X-Git-Url: https://perl5.git.perl.org/perl5.git/blobdiff_plain/8f8cf39ca802a67cf132f9179bbf212ddb1ec64e..f240c685c914970dc8ffec926f02d6048831bc09:/lib/utf8.pm diff --git a/lib/utf8.pm b/lib/utf8.pm index 5a37aec..23fbfac 100644 --- a/lib/utf8.pm +++ b/lib/utf8.pm @@ -2,11 +2,10 @@ package utf8; $utf8::hint_bits = 0x00800000; -our $VERSION = '1.00'; +our $VERSION = '1.17'; sub import { $^H |= $utf8::hint_bits; - $enc{caller()} = $_[1] if $_[1]; } sub unimport { @@ -16,6 +15,7 @@ sub unimport { sub AUTOLOAD { require "utf8_heavy.pl"; goto &$AUTOLOAD if defined &$AUTOLOAD; + require Carp; Carp::croak("Undefined subroutine $AUTOLOAD called"); } @@ -28,8 +28,30 @@ utf8 - Perl pragma to enable/disable UTF-8 (or UTF-EBCDIC) in source code =head1 SYNOPSIS - use utf8; - no utf8; + use utf8; + no utf8; + + # Convert the internal representation of a Perl scalar to/from UTF-8. + + $num_octets = utf8::upgrade($string); + $success = utf8::downgrade($string[, $fail_ok]); + + # Change each character of a Perl scalar to/from a series of + # characters that represent the UTF-8 bytes of each original character. + + utf8::encode($string); # "\x{100}" becomes "\xc4\x80" + utf8::decode($string); # "\xc4\x80" becomes "\x{100}" + + # Convert a code point from the platform native character set to + # Unicode, and vice-versa. + $unicode = utf8::native_to_unicode(ord('A')); # returns 65 on both + # ASCII and EBCDIC + # platforms + $native = utf8::unicode_to_native(65); # returns 65 on ASCII + # platforms; 193 on EBCDIC + + $flag = utf8::is_utf8($string); # since Perl 5.8.1 + $flag = utf8::valid($string); =head1 DESCRIPTION @@ -38,16 +60,22 @@ program text in the current lexical scope (allow UTF-EBCDIC on EBCDIC based platforms). The C pragma tells Perl to switch back to treating the source text as literal bytes in the current lexical scope. -This pragma is primarily a compatibility device. Perl versions -earlier than 5.6 allowed arbitrary bytes in source code, whereas -in future we would like to standardize on the UTF-8 encoding for -source text. Until UTF-8 becomes the default format for source -text, this pragma should be used to recognize UTF-8 in the source. +B The utility functions described below are +directly usable without C. + +Because it is not possible to reliably tell UTF-8 from native 8 bit +encodings, you need either a Byte Order Mark at the beginning of your +source code, or C, to instruct perl. + When UTF-8 becomes the standard source format, this pragma will -effectively become a no-op. For convenience in what follows the -term I is used to refer to UTF-8 on ASCII and ISO Latin based +effectively become a no-op. For convenience in what follows the term +I is used to refer to UTF-8 on ASCII and ISO Latin based platforms and UTF-EBCDIC on EBCDIC based platforms. +See also the effects of the C<-C> switch and its cousin, the +C environment variable, in L. + Enabling the C pragma has the following effect: =over 4 @@ -55,7 +83,7 @@ Enabling the C pragma has the following effect: =item * Bytes in the source text that have their high-bit set will be treated -as being part of a literal UTF-8 character. This includes most +as being part of a literal UTF-X sequence. This includes most literals such as identifier names, string constants, and constant regular expression patterns. @@ -67,58 +95,136 @@ treated as being part of a literal UTF-EBCDIC character. Note that if you have bytes with the eighth bit on in your script (for example embedded Latin-1 in your string literals), C will be unhappy since the bytes are most probably not well-formed -UTF-8. If you want to have such bytes and use utf8, you can disable -utf8 until the end the block (or file, if at top level) by C. +UTF-X. If you want to have such bytes under C, you can disable +this pragma until the end the block (or file, if at top level) by +C. =head2 Utility functions -The following functions are defined in the C package by the perl core. +The following functions are defined in the C package by the +Perl core. You do not need to say C to use these and in fact +you should not say that unless you really want to have UTF-8 source code. =over 4 -=item * $num_octets = utf8::upgrade($string); +=item * C<$num_octets = utf8::upgrade($string)> + +Converts in-place the internal representation of the string from an octet +sequence in the native encoding (Latin-1 or EBCDIC) to I. The +logical character sequence itself is unchanged. If I<$string> is already +stored as I, then this is a no-op. Returns the +number of octets necessary to represent the string as I. Can be +used to make sure that the UTF-8 flag is on, so that C<\w> or C +work as Unicode on strings containing characters in the range 0x80-0xFF +(on ASCII and derivatives). + +B +Therefore Encode is recommended for the general purposes; see also +L. + +=item * C<$success = utf8::downgrade($string[, $fail_ok])> + +Converts in-place the internal representation of the string from +I to the equivalent octet sequence in the native encoding (Latin-1 +or EBCDIC). The logical character sequence itself is unchanged. If +I<$string> is already stored as native 8 bit, then this is a no-op. Can +be used to +make sure that the UTF-8 flag is off, e.g. when you want to make sure +that the substr() or length() function works with the usually faster +byte algorithm. + +Fails if the original I sequence cannot be represented in the +native 8 bit encoding. On failure dies or, if the value of I<$fail_ok> is +true, returns false. + +Returns true on success. + +B +Therefore Encode is recommended for the general purposes; see also +L. + +=item * C + +Converts in-place the character sequence to the corresponding octet +sequence in I. That is, every (possibly wide) character gets +replaced with a sequence of one or more characters that represent the +individual I bytes of the character. The UTF8 flag is turned off. +Returns nothing. + + my $a = "\x{100}"; # $a contains one character, with ord 0x100 + utf8::encode($a); # $a contains two characters, with ords (on + # ASCII platforms) 0xc4 and 0x80 + +B +Therefore Encode is recommended for the general purposes; see also +L. + +=item * C<$success = utf8::decode($string)> + +Attempts to convert in-place the octet sequence encoded as I to the +corresponding character sequence. That is, it replaces each sequence of +characters in the string whose ords represent a valid UTF-X byte +sequence, with the corresponding single character. The UTF-8 flag is +turned on only if the source string contains multiple-byte I +characters. If I<$string> is invalid as I, returns false; +otherwise returns true. + + my $a = "\xc4\x80"; # $a contains two characters, with ords + # 0xc4 and 0x80 + utf8::decode($a); # On ASCII platforms, $a contains one char, + # with ord 0x100. On EBCDIC platforms, $a + # is unchanged and the function returns FALSE. + +(C<"\xc4\x80"> is not a valid sequence of bytes in any UTF-8-encoded +character(s) in the EBCDIC code pages that Perl supports, which is why the +above example returns failure on them. What does decode into C<\x{100}> +depends on the platform. It is C<"\x8C\x41"> in IBM-1047.) + +B +Therefore Encode is recommended for the general purposes; see also +L. + +=item * C<$unicode = utf8::native_to_unicode($code_point)> + +(Since Perl v5.8.0) +This takes an unsigned integer (which represents the ordinal number of a +character (or a code point) on the platform the program is being run on) and +returns its Unicode equivalent value. Since ASCII platforms natively use the +Unicode code points, this function returns its input on them. On EBCDIC +platforms it converts from EBCDIC to Unicode. + +A meaningless value will currently be returned if the input is not an unsigned +integer. -Converts (in-place) internal representation of string to Perl's internal -I form. Returns the number of octets necessary to represent -the string as I. Can be used to make sure that the -UTF-8 flag is on, so that C<\w> or C work as expected on strings -containing characters in the range 0x80-0xFF. Note that this should -not be used to convert -a legacy byte encoding to Unicode: use Encode for that. Affected -by the encoding pragma. +Since Perl v5.22.0, calls to this function are optimized out on ASCII +platforms, so there is no performance hit in using it there. -=item * utf8::downgrade($string[, FAIL_OK]) +=item * C<$native = utf8::unicode_to_native($code_point)> -Converts (in-place) internal representation of string to be un-encoded -bytes. Returns true on success. On failure dies or, if the value of -FAIL_OK is true, returns false. Can be used to make sure that the -UTF-8 flag is off, e.g. when you want to make sure that the substr() -or length() function works with the usually faster byte algorithm. -Note that this should not be used to convert Unicode back to a legacy -byte encoding: use Encode for that. B affected by the encoding -pragma. +(Since Perl v5.8.0) +This is the inverse of C, converting the other +direction. Again, on ASCII platforms, this returns its input, but on EBCDIC +platforms it will find the native platform code point, given any Unicode one. -=item * utf8::encode($string) +A meaningless value will currently be returned if the input is not an unsigned +integer. -Converts (in-place) I<$string> from logical characters to octet -sequence representing it in Perl's I encoding. Same as -Encode::encode_utf8(). Note that this should not be used to convert -a legacy byte encoding to Unicode: use Encode for that. +Since Perl v5.22.0, calls to this function are optimized out on ASCII +platforms, so there is no performance hit in using it there. -=item * $flag = utf8::decode($string) +=item * C<$flag = utf8::is_utf8($string)> -Attempts to convert I<$string> in-place from Perl's I encoding -into logical characters. Same as Encode::decode_utf8(). Note that this -should not be used to convert Unicode back to a legacy byte encoding: -use Encode for that. +(Since Perl 5.8.1) Test whether I<$string> is marked internally as encoded in +UTF-8. Functionally the same as Encode::is_utf8(). -=item * $flag = utf8::valid(STRING) +=item * C<$flag = utf8::valid($string)> -[INTERNAL] Test whether STRING is in a consistent state. Will return -true if string is held as bytes, or is well-formed UTF-8 and has the -UTF-8 flag on. Main reason for this routine is to allow Perl's -testsuite to check that operations have left strings in a consistent -state. +[INTERNAL] Test whether I<$string> is in a consistent state regarding +UTF-8. Will return true if it is well-formed UTF-8 and has the UTF-8 flag +on B if I<$string> is held as bytes (both these states are 'consistent'). +Main reason for this routine is to allow Perl's test suite to check +that operations have left strings in a consistent state. You most +probably want to use utf8::is_utf8() instead. =back @@ -127,10 +233,10 @@ cleared. See L for more on the UTF8 flag and the C API functions C, C, C, and C, which are wrapped by the Perl functions C, C, C and -C. Note that in the Perl 5.8.0 implementation the -functions utf8::valid, utf8::encode, utf8::decode, utf8::upgrade, -and utf8::downgrade are always available, without a C -statement-- this may change in future releases. +C. Also, the functions utf8::is_utf8, utf8::valid, +utf8::encode, utf8::decode, utf8::upgrade, and utf8::downgrade are +actually internal, and thus always available, without a C +statement. =head1 BUGS @@ -147,6 +253,6 @@ portable answers. =head1 SEE ALSO -L, L +L, L, L, L, L =cut