xref: /openbsd-src/gnu/usr.bin/perl/lib/utf8.pm (revision 99fd087599a8791921855f21bd7e36130f39aadc)
1package utf8;
2
3$utf8::hint_bits = 0x00800000;
4
5our $VERSION = '1.22';
6
7sub import {
8    $^H |= $utf8::hint_bits;
9}
10
11sub unimport {
12    $^H &= ~$utf8::hint_bits;
13}
14
15sub AUTOLOAD {
16    goto &$AUTOLOAD if defined &$AUTOLOAD;
17    require Carp;
18    Carp::croak("Undefined subroutine $AUTOLOAD called");
19}
20
211;
22__END__
23
24=head1 NAME
25
26utf8 - Perl pragma to enable/disable UTF-8 (or UTF-EBCDIC) in source code
27
28=head1 SYNOPSIS
29
30 use utf8;
31 no utf8;
32
33 # Convert the internal representation of a Perl scalar to/from UTF-8.
34
35 $num_octets = utf8::upgrade($string);
36 $success    = utf8::downgrade($string[, $fail_ok]);
37
38 # Change each character of a Perl scalar to/from a series of
39 # characters that represent the UTF-8 bytes of each original character.
40
41 utf8::encode($string);  # "\x{100}"  becomes "\xc4\x80"
42 utf8::decode($string);  # "\xc4\x80" becomes "\x{100}"
43
44 # Convert a code point from the platform native character set to
45 # Unicode, and vice-versa.
46 $unicode = utf8::native_to_unicode(ord('A')); # returns 65 on both
47                                               # ASCII and EBCDIC
48                                               # platforms
49 $native = utf8::unicode_to_native(65);        # returns 65 on ASCII
50                                               # platforms; 193 on
51                                               # EBCDIC
52
53 $flag = utf8::is_utf8($string); # since Perl 5.8.1
54 $flag = utf8::valid($string);
55
56=head1 DESCRIPTION
57
58The C<use utf8> pragma tells the Perl parser to allow UTF-8 in the
59program text in the current lexical scope.  The C<no utf8> pragma tells Perl
60to switch back to treating the source text as literal bytes in the current
61lexical scope.  (On EBCDIC platforms, technically it is allowing UTF-EBCDIC,
62and not UTF-8, but this distinction is academic, so in this document the term
63UTF-8 is used to mean both).
64
65B<Do not use this pragma for anything else than telling Perl that your
66script is written in UTF-8.> The utility functions described below are
67directly usable without C<use utf8;>.
68
69Because it is not possible to reliably tell UTF-8 from native 8 bit
70encodings, you need either a Byte Order Mark at the beginning of your
71source code, or C<use utf8;>, to instruct perl.
72
73When UTF-8 becomes the standard source format, this pragma will
74effectively become a no-op.
75
76See also the effects of the C<-C> switch and its cousin, the
77C<PERL_UNICODE> environment variable, in L<perlrun>.
78
79Enabling the C<utf8> pragma has the following effect:
80
81=over 4
82
83=item *
84
85Bytes in the source text that are not in the ASCII character set will be
86treated as being part of a literal UTF-8 sequence.  This includes most
87literals such as identifier names, string constants, and constant
88regular expression patterns.
89
90=back
91
92Note that if you have non-ASCII, non-UTF-8 bytes in your script (for example
93embedded Latin-1 in your string literals), C<use utf8> will be unhappy.  If
94you want to have such bytes under C<use utf8>, you can disable this pragma
95until the end the block (or file, if at top level) by C<no utf8;>.
96
97=head2 Utility functions
98
99The following functions are defined in the C<utf8::> package by the
100Perl core.  You do not need to say C<use utf8> to use these and in fact
101you should not say that unless you really want to have UTF-8 source code.
102
103=over 4
104
105=item * C<$num_octets = utf8::upgrade($string)>
106
107(Since Perl v5.8.0)
108Converts in-place the internal representation of the string from an octet
109sequence in the native encoding (Latin-1 or EBCDIC) to UTF-8. The
110logical character sequence itself is unchanged.  If I<$string> is already
111upgraded, then this is a no-op. Returns the
112number of octets necessary to represent the string as UTF-8.
113
114If your code needs to be compatible with versions of perl without
115C<use feature 'unicode_strings';>, you can force Unicode semantics on
116a given string:
117
118  # force unicode semantics for $string without the
119  # "unicode_strings" feature
120  utf8::upgrade($string);
121
122For example:
123
124  # without explicit or implicit use feature 'unicode_strings'
125  my $x = "\xDF";    # LATIN SMALL LETTER SHARP S
126  $x =~ /ss/i;       # won't match
127  my $y = uc($x);    # won't convert
128  utf8::upgrade($x);
129  $x =~ /ss/i;       # matches
130  my $z = uc($x);    # converts to "SS"
131
132B<Note that this function does not handle arbitrary encodings>;
133use L<Encode> instead.
134
135=item * C<$success = utf8::downgrade($string[, $fail_ok])>
136
137(Since Perl v5.8.0)
138Converts in-place the internal representation of the string from UTF-8 to the
139equivalent octet sequence in the native encoding (Latin-1 or EBCDIC). The
140logical character sequence itself is unchanged. If I<$string> is already
141stored as native 8 bit, then this is a no-op.  Can be used to make sure that
142the UTF-8 flag is off, e.g. when you want to make sure that the substr() or
143length() function works with the usually faster byte algorithm.
144
145Fails if the original UTF-8 sequence cannot be represented in the
146native 8 bit encoding. On failure dies or, if the value of I<$fail_ok> is
147true, returns false.
148
149Returns true on success.
150
151If your code expects an octet sequence this can be used to validate
152that you've received one:
153
154  # throw an exception if not representable as octets
155  utf8::downgrade($string)
156
157  # or do your own error handling
158  utf8::downgrade($string, 1) or die "string must be octets";
159
160B<Note that this function does not handle arbitrary encodings>;
161use L<Encode> instead.
162
163=item * C<utf8::encode($string)>
164
165(Since Perl v5.8.0)
166Converts in-place the character sequence to the corresponding octet
167sequence in Perl's extended UTF-8. That is, every (possibly wide) character
168gets replaced with a sequence of one or more characters that represent the
169individual UTF-8 bytes of the character.  The UTF8 flag is turned off.
170Returns nothing.
171
172 my $x = "\x{100}"; # $x contains one character, with ord 0x100
173 utf8::encode($x);  # $x contains two characters, with ords (on
174                    # ASCII platforms) 0xc4 and 0x80.  On EBCDIC
175                    # 1047, this would instead be 0x8C and 0x41.
176
177Similar to:
178
179  use Encode;
180  $x = Encode::encode("utf8", $x);
181
182B<Note that this function does not handle arbitrary encodings>;
183use L<Encode> instead.
184
185=item * C<$success = utf8::decode($string)>
186
187(Since Perl v5.8.0)
188Attempts to convert in-place the octet sequence encoded in Perl's extended
189UTF-8 to the corresponding character sequence. That is, it replaces each
190sequence of characters in the string whose ords represent a valid (extended)
191UTF-8 byte sequence, with the corresponding single character.  The UTF-8 flag
192is turned on only if the source string contains multiple-byte UTF-8
193characters.  If I<$string> is invalid as extended UTF-8, returns false;
194otherwise returns true.
195
196 my $x = "\xc4\x80"; # $x contains two characters, with ords
197                     # 0xc4 and 0x80
198 utf8::decode($x);   # On ASCII platforms, $x contains one char,
199                     # with ord 0x100.   Since these bytes aren't
200                     # legal UTF-EBCDIC, on EBCDIC platforms, $x is
201                     # unchanged and the function returns FALSE.
202
203B<Note that this function does not handle arbitrary encodings>;
204use L<Encode> instead.
205
206=item * C<$unicode = utf8::native_to_unicode($code_point)>
207
208(Since Perl v5.8.0)
209This takes an unsigned integer (which represents the ordinal number of a
210character (or a code point) on the platform the program is being run on) and
211returns its Unicode equivalent value.  Since ASCII platforms natively use the
212Unicode code points, this function returns its input on them.  On EBCDIC
213platforms it converts from EBCDIC to Unicode.
214
215A meaningless value will currently be returned if the input is not an unsigned
216integer.
217
218Since Perl v5.22.0, calls to this function are optimized out on ASCII
219platforms, so there is no performance hit in using it there.
220
221=item * C<$native = utf8::unicode_to_native($code_point)>
222
223(Since Perl v5.8.0)
224This is the inverse of C<utf8::native_to_unicode()>, converting the other
225direction.  Again, on ASCII platforms, this returns its input, but on EBCDIC
226platforms it will find the native platform code point, given any Unicode one.
227
228A meaningless value will currently be returned if the input is not an unsigned
229integer.
230
231Since Perl v5.22.0, calls to this function are optimized out on ASCII
232platforms, so there is no performance hit in using it there.
233
234=item * C<$flag = utf8::is_utf8($string)>
235
236(Since Perl 5.8.1)  Test whether I<$string> is marked internally as encoded in
237UTF-8.  Functionally the same as C<Encode::is_utf8($string)>.
238
239Typically only necessary for debugging and testing, if you need to
240dump the internals of an SV, L<Devel::Peek's|Devel::Peek> Dump()
241provides more detail in a compact form.
242
243If you still think you need this outside of debugging, testing or
244dealing with filenames, you should probably read L<perlunitut> and
245L<perlunifaq/What is "the UTF8 flag"?>.
246
247Don't use this flag as a marker to distinguish character and binary
248data: that should be decided for each variable when you write your
249code.
250
251To force unicode semantics in code portable to perl 5.8 and 5.10, call
252C<utf8::upgrade($string)> unconditionally.
253
254=item * C<$flag = utf8::valid($string)>
255
256[INTERNAL] Test whether I<$string> is in a consistent state regarding
257UTF-8.  Will return true if it is well-formed Perl extended UTF-8 and has the
258UTF-8 flag
259on B<or> if I<$string> is held as bytes (both these states are 'consistent').
260The main reason for this routine is to allow Perl's test suite to check
261that operations have left strings in a consistent state.
262
263=back
264
265C<utf8::encode> is like C<utf8::upgrade>, but the UTF8 flag is
266cleared.  See L<perlunicode>, and the C API
267functions C<L<sv_utf8_upgrade|perlapi/sv_utf8_upgrade>>,
268C<L<perlapi/sv_utf8_downgrade>>, C<L<perlapi/sv_utf8_encode>>,
269and C<L<perlapi/sv_utf8_decode>>, which are wrapped by the Perl functions
270C<utf8::upgrade>, C<utf8::downgrade>, C<utf8::encode> and
271C<utf8::decode>.  Also, the functions C<utf8::is_utf8>, C<utf8::valid>,
272C<utf8::encode>, C<utf8::decode>, C<utf8::upgrade>, and C<utf8::downgrade> are
273actually internal, and thus always available, without a C<require utf8>
274statement.
275
276=head1 BUGS
277
278Some filesystems may not support UTF-8 file names, or they may be supported
279incompatibly with Perl.  Therefore UTF-8 names that are visible to the
280filesystem, such as module names may not work.
281
282=head1 SEE ALSO
283
284L<perlunitut>, L<perluniintro>, L<perlrun>, L<bytes>, L<perlunicode>
285
286=cut
287