[Summary view] [Print] [Text view]

   1  package Encode::Unicode;
   2  
   3  use strict;
   4  use warnings;
   5  no warnings 'redefine';
   6  
   7  our $VERSION = do { my @r = ( q$Revision: 2.5 $ =~ /\d+/g ); sprintf "%d." . "%02d" x $#r, @r };
   8  
   9  use XSLoader;
  10  XSLoader::load( __PACKAGE__, $VERSION );
  11  
  12  #
  13  # Object Generator 8 transcoders all at once!
  14  #
  15  
  16  require Encode;
  17  
  18  our %BOM_Unknown = map { $_ => 1 } qw(UTF-16 UTF-32);
  19  
  20  for my $name (
  21      qw(UTF-16 UTF-16BE UTF-16LE
  22      UTF-32 UTF-32BE UTF-32LE
  23      UCS-2BE  UCS-2LE)
  24    )
  25  {
  26      my ( $size, $endian, $ucs2, $mask );
  27      $name =~ /^(\w+)-(\d+)(\w*)$/o;
  28      if ( $ucs2 = ( $1 eq 'UCS' ) ) {
  29          $size = 2;
  30      }
  31      else {
  32          $size = $2 / 8;
  33      }
  34      $endian = ( $3 eq 'BE' ) ? 'n' : ( $3 eq 'LE' ) ? 'v' : '';
  35      $size == 4 and $endian = uc($endian);
  36  
  37      $Encode::Encoding{$name} = bless {
  38          Name   => $name,
  39          size   => $size,
  40          endian => $endian,
  41          ucs2   => $ucs2,
  42      } => __PACKAGE__;
  43  }
  44  
  45  use base qw(Encode::Encoding);
  46  
  47  sub renew {
  48      my $self = shift;
  49      $BOM_Unknown{ $self->name } or return $self;
  50      my $clone = bless {%$self} => ref($self);
  51      $clone->{renewed}++;    # so the caller knows it is renewed.
  52      return $clone;
  53  }
  54  
  55  # There used to be a perl implemntation of (en|de)code but with
  56  # XS version is ripe, perl version is zapped for optimal speed
  57  
  58  *decode = \&decode_xs;
  59  *encode = \&encode_xs;
  60  
  61  1;
  62  __END__
  63  
  64  =head1 NAME
  65  
  66  Encode::Unicode -- Various Unicode Transformation Formats
  67  
  68  =cut
  69  
  70  =head1 SYNOPSIS
  71  
  72      use Encode qw/encode decode/; 
  73      $ucs2 = encode("UCS-2BE", $utf8);
  74      $utf8 = decode("UCS-2BE", $ucs2);
  75  
  76  =head1 ABSTRACT
  77  
  78  This module implements all Character Encoding Schemes of Unicode that
  79  are officially documented by Unicode Consortium (except, of course,
  80  for UTF-8, which is a native format in perl).
  81  
  82  =over 4
  83  
  84  =item L<http://www.unicode.org/glossary/> says:
  85  
  86  I<Character Encoding Scheme> A character encoding form plus byte
  87  serialization. There are Seven character encoding schemes in Unicode:
  88  UTF-8, UTF-16, UTF-16BE, UTF-16LE, UTF-32 (UCS-4), UTF-32BE (UCS-4BE) and
  89  UTF-32LE (UCS-4LE), and UTF-7.
  90  
  91  Since UTF-7 is a 7-bit (re)encoded version of UTF-16BE, It is not part of
  92  Unicode's Character Encoding Scheme.  It is separately implemented in
  93  Encode::Unicode::UTF7.  For details see L<Encode::Unicode::UTF7>.
  94  
  95  =item Quick Reference
  96  
  97                  Decodes from ord(N)           Encodes chr(N) to...
  98         octet/char BOM S.P d800-dfff  ord > 0xffff     \x{1abcd} ==
  99    ---------------+-----------------+------------------------------
 100    UCS-2BE       2   N   N  is bogus                  Not Available
 101    UCS-2LE       2   N   N     bogus                  Not Available
 102    UTF-16      2/4   Y   Y  is   S.P           S.P            BE/LE
 103    UTF-16BE    2/4   N   Y       S.P           S.P    0xd82a,0xdfcd
 104    UTF-16LE    2/4   N   Y       S.P           S.P    0x2ad8,0xcddf
 105    UTF-32        4   Y   -  is bogus         As is            BE/LE
 106    UTF-32BE      4   N   -     bogus         As is       0x0001abcd
 107    UTF-32LE      4   N   -     bogus         As is       0xcdab0100
 108    UTF-8       1-4   -   -     bogus   >= 4 octets   \xf0\x9a\af\8d
 109    ---------------+-----------------+------------------------------
 110  
 111  =back
 112  
 113  =head1 Size, Endianness, and BOM
 114  
 115  You can categorize these CES by 3 criteria:  size of each character,
 116  endianness, and Byte Order Mark.
 117  
 118  =head2 by size
 119  
 120  UCS-2 is a fixed-length encoding with each character taking 16 bits.
 121  It B<does not> support I<surrogate pairs>.  When a surrogate pair
 122  is encountered during decode(), its place is filled with \x{FFFD}
 123  if I<CHECK> is 0, or the routine croaks if I<CHECK> is 1.  When a
 124  character whose ord value is larger than 0xFFFF is encountered,
 125  its place is filled with \x{FFFD} if I<CHECK> is 0, or the routine
 126  croaks if I<CHECK> is 1.
 127  
 128  UTF-16 is almost the same as UCS-2 but it supports I<surrogate pairs>.
 129  When it encounters a high surrogate (0xD800-0xDBFF), it fetches the
 130  following low surrogate (0xDC00-0xDFFF) and C<desurrogate>s them to
 131  form a character.  Bogus surrogates result in death.  When \x{10000}
 132  or above is encountered during encode(), it C<ensurrogate>s them and
 133  pushes the surrogate pair to the output stream.
 134  
 135  UTF-32 (UCS-4) is a fixed-length encoding with each character taking 32 bits.
 136  Since it is 32-bit, there is no need for I<surrogate pairs>.
 137  
 138  =head2 by endianness
 139  
 140  The first (and now failed) goal of Unicode was to map all character
 141  repertoires into a fixed-length integer so that programmers are happy.
 142  Since each character is either a I<short> or I<long> in C, you have to
 143  pay attention to the endianness of each platform when you pass data
 144  to one another.
 145  
 146  Anything marked as BE is Big Endian (or network byte order) and LE is
 147  Little Endian (aka VAX byte order).  For anything not marked either
 148  BE or LE, a character called Byte Order Mark (BOM) indicating the
 149  endianness is prepended to the string.
 150  
 151  CAVEAT: Though BOM in utf8 (\xEF\xBB\xBF) is valid, it is meaningless
 152  and as of this writing Encode suite just leave it as is (\x{FeFF}).
 153  
 154  =over 4
 155  
 156  =item BOM as integer when fetched in network byte order
 157  
 158                16         32 bits/char
 159    -------------------------
 160    BE      0xFeFF 0x0000FeFF
 161    LE      0xFFFe 0xFFFe0000
 162    -------------------------
 163  
 164  =back
 165  
 166  This modules handles the BOM as follows.
 167  
 168  =over 4
 169  
 170  =item *
 171  
 172  When BE or LE is explicitly stated as the name of encoding, BOM is
 173  simply treated as a normal character (ZERO WIDTH NO-BREAK SPACE).
 174  
 175  =item *
 176  
 177  When BE or LE is omitted during decode(), it checks if BOM is at the
 178  beginning of the string; if one is found, the endianness is set to
 179  what the BOM says.  If no BOM is found, the routine dies.
 180  
 181  =item *
 182  
 183  When BE or LE is omitted during encode(), it returns a BE-encoded
 184  string with BOM prepended.  So when you want to encode a whole text
 185  file, make sure you encode() the whole text at once, not line by line
 186  or each line, not file, will have a BOM prepended.
 187  
 188  =item *
 189  
 190  C<UCS-2> is an exception.  Unlike others, this is an alias of UCS-2BE.
 191  UCS-2 is already registered by IANA and others that way.
 192  
 193  =back
 194  
 195  =head1 Surrogate Pairs
 196  
 197  To say the least, surrogate pairs were the biggest mistake of the
 198  Unicode Consortium.  But according to the late Douglas Adams in I<The
 199  Hitchhiker's Guide to the Galaxy> Trilogy, C<In the beginning the
 200  Universe was created. This has made a lot of people very angry and
 201  been widely regarded as a bad move>.  Their mistake was not of this
 202  magnitude so let's forgive them.
 203  
 204  (I don't dare make any comparison with Unicode Consortium and the
 205  Vogons here ;)  Or, comparing Encode to Babel Fish is completely
 206  appropriate -- if you can only stick this into your ear :)
 207  
 208  Surrogate pairs were born when the Unicode Consortium finally
 209  admitted that 16 bits were not big enough to hold all the world's
 210  character repertoires.  But they already made UCS-2 16-bit.  What
 211  do we do?
 212  
 213  Back then, the range 0xD800-0xDFFF was not allocated.  Let's split
 214  that range in half and use the first half to represent the C<upper
 215  half of a character> and the second half to represent the C<lower
 216  half of a character>.  That way, you can represent 1024 * 1024 =
 217  1048576 more characters.  Now we can store character ranges up to
 218  \x{10ffff} even with 16-bit encodings.  This pair of half-character is
 219  now called a I<surrogate pair> and UTF-16 is the name of the encoding
 220  that embraces them.
 221  
 222  Here is a formula to ensurrogate a Unicode character \x{10000} and
 223  above;
 224  
 225    $hi = ($uni - 0x10000) / 0x400 + 0xD800;
 226    $lo = ($uni - 0x10000) % 0x400 + 0xDC00;
 227  
 228  And to desurrogate;
 229  
 230   $uni = 0x10000 + ($hi - 0xD800) * 0x400 + ($lo - 0xDC00);
 231  
 232  Note this move has made \x{D800}-\x{DFFF} into a forbidden zone but
 233  perl does not prohibit the use of characters within this range.  To perl, 
 234  every one of \x{0000_0000} up to \x{ffff_ffff} (*) is I<a character>.
 235  
 236    (*) or \x{ffff_ffff_ffff_ffff} if your perl is compiled with 64-bit
 237    integer support!
 238  
 239  =head1 Error Checking
 240  
 241  Unlike most encodings which accept various ways to handle errors,
 242  Unicode encodings simply croaks.
 243  
 244    % perl -MEncode -e '$_ = "\xfe\xff\xd8\xd9\xda\xdb\0\n"' \
 245           -e 'Encode::from_to($_, "utf16","shift_jis", 0); print'
 246    UTF-16:Malformed LO surrogate d8d9 at /path/to/Encode.pm line 184.
 247    % perl -MEncode -e '$a = "BOM missing"' \
 248           -e ' Encode::from_to($a, "utf16", "shift_jis", 0); print'
 249    UTF-16:Unrecognised BOM 424f at /path/to/Encode.pm line 184.
 250  
 251  Unlike other encodings where mappings are not one-to-one against
 252  Unicode, UTFs are supposed to map 100% against one another.  So Encode
 253  is more strict on UTFs.
 254  
 255  Consider that "division by zero" of Encode :)
 256  
 257  =head1 SEE ALSO
 258  
 259  L<Encode>, L<Encode::Unicode::UTF7>, L<http://www.unicode.org/glossary/>,
 260  L<http://www.unicode.org/unicode/faq/utf_bom.html>,
 261  
 262  RFC 2781 L<http://rfc.net/rfc2781.html>,
 263  
 264  The whole Unicode standard L<http://www.unicode.org/unicode/uni2book/u2.html>
 265  
 266  Ch. 15, pp. 403 of C<Programming Perl (3rd Edition)>
 267  by Larry Wall, Tom Christiansen, Jon Orwant; 
 268  O'Reilly & Associates; ISBN 0-596-00027-8
 269  
 270  =cut