X-Git-Url: http://git.shadowcat.co.uk/gitweb/gitweb.cgi?a=blobdiff_plain;f=lib%2Futf8.pm;h=56c991bef9ad5f96988d0109c10d0a40404e422a;hb=b1fbf5c3d1dc6dd7934002da04dede2ae2e3ef65;hp=f357dbf9b929b4ccdcffd135a453d8dab051adb6;hpb=63708e74df7f3113a5e81bbb8ac68dc55f350a2d;p=p5sagit%2Fp5-mst-13.2.git diff --git a/lib/utf8.pm b/lib/utf8.pm index f357dbf..56c991b 100644 --- a/lib/utf8.pm +++ b/lib/utf8.pm @@ -2,7 +2,7 @@ package utf8; $utf8::hint_bits = 0x00800000; -our $VERSION = '1.02'; +our $VERSION = '1.06'; sub import { $^H |= $utf8::hint_bits; @@ -16,6 +16,7 @@ sub unimport { sub AUTOLOAD { require "utf8_heavy.pl"; goto &$AUTOLOAD if defined &$AUTOLOAD; + require Carp; Carp::croak("Undefined subroutine $AUTOLOAD called"); } @@ -31,9 +32,11 @@ utf8 - Perl pragma to enable/disable UTF-8 (or UTF-EBCDIC) in source code use utf8; no utf8; + # Convert a Perl scalar to/from UTF-8. $num_octets = utf8::upgrade($string); $success = utf8::downgrade($string[, FAIL_OK]); + # Change the native bytes of a Perl scalar to/from UTF-8 bytes. utf8::encode($string); utf8::decode($string); @@ -52,13 +55,21 @@ 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. +B The utility functions described below are +useful for their own purposes, but they are not really part of the +"pragmatic" effect. + Until UTF-8 becomes the default format for source text, either this -pragma or the L pragma should be used to recognize UTF-8 +pragma or the L pragma should be used to recognize UTF-8 in the source. 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 platforms and UTF-EBCDIC on EBCDIC based platforms. +See also the effects of the C<-C> switch and its cousin, the +C<$ENV{PERL_UNICODE}>, in L. + Enabling the C pragma has the following effect: =over 4 @@ -82,7 +93,7 @@ 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. If you want to automatically upgrade your 8-bit legacy bytes to UTF-8, -use the L pragma instead of this pragma. For example, if +use the L pragma instead of this pragma. For example, if you want to implicitly upgrade your ISO 8859-1 (Latin-1) bytes to UTF-8 as used in e.g. C and C<\x{...}>, try this: @@ -97,46 +108,65 @@ the same as 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 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) -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 (oon ASCII and -derivatives). Note that this should not be used to convert a legacy -byte encoding to Unicode: use Encode for that. Affected by the -encoding pragma. +Converts in-place the 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 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 I is recommended for the general purposes. + +Affected by the encoding pragma. =item * $success = utf8::downgrade($string[, FAIL_OK]) -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. +Converts in-place the character sequence in I +to the equivalent octet sequence in the native encoding (Latin-1 or EBCDIC). +I<$string> already encoded as octets does no harm. +Returns true on success. On failure dies or, if the value of +C is true, returns false. +Can be used to make sure that the UTF-8 flag is off, +e.g. when you want to make sure that the substr() or length() function +works with the usually faster byte algorithm. + +B +Therefore I is recommended for the general purposes. + +B affected by the encoding pragma. + +B this function is experimental and may change +or be removed without notice. =item * utf8::encode($string) -Converts (in-place) I<$string> from logical characters to octet -sequence representing it in Perl's I encoding. Returns -nothing. Same as Encode::encode_utf8(). Note that this should not be -used to convert a legacy byte encoding to Unicode: use Encode for -that. +Converts in-place the character sequence to the corresponding octet sequence +in I. The UTF-8 flag is turned off. Returns nothing. + +B +Therefore I is recommended for the general purposes. =item * utf8::decode($string) -Attempts to convert I<$string> in-place from Perl's I encoding -into logical characters. Returns nothing. Same as Encode::decode_utf8(). -Note that this should not be used to convert Unicode back to a legacy -byte encoding: use Encode for that. +Attempts to convert in-place the octet sequence in I +to the corresponding character sequence. The UTF-8 flag is turned on +only if the source string contains multiple-byte I characters. +If I<$string> is invalid as I, returns false; otherwise returns true. + +B +Therefore I is recommended for the general purposes. + +B this function is experimental and may change +or be removed without notice. =item * $flag = utf8::is_utf8(STRING) @@ -179,6 +209,6 @@ portable answers. =head1 SEE ALSO -L, L, L, L +L, L, L, L, L =cut