xref: /openbsd-src/gnu/usr.bin/perl/cpan/Encode/Unicode/Unicode.pm (revision ae3cb403620ab940fbaabb3055fac045a63d56b7)
1package Encode::Unicode;
2
3use strict;
4use warnings;
5no warnings 'redefine';
6
7our $VERSION = do { my @r = ( q$Revision: 2.15 $ =~ /\d+/g ); sprintf "%d." . "%02d" x $#r, @r };
8
9use XSLoader;
10XSLoader::load( __PACKAGE__, $VERSION );
11
12#
13# Object Generator 8 transcoders all at once!
14#
15
16require Encode;
17
18our %BOM_Unknown = map { $_ => 1 } qw(UTF-16 UTF-32);
19
20for 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
45use parent qw(Encode::Encoding);
46
47sub 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 implementation 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
611;
62__END__
63
64=head1 NAME
65
66Encode::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
78This module implements all Character Encoding Schemes of Unicode that
79are officially documented by Unicode Consortium (except, of course,
80for UTF-8, which is a native format in perl).
81
82=over 4
83
84=item L<http://www.unicode.org/glossary/> says:
85
86I<Character Encoding Scheme> A character encoding form plus byte
87serialization. There are Seven character encoding schemes in Unicode:
88UTF-8, UTF-16, UTF-16BE, UTF-16LE, UTF-32 (UCS-4), UTF-32BE (UCS-4BE) and
89UTF-32LE (UCS-4LE), and UTF-7.
90
91Since UTF-7 is a 7-bit (re)encoded version of UTF-16BE, It is not part of
92Unicode's Character Encoding Scheme.  It is separately implemented in
93Encode::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
115You can categorize these CES by 3 criteria:  size of each character,
116endianness, and Byte Order Mark.
117
118=head2 by size
119
120UCS-2 is a fixed-length encoding with each character taking 16 bits.
121It B<does not> support I<surrogate pairs>.  When a surrogate pair
122is encountered during decode(), its place is filled with \x{FFFD}
123if I<CHECK> is 0, or the routine croaks if I<CHECK> is 1.  When a
124character whose ord value is larger than 0xFFFF is encountered,
125its place is filled with \x{FFFD} if I<CHECK> is 0, or the routine
126croaks if I<CHECK> is 1.
127
128UTF-16 is almost the same as UCS-2 but it supports I<surrogate pairs>.
129When it encounters a high surrogate (0xD800-0xDBFF), it fetches the
130following low surrogate (0xDC00-0xDFFF) and C<desurrogate>s them to
131form a character.  Bogus surrogates result in death.  When \x{10000}
132or above is encountered during encode(), it C<ensurrogate>s them and
133pushes the surrogate pair to the output stream.
134
135UTF-32 (UCS-4) is a fixed-length encoding with each character taking 32 bits.
136Since it is 32-bit, there is no need for I<surrogate pairs>.
137
138=head2 by endianness
139
140The first (and now failed) goal of Unicode was to map all character
141repertoires into a fixed-length integer so that programmers are happy.
142Since each character is either a I<short> or I<long> in C, you have to
143pay attention to the endianness of each platform when you pass data
144to one another.
145
146Anything marked as BE is Big Endian (or network byte order) and LE is
147Little Endian (aka VAX byte order).  For anything not marked either
148BE or LE, a character called Byte Order Mark (BOM) indicating the
149endianness is prepended to the string.
150
151CAVEAT: Though BOM in utf8 (\xEF\xBB\xBF) is valid, it is meaningless
152and 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
166This modules handles the BOM as follows.
167
168=over 4
169
170=item *
171
172When BE or LE is explicitly stated as the name of encoding, BOM is
173simply treated as a normal character (ZERO WIDTH NO-BREAK SPACE).
174
175=item *
176
177When BE or LE is omitted during decode(), it checks if BOM is at the
178beginning of the string; if one is found, the endianness is set to
179what the BOM says.
180
181=item *
182
183Default Byte Order
184
185When no BOM is found, Encode 2.76 and blow croaked.  Since Encode
1862.77, it falls back to BE accordingly to RFC2781 and the Unicode
187Standard version 8.0
188
189=item *
190
191When BE or LE is omitted during encode(), it returns a BE-encoded
192string with BOM prepended.  So when you want to encode a whole text
193file, make sure you encode() the whole text at once, not line by line
194or each line, not file, will have a BOM prepended.
195
196=item *
197
198C<UCS-2> is an exception.  Unlike others, this is an alias of UCS-2BE.
199UCS-2 is already registered by IANA and others that way.
200
201=back
202
203=head1 Surrogate Pairs
204
205To say the least, surrogate pairs were the biggest mistake of the
206Unicode Consortium.  But according to the late Douglas Adams in I<The
207Hitchhiker's Guide to the Galaxy> Trilogy, C<In the beginning the
208Universe was created. This has made a lot of people very angry and
209been widely regarded as a bad move>.  Their mistake was not of this
210magnitude so let's forgive them.
211
212(I don't dare make any comparison with Unicode Consortium and the
213Vogons here ;)  Or, comparing Encode to Babel Fish is completely
214appropriate -- if you can only stick this into your ear :)
215
216Surrogate pairs were born when the Unicode Consortium finally
217admitted that 16 bits were not big enough to hold all the world's
218character repertoires.  But they already made UCS-2 16-bit.  What
219do we do?
220
221Back then, the range 0xD800-0xDFFF was not allocated.  Let's split
222that range in half and use the first half to represent the C<upper
223half of a character> and the second half to represent the C<lower
224half of a character>.  That way, you can represent 1024 * 1024 =
2251048576 more characters.  Now we can store character ranges up to
226\x{10ffff} even with 16-bit encodings.  This pair of half-character is
227now called a I<surrogate pair> and UTF-16 is the name of the encoding
228that embraces them.
229
230Here is a formula to ensurrogate a Unicode character \x{10000} and
231above;
232
233  $hi = ($uni - 0x10000) / 0x400 + 0xD800;
234  $lo = ($uni - 0x10000) % 0x400 + 0xDC00;
235
236And to desurrogate;
237
238 $uni = 0x10000 + ($hi - 0xD800) * 0x400 + ($lo - 0xDC00);
239
240Note this move has made \x{D800}-\x{DFFF} into a forbidden zone but
241perl does not prohibit the use of characters within this range.  To perl,
242every one of \x{0000_0000} up to \x{ffff_ffff} (*) is I<a character>.
243
244  (*) or \x{ffff_ffff_ffff_ffff} if your perl is compiled with 64-bit
245  integer support!
246
247=head1 Error Checking
248
249Unlike most encodings which accept various ways to handle errors,
250Unicode encodings simply croaks.
251
252  % perl -MEncode -e'$_ = "\xfe\xff\xd8\xd9\xda\xdb\0\n"' \
253         -e'Encode::from_to($_, "utf16","shift_jis", 0); print'
254  UTF-16:Malformed LO surrogate d8d9 at /path/to/Encode.pm line 184.
255  % perl -MEncode -e'$a = "BOM missing"' \
256         -e' Encode::from_to($a, "utf16", "shift_jis", 0); print'
257  UTF-16:Unrecognised BOM 424f at /path/to/Encode.pm line 184.
258
259Unlike other encodings where mappings are not one-to-one against
260Unicode, UTFs are supposed to map 100% against one another.  So Encode
261is more strict on UTFs.
262
263Consider that "division by zero" of Encode :)
264
265=head1 SEE ALSO
266
267L<Encode>, L<Encode::Unicode::UTF7>, L<http://www.unicode.org/glossary/>,
268L<http://www.unicode.org/unicode/faq/utf_bom.html>,
269
270RFC 2781 L<http://www.ietf.org/rfc/rfc2781.txt>,
271
272The whole Unicode standard L<http://www.unicode.org/unicode/uni2book/u2.html>
273
274Ch. 15, pp. 403 of C<Programming Perl (3rd Edition)>
275by Larry Wall, Tom Christiansen, Jon Orwant;
276O'Reilly & Associates; ISBN 0-596-00027-8
277
278=cut
279