| 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 "PERLLOCALE 1" |
| 132 | .TH PERLLOCALE 1 "2006-01-07" "perl v5.8.8" "Perl Programmers Reference Guide" |
| 133 | .SH "NAME" |
| 134 | perllocale \- Perl locale handling (internationalization and localization) |
| 135 | .SH "DESCRIPTION" |
| 136 | .IX Header "DESCRIPTION" |
| 137 | Perl supports language-specific notions of data such as \*(L"is this |
| 138 | a letter\*(R", \*(L"what is the uppercase equivalent of this letter\*(R", and |
| 139 | \&\*(L"which of these letters comes first\*(R". These are important issues, |
| 140 | especially for languages other than English\*(--but also for English: it |
| 141 | would be nai\*:ve to imagine that \f(CW\*(C`A\-Za\-z\*(C'\fR defines all the \*(L"letters\*(R" |
| 142 | needed to write in English. Perl is also aware that some character other |
| 143 | than '.' may be preferred as a decimal point, and that output date |
| 144 | representations may be language\-specific. The process of making an |
| 145 | application take account of its users' preferences in such matters is |
| 146 | called \fBinternationalization\fR (often abbreviated as \fBi18n\fR); telling |
| 147 | such an application about a particular set of preferences is known as |
| 148 | \&\fBlocalization\fR (\fBl10n\fR). |
| 149 | .PP |
| 150 | Perl can understand language-specific data via the standardized (\s-1ISO\s0 C, |
| 151 | \&\s-1XPG4\s0, \s-1POSIX\s0 1.c) method called \*(L"the locale system\*(R". The locale system is |
| 152 | controlled per application using one pragma, one function call, and |
| 153 | several environment variables. |
| 154 | .PP |
| 155 | \&\fB\s-1NOTE\s0\fR: This feature is new in Perl 5.004, and does not apply unless an |
| 156 | application specifically requests it\*(--see \*(L"Backward compatibility\*(R". |
| 157 | The one exception is that \fIwrite()\fR now \fBalways\fR uses the current locale |
| 158 | \&\- see \*(L"\s-1NOTES\s0\*(R". |
| 159 | .SH "PREPARING TO USE LOCALES" |
| 160 | .IX Header "PREPARING TO USE LOCALES" |
| 161 | If Perl applications are to understand and present your data |
| 162 | correctly according a locale of your choice, \fBall\fR of the following |
| 163 | must be true: |
| 164 | .IP "\(bu" 4 |
| 165 | \&\fBYour operating system must support the locale system\fR. If it does, |
| 166 | you should find that the \fIsetlocale()\fR function is a documented part of |
| 167 | its C library. |
| 168 | .IP "\(bu" 4 |
| 169 | \&\fBDefinitions for locales that you use must be installed\fR. You, or |
| 170 | your system administrator, must make sure that this is the case. The |
| 171 | available locales, the location in which they are kept, and the manner |
| 172 | in which they are installed all vary from system to system. Some systems |
| 173 | provide only a few, hard-wired locales and do not allow more to be |
| 174 | added. Others allow you to add \*(L"canned\*(R" locales provided by the system |
| 175 | supplier. Still others allow you or the system administrator to define |
| 176 | and add arbitrary locales. (You may have to ask your supplier to |
| 177 | provide canned locales that are not delivered with your operating |
| 178 | system.) Read your system documentation for further illumination. |
| 179 | .IP "\(bu" 4 |
| 180 | \&\fBPerl must believe that the locale system is supported\fR. If it does, |
| 181 | \&\f(CW\*(C`perl \-V:d_setlocale\*(C'\fR will say that the value for \f(CW\*(C`d_setlocale\*(C'\fR is |
| 182 | \&\f(CW\*(C`define\*(C'\fR. |
| 183 | .PP |
| 184 | If you want a Perl application to process and present your data |
| 185 | according to a particular locale, the application code should include |
| 186 | the \f(CW\*(C`use\ locale\*(C'\fR pragma (see \*(L"The use locale pragma\*(R") where |
| 187 | appropriate, and \fBat least one\fR of the following must be true: |
| 188 | .IP "\(bu" 4 |
| 189 | \&\fBThe locale-determining environment variables (see \*(L"\s-1ENVIRONMENT\s0\*(R") |
| 190 | must be correctly set up\fR at the time the application is started, either |
| 191 | by yourself or by whoever set up your system account. |
| 192 | .IP "\(bu" 4 |
| 193 | \&\fBThe application must set its own locale\fR using the method described in |
| 194 | \&\*(L"The setlocale function\*(R". |
| 195 | .SH "USING LOCALES" |
| 196 | .IX Header "USING LOCALES" |
| 197 | .Sh "The use locale pragma" |
| 198 | .IX Subsection "The use locale pragma" |
| 199 | By default, Perl ignores the current locale. The \f(CW\*(C`use\ locale\*(C'\fR |
| 200 | pragma tells Perl to use the current locale for some operations: |
| 201 | .IP "\(bu" 4 |
| 202 | \&\fBThe comparison operators\fR (\f(CW\*(C`lt\*(C'\fR, \f(CW\*(C`le\*(C'\fR, \f(CW\*(C`cmp\*(C'\fR, \f(CW\*(C`ge\*(C'\fR, and \f(CW\*(C`gt\*(C'\fR) and |
| 203 | the \s-1POSIX\s0 string collation functions \fIstrcoll()\fR and \fIstrxfrm()\fR use |
| 204 | \&\f(CW\*(C`LC_COLLATE\*(C'\fR. \fIsort()\fR is also affected if used without an |
| 205 | explicit comparison function, because it uses \f(CW\*(C`cmp\*(C'\fR by default. |
| 206 | .Sp |
| 207 | \&\fBNote:\fR \f(CW\*(C`eq\*(C'\fR and \f(CW\*(C`ne\*(C'\fR are unaffected by locale: they always |
| 208 | perform a char-by-char comparison of their scalar operands. What's |
| 209 | more, if \f(CW\*(C`cmp\*(C'\fR finds that its operands are equal according to the |
| 210 | collation sequence specified by the current locale, it goes on to |
| 211 | perform a char-by-char comparison, and only returns \fI0\fR (equal) if the |
| 212 | operands are char-for-char identical. If you really want to know whether |
| 213 | two strings\*(--which \f(CW\*(C`eq\*(C'\fR and \f(CW\*(C`cmp\*(C'\fR may consider different\*(--are equal |
| 214 | as far as collation in the locale is concerned, see the discussion in |
| 215 | \&\*(L"Category \s-1LC_COLLATE:\s0 Collation\*(R". |
| 216 | .IP "\(bu" 4 |
| 217 | \&\fBRegular expressions and case-modification functions\fR (\fIuc()\fR, \fIlc()\fR, |
| 218 | \&\fIucfirst()\fR, and \fIlcfirst()\fR) use \f(CW\*(C`LC_CTYPE\*(C'\fR |
| 219 | .IP "\(bu" 4 |
| 220 | \&\fBThe formatting functions\fR (\fIprintf()\fR, \fIsprintf()\fR and \fIwrite()\fR) use |
| 221 | \&\f(CW\*(C`LC_NUMERIC\*(C'\fR |
| 222 | .IP "\(bu" 4 |
| 223 | \&\fBThe \s-1POSIX\s0 date formatting function\fR (\fIstrftime()\fR) uses \f(CW\*(C`LC_TIME\*(C'\fR. |
| 224 | .PP |
| 225 | \&\f(CW\*(C`LC_COLLATE\*(C'\fR, \f(CW\*(C`LC_CTYPE\*(C'\fR, and so on, are discussed further in |
| 226 | \&\*(L"\s-1LOCALE\s0 \s-1CATEGORIES\s0\*(R". |
| 227 | .PP |
| 228 | The default behavior is restored with the \f(CW\*(C`no\ locale\*(C'\fR pragma, or |
| 229 | upon reaching the end of block enclosing \f(CW\*(C`use locale\*(C'\fR. |
| 230 | .PP |
| 231 | The string result of any operation that uses locale |
| 232 | information is tainted, as it is possible for a locale to be |
| 233 | untrustworthy. See \*(L"\s-1SECURITY\s0\*(R". |
| 234 | .Sh "The setlocale function" |
| 235 | .IX Subsection "The setlocale function" |
| 236 | You can switch locales as often as you wish at run time with the |
| 237 | \&\fIPOSIX::setlocale()\fR function: |
| 238 | .PP |
| 239 | .Vb 2 |
| 240 | \& # This functionality not usable prior to Perl 5.004 |
| 241 | \& require 5.004; |
| 242 | .Ve |
| 243 | .PP |
| 244 | .Vb 4 |
| 245 | \& # Import locale-handling tool set from POSIX module. |
| 246 | \& # This example uses: setlocale -- the function call |
| 247 | \& # LC_CTYPE -- explained below |
| 248 | \& use POSIX qw(locale_h); |
| 249 | .Ve |
| 250 | .PP |
| 251 | .Vb 2 |
| 252 | \& # query and save the old locale |
| 253 | \& $old_locale = setlocale(LC_CTYPE); |
| 254 | .Ve |
| 255 | .PP |
| 256 | .Vb 2 |
| 257 | \& setlocale(LC_CTYPE, "fr_CA.ISO8859-1"); |
| 258 | \& # LC_CTYPE now in locale "French, Canada, codeset ISO 8859-1" |
| 259 | .Ve |
| 260 | .PP |
| 261 | .Vb 3 |
| 262 | \& setlocale(LC_CTYPE, ""); |
| 263 | \& # LC_CTYPE now reset to default defined by LC_ALL/LC_CTYPE/LANG |
| 264 | \& # environment variables. See below for documentation. |
| 265 | .Ve |
| 266 | .PP |
| 267 | .Vb 2 |
| 268 | \& # restore the old locale |
| 269 | \& setlocale(LC_CTYPE, $old_locale); |
| 270 | .Ve |
| 271 | .PP |
| 272 | The first argument of \fIsetlocale()\fR gives the \fBcategory\fR, the second the |
| 273 | \&\fBlocale\fR. The category tells in what aspect of data processing you |
| 274 | want to apply locale-specific rules. Category names are discussed in |
| 275 | \&\*(L"\s-1LOCALE\s0 \s-1CATEGORIES\s0\*(R" and \*(L"\s-1ENVIRONMENT\s0\*(R". The locale is the name of a |
| 276 | collection of customization information corresponding to a particular |
| 277 | combination of language, country or territory, and codeset. Read on for |
| 278 | hints on the naming of locales: not all systems name locales as in the |
| 279 | example. |
| 280 | .PP |
| 281 | If no second argument is provided and the category is something else |
| 282 | than \s-1LC_ALL\s0, the function returns a string naming the current locale |
| 283 | for the category. You can use this value as the second argument in a |
| 284 | subsequent call to \fIsetlocale()\fR. |
| 285 | .PP |
| 286 | If no second argument is provided and the category is \s-1LC_ALL\s0, the |
| 287 | result is implementation\-dependent. It may be a string of |
| 288 | concatenated locales names (separator also implementation\-dependent) |
| 289 | or a single locale name. Please consult your \fIsetlocale\fR\|(3) for |
| 290 | details. |
| 291 | .PP |
| 292 | If a second argument is given and it corresponds to a valid locale, |
| 293 | the locale for the category is set to that value, and the function |
| 294 | returns the now-current locale value. You can then use this in yet |
| 295 | another call to \fIsetlocale()\fR. (In some implementations, the return |
| 296 | value may sometimes differ from the value you gave as the second |
| 297 | argument\*(--think of it as an alias for the value you gave.) |
| 298 | .PP |
| 299 | As the example shows, if the second argument is an empty string, the |
| 300 | category's locale is returned to the default specified by the |
| 301 | corresponding environment variables. Generally, this results in a |
| 302 | return to the default that was in force when Perl started up: changes |
| 303 | to the environment made by the application after startup may or may not |
| 304 | be noticed, depending on your system's C library. |
| 305 | .PP |
| 306 | If the second argument does not correspond to a valid locale, the locale |
| 307 | for the category is not changed, and the function returns \fIundef\fR. |
| 308 | .PP |
| 309 | For further information about the categories, consult \fIsetlocale\fR\|(3). |
| 310 | .Sh "Finding locales" |
| 311 | .IX Subsection "Finding locales" |
| 312 | For locales available in your system, consult also \fIsetlocale\fR\|(3) to |
| 313 | see whether it leads to the list of available locales (search for the |
| 314 | \&\fI\s-1SEE\s0 \s-1ALSO\s0\fR section). If that fails, try the following command lines: |
| 315 | .PP |
| 316 | .Vb 1 |
| 317 | \& locale -a |
| 318 | .Ve |
| 319 | .PP |
| 320 | .Vb 1 |
| 321 | \& nlsinfo |
| 322 | .Ve |
| 323 | .PP |
| 324 | .Vb 1 |
| 325 | \& ls /usr/lib/nls/loc |
| 326 | .Ve |
| 327 | .PP |
| 328 | .Vb 1 |
| 329 | \& ls /usr/lib/locale |
| 330 | .Ve |
| 331 | .PP |
| 332 | .Vb 1 |
| 333 | \& ls /usr/lib/nls |
| 334 | .Ve |
| 335 | .PP |
| 336 | .Vb 1 |
| 337 | \& ls /usr/share/locale |
| 338 | .Ve |
| 339 | .PP |
| 340 | and see whether they list something resembling these |
| 341 | .PP |
| 342 | .Vb 7 |
| 343 | \& en_US.ISO8859-1 de_DE.ISO8859-1 ru_RU.ISO8859-5 |
| 344 | \& en_US.iso88591 de_DE.iso88591 ru_RU.iso88595 |
| 345 | \& en_US de_DE ru_RU |
| 346 | \& en de ru |
| 347 | \& english german russian |
| 348 | \& english.iso88591 german.iso88591 russian.iso88595 |
| 349 | \& english.roman8 russian.koi8r |
| 350 | .Ve |
| 351 | .PP |
| 352 | Sadly, even though the calling interface for \fIsetlocale()\fR has been |
| 353 | standardized, names of locales and the directories where the |
| 354 | configuration resides have not been. The basic form of the name is |
| 355 | \&\fIlanguage_territory\fR\fB.\fR\fIcodeset\fR, but the latter parts after |
| 356 | \&\fIlanguage\fR are not always present. The \fIlanguage\fR and \fIcountry\fR |
| 357 | are usually from the standards \fB\s-1ISO\s0 3166\fR and \fB\s-1ISO\s0 639\fR, the |
| 358 | two-letter abbreviations for the countries and the languages of the |
| 359 | world, respectively. The \fIcodeset\fR part often mentions some \fB\s-1ISO\s0 |
| 360 | 8859\fR character set, the Latin codesets. For example, \f(CW\*(C`ISO 8859\-1\*(C'\fR |
| 361 | is the so-called \*(L"Western European codeset\*(R" that can be used to encode |
| 362 | most Western European languages adequately. Again, there are several |
| 363 | ways to write even the name of that one standard. Lamentably. |
| 364 | .PP |
| 365 | Two special locales are worth particular mention: \*(L"C\*(R" and \*(L"\s-1POSIX\s0\*(R". |
| 366 | Currently these are effectively the same locale: the difference is |
| 367 | mainly that the first one is defined by the C standard, the second by |
| 368 | the \s-1POSIX\s0 standard. They define the \fBdefault locale\fR in which |
| 369 | every program starts in the absence of locale information in its |
| 370 | environment. (The \fIdefault\fR default locale, if you will.) Its language |
| 371 | is (American) English and its character codeset \s-1ASCII\s0. |
| 372 | .PP |
| 373 | \&\fB\s-1NOTE\s0\fR: Not all systems have the \*(L"\s-1POSIX\s0\*(R" locale (not all systems are |
| 374 | POSIX\-conformant), so use \*(L"C\*(R" when you need explicitly to specify this |
| 375 | default locale. |
| 376 | .Sh "\s-1LOCALE\s0 \s-1PROBLEMS\s0" |
| 377 | .IX Subsection "LOCALE PROBLEMS" |
| 378 | You may encounter the following warning message at Perl startup: |
| 379 | .PP |
| 380 | .Vb 6 |
| 381 | \& perl: warning: Setting locale failed. |
| 382 | \& perl: warning: Please check that your locale settings: |
| 383 | \& LC_ALL = "En_US", |
| 384 | \& LANG = (unset) |
| 385 | \& are supported and installed on your system. |
| 386 | \& perl: warning: Falling back to the standard locale ("C"). |
| 387 | .Ve |
| 388 | .PP |
| 389 | This means that your locale settings had \s-1LC_ALL\s0 set to \*(L"En_US\*(R" and |
| 390 | \&\s-1LANG\s0 exists but has no value. Perl tried to believe you but could not. |
| 391 | Instead, Perl gave up and fell back to the \*(L"C\*(R" locale, the default locale |
| 392 | that is supposed to work no matter what. This usually means your locale |
| 393 | settings were wrong, they mention locales your system has never heard |
| 394 | of, or the locale installation in your system has problems (for example, |
| 395 | some system files are broken or missing). There are quick and temporary |
| 396 | fixes to these problems, as well as more thorough and lasting fixes. |
| 397 | .Sh "Temporarily fixing locale problems" |
| 398 | .IX Subsection "Temporarily fixing locale problems" |
| 399 | The two quickest fixes are either to render Perl silent about any |
| 400 | locale inconsistencies or to run Perl under the default locale \*(L"C\*(R". |
| 401 | .PP |
| 402 | Perl's moaning about locale problems can be silenced by setting the |
| 403 | environment variable \s-1PERL_BADLANG\s0 to a zero value, for example \*(L"0\*(R". |
| 404 | This method really just sweeps the problem under the carpet: you tell |
| 405 | Perl to shut up even when Perl sees that something is wrong. Do not |
| 406 | be surprised if later something locale-dependent misbehaves. |
| 407 | .PP |
| 408 | Perl can be run under the \*(L"C\*(R" locale by setting the environment |
| 409 | variable \s-1LC_ALL\s0 to \*(L"C\*(R". This method is perhaps a bit more civilized |
| 410 | than the \s-1PERL_BADLANG\s0 approach, but setting \s-1LC_ALL\s0 (or |
| 411 | other locale variables) may affect other programs as well, not just |
| 412 | Perl. In particular, external programs run from within Perl will see |
| 413 | these changes. If you make the new settings permanent (read on), all |
| 414 | programs you run see the changes. See \s-1ENVIRONMENT\s0 for |
| 415 | the full list of relevant environment variables and \*(L"\s-1USING\s0 \s-1LOCALES\s0\*(R" |
| 416 | for their effects in Perl. Effects in other programs are |
| 417 | easily deducible. For example, the variable \s-1LC_COLLATE\s0 may well affect |
| 418 | your \fBsort\fR program (or whatever the program that arranges \*(L"records\*(R" |
| 419 | alphabetically in your system is called). |
| 420 | .PP |
| 421 | You can test out changing these variables temporarily, and if the |
| 422 | new settings seem to help, put those settings into your shell startup |
| 423 | files. Consult your local documentation for the exact details. For in |
| 424 | Bourne-like shells (\fBsh\fR, \fBksh\fR, \fBbash\fR, \fBzsh\fR): |
| 425 | .PP |
| 426 | .Vb 2 |
| 427 | \& LC_ALL=en_US.ISO8859-1 |
| 428 | \& export LC_ALL |
| 429 | .Ve |
| 430 | .PP |
| 431 | This assumes that we saw the locale \*(L"en_US.ISO8859\-1\*(R" using the commands |
| 432 | discussed above. We decided to try that instead of the above faulty |
| 433 | locale \*(L"En_US\*(R"\-\-and in Cshish shells (\fBcsh\fR, \fBtcsh\fR) |
| 434 | .PP |
| 435 | .Vb 1 |
| 436 | \& setenv LC_ALL en_US.ISO8859-1 |
| 437 | .Ve |
| 438 | .PP |
| 439 | or if you have the \*(L"env\*(R" application you can do in any shell |
| 440 | .PP |
| 441 | .Vb 1 |
| 442 | \& env LC_ALL=en_US.ISO8859-1 perl ... |
| 443 | .Ve |
| 444 | .PP |
| 445 | If you do not know what shell you have, consult your local |
| 446 | helpdesk or the equivalent. |
| 447 | .Sh "Permanently fixing locale problems" |
| 448 | .IX Subsection "Permanently fixing locale problems" |
| 449 | The slower but superior fixes are when you may be able to yourself |
| 450 | fix the misconfiguration of your own environment variables. The |
| 451 | mis(sing)configuration of the whole system's locales usually requires |
| 452 | the help of your friendly system administrator. |
| 453 | .PP |
| 454 | First, see earlier in this document about \*(L"Finding locales\*(R". That tells |
| 455 | how to find which locales are really supported\*(--and more importantly, |
| 456 | installed\*(--on your system. In our example error message, environment |
| 457 | variables affecting the locale are listed in the order of decreasing |
| 458 | importance (and unset variables do not matter). Therefore, having |
| 459 | \&\s-1LC_ALL\s0 set to \*(L"En_US\*(R" must have been the bad choice, as shown by the |
| 460 | error message. First try fixing locale settings listed first. |
| 461 | .PP |
| 462 | Second, if using the listed commands you see something \fBexactly\fR |
| 463 | (prefix matches do not count and case usually counts) like \*(L"En_US\*(R" |
| 464 | without the quotes, then you should be okay because you are using a |
| 465 | locale name that should be installed and available in your system. |
| 466 | In this case, see \*(L"Permanently fixing your system's locale configuration\*(R". |
| 467 | .Sh "Permanently fixing your system's locale configuration" |
| 468 | .IX Subsection "Permanently fixing your system's locale configuration" |
| 469 | This is when you see something like: |
| 470 | .PP |
| 471 | .Vb 4 |
| 472 | \& perl: warning: Please check that your locale settings: |
| 473 | \& LC_ALL = "En_US", |
| 474 | \& LANG = (unset) |
| 475 | \& are supported and installed on your system. |
| 476 | .Ve |
| 477 | .PP |
| 478 | but then cannot see that \*(L"En_US\*(R" listed by the above-mentioned |
| 479 | commands. You may see things like \*(L"en_US.ISO8859\-1\*(R", but that isn't |
| 480 | the same. In this case, try running under a locale |
| 481 | that you can list and which somehow matches what you tried. The |
| 482 | rules for matching locale names are a bit vague because |
| 483 | standardization is weak in this area. See again the |
| 484 | \&\*(L"Finding locales\*(R" about general rules. |
| 485 | .Sh "Fixing system locale configuration" |
| 486 | .IX Subsection "Fixing system locale configuration" |
| 487 | Contact a system administrator (preferably your own) and report the exact |
| 488 | error message you get, and ask them to read this same documentation you |
| 489 | are now reading. They should be able to check whether there is something |
| 490 | wrong with the locale configuration of the system. The \*(L"Finding locales\*(R" |
| 491 | section is unfortunately a bit vague about the exact commands and places |
| 492 | because these things are not that standardized. |
| 493 | .Sh "The localeconv function" |
| 494 | .IX Subsection "The localeconv function" |
| 495 | The \fIPOSIX::localeconv()\fR function allows you to get particulars of the |
| 496 | locale-dependent numeric formatting information specified by the current |
| 497 | \&\f(CW\*(C`LC_NUMERIC\*(C'\fR and \f(CW\*(C`LC_MONETARY\*(C'\fR locales. (If you just want the name of |
| 498 | the current locale for a particular category, use \fIPOSIX::setlocale()\fR |
| 499 | with a single parameter\*(--see \*(L"The setlocale function\*(R".) |
| 500 | .PP |
| 501 | .Vb 1 |
| 502 | \& use POSIX qw(locale_h); |
| 503 | .Ve |
| 504 | .PP |
| 505 | .Vb 2 |
| 506 | \& # Get a reference to a hash of locale-dependent info |
| 507 | \& $locale_values = localeconv(); |
| 508 | .Ve |
| 509 | .PP |
| 510 | .Vb 4 |
| 511 | \& # Output sorted list of the values |
| 512 | \& for (sort keys %$locale_values) { |
| 513 | \& printf "%-20s = %s\en", $_, $locale_values->{$_} |
| 514 | \& } |
| 515 | .Ve |
| 516 | .PP |
| 517 | \&\fIlocaleconv()\fR takes no arguments, and returns \fBa reference to\fR a hash. |
| 518 | The keys of this hash are variable names for formatting, such as |
| 519 | \&\f(CW\*(C`decimal_point\*(C'\fR and \f(CW\*(C`thousands_sep\*(C'\fR. The values are the |
| 520 | corresponding, er, values. See \*(L"localeconv\*(R" in \s-1POSIX\s0 for a longer |
| 521 | example listing the categories an implementation might be expected to |
| 522 | provide; some provide more and others fewer. You don't need an |
| 523 | explicit \f(CW\*(C`use locale\*(C'\fR, because \fIlocaleconv()\fR always observes the |
| 524 | current locale. |
| 525 | .PP |
| 526 | Here's a simple-minded example program that rewrites its command-line |
| 527 | parameters as integers correctly formatted in the current locale: |
| 528 | .PP |
| 529 | .Vb 3 |
| 530 | \& # See comments in previous example |
| 531 | \& require 5.004; |
| 532 | \& use POSIX qw(locale_h); |
| 533 | .Ve |
| 534 | .PP |
| 535 | .Vb 3 |
| 536 | \& # Get some of locale's numeric formatting parameters |
| 537 | \& my ($thousands_sep, $grouping) = |
| 538 | \& @{localeconv()}{'thousands_sep', 'grouping'}; |
| 539 | .Ve |
| 540 | .PP |
| 541 | .Vb 2 |
| 542 | \& # Apply defaults if values are missing |
| 543 | \& $thousands_sep = ',' unless $thousands_sep; |
| 544 | .Ve |
| 545 | .PP |
| 546 | .Vb 16 |
| 547 | \& # grouping and mon_grouping are packed lists |
| 548 | \& # of small integers (characters) telling the |
| 549 | \& # grouping (thousand_seps and mon_thousand_seps |
| 550 | \& # being the group dividers) of numbers and |
| 551 | \& # monetary quantities. The integers' meanings: |
| 552 | \& # 255 means no more grouping, 0 means repeat |
| 553 | \& # the previous grouping, 1-254 means use that |
| 554 | \& # as the current grouping. Grouping goes from |
| 555 | \& # right to left (low to high digits). In the |
| 556 | \& # below we cheat slightly by never using anything |
| 557 | \& # else than the first grouping (whatever that is). |
| 558 | \& if ($grouping) { |
| 559 | \& @grouping = unpack("C*", $grouping); |
| 560 | \& } else { |
| 561 | \& @grouping = (3); |
| 562 | \& } |
| 563 | .Ve |
| 564 | .PP |
| 565 | .Vb 8 |
| 566 | \& # Format command line params for current locale |
| 567 | \& for (@ARGV) { |
| 568 | \& $_ = int; # Chop non-integer part |
| 569 | \& 1 while |
| 570 | \& s/(\ed)(\ed{$grouping[0]}($|$thousands_sep))/$1$thousands_sep$2/; |
| 571 | \& print "$_"; |
| 572 | \& } |
| 573 | \& print "\en"; |
| 574 | .Ve |
| 575 | .Sh "I18N::Langinfo" |
| 576 | .IX Subsection "I18N::Langinfo" |
| 577 | Another interface for querying locale-dependent information is the |
| 578 | \&\fII18N::Langinfo::langinfo()\fR function, available at least in UNIX-like |
| 579 | systems and \s-1VMS\s0. |
| 580 | .PP |
| 581 | The following example will import the \fIlanginfo()\fR function itself and |
| 582 | three constants to be used as arguments to \fIlanginfo()\fR: a constant for |
| 583 | the abbreviated first day of the week (the numbering starts from |
| 584 | Sunday = 1) and two more constants for the affirmative and negative |
| 585 | answers for a yes/no question in the current locale. |
| 586 | .PP |
| 587 | .Vb 1 |
| 588 | \& use I18N::Langinfo qw(langinfo ABDAY_1 YESSTR NOSTR); |
| 589 | .Ve |
| 590 | .PP |
| 591 | .Vb 1 |
| 592 | \& my ($abday_1, $yesstr, $nostr) = map { langinfo } qw(ABDAY_1 YESSTR NOSTR); |
| 593 | .Ve |
| 594 | .PP |
| 595 | .Vb 1 |
| 596 | \& print "$abday_1? [$yesstr/$nostr] "; |
| 597 | .Ve |
| 598 | .PP |
| 599 | In other words, in the \*(L"C\*(R" (or English) locale the above will probably |
| 600 | print something like: |
| 601 | .PP |
| 602 | .Vb 1 |
| 603 | \& Sun? [yes/no] |
| 604 | .Ve |
| 605 | .PP |
| 606 | See I18N::Langinfo for more information. |
| 607 | .SH "LOCALE CATEGORIES" |
| 608 | .IX Header "LOCALE CATEGORIES" |
| 609 | The following subsections describe basic locale categories. Beyond these, |
| 610 | some combination categories allow manipulation of more than one |
| 611 | basic category at a time. See \*(L"\s-1ENVIRONMENT\s0\*(R" for a discussion of these. |
| 612 | .Sh "Category \s-1LC_COLLATE:\s0 Collation" |
| 613 | .IX Subsection "Category LC_COLLATE: Collation" |
| 614 | In the scope of \f(CW\*(C`use\ locale\*(C'\fR, Perl looks to the \f(CW\*(C`LC_COLLATE\*(C'\fR |
| 615 | environment variable to determine the application's notions on collation |
| 616 | (ordering) of characters. For example, 'b' follows 'a' in Latin |
| 617 | alphabets, but where do 'a\*'' and 'a\*o' belong? And while |
| 618 | \&'color' follows 'chocolate' in English, what about in Spanish? |
| 619 | .PP |
| 620 | The following collations all make sense and you may meet any of them |
| 621 | if you \*(L"use locale\*(R". |
| 622 | .PP |
| 623 | .Vb 4 |
| 624 | \& A B C D E a b c d e |
| 625 | \& A a B b C c D d E e |
| 626 | \& a A b B c C d D e E |
| 627 | \& a b c d e A B C D E |
| 628 | .Ve |
| 629 | .PP |
| 630 | Here is a code snippet to tell what \*(L"word\*(R" |
| 631 | characters are in the current locale, in that locale's order: |
| 632 | .PP |
| 633 | .Vb 2 |
| 634 | \& use locale; |
| 635 | \& print +(sort grep /\ew/, map { chr } 0..255), "\en"; |
| 636 | .Ve |
| 637 | .PP |
| 638 | Compare this with the characters that you see and their order if you |
| 639 | state explicitly that the locale should be ignored: |
| 640 | .PP |
| 641 | .Vb 2 |
| 642 | \& no locale; |
| 643 | \& print +(sort grep /\ew/, map { chr } 0..255), "\en"; |
| 644 | .Ve |
| 645 | .PP |
| 646 | This machine-native collation (which is what you get unless \f(CW\*(C`use\ locale\*(C'\fR has appeared earlier in the same block) must be used for |
| 647 | sorting raw binary data, whereas the locale-dependent collation of the |
| 648 | first example is useful for natural text. |
| 649 | .PP |
| 650 | As noted in \*(L"\s-1USING\s0 \s-1LOCALES\s0\*(R", \f(CW\*(C`cmp\*(C'\fR compares according to the current |
| 651 | collation locale when \f(CW\*(C`use locale\*(C'\fR is in effect, but falls back to a |
| 652 | char-by-char comparison for strings that the locale says are equal. You |
| 653 | can use \fIPOSIX::strcoll()\fR if you don't want this fall\-back: |
| 654 | .PP |
| 655 | .Vb 3 |
| 656 | \& use POSIX qw(strcoll); |
| 657 | \& $equal_in_locale = |
| 658 | \& !strcoll("space and case ignored", "SpaceAndCaseIgnored"); |
| 659 | .Ve |
| 660 | .PP |
| 661 | $equal_in_locale will be true if the collation locale specifies a |
| 662 | dictionary-like ordering that ignores space characters completely and |
| 663 | which folds case. |
| 664 | .PP |
| 665 | If you have a single string that you want to check for \*(L"equality in |
| 666 | locale\*(R" against several others, you might think you could gain a little |
| 667 | efficiency by using \fIPOSIX::strxfrm()\fR in conjunction with \f(CW\*(C`eq\*(C'\fR: |
| 668 | .PP |
| 669 | .Vb 8 |
| 670 | \& use POSIX qw(strxfrm); |
| 671 | \& $xfrm_string = strxfrm("Mixed-case string"); |
| 672 | \& print "locale collation ignores spaces\en" |
| 673 | \& if $xfrm_string eq strxfrm("Mixed-casestring"); |
| 674 | \& print "locale collation ignores hyphens\en" |
| 675 | \& if $xfrm_string eq strxfrm("Mixedcase string"); |
| 676 | \& print "locale collation ignores case\en" |
| 677 | \& if $xfrm_string eq strxfrm("mixed-case string"); |
| 678 | .Ve |
| 679 | .PP |
| 680 | \&\fIstrxfrm()\fR takes a string and maps it into a transformed string for use |
| 681 | in char-by-char comparisons against other transformed strings during |
| 682 | collation. \*(L"Under the hood\*(R", locale-affected Perl comparison operators |
| 683 | call \fIstrxfrm()\fR for both operands, then do a char-by-char |
| 684 | comparison of the transformed strings. By calling \fIstrxfrm()\fR explicitly |
| 685 | and using a non locale-affected comparison, the example attempts to save |
| 686 | a couple of transformations. But in fact, it doesn't save anything: Perl |
| 687 | magic (see \*(L"Magic Variables\*(R" in perlguts) creates the transformed version of a |
| 688 | string the first time it's needed in a comparison, then keeps this version around |
| 689 | in case it's needed again. An example rewritten the easy way with |
| 690 | \&\f(CW\*(C`cmp\*(C'\fR runs just about as fast. It also copes with null characters |
| 691 | embedded in strings; if you call \fIstrxfrm()\fR directly, it treats the first |
| 692 | null it finds as a terminator. don't expect the transformed strings |
| 693 | it produces to be portable across systems\*(--or even from one revision |
| 694 | of your operating system to the next. In short, don't call \fIstrxfrm()\fR |
| 695 | directly: let Perl do it for you. |
| 696 | .PP |
| 697 | Note: \f(CW\*(C`use locale\*(C'\fR isn't shown in some of these examples because it isn't |
| 698 | needed: \fIstrcoll()\fR and \fIstrxfrm()\fR exist only to generate locale-dependent |
| 699 | results, and so always obey the current \f(CW\*(C`LC_COLLATE\*(C'\fR locale. |
| 700 | .Sh "Category \s-1LC_CTYPE:\s0 Character Types" |
| 701 | .IX Subsection "Category LC_CTYPE: Character Types" |
| 702 | In the scope of \f(CW\*(C`use\ locale\*(C'\fR, Perl obeys the \f(CW\*(C`LC_CTYPE\*(C'\fR locale |
| 703 | setting. This controls the application's notion of which characters are |
| 704 | alphabetic. This affects Perl's \f(CW\*(C`\ew\*(C'\fR regular expression metanotation, |
| 705 | which stands for alphanumeric characters\*(--that is, alphabetic, |
| 706 | numeric, and including other special characters such as the underscore or |
| 707 | hyphen. (Consult perlre for more information about |
| 708 | regular expressions.) Thanks to \f(CW\*(C`LC_CTYPE\*(C'\fR, depending on your locale |
| 709 | setting, characters like '\*(ae', '\*(d-', '\*8', and |
| 710 | \&'o\*/' may be understood as \f(CW\*(C`\ew\*(C'\fR characters. |
| 711 | .PP |
| 712 | The \f(CW\*(C`LC_CTYPE\*(C'\fR locale also provides the map used in transliterating |
| 713 | characters between lower and uppercase. This affects the case-mapping |
| 714 | functions\*(--\fIlc()\fR, lcfirst, \fIuc()\fR, and \fIucfirst()\fR; case-mapping |
| 715 | interpolation with \f(CW\*(C`\el\*(C'\fR, \f(CW\*(C`\eL\*(C'\fR, \f(CW\*(C`\eu\*(C'\fR, or \f(CW\*(C`\eU\*(C'\fR in double-quoted strings |
| 716 | and \f(CW\*(C`s///\*(C'\fR substitutions; and case-independent regular expression |
| 717 | pattern matching using the \f(CW\*(C`i\*(C'\fR modifier. |
| 718 | .PP |
| 719 | Finally, \f(CW\*(C`LC_CTYPE\*(C'\fR affects the \s-1POSIX\s0 character-class test |
| 720 | functions\*(--\fIisalpha()\fR, \fIislower()\fR, and so on. For example, if you move |
| 721 | from the \*(L"C\*(R" locale to a 7\-bit Scandinavian one, you may find\*(--possibly |
| 722 | to your surprise\*(--that \*(L"|\*(R" moves from the \fIispunct()\fR class to \fIisalpha()\fR. |
| 723 | .PP |
| 724 | \&\fBNote:\fR A broken or malicious \f(CW\*(C`LC_CTYPE\*(C'\fR locale definition may result |
| 725 | in clearly ineligible characters being considered to be alphanumeric by |
| 726 | your application. For strict matching of (mundane) letters and |
| 727 | digits\*(--for example, in command strings\*(--locale\-aware applications |
| 728 | should use \f(CW\*(C`\ew\*(C'\fR inside a \f(CW\*(C`no locale\*(C'\fR block. See \*(L"\s-1SECURITY\s0\*(R". |
| 729 | .Sh "Category \s-1LC_NUMERIC:\s0 Numeric Formatting" |
| 730 | .IX Subsection "Category LC_NUMERIC: Numeric Formatting" |
| 731 | In the scope of \f(CW\*(C`use\ locale\*(C'\fR, Perl obeys the \f(CW\*(C`LC_NUMERIC\*(C'\fR locale |
| 732 | information, which controls an application's idea of how numbers should |
| 733 | be formatted for human readability by the \fIprintf()\fR, \fIsprintf()\fR, and |
| 734 | \&\fIwrite()\fR functions. String-to-numeric conversion by the \fIPOSIX::strtod()\fR |
| 735 | function is also affected. In most implementations the only effect is to |
| 736 | change the character used for the decimal point\*(--perhaps from '.' to ','. |
| 737 | These functions aren't aware of such niceties as thousands separation and |
| 738 | so on. (See \*(L"The localeconv function\*(R" if you care about these things.) |
| 739 | .PP |
| 740 | Output produced by \fIprint()\fR is also affected by the current locale: it |
| 741 | depends on whether \f(CW\*(C`use locale\*(C'\fR or \f(CW\*(C`no locale\*(C'\fR is in effect, and |
| 742 | corresponds to what you'd get from \fIprintf()\fR in the \*(L"C\*(R" locale. The |
| 743 | same is true for Perl's internal conversions between numeric and |
| 744 | string formats: |
| 745 | .PP |
| 746 | .Vb 2 |
| 747 | \& use POSIX qw(strtod); |
| 748 | \& use locale; |
| 749 | .Ve |
| 750 | .PP |
| 751 | .Vb 1 |
| 752 | \& $n = 5/2; # Assign numeric 2.5 to $n |
| 753 | .Ve |
| 754 | .PP |
| 755 | .Vb 1 |
| 756 | \& $a = " $n"; # Locale-dependent conversion to string |
| 757 | .Ve |
| 758 | .PP |
| 759 | .Vb 1 |
| 760 | \& print "half five is $n\en"; # Locale-dependent output |
| 761 | .Ve |
| 762 | .PP |
| 763 | .Vb 1 |
| 764 | \& printf "half five is %g\en", $n; # Locale-dependent output |
| 765 | .Ve |
| 766 | .PP |
| 767 | .Vb 2 |
| 768 | \& print "DECIMAL POINT IS COMMA\en" |
| 769 | \& if $n == (strtod("2,5"))[0]; # Locale-dependent conversion |
| 770 | .Ve |
| 771 | .PP |
| 772 | See also I18N::Langinfo and \f(CW\*(C`RADIXCHAR\*(C'\fR. |
| 773 | .Sh "Category \s-1LC_MONETARY:\s0 Formatting of monetary amounts" |
| 774 | .IX Subsection "Category LC_MONETARY: Formatting of monetary amounts" |
| 775 | The C standard defines the \f(CW\*(C`LC_MONETARY\*(C'\fR category, but no function |
| 776 | that is affected by its contents. (Those with experience of standards |
| 777 | committees will recognize that the working group decided to punt on the |
| 778 | issue.) Consequently, Perl takes no notice of it. If you really want |
| 779 | to use \f(CW\*(C`LC_MONETARY\*(C'\fR, you can query its contents\*(--see |
| 780 | \&\*(L"The localeconv function\*(R"\-\-and use the information that it returns in your |
| 781 | application's own formatting of currency amounts. However, you may well |
| 782 | find that the information, voluminous and complex though it may be, still |
| 783 | does not quite meet your requirements: currency formatting is a hard nut |
| 784 | to crack. |
| 785 | .PP |
| 786 | See also I18N::Langinfo and \f(CW\*(C`CRNCYSTR\*(C'\fR. |
| 787 | .Sh "\s-1LC_TIME\s0" |
| 788 | .IX Subsection "LC_TIME" |
| 789 | Output produced by \fIPOSIX::strftime()\fR, which builds a formatted |
| 790 | human-readable date/time string, is affected by the current \f(CW\*(C`LC_TIME\*(C'\fR |
| 791 | locale. Thus, in a French locale, the output produced by the \f(CW%B\fR |
| 792 | format element (full month name) for the first month of the year would |
| 793 | be \*(L"janvier\*(R". Here's how to get a list of long month names in the |
| 794 | current locale: |
| 795 | .PP |
| 796 | .Vb 5 |
| 797 | \& use POSIX qw(strftime); |
| 798 | \& for (0..11) { |
| 799 | \& $long_month_name[$_] = |
| 800 | \& strftime("%B", 0, 0, 0, 1, $_, 96); |
| 801 | \& } |
| 802 | .Ve |
| 803 | .PP |
| 804 | Note: \f(CW\*(C`use locale\*(C'\fR isn't needed in this example: as a function that |
| 805 | exists only to generate locale-dependent results, \fIstrftime()\fR always |
| 806 | obeys the current \f(CW\*(C`LC_TIME\*(C'\fR locale. |
| 807 | .PP |
| 808 | See also I18N::Langinfo and \f(CW\*(C`ABDAY_1\*(C'\fR..\f(CW\*(C`ABDAY_7\*(C'\fR, \f(CW\*(C`DAY_1\*(C'\fR..\f(CW\*(C`DAY_7\*(C'\fR, |
| 809 | \&\f(CW\*(C`ABMON_1\*(C'\fR..\f(CW\*(C`ABMON_12\*(C'\fR, and \f(CW\*(C`ABMON_1\*(C'\fR..\f(CW\*(C`ABMON_12\*(C'\fR. |
| 810 | .Sh "Other categories" |
| 811 | .IX Subsection "Other categories" |
| 812 | The remaining locale category, \f(CW\*(C`LC_MESSAGES\*(C'\fR (possibly supplemented |
| 813 | by others in particular implementations) is not currently used by |
| 814 | Perl\*(--except possibly to affect the behavior of library functions |
| 815 | called by extensions outside the standard Perl distribution and by the |
| 816 | operating system and its utilities. Note especially that the string |
| 817 | value of \f(CW$!\fR and the error messages given by external utilities may |
| 818 | be changed by \f(CW\*(C`LC_MESSAGES\*(C'\fR. If you want to have portable error |
| 819 | codes, use \f(CW\*(C`%!\*(C'\fR. See Errno. |
| 820 | .SH "SECURITY" |
| 821 | .IX Header "SECURITY" |
| 822 | Although the main discussion of Perl security issues can be found in |
| 823 | perlsec, a discussion of Perl's locale handling would be incomplete |
| 824 | if it did not draw your attention to locale-dependent security issues. |
| 825 | Locales\*(--particularly on systems that allow unprivileged users to |
| 826 | build their own locales\*(--are untrustworthy. A malicious (or just plain |
| 827 | broken) locale can make a locale-aware application give unexpected |
| 828 | results. Here are a few possibilities: |
| 829 | .IP "\(bu" 4 |
| 830 | Regular expression checks for safe file names or mail addresses using |
| 831 | \&\f(CW\*(C`\ew\*(C'\fR may be spoofed by an \f(CW\*(C`LC_CTYPE\*(C'\fR locale that claims that |
| 832 | characters such as ">\*(L" and \*(R"|" are alphanumeric. |
| 833 | .IP "\(bu" 4 |
| 834 | String interpolation with case\-mapping, as in, say, \f(CW\*(C`$dest = |
| 835 | "C:\eU$name.$ext"\*(C'\fR, may produce dangerous results if a bogus \s-1LC_CTYPE\s0 |
| 836 | case-mapping table is in effect. |
| 837 | .IP "\(bu" 4 |
| 838 | A sneaky \f(CW\*(C`LC_COLLATE\*(C'\fR locale could result in the names of students with |
| 839 | \&\*(L"D\*(R" grades appearing ahead of those with \*(L"A\*(R"s. |
| 840 | .IP "\(bu" 4 |
| 841 | An application that takes the trouble to use information in |
| 842 | \&\f(CW\*(C`LC_MONETARY\*(C'\fR may format debits as if they were credits and vice versa |
| 843 | if that locale has been subverted. Or it might make payments in \s-1US\s0 |
| 844 | dollars instead of Hong Kong dollars. |
| 845 | .IP "\(bu" 4 |
| 846 | The date and day names in dates formatted by \fIstrftime()\fR could be |
| 847 | manipulated to advantage by a malicious user able to subvert the |
| 848 | \&\f(CW\*(C`LC_DATE\*(C'\fR locale. (\*(L"Look\*(--it says I wasn't in the building on |
| 849 | Sunday.\*(R") |
| 850 | .PP |
| 851 | Such dangers are not peculiar to the locale system: any aspect of an |
| 852 | application's environment which may be modified maliciously presents |
| 853 | similar challenges. Similarly, they are not specific to Perl: any |
| 854 | programming language that allows you to write programs that take |
| 855 | account of their environment exposes you to these issues. |
| 856 | .PP |
| 857 | Perl cannot protect you from all possibilities shown in the |
| 858 | examples\*(--there is no substitute for your own vigilance\*(--but, when |
| 859 | \&\f(CW\*(C`use locale\*(C'\fR is in effect, Perl uses the tainting mechanism (see |
| 860 | perlsec) to mark string results that become locale\-dependent, and |
| 861 | which may be untrustworthy in consequence. Here is a summary of the |
| 862 | tainting behavior of operators and functions that may be affected by |
| 863 | the locale: |
| 864 | .IP "\(bu" 4 |
| 865 | \&\fBComparison operators\fR (\f(CW\*(C`lt\*(C'\fR, \f(CW\*(C`le\*(C'\fR, \f(CW\*(C`ge\*(C'\fR, \f(CW\*(C`gt\*(C'\fR and \f(CW\*(C`cmp\*(C'\fR): |
| 866 | .Sp |
| 867 | Scalar true/false (or less/equal/greater) result is never tainted. |
| 868 | .IP "\(bu" 4 |
| 869 | \&\fBCase-mapping interpolation\fR (with \f(CW\*(C`\el\*(C'\fR, \f(CW\*(C`\eL\*(C'\fR, \f(CW\*(C`\eu\*(C'\fR or \f(CW\*(C`\eU\*(C'\fR) |
| 870 | .Sp |
| 871 | Result string containing interpolated material is tainted if |
| 872 | \&\f(CW\*(C`use locale\*(C'\fR is in effect. |
| 873 | .IP "\(bu" 4 |
| 874 | \&\fBMatching operator\fR (\f(CW\*(C`m//\*(C'\fR): |
| 875 | .Sp |
| 876 | Scalar true/false result never tainted. |
| 877 | .Sp |
| 878 | Subpatterns, either delivered as a list-context result or as \f(CW$1\fR etc. |
| 879 | are tainted if \f(CW\*(C`use locale\*(C'\fR is in effect, and the subpattern regular |
| 880 | expression contains \f(CW\*(C`\ew\*(C'\fR (to match an alphanumeric character), \f(CW\*(C`\eW\*(C'\fR |
| 881 | (non\-alphanumeric character), \f(CW\*(C`\es\*(C'\fR (whitespace character), or \f(CW\*(C`\eS\*(C'\fR |
| 882 | (non whitespace character). The matched-pattern variable, $&, $` |
| 883 | (pre\-match), $' (post\-match), and $+ (last match) are also tainted if |
| 884 | \&\f(CW\*(C`use locale\*(C'\fR is in effect and the regular expression contains \f(CW\*(C`\ew\*(C'\fR, |
| 885 | \&\f(CW\*(C`\eW\*(C'\fR, \f(CW\*(C`\es\*(C'\fR, or \f(CW\*(C`\eS\*(C'\fR. |
| 886 | .IP "\(bu" 4 |
| 887 | \&\fBSubstitution operator\fR (\f(CW\*(C`s///\*(C'\fR): |
| 888 | .Sp |
| 889 | Has the same behavior as the match operator. Also, the left |
| 890 | operand of \f(CW\*(C`=~\*(C'\fR becomes tainted when \f(CW\*(C`use locale\*(C'\fR in effect |
| 891 | if modified as a result of a substitution based on a regular |
| 892 | expression match involving \f(CW\*(C`\ew\*(C'\fR, \f(CW\*(C`\eW\*(C'\fR, \f(CW\*(C`\es\*(C'\fR, or \f(CW\*(C`\eS\*(C'\fR; or of |
| 893 | case-mapping with \f(CW\*(C`\el\*(C'\fR, \f(CW\*(C`\eL\*(C'\fR,\f(CW\*(C`\eu\*(C'\fR or \f(CW\*(C`\eU\*(C'\fR. |
| 894 | .IP "\(bu" 4 |
| 895 | \&\fBOutput formatting functions\fR (\fIprintf()\fR and \fIwrite()\fR): |
| 896 | .Sp |
| 897 | Results are never tainted because otherwise even output from print, |
| 898 | for example \f(CW\*(C`print(1/7)\*(C'\fR, should be tainted if \f(CW\*(C`use locale\*(C'\fR is in |
| 899 | effect. |
| 900 | .IP "\(bu" 4 |
| 901 | \&\fBCase-mapping functions\fR (\fIlc()\fR, \fIlcfirst()\fR, \fIuc()\fR, \fIucfirst()\fR): |
| 902 | .Sp |
| 903 | Results are tainted if \f(CW\*(C`use locale\*(C'\fR is in effect. |
| 904 | .IP "\(bu" 4 |
| 905 | \&\fB\s-1POSIX\s0 locale-dependent functions\fR (\fIlocaleconv()\fR, \fIstrcoll()\fR, |
| 906 | \&\fIstrftime()\fR, \fIstrxfrm()\fR): |
| 907 | .Sp |
| 908 | Results are never tainted. |
| 909 | .IP "\(bu" 4 |
| 910 | \&\fB\s-1POSIX\s0 character class tests\fR (\fIisalnum()\fR, \fIisalpha()\fR, \fIisdigit()\fR, |
| 911 | \&\fIisgraph()\fR, \fIislower()\fR, \fIisprint()\fR, \fIispunct()\fR, \fIisspace()\fR, \fIisupper()\fR, |
| 912 | \&\fIisxdigit()\fR): |
| 913 | .Sp |
| 914 | True/false results are never tainted. |
| 915 | .PP |
| 916 | Three examples illustrate locale-dependent tainting. |
| 917 | The first program, which ignores its locale, won't run: a value taken |
| 918 | directly from the command line may not be used to name an output file |
| 919 | when taint checks are enabled. |
| 920 | .PP |
| 921 | .Vb 2 |
| 922 | \& #/usr/local/bin/perl -T |
| 923 | \& # Run with taint checking |
| 924 | .Ve |
| 925 | .PP |
| 926 | .Vb 2 |
| 927 | \& # Command line sanity check omitted... |
| 928 | \& $tainted_output_file = shift; |
| 929 | .Ve |
| 930 | .PP |
| 931 | .Vb 2 |
| 932 | \& open(F, ">$tainted_output_file") |
| 933 | \& or warn "Open of $untainted_output_file failed: $!\en"; |
| 934 | .Ve |
| 935 | .PP |
| 936 | The program can be made to run by \*(L"laundering\*(R" the tainted value through |
| 937 | a regular expression: the second example\*(--which still ignores locale |
| 938 | information\*(--runs, creating the file named on its command line |
| 939 | if it can. |
| 940 | .PP |
| 941 | .Vb 1 |
| 942 | \& #/usr/local/bin/perl -T |
| 943 | .Ve |
| 944 | .PP |
| 945 | .Vb 3 |
| 946 | \& $tainted_output_file = shift; |
| 947 | \& $tainted_output_file =~ m%[\ew/]+%; |
| 948 | \& $untainted_output_file = $&; |
| 949 | .Ve |
| 950 | .PP |
| 951 | .Vb 2 |
| 952 | \& open(F, ">$untainted_output_file") |
| 953 | \& or warn "Open of $untainted_output_file failed: $!\en"; |
| 954 | .Ve |
| 955 | .PP |
| 956 | Compare this with a similar but locale-aware program: |
| 957 | .PP |
| 958 | .Vb 1 |
| 959 | \& #/usr/local/bin/perl -T |
| 960 | .Ve |
| 961 | .PP |
| 962 | .Vb 4 |
| 963 | \& $tainted_output_file = shift; |
| 964 | \& use locale; |
| 965 | \& $tainted_output_file =~ m%[\ew/]+%; |
| 966 | \& $localized_output_file = $&; |
| 967 | .Ve |
| 968 | .PP |
| 969 | .Vb 2 |
| 970 | \& open(F, ">$localized_output_file") |
| 971 | \& or warn "Open of $localized_output_file failed: $!\en"; |
| 972 | .Ve |
| 973 | .PP |
| 974 | This third program fails to run because $& is tainted: it is the result |
| 975 | of a match involving \f(CW\*(C`\ew\*(C'\fR while \f(CW\*(C`use locale\*(C'\fR is in effect. |
| 976 | .SH "ENVIRONMENT" |
| 977 | .IX Header "ENVIRONMENT" |
| 978 | .IP "\s-1PERL_BADLANG\s0" 12 |
| 979 | .IX Item "PERL_BADLANG" |
| 980 | A string that can suppress Perl's warning about failed locale settings |
| 981 | at startup. Failure can occur if the locale support in the operating |
| 982 | system is lacking (broken) in some way\*(--or if you mistyped the name of |
| 983 | a locale when you set up your environment. If this environment |
| 984 | variable is absent, or has a value that does not evaluate to integer |
| 985 | zero\*(--that is, \*(L"0\*(R" or ""\-\- Perl will complain about locale setting |
| 986 | failures. |
| 987 | .Sp |
| 988 | \&\fB\s-1NOTE\s0\fR: \s-1PERL_BADLANG\s0 only gives you a way to hide the warning message. |
| 989 | The message tells about some problem in your system's locale support, |
| 990 | and you should investigate what the problem is. |
| 991 | .PP |
| 992 | The following environment variables are not specific to Perl: They are |
| 993 | part of the standardized (\s-1ISO\s0 C, \s-1XPG4\s0, \s-1POSIX\s0 1.c) \fIsetlocale()\fR method |
| 994 | for controlling an application's opinion on data. |
| 995 | .IP "\s-1LC_ALL\s0" 12 |
| 996 | .IX Item "LC_ALL" |
| 997 | \&\f(CW\*(C`LC_ALL\*(C'\fR is the \*(L"override\-all\*(R" locale environment variable. If |
| 998 | set, it overrides all the rest of the locale environment variables. |
| 999 | .IP "\s-1LANGUAGE\s0" 12 |
| 1000 | .IX Item "LANGUAGE" |
| 1001 | \&\fB\s-1NOTE\s0\fR: \f(CW\*(C`LANGUAGE\*(C'\fR is a \s-1GNU\s0 extension, it affects you only if you |
| 1002 | are using the \s-1GNU\s0 libc. This is the case if you are using e.g. Linux. |
| 1003 | If you are using \*(L"commercial\*(R" UNIXes you are most probably \fInot\fR |
| 1004 | using \s-1GNU\s0 libc and you can ignore \f(CW\*(C`LANGUAGE\*(C'\fR. |
| 1005 | .Sp |
| 1006 | However, in the case you are using \f(CW\*(C`LANGUAGE\*(C'\fR: it affects the |
| 1007 | language of informational, warning, and error messages output by |
| 1008 | commands (in other words, it's like \f(CW\*(C`LC_MESSAGES\*(C'\fR) but it has higher |
| 1009 | priority than \s-1LC_ALL\s0. Moreover, it's not a single value but |
| 1010 | instead a \*(L"path\*(R" (\*(L":\*(R"\-separated list) of \fIlanguages\fR (not locales). |
| 1011 | See the \s-1GNU\s0 \f(CW\*(C`gettext\*(C'\fR library documentation for more information. |
| 1012 | .IP "\s-1LC_CTYPE\s0" 12 |
| 1013 | .IX Item "LC_CTYPE" |
| 1014 | In the absence of \f(CW\*(C`LC_ALL\*(C'\fR, \f(CW\*(C`LC_CTYPE\*(C'\fR chooses the character type |
| 1015 | locale. In the absence of both \f(CW\*(C`LC_ALL\*(C'\fR and \f(CW\*(C`LC_CTYPE\*(C'\fR, \f(CW\*(C`LANG\*(C'\fR |
| 1016 | chooses the character type locale. |
| 1017 | .IP "\s-1LC_COLLATE\s0" 12 |
| 1018 | .IX Item "LC_COLLATE" |
| 1019 | In the absence of \f(CW\*(C`LC_ALL\*(C'\fR, \f(CW\*(C`LC_COLLATE\*(C'\fR chooses the collation |
| 1020 | (sorting) locale. In the absence of both \f(CW\*(C`LC_ALL\*(C'\fR and \f(CW\*(C`LC_COLLATE\*(C'\fR, |
| 1021 | \&\f(CW\*(C`LANG\*(C'\fR chooses the collation locale. |
| 1022 | .IP "\s-1LC_MONETARY\s0" 12 |
| 1023 | .IX Item "LC_MONETARY" |
| 1024 | In the absence of \f(CW\*(C`LC_ALL\*(C'\fR, \f(CW\*(C`LC_MONETARY\*(C'\fR chooses the monetary |
| 1025 | formatting locale. In the absence of both \f(CW\*(C`LC_ALL\*(C'\fR and \f(CW\*(C`LC_MONETARY\*(C'\fR, |
| 1026 | \&\f(CW\*(C`LANG\*(C'\fR chooses the monetary formatting locale. |
| 1027 | .IP "\s-1LC_NUMERIC\s0" 12 |
| 1028 | .IX Item "LC_NUMERIC" |
| 1029 | In the absence of \f(CW\*(C`LC_ALL\*(C'\fR, \f(CW\*(C`LC_NUMERIC\*(C'\fR chooses the numeric format |
| 1030 | locale. In the absence of both \f(CW\*(C`LC_ALL\*(C'\fR and \f(CW\*(C`LC_NUMERIC\*(C'\fR, \f(CW\*(C`LANG\*(C'\fR |
| 1031 | chooses the numeric format. |
| 1032 | .IP "\s-1LC_TIME\s0" 12 |
| 1033 | .IX Item "LC_TIME" |
| 1034 | In the absence of \f(CW\*(C`LC_ALL\*(C'\fR, \f(CW\*(C`LC_TIME\*(C'\fR chooses the date and time |
| 1035 | formatting locale. In the absence of both \f(CW\*(C`LC_ALL\*(C'\fR and \f(CW\*(C`LC_TIME\*(C'\fR, |
| 1036 | \&\f(CW\*(C`LANG\*(C'\fR chooses the date and time formatting locale. |
| 1037 | .IP "\s-1LANG\s0" 12 |
| 1038 | .IX Item "LANG" |
| 1039 | \&\f(CW\*(C`LANG\*(C'\fR is the \*(L"catch\-all\*(R" locale environment variable. If it is set, it |
| 1040 | is used as the last resort after the overall \f(CW\*(C`LC_ALL\*(C'\fR and the |
| 1041 | category-specific \f(CW\*(C`LC_...\*(C'\fR. |
| 1042 | .SH "NOTES" |
| 1043 | .IX Header "NOTES" |
| 1044 | .Sh "Backward compatibility" |
| 1045 | .IX Subsection "Backward compatibility" |
| 1046 | Versions of Perl prior to 5.004 \fBmostly\fR ignored locale information, |
| 1047 | generally behaving as if something similar to the \f(CW"C"\fR locale were |
| 1048 | always in force, even if the program environment suggested otherwise |
| 1049 | (see \*(L"The setlocale function\*(R"). By default, Perl still behaves this |
| 1050 | way for backward compatibility. If you want a Perl application to pay |
| 1051 | attention to locale information, you \fBmust\fR use the \f(CW\*(C`use\ locale\*(C'\fR |
| 1052 | pragma (see \*(L"The use locale pragma\*(R") to instruct it to do so. |
| 1053 | .PP |
| 1054 | Versions of Perl from 5.002 to 5.003 did use the \f(CW\*(C`LC_CTYPE\*(C'\fR |
| 1055 | information if available; that is, \f(CW\*(C`\ew\*(C'\fR did understand what |
| 1056 | were the letters according to the locale environment variables. |
| 1057 | The problem was that the user had no control over the feature: |
| 1058 | if the C library supported locales, Perl used them. |
| 1059 | .Sh "I18N:Collate obsolete" |
| 1060 | .IX Subsection "I18N:Collate obsolete" |
| 1061 | In versions of Perl prior to 5.004, per-locale collation was possible |
| 1062 | using the \f(CW\*(C`I18N::Collate\*(C'\fR library module. This module is now mildly |
| 1063 | obsolete and should be avoided in new applications. The \f(CW\*(C`LC_COLLATE\*(C'\fR |
| 1064 | functionality is now integrated into the Perl core language: One can |
| 1065 | use locale-specific scalar data completely normally with \f(CW\*(C`use locale\*(C'\fR, |
| 1066 | so there is no longer any need to juggle with the scalar references of |
| 1067 | \&\f(CW\*(C`I18N::Collate\*(C'\fR. |
| 1068 | .Sh "Sort speed and memory use impacts" |
| 1069 | .IX Subsection "Sort speed and memory use impacts" |
| 1070 | Comparing and sorting by locale is usually slower than the default |
| 1071 | sorting; slow-downs of two to four times have been observed. It will |
| 1072 | also consume more memory: once a Perl scalar variable has participated |
| 1073 | in any string comparison or sorting operation obeying the locale |
| 1074 | collation rules, it will take 3\-15 times more memory than before. (The |
| 1075 | exact multiplier depends on the string's contents, the operating system |
| 1076 | and the locale.) These downsides are dictated more by the operating |
| 1077 | system's implementation of the locale system than by Perl. |
| 1078 | .Sh "\fIwrite()\fP and \s-1LC_NUMERIC\s0" |
| 1079 | .IX Subsection "write() and LC_NUMERIC" |
| 1080 | Formats are the only part of Perl that unconditionally use information |
| 1081 | from a program's locale; if a program's environment specifies an |
| 1082 | \&\s-1LC_NUMERIC\s0 locale, it is always used to specify the decimal point |
| 1083 | character in formatted output. Formatted output cannot be controlled by |
| 1084 | \&\f(CW\*(C`use locale\*(C'\fR because the pragma is tied to the block structure of the |
| 1085 | program, and, for historical reasons, formats exist outside that block |
| 1086 | structure. |
| 1087 | .Sh "Freely available locale definitions" |
| 1088 | .IX Subsection "Freely available locale definitions" |
| 1089 | There is a large collection of locale definitions at |
| 1090 | ftp://dkuug.dk/i18n/WG15\-collection . You should be aware that it is |
| 1091 | unsupported, and is not claimed to be fit for any purpose. If your |
| 1092 | system allows installation of arbitrary locales, you may find the |
| 1093 | definitions useful as they are, or as a basis for the development of |
| 1094 | your own locales. |
| 1095 | .Sh "I18n and l10n" |
| 1096 | .IX Subsection "I18n and l10n" |
| 1097 | \&\*(L"Internationalization\*(R" is often abbreviated as \fBi18n\fR because its first |
| 1098 | and last letters are separated by eighteen others. (You may guess why |
| 1099 | the internalin ... internaliti ... i18n tends to get abbreviated.) In |
| 1100 | the same way, \*(L"localization\*(R" is often abbreviated to \fBl10n\fR. |
| 1101 | .Sh "An imperfect standard" |
| 1102 | .IX Subsection "An imperfect standard" |
| 1103 | Internationalization, as defined in the C and \s-1POSIX\s0 standards, can be |
| 1104 | criticized as incomplete, ungainly, and having too large a granularity. |
| 1105 | (Locales apply to a whole process, when it would arguably be more useful |
| 1106 | to have them apply to a single thread, window group, or whatever.) They |
| 1107 | also have a tendency, like standards groups, to divide the world into |
| 1108 | nations, when we all know that the world can equally well be divided |
| 1109 | into bankers, bikers, gamers, and so on. But, for now, it's the only |
| 1110 | standard we've got. This may be construed as a bug. |
| 1111 | .SH "Unicode and UTF\-8" |
| 1112 | .IX Header "Unicode and UTF-8" |
| 1113 | The support of Unicode is new starting from Perl version 5.6, and |
| 1114 | more fully implemented in the version 5.8. See perluniintro and |
| 1115 | perlunicode for more details. |
| 1116 | .PP |
| 1117 | Usually locale settings and Unicode do not affect each other, but |
| 1118 | there are exceptions, see \*(L"Locales\*(R" in perlunicode for examples. |
| 1119 | .SH "BUGS" |
| 1120 | .IX Header "BUGS" |
| 1121 | .Sh "Broken systems" |
| 1122 | .IX Subsection "Broken systems" |
| 1123 | In certain systems, the operating system's locale support |
| 1124 | is broken and cannot be fixed or used by Perl. Such deficiencies can |
| 1125 | and will result in mysterious hangs and/or Perl core dumps when the |
| 1126 | \&\f(CW\*(C`use locale\*(C'\fR is in effect. When confronted with such a system, |
| 1127 | please report in excruciating detail to <\fIperlbug@perl.org\fR>, and |
| 1128 | complain to your vendor: bug fixes may exist for these problems |
| 1129 | in your operating system. Sometimes such bug fixes are called an |
| 1130 | operating system upgrade. |
| 1131 | .SH "SEE ALSO" |
| 1132 | .IX Header "SEE ALSO" |
| 1133 | I18N::Langinfo, perluniintro, perlunicode, open, |
| 1134 | \&\*(L"isalnum\*(R" in \s-1POSIX\s0, \*(L"isalpha\*(R" in \s-1POSIX\s0, |
| 1135 | \&\*(L"isdigit\*(R" in \s-1POSIX\s0, \*(L"isgraph\*(R" in \s-1POSIX\s0, \*(L"islower\*(R" in \s-1POSIX\s0, |
| 1136 | \&\*(L"isprint\*(R" in \s-1POSIX\s0, \*(L"ispunct\*(R" in \s-1POSIX\s0, \*(L"isspace\*(R" in \s-1POSIX\s0, |
| 1137 | \&\*(L"isupper\*(R" in \s-1POSIX\s0, \*(L"isxdigit\*(R" in \s-1POSIX\s0, \*(L"localeconv\*(R" in \s-1POSIX\s0, |
| 1138 | \&\*(L"setlocale\*(R" in \s-1POSIX\s0, \*(L"strcoll\*(R" in \s-1POSIX\s0, \*(L"strftime\*(R" in \s-1POSIX\s0, |
| 1139 | \&\*(L"strtod\*(R" in \s-1POSIX\s0, \*(L"strxfrm\*(R" in \s-1POSIX\s0. |
| 1140 | .SH "HISTORY" |
| 1141 | .IX Header "HISTORY" |
| 1142 | Jarkko Hietaniemi's original \fIperli18n.pod\fR heavily hacked by Dominic |
| 1143 | Dunlop, assisted by the perl5\-porters. Prose worked over a bit by |
| 1144 | Tom Christiansen. |
| 1145 | .PP |
| 1146 | Last update: Thu Jun 11 08:44:13 \s-1MDT\s0 1998 |