package Archive::Ar; ########################################################### # Archive::Ar - Pure perl module to handle ar achives # # Copyright 2003 - Jay Bonci # Licensed under the same terms as perl itself # ########################################################### use strict; use Exporter; use File::Spec; use Time::Local; use vars qw($VERSION @ISA @EXPORT); $VERSION = '1.1'; use constant ARMAG => "!\n"; use constant SARMAG => length(ARMAG); use constant ARFMAG => "`\n"; @ISA=qw(Exporter); @EXPORT=qw/read read_memory list_files add_files add_data write get_content DEBUG/; sub new { my ($class, $filenameorhandle, $debug) = @_; my $this = {}; my $obj = bless $this, $class; $obj->{_verbose} = 0; $obj->_initValues(); if($debug) { $obj->DEBUG(); } if($filenameorhandle){ unless($obj->read($filenameorhandle)){ $obj->_dowarn("new() failed on filename or filehandle read"); return; } } return $obj; } sub read { my ($this, $filenameorhandle) = @_; my $retval; $this->_initValues(); if(ref $filenameorhandle eq "GLOB") { unless($retval = $this->_readFromFilehandle($filenameorhandle)) { $this->_dowarn("Read from filehandle failed"); return; } }else { unless($retval = $this->_readFromFilename($filenameorhandle)) { $this->_dowarn("Read from filename failed"); return; } } unless($this->_parseData()) { $this->_dowarn("read() failed on data structure analysis. Probable bad file"); return; } return $retval; } sub read_memory { my ($this, $data) = @_; $this->_initValues(); unless($data) { $this->_dowarn("read_memory() can't continue because no data was given"); return; } $this->{_filedata} = $data; unless($this->_parseData()) { $this->_dowarn("read_memory() failed on data structure analysis. Probable bad file"); return; } return length($data); } sub list_files { my($this) = @_; return \@{$this->{_files}}; } sub add_files { my($this, $filenameorarray, @otherfiles) = @_; my $filelist; if(ref $filenameorarray eq "ARRAY") { $filelist = $filenameorarray; }else { $filelist = [$filenameorarray]; if(@otherfiles) { push @$filelist, @otherfiles; } } my $filecount = 0; foreach my $filename (@$filelist) { my @props = stat($filename); unless(@props) { $this->_dowarn("Could not stat() filename. add_files() for this file failed"); next; } my ($dev,$ino,$mode,$nlink,$uid,$gid,$rdev,$size,$atime,$mtime,$ctime,$blksize,$blocks) = @props; my $header = { "date" => $mtime, "uid" => $uid, "gid" => $gid, "mode" => $mode, "size" => $size, }; local $/ = undef; unless(open HANDLE, $filename) { $this->_dowarn("Could not open filename. add_files() for this file failed"); next; } $header->{data} = ; close HANDLE; # fix the filename (undef, undef, $filename) = File::Spec->splitpath($filename); $header->{name} = $filename; $this->_addFile($header); $filecount++; } return $filecount; } sub add_data { my($this, $filename, $data, $params) = @_; unless ($filename) { $this->_dowarn("No filename given; add_data() can't proceed"); return; } $params ||= {}; $data ||= ""; (undef, undef, $filename) = File::Spec->splitpath($filename); $params->{name} = $filename; $params->{size} = length($data); $params->{data} = $data; $params->{uid} ||= 0; $params->{gid} ||= 0; $params->{date} ||= timelocal(localtime()); $params->{mode} ||= "100644"; unless($this->_addFile($params)) { $this->_dowarn("add_data failed due to a failure in _addFile"); return; } return $params->{size}; } sub write { my($this, $filename) = @_; my $outstr; $outstr= ARMAG; foreach(@{$this->{_files}}) { my $content = $this->get_content($_); unless($content) { $this->_dowarn("Internal Error. $_ file in _files list but no filedata"); next; } # For whatever reason, the uids and gids get stripped # if they are zero. We'll blank them here to emulate that $content->{uid} ||= ""; $content->{gid} ||= ""; $outstr.= pack("A16A12A6A6A8A10", @$content{qw/name date uid gid mode size/}); $outstr.= ARFMAG; $outstr.= $content->{data}; } return $outstr unless $filename; unless(open HANDLE, ">$filename") { $this->_dowarn("Can't open filename $filename"); return; } print HANDLE $outstr; close HANDLE; return length($outstr); } sub get_content { my ($this, $filename) = @_; unless($filename) { $this->_dowarn("get_content can't continue without a filename"); return; } unless(exists($this->{_filehash}->{$filename})) { $this->_dowarn("get_content failed because there is not a file named $filename"); return; } return $this->{_filehash}->{$filename}; } sub DEBUG { my($this, $verbose) = @_; $verbose = 1 unless(defined($verbose) and int($verbose) == 0); $this->{_verbose} = $verbose; return; } sub _parseData { my($this) = @_; unless($this->{_filedata}) { $this->_dowarn("Cannot parse this archive. It appears to be blank"); return; } my $scratchdata = $this->{_filedata}; unless(substr($scratchdata, 0, SARMAG, "") eq ARMAG) { $this->_dowarn("Bad magic header token. Either this file is not an ar archive, or it is damaged. If you are sure of the file integrity, Archive::Ar may not support this type of ar archive currently. Please report this as a bug"); return ""; } while($scratchdata =~ /\S/) { if($scratchdata =~ s/^(.{58})`\n//m) { my @fields = unpack("A16A12A6A6A8A10", $1); for(0..@fields) { $fields[$_] ||= ""; $fields[$_] =~ s/\s*$//g; } my $headers = {}; @$headers{qw/name date uid gid mode size/} = @fields; $headers->{data} = substr($scratchdata, 0, $headers->{size}, ""); $this->_addFile($headers); }else{ $this->_dowarn("File format appears to be corrupt. The file header is not of the right size, or does not exist at all"); return; } } return scalar($this->{_files}); } sub _readFromFilename { my ($this, $filename) = @_; my $handle; open $handle, $filename or return; return $this->_readFromFilehandle($handle); } sub _readFromFilehandle { my ($this, $filehandle) = @_; return unless $filehandle; #handle has to be open return unless(fileno $filehandle); local $/ = undef; $this->{_filedata} = <$filehandle>; close $filehandle; return length($this->{_filedata}); } sub _addFile { my ($this, $file) = @_; return unless $file; foreach(qw/name date uid gid mode size data/) { unless(exists($file->{$_})) { $this->_dowarn("Can't _addFile because virtual file is missing $_ parameter"); return; } } if(exists($this->{_filehash}->{$file->{name}})) { $this->_dowarn("Can't _addFile because virtual file already exists with that name in the archive"); return; } push @{$this->{_files}}, $file->{name}; $this->{_filehash}->{$file->{name}} = $file; return $file->{name}; } sub _initValues { my ($this) = @_; $this->{_files} = []; $this->{_filehash} = {}; $this->{_filedata} =""; return; } sub _dowarn { my ($this, $warning) = @_; if($this->{_verbose}) { warn "DEBUG: $warning"; } return; } 1; =head1 NAME Archive::Ar - Interface for manipulating ar archives =head1 SYNOPSIS use Archive::Ar; my $ar = new Archive::Ar("./foo.ar"); $ar->add_data("newfile.txt","Some contents", $properties); $ar->add_files("./bar.tar.gz", "bat.pl") $ar->add_files(["./again.gz"]); my $filedata = $ar->get_content("bar.tar.gz"); my @files = $ar->list_files(); $ar->read("foo.deb"); $ar->write("outbound.ar"); $ar->DEBUG(); =head1 DESCRIPTION Archive::Ar is a pure-perl way to handle standard ar archives. This is useful if you have those types of old archives on the system, but it is also useful because .deb packages for the Debian GNU/Linux distribution are ar archives. This is one building block in a future chain of modules to build, manipulate, extrace, and test debian modules with no platform or architecture independance. You may notice that the API to Archive::Ar is similar to Archive::Tar, and this was done intentionally to keep similarity between the Archive::* modules =head2 Class Methods =over 4 =item new() =item new($filename); =item new(*GLOB, $debug); Returns a new Archive::Ar object. Without a filename or glob, it returns an empty object. If passed a filename as a scalar or in a GLOB, it will attempt to populate from either of those sources. If it fails, you will receive undef, instead of an object reference. This also can take a second optional debugging parameter. This acts exactly as if DEBUG() is called on the object before it is returned. If you have a new() that keeps failing, this should help. =item read($filename) =item read(*GLOB); This reads a new file into the object, removing any ar archive already represented in the object. Any calls to DEBUG() are not lost by reading in a new file. Returns the number of bytes read, undef on failure. =item read_memory($data) This read information from the first parameter, and attempts to parse and treat it like an ar archive. Like read(), it will wipe out whatever you have in the object and replace it with the contents of the new archive, even if it fails. Returns the number of bytes read (processed) if successful, undef otherwise. =item list_files() This lists the files contained inside of the archive by filename, as an array. =item add_files("filename1", "filename2") =item add_files(["filename1", "filename2"]) Takes an array or an arrayref of filenames to add to the ar archive, in order. The filenames can be paths to files, in which case the path information is stripped off. Filenames longer than 16 characters are truncated when written to disk in the format, so keep that in mind when adding files. Due to the nature of the ar archive format, add_files() will store the uid, gid, mode, size, and creation date of the file as returned by stat(); add_files() returns the number of files sucessfully added, or undef on failure. =item add_data("filename", $filedata) Takes an filename and a set of data to represent it. Unlike add_files, add_data is a virtual add, and does not require data on disk to be present. The data is a hash that looks like: $filedata = { "data" => $data, "uid" => $uid, #defaults to zero "gid" => $gid, #defaults to zero "date" => $date, #date in epoch seconds. Defaults to now. "mode" => $mode, #defaults to "100644"; } You cannot add_data over another file however. This returns the file length in bytes if it is successful, undef otherwise. =item write() =item write("filename.ar") This method will return the data as an .ar archive, or will write to the filename present if specified. If given a filename, write() will return the length of the file written, in bytes, or undef on failure. If the filename already exists, it will overwrite that file. =item get_content("filename") This returns a hash with the file content in it, including the data that the file would naturally contain. If the file does not exist or no filename is given, this returns undef. On success, a hash is returned with the following keys: name - The file name date - The file date (in epoch seconds) uid - The uid of the file gid - The gid of the file mode - The mode permissions size - The size (in bytes) of the file data - The contained data =item DEBUG() This method turns on debugging. Optionally this can be done by passing in a value as the second parameter to new. While verbosity is enabled, Archive::Ar will toss a warn() if there is a suspicious condition or other problem while proceeding. This should help iron out any problems you have while using the module. =head1 CHANGES =over 4 =item Version 1.1 Documentation cleanups =item Version 1.0 This is the initial public release for CPAN, so everything is new. =head1 TODO A better unit test suite perhaps. I have a private one, but a public one would be nice if there was good file faking module. Fix / investigate stuff in the BUGS section. =head1 BUGS To be honest, I'm not sure of a couple of things. The first is that I know of ar archives made on old AIX systems (pre 4.3?) that have a different header with a different magic string, etc. This module perfectly (hopefully) handles ar archives made with the modern ar command from the binutils distribtuion. If anyone knows of anyway to produce these old-style AIX archives, or would like to produce a few for testing, I would be much grateful. There's no really good reason why this module /shouldn't/ run on Win32 platforms, but admittedly, this might change when we have a file exporting function that supports owner and permission writing. If you read in and write out a file, you get different md5sums, but it's still a valid archive. I'm still investigating this, and consider it a minor bug. =head1 COPYRIGHT Archive::Ar is copyright 2003 Jay Bonci Ejaybonci@cpan.orgE. This program is free software; you can redistribute it and/or modify it under the same terms as Perl itself. =cut