Commit | Line | Data |
---|---|---|
920dae64 AT |
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 "charnames 3" | |
132 | .TH charnames 3 "2001-09-21" "perl v5.8.8" "Perl Programmers Reference Guide" | |
133 | .SH "NAME" | |
134 | charnames \- define character names for \f(CW\*(C`\eN{named}\*(C'\fR string literal escapes | |
135 | .SH "SYNOPSIS" | |
136 | .IX Header "SYNOPSIS" | |
137 | .Vb 2 | |
138 | \& use charnames ':full'; | |
139 | \& print "\eN{GREEK SMALL LETTER SIGMA} is called sigma.\en"; | |
140 | .Ve | |
141 | .PP | |
142 | .Vb 2 | |
143 | \& use charnames ':short'; | |
144 | \& print "\eN{greek:Sigma} is an upper-case sigma.\en"; | |
145 | .Ve | |
146 | .PP | |
147 | .Vb 2 | |
148 | \& use charnames qw(cyrillic greek); | |
149 | \& print "\eN{sigma} is Greek sigma, and \eN{be} is Cyrillic b.\en"; | |
150 | .Ve | |
151 | .PP | |
152 | .Vb 4 | |
153 | \& use charnames ":full", ":alias" => { | |
154 | \& e_ACUTE => "LATIN SMALL LETTER E WITH ACUTE", | |
155 | \& }; | |
156 | \& print "\eN{e_ACUTE} is a small letter e with an acute.\en"; | |
157 | .Ve | |
158 | .PP | |
159 | .Vb 3 | |
160 | \& use charnames (); | |
161 | \& print charnames::viacode(0x1234); # prints "ETHIOPIC SYLLABLE SEE" | |
162 | \& printf "%04X", charnames::vianame("GOTHIC LETTER AHSA"); # prints "10330" | |
163 | .Ve | |
164 | .SH "DESCRIPTION" | |
165 | .IX Header "DESCRIPTION" | |
166 | Pragma \f(CW\*(C`use charnames\*(C'\fR supports arguments \f(CW\*(C`:full\*(C'\fR, \f(CW\*(C`:short\*(C'\fR, script | |
167 | names and customized aliases. If \f(CW\*(C`:full\*(C'\fR is present, for expansion of | |
168 | \&\f(CW\*(C`\eN{CHARNAME}\*(C'\fR, the string \f(CW\*(C`CHARNAME\*(C'\fR is first looked up in the list of | |
169 | standard Unicode character names. If \f(CW\*(C`:short\*(C'\fR is present, and | |
170 | \&\f(CW\*(C`CHARNAME\*(C'\fR has the form \f(CW\*(C`SCRIPT:CNAME\*(C'\fR, then \f(CW\*(C`CNAME\*(C'\fR is looked up | |
171 | as a letter in script \f(CW\*(C`SCRIPT\*(C'\fR. If pragma \f(CW\*(C`use charnames\*(C'\fR is used | |
172 | with script name arguments, then for \f(CW\*(C`\eN{CHARNAME}\*(C'\fR the name | |
173 | \&\f(CW\*(C`CHARNAME\*(C'\fR is looked up as a letter in the given scripts (in the | |
174 | specified order). Customized aliases are explained in \*(L"\s-1CUSTOM\s0 \s-1ALIASES\s0\*(R". | |
175 | .PP | |
176 | For lookup of \f(CW\*(C`CHARNAME\*(C'\fR inside a given script \f(CW\*(C`SCRIPTNAME\*(C'\fR | |
177 | this pragma looks for the names | |
178 | .PP | |
179 | .Vb 3 | |
180 | \& SCRIPTNAME CAPITAL LETTER CHARNAME | |
181 | \& SCRIPTNAME SMALL LETTER CHARNAME | |
182 | \& SCRIPTNAME LETTER CHARNAME | |
183 | .Ve | |
184 | .PP | |
185 | in the table of standard Unicode names. If \f(CW\*(C`CHARNAME\*(C'\fR is lowercase, | |
186 | then the \f(CW\*(C`CAPITAL\*(C'\fR variant is ignored, otherwise the \f(CW\*(C`SMALL\*(C'\fR variant | |
187 | is ignored. | |
188 | .PP | |
189 | Note that \f(CW\*(C`\eN{...}\*(C'\fR is compile\-time, it's a special form of string | |
190 | constant used inside double-quoted strings: in other words, you cannot | |
191 | use variables inside the \f(CW\*(C`\eN{...}\*(C'\fR. If you want similar run-time | |
192 | functionality, use \fIcharnames::vianame()\fR. | |
193 | .PP | |
194 | For the C0 and C1 control characters (U+0000..U+001F, U+0080..U+009F) | |
195 | as of Unicode 3.1, there are no official Unicode names but you can use | |
196 | instead the \s-1ISO\s0 6429 names (\s-1LINE\s0 \s-1FEED\s0, \s-1ESCAPE\s0, and so forth). In | |
197 | Unicode 3.2 (as of Perl 5.8) some naming changes take place \s-1ISO\s0 6429 | |
198 | has been updated, see \*(L"\s-1ALIASES\s0\*(R". Also note that the U+UU80, U+0081, | |
199 | U+0084, and U+0099 do not have names even in \s-1ISO\s0 6429. | |
200 | .PP | |
201 | Since the Unicode standard uses \*(L"U+HHHH\*(R", so can you: \*(L"\eN{U+263a}\*(R" | |
202 | is the Unicode smiley face, or \*(L"\eN{\s-1WHITE\s0 \s-1SMILING\s0 \s-1FACE\s0}\*(R". | |
203 | .SH "CUSTOM TRANSLATORS" | |
204 | .IX Header "CUSTOM TRANSLATORS" | |
205 | The mechanism of translation of \f(CW\*(C`\eN{...}\*(C'\fR escapes is general and not | |
206 | hardwired into \fIcharnames.pm\fR. A module can install custom | |
207 | translations (inside the scope which \f(CW\*(C`use\*(C'\fRs the module) with the | |
208 | following magic incantation: | |
209 | .PP | |
210 | .Vb 6 | |
211 | \& use charnames (); # for $charnames::hint_bits | |
212 | \& sub import { | |
213 | \& shift; | |
214 | \& $^H |= $charnames::hint_bits; | |
215 | \& $^H{charnames} = \e&translator; | |
216 | \& } | |
217 | .Ve | |
218 | .PP | |
219 | Here \fItranslator()\fR is a subroutine which takes \f(CW\*(C`CHARNAME\*(C'\fR as an | |
220 | argument, and returns text to insert into the string instead of the | |
221 | \&\f(CW\*(C`\eN{CHARNAME}\*(C'\fR escape. Since the text to insert should be different | |
222 | in \f(CW\*(C`bytes\*(C'\fR mode and out of it, the function should check the current | |
223 | state of \f(CW\*(C`bytes\*(C'\fR\-flag as in: | |
224 | .PP | |
225 | .Vb 9 | |
226 | \& use bytes (); # for $bytes::hint_bits | |
227 | \& sub translator { | |
228 | \& if ($^H & $bytes::hint_bits) { | |
229 | \& return bytes_translator(@_); | |
230 | \& } | |
231 | \& else { | |
232 | \& return utf8_translator(@_); | |
233 | \& } | |
234 | \& } | |
235 | .Ve | |
236 | .SH "CUSTOM ALIASES" | |
237 | .IX Header "CUSTOM ALIASES" | |
238 | This version of charnames supports three mechanisms of adding local | |
239 | or customized aliases to standard Unicode naming conventions (:full) | |
240 | .Sh "Anonymous hashes" | |
241 | .IX Subsection "Anonymous hashes" | |
242 | .Vb 4 | |
243 | \& use charnames ":full", ":alias" => { | |
244 | \& e_ACUTE => "LATIN SMALL LETTER E WITH ACUTE", | |
245 | \& }; | |
246 | \& my $str = "\eN{e_ACUTE}"; | |
247 | .Ve | |
248 | .Sh "Alias file" | |
249 | .IX Subsection "Alias file" | |
250 | .Vb 1 | |
251 | \& use charnames ":full", ":alias" => "pro"; | |
252 | .Ve | |
253 | .PP | |
254 | .Vb 2 | |
255 | \& will try to read "unicore/pro_alias.pl" from the @INC path. This | |
256 | \& file should return a list in plain perl: | |
257 | .Ve | |
258 | .PP | |
259 | .Vb 9 | |
260 | \& ( | |
261 | \& A_GRAVE => "LATIN CAPITAL LETTER A WITH GRAVE", | |
262 | \& A_CIRCUM => "LATIN CAPITAL LETTER A WITH CIRCUMFLEX", | |
263 | \& A_DIAERES => "LATIN CAPITAL LETTER A WITH DIAERESIS", | |
264 | \& A_TILDE => "LATIN CAPITAL LETTER A WITH TILDE", | |
265 | \& A_BREVE => "LATIN CAPITAL LETTER A WITH BREVE", | |
266 | \& A_RING => "LATIN CAPITAL LETTER A WITH RING ABOVE", | |
267 | \& A_MACRON => "LATIN CAPITAL LETTER A WITH MACRON", | |
268 | \& ); | |
269 | .Ve | |
270 | .Sh "Alias shortcut" | |
271 | .IX Subsection "Alias shortcut" | |
272 | .Vb 1 | |
273 | \& use charnames ":alias" => ":pro"; | |
274 | .Ve | |
275 | .PP | |
276 | .Vb 3 | |
277 | \& works exactly the same as the alias pairs, only this time, | |
278 | \& ":full" is inserted automatically as first argument (if no | |
279 | \& other argument is given). | |
280 | .Ve | |
281 | .SH "charnames::viacode(code)" | |
282 | .IX Header "charnames::viacode(code)" | |
283 | Returns the full name of the character indicated by the numeric code. | |
284 | The example | |
285 | .PP | |
286 | .Vb 1 | |
287 | \& print charnames::viacode(0x2722); | |
288 | .Ve | |
289 | .PP | |
290 | prints \*(L"\s-1FOUR\s0 TEARDROP-SPOKED \s-1ASTERISK\s0\*(R". | |
291 | .PP | |
292 | Returns undef if no name is known for the code. | |
293 | .PP | |
294 | This works only for the standard names, and does not yet apply | |
295 | to custom translators. | |
296 | .PP | |
297 | Notice that the name returned for of U+FEFF is \*(L"\s-1ZERO\s0 \s-1WIDTH\s0 NO-BREAK | |
298 | \&\s-1SPACE\s0\*(R", not \*(L"\s-1BYTE\s0 \s-1ORDER\s0 \s-1MARK\s0\*(R". | |
299 | .SH "charnames::vianame(name)" | |
300 | .IX Header "charnames::vianame(name)" | |
301 | Returns the code point indicated by the name. | |
302 | The example | |
303 | .PP | |
304 | .Vb 1 | |
305 | \& printf "%04X", charnames::vianame("FOUR TEARDROP-SPOKED ASTERISK"); | |
306 | .Ve | |
307 | .PP | |
308 | prints \*(L"2722\*(R". | |
309 | .PP | |
310 | Returns undef if the name is unknown. | |
311 | .PP | |
312 | This works only for the standard names, and does not yet apply | |
313 | to custom translators. | |
314 | .SH "ALIASES" | |
315 | .IX Header "ALIASES" | |
316 | A few aliases have been defined for convenience: instead of having | |
317 | to use the official names | |
318 | .PP | |
319 | .Vb 4 | |
320 | \& LINE FEED (LF) | |
321 | \& FORM FEED (FF) | |
322 | \& CARRIAGE RETURN (CR) | |
323 | \& NEXT LINE (NEL) | |
324 | .Ve | |
325 | .PP | |
326 | (yes, with parentheses) one can use | |
327 | .PP | |
328 | .Vb 8 | |
329 | \& LINE FEED | |
330 | \& FORM FEED | |
331 | \& CARRIAGE RETURN | |
332 | \& NEXT LINE | |
333 | \& LF | |
334 | \& FF | |
335 | \& CR | |
336 | \& NEL | |
337 | .Ve | |
338 | .PP | |
339 | One can also use | |
340 | .PP | |
341 | .Vb 2 | |
342 | \& BYTE ORDER MARK | |
343 | \& BOM | |
344 | .Ve | |
345 | .PP | |
346 | and | |
347 | .PP | |
348 | .Vb 2 | |
349 | \& ZWNJ | |
350 | \& ZWJ | |
351 | .Ve | |
352 | .PP | |
353 | for \s-1ZERO\s0 \s-1WIDTH\s0 NON-JOINER and \s-1ZERO\s0 \s-1WIDTH\s0 \s-1JOINER\s0. | |
354 | .PP | |
355 | For backward compatibility one can use the old names for | |
356 | certain C0 and C1 controls | |
357 | .PP | |
358 | .Vb 1 | |
359 | \& old new | |
360 | .Ve | |
361 | .PP | |
362 | .Vb 8 | |
363 | \& HORIZONTAL TABULATION CHARACTER TABULATION | |
364 | \& VERTICAL TABULATION LINE TABULATION | |
365 | \& FILE SEPARATOR INFORMATION SEPARATOR FOUR | |
366 | \& GROUP SEPARATOR INFORMATION SEPARATOR THREE | |
367 | \& RECORD SEPARATOR INFORMATION SEPARATOR TWO | |
368 | \& UNIT SEPARATOR INFORMATION SEPARATOR ONE | |
369 | \& PARTIAL LINE DOWN PARTIAL LINE FORWARD | |
370 | \& PARTIAL LINE UP PARTIAL LINE BACKWARD | |
371 | .Ve | |
372 | .PP | |
373 | but the old names in addition to giving the character | |
374 | will also give a warning about being deprecated. | |
375 | .SH "ILLEGAL CHARACTERS" | |
376 | .IX Header "ILLEGAL CHARACTERS" | |
377 | If you ask by name for a character that does not exist, a warning is | |
378 | given and the Unicode \fIreplacement character\fR \*(L"\ex{\s-1FFFD\s0}\*(R" is returned. | |
379 | .PP | |
380 | If you ask by code for a character that does not exist, no warning is | |
381 | given and \f(CW\*(C`undef\*(C'\fR is returned. (Though if you ask for a code point | |
382 | past U+10FFFF you do get a warning.) | |
383 | .SH "BUGS" | |
384 | .IX Header "BUGS" | |
385 | Since evaluation of the translation function happens in a middle of | |
386 | compilation (of a string literal), the translation function should not | |
387 | do any \f(CW\*(C`eval\*(C'\fRs or \f(CW\*(C`require\*(C'\fRs. This restriction should be lifted in | |
388 | a future version of Perl. |