X-Git-Url: https://perl5.git.perl.org/perl5.git/blobdiff_plain/075d4edd61a9648945541c8a76d8c03d4588400b..f83c6033e71dad81af816912dd321593b6987890:/lib/utf8.pm diff --git a/lib/utf8.pm b/lib/utf8.pm index a985021..4980c7c 100644 --- a/lib/utf8.pm +++ b/lib/utf8.pm @@ -2,11 +2,10 @@ package utf8; $utf8::hint_bits = 0x00800000; -our $VERSION = '1.07'; +our $VERSION = '1.14'; sub import { $^H |= $utf8::hint_bits; - $enc{caller()} = $_[1] if $_[1]; } sub unimport { @@ -29,19 +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 a Perl scalar to/from UTF-8. - $num_octets = utf8::upgrade($string); - $success = utf8::downgrade($string[, FAIL_OK]); + # Convert the internal representation of a Perl scalar to/from UTF-8. - # Change the native bytes of a Perl scalar to/from UTF-8 bytes. - utf8::encode($string); - utf8::decode($string); + $num_octets = utf8::upgrade($string); + $success = utf8::downgrade($string[, $fail_ok]); - $flag = utf8::is_utf8(STRING); # since Perl 5.8.1 - $flag = utf8::valid(STRING); + # Change each character of a Perl scalar to/from a series of + # characters that represent the UTF-8 bytes of each original character. + + utf8::encode($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 @@ -93,15 +103,16 @@ C. 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. +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 octet sequence in the native encoding -(Latin-1 or EBCDIC) to the equivalent character sequence in I. -I<$string> already encoded as characters does no harm. Returns the +Converts in-place the internal representation of the string from an octet +sequence in the native encoding (Latin-1 or EBCDIC) to I. The +logical character sequence itself is unchanged. If I<$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 @@ -111,17 +122,19 @@ B Therefore Encode is recommended for the general purposes; see also L. -=item * $success = utf8::downgrade($string[, FAIL_OK]) +=item * C<$success = utf8::downgrade($string[, $fail_ok])> -Converts in-place the internal octet sequence in I to the -equivalent octet sequence in the native encoding (Latin-1 or EBCDIC). -I<$string> already encoded as native 8 bit does no harm. Can be used to +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<$string> is already stored as native 8 bit, then this is a no-op. Can +be used to make sure that the UTF-8 flag is off, e.g. when you want to make sure that the substr() or length() function works with the usually faster byte algorithm. Fails if the original I sequence cannot be represented in the -native 8 bit encoding. On failure dies or, if the value of C is +native 8 bit encoding. On failure dies or, if the value of I<$fail_ok> is true, returns false. Returns true on success. @@ -130,39 +143,78 @@ B Therefore Encode is recommended for the general purposes; see also L. -=item * utf8::encode($string) +=item * C Converts in-place the character sequence to the corresponding octet -sequence in I. The UTF8 flag is turned off, so that after this -operation, the string is a byte string. Returns nothing. +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 * $success = utf8::decode($string) +=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, $a + # is unchanged and the function returns FALSE. -Attempts to convert in-place the octet sequence in I to the -corresponding character sequence. The UTF-8 flag is turned on only if -the source string contains multiple-byte I characters. If -I<$string> is invalid as I, returns false; otherwise returns -true. +(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 * $flag = utf8::is_utf8(STRING) +=item * C<$unicode = utf8::native_to_unicode($code_point)> + +This takes an unsigned integer (which represents the ordinal number of a +character (or a code point) on the platform the program is being run on) and +returns its Unicode equivalent value. Since ASCII platforms natively use the +Unicode code points, this function returns its input on them. On EBCDIC +platforms it converts from EBCIDC to Unicode. + +A meaningless value will currently be returned if the input is not an unsigned +integer. + +=item * C<$native = utf8::unicode_to_native($code_point)> + +This is the inverse of C, converting the other +direction. Again, on ASCII platforms, this returns its input, but on EBCDIC +platforms it will find the native platform code point, given any Unicode one. + +A meaningless value will currently be returned if the input is not an unsigned +integer. + +=item * C<$flag = utf8::is_utf8($string)> -(Since Perl 5.8.1) Test whether STRING is in UTF-8 internally. -Functionally the same as Encode::is_utf8(). +(Since Perl 5.8.1) Test whether I<$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($string)> -[INTERNAL] Test whether STRING is in a consistent state regarding -UTF-8. Will return true is well-formed UTF-8 and has the UTF-8 flag -on B if string is held as bytes (both these states are 'consistent'). -Main reason for this routine is to allow Perl's testsuite to check +[INTERNAL] Test whether I<$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.