix) { + throw Error::Simple("rev-parse confused me - $dir does not have trailing $prefix"); + } + substr($dir, -length($prefix)) = ''; + } + $opts{WorkingCopy} = $dir; + $opts{WorkingSubdir} = $prefix; + + } else { + # A bare repository? Let's see... + $dir = $opts{Directory}; - if ($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} = $opts{Directory}; + unless (-d "$dir/refs" and -d "$dir/objects" and -e "$dir/HEAD") { + # Mimick git-rev-parse --git-dir error message: + throw Error::Simple('fatal: Not a git repository'); + } + my $search = Git->repository(Repository => $dir); + try { + $search->command('symbolic-ref', 'HEAD'); + } catch Git::Error::Command with { + # Mimick git-rev-parse --git-dir error message: + throw Error::Simple('fatal: Not a git repository'); } - delete $opts{Directory}; + + $opts{Repository} = abs_path($dir); } + + delete $opts{Directory}; } $self = { opts => \%opts }; @@ -175,9 +225,21 @@ sub repository { =item command ( COMMAND [, ARGUMENTS... ] ) +=item command ( [ COMMAND, ARGUMENTS... ], { Opt => Val ... } ) + Execute the given Git C (specify it without the 'git-' prefix), optionally with the specified extra C. +The second more elaborate form can be used if you want to further adjust +the command execution. Currently, only one option is supported: + +B - How to deal with the command's error output. By default (C) +it is delivered to the caller's C. A false value (0 or '') will cause +it to be thrown away. If you want to process it, you can get it in a filehandle +you specify, but you must be extremely careful; if the error output is not +very short and you want to read it in the same process as where you called +C, you are set up for a nice deadlock! + 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). @@ -192,21 +254,35 @@ In both cases, the command's stdin and stderr are the same as the caller's. =cut sub command { - my $fh = command_pipe(@_); + my ($fh, $ctx) = command_output_pipe(@_); if (not defined wantarray) { - _cmd_close($fh); + # Nothing to pepper the possible exception with. + _cmd_close($fh, $ctx); } elsif (not wantarray) { local $/; my $text = <$fh>; - _cmd_close($fh); + try { + _cmd_close($fh, $ctx); + } catch Git::Error::Command with { + # Pepper with the output: + my $E = shift; + $E->{'-outputref'} = \$text; + throw $E; + }; return $text; } else { my @lines = <$fh>; - _cmd_close($fh); chomp @lines; + try { + _cmd_close($fh, $ctx); + } catch Git::Error::Command with { + my $E = shift; + $E->{'-outputref'} = \@lines; + throw $E; + }; return @lines; } } @@ -214,6 +290,8 @@ sub command { =item command_oneline ( COMMAND [, ARGUMENTS... ] ) +=item command_oneline ( [ COMMAND, ARGUMENTS... ], { Opt => Val ... } ) + Execute the given C in the same way as command() does but always return a scalar string containing the first line of the command's standard output. @@ -221,36 +299,80 @@ of the command's standard output. =cut sub command_oneline { - my $fh = command_pipe(@_); + my ($fh, $ctx) = command_output_pipe(@_); my $line = <$fh>; - _cmd_close($fh); - - chomp $line; + defined $line and chomp $line; + try { + _cmd_close($fh, $ctx); + } catch Git::Error::Command with { + # Pepper with the output: + my $E = shift; + $E->{'-outputref'} = \$line; + throw $E; + }; return $line; } -=item command_pipe ( COMMAND [, ARGUMENTS... ] ) +=item command_output_pipe ( COMMAND [, ARGUMENTS... ] ) + +=item command_output_pipe ( [ COMMAND, ARGUMENTS... ], { Opt => Val ... } ) Execute the given C in the same way as command() does but return a pipe filehandle from which the command output can be read. +The function can return C<($pipe, $ctx)> in array context. +See C for details. + =cut -sub command_pipe { - my ($self, $cmd, @args) = _maybe_self(@_); +sub command_output_pipe { + _command_common_pipe('-|', @_); +} - $cmd =~ /^[a-z0-9A-Z_-]+$/ 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 $fh; +=item command_input_pipe ( COMMAND [, ARGUMENTS... ] ) + +=item command_input_pipe ( [ COMMAND, ARGUMENTS... ], { Opt => Val ... } ) + +Execute the given C in the same way as command_output_pipe() +does but return an input pipe filehandle instead; the command output +is not captured. + +The function can return C<($pipe, $ctx)> in array context. +See C for details. + +=cut + +sub command_input_pipe { + _command_common_pipe('|-', @_); +} + + +=item command_close_pipe ( PIPE [, CTX ] ) + +Close the C as returned from C, checking +whether the command finished successfuly. The optional C argument +is required if you want to see the command name in the error message, +and it is the second value returned by C when +called in array context. The call idiom is: + + my ($fh, $ctx) = $r->command_output_pipe('status'); + while (<$fh>) { ... } + $r->command_close_pipe($fh, $ctx); + +Note that you should not rely on whatever actually is in C; +currently it is simply the command name but in future the context might +have more complicated structure. + +=cut + +sub command_close_pipe { + my ($self, $fh, $ctx) = _maybe_self(@_); + $ctx ||= ''; + _cmd_close($fh, $ctx); } @@ -270,68 +392,310 @@ The function returns only after the command has finished running. sub command_noisy { my ($self, $cmd, @args) = _maybe_self(@_); - - $cmd =~ /^[a-z0-9A-Z_-]+$/ or croak "bad command: $cmd"; + _check_valid_cmd($cmd); my $pid = fork; if (not defined $pid) { - croak "fork failed: $!"; + throw Error::Simple("fork failed: $!"); } elsif ($pid == 0) { _cmd_exec($self, $cmd, @args); } - if (waitpid($pid, 0) > 0 and $? != 0) { - croak "exit status: $?"; + if (waitpid($pid, 0) > 0 and $?>>8 != 0) { + throw Git::Error::Command(join(' ', $cmd, @args), $? >> 8); } } +=item version () + +Return the Git version in use. + +=cut + +sub version { + my $verstr = command_oneline('--version'); + $verstr =~ s/^git version //; + $verstr; +} + + =item exec_path () -Return path to the git sub-command executables (the same as +Return path to the Git sub-command executables (the same as C). Useful mostly only internally. -Implementation of this function is very fast; no external command calls -are involved. +=cut + +sub exec_path { command_oneline('--exec-path') } + + +=item repo_path () + +Return path to the git repository. Must be called on a repository instance. =cut -# Implemented in Git.xs. +sub repo_path { $_[0]->{opts}->{Repository} } -=item hash_object ( FILENAME [, TYPE ] ) +=item wc_path () -=item hash_object ( FILEHANDLE [, TYPE ] ) +Return path to the working copy. Must be called on a repository instance. -Compute the SHA1 object id of the given C (or data waiting in -C) considering it is of the C object type (C -(default), C, C). +=cut + +sub wc_path { $_[0]->{opts}->{WorkingCopy} } + + +=item wc_subdir () + +Return path to the subdirectory inside of a working copy. Must be called +on a repository instance. + +=cut -In case of C 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). +sub wc_subdir { $_[0]->{opts}->{WorkingSubdir} ||= '' } + + +=item wc_chdir ( SUBDIR ) + +Change the working copy subdirectory to work within. The C is +relative to the working copy root directory (not the current subdirectory). +Must be called on a repository instance attached to a working copy +and the directory must exist. + +=cut + +sub wc_chdir { + my ($self, $subdir) = @_; + $self->wc_path() + or throw Error::Simple("bare repository"); + + -d $self->wc_path().'/'.$subdir + or throw Error::Simple("subdir not found: $!"); + # Of course we will not "hold" the subdirectory so anyone + # can delete it now and we will never know. But at least we tried. + + $self->{opts}->{WorkingSubdir} = $subdir; +} + + +=item config ( VARIABLE ) + +Retrieve the configuration C in the same manner as C +does. In scalar context requires the variable to be set only one time +(exception is thrown otherwise), in array context returns allows the +variable to be set multiple times and returns all the values. + +Must be called on a repository instance. + +This currently wraps command('repo-config') so it is not so fast. + +=cut + +sub config { + my ($self, $var) = @_; + $self->repo_path() + or throw Error::Simple("not a repository"); + + try { + if (wantarray) { + return $self->command('repo-config', '--get-all', $var); + } else { + return $self->command_oneline('repo-config', '--get', $var); + } + } catch Git::Error::Command with { + my $E = shift; + if ($E->value() == 1) { + # Key not found. + return undef; + } else { + throw $E; + } + }; +} + + +=item ident ( TYPE | IDENTSTR ) + +=item ident_person ( TYPE | IDENTSTR | IDENTARRAY ) + +This suite of functions retrieves and parses ident information, as stored +in the commit and tag objects or produced by C (thus +C can be either I or I; case is insignificant). + +The C method retrieves the ident information from C +and either returns it as a scalar string or as an array with the fields parsed. +Alternatively, it can take a prepared ident string (e.g. from the commit +object) and just parse it. + +C returns the person part of the ident - name and email; +it can take the same arguments as C or the array returned by C. + +The synopsis is like: + + my ($name, $email, $time_tz) = ident('author'); + "$name <$email>" eq ident_person('author'); + "$name <$email>" eq ident_person($name); + $time_tz =~ /^\d+ [+-]\d{4}$/; + +Both methods must be called on a repository instance. + +=cut + +sub ident { + my ($self, $type) = @_; + my $identstr; + if (lc $type eq lc 'committer' or lc $type eq lc 'author') { + $identstr = $self->command_oneline('var', 'GIT_'.uc($type).'_IDENT'); + } else { + $identstr = $type; + } + if (wantarray) { + return $identstr =~ /^(.*) <(.*)> (\d+ [+-]\d{4})$/; + } else { + return $identstr; + } +} + +sub ident_person { + my ($self, @ident) = @_; + $#ident == 0 and @ident = $self->ident($ident[0]); + return "$ident[0] <$ident[1]>"; +} + + +=item hash_object ( TYPE, FILENAME ) + +Compute the SHA1 object id of the given C (or data waiting in +C) considering it is of the C object type (C, +C, C). 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. +# TODO: Support for passing FILEHANDLE instead of FILENAME +sub hash_object { + my ($self, $type, $file) = _maybe_self(@_); + command_oneline('hash-object', '-t', $type, $file); +} + =back -=head1 TODO +=head1 ERROR HANDLING + +All functions are supposed to throw Perl exceptions in case of errors. +See the L module on how to catch those. Most exceptions are mere +L instances. + +However, the C, C and C +functions suite can throw C exceptions as well: those are +thrown when the external command returns an error code and contain the error +code as well as access to the captured command's output. The exception class +provides the usual C and C (command's exit code) methods and +in addition also a C method that returns either an array or a +string with the captured command output (depending on the original function +call context; C returns C) and $ which +returns the command and its arguments (but without proper quoting). + +Note that the C functions cannot throw this exception since +it has no idea whether the command failed or not. You will only find out +at the time you C the pipe; if you want to have that automated, +use C, which can throw the exception. + +=cut + +{ + package Git::Error::Command; + + @Git::Error::Command::ISA = qw(Error); + + sub new { + my $self = shift; + my $cmdline = '' . shift; + my $value = 0 + shift; + my $outputref = shift; + my(@args) = (); + + local $Error::Depth = $Error::Depth + 1; + + push(@args, '-cmdline', $cmdline); + push(@args, '-value', $value); + push(@args, '-outputref', $outputref); + + $self->SUPER::new(-text => 'command returned error', @args); + } + + sub stringify { + my $self = shift; + my $text = $self->SUPER::stringify; + $self->cmdline() . ': ' . $text . ': ' . $self->value() . "\n"; + } + + sub cmdline { + my $self = shift; + $self->{'-cmdline'}; + } + + sub cmd_output { + my $self = shift; + my $ref = $self->{'-outputref'}; + defined $ref or undef; + if (ref $ref eq 'ARRAY') { + return @$ref; + } else { # SCALAR + return $$ref; + } + } +} + +=over 4 + +=item git_cmd_try { CODE } ERRMSG + +This magical statement will automatically catch any C +exceptions thrown by C and make your program die with C +on its lips; the message will have %s substituted for the command line +and %d for the exit status. This statement is useful mostly for producing +more user-friendly error messages. + +In case of no exception caught the statement returns C's return value. -This is still fairly crude. -We need some good way to report errors back except just dying. +Note that this is the only auto-exported function. + +=cut + +sub git_cmd_try(&$) { + my ($code, $errmsg) = @_; + my @result; + my $err; + my $array = wantarray; + try { + if ($array) { + @result = &$code; + } else { + $result[0] = &$code; + } + } catch Git::Error::Command with { + my $E = shift; + $err = $errmsg; + $err =~ s/\%s/$E->cmdline()/ge; + $err =~ s/\%d/$E->value()/ge; + # We can't croak here since Error.pm would mangle + # that to Error::Simple. + }; + $err and croak $err; + return $array ? @result : $result[0]; +} + + +=back =head1 COPYRIGHT @@ -352,31 +716,79 @@ sub _maybe_self { ref $_[0] eq 'Git' ? @_ : (undef, @_); } +# Check if the command id is something reasonable. +sub _check_valid_cmd { + my ($cmd) = @_; + $cmd =~ /^[a-z0-9A-Z_-]+$/ or throw Error::Simple("bad command: $cmd"); +} + +# Common backend for the pipe creators. +sub _command_common_pipe { + my $direction = shift; + my ($self, @p) = _maybe_self(@_); + my (%opts, $cmd, @args); + if (ref $p[0]) { + ($cmd, @args) = @{shift @p}; + %opts = ref $p[0] ? %{$p[0]} : @p; + } else { + ($cmd, @args) = @p; + } + _check_valid_cmd($cmd); + + my $fh; + if ($^O eq '##INSERT_ACTIVESTATE_STRING_HERE##') { + # ActiveState Perl + #defined $opts{STDERR} and + # warn 'ignoring STDERR option - running w/ ActiveState'; + $direction eq '-|' or + die 'input pipe for ActiveState not implemented'; + tie ($fh, 'Git::activestate_pipe', $cmd, @args); + + } else { + my $pid = open($fh, $direction); + if (not defined $pid) { + throw Error::Simple("open failed: $!"); + } elsif ($pid == 0) { + if (defined $opts{STDERR}) { + close STDERR; + } + if ($opts{STDERR}) { + open (STDERR, '>&', $opts{STDERR}) + or die "dup failed: $!"; + } + _cmd_exec($self, $cmd, @args); + } + } + return wantarray ? ($fh, join(' ', $cmd, @args)) : $fh; +} + # When already in the subprocess, set up the appropriate state # for the given repository and execute the git command. sub _cmd_exec { my ($self, @args) = @_; if ($self) { - $self->{opts}->{Repository} and $ENV{'GIT_DIR'} = $self->{opts}->{Repository}; - $self->{opts}->{WorkingCopy} and chdir($self->{opts}->{WorkingCopy}); + $self->repo_path() and $ENV{'GIT_DIR'} = $self->repo_path(); + $self->wc_path() and chdir($self->wc_path()); + $self->wc_subdir() and chdir($self->wc_subdir()); } - xs__execv_git_cmd(@args); - croak "exec failed: $!"; + _execv_git_cmd(@args); + die "exec failed: $!"; } # Execute the given Git command ($_[0]) with arguments ($_[1..]) # by searching for it at proper places. -# _execv_git_cmd(), implemented in Git.xs. +sub _execv_git_cmd { exec('git', @_); } # Close pipe to a subprocess. sub _cmd_close { - my ($fh) = @_; + my ($fh, $ctx) = @_; if (not close $fh) { if ($!) { # It's just close, no point in fatalities carp "error closing pipe: $!"; } elsif ($? >> 8) { - croak "exit status: ".($? >> 8); + # The caller should pepper this. + throw Git::Error::Command($ctx, $? >> 8); } # else we might e.g. closed a live stream; the command # dying of SIGPIPE would drive us here. @@ -384,38 +796,42 @@ sub _cmd_close { } -# 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(@_); +sub DESTROY { } - 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}); - } +# Pipe implementation for ActiveState Perl. + +package Git::activestate_pipe; +use strict; - &$xsfunc(@args); +sub TIEHANDLE { + my ($class, @params) = @_; + # FIXME: This is probably horrible idea and the thing will explode + # at the moment you give it arguments that require some quoting, + # but I have no ActiveState clue... --pasky + my $cmdline = join " ", @params; + my @data = qx{$cmdline}; + bless { i => 0, data => \@data }, $class; } -sub AUTOLOAD { - my $xsname; - our $AUTOLOAD; - ($xsname = $AUTOLOAD) =~ s/.*:://; - croak "&Git::$xsname not defined" if $xsname =~ /^xs_/; - $xsname = 'xs_'.$xsname; - _call_gate(\&$xsname, @_); +sub READLINE { + my $self = shift; + if ($self->{i} >= scalar @{$self->{data}}) { + return undef; + } + return $self->{'data'}->[ $self->{i}++ ]; } -sub DESTROY { } +sub CLOSE { + my $self = shift; + delete $self->{data}; + delete $self->{i}; +} + +sub EOF { + my $self = shift; + return ($self->{i} >= scalar @{$self->{data}}); +} 1; # Famous last words