| 1 | .\" Automatically generated by Pod::Man v1.37, Pod::Parser v1.32 |
| 2 | .\" |
| 3 | .\" Standard preamble: |
| 4 | .\" ======================================================================== |
| 5 | .de Sh \" Subsection heading |
| 6 | .br |
| 7 | .if t .Sp |
| 8 | .ne 5 |
| 9 | .PP |
| 10 | \fB\\$1\fR |
| 11 | .PP |
| 12 | .. |
| 13 | .de Sp \" Vertical space (when we can't use .PP) |
| 14 | .if t .sp .5v |
| 15 | .if n .sp |
| 16 | .. |
| 17 | .de Vb \" Begin verbatim text |
| 18 | .ft CW |
| 19 | .nf |
| 20 | .ne \\$1 |
| 21 | .. |
| 22 | .de Ve \" End verbatim text |
| 23 | .ft R |
| 24 | .fi |
| 25 | .. |
| 26 | .\" Set up some character translations and predefined strings. \*(-- will |
| 27 | .\" give an unbreakable dash, \*(PI will give pi, \*(L" will give a left |
| 28 | .\" double quote, and \*(R" will give a right double quote. | will give a |
| 29 | .\" real vertical bar. \*(C+ will give a nicer C++. Capital omega is used to |
| 30 | .\" do unbreakable dashes and therefore won't be available. \*(C` and \*(C' |
| 31 | .\" expand to `' in nroff, nothing in troff, for use with C<>. |
| 32 | .tr \(*W-|\(bv\*(Tr |
| 33 | .ds C+ C\v'-.1v'\h'-1p'\s-2+\h'-1p'+\s0\v'.1v'\h'-1p' |
| 34 | .ie n \{\ |
| 35 | . ds -- \(*W- |
| 36 | . ds PI pi |
| 37 | . if (\n(.H=4u)&(1m=24u) .ds -- \(*W\h'-12u'\(*W\h'-12u'-\" diablo 10 pitch |
| 38 | . if (\n(.H=4u)&(1m=20u) .ds -- \(*W\h'-12u'\(*W\h'-8u'-\" diablo 12 pitch |
| 39 | . ds L" "" |
| 40 | . ds R" "" |
| 41 | . ds C` "" |
| 42 | . ds C' "" |
| 43 | 'br\} |
| 44 | .el\{\ |
| 45 | . ds -- \|\(em\| |
| 46 | . ds PI \(*p |
| 47 | . ds L" `` |
| 48 | . ds R" '' |
| 49 | 'br\} |
| 50 | .\" |
| 51 | .\" If the F register is turned on, we'll generate index entries on stderr for |
| 52 | .\" titles (.TH), headers (.SH), subsections (.Sh), items (.Ip), and index |
| 53 | .\" entries marked with X<> in POD. Of course, you'll have to process the |
| 54 | .\" output yourself in some meaningful fashion. |
| 55 | .if \nF \{\ |
| 56 | . de IX |
| 57 | . tm Index:\\$1\t\\n%\t"\\$2" |
| 58 | .. |
| 59 | . nr % 0 |
| 60 | . rr F |
| 61 | .\} |
| 62 | .\" |
| 63 | .\" For nroff, turn off justification. Always turn off hyphenation; it makes |
| 64 | .\" way too many mistakes in technical documents. |
| 65 | .hy 0 |
| 66 | .if n .na |
| 67 | .\" |
| 68 | .\" Accent mark definitions (@(#)ms.acc 1.5 88/02/08 SMI; from UCB 4.2). |
| 69 | .\" Fear. Run. Save yourself. No user-serviceable parts. |
| 70 | . \" fudge factors for nroff and troff |
| 71 | .if n \{\ |
| 72 | . ds #H 0 |
| 73 | . ds #V .8m |
| 74 | . ds #F .3m |
| 75 | . ds #[ \f1 |
| 76 | . ds #] \fP |
| 77 | .\} |
| 78 | .if t \{\ |
| 79 | . ds #H ((1u-(\\\\n(.fu%2u))*.13m) |
| 80 | . ds #V .6m |
| 81 | . ds #F 0 |
| 82 | . ds #[ \& |
| 83 | . ds #] \& |
| 84 | .\} |
| 85 | . \" simple accents for nroff and troff |
| 86 | .if n \{\ |
| 87 | . ds ' \& |
| 88 | . ds ` \& |
| 89 | . ds ^ \& |
| 90 | . ds , \& |
| 91 | . ds ~ ~ |
| 92 | . ds / |
| 93 | .\} |
| 94 | .if t \{\ |
| 95 | . ds ' \\k:\h'-(\\n(.wu*8/10-\*(#H)'\'\h"|\\n:u" |
| 96 | . ds ` \\k:\h'-(\\n(.wu*8/10-\*(#H)'\`\h'|\\n:u' |
| 97 | . ds ^ \\k:\h'-(\\n(.wu*10/11-\*(#H)'^\h'|\\n:u' |
| 98 | . ds , \\k:\h'-(\\n(.wu*8/10)',\h'|\\n:u' |
| 99 | . ds ~ \\k:\h'-(\\n(.wu-\*(#H-.1m)'~\h'|\\n:u' |
| 100 | . ds / \\k:\h'-(\\n(.wu*8/10-\*(#H)'\z\(sl\h'|\\n:u' |
| 101 | .\} |
| 102 | . \" troff and (daisy-wheel) nroff accents |
| 103 | .ds : \\k:\h'-(\\n(.wu*8/10-\*(#H+.1m+\*(#F)'\v'-\*(#V'\z.\h'.2m+\*(#F'.\h'|\\n:u'\v'\*(#V' |
| 104 | .ds 8 \h'\*(#H'\(*b\h'-\*(#H' |
| 105 | .ds o \\k:\h'-(\\n(.wu+\w'\(de'u-\*(#H)/2u'\v'-.3n'\*(#[\z\(de\v'.3n'\h'|\\n:u'\*(#] |
| 106 | .ds d- \h'\*(#H'\(pd\h'-\w'~'u'\v'-.25m'\f2\(hy\fP\v'.25m'\h'-\*(#H' |
| 107 | .ds D- D\\k:\h'-\w'D'u'\v'-.11m'\z\(hy\v'.11m'\h'|\\n:u' |
| 108 | .ds th \*(#[\v'.3m'\s+1I\s-1\v'-.3m'\h'-(\w'I'u*2/3)'\s-1o\s+1\*(#] |
| 109 | .ds Th \*(#[\s+2I\s-2\h'-\w'I'u*3/5'\v'-.3m'o\v'.3m'\*(#] |
| 110 | .ds ae a\h'-(\w'a'u*4/10)'e |
| 111 | .ds Ae A\h'-(\w'A'u*4/10)'E |
| 112 | . \" corrections for vroff |
| 113 | .if v .ds ~ \\k:\h'-(\\n(.wu*9/10-\*(#H)'\s-2\u~\d\s+2\h'|\\n:u' |
| 114 | .if v .ds ^ \\k:\h'-(\\n(.wu*10/11-\*(#H)'\v'-.4m'^\v'.4m'\h'|\\n:u' |
| 115 | . \" for low resolution devices (crt and lpr) |
| 116 | .if \n(.H>23 .if \n(.V>19 \ |
| 117 | \{\ |
| 118 | . ds : e |
| 119 | . ds 8 ss |
| 120 | . ds o a |
| 121 | . ds d- d\h'-1'\(ga |
| 122 | . ds D- D\h'-1'\(hy |
| 123 | . ds th \o'bp' |
| 124 | . ds Th \o'LP' |
| 125 | . ds ae ae |
| 126 | . ds Ae AE |
| 127 | .\} |
| 128 | .rm #[ #] #H #V #F C |
| 129 | .\" ======================================================================== |
| 130 | .\" |
| 131 | .IX Title "utf8 3" |
| 132 | .TH utf8 3 "2001-09-21" "perl v5.8.8" "Perl Programmers Reference Guide" |
| 133 | .SH "NAME" |
| 134 | utf8 \- Perl pragma to enable/disable UTF\-8 (or UTF\-EBCDIC) in source code |
| 135 | .SH "SYNOPSIS" |
| 136 | .IX Header "SYNOPSIS" |
| 137 | .Vb 2 |
| 138 | \& use utf8; |
| 139 | \& no utf8; |
| 140 | .Ve |
| 141 | .PP |
| 142 | .Vb 3 |
| 143 | \& # Convert a Perl scalar to/from UTF-8. |
| 144 | \& $num_octets = utf8::upgrade($string); |
| 145 | \& $success = utf8::downgrade($string[, FAIL_OK]); |
| 146 | .Ve |
| 147 | .PP |
| 148 | .Vb 3 |
| 149 | \& # Change the native bytes of a Perl scalar to/from UTF-8 bytes. |
| 150 | \& utf8::encode($string); |
| 151 | \& utf8::decode($string); |
| 152 | .Ve |
| 153 | .PP |
| 154 | .Vb 2 |
| 155 | \& $flag = utf8::is_utf8(STRING); # since Perl 5.8.1 |
| 156 | \& $flag = utf8::valid(STRING); |
| 157 | .Ve |
| 158 | .SH "DESCRIPTION" |
| 159 | .IX Header "DESCRIPTION" |
| 160 | The \f(CW\*(C`use utf8\*(C'\fR pragma tells the Perl parser to allow \s-1UTF\-8\s0 in the |
| 161 | program text in the current lexical scope (allow UTF-EBCDIC on \s-1EBCDIC\s0 based |
| 162 | platforms). The \f(CW\*(C`no utf8\*(C'\fR pragma tells Perl to switch back to treating |
| 163 | the source text as literal bytes in the current lexical scope. |
| 164 | .PP |
| 165 | This pragma is primarily a compatibility device. Perl versions |
| 166 | earlier than 5.6 allowed arbitrary bytes in source code, whereas |
| 167 | in future we would like to standardize on the \s-1UTF\-8\s0 encoding for |
| 168 | source text. |
| 169 | .PP |
| 170 | \&\fBDo not use this pragma for anything else than telling Perl that your |
| 171 | script is written in \s-1UTF\-8\s0.\fR The utility functions described below are |
| 172 | useful for their own purposes, but they are not really part of the |
| 173 | \&\*(L"pragmatic\*(R" effect. |
| 174 | .PP |
| 175 | Until \s-1UTF\-8\s0 becomes the default format for source text, either this |
| 176 | pragma or the encoding pragma should be used to recognize \s-1UTF\-8\s0 |
| 177 | in the source. When \s-1UTF\-8\s0 becomes the standard source format, this |
| 178 | pragma will effectively become a no\-op. For convenience in what |
| 179 | follows the term \fIUTF-X\fR is used to refer to \s-1UTF\-8\s0 on \s-1ASCII\s0 and \s-1ISO\s0 |
| 180 | Latin based platforms and UTF-EBCDIC on \s-1EBCDIC\s0 based platforms. |
| 181 | .PP |
| 182 | See also the effects of the \f(CW\*(C`\-C\*(C'\fR switch and its cousin, the |
| 183 | \&\f(CW$ENV{PERL_UNICODE}\fR, in perlrun. |
| 184 | .PP |
| 185 | Enabling the \f(CW\*(C`utf8\*(C'\fR pragma has the following effect: |
| 186 | .IP "\(bu" 4 |
| 187 | Bytes in the source text that have their high-bit set will be treated |
| 188 | as being part of a literal \s-1UTF\-8\s0 character. This includes most |
| 189 | literals such as identifier names, string constants, and constant |
| 190 | regular expression patterns. |
| 191 | .Sp |
| 192 | On \s-1EBCDIC\s0 platforms characters in the Latin 1 character set are |
| 193 | treated as being part of a literal UTF-EBCDIC character. |
| 194 | .PP |
| 195 | Note that if you have bytes with the eighth bit on in your script |
| 196 | (for example embedded Latin\-1 in your string literals), \f(CW\*(C`use utf8\*(C'\fR |
| 197 | will be unhappy since the bytes are most probably not well-formed |
| 198 | \&\s-1UTF\-8\s0. If you want to have such bytes and use utf8, you can disable |
| 199 | utf8 until the end the block (or file, if at top level) by \f(CW\*(C`no utf8;\*(C'\fR. |
| 200 | .PP |
| 201 | If you want to automatically upgrade your 8\-bit legacy bytes to \s-1UTF\-8\s0, |
| 202 | use the encoding pragma instead of this pragma. For example, if |
| 203 | you want to implicitly upgrade your \s-1ISO\s0 8859\-1 (Latin\-1) bytes to \s-1UTF\-8\s0 |
| 204 | as used in e.g. \f(CW\*(C`chr()\*(C'\fR and \f(CW\*(C`\ex{...}\*(C'\fR, try this: |
| 205 | .PP |
| 206 | .Vb 3 |
| 207 | \& use encoding "latin-1"; |
| 208 | \& my $c = chr(0xc4); |
| 209 | \& my $x = "\ex{c5}"; |
| 210 | .Ve |
| 211 | .PP |
| 212 | In case you are wondering: yes, \f(CW\*(C`use encoding 'utf8';\*(C'\fR works much |
| 213 | the same as \f(CW\*(C`use utf8;\*(C'\fR. |
| 214 | .Sh "Utility functions" |
| 215 | .IX Subsection "Utility functions" |
| 216 | The following functions are defined in the \f(CW\*(C`utf8::\*(C'\fR package by the |
| 217 | Perl core. You do not need to say \f(CW\*(C`use utf8\*(C'\fR to use these and in fact |
| 218 | you should not say that unless you really want to have \s-1UTF\-8\s0 source code. |
| 219 | .ie n .IP "* $num_octets = utf8::upgrade($string)" 4 |
| 220 | .el .IP "* \f(CW$num_octets\fR = utf8::upgrade($string)" 4 |
| 221 | .IX Item "$num_octets = utf8::upgrade($string)" |
| 222 | Converts in-place the octet sequence in the native encoding |
| 223 | (Latin\-1 or \s-1EBCDIC\s0) to the equivalent character sequence in \fIUTF-X\fR. |
| 224 | \&\fI$string\fR already encoded as characters does no harm. |
| 225 | Returns the number of octets necessary to represent the string as \fIUTF-X\fR. |
| 226 | Can be used to make sure that the \s-1UTF\-8\s0 flag is on, |
| 227 | so that \f(CW\*(C`\ew\*(C'\fR or \f(CW\*(C`lc()\*(C'\fR work as Unicode on strings |
| 228 | containing characters in the range 0x80\-0xFF (on \s-1ASCII\s0 and |
| 229 | derivatives). |
| 230 | .Sp |
| 231 | \&\fBNote that this function does not handle arbitrary encodings.\fR |
| 232 | Therefore \fIEncode.pm\fR is recommended for the general purposes. |
| 233 | .Sp |
| 234 | Affected by the encoding pragma. |
| 235 | .ie n .IP "* $success = utf8::downgrade($string[, \s-1FAIL_OK\s0])" 4 |
| 236 | .el .IP "* \f(CW$success\fR = utf8::downgrade($string[, \s-1FAIL_OK\s0])" 4 |
| 237 | .IX Item "$success = utf8::downgrade($string[, FAIL_OK])" |
| 238 | Converts in-place the character sequence in \fIUTF-X\fR |
| 239 | to the equivalent octet sequence in the native encoding (Latin\-1 or \s-1EBCDIC\s0). |
| 240 | \&\fI$string\fR already encoded as octets does no harm. |
| 241 | Returns true on success. On failure dies or, if the value of |
| 242 | \&\f(CW\*(C`FAIL_OK\*(C'\fR is true, returns false. |
| 243 | Can be used to make sure that the \s-1UTF\-8\s0 flag is off, |
| 244 | e.g. when you want to make sure that the \fIsubstr()\fR or \fIlength()\fR function |
| 245 | works with the usually faster byte algorithm. |
| 246 | .Sp |
| 247 | \&\fBNote that this function does not handle arbitrary encodings.\fR |
| 248 | Therefore \fIEncode.pm\fR is recommended for the general purposes. |
| 249 | .Sp |
| 250 | \&\fBNot\fR affected by the encoding pragma. |
| 251 | .Sp |
| 252 | \&\fB\s-1NOTE:\s0\fR this function is experimental and may change |
| 253 | or be removed without notice. |
| 254 | .IP "* utf8::encode($string)" 4 |
| 255 | .IX Item "utf8::encode($string)" |
| 256 | Converts in-place the character sequence to the corresponding octet sequence |
| 257 | in \fIUTF-X\fR. The \s-1UTF\-8\s0 flag is turned off. Returns nothing. |
| 258 | .Sp |
| 259 | \&\fBNote that this function does not handle arbitrary encodings.\fR |
| 260 | Therefore \fIEncode.pm\fR is recommended for the general purposes. |
| 261 | .IP "* utf8::decode($string)" 4 |
| 262 | .IX Item "utf8::decode($string)" |
| 263 | Attempts to convert in-place the octet sequence in \fIUTF-X\fR |
| 264 | to the corresponding character sequence. The \s-1UTF\-8\s0 flag is turned on |
| 265 | only if the source string contains multiple-byte \fIUTF-X\fR characters. |
| 266 | If \fI$string\fR is invalid as \fIUTF-X\fR, returns false; otherwise returns true. |
| 267 | .Sp |
| 268 | \&\fBNote that this function does not handle arbitrary encodings.\fR |
| 269 | Therefore \fIEncode.pm\fR is recommended for the general purposes. |
| 270 | .Sp |
| 271 | \&\fB\s-1NOTE:\s0\fR this function is experimental and may change |
| 272 | or be removed without notice. |
| 273 | .ie n .IP "* $flag = utf8::is_utf8(\s-1STRING\s0)" 4 |
| 274 | .el .IP "* \f(CW$flag\fR = utf8::is_utf8(\s-1STRING\s0)" 4 |
| 275 | .IX Item "$flag = utf8::is_utf8(STRING)" |
| 276 | (Since Perl 5.8.1) Test whether \s-1STRING\s0 is in \s-1UTF\-8\s0. Functionally |
| 277 | the same as \fIEncode::is_utf8()\fR. |
| 278 | .ie n .IP "* $flag = utf8::valid(\s-1STRING\s0)" 4 |
| 279 | .el .IP "* \f(CW$flag\fR = utf8::valid(\s-1STRING\s0)" 4 |
| 280 | .IX Item "$flag = utf8::valid(STRING)" |
| 281 | [\s-1INTERNAL\s0] Test whether \s-1STRING\s0 is in a consistent state regarding |
| 282 | \&\s-1UTF\-8\s0. Will return true is well-formed \s-1UTF\-8\s0 and has the \s-1UTF\-8\s0 flag |
| 283 | on \fBor\fR if string is held as bytes (both these states are 'consistent'). |
| 284 | Main reason for this routine is to allow Perl's testsuite to check |
| 285 | that operations have left strings in a consistent state. You most |
| 286 | probably want to use \fIutf8::is_utf8()\fR instead. |
| 287 | .PP |
| 288 | \&\f(CW\*(C`utf8::encode\*(C'\fR is like \f(CW\*(C`utf8::upgrade\*(C'\fR, but the \s-1UTF8\s0 flag is |
| 289 | cleared. See perlunicode for more on the \s-1UTF8\s0 flag and the C \s-1API\s0 |
| 290 | functions \f(CW\*(C`sv_utf8_upgrade\*(C'\fR, \f(CW\*(C`sv_utf8_downgrade\*(C'\fR, \f(CW\*(C`sv_utf8_encode\*(C'\fR, |
| 291 | and \f(CW\*(C`sv_utf8_decode\*(C'\fR, which are wrapped by the Perl functions |
| 292 | \&\f(CW\*(C`utf8::upgrade\*(C'\fR, \f(CW\*(C`utf8::downgrade\*(C'\fR, \f(CW\*(C`utf8::encode\*(C'\fR and |
| 293 | \&\f(CW\*(C`utf8::decode\*(C'\fR. Note that in the Perl 5.8.0 and 5.8.1 implementation |
| 294 | the functions utf8::is_utf8, utf8::valid, utf8::encode, utf8::decode, |
| 295 | utf8::upgrade, and utf8::downgrade are always available, without a |
| 296 | \&\f(CW\*(C`require utf8\*(C'\fR statement\*(-- this may change in future releases. |
| 297 | .SH "BUGS" |
| 298 | .IX Header "BUGS" |
| 299 | One can have Unicode in identifier names, but not in package/class or |
| 300 | subroutine names. While some limited functionality towards this does |
| 301 | exist as of Perl 5.8.0, that is more accidental than designed; use of |
| 302 | Unicode for the said purposes is unsupported. |
| 303 | .PP |
| 304 | One reason of this unfinishedness is its (currently) inherent |
| 305 | unportability: since both package names and subroutine names may need |
| 306 | to be mapped to file and directory names, the Unicode capability of |
| 307 | the filesystem becomes important\*(-- and there unfortunately aren't |
| 308 | portable answers. |
| 309 | .SH "SEE ALSO" |
| 310 | .IX Header "SEE ALSO" |
| 311 | perluniintro, encoding, perlrun, bytes, perlunicode |