eaiovnaovbqoebvqoeavibavo Zlib.pm000064400000125527147633763450006040 0ustar00 package Compress::Zlib; require 5.006 ; require Exporter; use Carp ; use IO::Handle ; use Scalar::Util qw(dualvar); use IO::Compress::Base::Common 2.061 ; use Compress::Raw::Zlib 2.061 ; use IO::Compress::Gzip 2.061 ; use IO::Uncompress::Gunzip 2.061 ; use strict ; use warnings ; use bytes ; our ($VERSION, $XS_VERSION, @ISA, @EXPORT, @EXPORT_OK, %EXPORT_TAGS); $VERSION = '2.061'; $XS_VERSION = $VERSION; $VERSION = eval $VERSION; @ISA = qw(Exporter); # Items to export into callers namespace by default. Note: do not export # names by default without a very good reason. Use EXPORT_OK instead. # Do not simply export all your public functions/methods/constants. @EXPORT = qw( deflateInit inflateInit compress uncompress gzopen $gzerrno ); push @EXPORT, @Compress::Raw::Zlib::EXPORT ; @EXPORT_OK = qw(memGunzip memGzip zlib_version); %EXPORT_TAGS = ( ALL => \@EXPORT ); BEGIN { *zlib_version = \&Compress::Raw::Zlib::zlib_version; } use constant FLAG_APPEND => 1 ; use constant FLAG_CRC => 2 ; use constant FLAG_ADLER => 4 ; use constant FLAG_CONSUME_INPUT => 8 ; our (@my_z_errmsg); @my_z_errmsg = ( "need dictionary", # Z_NEED_DICT 2 "stream end", # Z_STREAM_END 1 "", # Z_OK 0 "file error", # Z_ERRNO (-1) "stream error", # Z_STREAM_ERROR (-2) "data error", # Z_DATA_ERROR (-3) "insufficient memory", # Z_MEM_ERROR (-4) "buffer error", # Z_BUF_ERROR (-5) "incompatible version",# Z_VERSION_ERROR(-6) ); sub _set_gzerr { my $value = shift ; if ($value == 0) { $Compress::Zlib::gzerrno = 0 ; } elsif ($value == Z_ERRNO() || $value > 2) { $Compress::Zlib::gzerrno = $! ; } else { $Compress::Zlib::gzerrno = dualvar($value+0, $my_z_errmsg[2 - $value]); } return $value ; } sub _set_gzerr_undef { _set_gzerr(@_); return undef; } sub _save_gzerr { my $gz = shift ; my $test_eof = shift ; my $value = $gz->errorNo() || 0 ; my $eof = $gz->eof() ; if ($test_eof) { # gzread uses Z_STREAM_END to denote a successful end $value = Z_STREAM_END() if $gz->eof() && $value == 0 ; } _set_gzerr($value) ; } sub gzopen($$) { my ($file, $mode) = @_ ; my $gz ; my %defOpts = (Level => Z_DEFAULT_COMPRESSION(), Strategy => Z_DEFAULT_STRATEGY(), ); my $writing ; $writing = ! ($mode =~ /r/i) ; $writing = ($mode =~ /[wa]/i) ; $defOpts{Level} = $1 if $mode =~ /(\d)/; $defOpts{Strategy} = Z_FILTERED() if $mode =~ /f/i; $defOpts{Strategy} = Z_HUFFMAN_ONLY() if $mode =~ /h/i; $defOpts{Append} = 1 if $mode =~ /a/i; my $infDef = $writing ? 'deflate' : 'inflate'; my @params = () ; croak "gzopen: file parameter is not a filehandle or filename" unless isaFilehandle $file || isaFilename $file || (ref $file && ref $file eq 'SCALAR'); return undef unless $mode =~ /[rwa]/i ; _set_gzerr(0) ; if ($writing) { $gz = new IO::Compress::Gzip($file, Minimal => 1, AutoClose => 1, %defOpts) or $Compress::Zlib::gzerrno = $IO::Compress::Gzip::GzipError; } else { $gz = new IO::Uncompress::Gunzip($file, Transparent => 1, Append => 0, AutoClose => 1, MultiStream => 1, Strict => 0) or $Compress::Zlib::gzerrno = $IO::Uncompress::Gunzip::GunzipError; } return undef if ! defined $gz ; bless [$gz, $infDef], 'Compress::Zlib::gzFile'; } sub Compress::Zlib::gzFile::gzread { my $self = shift ; return _set_gzerr(Z_STREAM_ERROR()) if $self->[1] ne 'inflate'; my $len = defined $_[1] ? $_[1] : 4096 ; my $gz = $self->[0] ; if ($self->gzeof() || $len == 0) { # Zap the output buffer to match ver 1 behaviour. $_[0] = "" ; _save_gzerr($gz, 1); return 0 ; } my $status = $gz->read($_[0], $len) ; _save_gzerr($gz, 1); return $status ; } sub Compress::Zlib::gzFile::gzreadline { my $self = shift ; my $gz = $self->[0] ; { # Maintain backward compatibility with 1.x behaviour # It didn't support $/, so this can't either. local $/ = "\n" ; $_[0] = $gz->getline() ; } _save_gzerr($gz, 1); return defined $_[0] ? length $_[0] : 0 ; } sub Compress::Zlib::gzFile::gzwrite { my $self = shift ; my $gz = $self->[0] ; return _set_gzerr(Z_STREAM_ERROR()) if $self->[1] ne 'deflate'; $] >= 5.008 and (utf8::downgrade($_[0], 1) or croak "Wide character in gzwrite"); my $status = $gz->write($_[0]) ; _save_gzerr($gz); return $status ; } sub Compress::Zlib::gzFile::gztell { my $self = shift ; my $gz = $self->[0] ; my $status = $gz->tell() ; _save_gzerr($gz); return $status ; } sub Compress::Zlib::gzFile::gzseek { my $self = shift ; my $offset = shift ; my $whence = shift ; my $gz = $self->[0] ; my $status ; eval { $status = $gz->seek($offset, $whence) ; }; if ($@) { my $error = $@; $error =~ s/^.*: /gzseek: /; $error =~ s/ at .* line \d+\s*$//; croak $error; } _save_gzerr($gz); return $status ; } sub Compress::Zlib::gzFile::gzflush { my $self = shift ; my $f = shift ; my $gz = $self->[0] ; my $status = $gz->flush($f) ; my $err = _save_gzerr($gz); return $status ? 0 : $err; } sub Compress::Zlib::gzFile::gzclose { my $self = shift ; my $gz = $self->[0] ; my $status = $gz->close() ; my $err = _save_gzerr($gz); return $status ? 0 : $err; } sub Compress::Zlib::gzFile::gzeof { my $self = shift ; my $gz = $self->[0] ; return 0 if $self->[1] ne 'inflate'; my $status = $gz->eof() ; _save_gzerr($gz); return $status ; } sub Compress::Zlib::gzFile::gzsetparams { my $self = shift ; croak "Usage: Compress::Zlib::gzFile::gzsetparams(file, level, strategy)" unless @_ eq 2 ; my $gz = $self->[0] ; my $level = shift ; my $strategy = shift; return _set_gzerr(Z_STREAM_ERROR()) if $self->[1] ne 'deflate'; my $status = *$gz->{Compress}->deflateParams(-Level => $level, -Strategy => $strategy); _save_gzerr($gz); return $status ; } sub Compress::Zlib::gzFile::gzerror { my $self = shift ; my $gz = $self->[0] ; return $Compress::Zlib::gzerrno ; } sub compress($;$) { my ($x, $output, $err, $in) =('', '', '', '') ; if (ref $_[0] ) { $in = $_[0] ; croak "not a scalar reference" unless ref $in eq 'SCALAR' ; } else { $in = \$_[0] ; } $] >= 5.008 and (utf8::downgrade($$in, 1) or croak "Wide character in compress"); my $level = (@_ == 2 ? $_[1] : Z_DEFAULT_COMPRESSION() ); $x = Compress::Raw::Zlib::_deflateInit(FLAG_APPEND, $level, Z_DEFLATED, MAX_WBITS, MAX_MEM_LEVEL, Z_DEFAULT_STRATEGY, 4096, '') or return undef ; $err = $x->deflate($in, $output) ; return undef unless $err == Z_OK() ; $err = $x->flush($output) ; return undef unless $err == Z_OK() ; return $output ; } sub uncompress($) { my ($output, $in) =('', '') ; if (ref $_[0] ) { $in = $_[0] ; croak "not a scalar reference" unless ref $in eq 'SCALAR' ; } else { $in = \$_[0] ; } $] >= 5.008 and (utf8::downgrade($$in, 1) or croak "Wide character in uncompress"); my ($obj, $status) = Compress::Raw::Zlib::_inflateInit(0, MAX_WBITS, 4096, "") ; $status == Z_OK or return undef; $obj->inflate($in, $output) == Z_STREAM_END or return undef; return $output; } sub deflateInit(@) { my ($got) = ParseParameters(0, { 'bufsize' => [IO::Compress::Base::Common::Parse_unsigned, 4096], 'level' => [IO::Compress::Base::Common::Parse_signed, Z_DEFAULT_COMPRESSION()], 'method' => [IO::Compress::Base::Common::Parse_unsigned, Z_DEFLATED()], 'windowbits' => [IO::Compress::Base::Common::Parse_signed, MAX_WBITS()], 'memlevel' => [IO::Compress::Base::Common::Parse_unsigned, MAX_MEM_LEVEL()], 'strategy' => [IO::Compress::Base::Common::Parse_unsigned, Z_DEFAULT_STRATEGY()], 'dictionary' => [IO::Compress::Base::Common::Parse_any, ""], }, @_ ) ; croak "Compress::Zlib::deflateInit: Bufsize must be >= 1, you specified " . $got->getValue('bufsize') unless $got->getValue('bufsize') >= 1; my $obj ; my $status = 0 ; ($obj, $status) = Compress::Raw::Zlib::_deflateInit(0, $got->getValue('level'), $got->getValue('method'), $got->getValue('windowbits'), $got->getValue('memlevel'), $got->getValue('strategy'), $got->getValue('bufsize'), $got->getValue('dictionary')) ; my $x = ($status == Z_OK() ? bless $obj, "Zlib::OldDeflate" : undef) ; return wantarray ? ($x, $status) : $x ; } sub inflateInit(@) { my ($got) = ParseParameters(0, { 'bufsize' => [IO::Compress::Base::Common::Parse_unsigned, 4096], 'windowbits' => [IO::Compress::Base::Common::Parse_signed, MAX_WBITS()], 'dictionary' => [IO::Compress::Base::Common::Parse_any, ""], }, @_) ; croak "Compress::Zlib::inflateInit: Bufsize must be >= 1, you specified " . $got->getValue('bufsize') unless $got->getValue('bufsize') >= 1; my $status = 0 ; my $obj ; ($obj, $status) = Compress::Raw::Zlib::_inflateInit(FLAG_CONSUME_INPUT, $got->getValue('windowbits'), $got->getValue('bufsize'), $got->getValue('dictionary')) ; my $x = ($status == Z_OK() ? bless $obj, "Zlib::OldInflate" : undef) ; wantarray ? ($x, $status) : $x ; } package Zlib::OldDeflate ; our (@ISA); @ISA = qw(Compress::Raw::Zlib::deflateStream); sub deflate { my $self = shift ; my $output ; my $status = $self->SUPER::deflate($_[0], $output) ; wantarray ? ($output, $status) : $output ; } sub flush { my $self = shift ; my $output ; my $flag = shift || Compress::Zlib::Z_FINISH(); my $status = $self->SUPER::flush($output, $flag) ; wantarray ? ($output, $status) : $output ; } package Zlib::OldInflate ; our (@ISA); @ISA = qw(Compress::Raw::Zlib::inflateStream); sub inflate { my $self = shift ; my $output ; my $status = $self->SUPER::inflate($_[0], $output) ; wantarray ? ($output, $status) : $output ; } package Compress::Zlib ; use IO::Compress::Gzip::Constants 2.061 ; sub memGzip($) { _set_gzerr(0); my $x = Compress::Raw::Zlib::_deflateInit(FLAG_APPEND|FLAG_CRC, Z_BEST_COMPRESSION, Z_DEFLATED, -MAX_WBITS(), MAX_MEM_LEVEL, Z_DEFAULT_STRATEGY, 4096, '') or return undef ; # if the deflation buffer isn't a reference, make it one my $string = (ref $_[0] ? $_[0] : \$_[0]) ; $] >= 5.008 and (utf8::downgrade($$string, 1) or croak "Wide character in memGzip"); my $out; my $status ; $x->deflate($string, $out) == Z_OK or return undef ; $x->flush($out) == Z_OK or return undef ; return IO::Compress::Gzip::Constants::GZIP_MINIMUM_HEADER . $out . pack("V V", $x->crc32(), $x->total_in()); } sub _removeGzipHeader($) { my $string = shift ; return Z_DATA_ERROR() if length($$string) < GZIP_MIN_HEADER_SIZE ; my ($magic1, $magic2, $method, $flags, $time, $xflags, $oscode) = unpack ('CCCCVCC', $$string); return Z_DATA_ERROR() unless $magic1 == GZIP_ID1 and $magic2 == GZIP_ID2 and $method == Z_DEFLATED() and !($flags & GZIP_FLG_RESERVED) ; substr($$string, 0, GZIP_MIN_HEADER_SIZE) = '' ; # skip extra field if ($flags & GZIP_FLG_FEXTRA) { return Z_DATA_ERROR() if length($$string) < GZIP_FEXTRA_HEADER_SIZE ; my ($extra_len) = unpack ('v', $$string); $extra_len += GZIP_FEXTRA_HEADER_SIZE; return Z_DATA_ERROR() if length($$string) < $extra_len ; substr($$string, 0, $extra_len) = ''; } # skip orig name if ($flags & GZIP_FLG_FNAME) { my $name_end = index ($$string, GZIP_NULL_BYTE); return Z_DATA_ERROR() if $name_end == -1 ; substr($$string, 0, $name_end + 1) = ''; } # skip comment if ($flags & GZIP_FLG_FCOMMENT) { my $comment_end = index ($$string, GZIP_NULL_BYTE); return Z_DATA_ERROR() if $comment_end == -1 ; substr($$string, 0, $comment_end + 1) = ''; } # skip header crc if ($flags & GZIP_FLG_FHCRC) { return Z_DATA_ERROR() if length ($$string) < GZIP_FHCRC_SIZE ; substr($$string, 0, GZIP_FHCRC_SIZE) = ''; } return Z_OK(); } sub _ret_gun_error { $Compress::Zlib::gzerrno = $IO::Uncompress::Gunzip::GunzipError; return undef; } sub memGunzip($) { # if the buffer isn't a reference, make it one my $string = (ref $_[0] ? $_[0] : \$_[0]); $] >= 5.008 and (utf8::downgrade($$string, 1) or croak "Wide character in memGunzip"); _set_gzerr(0); my $status = _removeGzipHeader($string) ; $status == Z_OK() or return _set_gzerr_undef($status); my $bufsize = length $$string > 4096 ? length $$string : 4096 ; my $x = Compress::Raw::Zlib::_inflateInit(FLAG_CRC | FLAG_CONSUME_INPUT, -MAX_WBITS(), $bufsize, '') or return _ret_gun_error(); my $output = '' ; $status = $x->inflate($string, $output); if ( $status == Z_OK() ) { _set_gzerr(Z_DATA_ERROR()); return undef; } return _ret_gun_error() if ($status != Z_STREAM_END()); if (length $$string >= 8) { my ($crc, $len) = unpack ("VV", substr($$string, 0, 8)); substr($$string, 0, 8) = ''; return _set_gzerr_undef(Z_DATA_ERROR()) unless $len == length($output) and $crc == Compress::Raw::Zlib::crc32($output); } else { $$string = ''; } return $output; } # Autoload methods go after __END__, and are processed by the autosplit program. 1; __END__ =head1 NAME Compress::Zlib - Interface to zlib compression library =head1 SYNOPSIS use Compress::Zlib ; ($d, $status) = deflateInit( [OPT] ) ; $status = $d->deflate($input, $output) ; $status = $d->flush([$flush_type]) ; $d->deflateParams(OPTS) ; $d->deflateTune(OPTS) ; $d->dict_adler() ; $d->crc32() ; $d->adler32() ; $d->total_in() ; $d->total_out() ; $d->msg() ; $d->get_Strategy(); $d->get_Level(); $d->get_BufSize(); ($i, $status) = inflateInit( [OPT] ) ; $status = $i->inflate($input, $output [, $eof]) ; $status = $i->inflateSync($input) ; $i->dict_adler() ; $d->crc32() ; $d->adler32() ; $i->total_in() ; $i->total_out() ; $i->msg() ; $d->get_BufSize(); $dest = compress($source) ; $dest = uncompress($source) ; $gz = gzopen($filename or filehandle, $mode) ; $bytesread = $gz->gzread($buffer [,$size]) ; $bytesread = $gz->gzreadline($line) ; $byteswritten = $gz->gzwrite($buffer) ; $status = $gz->gzflush($flush) ; $offset = $gz->gztell() ; $status = $gz->gzseek($offset, $whence) ; $status = $gz->gzclose() ; $status = $gz->gzeof() ; $status = $gz->gzsetparams($level, $strategy) ; $errstring = $gz->gzerror() ; $gzerrno $dest = Compress::Zlib::memGzip($buffer) ; $dest = Compress::Zlib::memGunzip($buffer) ; $crc = adler32($buffer [,$crc]) ; $crc = crc32($buffer [,$crc]) ; $crc = adler32_combine($crc1, $crc2, $len2)l $crc = crc32_combine($adler1, $adler2, $len2) my $version = Compress::Raw::Zlib::zlib_version(); =head1 DESCRIPTION The I module provides a Perl interface to the I compression library (see L for details about where to get I). The C module can be split into two general areas of functionality, namely a simple read/write interface to I files and a low-level in-memory compression/decompression interface. Each of these areas will be discussed in the following sections. =head2 Notes for users of Compress::Zlib version 1 The main change in C version 2.x is that it does not now interface directly to the zlib library. Instead it uses the C and C modules for reading/writing gzip files, and the C module for some low-level zlib access. The interface provided by version 2 of this module should be 100% backward compatible with version 1. If you find a difference in the expected behaviour please contact the author (See L). See L With the creation of the C and C modules no new features are planned for C - the new modules do everything that C does and then some. Development on C will be limited to bug fixes only. If you are writing new code, your first port of call should be one of the new C or C modules. =head1 GZIP INTERFACE A number of functions are supplied in I for reading and writing I files that conform to RFC 1952. This module provides an interface to most of them. If you have previously used C 1.x, the following enhancements/changes have been made to the C interface: =over 5 =item 1 If you want to open either STDIN or STDOUT with C, you can now optionally use the special filename "C<->" as a synonym for C<\*STDIN> and C<\*STDOUT>. =item 2 In C version 1.x, C used the zlib library to open the underlying file. This made things especially tricky when a Perl filehandle was passed to C. Behind the scenes the numeric C file descriptor had to be extracted from the Perl filehandle and this passed to the zlib library. Apart from being non-portable to some operating systems, this made it difficult to use C in situations where you wanted to extract/create a gzip data stream that is embedded in a larger file, without having to resort to opening and closing the file multiple times. It also made it impossible to pass a perl filehandle that wasn't associated with a real filesystem file, like, say, an C. In C version 2.x, the C interface has been completely rewritten to use the L for writing gzip files and L for reading gzip files. None of the limitations mentioned above apply. =item 3 Addition of C to provide a restricted C interface. =item 4. Added C. =back A more complete and flexible interface for reading/writing gzip files/buffers is included with the module C. See L and L for more details. =over 5 =item B<$gz = gzopen($filename, $mode)> =item B<$gz = gzopen($filehandle, $mode)> This function opens either the I file C<$filename> for reading or writing or attaches to the opened filehandle, C<$filehandle>. It returns an object on success and C on failure. When writing a gzip file this interface will I create the smallest possible gzip header (exactly 10 bytes). If you want greater control over what gets stored in the gzip header (like the original filename or a comment) use L instead. Similarly if you want to read the contents of the gzip header use L. The second parameter, C<$mode>, is used to specify whether the file is opened for reading or writing and to optionally specify a compression level and compression strategy when writing. The format of the C<$mode> parameter is similar to the mode parameter to the 'C' function C, so "rb" is used to open for reading, "wb" for writing and "ab" for appending (writing at the end of the file). To specify a compression level when writing, append a digit between 0 and 9 to the mode string -- 0 means no compression and 9 means maximum compression. If no compression level is specified Z_DEFAULT_COMPRESSION is used. To specify the compression strategy when writing, append 'f' for filtered data, 'h' for Huffman only compression, or 'R' for run-length encoding. If no strategy is specified Z_DEFAULT_STRATEGY is used. So, for example, "wb9" means open for writing with the maximum compression using the default strategy and "wb4R" means open for writing with compression level 4 and run-length encoding. Refer to the I documentation for the exact format of the C<$mode> parameter. =item B<$bytesread = $gz-Egzread($buffer [, $size]) ;> Reads C<$size> bytes from the compressed file into C<$buffer>. If C<$size> is not specified, it will default to 4096. If the scalar C<$buffer> is not large enough, it will be extended automatically. Returns the number of bytes actually read. On EOF it returns 0 and in the case of an error, -1. =item B<$bytesread = $gz-Egzreadline($line) ;> Reads the next line from the compressed file into C<$line>. Returns the number of bytes actually read. On EOF it returns 0 and in the case of an error, -1. It is legal to intermix calls to C and C. To maintain backward compatibility with version 1.x of this module C ignores the C<$/> variable - it I uses the string C<"\n"> as the line delimiter. If you want to read a gzip file a line at a time and have it respect the C<$/> variable (or C<$INPUT_RECORD_SEPARATOR>, or C<$RS> when C is in use) see L. =item B<$byteswritten = $gz-Egzwrite($buffer) ;> Writes the contents of C<$buffer> to the compressed file. Returns the number of bytes actually written, or 0 on error. =item B<$status = $gz-Egzflush($flush_type) ;> Flushes all pending output into the compressed file. This method takes an optional parameter, C<$flush_type>, that controls how the flushing will be carried out. By default the C<$flush_type> used is C. Other valid values for C<$flush_type> are C, C, C and C. It is strongly recommended that you only set the C parameter if you fully understand the implications of what it does - overuse of C can seriously degrade the level of compression achieved. See the C documentation for details. Returns 0 on success. =item B<$offset = $gz-Egztell() ;> Returns the uncompressed file offset. =item B<$status = $gz-Egzseek($offset, $whence) ;> Provides a sub-set of the C functionality, with the restriction that it is only legal to seek forward in the compressed file. It is a fatal error to attempt to seek backward. When opened for writing, empty parts of the file will have NULL (0x00) bytes written to them. The C<$whence> parameter should be one of SEEK_SET, SEEK_CUR or SEEK_END. Returns 1 on success, 0 on failure. =item B<$gz-Egzclose> Closes the compressed file. Any pending data is flushed to the file before it is closed. Returns 0 on success. =item B<$gz-Egzsetparams($level, $strategy> Change settings for the deflate stream C<$gz>. The list of the valid options is shown below. Options not specified will remain unchanged. Note: This method is only available if you are running zlib 1.0.6 or better. =over 5 =item B<$level> Defines the compression level. Valid values are 0 through 9, C, C, C, and C. =item B<$strategy> Defines the strategy used to tune the compression. The valid values are C, C and C. =back =item B<$gz-Egzerror> Returns the I error message or number for the last operation associated with C<$gz>. The return value will be the I error number when used in a numeric context and the I error message when used in a string context. The I error number constants, shown below, are available for use. Z_OK Z_STREAM_END Z_ERRNO Z_STREAM_ERROR Z_DATA_ERROR Z_MEM_ERROR Z_BUF_ERROR =item B<$gzerrno> The C<$gzerrno> scalar holds the error code associated with the most recent I routine. Note that unlike C, the error is I associated with a particular file. As with C it returns an error number in numeric context and an error message in string context. Unlike C though, the error message will correspond to the I message when the error is associated with I itself, or the UNIX error message when it is not (i.e. I returned C). As there is an overlap between the error numbers used by I and UNIX, C<$gzerrno> should only be used to check for the presence of I error in numeric context. Use C to check for specific I errors. The I example below shows how the variable can be used safely. =back =head2 Examples Here is an example script which uses the interface. It implements a I function. use strict ; use warnings ; use Compress::Zlib ; # use stdin if no files supplied @ARGV = '-' unless @ARGV ; foreach my $file (@ARGV) { my $buffer ; my $gz = gzopen($file, "rb") or die "Cannot open $file: $gzerrno\n" ; print $buffer while $gz->gzread($buffer) > 0 ; die "Error reading from $file: $gzerrno" . ($gzerrno+0) . "\n" if $gzerrno != Z_STREAM_END ; $gz->gzclose() ; } Below is a script which makes use of C. It implements a very simple I like script. use strict ; use warnings ; use Compress::Zlib ; die "Usage: gzgrep pattern [file...]\n" unless @ARGV >= 1; my $pattern = shift ; # use stdin if no files supplied @ARGV = '-' unless @ARGV ; foreach my $file (@ARGV) { my $gz = gzopen($file, "rb") or die "Cannot open $file: $gzerrno\n" ; while ($gz->gzreadline($_) > 0) { print if /$pattern/ ; } die "Error reading from $file: $gzerrno\n" if $gzerrno != Z_STREAM_END ; $gz->gzclose() ; } This script, I, does the opposite of the I script above. It reads from standard input and writes a gzip data stream to standard output. use strict ; use warnings ; use Compress::Zlib ; binmode STDOUT; # gzopen only sets it on the fd my $gz = gzopen(\*STDOUT, "wb") or die "Cannot open stdout: $gzerrno\n" ; while (<>) { $gz->gzwrite($_) or die "error writing: $gzerrno\n" ; } $gz->gzclose ; =head2 Compress::Zlib::memGzip This function is used to create an in-memory gzip file with the minimum possible gzip header (exactly 10 bytes). $dest = Compress::Zlib::memGzip($buffer) or die "Cannot compress: $gzerrno\n"; If successful, it returns the in-memory gzip file. Otherwise it returns C and the C<$gzerrno> variable will store the zlib error code. The C<$buffer> parameter can either be a scalar or a scalar reference. See L for an alternative way to carry out in-memory gzip compression. =head2 Compress::Zlib::memGunzip This function is used to uncompress an in-memory gzip file. $dest = Compress::Zlib::memGunzip($buffer) or die "Cannot uncompress: $gzerrno\n"; If successful, it returns the uncompressed gzip file. Otherwise it returns C and the C<$gzerrno> variable will store the zlib error code. The C<$buffer> parameter can either be a scalar or a scalar reference. The contents of the C<$buffer> parameter are destroyed after calling this function. If C<$buffer> consists of multiple concatenated gzip data streams only the first will be uncompressed. Use C with the C option in the C module if you need to deal with concatenated data streams. See L for an alternative way to carry out in-memory gzip uncompression. =head1 COMPRESS/UNCOMPRESS Two functions are provided to perform in-memory compression/uncompression of RFC 1950 data streams. They are called C and C. =over 5 =item B<$dest = compress($source [, $level] ) ;> Compresses C<$source>. If successful it returns the compressed data. Otherwise it returns I. The source buffer, C<$source>, can either be a scalar or a scalar reference. The C<$level> parameter defines the compression level. Valid values are 0 through 9, C, C, C, and C. If C<$level> is not specified C will be used. =item B<$dest = uncompress($source) ;> Uncompresses C<$source>. If successful it returns the uncompressed data. Otherwise it returns I. The source buffer can either be a scalar or a scalar reference. =back Please note: the two functions defined above are I compatible with the Unix commands of the same name. See L and L included with this distribution for an alternative interface for reading/writing RFC 1950 files/buffers. =head1 Deflate Interface This section defines an interface that allows in-memory compression using the I interface provided by zlib. Here is a definition of the interface available: =head2 B<($d, $status) = deflateInit( [OPT] )> Initialises a deflation stream. It combines the features of the I functions C, C and C. If successful, it will return the initialised deflation stream, C<$d> and C<$status> of C in a list context. In scalar context it returns the deflation stream, C<$d>, only. If not successful, the returned deflation stream (C<$d>) will be I and C<$status> will hold the exact I error code. The function optionally takes a number of named options specified as C<< -Name=>value >> pairs. This allows individual options to be tailored without having to specify them all in the parameter list. For backward compatibility, it is also possible to pass the parameters as a reference to a hash containing the name=>value pairs. The function takes one optional parameter, a reference to a hash. The contents of the hash allow the deflation interface to be tailored. Here is a list of the valid options: =over 5 =item B<-Level> Defines the compression level. Valid values are 0 through 9, C, C, C, and C. The default is Z_DEFAULT_COMPRESSION. =item B<-Method> Defines the compression method. The only valid value at present (and the default) is Z_DEFLATED. =item B<-WindowBits> To create an RFC 1950 data stream, set C to a positive number. To create an RFC 1951 data stream, set C to C<-MAX_WBITS>. For a full definition of the meaning and valid values for C refer to the I documentation for I. Defaults to MAX_WBITS. =item B<-MemLevel> For a definition of the meaning and valid values for C refer to the I documentation for I. Defaults to MAX_MEM_LEVEL. =item B<-Strategy> Defines the strategy used to tune the compression. The valid values are C, C and C. The default is Z_DEFAULT_STRATEGY. =item B<-Dictionary> When a dictionary is specified I will automatically call C directly after calling C. The Adler32 value for the dictionary can be obtained by calling the method C<$d->dict_adler()>. The default is no dictionary. =item B<-Bufsize> Sets the initial size for the deflation buffer. If the buffer has to be reallocated to increase the size, it will grow in increments of C. The default is 4096. =back Here is an example of using the C optional parameter list to override the default buffer size and compression level. All other options will take their default values. deflateInit( -Bufsize => 300, -Level => Z_BEST_SPEED ) ; =head2 B<($out, $status) = $d-Edeflate($buffer)> Deflates the contents of C<$buffer>. The buffer can either be a scalar or a scalar reference. When finished, C<$buffer> will be completely processed (assuming there were no errors). If the deflation was successful it returns the deflated output, C<$out>, and a status value, C<$status>, of C. On error, C<$out> will be I and C<$status> will contain the I error code. In a scalar context C will return C<$out> only. As with the I function in I, it is not necessarily the case that any output will be produced by this method. So don't rely on the fact that C<$out> is empty for an error test. =head2 B<($out, $status) = $d-Eflush()> =head2 B<($out, $status) = $d-Eflush($flush_type)> Typically used to finish the deflation. Any pending output will be returned via C<$out>. C<$status> will have a value C if successful. In a scalar context C will return C<$out> only. Note that flushing can seriously degrade the compression ratio, so it should only be used to terminate a decompression (using C) or when you want to create a I (using C). By default the C used is C. Other valid values for C are C, C, C and C. It is strongly recommended that you only set the C parameter if you fully understand the implications of what it does. See the C documentation for details. =head2 B<$status = $d-EdeflateParams([OPT])> Change settings for the deflate stream C<$d>. The list of the valid options is shown below. Options not specified will remain unchanged. =over 5 =item B<-Level> Defines the compression level. Valid values are 0 through 9, C, C, C, and C. =item B<-Strategy> Defines the strategy used to tune the compression. The valid values are C, C and C. =back =head2 B<$d-Edict_adler()> Returns the adler32 value for the dictionary. =head2 B<$d-Emsg()> Returns the last error message generated by zlib. =head2 B<$d-Etotal_in()> Returns the total number of bytes uncompressed bytes input to deflate. =head2 B<$d-Etotal_out()> Returns the total number of compressed bytes output from deflate. =head2 Example Here is a trivial example of using C. It simply reads standard input, deflates it and writes it to standard output. use strict ; use warnings ; use Compress::Zlib ; binmode STDIN; binmode STDOUT; my $x = deflateInit() or die "Cannot create a deflation stream\n" ; my ($output, $status) ; while (<>) { ($output, $status) = $x->deflate($_) ; $status == Z_OK or die "deflation failed\n" ; print $output ; } ($output, $status) = $x->flush() ; $status == Z_OK or die "deflation failed\n" ; print $output ; =head1 Inflate Interface This section defines the interface available that allows in-memory uncompression using the I interface provided by zlib. Here is a definition of the interface: =head2 B<($i, $status) = inflateInit()> Initialises an inflation stream. In a list context it returns the inflation stream, C<$i>, and the I status code in C<$status>. In a scalar context it returns the inflation stream only. If successful, C<$i> will hold the inflation stream and C<$status> will be C. If not successful, C<$i> will be I and C<$status> will hold the I error code. The function optionally takes a number of named options specified as C<< -Name=>value >> pairs. This allows individual options to be tailored without having to specify them all in the parameter list. For backward compatibility, it is also possible to pass the parameters as a reference to a hash containing the name=>value pairs. The function takes one optional parameter, a reference to a hash. The contents of the hash allow the deflation interface to be tailored. Here is a list of the valid options: =over 5 =item B<-WindowBits> To uncompress an RFC 1950 data stream, set C to a positive number. To uncompress an RFC 1951 data stream, set C to C<-MAX_WBITS>. For a full definition of the meaning and valid values for C refer to the I documentation for I. Defaults to MAX_WBITS. =item B<-Bufsize> Sets the initial size for the inflation buffer. If the buffer has to be reallocated to increase the size, it will grow in increments of C. Default is 4096. =item B<-Dictionary> The default is no dictionary. =back Here is an example of using the C optional parameter to override the default buffer size. inflateInit( -Bufsize => 300 ) ; =head2 B<($out, $status) = $i-Einflate($buffer)> Inflates the complete contents of C<$buffer>. The buffer can either be a scalar or a scalar reference. Returns C if successful and C if the end of the compressed data has been successfully reached. If not successful, C<$out> will be I and C<$status> will hold the I error code. The C<$buffer> parameter is modified by C. On completion it will contain what remains of the input buffer after inflation. This means that C<$buffer> will be an empty string when the return status is C. When the return status is C the C<$buffer> parameter will contains what (if anything) was stored in the input buffer after the deflated data stream. This feature is useful when processing a file format that encapsulates a compressed data stream (e.g. gzip, zip). =head2 B<$status = $i-EinflateSync($buffer)> Scans C<$buffer> until it reaches either a I or the end of the buffer. If a I is found, C is returned and C<$buffer> will be have all data up to the flush point removed. This can then be passed to the C method. Any other return code means that a flush point was not found. If more data is available, C can be called repeatedly with more compressed data until the flush point is found. =head2 B<$i-Edict_adler()> Returns the adler32 value for the dictionary. =head2 B<$i-Emsg()> Returns the last error message generated by zlib. =head2 B<$i-Etotal_in()> Returns the total number of bytes compressed bytes input to inflate. =head2 B<$i-Etotal_out()> Returns the total number of uncompressed bytes output from inflate. =head2 Example Here is an example of using C. use strict ; use warnings ; use Compress::Zlib ; my $x = inflateInit() or die "Cannot create a inflation stream\n" ; my $input = '' ; binmode STDIN; binmode STDOUT; my ($output, $status) ; while (read(STDIN, $input, 4096)) { ($output, $status) = $x->inflate(\$input) ; print $output if $status == Z_OK or $status == Z_STREAM_END ; last if $status != Z_OK ; } die "inflation failed\n" unless $status == Z_STREAM_END ; =head1 CHECKSUM FUNCTIONS Two functions are provided by I to calculate checksums. For the Perl interface, the order of the two parameters in both functions has been reversed. This allows both running checksums and one off calculations to be done. $crc = adler32($buffer [,$crc]) ; $crc = crc32($buffer [,$crc]) ; The buffer parameters can either be a scalar or a scalar reference. If the $crc parameters is C, the crc value will be reset. If you have built this module with zlib 1.2.3 or better, two more CRC-related functions are available. $crc = adler32_combine($crc1, $crc2, $len2)l $crc = crc32_combine($adler1, $adler2, $len2) These functions allow checksums to be merged. =head1 Misc =head2 my $version = Compress::Zlib::zlib_version(); Returns the version of the zlib library. =head1 CONSTANTS All the I constants are automatically imported when you make use of I. =head1 SEE ALSO L, L, L, L, L, L, L, L, L, L, L, L, L, L, L, L, L, L L L, L, L, L For RFC 1950, 1951 and 1952 see F, F and F The I compression library was written by Jean-loup Gailly F and Mark Adler F. The primary site for the I compression library is F. The primary site for gzip is F. =head1 AUTHOR This module was written by Paul Marquess, F. =head1 MODIFICATION HISTORY See the Changes file. =head1 COPYRIGHT AND LICENSE Copyright (c) 1995-2013 Paul Marquess. All rights reserved. This program is free software; you can redistribute it and/or modify it under the same terms as Perl itself. RawDeflate.pm000064400000062427147634556060007153 0ustar00package IO::Compress::RawDeflate ; # create RFC1951 # use strict ; use warnings; use bytes; use IO::Compress::Base 2.061 ; use IO::Compress::Base::Common 2.061 qw(:Status ); use IO::Compress::Adapter::Deflate 2.061 ; require Exporter ; our ($VERSION, @ISA, @EXPORT_OK, %DEFLATE_CONSTANTS, %EXPORT_TAGS, $RawDeflateError); $VERSION = '2.061'; $RawDeflateError = ''; @ISA = qw(Exporter IO::Compress::Base); @EXPORT_OK = qw( $RawDeflateError rawdeflate ) ; push @EXPORT_OK, @IO::Compress::Adapter::Deflate::EXPORT_OK ; %EXPORT_TAGS = %IO::Compress::Adapter::Deflate::DEFLATE_CONSTANTS; { my %seen; foreach (keys %EXPORT_TAGS ) { push @{$EXPORT_TAGS{constants}}, grep { !$seen{$_}++ } @{ $EXPORT_TAGS{$_} } } $EXPORT_TAGS{all} = $EXPORT_TAGS{constants} ; } %DEFLATE_CONSTANTS = %EXPORT_TAGS; #push @{ $EXPORT_TAGS{all} }, @EXPORT_OK ; Exporter::export_ok_tags('all'); sub new { my $class = shift ; my $obj = IO::Compress::Base::Common::createSelfTiedObject($class, \$RawDeflateError); return $obj->_create(undef, @_); } sub rawdeflate { my $obj = IO::Compress::Base::Common::createSelfTiedObject(undef, \$RawDeflateError); return $obj->_def(@_); } sub ckParams { my $self = shift ; my $got = shift; return 1 ; } sub mkComp { my $self = shift ; my $got = shift ; my ($obj, $errstr, $errno) = IO::Compress::Adapter::Deflate::mkCompObject( $got->getValue('crc32'), $got->getValue('adler32'), $got->getValue('level'), $got->getValue('strategy') ); return $self->saveErrorString(undef, $errstr, $errno) if ! defined $obj; return $obj; } sub mkHeader { my $self = shift ; return ''; } sub mkTrailer { my $self = shift ; return ''; } sub mkFinalTrailer { return ''; } #sub newHeader #{ # my $self = shift ; # return ''; #} sub getExtraParams { my $self = shift ; return getZlibParams(); } use IO::Compress::Base::Common 2.061 qw(:Parse); use Compress::Raw::Zlib 2.061 qw(Z_DEFLATED Z_DEFAULT_COMPRESSION Z_DEFAULT_STRATEGY); our %PARAMS = ( #'method' => [IO::Compress::Base::Common::Parse_unsigned, Z_DEFLATED], 'level' => [IO::Compress::Base::Common::Parse_signed, Z_DEFAULT_COMPRESSION], 'strategy' => [IO::Compress::Base::Common::Parse_signed, Z_DEFAULT_STRATEGY], 'crc32' => [IO::Compress::Base::Common::Parse_boolean, 0], 'adler32' => [IO::Compress::Base::Common::Parse_boolean, 0], 'merge' => [IO::Compress::Base::Common::Parse_boolean, 0], ); sub getZlibParams { return %PARAMS; } sub getInverseClass { return ('IO::Uncompress::RawInflate', \$IO::Uncompress::RawInflate::RawInflateError); } sub getFileInfo { my $self = shift ; my $params = shift; my $file = shift ; } use IO::Seekable qw(SEEK_SET); sub createMerge { my $self = shift ; my $outValue = shift ; my $outType = shift ; my ($invClass, $error_ref) = $self->getInverseClass(); eval "require $invClass" or die "aaaahhhh" ; my $inf = $invClass->new( $outValue, Transparent => 0, #Strict => 1, AutoClose => 0, Scan => 1) or return $self->saveErrorString(undef, "Cannot create InflateScan object: $$error_ref" ) ; my $end_offset = 0; $inf->scan() or return $self->saveErrorString(undef, "Error Scanning: $$error_ref", $inf->errorNo) ; $inf->zap($end_offset) or return $self->saveErrorString(undef, "Error Zapping: $$error_ref", $inf->errorNo) ; my $def = *$self->{Compress} = $inf->createDeflate(); *$self->{Header} = *$inf->{Info}{Header}; *$self->{UnCompSize} = *$inf->{UnCompSize}->clone(); *$self->{CompSize} = *$inf->{CompSize}->clone(); # TODO -- fix this #*$self->{CompSize} = new U64(0, *$self->{UnCompSize_32bit}); if ( $outType eq 'buffer') { substr( ${ *$self->{Buffer} }, $end_offset) = '' } elsif ($outType eq 'handle' || $outType eq 'filename') { *$self->{FH} = *$inf->{FH} ; delete *$inf->{FH}; *$self->{FH}->flush() ; *$self->{Handle} = 1 if $outType eq 'handle'; #seek(*$self->{FH}, $end_offset, SEEK_SET) *$self->{FH}->seek($end_offset, SEEK_SET) or return $self->saveErrorString(undef, $!, $!) ; } return $def ; } #### zlib specific methods sub deflateParams { my $self = shift ; my $level = shift ; my $strategy = shift ; my $status = *$self->{Compress}->deflateParams(Level => $level, Strategy => $strategy) ; return $self->saveErrorString(0, *$self->{Compress}{Error}, *$self->{Compress}{ErrorNo}) if $status == STATUS_ERROR; return 1; } 1; __END__ =head1 NAME IO::Compress::RawDeflate - Write RFC 1951 files/buffers =head1 SYNOPSIS use IO::Compress::RawDeflate qw(rawdeflate $RawDeflateError) ; my $status = rawdeflate $input => $output [,OPTS] or die "rawdeflate failed: $RawDeflateError\n"; my $z = new IO::Compress::RawDeflate $output [,OPTS] or die "rawdeflate failed: $RawDeflateError\n"; $z->print($string); $z->printf($format, $string); $z->write($string); $z->syswrite($string [, $length, $offset]); $z->flush(); $z->tell(); $z->eof(); $z->seek($position, $whence); $z->binmode(); $z->fileno(); $z->opened(); $z->autoflush(); $z->input_line_number(); $z->newStream( [OPTS] ); $z->deflateParams(); $z->close() ; $RawDeflateError ; # IO::File mode print $z $string; printf $z $format, $string; tell $z eof $z seek $z, $position, $whence binmode $z fileno $z close $z ; =head1 DESCRIPTION This module provides a Perl interface that allows writing compressed data to files or buffer as defined in RFC 1951. Note that RFC 1951 data is not a good choice of compression format to use in isolation, especially if you want to auto-detect it. For reading RFC 1951 files/buffers, see the companion module L. =head1 Functional Interface A top-level function, C, is provided to carry out "one-shot" compression between buffers and/or files. For finer control over the compression process, see the L section. use IO::Compress::RawDeflate qw(rawdeflate $RawDeflateError) ; rawdeflate $input_filename_or_reference => $output_filename_or_reference [,OPTS] or die "rawdeflate failed: $RawDeflateError\n"; The functional interface needs Perl5.005 or better. =head2 rawdeflate $input_filename_or_reference => $output_filename_or_reference [, OPTS] C expects at least two parameters, C<$input_filename_or_reference> and C<$output_filename_or_reference>. =head3 The C<$input_filename_or_reference> parameter The parameter, C<$input_filename_or_reference>, is used to define the source of the uncompressed data. It can take one of the following forms: =over 5 =item A filename If the <$input_filename_or_reference> parameter is a simple scalar, it is assumed to be a filename. This file will be opened for reading and the input data will be read from it. =item A filehandle If the C<$input_filename_or_reference> parameter is a filehandle, the input data will be read from it. The string '-' can be used as an alias for standard input. =item A scalar reference If C<$input_filename_or_reference> is a scalar reference, the input data will be read from C<$$input_filename_or_reference>. =item An array reference If C<$input_filename_or_reference> is an array reference, each element in the array must be a filename. The input data will be read from each file in turn. The complete array will be walked to ensure that it only contains valid filenames before any data is compressed. =item An Input FileGlob string If C<$input_filename_or_reference> is a string that is delimited by the characters "<" and ">" C will assume that it is an I. The input is the list of files that match the fileglob. See L for more details. =back If the C<$input_filename_or_reference> parameter is any other type, C will be returned. =head3 The C<$output_filename_or_reference> parameter The parameter C<$output_filename_or_reference> is used to control the destination of the compressed data. This parameter can take one of these forms. =over 5 =item A filename If the C<$output_filename_or_reference> parameter is a simple scalar, it is assumed to be a filename. This file will be opened for writing and the compressed data will be written to it. =item A filehandle If the C<$output_filename_or_reference> parameter is a filehandle, the compressed data will be written to it. The string '-' can be used as an alias for standard output. =item A scalar reference If C<$output_filename_or_reference> is a scalar reference, the compressed data will be stored in C<$$output_filename_or_reference>. =item An Array Reference If C<$output_filename_or_reference> is an array reference, the compressed data will be pushed onto the array. =item An Output FileGlob If C<$output_filename_or_reference> is a string that is delimited by the characters "<" and ">" C will assume that it is an I. The output is the list of files that match the fileglob. When C<$output_filename_or_reference> is an fileglob string, C<$input_filename_or_reference> must also be a fileglob string. Anything else is an error. See L for more details. =back If the C<$output_filename_or_reference> parameter is any other type, C will be returned. =head2 Notes When C<$input_filename_or_reference> maps to multiple files/buffers and C<$output_filename_or_reference> is a single file/buffer the input files/buffers will be stored in C<$output_filename_or_reference> as a concatenated series of compressed data streams. =head2 Optional Parameters Unless specified below, the optional parameters for C, C, are the same as those used with the OO interface defined in the L section below. =over 5 =item C<< AutoClose => 0|1 >> This option applies to any input or output data streams to C that are filehandles. If C is specified, and the value is true, it will result in all input and/or output filehandles being closed once C has completed. This parameter defaults to 0. =item C<< BinModeIn => 0|1 >> When reading from a file or filehandle, set C before reading. Defaults to 0. =item C<< Append => 0|1 >> The behaviour of this option is dependent on the type of output data stream. =over 5 =item * A Buffer If C is enabled, all compressed data will be append to the end of the output buffer. Otherwise the output buffer will be cleared before any compressed data is written to it. =item * A Filename If C is enabled, the file will be opened in append mode. Otherwise the contents of the file, if any, will be truncated before any compressed data is written to it. =item * A Filehandle If C is enabled, the filehandle will be positioned to the end of the file via a call to C before any compressed data is written to it. Otherwise the file pointer will not be moved. =back When C is specified, and set to true, it will I all compressed data to the output data stream. So when the output is a filehandle it will carry out a seek to the eof before writing any compressed data. If the output is a filename, it will be opened for appending. If the output is a buffer, all compressed data will be appended to the existing buffer. Conversely when C is not specified, or it is present and is set to false, it will operate as follows. When the output is a filename, it will truncate the contents of the file before writing any compressed data. If the output is a filehandle its position will not be changed. If the output is a buffer, it will be wiped before any compressed data is output. Defaults to 0. =back =head2 Examples To read the contents of the file C and write the compressed data to the file C. use strict ; use warnings ; use IO::Compress::RawDeflate qw(rawdeflate $RawDeflateError) ; my $input = "file1.txt"; rawdeflate $input => "$input.1951" or die "rawdeflate failed: $RawDeflateError\n"; To read from an existing Perl filehandle, C<$input>, and write the compressed data to a buffer, C<$buffer>. use strict ; use warnings ; use IO::Compress::RawDeflate qw(rawdeflate $RawDeflateError) ; use IO::File ; my $input = new IO::File " \$buffer or die "rawdeflate failed: $RawDeflateError\n"; To compress all files in the directory "/my/home" that match "*.txt" and store the compressed data in the same directory use strict ; use warnings ; use IO::Compress::RawDeflate qw(rawdeflate $RawDeflateError) ; rawdeflate '' => '<*.1951>' or die "rawdeflate failed: $RawDeflateError\n"; and if you want to compress each file one at a time, this will do the trick use strict ; use warnings ; use IO::Compress::RawDeflate qw(rawdeflate $RawDeflateError) ; for my $input ( glob "/my/home/*.txt" ) { my $output = "$input.1951" ; rawdeflate $input => $output or die "Error compressing '$input': $RawDeflateError\n"; } =head1 OO Interface =head2 Constructor The format of the constructor for C is shown below my $z = new IO::Compress::RawDeflate $output [,OPTS] or die "IO::Compress::RawDeflate failed: $RawDeflateError\n"; It returns an C object on success and undef on failure. The variable C<$RawDeflateError> will contain an error message on failure. If you are running Perl 5.005 or better the object, C<$z>, returned from IO::Compress::RawDeflate can be used exactly like an L filehandle. This means that all normal output file operations can be carried out with C<$z>. For example, to write to a compressed file/buffer you can use either of these forms $z->print("hello world\n"); print $z "hello world\n"; The mandatory parameter C<$output> is used to control the destination of the compressed data. This parameter can take one of these forms. =over 5 =item A filename If the C<$output> parameter is a simple scalar, it is assumed to be a filename. This file will be opened for writing and the compressed data will be written to it. =item A filehandle If the C<$output> parameter is a filehandle, the compressed data will be written to it. The string '-' can be used as an alias for standard output. =item A scalar reference If C<$output> is a scalar reference, the compressed data will be stored in C<$$output>. =back If the C<$output> parameter is any other type, C::new will return undef. =head2 Constructor Options C is any combination of the following options: =over 5 =item C<< AutoClose => 0|1 >> This option is only valid when the C<$output> parameter is a filehandle. If specified, and the value is true, it will result in the C<$output> being closed once either the C method is called or the C object is destroyed. This parameter defaults to 0. =item C<< Append => 0|1 >> Opens C<$output> in append mode. The behaviour of this option is dependent on the type of C<$output>. =over 5 =item * A Buffer If C<$output> is a buffer and C is enabled, all compressed data will be append to the end of C<$output>. Otherwise C<$output> will be cleared before any data is written to it. =item * A Filename If C<$output> is a filename and C is enabled, the file will be opened in append mode. Otherwise the contents of the file, if any, will be truncated before any compressed data is written to it. =item * A Filehandle If C<$output> is a filehandle, the file pointer will be positioned to the end of the file via a call to C before any compressed data is written to it. Otherwise the file pointer will not be moved. =back This parameter defaults to 0. =item C<< Merge => 0|1 >> This option is used to compress input data and append it to an existing compressed data stream in C<$output>. The end result is a single compressed data stream stored in C<$output>. It is a fatal error to attempt to use this option when C<$output> is not an RFC 1951 data stream. There are a number of other limitations with the C option: =over 5 =item 1 This module needs to have been built with zlib 1.2.1 or better to work. A fatal error will be thrown if C is used with an older version of zlib. =item 2 If C<$output> is a file or a filehandle, it must be seekable. =back This parameter defaults to 0. =item -Level Defines the compression level used by zlib. The value should either be a number between 0 and 9 (0 means no compression and 9 is maximum compression), or one of the symbolic constants defined below. Z_NO_COMPRESSION Z_BEST_SPEED Z_BEST_COMPRESSION Z_DEFAULT_COMPRESSION The default is Z_DEFAULT_COMPRESSION. Note, these constants are not imported by C by default. use IO::Compress::RawDeflate qw(:strategy); use IO::Compress::RawDeflate qw(:constants); use IO::Compress::RawDeflate qw(:all); =item -Strategy Defines the strategy used to tune the compression. Use one of the symbolic constants defined below. Z_FILTERED Z_HUFFMAN_ONLY Z_RLE Z_FIXED Z_DEFAULT_STRATEGY The default is Z_DEFAULT_STRATEGY. =item C<< Strict => 0|1 >> This is a placeholder option. =back =head2 Examples TODO =head1 Methods =head2 print Usage is $z->print($data) print $z $data Compresses and outputs the contents of the C<$data> parameter. This has the same behaviour as the C built-in. Returns true if successful. =head2 printf Usage is $z->printf($format, $data) printf $z $format, $data Compresses and outputs the contents of the C<$data> parameter. Returns true if successful. =head2 syswrite Usage is $z->syswrite $data $z->syswrite $data, $length $z->syswrite $data, $length, $offset Compresses and outputs the contents of the C<$data> parameter. Returns the number of uncompressed bytes written, or C if unsuccessful. =head2 write Usage is $z->write $data $z->write $data, $length $z->write $data, $length, $offset Compresses and outputs the contents of the C<$data> parameter. Returns the number of uncompressed bytes written, or C if unsuccessful. =head2 flush Usage is $z->flush; $z->flush($flush_type); Flushes any pending compressed data to the output file/buffer. This method takes an optional parameter, C<$flush_type>, that controls how the flushing will be carried out. By default the C<$flush_type> used is C. Other valid values for C<$flush_type> are C, C, C and C. It is strongly recommended that you only set the C parameter if you fully understand the implications of what it does - overuse of C can seriously degrade the level of compression achieved. See the C documentation for details. Returns true on success. =head2 tell Usage is $z->tell() tell $z Returns the uncompressed file offset. =head2 eof Usage is $z->eof(); eof($z); Returns true if the C method has been called. =head2 seek $z->seek($position, $whence); seek($z, $position, $whence); Provides a sub-set of the C functionality, with the restriction that it is only legal to seek forward in the output file/buffer. It is a fatal error to attempt to seek backward. Empty parts of the file/buffer will have NULL (0x00) bytes written to them. The C<$whence> parameter takes one the usual values, namely SEEK_SET, SEEK_CUR or SEEK_END. Returns 1 on success, 0 on failure. =head2 binmode Usage is $z->binmode binmode $z ; This is a noop provided for completeness. =head2 opened $z->opened() Returns true if the object currently refers to a opened file/buffer. =head2 autoflush my $prev = $z->autoflush() my $prev = $z->autoflush(EXPR) If the C<$z> object is associated with a file or a filehandle, this method returns the current autoflush setting for the underlying filehandle. If C is present, and is non-zero, it will enable flushing after every write/print operation. If C<$z> is associated with a buffer, this method has no effect and always returns C. B that the special variable C<$|> B be used to set or retrieve the autoflush setting. =head2 input_line_number $z->input_line_number() $z->input_line_number(EXPR) This method always returns C when compressing. =head2 fileno $z->fileno() fileno($z) If the C<$z> object is associated with a file or a filehandle, C will return the underlying file descriptor. Once the C method is called C will return C. If the C<$z> object is associated with a buffer, this method will return C. =head2 close $z->close() ; close $z ; Flushes any pending compressed data and then closes the output file/buffer. For most versions of Perl this method will be automatically invoked if the IO::Compress::RawDeflate object is destroyed (either explicitly or by the variable with the reference to the object going out of scope). The exceptions are Perl versions 5.005 through 5.00504 and 5.8.0. In these cases, the C method will be called automatically, but not until global destruction of all live objects when the program is terminating. Therefore, if you want your scripts to be able to run on all versions of Perl, you should call C explicitly and not rely on automatic closing. Returns true on success, otherwise 0. If the C option has been enabled when the IO::Compress::RawDeflate object was created, and the object is associated with a file, the underlying file will also be closed. =head2 newStream([OPTS]) Usage is $z->newStream( [OPTS] ) Closes the current compressed data stream and starts a new one. OPTS consists of any of the the options that are available when creating the C<$z> object. See the L section for more details. =head2 deflateParams Usage is $z->deflateParams TODO =head1 Importing A number of symbolic constants are required by some methods in C. None are imported by default. =over 5 =item :all Imports C, C<$RawDeflateError> and all symbolic constants that can be used by C. Same as doing this use IO::Compress::RawDeflate qw(rawdeflate $RawDeflateError :constants) ; =item :constants Import all symbolic constants. Same as doing this use IO::Compress::RawDeflate qw(:flush :level :strategy) ; =item :flush These symbolic constants are used by the C method. Z_NO_FLUSH Z_PARTIAL_FLUSH Z_SYNC_FLUSH Z_FULL_FLUSH Z_FINISH Z_BLOCK =item :level These symbolic constants are used by the C option in the constructor. Z_NO_COMPRESSION Z_BEST_SPEED Z_BEST_COMPRESSION Z_DEFAULT_COMPRESSION =item :strategy These symbolic constants are used by the C option in the constructor. Z_FILTERED Z_HUFFMAN_ONLY Z_RLE Z_FIXED Z_DEFAULT_STRATEGY =back =head1 EXAMPLES =head2 Apache::GZip Revisited See L =head2 Working with Net::FTP See L =head1 SEE ALSO L, L, L, L, L, L, L, L, L, L, L, L, L, L, L, L, L, L L L, L, L, L For RFC 1950, 1951 and 1952 see F, F and F The I compression library was written by Jean-loup Gailly F and Mark Adler F. The primary site for the I compression library is F. The primary site for gzip is F. =head1 AUTHOR This module was written by Paul Marquess, F. =head1 MODIFICATION HISTORY See the Changes file. =head1 COPYRIGHT AND LICENSE Copyright (c) 2005-2013 Paul Marquess. All rights reserved. This program is free software; you can redistribute it and/or modify it under the same terms as Perl itself. Gzip/Constants.pm000064400000007477147634556060010026 0ustar00package IO::Compress::Gzip::Constants; use strict ; use warnings; use bytes; require Exporter; our ($VERSION, @ISA, @EXPORT, %GZIP_OS_Names); our ($GZIP_FNAME_INVALID_CHAR_RE, $GZIP_FCOMMENT_INVALID_CHAR_RE); $VERSION = '2.061'; @ISA = qw(Exporter); @EXPORT= qw( GZIP_ID_SIZE GZIP_ID1 GZIP_ID2 GZIP_FLG_DEFAULT GZIP_FLG_FTEXT GZIP_FLG_FHCRC GZIP_FLG_FEXTRA GZIP_FLG_FNAME GZIP_FLG_FCOMMENT GZIP_FLG_RESERVED GZIP_CM_DEFLATED GZIP_MIN_HEADER_SIZE GZIP_TRAILER_SIZE GZIP_MTIME_DEFAULT GZIP_XFL_DEFAULT GZIP_FEXTRA_HEADER_SIZE GZIP_FEXTRA_MAX_SIZE GZIP_FEXTRA_SUBFIELD_HEADER_SIZE GZIP_FEXTRA_SUBFIELD_ID_SIZE GZIP_FEXTRA_SUBFIELD_LEN_SIZE GZIP_FEXTRA_SUBFIELD_MAX_SIZE $GZIP_FNAME_INVALID_CHAR_RE $GZIP_FCOMMENT_INVALID_CHAR_RE GZIP_FHCRC_SIZE GZIP_ISIZE_MAX GZIP_ISIZE_MOD_VALUE GZIP_NULL_BYTE GZIP_OS_DEFAULT %GZIP_OS_Names GZIP_MINIMUM_HEADER ); # Constant names derived from RFC 1952 use constant GZIP_ID_SIZE => 2 ; use constant GZIP_ID1 => 0x1F; use constant GZIP_ID2 => 0x8B; use constant GZIP_MIN_HEADER_SIZE => 10 ;# minimum gzip header size use constant GZIP_TRAILER_SIZE => 8 ; use constant GZIP_FLG_DEFAULT => 0x00 ; use constant GZIP_FLG_FTEXT => 0x01 ; use constant GZIP_FLG_FHCRC => 0x02 ; # called CONTINUATION in gzip use constant GZIP_FLG_FEXTRA => 0x04 ; use constant GZIP_FLG_FNAME => 0x08 ; use constant GZIP_FLG_FCOMMENT => 0x10 ; #use constant GZIP_FLG_ENCRYPTED => 0x20 ; # documented in gzip sources use constant GZIP_FLG_RESERVED => (0x20 | 0x40 | 0x80) ; use constant GZIP_XFL_DEFAULT => 0x00 ; use constant GZIP_MTIME_DEFAULT => 0x00 ; use constant GZIP_FEXTRA_HEADER_SIZE => 2 ; use constant GZIP_FEXTRA_MAX_SIZE => 0xFFFF ; use constant GZIP_FEXTRA_SUBFIELD_ID_SIZE => 2 ; use constant GZIP_FEXTRA_SUBFIELD_LEN_SIZE => 2 ; use constant GZIP_FEXTRA_SUBFIELD_HEADER_SIZE => GZIP_FEXTRA_SUBFIELD_ID_SIZE + GZIP_FEXTRA_SUBFIELD_LEN_SIZE; use constant GZIP_FEXTRA_SUBFIELD_MAX_SIZE => GZIP_FEXTRA_MAX_SIZE - GZIP_FEXTRA_SUBFIELD_HEADER_SIZE ; if (ord('A') == 193) { # EBCDIC $GZIP_FNAME_INVALID_CHAR_RE = '[\x00-\x3f\xff]'; $GZIP_FCOMMENT_INVALID_CHAR_RE = '[\x00-\x0a\x11-\x14\x16-\x3f\xff]'; } else { $GZIP_FNAME_INVALID_CHAR_RE = '[\x00-\x1F\x7F-\x9F]'; $GZIP_FCOMMENT_INVALID_CHAR_RE = '[\x00-\x09\x11-\x1F\x7F-\x9F]'; } use constant GZIP_FHCRC_SIZE => 2 ; # aka CONTINUATION in gzip use constant GZIP_CM_DEFLATED => 8 ; use constant GZIP_NULL_BYTE => "\x00"; use constant GZIP_ISIZE_MAX => 0xFFFFFFFF ; use constant GZIP_ISIZE_MOD_VALUE => GZIP_ISIZE_MAX + 1 ; # OS Names sourced from http://www.gzip.org/format.txt use constant GZIP_OS_DEFAULT=> 0xFF ; %GZIP_OS_Names = ( 0 => 'MS-DOS', 1 => 'Amiga', 2 => 'VMS', 3 => 'Unix', 4 => 'VM/CMS', 5 => 'Atari TOS', 6 => 'HPFS (OS/2, NT)', 7 => 'Macintosh', 8 => 'Z-System', 9 => 'CP/M', 10 => 'TOPS-20', 11 => 'NTFS (NT)', 12 => 'SMS QDOS', 13 => 'Acorn RISCOS', 14 => 'VFAT file system (Win95, NT)', 15 => 'MVS', 16 => 'BeOS', 17 => 'Tandem/NSK', 18 => 'THEOS', GZIP_OS_DEFAULT() => 'Unknown', ) ; use constant GZIP_MINIMUM_HEADER => pack("C4 V C C", GZIP_ID1, GZIP_ID2, GZIP_CM_DEFLATED, GZIP_FLG_DEFAULT, GZIP_MTIME_DEFAULT, GZIP_XFL_DEFAULT, GZIP_OS_DEFAULT) ; 1; Base/Common.pm000064400000055073147634556060007236 0ustar00package IO::Compress::Base::Common; use strict ; use warnings; use bytes; use Carp; use Scalar::Util qw(blessed readonly); use File::GlobMapper; require Exporter; our ($VERSION, @ISA, @EXPORT, %EXPORT_TAGS, $HAS_ENCODE); @ISA = qw(Exporter); $VERSION = '2.061'; @EXPORT = qw( isaFilehandle isaFilename isaScalar whatIsInput whatIsOutput isaFileGlobString cleanFileGlobString oneTarget setBinModeInput setBinModeOutput ckInOutParams createSelfTiedObject isGeMax32 MAX32 WANT_CODE WANT_EXT WANT_UNDEF WANT_HASH STATUS_OK STATUS_ENDSTREAM STATUS_EOF STATUS_ERROR ); %EXPORT_TAGS = ( Status => [qw( STATUS_OK STATUS_ENDSTREAM STATUS_EOF STATUS_ERROR )]); use constant STATUS_OK => 0; use constant STATUS_ENDSTREAM => 1; use constant STATUS_EOF => 2; use constant STATUS_ERROR => -1; use constant MAX16 => 0xFFFF ; use constant MAX32 => 0xFFFFFFFF ; use constant MAX32cmp => 0xFFFFFFFF + 1 - 1; # for 5.6.x on 32-bit need to force an non-IV value sub isGeMax32 { return $_[0] >= MAX32cmp ; } sub hasEncode() { if (! defined $HAS_ENCODE) { eval { require Encode; Encode->import(); }; $HAS_ENCODE = $@ ? 0 : 1 ; } return $HAS_ENCODE; } sub getEncoding($$$) { my $obj = shift; my $class = shift ; my $want_encoding = shift ; $obj->croakError("$class: Encode module needed to use -Encode") if ! hasEncode(); my $encoding = Encode::find_encoding($want_encoding); $obj->croakError("$class: Encoding '$want_encoding' is not available") if ! $encoding; return $encoding; } our ($needBinmode); $needBinmode = ($^O eq 'MSWin32' || ($] >= 5.006 && eval ' ${^UNICODE} || ${^UTF8LOCALE} ')) ? 1 : 1 ; sub setBinModeInput($) { my $handle = shift ; binmode $handle if $needBinmode; } sub setBinModeOutput($) { my $handle = shift ; binmode $handle if $needBinmode; } sub isaFilehandle($) { use utf8; # Pragma needed to keep Perl 5.6.0 happy return (defined $_[0] and (UNIVERSAL::isa($_[0],'GLOB') or UNIVERSAL::isa($_[0],'IO::Handle') or UNIVERSAL::isa(\$_[0],'GLOB')) ) } sub isaScalar { return ( defined($_[0]) and ref($_[0]) eq 'SCALAR' and defined ${ $_[0] } ) ; } sub isaFilename($) { return (defined $_[0] and ! ref $_[0] and UNIVERSAL::isa(\$_[0], 'SCALAR')); } sub isaFileGlobString { return defined $_[0] && $_[0] =~ /^<.*>$/; } sub cleanFileGlobString { my $string = shift ; $string =~ s/^\s*<\s*(.*)\s*>\s*$/$1/; return $string; } use constant WANT_CODE => 1 ; use constant WANT_EXT => 2 ; use constant WANT_UNDEF => 4 ; #use constant WANT_HASH => 8 ; use constant WANT_HASH => 0 ; sub whatIsInput($;$) { my $got = whatIs(@_); if (defined $got && $got eq 'filename' && defined $_[0] && $_[0] eq '-') { #use IO::File; $got = 'handle'; $_[0] = *STDIN; #$_[0] = new IO::File("<-"); } return $got; } sub whatIsOutput($;$) { my $got = whatIs(@_); if (defined $got && $got eq 'filename' && defined $_[0] && $_[0] eq '-') { $got = 'handle'; $_[0] = *STDOUT; #$_[0] = new IO::File(">-"); } return $got; } sub whatIs ($;$) { return 'handle' if isaFilehandle($_[0]); my $wantCode = defined $_[1] && $_[1] & WANT_CODE ; my $extended = defined $_[1] && $_[1] & WANT_EXT ; my $undef = defined $_[1] && $_[1] & WANT_UNDEF ; my $hash = defined $_[1] && $_[1] & WANT_HASH ; return 'undef' if ! defined $_[0] && $undef ; if (ref $_[0]) { return '' if blessed($_[0]); # is an object #return '' if UNIVERSAL::isa($_[0], 'UNIVERSAL'); # is an object return 'buffer' if UNIVERSAL::isa($_[0], 'SCALAR'); return 'array' if UNIVERSAL::isa($_[0], 'ARRAY') && $extended ; return 'hash' if UNIVERSAL::isa($_[0], 'HASH') && $hash ; return 'code' if UNIVERSAL::isa($_[0], 'CODE') && $wantCode ; return ''; } return 'fileglob' if $extended && isaFileGlobString($_[0]); return 'filename'; } sub oneTarget { return $_[0] =~ /^(code|handle|buffer|filename)$/; } sub IO::Compress::Base::Validator::new { my $class = shift ; my $Class = shift ; my $error_ref = shift ; my $reportClass = shift ; my %data = (Class => $Class, Error => $error_ref, reportClass => $reportClass, ) ; my $obj = bless \%data, $class ; local $Carp::CarpLevel = 1; my $inType = $data{inType} = whatIsInput($_[0], WANT_EXT|WANT_HASH); my $outType = $data{outType} = whatIsOutput($_[1], WANT_EXT|WANT_HASH); my $oneInput = $data{oneInput} = oneTarget($inType); my $oneOutput = $data{oneOutput} = oneTarget($outType); if (! $inType) { $obj->croakError("$reportClass: illegal input parameter") ; #return undef ; } # if ($inType eq 'hash') # { # $obj->{Hash} = 1 ; # $obj->{oneInput} = 1 ; # return $obj->validateHash($_[0]); # } if (! $outType) { $obj->croakError("$reportClass: illegal output parameter") ; #return undef ; } if ($inType ne 'fileglob' && $outType eq 'fileglob') { $obj->croakError("Need input fileglob for outout fileglob"); } # if ($inType ne 'fileglob' && $outType eq 'hash' && $inType ne 'filename' ) # { # $obj->croakError("input must ne filename or fileglob when output is a hash"); # } if ($inType eq 'fileglob' && $outType eq 'fileglob') { $data{GlobMap} = 1 ; $data{inType} = $data{outType} = 'filename'; my $mapper = new File::GlobMapper($_[0], $_[1]); if ( ! $mapper ) { return $obj->saveErrorString($File::GlobMapper::Error) ; } $data{Pairs} = $mapper->getFileMap(); return $obj; } $obj->croakError("$reportClass: input and output $inType are identical") if $inType eq $outType && $_[0] eq $_[1] && $_[0] ne '-' ; if ($inType eq 'fileglob') # && $outType ne 'fileglob' { my $glob = cleanFileGlobString($_[0]); my @inputs = glob($glob); if (@inputs == 0) { # TODO -- legal or die? die "globmap matched zero file -- legal or die???" ; } elsif (@inputs == 1) { $obj->validateInputFilenames($inputs[0]) or return undef; $_[0] = $inputs[0] ; $data{inType} = 'filename' ; $data{oneInput} = 1; } else { $obj->validateInputFilenames(@inputs) or return undef; $_[0] = [ @inputs ] ; $data{inType} = 'filenames' ; } } elsif ($inType eq 'filename') { $obj->validateInputFilenames($_[0]) or return undef; } elsif ($inType eq 'array') { $data{inType} = 'filenames' ; $obj->validateInputArray($_[0]) or return undef ; } return $obj->saveErrorString("$reportClass: output buffer is read-only") if $outType eq 'buffer' && readonly(${ $_[1] }); if ($outType eq 'filename' ) { $obj->croakError("$reportClass: output filename is undef or null string") if ! defined $_[1] || $_[1] eq '' ; if (-e $_[1]) { if (-d _ ) { return $obj->saveErrorString("output file '$_[1]' is a directory"); } } } return $obj ; } sub IO::Compress::Base::Validator::saveErrorString { my $self = shift ; ${ $self->{Error} } = shift ; return undef; } sub IO::Compress::Base::Validator::croakError { my $self = shift ; $self->saveErrorString($_[0]); croak $_[0]; } sub IO::Compress::Base::Validator::validateInputFilenames { my $self = shift ; foreach my $filename (@_) { $self->croakError("$self->{reportClass}: input filename is undef or null string") if ! defined $filename || $filename eq '' ; next if $filename eq '-'; if (! -e $filename ) { return $self->saveErrorString("input file '$filename' does not exist"); } if (-d _ ) { return $self->saveErrorString("input file '$filename' is a directory"); } # if (! -r _ ) # { # return $self->saveErrorString("cannot open file '$filename': $!"); # } } return 1 ; } sub IO::Compress::Base::Validator::validateInputArray { my $self = shift ; if ( @{ $_[0] } == 0 ) { return $self->saveErrorString("empty array reference") ; } foreach my $element ( @{ $_[0] } ) { my $inType = whatIsInput($element); if (! $inType) { $self->croakError("unknown input parameter") ; } elsif($inType eq 'filename') { $self->validateInputFilenames($element) or return undef ; } else { $self->croakError("not a filename") ; } } return 1 ; } #sub IO::Compress::Base::Validator::validateHash #{ # my $self = shift ; # my $href = shift ; # # while (my($k, $v) = each %$href) # { # my $ktype = whatIsInput($k); # my $vtype = whatIsOutput($v, WANT_EXT|WANT_UNDEF) ; # # if ($ktype ne 'filename') # { # return $self->saveErrorString("hash key not filename") ; # } # # my %valid = map { $_ => 1 } qw(filename buffer array undef handle) ; # if (! $valid{$vtype}) # { # return $self->saveErrorString("hash value not ok") ; # } # } # # return $self ; #} sub createSelfTiedObject { my $class = shift || (caller)[0] ; my $error_ref = shift ; my $obj = bless Symbol::gensym(), ref($class) || $class; tie *$obj, $obj if $] >= 5.005; *$obj->{Closed} = 1 ; $$error_ref = ''; *$obj->{Error} = $error_ref ; my $errno = 0 ; *$obj->{ErrorNo} = \$errno ; return $obj; } #package Parse::Parameters ; # # #require Exporter; #our ($VERSION, @ISA, @EXPORT); #$VERSION = '2.000_08'; #@ISA = qw(Exporter); $EXPORT_TAGS{Parse} = [qw( ParseParameters Parse_any Parse_unsigned Parse_signed Parse_boolean Parse_string Parse_code Parse_writable_scalar ) ]; push @EXPORT, @{ $EXPORT_TAGS{Parse} } ; use constant Parse_any => 0x01; use constant Parse_unsigned => 0x02; use constant Parse_signed => 0x04; use constant Parse_boolean => 0x08; use constant Parse_string => 0x10; use constant Parse_code => 0x20; #use constant Parse_store_ref => 0x100 ; #use constant Parse_multiple => 0x100 ; use constant Parse_writable => 0x200 ; use constant Parse_writable_scalar => 0x400 | Parse_writable ; use constant OFF_PARSED => 0 ; use constant OFF_TYPE => 1 ; use constant OFF_DEFAULT => 2 ; use constant OFF_FIXED => 3 ; #use constant OFF_FIRST_ONLY => 4 ; #use constant OFF_STICKY => 5 ; use constant IxError => 0; use constant IxGot => 1 ; sub ParseParameters { my $level = shift || 0 ; my $sub = (caller($level + 1))[3] ; local $Carp::CarpLevel = 1 ; return $_[1] if @_ == 2 && defined $_[1] && UNIVERSAL::isa($_[1], "IO::Compress::Base::Parameters"); my $p = new IO::Compress::Base::Parameters() ; $p->parse(@_) or croak "$sub: $p->[IxError]" ; return $p; } use strict; use warnings; use Carp; sub Init { my $default = shift ; my %got ; my $obj = IO::Compress::Base::Parameters::new(); while (my ($key, $v) = each %$default) { croak "need 2 params [@$v]" if @$v != 2 ; my ($type, $value) = @$v ; # my ($first_only, $sticky, $type, $value) = @$v ; my $sticky = 0; my $x ; $obj->_checkType($key, \$value, $type, 0, \$x) or return undef ; $key = lc $key; # if (! $sticky) { # $x = [] # if $type & Parse_multiple; # $got{$key} = [0, $type, $value, $x, $first_only, $sticky] ; $got{$key} = [0, $type, $value, $x] ; # } # # $got{$key}[OFF_PARSED] = 0 ; } return bless \%got, "IO::Compress::Base::Parameters::Defaults" ; } sub IO::Compress::Base::Parameters::new { #my $class = shift ; my $obj; $obj->[IxError] = ''; $obj->[IxGot] = {} ; return bless $obj, 'IO::Compress::Base::Parameters' ; } sub IO::Compress::Base::Parameters::setError { my $self = shift ; my $error = shift ; my $retval = @_ ? shift : undef ; $self->[IxError] = $error ; return $retval; } sub IO::Compress::Base::Parameters::getError { my $self = shift ; return $self->[IxError] ; } sub IO::Compress::Base::Parameters::parse { my $self = shift ; my $default = shift ; my $got = $self->[IxGot] ; my $firstTime = keys %{ $got } == 0 ; my (@Bad) ; my @entered = () ; # Allow the options to be passed as a hash reference or # as the complete hash. if (@_ == 0) { @entered = () ; } elsif (@_ == 1) { my $href = $_[0] ; return $self->setError("Expected even number of parameters, got 1") if ! defined $href or ! ref $href or ref $href ne "HASH" ; foreach my $key (keys %$href) { push @entered, $key ; push @entered, \$href->{$key} ; } } else { my $count = @_; return $self->setError("Expected even number of parameters, got $count") if $count % 2 != 0 ; for my $i (0.. $count / 2 - 1) { push @entered, $_[2 * $i] ; push @entered, \$_[2 * $i + 1] ; } } foreach my $key (keys %$default) { my ($type, $value) = @{ $default->{$key} } ; if ($firstTime) { $got->{$key} = [0, $type, $value, $value] ; } else { $got->{$key}[OFF_PARSED] = 0 ; } } my %parsed = (); for my $i (0.. @entered / 2 - 1) { my $key = $entered[2* $i] ; my $value = $entered[2* $i+1] ; #print "Key [$key] Value [$value]" ; #print defined $$value ? "[$$value]\n" : "[undef]\n"; $key =~ s/^-// ; my $canonkey = lc $key; if ($got->{$canonkey}) { my $type = $got->{$canonkey}[OFF_TYPE] ; my $parsed = $parsed{$canonkey}; ++ $parsed{$canonkey}; return $self->setError("Muliple instances of '$key' found") if $parsed ; my $s ; $self->_checkType($key, $value, $type, 1, \$s) or return undef ; $value = $$value ; $got->{$canonkey} = [1, $type, $value, $s] ; } else { push (@Bad, $key) } } if (@Bad) { my ($bad) = join(", ", @Bad) ; return $self->setError("unknown key value(s) $bad") ; } return 1; } sub IO::Compress::Base::Parameters::_checkType { my $self = shift ; my $key = shift ; my $value = shift ; my $type = shift ; my $validate = shift ; my $output = shift; #local $Carp::CarpLevel = $level ; #print "PARSE $type $key $value $validate $sub\n" ; if ($type & Parse_writable_scalar) { return $self->setError("Parameter '$key' not writable") if readonly $$value ; if (ref $$value) { return $self->setError("Parameter '$key' not a scalar reference") if ref $$value ne 'SCALAR' ; $$output = $$value ; } else { return $self->setError("Parameter '$key' not a scalar") if ref $value ne 'SCALAR' ; $$output = $value ; } return 1; } $value = $$value ; if ($type & Parse_any) { $$output = $value ; return 1; } elsif ($type & Parse_unsigned) { return $self->setError("Parameter '$key' must be an unsigned int, got 'undef'") if ! defined $value ; return $self->setError("Parameter '$key' must be an unsigned int, got '$value'") if $value !~ /^\d+$/; $$output = defined $value ? $value : 0 ; return 1; } elsif ($type & Parse_signed) { return $self->setError("Parameter '$key' must be a signed int, got 'undef'") if ! defined $value ; return $self->setError("Parameter '$key' must be a signed int, got '$value'") if $value !~ /^-?\d+$/; $$output = defined $value ? $value : 0 ; return 1 ; } elsif ($type & Parse_boolean) { return $self->setError("Parameter '$key' must be an int, got '$value'") if defined $value && $value !~ /^\d*$/; $$output = defined $value && $value != 0 ? 1 : 0 ; return 1; } elsif ($type & Parse_string) { $$output = defined $value ? $value : "" ; return 1; } elsif ($type & Parse_code) { return $self->setError("Parameter '$key' must be a code reference, got '$value'") if (! defined $value || ref $value ne 'CODE') ; $$output = defined $value ? $value : "" ; return 1; } $$output = $value ; return 1; } sub IO::Compress::Base::Parameters::parsed { return $_[0]->[IxGot]{$_[1]}[OFF_PARSED] ; } sub IO::Compress::Base::Parameters::getValue { return $_[0]->[IxGot]{$_[1]}[OFF_FIXED] ; } sub IO::Compress::Base::Parameters::setValue { $_[0]->[IxGot]{$_[1]}[OFF_PARSED] = 1; $_[0]->[IxGot]{$_[1]}[OFF_DEFAULT] = $_[2] ; $_[0]->[IxGot]{$_[1]}[OFF_FIXED] = $_[2] ; } sub IO::Compress::Base::Parameters::valueRef { return $_[0]->[IxGot]{$_[1]}[OFF_FIXED] ; } sub IO::Compress::Base::Parameters::valueOrDefault { my $self = shift ; my $name = shift ; my $default = shift ; my $value = $self->[IxGot]{$name}[OFF_DEFAULT] ; return $value if defined $value ; return $default ; } sub IO::Compress::Base::Parameters::wantValue { return defined $_[0]->[IxGot]{$_[1]}[OFF_DEFAULT] ; } sub IO::Compress::Base::Parameters::clone { my $self = shift ; my $obj = [] ; my %got ; my $hash = $self->[IxGot] ; for my $k (keys %{ $hash }) { $got{$k} = [ @{ $hash->{$k} } ]; } $obj->[IxError] = $self->[IxError]; $obj->[IxGot] = \%got ; return bless $obj, 'IO::Compress::Base::Parameters' ; } package U64; use constant MAX32 => 0xFFFFFFFF ; use constant HI_1 => MAX32 + 1 ; use constant LOW => 0 ; use constant HIGH => 1; sub new { return bless [ 0, 0 ], $_[0] if @_ == 1 ; return bless [ $_[1], 0 ], $_[0] if @_ == 2 ; return bless [ $_[2], $_[1] ], $_[0] if @_ == 3 ; } sub newUnpack_V64 { my ($low, $hi) = unpack "V V", $_[0] ; bless [ $low, $hi ], "U64"; } sub newUnpack_V32 { my $string = shift; my $low = unpack "V", $string ; bless [ $low, 0 ], "U64"; } sub reset { $_[0]->[HIGH] = $_[0]->[LOW] = 0; } sub clone { bless [ @{$_[0]} ], ref $_[0] ; } sub getHigh { return $_[0]->[HIGH]; } sub getLow { return $_[0]->[LOW]; } sub get32bit { return $_[0]->[LOW]; } sub get64bit { # Not using << here because the result will still be # a 32-bit value on systems where int size is 32-bits return $_[0]->[HIGH] * HI_1 + $_[0]->[LOW]; } sub add { # my $self = shift; my $value = $_[1]; if (ref $value eq 'U64') { $_[0]->[HIGH] += $value->[HIGH] ; $value = $value->[LOW]; } elsif ($value > MAX32) { $_[0]->[HIGH] += int($value / HI_1) ; $value = $value % HI_1; } my $available = MAX32 - $_[0]->[LOW] ; if ($value > $available) { ++ $_[0]->[HIGH] ; $_[0]->[LOW] = $value - $available - 1; } else { $_[0]->[LOW] += $value ; } } sub add32 { # my $self = shift; my $value = $_[1]; if ($value > MAX32) { $_[0]->[HIGH] += int($value / HI_1) ; $value = $value % HI_1; } my $available = MAX32 - $_[0]->[LOW] ; if ($value > $available) { ++ $_[0]->[HIGH] ; $_[0]->[LOW] = $value - $available - 1; } else { $_[0]->[LOW] += $value ; } } sub subtract { my $self = shift; my $value = shift; if (ref $value eq 'U64') { if ($value->[HIGH]) { die "bad" if $self->[HIGH] == 0 || $value->[HIGH] > $self->[HIGH] ; $self->[HIGH] -= $value->[HIGH] ; } $value = $value->[LOW] ; } if ($value > $self->[LOW]) { -- $self->[HIGH] ; $self->[LOW] = MAX32 - $value + $self->[LOW] + 1 ; } else { $self->[LOW] -= $value; } } sub equal { my $self = shift; my $other = shift; return $self->[LOW] == $other->[LOW] && $self->[HIGH] == $other->[HIGH] ; } sub gt { my $self = shift; my $other = shift; return $self->cmp($other) > 0 ; } sub cmp { my $self = shift; my $other = shift ; if ($self->[LOW] == $other->[LOW]) { return $self->[HIGH] - $other->[HIGH] ; } else { return $self->[LOW] - $other->[LOW] ; } } sub is64bit { return $_[0]->[HIGH] > 0 ; } sub isAlmost64bit { return $_[0]->[HIGH] > 0 || $_[0]->[LOW] == MAX32 ; } sub getPacked_V64 { return pack "V V", @{ $_[0] } ; } sub getPacked_V32 { return pack "V", $_[0]->[LOW] ; } sub pack_V64 { return pack "V V", $_[0], 0; } sub full32 { return $_[0] == MAX32 ; } sub Value_VV64 { my $buffer = shift; my ($lo, $hi) = unpack ("V V" , $buffer); no warnings 'uninitialized'; return $hi * HI_1 + $lo; } package IO::Compress::Base::Common; 1; FAQ.pod000064400000047562147634556060005715 0ustar00 =head1 NAME IO::Compress::FAQ -- Frequently Asked Questions about IO::Compress =head1 DESCRIPTION Common questions answered. =head1 GENERAL =head2 Compatibility with Unix compress/uncompress. Although C has a pair of functions called C and C, they are I related to the Unix programs of the same name. The C module is not compatible with Unix C. If you have the C program available, you can use this to read compressed files open F, "uncompress -c $filename |"; while () { ... Alternatively, if you have the C program available, you can use this to read compressed files open F, "gunzip -c $filename |"; while () { ... and this to write compress files, if you have the C program available open F, "| compress -c $filename "; print F "data"; ... close F ; =head2 Accessing .tar.Z files The C module can optionally use C (via the C module) to access tar files that have been compressed with C. Unfortunately tar files compressed with the Unix C utility cannot be read by C and so cannot be directly accessed by C. If the C or C programs are available, you can use one of these workarounds to read C<.tar.Z> files from C Firstly with C use strict; use warnings; use Archive::Tar; open F, "uncompress -c $filename |"; my $tar = Archive::Tar->new(*F); ... and this with C use strict; use warnings; use Archive::Tar; open F, "gunzip -c $filename |"; my $tar = Archive::Tar->new(*F); ... Similarly, if the C program is available, you can use this to write a C<.tar.Z> file use strict; use warnings; use Archive::Tar; use IO::File; my $fh = new IO::File "| compress -c >$filename"; my $tar = Archive::Tar->new(); ... $tar->write($fh); $fh->close ; =head2 How do I recompress using a different compression? This is easier that you might expect if you realise that all the C objects are derived from C and that all the C modules can read from an C filehandle. So, for example, say you have a file compressed with gzip that you want to recompress with bzip2. Here is all that is needed to carry out the recompression. use IO::Uncompress::Gunzip ':all'; use IO::Compress::Bzip2 ':all'; my $gzipFile = "somefile.gz"; my $bzipFile = "somefile.bz2"; my $gunzip = new IO::Uncompress::Gunzip $gzipFile or die "Cannot gunzip $gzipFile: $GunzipError\n" ; bzip2 $gunzip => $bzipFile or die "Cannot bzip2 to $bzipFile: $Bzip2Error\n" ; Note, there is a limitation of this technique. Some compression file formats store extra information along with the compressed data payload. For example, gzip can optionally store the original filename and Zip stores a lot of information about the original file. If the original compressed file contains any of this extra information, it will not be transferred to the new compressed file usign the technique above. =head1 ZIP =head2 What Compression Types do IO::Compress::Zip & IO::Uncompress::Unzip support? The following compression formats are supported by C and C =over 5 =item * Store (method 0) No compression at all. =item * Deflate (method 8) This is the default compression used when creating a zip file with C. =item * Bzip2 (method 12) Only supported if the C module is installed. =item * Lzma (method 14) Only supported if the C module is installed. =back =head2 Can I Read/Write Zip files larger the 4 Gig? Yes, both the C and C modules support the zip feature called I. That allows them to read/write files/buffers larger than 4Gig. If you are creating a Zip file using the one-shot interface, and any of the input files is greater than 4Gig, a zip64 complaint zip file will be created. zip "really-large-file" => "my.zip"; Similarly with the one-shot interface, if the input is a buffer larger than 4 Gig, a zip64 complaint zip file will be created. zip \$really_large_buffer => "my.zip"; The one-shot interface allows you to force the creation of a zip64 zip file by including the C option. zip $filehandle => "my.zip", Zip64 => 1; If you want to create a zip64 zip file with the OO interface you must specify the C option. my $zip = new IO::Compress::Zip "whatever", Zip64 => 1; When uncompressing with C, it will automatically detect if the zip file is zip64. If you intend to manipulate the Zip64 zip files created with C using an external zip/unzip, make sure that it supports Zip64. In particular, if you are using Info-Zip you need to have zip version 3.x or better to update a Zip64 archive and unzip version 6.x to read a zip64 archive. =head2 Can I write more that 64K entries is a Zip files? Yes. Zip64 allows this. See previous question. =head2 Zip Resources The primary reference for zip files is the "appnote" document available at L An alternatively is the Info-Zip appnote. This is available from L =head1 GZIP =head2 Gzip Resources The primary reference for gzip files is RFC 1952 L The primary site for gzip is F. =head2 Dealing with Concatenated gzip files If the gunzip program encounters a file containing multiple gzip files concatenated together it will automatically uncompress them all. The example below illustrates this behaviour $ echo abc | gzip -c >x.gz $ echo def | gzip -c >>x.gz $ gunzip -c x.gz abc def By default C will I bahave like the gunzip program. It will only uncompress the first gzip data stream in the file, as shown below $ perl -MIO::Uncompress::Gunzip=:all -e 'gunzip "x.gz" => \*STDOUT' abc To force C to uncompress all the gzip data streams, include the C option, as shown below $ perl -MIO::Uncompress::Gunzip=:all -e 'gunzip "x.gz" => \*STDOUT, MultiStream => 1' abc def =head1 ZLIB =head2 Zlib Resources The primary site for the I compression library is F. =head1 Bzip2 =head2 Bzip2 Resources The primary site for bzip2 is F. =head2 Dealing with Concatenated bzip2 files If the bunzip2 program encounters a file containing multiple bzip2 files concatenated together it will automatically uncompress them all. The example below illustrates this behaviour $ echo abc | bzip2 -c >x.bz2 $ echo def | bzip2 -c >>x.bz2 $ bunzip2 -c x.bz2 abc def By default C will I bahave like the bunzip2 program. It will only uncompress the first bunzip2 data stream in the file, as shown below $ perl -MIO::Uncompress::Bunzip2=:all -e 'bunzip2 "x.bz2" => \*STDOUT' abc To force C to uncompress all the bzip2 data streams, include the C option, as shown below $ perl -MIO::Uncompress::Bunzip2=:all -e 'bunzip2 "x.bz2" => \*STDOUT, MultiStream => 1' abc def =head2 Interoperating with Pbzip2 Pbzip2 (L) is a parallel implementation of bzip2. The output from pbzip2 consists of a series of concatenated bzip2 data streams. By default C will only uncompress the first bzip2 data stream in a pbzip2 file. To uncompress the complete pbzip2 file you must include the C option, like this. bunzip2 $input => \$output, MultiStream => 1 or die "bunzip2 failed: $Bunzip2Error\n"; =head1 HTTP & NETWORK =head2 Apache::GZip Revisited Below is a mod_perl Apache compression module, called C, taken from F package Apache::GZip; #File: Apache::GZip.pm use strict vars; use Apache::Constants ':common'; use Compress::Zlib; use IO::File; use constant GZIP_MAGIC => 0x1f8b; use constant OS_MAGIC => 0x03; sub handler { my $r = shift; my ($fh,$gz); my $file = $r->filename; return DECLINED unless $fh=IO::File->new($file); $r->header_out('Content-Encoding'=>'gzip'); $r->send_http_header; return OK if $r->header_only; tie *STDOUT,'Apache::GZip',$r; print($_) while <$fh>; untie *STDOUT; return OK; } sub TIEHANDLE { my($class,$r) = @_; # initialize a deflation stream my $d = deflateInit(-WindowBits=>-MAX_WBITS()) || return undef; # gzip header -- don't ask how I found out $r->print(pack("nccVcc",GZIP_MAGIC,Z_DEFLATED,0,time(),0,OS_MAGIC)); return bless { r => $r, crc => crc32(undef), d => $d, l => 0 },$class; } sub PRINT { my $self = shift; foreach (@_) { # deflate the data my $data = $self->{d}->deflate($_); $self->{r}->print($data); # keep track of its length and crc $self->{l} += length($_); $self->{crc} = crc32($_,$self->{crc}); } } sub DESTROY { my $self = shift; # flush the output buffers my $data = $self->{d}->flush; $self->{r}->print($data); # print the CRC and the total length (uncompressed) $self->{r}->print(pack("LL",@{$self}{qw/crc l/})); } 1; Here's the Apache configuration entry you'll need to make use of it. Once set it will result in everything in the /compressed directory will be compressed automagically. SetHandler perl-script PerlHandler Apache::GZip Although at first sight there seems to be quite a lot going on in C, you could sum up what the code was doing as follows -- read the contents of the file in C<< $r->filename >>, compress it and write the compressed data to standard output. That's all. This code has to jump through a few hoops to achieve this because =over =item 1. The gzip support in C version 1.x can only work with a real filesystem filehandle. The filehandles used by Apache modules are not associated with the filesystem. =item 2. That means all the gzip support has to be done by hand - in this case by creating a tied filehandle to deal with creating the gzip header and trailer. =back C doesn't have that filehandle limitation (this was one of the reasons for writing it in the first place). So if C is used instead of C the whole tied filehandle code can be removed. Here is the rewritten code. package Apache::GZip; use strict vars; use Apache::Constants ':common'; use IO::Compress::Gzip; use IO::File; sub handler { my $r = shift; my ($fh,$gz); my $file = $r->filename; return DECLINED unless $fh=IO::File->new($file); $r->header_out('Content-Encoding'=>'gzip'); $r->send_http_header; return OK if $r->header_only; my $gz = new IO::Compress::Gzip '-', Minimal => 1 or return DECLINED ; print $gz $_ while <$fh>; return OK; } or even more succinctly, like this, using a one-shot gzip package Apache::GZip; use strict vars; use Apache::Constants ':common'; use IO::Compress::Gzip qw(gzip); sub handler { my $r = shift; $r->header_out('Content-Encoding'=>'gzip'); $r->send_http_header; return OK if $r->header_only; gzip $r->filename => '-', Minimal => 1 or return DECLINED ; return OK; } 1; The use of one-shot C above just reads from C<< $r->filename >> and writes the compressed data to standard output. Note the use of the C option in the code above. When using gzip for Content-Encoding you should I use this option. In the example above it will prevent the filename being included in the gzip header and make the size of the gzip data stream a slight bit smaller. =head2 Compressed files and Net::FTP The C module provides two low-level methods called C and C that both return filehandles. These filehandles can used with the C modules to compress or uncompress files read from or written to an FTP Server on the fly, without having to create a temporary file. Firstly, here is code that uses C to uncompressed a file as it is read from the FTP Server. use Net::FTP; use IO::Uncompress::Gunzip qw(:all); my $ftp = new Net::FTP ... my $retr_fh = $ftp->retr($compressed_filename); gunzip $retr_fh => $outFilename, AutoClose => 1 or die "Cannot uncompress '$compressed_file': $GunzipError\n"; and this to compress a file as it is written to the FTP Server use Net::FTP; use IO::Compress::Gzip qw(:all); my $stor_fh = $ftp->stor($filename); gzip "filename" => $stor_fh, AutoClose => 1 or die "Cannot compress '$filename': $GzipError\n"; =head1 MISC =head2 Using C to uncompress data embedded in a larger file/buffer. A fairly common use-case is where compressed data is embedded in a larger file/buffer and you want to read both. As an example consider the structure of a zip file. This is a well-defined file format that mixes both compressed and uncompressed sections of data in a single file. For the purposes of this discussion you can think of a zip file as sequence of compressed data streams, each of which is prefixed by an uncompressed local header. The local header contains information about the compressed data stream, including the name of the compressed file and, in particular, the length of the compressed data stream. To illustrate how to use C here is a script that walks a zip file and prints out how many lines are in each compressed file (if you intend write code to walking through a zip file for real see L ). Also, although this example uses the zlib-based compression, the technique can be used by the other C modules. use strict; use warnings; use IO::File; use IO::Uncompress::RawInflate qw(:all); use constant ZIP_LOCAL_HDR_SIG => 0x04034b50; use constant ZIP_LOCAL_HDR_LENGTH => 30; my $file = $ARGV[0] ; my $fh = new IO::File "<$file" or die "Cannot open '$file': $!\n"; while (1) { my $sig; my $buffer; my $x ; ($x = $fh->read($buffer, ZIP_LOCAL_HDR_LENGTH)) == ZIP_LOCAL_HDR_LENGTH or die "Truncated file: $!\n"; my $signature = unpack ("V", substr($buffer, 0, 4)); last unless $signature == ZIP_LOCAL_HDR_SIG; # Read Local Header my $gpFlag = unpack ("v", substr($buffer, 6, 2)); my $compressedMethod = unpack ("v", substr($buffer, 8, 2)); my $compressedLength = unpack ("V", substr($buffer, 18, 4)); my $uncompressedLength = unpack ("V", substr($buffer, 22, 4)); my $filename_length = unpack ("v", substr($buffer, 26, 2)); my $extra_length = unpack ("v", substr($buffer, 28, 2)); my $filename ; $fh->read($filename, $filename_length) == $filename_length or die "Truncated file\n"; $fh->read($buffer, $extra_length) == $extra_length or die "Truncated file\n"; if ($compressedMethod != 8 && $compressedMethod != 0) { warn "Skipping file '$filename' - not deflated $compressedMethod\n"; $fh->read($buffer, $compressedLength) == $compressedLength or die "Truncated file\n"; next; } if ($compressedMethod == 0 && $gpFlag & 8 == 8) { die "Streamed Stored not supported for '$filename'\n"; } next if $compressedLength == 0; # Done reading the Local Header my $inf = new IO::Uncompress::RawInflate $fh, Transparent => 1, InputLength => $compressedLength or die "Cannot uncompress $file [$filename]: $RawInflateError\n" ; my $line_count = 0; while (<$inf>) { ++ $line_count; } print "$filename: $line_count\n"; } The majority of the code above is concerned with reading the zip local header data. The code that I want to focus on is at the bottom. while (1) { # read local zip header data # get $filename # get $compressedLength my $inf = new IO::Uncompress::RawInflate $fh, Transparent => 1, InputLength => $compressedLength or die "Cannot uncompress $file [$filename]: $RawInflateError\n" ; my $line_count = 0; while (<$inf>) { ++ $line_count; } print "$filename: $line_count\n"; } The call to C creates a new filehandle C<$inf> that can be used to read from the parent filehandle C<$fh>, uncompressing it as it goes. The use of the C option will guarantee that I C<$compressedLength> bytes of compressed data will be read from the C<$fh> filehandle (The only exception is for an error case like a truncated file or a corrupt data stream). This means that once RawInflate is finished C<$fh> will be left at the byte directly after the compressed data stream. Now consider what the code looks like without C while (1) { # read local zip header data # get $filename # get $compressedLength # read all the compressed data into $data read($fh, $data, $compressedLength); my $inf = new IO::Uncompress::RawInflate \$data, Transparent => 1, or die "Cannot uncompress $file [$filename]: $RawInflateError\n" ; my $line_count = 0; while (<$inf>) { ++ $line_count; } print "$filename: $line_count\n"; } The difference here is the addition of the temporary variable C<$data>. This is used to store a copy of the compressed data while it is being uncompressed. If you know that C<$compressedLength> isn't that big then using temporary storage won't be a problem. But if C<$compressedLength> is very large or you are writing an application that other people will use, and so have no idea how big C<$compressedLength> will be, it could be an issue. Using C avoids the use of temporary storage and means the application can cope with large compressed data streams. One final point -- obviously C can only be used whenever you know the length of the compressed data beforehand, like here with a zip file. =head1 SEE ALSO L, L, L, L, L, L, L, L, L, L, L, L, L, L, L, L, L, L, L L L, L, L, L =head1 AUTHOR This module was written by Paul Marquess, F. =head1 MODIFICATION HISTORY See the Changes file. =head1 COPYRIGHT AND LICENSE Copyright (c) 2005-2013 Paul Marquess. All rights reserved. This program is free software; you can redistribute it and/or modify it under the same terms as Perl itself. Adapter/Deflate.pm000064400000006110147634556060010044 0ustar00package IO::Compress::Adapter::Deflate ; use strict; use warnings; use bytes; use IO::Compress::Base::Common 2.061 qw(:Status); use Compress::Raw::Zlib 2.061 qw( !crc32 !adler32 ) ; require Exporter; our ($VERSION, @ISA, @EXPORT_OK, %EXPORT_TAGS, @EXPORT, %DEFLATE_CONSTANTS); $VERSION = '2.061'; @ISA = qw(Exporter); @EXPORT_OK = @Compress::Raw::Zlib::DEFLATE_CONSTANTS; %EXPORT_TAGS = %Compress::Raw::Zlib::DEFLATE_CONSTANTS; @EXPORT = @EXPORT_OK; %DEFLATE_CONSTANTS = %EXPORT_TAGS ; sub mkCompObject { my $crc32 = shift ; my $adler32 = shift ; my $level = shift ; my $strategy = shift ; my ($def, $status) = new Compress::Raw::Zlib::Deflate -AppendOutput => 1, -CRC32 => $crc32, -ADLER32 => $adler32, -Level => $level, -Strategy => $strategy, -WindowBits => - MAX_WBITS; return (undef, "Cannot create Deflate object: $status", $status) if $status != Z_OK; return bless {'Def' => $def, 'Error' => '', } ; } sub compr { my $self = shift ; my $def = $self->{Def}; my $status = $def->deflate($_[0], $_[1]) ; $self->{ErrorNo} = $status; if ($status != Z_OK) { $self->{Error} = "Deflate Error: $status"; return STATUS_ERROR; } return STATUS_OK; } sub flush { my $self = shift ; my $def = $self->{Def}; my $opt = $_[1] || Z_FINISH; my $status = $def->flush($_[0], $opt); $self->{ErrorNo} = $status; if ($status != Z_OK) { $self->{Error} = "Deflate Error: $status"; return STATUS_ERROR; } return STATUS_OK; } sub close { my $self = shift ; my $def = $self->{Def}; $def->flush($_[0], Z_FINISH) if defined $def ; } sub reset { my $self = shift ; my $def = $self->{Def}; my $status = $def->deflateReset() ; $self->{ErrorNo} = $status; if ($status != Z_OK) { $self->{Error} = "Deflate Error: $status"; return STATUS_ERROR; } return STATUS_OK; } sub deflateParams { my $self = shift ; my $def = $self->{Def}; my $status = $def->deflateParams(@_); $self->{ErrorNo} = $status; if ($status != Z_OK) { $self->{Error} = "deflateParams Error: $status"; return STATUS_ERROR; } return STATUS_OK; } #sub total_out #{ # my $self = shift ; # $self->{Def}->total_out(); #} # #sub total_in #{ # my $self = shift ; # $self->{Def}->total_in(); #} sub compressedBytes { my $self = shift ; $self->{Def}->compressedBytes(); } sub uncompressedBytes { my $self = shift ; $self->{Def}->uncompressedBytes(); } sub crc32 { my $self = shift ; $self->{Def}->crc32(); } sub adler32 { my $self = shift ; $self->{Def}->adler32(); } 1; __END__ Adapter/Identity.pm000064400000002636147634556060010302 0ustar00package IO::Compress::Adapter::Identity ; use strict; use warnings; use bytes; use IO::Compress::Base::Common 2.061 qw(:Status); our ($VERSION); $VERSION = '2.061'; sub mkCompObject { my $level = shift ; my $strategy = shift ; return bless { 'CompSize' => 0, 'UnCompSize' => 0, 'Error' => '', 'ErrorNo' => 0, } ; } sub compr { my $self = shift ; if (defined ${ $_[0] } && length ${ $_[0] }) { $self->{CompSize} += length ${ $_[0] } ; $self->{UnCompSize} = $self->{CompSize} ; if ( ref $_[1] ) { ${ $_[1] } .= ${ $_[0] } } else { $_[1] .= ${ $_[0] } } } return STATUS_OK ; } sub flush { my $self = shift ; return STATUS_OK; } sub close { my $self = shift ; return STATUS_OK; } sub reset { my $self = shift ; $self->{CompSize} = 0; $self->{UnCompSize} = 0; return STATUS_OK; } sub deflateParams { my $self = shift ; return STATUS_OK; } #sub total_out #{ # my $self = shift ; # return $self->{UnCompSize} ; #} # #sub total_in #{ # my $self = shift ; # return $self->{UnCompSize} ; #} sub compressedBytes { my $self = shift ; return $self->{UnCompSize} ; } sub uncompressedBytes { my $self = shift ; return $self->{UnCompSize} ; } 1; __END__ Adapter/Bzip2.pm000064400000005044147634556060007473 0ustar00package IO::Compress::Adapter::Bzip2 ; use strict; use warnings; use bytes; use IO::Compress::Base::Common 2.061 qw(:Status); use Compress::Raw::Bzip2 2.061 ; our ($VERSION); $VERSION = '2.061'; sub mkCompObject { my $BlockSize100K = shift ; my $WorkFactor = shift ; my $Verbosity = shift ; $BlockSize100K = 1 if ! defined $BlockSize100K ; $WorkFactor = 0 if ! defined $WorkFactor ; $Verbosity = 0 if ! defined $Verbosity ; my ($def, $status) = new Compress::Raw::Bzip2(1, $BlockSize100K, $WorkFactor, $Verbosity); return (undef, "Could not create Deflate object: $status", $status) if $status != BZ_OK ; return bless {'Def' => $def, 'Error' => '', 'ErrorNo' => 0, } ; } sub compr { my $self = shift ; my $def = $self->{Def}; my $status = $def->bzdeflate($_[0], $_[1]) ; $self->{ErrorNo} = $status; if ($status != BZ_RUN_OK) { $self->{Error} = "Deflate Error: $status"; return STATUS_ERROR; } return STATUS_OK; } sub flush { my $self = shift ; my $def = $self->{Def}; my $status = $def->bzflush($_[0]); $self->{ErrorNo} = $status; if ($status != BZ_RUN_OK) { $self->{Error} = "Deflate Error: $status"; return STATUS_ERROR; } return STATUS_OK; } sub close { my $self = shift ; my $def = $self->{Def}; my $status = $def->bzclose($_[0]); $self->{ErrorNo} = $status; if ($status != BZ_STREAM_END) { $self->{Error} = "Deflate Error: $status"; return STATUS_ERROR; } return STATUS_OK; } sub reset { my $self = shift ; my $outer = $self->{Outer}; my ($def, $status) = new Compress::Raw::Bzip2(); $self->{ErrorNo} = ($status == BZ_OK) ? 0 : $status ; if ($status != BZ_OK) { $self->{Error} = "Cannot create Deflate object: $status"; return STATUS_ERROR; } $self->{Def} = $def; return STATUS_OK; } sub compressedBytes { my $self = shift ; $self->{Def}->compressedBytes(); } sub uncompressedBytes { my $self = shift ; $self->{Def}->uncompressedBytes(); } #sub total_out #{ # my $self = shift ; # 0; #} # #sub total_in #{ # my $self = shift ; # $self->{Def}->total_in(); #} # #sub crc32 #{ # my $self = shift ; # $self->{Def}->crc32(); #} # #sub adler32 #{ # my $self = shift ; # $self->{Def}->adler32(); #} 1; __END__ Zip.pm000064400000161371147634556060005675 0ustar00package IO::Compress::Zip ; use strict ; use warnings; use bytes; use IO::Compress::Base::Common 2.061 qw(:Status ); use IO::Compress::RawDeflate 2.061 (); use IO::Compress::Adapter::Deflate 2.061 ; use IO::Compress::Adapter::Identity 2.061 ; use IO::Compress::Zlib::Extra 2.061 ; use IO::Compress::Zip::Constants 2.061 ; use File::Spec(); use Config; use Compress::Raw::Zlib 2.061 (); BEGIN { eval { require IO::Compress::Adapter::Bzip2 ; import IO::Compress::Adapter::Bzip2 2.061 ; require IO::Compress::Bzip2 ; import IO::Compress::Bzip2 2.061 ; } ; eval { require IO::Compress::Adapter::Lzma ; import IO::Compress::Adapter::Lzma 2.061 ; require IO::Compress::Lzma ; import IO::Compress::Lzma 2.061 ; } ; } require Exporter ; our ($VERSION, @ISA, @EXPORT_OK, %EXPORT_TAGS, %DEFLATE_CONSTANTS, $ZipError); $VERSION = '2.061'; $ZipError = ''; @ISA = qw(Exporter IO::Compress::RawDeflate); @EXPORT_OK = qw( $ZipError zip ) ; %EXPORT_TAGS = %IO::Compress::RawDeflate::DEFLATE_CONSTANTS ; push @{ $EXPORT_TAGS{all} }, @EXPORT_OK ; $EXPORT_TAGS{zip_method} = [qw( ZIP_CM_STORE ZIP_CM_DEFLATE ZIP_CM_BZIP2 ZIP_CM_LZMA)]; push @{ $EXPORT_TAGS{all} }, @{ $EXPORT_TAGS{zip_method} }; Exporter::export_ok_tags('all'); sub new { my $class = shift ; my $obj = IO::Compress::Base::Common::createSelfTiedObject($class, \$ZipError); $obj->_create(undef, @_); } sub zip { my $obj = IO::Compress::Base::Common::createSelfTiedObject(undef, \$ZipError); return $obj->_def(@_); } sub isMethodAvailable { my $method = shift; # Store & Deflate are always available return 1 if $method == ZIP_CM_STORE || $method == ZIP_CM_DEFLATE ; return 1 if $method == ZIP_CM_BZIP2 and defined $IO::Compress::Adapter::Bzip2::VERSION; return 1 if $method == ZIP_CM_LZMA and defined $IO::Compress::Adapter::Lzma::VERSION; return 0; } sub beforePayload { my $self = shift ; if (*$self->{ZipData}{Sparse} ) { my $inc = 1024 * 100 ; my $NULLS = ("\x00" x $inc) ; my $sparse = *$self->{ZipData}{Sparse} ; *$self->{CompSize}->add( $sparse ); *$self->{UnCompSize}->add( $sparse ); *$self->{FH}->seek($sparse, IO::Handle::SEEK_CUR); *$self->{ZipData}{CRC32} = Compress::Raw::Zlib::crc32($NULLS, *$self->{ZipData}{CRC32}) for 1 .. int $sparse / $inc; *$self->{ZipData}{CRC32} = Compress::Raw::Zlib::crc32(substr($NULLS, 0, $sparse % $inc), *$self->{ZipData}{CRC32}) if $sparse % $inc; } } sub mkComp { my $self = shift ; my $got = shift ; my ($obj, $errstr, $errno) ; if (*$self->{ZipData}{Method} == ZIP_CM_STORE) { ($obj, $errstr, $errno) = IO::Compress::Adapter::Identity::mkCompObject( $got->getValue('level'), $got->getValue('strategy') ); *$self->{ZipData}{CRC32} = Compress::Raw::Zlib::crc32(undef); } elsif (*$self->{ZipData}{Method} == ZIP_CM_DEFLATE) { ($obj, $errstr, $errno) = IO::Compress::Adapter::Deflate::mkCompObject( $got->getValue('crc32'), $got->getValue('adler32'), $got->getValue('level'), $got->getValue('strategy') ); } elsif (*$self->{ZipData}{Method} == ZIP_CM_BZIP2) { ($obj, $errstr, $errno) = IO::Compress::Adapter::Bzip2::mkCompObject( $got->getValue('blocksize100k'), $got->getValue('workfactor'), $got->getValue('verbosity') ); *$self->{ZipData}{CRC32} = Compress::Raw::Zlib::crc32(undef); } elsif (*$self->{ZipData}{Method} == ZIP_CM_LZMA) { ($obj, $errstr, $errno) = IO::Compress::Adapter::Lzma::mkRawZipCompObject($got->getValue('preset'), $got->getValue('extreme'), ); *$self->{ZipData}{CRC32} = Compress::Raw::Zlib::crc32(undef); } return $self->saveErrorString(undef, $errstr, $errno) if ! defined $obj; if (! defined *$self->{ZipData}{SizesOffset}) { *$self->{ZipData}{SizesOffset} = 0; *$self->{ZipData}{Offset} = new U64 ; } *$self->{ZipData}{AnyZip64} = 0 if ! defined *$self->{ZipData}{AnyZip64} ; return $obj; } sub reset { my $self = shift ; *$self->{Compress}->reset(); *$self->{ZipData}{CRC32} = Compress::Raw::Zlib::crc32(''); return STATUS_OK; } sub filterUncompressed { my $self = shift ; if (*$self->{ZipData}{Method} == ZIP_CM_DEFLATE) { *$self->{ZipData}{CRC32} = *$self->{Compress}->crc32(); } else { *$self->{ZipData}{CRC32} = Compress::Raw::Zlib::crc32(${$_[0]}, *$self->{ZipData}{CRC32}); } } sub canonicalName { # This sub is derived from Archive::Zip::_asZipDirName # Return the normalized name as used in a zip file (path # separators become slashes, etc.). # Will translate internal slashes in path components (i.e. on Macs) to # underscores. Discards volume names. # When $forceDir is set, returns paths with trailing slashes # # input output # . '.' # ./a a # ./a/b a/b # ./a/b/ a/b # a/b/ a/b # /a/b/ a/b # c:\a\b\c.doc a/b/c.doc # on Windows # "i/o maps:whatever" i_o maps/whatever # on Macs my $name = shift; my $forceDir = shift ; my ( $volume, $directories, $file ) = File::Spec->splitpath( File::Spec->canonpath($name), $forceDir ); my @dirs = map { $_ =~ s{/}{_}g; $_ } File::Spec->splitdir($directories); if ( @dirs > 0 ) { pop (@dirs) if $dirs[-1] eq '' } # remove empty component push @dirs, defined($file) ? $file : '' ; my $normalised_path = join '/', @dirs; # Leading directory separators should not be stored in zip archives. # Example: # C:\a\b\c\ a/b/c # C:\a\b\c.txt a/b/c.txt # /a/b/c/ a/b/c # /a/b/c.txt a/b/c.txt $normalised_path =~ s{^/}{}; # remove leading separator return $normalised_path; } sub mkHeader { my $self = shift; my $param = shift ; *$self->{ZipData}{LocalHdrOffset} = U64::clone(*$self->{ZipData}{Offset}); my $comment = ''; $comment = $param->valueOrDefault('comment') ; my $filename = ''; $filename = $param->valueOrDefault('name') ; $filename = canonicalName($filename) if length $filename && $param->getValue('canonicalname') ; if (defined *$self->{ZipData}{FilterName} ) { local *_ = \$filename ; &{ *$self->{ZipData}{FilterName} }() ; } # if ( $param->getValue('utf8') ) { # require Encode ; # $filename = Encode::encode_utf8($filename) # if length $filename ; # $comment = Encode::encode_utf8($comment) # if length $comment ; # } my $hdr = ''; my $time = _unixToDosTime($param->getValue('time')); my $extra = ''; my $ctlExtra = ''; my $empty = 0; my $osCode = $param->getValue('os_code') ; my $extFileAttr = 0 ; # This code assumes Unix. # TODO - revisit this $extFileAttr = 0100644 << 16 if $osCode == ZIP_OS_CODE_UNIX ; if (*$self->{ZipData}{Zip64}) { $empty = IO::Compress::Base::Common::MAX32; my $x = ''; $x .= pack "V V", 0, 0 ; # uncompressedLength $x .= pack "V V", 0, 0 ; # compressedLength $extra .= IO::Compress::Zlib::Extra::mkSubField(ZIP_EXTRA_ID_ZIP64, $x); } if (! $param->getValue('minimal')) { if ($param->parsed('mtime')) { $extra .= mkExtendedTime($param->getValue('mtime'), $param->getValue('atime'), $param->getValue('ctime')); $ctlExtra .= mkExtendedTime($param->getValue('mtime')); } if ( $osCode == ZIP_OS_CODE_UNIX ) { if ( $param->getValue('want_exunixn') ) { my $ux3 = mkUnixNExtra( @{ $param->getValue('want_exunixn') }); $extra .= $ux3; $ctlExtra .= $ux3; } if ( $param->getValue('exunix2') ) { $extra .= mkUnix2Extra( @{ $param->getValue('exunix2') }); $ctlExtra .= mkUnix2Extra(); } } $extFileAttr = $param->getValue('extattr') if defined $param->getValue('extattr') ; $extra .= $param->getValue('extrafieldlocal') if defined $param->getValue('extrafieldlocal'); $ctlExtra .= $param->getValue('extrafieldcentral') if defined $param->getValue('extrafieldcentral'); } my $method = *$self->{ZipData}{Method} ; my $gpFlag = 0 ; $gpFlag |= ZIP_GP_FLAG_STREAMING_MASK if *$self->{ZipData}{Stream} ; $gpFlag |= ZIP_GP_FLAG_LZMA_EOS_PRESENT if $method == ZIP_CM_LZMA ; # $gpFlag |= ZIP_GP_FLAG_LANGUAGE_ENCODING # if $param->getValue('utf8') && (length($filename) || length($comment)); my $version = $ZIP_CM_MIN_VERSIONS{$method}; $version = ZIP64_MIN_VERSION if ZIP64_MIN_VERSION > $version && *$self->{ZipData}{Zip64}; my $madeBy = ($param->getValue('os_code') << 8) + $version; my $extract = $version; *$self->{ZipData}{Version} = $version; *$self->{ZipData}{MadeBy} = $madeBy; my $ifa = 0; $ifa |= ZIP_IFA_TEXT_MASK if $param->getValue('textflag'); $hdr .= pack "V", ZIP_LOCAL_HDR_SIG ; # signature $hdr .= pack 'v', $extract ; # extract Version & OS $hdr .= pack 'v', $gpFlag ; # general purpose flag (set streaming mode) $hdr .= pack 'v', $method ; # compression method (deflate) $hdr .= pack 'V', $time ; # last mod date/time $hdr .= pack 'V', 0 ; # crc32 - 0 when streaming $hdr .= pack 'V', $empty ; # compressed length - 0 when streaming $hdr .= pack 'V', $empty ; # uncompressed length - 0 when streaming $hdr .= pack 'v', length $filename ; # filename length $hdr .= pack 'v', length $extra ; # extra length $hdr .= $filename ; # Remember the offset for the compressed & uncompressed lengths in the # local header. if (*$self->{ZipData}{Zip64}) { *$self->{ZipData}{SizesOffset} = *$self->{ZipData}{Offset}->get64bit() + length($hdr) + 4 ; } else { *$self->{ZipData}{SizesOffset} = *$self->{ZipData}{Offset}->get64bit() + 18; } $hdr .= $extra ; my $ctl = ''; $ctl .= pack "V", ZIP_CENTRAL_HDR_SIG ; # signature $ctl .= pack 'v', $madeBy ; # version made by $ctl .= pack 'v', $extract ; # extract Version $ctl .= pack 'v', $gpFlag ; # general purpose flag (streaming mode) $ctl .= pack 'v', $method ; # compression method (deflate) $ctl .= pack 'V', $time ; # last mod date/time $ctl .= pack 'V', 0 ; # crc32 $ctl .= pack 'V', $empty ; # compressed length $ctl .= pack 'V', $empty ; # uncompressed length $ctl .= pack 'v', length $filename ; # filename length *$self->{ZipData}{ExtraOffset} = length $ctl; *$self->{ZipData}{ExtraSize} = length $ctlExtra ; $ctl .= pack 'v', length $ctlExtra ; # extra length $ctl .= pack 'v', length $comment ; # file comment length $ctl .= pack 'v', 0 ; # disk number start $ctl .= pack 'v', $ifa ; # internal file attributes $ctl .= pack 'V', $extFileAttr ; # external file attributes # offset to local hdr if (*$self->{ZipData}{LocalHdrOffset}->is64bit() ) { $ctl .= pack 'V', IO::Compress::Base::Common::MAX32 ; } else { $ctl .= *$self->{ZipData}{LocalHdrOffset}->getPacked_V32() ; } $ctl .= $filename ; $ctl .= $ctlExtra ; $ctl .= $comment ; *$self->{ZipData}{Offset}->add32(length $hdr) ; *$self->{ZipData}{CentralHeader} = $ctl; return $hdr; } sub mkTrailer { my $self = shift ; my $crc32 ; if (*$self->{ZipData}{Method} == ZIP_CM_DEFLATE) { $crc32 = pack "V", *$self->{Compress}->crc32(); } else { $crc32 = pack "V", *$self->{ZipData}{CRC32}; } my $ctl = *$self->{ZipData}{CentralHeader} ; my $sizes ; if (! *$self->{ZipData}{Zip64}) { $sizes .= *$self->{CompSize}->getPacked_V32() ; # Compressed size $sizes .= *$self->{UnCompSize}->getPacked_V32() ; # Uncompressed size } else { $sizes .= *$self->{CompSize}->getPacked_V64() ; # Compressed size $sizes .= *$self->{UnCompSize}->getPacked_V64() ; # Uncompressed size } my $data = $crc32 . $sizes ; my $xtrasize = *$self->{UnCompSize}->getPacked_V64() ; # Uncompressed size $xtrasize .= *$self->{CompSize}->getPacked_V64() ; # Compressed size my $hdr = ''; if (*$self->{ZipData}{Stream}) { $hdr = pack "V", ZIP_DATA_HDR_SIG ; # signature $hdr .= $data ; } else { $self->writeAt(*$self->{ZipData}{LocalHdrOffset}->get64bit() + 14, $crc32) or return undef; $self->writeAt(*$self->{ZipData}{SizesOffset}, *$self->{ZipData}{Zip64} ? $xtrasize : $sizes) or return undef; } # Central Header Record/Zip64 extended field substr($ctl, 16, length $crc32) = $crc32 ; my $x = ''; # uncompressed length if (*$self->{UnCompSize}->isAlmost64bit() || *$self->{ZipData}{Zip64} > 1) { $x .= *$self->{UnCompSize}->getPacked_V64() ; } else { substr($ctl, 24, 4) = *$self->{UnCompSize}->getPacked_V32() ; } # compressed length if (*$self->{CompSize}->isAlmost64bit() || *$self->{ZipData}{Zip64} > 1) { $x .= *$self->{CompSize}->getPacked_V64() ; } else { substr($ctl, 20, 4) = *$self->{CompSize}->getPacked_V32() ; } # Local Header offset $x .= *$self->{ZipData}{LocalHdrOffset}->getPacked_V64() if *$self->{ZipData}{LocalHdrOffset}->is64bit() ; # disk no - always zero, so don't need it #$x .= pack "V", 0 ; if (length $x) { my $xtra = IO::Compress::Zlib::Extra::mkSubField(ZIP_EXTRA_ID_ZIP64, $x); $ctl .= $xtra ; substr($ctl, *$self->{ZipData}{ExtraOffset}, 2) = pack 'v', *$self->{ZipData}{ExtraSize} + length $xtra; *$self->{ZipData}{AnyZip64} = 1; } *$self->{ZipData}{Offset}->add32(length($hdr)); *$self->{ZipData}{Offset}->add( *$self->{CompSize} ); push @{ *$self->{ZipData}{CentralDir} }, $ctl ; return $hdr; } sub mkFinalTrailer { my $self = shift ; my $comment = ''; $comment = *$self->{ZipData}{ZipComment} ; my $cd_offset = *$self->{ZipData}{Offset}->get32bit() ; # offset to start central dir my $entries = @{ *$self->{ZipData}{CentralDir} }; *$self->{ZipData}{AnyZip64} = 1 if *$self->{ZipData}{Offset}->is64bit || $entries >= 0xFFFF ; my $cd = join '', @{ *$self->{ZipData}{CentralDir} }; my $cd_len = length $cd ; my $z64e = ''; if ( *$self->{ZipData}{AnyZip64} ) { my $v = *$self->{ZipData}{Version} ; my $mb = *$self->{ZipData}{MadeBy} ; $z64e .= pack 'v', $mb ; # Version made by $z64e .= pack 'v', $v ; # Version to extract $z64e .= pack 'V', 0 ; # number of disk $z64e .= pack 'V', 0 ; # number of disk with central dir $z64e .= U64::pack_V64 $entries ; # entries in central dir on this disk $z64e .= U64::pack_V64 $entries ; # entries in central dir $z64e .= U64::pack_V64 $cd_len ; # size of central dir $z64e .= *$self->{ZipData}{Offset}->getPacked_V64() ; # offset to start central dir $z64e = pack("V", ZIP64_END_CENTRAL_REC_HDR_SIG) # signature . U64::pack_V64(length $z64e) . $z64e ; *$self->{ZipData}{Offset}->add32(length $cd) ; $z64e .= pack "V", ZIP64_END_CENTRAL_LOC_HDR_SIG; # signature $z64e .= pack 'V', 0 ; # number of disk with central dir $z64e .= *$self->{ZipData}{Offset}->getPacked_V64() ; # offset to end zip64 central dir $z64e .= pack 'V', 1 ; # Total number of disks $cd_offset = IO::Compress::Base::Common::MAX32 ; $cd_len = IO::Compress::Base::Common::MAX32 if IO::Compress::Base::Common::isGeMax32 $cd_len ; $entries = 0xFFFF if $entries >= 0xFFFF ; } my $ecd = ''; $ecd .= pack "V", ZIP_END_CENTRAL_HDR_SIG ; # signature $ecd .= pack 'v', 0 ; # number of disk $ecd .= pack 'v', 0 ; # number of disk with central dir $ecd .= pack 'v', $entries ; # entries in central dir on this disk $ecd .= pack 'v', $entries ; # entries in central dir $ecd .= pack 'V', $cd_len ; # size of central dir $ecd .= pack 'V', $cd_offset ; # offset to start central dir $ecd .= pack 'v', length $comment ; # zipfile comment length $ecd .= $comment; return $cd . $z64e . $ecd ; } sub ckParams { my $self = shift ; my $got = shift; $got->setValue('crc32' => 1); if (! $got->parsed('time') ) { # Modification time defaults to now. $got->setValue('time' => time) ; } if ($got->parsed('extime') ) { my $timeRef = $got->getValue('extime'); if ( defined $timeRef) { return $self->saveErrorString(undef, "exTime not a 3-element array ref") if ref $timeRef ne 'ARRAY' || @$timeRef != 3; } $got->setValue("mtime", $timeRef->[1]); $got->setValue("atime", $timeRef->[0]); $got->setValue("ctime", $timeRef->[2]); } # Unix2/3 Extended Attribute for my $name (qw(exunix2 exunixn)) { if ($got->parsed($name) ) { my $idRef = $got->getValue($name); if ( defined $idRef) { return $self->saveErrorString(undef, "$name not a 2-element array ref") if ref $idRef ne 'ARRAY' || @$idRef != 2; } $got->setValue("uid", $idRef->[0]); $got->setValue("gid", $idRef->[1]); $got->setValue("want_$name", $idRef); } } *$self->{ZipData}{AnyZip64} = 1 if $got->getValue('zip64'); *$self->{ZipData}{Zip64} = $got->getValue('zip64'); *$self->{ZipData}{Stream} = $got->getValue('stream'); my $method = $got->getValue('method'); return $self->saveErrorString(undef, "Unknown Method '$method'") if ! defined $ZIP_CM_MIN_VERSIONS{$method}; return $self->saveErrorString(undef, "Bzip2 not available") if $method == ZIP_CM_BZIP2 and ! defined $IO::Compress::Adapter::Bzip2::VERSION; return $self->saveErrorString(undef, "Lzma not available") if $method == ZIP_CM_LZMA and ! defined $IO::Compress::Adapter::Lzma::VERSION; *$self->{ZipData}{Method} = $method; *$self->{ZipData}{ZipComment} = $got->getValue('zipcomment') ; for my $name (qw( extrafieldlocal extrafieldcentral )) { my $data = $got->getValue($name) ; if (defined $data) { my $bad = IO::Compress::Zlib::Extra::parseExtraField($data, 1, 0) ; return $self->saveErrorString(undef, "Error with $name Parameter: $bad") if $bad ; $got->setValue($name, $data) ; } } return undef if defined $IO::Compress::Bzip2::VERSION and ! IO::Compress::Bzip2::ckParams($self, $got); if ($got->parsed('sparse') ) { *$self->{ZipData}{Sparse} = $got->getValue('sparse') ; *$self->{ZipData}{Method} = ZIP_CM_STORE; } if ($got->parsed('filtername')) { my $v = $got->getValue('filtername') ; *$self->{ZipData}{FilterName} = $v if ref $v eq 'CODE' ; } return 1 ; } sub outputPayload { my $self = shift ; return 1 if *$self->{ZipData}{Sparse} ; return $self->output(@_); } #sub newHeader #{ # my $self = shift ; # # return $self->mkHeader(*$self->{Got}); #} our %PARAMS = ( 'stream' => [IO::Compress::Base::Common::Parse_boolean, 1], #'store' => [IO::Compress::Base::Common::Parse_boolean, 0], 'method' => [IO::Compress::Base::Common::Parse_unsigned, ZIP_CM_DEFLATE], # # Zip header fields 'minimal' => [IO::Compress::Base::Common::Parse_boolean, 0], 'zip64' => [IO::Compress::Base::Common::Parse_boolean, 0], 'comment' => [IO::Compress::Base::Common::Parse_any, ''], 'zipcomment'=> [IO::Compress::Base::Common::Parse_any, ''], 'name' => [IO::Compress::Base::Common::Parse_any, ''], 'filtername'=> [IO::Compress::Base::Common::Parse_code, undef], 'canonicalname'=> [IO::Compress::Base::Common::Parse_boolean, 0], # 'utf8' => [IO::Compress::Base::Common::Parse_boolean, 0], 'time' => [IO::Compress::Base::Common::Parse_any, undef], 'extime' => [IO::Compress::Base::Common::Parse_any, undef], 'exunix2' => [IO::Compress::Base::Common::Parse_any, undef], 'exunixn' => [IO::Compress::Base::Common::Parse_any, undef], 'extattr' => [IO::Compress::Base::Common::Parse_any, $Compress::Raw::Zlib::gzip_os_code == 3 ? 0100644 << 16 : 0], 'os_code' => [IO::Compress::Base::Common::Parse_unsigned, $Compress::Raw::Zlib::gzip_os_code], 'textflag' => [IO::Compress::Base::Common::Parse_boolean, 0], 'extrafieldlocal' => [IO::Compress::Base::Common::Parse_any, undef], 'extrafieldcentral'=> [IO::Compress::Base::Common::Parse_any, undef], # Lzma 'preset' => [IO::Compress::Base::Common::Parse_unsigned, 6], 'extreme' => [IO::Compress::Base::Common::Parse_boolean, 0], # For internal use only 'sparse' => [IO::Compress::Base::Common::Parse_unsigned, 0], IO::Compress::RawDeflate::getZlibParams(), defined $IO::Compress::Bzip2::VERSION ? IO::Compress::Bzip2::getExtraParams() : () ); sub getExtraParams { return %PARAMS ; } sub getInverseClass { return ('IO::Uncompress::Unzip', \$IO::Uncompress::Unzip::UnzipError); } sub getFileInfo { my $self = shift ; my $params = shift; my $filename = shift ; if (IO::Compress::Base::Common::isaScalar($filename)) { $params->setValue(zip64 => 1) if IO::Compress::Base::Common::isGeMax32 length (${ $filename }) ; return ; } my ($mode, $uid, $gid, $size, $atime, $mtime, $ctime) ; if ( $params->parsed('storelinks') ) { ($mode, $uid, $gid, $size, $atime, $mtime, $ctime) = (lstat($filename))[2, 4,5,7, 8,9,10] ; } else { ($mode, $uid, $gid, $size, $atime, $mtime, $ctime) = (stat($filename))[2, 4,5,7, 8,9,10] ; } $params->setValue(textflag => -T $filename ) if ! $params->parsed('textflag'); $params->setValue(zip64 => 1) if IO::Compress::Base::Common::isGeMax32 $size ; $params->setValue('name' => $filename) if ! $params->parsed('name') ; $params->setValue('time' => $mtime) if ! $params->parsed('time') ; if ( ! $params->parsed('extime')) { $params->setValue('mtime' => $mtime) ; $params->setValue('atime' => $atime) ; $params->setValue('ctime' => undef) ; # No Creation time # TODO - see if can fillout creation time on non-Unix } # NOTE - Unix specific code alert if (! $params->parsed('extattr')) { use Fcntl qw(:mode) ; my $attr = $mode << 16; $attr |= ZIP_A_RONLY if ($mode & S_IWRITE) == 0 ; $attr |= ZIP_A_DIR if ($mode & S_IFMT ) == S_IFDIR ; $params->setValue('extattr' => $attr); } $params->setValue('want_exunixn', [$uid, $gid]); $params->setValue('uid' => $uid) ; $params->setValue('gid' => $gid) ; } sub mkExtendedTime { # order expected is m, a, c my $times = ''; my $bit = 1 ; my $flags = 0; for my $time (@_) { if (defined $time) { $flags |= $bit; $times .= pack("V", $time); } $bit <<= 1 ; } return IO::Compress::Zlib::Extra::mkSubField(ZIP_EXTRA_ID_EXT_TIMESTAMP, pack("C", $flags) . $times); } sub mkUnix2Extra { my $ids = ''; for my $id (@_) { $ids .= pack("v", $id); } return IO::Compress::Zlib::Extra::mkSubField(ZIP_EXTRA_ID_INFO_ZIP_UNIX2, $ids); } sub mkUnixNExtra { my $uid = shift; my $gid = shift; # Assumes UID/GID are 32-bit my $ids ; $ids .= pack "C", 1; # version $ids .= pack "C", $Config{uidsize}; $ids .= pack "V", $uid; $ids .= pack "C", $Config{gidsize}; $ids .= pack "V", $gid; return IO::Compress::Zlib::Extra::mkSubField(ZIP_EXTRA_ID_INFO_ZIP_UNIXN, $ids); } # from Archive::Zip sub _unixToDosTime # Archive::Zip::Member { my $time_t = shift; # TODO - add something to cope with unix time < 1980 my ( $sec, $min, $hour, $mday, $mon, $year ) = localtime($time_t); my $dt = 0; $dt += ( $sec >> 1 ); $dt += ( $min << 5 ); $dt += ( $hour << 11 ); $dt += ( $mday << 16 ); $dt += ( ( $mon + 1 ) << 21 ); $dt += ( ( $year - 80 ) << 25 ); return $dt; } 1; __END__ =head1 NAME IO::Compress::Zip - Write zip files/buffers =head1 SYNOPSIS use IO::Compress::Zip qw(zip $ZipError) ; my $status = zip $input => $output [,OPTS] or die "zip failed: $ZipError\n"; my $z = new IO::Compress::Zip $output [,OPTS] or die "zip failed: $ZipError\n"; $z->print($string); $z->printf($format, $string); $z->write($string); $z->syswrite($string [, $length, $offset]); $z->flush(); $z->tell(); $z->eof(); $z->seek($position, $whence); $z->binmode(); $z->fileno(); $z->opened(); $z->autoflush(); $z->input_line_number(); $z->newStream( [OPTS] ); $z->deflateParams(); $z->close() ; $ZipError ; # IO::File mode print $z $string; printf $z $format, $string; tell $z eof $z seek $z, $position, $whence binmode $z fileno $z close $z ; =head1 DESCRIPTION This module provides a Perl interface that allows writing zip compressed data to files or buffer. The primary purpose of this module is to provide streaming write access to zip files and buffers. It is not a general-purpose file archiver. If that is what you want, check out C. At present three compression methods are supported by IO::Compress::Zip, namely Store (no compression at all), Deflate, Bzip2 and LZMA. Note that to create Bzip2 content, the module C must be installed. Note that to create LZMA content, the module C must be installed. For reading zip files/buffers, see the companion module L. =head1 Functional Interface A top-level function, C, is provided to carry out "one-shot" compression between buffers and/or files. For finer control over the compression process, see the L section. use IO::Compress::Zip qw(zip $ZipError) ; zip $input_filename_or_reference => $output_filename_or_reference [,OPTS] or die "zip failed: $ZipError\n"; The functional interface needs Perl5.005 or better. =head2 zip $input_filename_or_reference => $output_filename_or_reference [, OPTS] C expects at least two parameters, C<$input_filename_or_reference> and C<$output_filename_or_reference>. =head3 The C<$input_filename_or_reference> parameter The parameter, C<$input_filename_or_reference>, is used to define the source of the uncompressed data. It can take one of the following forms: =over 5 =item A filename If the <$input_filename_or_reference> parameter is a simple scalar, it is assumed to be a filename. This file will be opened for reading and the input data will be read from it. =item A filehandle If the C<$input_filename_or_reference> parameter is a filehandle, the input data will be read from it. The string '-' can be used as an alias for standard input. =item A scalar reference If C<$input_filename_or_reference> is a scalar reference, the input data will be read from C<$$input_filename_or_reference>. =item An array reference If C<$input_filename_or_reference> is an array reference, each element in the array must be a filename. The input data will be read from each file in turn. The complete array will be walked to ensure that it only contains valid filenames before any data is compressed. =item An Input FileGlob string If C<$input_filename_or_reference> is a string that is delimited by the characters "<" and ">" C will assume that it is an I. The input is the list of files that match the fileglob. See L for more details. =back If the C<$input_filename_or_reference> parameter is any other type, C will be returned. In addition, if C<$input_filename_or_reference> is a simple filename, the default values for the C, C