7 use bytes (); # for $bytes::hint_bits
9 # The hashes are stored as utf8 strings. This makes it easier to deal with
10 # sequences. I (khw) also tried making Name.pl utf8, but it slowed things
11 # down by a factor of 7. I then tried making Name.pl store the ut8
12 # equivalents but not calling them utf8. That led to similar speed as leaving
13 # it alone, but since that is harder for a human to parse, I left it as-is.
15 my %system_aliases = (
16 # Icky 3.2 names with parentheses.
17 'LINE FEED' => pack("U", 0x0A), # LINE FEED (LF)
18 'FORM FEED' => pack("U", 0x0C), # FORM FEED (FF)
19 'CARRIAGE RETURN' => pack("U", 0x0D), # CARRIAGE RETURN (CR)
20 'NEXT LINE' => pack("U", 0x85), # NEXT LINE (NEL)
22 # Some variant names from Wikipedia
23 'SINGLE-SHIFT 2' => pack("U", 0x8E),
24 'SINGLE-SHIFT 3' => pack("U", 0x8F),
25 'PRIVATE USE 1' => pack("U", 0x91),
26 'PRIVATE USE 2' => pack("U", 0x92),
27 'START OF PROTECTED AREA' => pack("U", 0x96),
28 'END OF PROTECTED AREA' => pack("U", 0x97),
30 # Convenience. Standard abbreviations for the controls
31 'NUL' => pack("U", 0x00), # NULL
32 'SOH' => pack("U", 0x01), # START OF HEADING
33 'STX' => pack("U", 0x02), # START OF TEXT
34 'ETX' => pack("U", 0x03), # END OF TEXT
35 'EOT' => pack("U", 0x04), # END OF TRANSMISSION
36 'ENQ' => pack("U", 0x05), # ENQUIRY
37 'ACK' => pack("U", 0x06), # ACKNOWLEDGE
38 'BEL' => pack("U", 0x07), # ALERT; formerly BELL
39 'BS' => pack("U", 0x08), # BACKSPACE
40 'HT' => pack("U", 0x09), # HORIZONTAL TABULATION
41 'LF' => pack("U", 0x0A), # LINE FEED (LF)
42 'VT' => pack("U", 0x0B), # VERTICAL TABULATION
43 'FF' => pack("U", 0x0C), # FORM FEED (FF)
44 'CR' => pack("U", 0x0D), # CARRIAGE RETURN (CR)
45 'SO' => pack("U", 0x0E), # SHIFT OUT
46 'SI' => pack("U", 0x0F), # SHIFT IN
47 'DLE' => pack("U", 0x10), # DATA LINK ESCAPE
48 'DC1' => pack("U", 0x11), # DEVICE CONTROL ONE
49 'DC2' => pack("U", 0x12), # DEVICE CONTROL TWO
50 'DC3' => pack("U", 0x13), # DEVICE CONTROL THREE
51 'DC4' => pack("U", 0x14), # DEVICE CONTROL FOUR
52 'NAK' => pack("U", 0x15), # NEGATIVE ACKNOWLEDGE
53 'SYN' => pack("U", 0x16), # SYNCHRONOUS IDLE
54 'ETB' => pack("U", 0x17), # END OF TRANSMISSION BLOCK
55 'CAN' => pack("U", 0x18), # CANCEL
56 'EOM' => pack("U", 0x19), # END OF MEDIUM
57 'SUB' => pack("U", 0x1A), # SUBSTITUTE
58 'ESC' => pack("U", 0x1B), # ESCAPE
59 'FS' => pack("U", 0x1C), # FILE SEPARATOR
60 'GS' => pack("U", 0x1D), # GROUP SEPARATOR
61 'RS' => pack("U", 0x1E), # RECORD SEPARATOR
62 'US' => pack("U", 0x1F), # UNIT SEPARATOR
63 'DEL' => pack("U", 0x7F), # DELETE
64 'BPH' => pack("U", 0x82), # BREAK PERMITTED HERE
65 'NBH' => pack("U", 0x83), # NO BREAK HERE
66 'NEL' => pack("U", 0x85), # NEXT LINE (NEL)
67 'SSA' => pack("U", 0x86), # START OF SELECTED AREA
68 'ESA' => pack("U", 0x87), # END OF SELECTED AREA
69 'HTS' => pack("U", 0x88), # CHARACTER TABULATION SET
70 'HTJ' => pack("U", 0x89), # CHARACTER TABULATION WITH JUSTIFICATION
71 'VTS' => pack("U", 0x8A), # LINE TABULATION SET
72 'PLD' => pack("U", 0x8B), # PARTIAL LINE FORWARD
73 'PLU' => pack("U", 0x8C), # PARTIAL LINE BACKWARD
74 'RI ' => pack("U", 0x8D), # REVERSE LINE FEED
75 'SS2' => pack("U", 0x8E), # SINGLE SHIFT TWO
76 'SS3' => pack("U", 0x8F), # SINGLE SHIFT THREE
77 'DCS' => pack("U", 0x90), # DEVICE CONTROL STRING
78 'PU1' => pack("U", 0x91), # PRIVATE USE ONE
79 'PU2' => pack("U", 0x92), # PRIVATE USE TWO
80 'STS' => pack("U", 0x93), # SET TRANSMIT STATE
81 'CCH' => pack("U", 0x94), # CANCEL CHARACTER
82 'MW ' => pack("U", 0x95), # MESSAGE WAITING
83 'SPA' => pack("U", 0x96), # START OF GUARDED AREA
84 'EPA' => pack("U", 0x97), # END OF GUARDED AREA
85 'SOS' => pack("U", 0x98), # START OF STRING
86 'SCI' => pack("U", 0x9A), # SINGLE CHARACTER INTRODUCER
87 'CSI' => pack("U", 0x9B), # CONTROL SEQUENCE INTRODUCER
88 'ST ' => pack("U", 0x9C), # STRING TERMINATOR
89 'OSC' => pack("U", 0x9D), # OPERATING SYSTEM COMMAND
90 'PM ' => pack("U", 0x9E), # PRIVACY MESSAGE
91 'APC' => pack("U", 0x9F), # APPLICATION PROGRAM COMMAND
93 # There are no names for these in the Unicode standard; perhaps should be
94 # deprecated, but then again there are no alternative names, so am not
95 # deprecating. And if did, the code would have to change to not recommend
96 # an alternative for these.
97 'PADDING CHARACTER' => pack("U", 0x80),
98 'PAD' => pack("U", 0x80),
99 'HIGH OCTET PRESET' => pack("U", 0x81),
100 'HOP' => pack("U", 0x81),
101 'INDEX' => pack("U", 0x84),
102 'IND' => pack("U", 0x84),
103 'SINGLE GRAPHIC CHARACTER INTRODUCER' => pack("U", 0x99),
104 'SGC' => pack("U", 0x99),
106 # More convenience. For further convenience, it is suggested some way of
107 # using the NamesList aliases be implemented, but there are ambiguities in
109 'BOM' => pack("U", 0xFEFF), # BYTE ORDER MARK
110 'BYTE ORDER MARK'=> pack("U", 0xFEFF),
111 'CGJ' => pack("U", 0x034F), # COMBINING GRAPHEME JOINER
112 'FVS1' => pack("U", 0x180B), # MONGOLIAN FREE VARIATION SELECTOR ONE
113 'FVS2' => pack("U", 0x180C), # MONGOLIAN FREE VARIATION SELECTOR TWO
114 'FVS3' => pack("U", 0x180D), # MONGOLIAN FREE VARIATION SELECTOR THREE
115 'LRE' => pack("U", 0x202A), # LEFT-TO-RIGHT EMBEDDING
116 'LRM' => pack("U", 0x200E), # LEFT-TO-RIGHT MARK
117 'LRO' => pack("U", 0x202D), # LEFT-TO-RIGHT OVERRIDE
118 'MMSP' => pack("U", 0x205F), # MEDIUM MATHEMATICAL SPACE
119 'MVS' => pack("U", 0x180E), # MONGOLIAN VOWEL SEPARATOR
120 'NBSP' => pack("U", 0x00A0), # NO-BREAK SPACE
121 'NNBSP' => pack("U", 0x202F), # NARROW NO-BREAK SPACE
122 'PDF' => pack("U", 0x202C), # POP DIRECTIONAL FORMATTING
123 'RLE' => pack("U", 0x202B), # RIGHT-TO-LEFT EMBEDDING
124 'RLM' => pack("U", 0x200F), # RIGHT-TO-LEFT MARK
125 'RLO' => pack("U", 0x202E), # RIGHT-TO-LEFT OVERRIDE
126 'SHY' => pack("U", 0x00AD), # SOFT HYPHEN
127 'VS1' => pack("U", 0xFE00), # VARIATION SELECTOR-1
128 'VS2' => pack("U", 0xFE01), # VARIATION SELECTOR-2
129 'VS3' => pack("U", 0xFE02), # VARIATION SELECTOR-3
130 'VS4' => pack("U", 0xFE03), # VARIATION SELECTOR-4
131 'VS5' => pack("U", 0xFE04), # VARIATION SELECTOR-5
132 'VS6' => pack("U", 0xFE05), # VARIATION SELECTOR-6
133 'VS7' => pack("U", 0xFE06), # VARIATION SELECTOR-7
134 'VS8' => pack("U", 0xFE07), # VARIATION SELECTOR-8
135 'VS9' => pack("U", 0xFE08), # VARIATION SELECTOR-9
136 'VS10' => pack("U", 0xFE09), # VARIATION SELECTOR-10
137 'VS11' => pack("U", 0xFE0A), # VARIATION SELECTOR-11
138 'VS12' => pack("U", 0xFE0B), # VARIATION SELECTOR-12
139 'VS13' => pack("U", 0xFE0C), # VARIATION SELECTOR-13
140 'VS14' => pack("U", 0xFE0D), # VARIATION SELECTOR-14
141 'VS15' => pack("U", 0xFE0E), # VARIATION SELECTOR-15
142 'VS16' => pack("U", 0xFE0F), # VARIATION SELECTOR-16
143 'VS17' => pack("U", 0xE0100), # VARIATION SELECTOR-17
144 'VS18' => pack("U", 0xE0101), # VARIATION SELECTOR-18
145 'VS19' => pack("U", 0xE0102), # VARIATION SELECTOR-19
146 'VS20' => pack("U", 0xE0103), # VARIATION SELECTOR-20
147 'VS21' => pack("U", 0xE0104), # VARIATION SELECTOR-21
148 'VS22' => pack("U", 0xE0105), # VARIATION SELECTOR-22
149 'VS23' => pack("U", 0xE0106), # VARIATION SELECTOR-23
150 'VS24' => pack("U", 0xE0107), # VARIATION SELECTOR-24
151 'VS25' => pack("U", 0xE0108), # VARIATION SELECTOR-25
152 'VS26' => pack("U", 0xE0109), # VARIATION SELECTOR-26
153 'VS27' => pack("U", 0xE010A), # VARIATION SELECTOR-27
154 'VS28' => pack("U", 0xE010B), # VARIATION SELECTOR-28
155 'VS29' => pack("U", 0xE010C), # VARIATION SELECTOR-29
156 'VS30' => pack("U", 0xE010D), # VARIATION SELECTOR-30
157 'VS31' => pack("U", 0xE010E), # VARIATION SELECTOR-31
158 'VS32' => pack("U", 0xE010F), # VARIATION SELECTOR-32
159 'VS33' => pack("U", 0xE0110), # VARIATION SELECTOR-33
160 'VS34' => pack("U", 0xE0111), # VARIATION SELECTOR-34
161 'VS35' => pack("U", 0xE0112), # VARIATION SELECTOR-35
162 'VS36' => pack("U", 0xE0113), # VARIATION SELECTOR-36
163 'VS37' => pack("U", 0xE0114), # VARIATION SELECTOR-37
164 'VS38' => pack("U", 0xE0115), # VARIATION SELECTOR-38
165 'VS39' => pack("U", 0xE0116), # VARIATION SELECTOR-39
166 'VS40' => pack("U", 0xE0117), # VARIATION SELECTOR-40
167 'VS41' => pack("U", 0xE0118), # VARIATION SELECTOR-41
168 'VS42' => pack("U", 0xE0119), # VARIATION SELECTOR-42
169 'VS43' => pack("U", 0xE011A), # VARIATION SELECTOR-43
170 'VS44' => pack("U", 0xE011B), # VARIATION SELECTOR-44
171 'VS45' => pack("U", 0xE011C), # VARIATION SELECTOR-45
172 'VS46' => pack("U", 0xE011D), # VARIATION SELECTOR-46
173 'VS47' => pack("U", 0xE011E), # VARIATION SELECTOR-47
174 'VS48' => pack("U", 0xE011F), # VARIATION SELECTOR-48
175 'VS49' => pack("U", 0xE0120), # VARIATION SELECTOR-49
176 'VS50' => pack("U", 0xE0121), # VARIATION SELECTOR-50
177 'VS51' => pack("U", 0xE0122), # VARIATION SELECTOR-51
178 'VS52' => pack("U", 0xE0123), # VARIATION SELECTOR-52
179 'VS53' => pack("U", 0xE0124), # VARIATION SELECTOR-53
180 'VS54' => pack("U", 0xE0125), # VARIATION SELECTOR-54
181 'VS55' => pack("U", 0xE0126), # VARIATION SELECTOR-55
182 'VS56' => pack("U", 0xE0127), # VARIATION SELECTOR-56
183 'VS57' => pack("U", 0xE0128), # VARIATION SELECTOR-57
184 'VS58' => pack("U", 0xE0129), # VARIATION SELECTOR-58
185 'VS59' => pack("U", 0xE012A), # VARIATION SELECTOR-59
186 'VS60' => pack("U", 0xE012B), # VARIATION SELECTOR-60
187 'VS61' => pack("U", 0xE012C), # VARIATION SELECTOR-61
188 'VS62' => pack("U", 0xE012D), # VARIATION SELECTOR-62
189 'VS63' => pack("U", 0xE012E), # VARIATION SELECTOR-63
190 'VS64' => pack("U", 0xE012F), # VARIATION SELECTOR-64
191 'VS65' => pack("U", 0xE0130), # VARIATION SELECTOR-65
192 'VS66' => pack("U", 0xE0131), # VARIATION SELECTOR-66
193 'VS67' => pack("U", 0xE0132), # VARIATION SELECTOR-67
194 'VS68' => pack("U", 0xE0133), # VARIATION SELECTOR-68
195 'VS69' => pack("U", 0xE0134), # VARIATION SELECTOR-69
196 'VS70' => pack("U", 0xE0135), # VARIATION SELECTOR-70
197 'VS71' => pack("U", 0xE0136), # VARIATION SELECTOR-71
198 'VS72' => pack("U", 0xE0137), # VARIATION SELECTOR-72
199 'VS73' => pack("U", 0xE0138), # VARIATION SELECTOR-73
200 'VS74' => pack("U", 0xE0139), # VARIATION SELECTOR-74
201 'VS75' => pack("U", 0xE013A), # VARIATION SELECTOR-75
202 'VS76' => pack("U", 0xE013B), # VARIATION SELECTOR-76
203 'VS77' => pack("U", 0xE013C), # VARIATION SELECTOR-77
204 'VS78' => pack("U", 0xE013D), # VARIATION SELECTOR-78
205 'VS79' => pack("U", 0xE013E), # VARIATION SELECTOR-79
206 'VS80' => pack("U", 0xE013F), # VARIATION SELECTOR-80
207 'VS81' => pack("U", 0xE0140), # VARIATION SELECTOR-81
208 'VS82' => pack("U", 0xE0141), # VARIATION SELECTOR-82
209 'VS83' => pack("U", 0xE0142), # VARIATION SELECTOR-83
210 'VS84' => pack("U", 0xE0143), # VARIATION SELECTOR-84
211 'VS85' => pack("U", 0xE0144), # VARIATION SELECTOR-85
212 'VS86' => pack("U", 0xE0145), # VARIATION SELECTOR-86
213 'VS87' => pack("U", 0xE0146), # VARIATION SELECTOR-87
214 'VS88' => pack("U", 0xE0147), # VARIATION SELECTOR-88
215 'VS89' => pack("U", 0xE0148), # VARIATION SELECTOR-89
216 'VS90' => pack("U", 0xE0149), # VARIATION SELECTOR-90
217 'VS91' => pack("U", 0xE014A), # VARIATION SELECTOR-91
218 'VS92' => pack("U", 0xE014B), # VARIATION SELECTOR-92
219 'VS93' => pack("U", 0xE014C), # VARIATION SELECTOR-93
220 'VS94' => pack("U", 0xE014D), # VARIATION SELECTOR-94
221 'VS95' => pack("U", 0xE014E), # VARIATION SELECTOR-95
222 'VS96' => pack("U", 0xE014F), # VARIATION SELECTOR-96
223 'VS97' => pack("U", 0xE0150), # VARIATION SELECTOR-97
224 'VS98' => pack("U", 0xE0151), # VARIATION SELECTOR-98
225 'VS99' => pack("U", 0xE0152), # VARIATION SELECTOR-99
226 'VS100' => pack("U", 0xE0153), # VARIATION SELECTOR-100
227 'VS101' => pack("U", 0xE0154), # VARIATION SELECTOR-101
228 'VS102' => pack("U", 0xE0155), # VARIATION SELECTOR-102
229 'VS103' => pack("U", 0xE0156), # VARIATION SELECTOR-103
230 'VS104' => pack("U", 0xE0157), # VARIATION SELECTOR-104
231 'VS105' => pack("U", 0xE0158), # VARIATION SELECTOR-105
232 'VS106' => pack("U", 0xE0159), # VARIATION SELECTOR-106
233 'VS107' => pack("U", 0xE015A), # VARIATION SELECTOR-107
234 'VS108' => pack("U", 0xE015B), # VARIATION SELECTOR-108
235 'VS109' => pack("U", 0xE015C), # VARIATION SELECTOR-109
236 'VS110' => pack("U", 0xE015D), # VARIATION SELECTOR-110
237 'VS111' => pack("U", 0xE015E), # VARIATION SELECTOR-111
238 'VS112' => pack("U", 0xE015F), # VARIATION SELECTOR-112
239 'VS113' => pack("U", 0xE0160), # VARIATION SELECTOR-113
240 'VS114' => pack("U", 0xE0161), # VARIATION SELECTOR-114
241 'VS115' => pack("U", 0xE0162), # VARIATION SELECTOR-115
242 'VS116' => pack("U", 0xE0163), # VARIATION SELECTOR-116
243 'VS117' => pack("U", 0xE0164), # VARIATION SELECTOR-117
244 'VS118' => pack("U", 0xE0165), # VARIATION SELECTOR-118
245 'VS119' => pack("U", 0xE0166), # VARIATION SELECTOR-119
246 'VS120' => pack("U", 0xE0167), # VARIATION SELECTOR-120
247 'VS121' => pack("U", 0xE0168), # VARIATION SELECTOR-121
248 'VS122' => pack("U", 0xE0169), # VARIATION SELECTOR-122
249 'VS123' => pack("U", 0xE016A), # VARIATION SELECTOR-123
250 'VS124' => pack("U", 0xE016B), # VARIATION SELECTOR-124
251 'VS125' => pack("U", 0xE016C), # VARIATION SELECTOR-125
252 'VS126' => pack("U", 0xE016D), # VARIATION SELECTOR-126
253 'VS127' => pack("U", 0xE016E), # VARIATION SELECTOR-127
254 'VS128' => pack("U", 0xE016F), # VARIATION SELECTOR-128
255 'VS129' => pack("U", 0xE0170), # VARIATION SELECTOR-129
256 'VS130' => pack("U", 0xE0171), # VARIATION SELECTOR-130
257 'VS131' => pack("U", 0xE0172), # VARIATION SELECTOR-131
258 'VS132' => pack("U", 0xE0173), # VARIATION SELECTOR-132
259 'VS133' => pack("U", 0xE0174), # VARIATION SELECTOR-133
260 'VS134' => pack("U", 0xE0175), # VARIATION SELECTOR-134
261 'VS135' => pack("U", 0xE0176), # VARIATION SELECTOR-135
262 'VS136' => pack("U", 0xE0177), # VARIATION SELECTOR-136
263 'VS137' => pack("U", 0xE0178), # VARIATION SELECTOR-137
264 'VS138' => pack("U", 0xE0179), # VARIATION SELECTOR-138
265 'VS139' => pack("U", 0xE017A), # VARIATION SELECTOR-139
266 'VS140' => pack("U", 0xE017B), # VARIATION SELECTOR-140
267 'VS141' => pack("U", 0xE017C), # VARIATION SELECTOR-141
268 'VS142' => pack("U", 0xE017D), # VARIATION SELECTOR-142
269 'VS143' => pack("U", 0xE017E), # VARIATION SELECTOR-143
270 'VS144' => pack("U", 0xE017F), # VARIATION SELECTOR-144
271 'VS145' => pack("U", 0xE0180), # VARIATION SELECTOR-145
272 'VS146' => pack("U", 0xE0181), # VARIATION SELECTOR-146
273 'VS147' => pack("U", 0xE0182), # VARIATION SELECTOR-147
274 'VS148' => pack("U", 0xE0183), # VARIATION SELECTOR-148
275 'VS149' => pack("U", 0xE0184), # VARIATION SELECTOR-149
276 'VS150' => pack("U", 0xE0185), # VARIATION SELECTOR-150
277 'VS151' => pack("U", 0xE0186), # VARIATION SELECTOR-151
278 'VS152' => pack("U", 0xE0187), # VARIATION SELECTOR-152
279 'VS153' => pack("U", 0xE0188), # VARIATION SELECTOR-153
280 'VS154' => pack("U", 0xE0189), # VARIATION SELECTOR-154
281 'VS155' => pack("U", 0xE018A), # VARIATION SELECTOR-155
282 'VS156' => pack("U", 0xE018B), # VARIATION SELECTOR-156
283 'VS157' => pack("U", 0xE018C), # VARIATION SELECTOR-157
284 'VS158' => pack("U", 0xE018D), # VARIATION SELECTOR-158
285 'VS159' => pack("U", 0xE018E), # VARIATION SELECTOR-159
286 'VS160' => pack("U", 0xE018F), # VARIATION SELECTOR-160
287 'VS161' => pack("U", 0xE0190), # VARIATION SELECTOR-161
288 'VS162' => pack("U", 0xE0191), # VARIATION SELECTOR-162
289 'VS163' => pack("U", 0xE0192), # VARIATION SELECTOR-163
290 'VS164' => pack("U", 0xE0193), # VARIATION SELECTOR-164
291 'VS165' => pack("U", 0xE0194), # VARIATION SELECTOR-165
292 'VS166' => pack("U", 0xE0195), # VARIATION SELECTOR-166
293 'VS167' => pack("U", 0xE0196), # VARIATION SELECTOR-167
294 'VS168' => pack("U", 0xE0197), # VARIATION SELECTOR-168
295 'VS169' => pack("U", 0xE0198), # VARIATION SELECTOR-169
296 'VS170' => pack("U", 0xE0199), # VARIATION SELECTOR-170
297 'VS171' => pack("U", 0xE019A), # VARIATION SELECTOR-171
298 'VS172' => pack("U", 0xE019B), # VARIATION SELECTOR-172
299 'VS173' => pack("U", 0xE019C), # VARIATION SELECTOR-173
300 'VS174' => pack("U", 0xE019D), # VARIATION SELECTOR-174
301 'VS175' => pack("U", 0xE019E), # VARIATION SELECTOR-175
302 'VS176' => pack("U", 0xE019F), # VARIATION SELECTOR-176
303 'VS177' => pack("U", 0xE01A0), # VARIATION SELECTOR-177
304 'VS178' => pack("U", 0xE01A1), # VARIATION SELECTOR-178
305 'VS179' => pack("U", 0xE01A2), # VARIATION SELECTOR-179
306 'VS180' => pack("U", 0xE01A3), # VARIATION SELECTOR-180
307 'VS181' => pack("U", 0xE01A4), # VARIATION SELECTOR-181
308 'VS182' => pack("U", 0xE01A5), # VARIATION SELECTOR-182
309 'VS183' => pack("U", 0xE01A6), # VARIATION SELECTOR-183
310 'VS184' => pack("U", 0xE01A7), # VARIATION SELECTOR-184
311 'VS185' => pack("U", 0xE01A8), # VARIATION SELECTOR-185
312 'VS186' => pack("U", 0xE01A9), # VARIATION SELECTOR-186
313 'VS187' => pack("U", 0xE01AA), # VARIATION SELECTOR-187
314 'VS188' => pack("U", 0xE01AB), # VARIATION SELECTOR-188
315 'VS189' => pack("U", 0xE01AC), # VARIATION SELECTOR-189
316 'VS190' => pack("U", 0xE01AD), # VARIATION SELECTOR-190
317 'VS191' => pack("U", 0xE01AE), # VARIATION SELECTOR-191
318 'VS192' => pack("U", 0xE01AF), # VARIATION SELECTOR-192
319 'VS193' => pack("U", 0xE01B0), # VARIATION SELECTOR-193
320 'VS194' => pack("U", 0xE01B1), # VARIATION SELECTOR-194
321 'VS195' => pack("U", 0xE01B2), # VARIATION SELECTOR-195
322 'VS196' => pack("U", 0xE01B3), # VARIATION SELECTOR-196
323 'VS197' => pack("U", 0xE01B4), # VARIATION SELECTOR-197
324 'VS198' => pack("U", 0xE01B5), # VARIATION SELECTOR-198
325 'VS199' => pack("U", 0xE01B6), # VARIATION SELECTOR-199
326 'VS200' => pack("U", 0xE01B7), # VARIATION SELECTOR-200
327 'VS201' => pack("U", 0xE01B8), # VARIATION SELECTOR-201
328 'VS202' => pack("U", 0xE01B9), # VARIATION SELECTOR-202
329 'VS203' => pack("U", 0xE01BA), # VARIATION SELECTOR-203
330 'VS204' => pack("U", 0xE01BB), # VARIATION SELECTOR-204
331 'VS205' => pack("U", 0xE01BC), # VARIATION SELECTOR-205
332 'VS206' => pack("U", 0xE01BD), # VARIATION SELECTOR-206
333 'VS207' => pack("U", 0xE01BE), # VARIATION SELECTOR-207
334 'VS208' => pack("U", 0xE01BF), # VARIATION SELECTOR-208
335 'VS209' => pack("U", 0xE01C0), # VARIATION SELECTOR-209
336 'VS210' => pack("U", 0xE01C1), # VARIATION SELECTOR-210
337 'VS211' => pack("U", 0xE01C2), # VARIATION SELECTOR-211
338 'VS212' => pack("U", 0xE01C3), # VARIATION SELECTOR-212
339 'VS213' => pack("U", 0xE01C4), # VARIATION SELECTOR-213
340 'VS214' => pack("U", 0xE01C5), # VARIATION SELECTOR-214
341 'VS215' => pack("U", 0xE01C6), # VARIATION SELECTOR-215
342 'VS216' => pack("U", 0xE01C7), # VARIATION SELECTOR-216
343 'VS217' => pack("U", 0xE01C8), # VARIATION SELECTOR-217
344 'VS218' => pack("U", 0xE01C9), # VARIATION SELECTOR-218
345 'VS219' => pack("U", 0xE01CA), # VARIATION SELECTOR-219
346 'VS220' => pack("U", 0xE01CB), # VARIATION SELECTOR-220
347 'VS221' => pack("U", 0xE01CC), # VARIATION SELECTOR-221
348 'VS222' => pack("U", 0xE01CD), # VARIATION SELECTOR-222
349 'VS223' => pack("U", 0xE01CE), # VARIATION SELECTOR-223
350 'VS224' => pack("U", 0xE01CF), # VARIATION SELECTOR-224
351 'VS225' => pack("U", 0xE01D0), # VARIATION SELECTOR-225
352 'VS226' => pack("U", 0xE01D1), # VARIATION SELECTOR-226
353 'VS227' => pack("U", 0xE01D2), # VARIATION SELECTOR-227
354 'VS228' => pack("U", 0xE01D3), # VARIATION SELECTOR-228
355 'VS229' => pack("U", 0xE01D4), # VARIATION SELECTOR-229
356 'VS230' => pack("U", 0xE01D5), # VARIATION SELECTOR-230
357 'VS231' => pack("U", 0xE01D6), # VARIATION SELECTOR-231
358 'VS232' => pack("U", 0xE01D7), # VARIATION SELECTOR-232
359 'VS233' => pack("U", 0xE01D8), # VARIATION SELECTOR-233
360 'VS234' => pack("U", 0xE01D9), # VARIATION SELECTOR-234
361 'VS235' => pack("U", 0xE01DA), # VARIATION SELECTOR-235
362 'VS236' => pack("U", 0xE01DB), # VARIATION SELECTOR-236
363 'VS237' => pack("U", 0xE01DC), # VARIATION SELECTOR-237
364 'VS238' => pack("U", 0xE01DD), # VARIATION SELECTOR-238
365 'VS239' => pack("U", 0xE01DE), # VARIATION SELECTOR-239
366 'VS240' => pack("U", 0xE01DF), # VARIATION SELECTOR-240
367 'VS241' => pack("U", 0xE01E0), # VARIATION SELECTOR-241
368 'VS242' => pack("U", 0xE01E1), # VARIATION SELECTOR-242
369 'VS243' => pack("U", 0xE01E2), # VARIATION SELECTOR-243
370 'VS244' => pack("U", 0xE01E3), # VARIATION SELECTOR-244
371 'VS245' => pack("U", 0xE01E4), # VARIATION SELECTOR-245
372 'VS246' => pack("U", 0xE01E5), # VARIATION SELECTOR-246
373 'VS247' => pack("U", 0xE01E6), # VARIATION SELECTOR-247
374 'VS248' => pack("U", 0xE01E7), # VARIATION SELECTOR-248
375 'VS249' => pack("U", 0xE01E8), # VARIATION SELECTOR-249
376 'VS250' => pack("U", 0xE01E9), # VARIATION SELECTOR-250
377 'VS251' => pack("U", 0xE01EA), # VARIATION SELECTOR-251
378 'VS252' => pack("U", 0xE01EB), # VARIATION SELECTOR-252
379 'VS253' => pack("U", 0xE01EC), # VARIATION SELECTOR-253
380 'VS254' => pack("U", 0xE01ED), # VARIATION SELECTOR-254
381 'VS255' => pack("U", 0xE01EE), # VARIATION SELECTOR-255
382 'VS256' => pack("U", 0xE01EF), # VARIATION SELECTOR-256
383 'WJ' => pack("U", 0x2060), # WORD JOINER
384 'ZWJ' => pack("U", 0x200D), # ZERO WIDTH JOINER
385 'ZWNJ' => pack("U", 0x200C), # ZERO WIDTH NON-JOINER
386 'ZWSP' => pack("U", 0x200B), # ZERO WIDTH SPACE
389 my %deprecated_aliases = (
390 # Pre-3.2 compatibility (only for the first 256 characters).
391 # Use of these gives deprecated message.
392 'HORIZONTAL TABULATION' => pack("U", 0x09), # CHARACTER TABULATION
393 'VERTICAL TABULATION' => pack("U", 0x0B), # LINE TABULATION
394 'FILE SEPARATOR' => pack("U", 0x1C), # INFORMATION SEPARATOR FOUR
395 'GROUP SEPARATOR' => pack("U", 0x1D), # INFORMATION SEPARATOR THREE
396 'RECORD SEPARATOR' => pack("U", 0x1E), # INFORMATION SEPARATOR TWO
397 'UNIT SEPARATOR' => pack("U", 0x1F), # INFORMATION SEPARATOR ONE
398 'HORIZONTAL TABULATION SET' => pack("U", 0x88), # CHARACTER TABULATION SET
399 'HORIZONTAL TABULATION WITH JUSTIFICATION' => pack("U", 0x89), # CHARACTER TABULATION WITH JUSTIFICATION
400 'PARTIAL LINE DOWN' => pack("U", 0x8B), # PARTIAL LINE FORWARD
401 'PARTIAL LINE UP' => pack("U", 0x8C), # PARTIAL LINE BACKWARD
402 'VERTICAL TABULATION SET' => pack("U", 0x8A), # LINE TABULATION SET
403 'REVERSE INDEX' => pack("U", 0x8D), # REVERSE LINE FEED
405 # Unicode 6.0 co-opted this for U+1F514, so deprecate it for now.
406 'BELL' => pack("U", 0x07),
410 my $txt; # The table of official character names
412 my %full_names_cache; # Holds already-looked-up names, so don't have to
413 # re-look them up again. The previous versions of charnames had scoping
414 # bugs. For example if we use script A in one scope and find and cache
415 # what Z resolves to, we can't use that cache in a different scope that
416 # uses script B instead of A, as Z might be an entirely different letter
417 # there; or there might be different aliases in effect in different
418 # scopes, or :short may be in effect or not effect in different scopes,
419 # or various combinations thereof. This was solved in this version
420 # mostly by moving things to %^H. But some things couldn't be moved
421 # there. One of them was the cache of runtime looked-up names, in part
422 # because %^H is read-only at runtime. I (khw) don't know why the cache
423 # was run-time only in the previous versions: perhaps oversight; perhaps
424 # that compile time looking doesn't happen in a loop so didn't think it
425 # was worthwhile; perhaps not wanting to make the cache too large. But
426 # I decided to make it compile time as well; this could easily be
428 # Anyway, this hash is not scoped, and is added to at runtime. It
429 # doesn't have scoping problems because the data in it is restricted to
430 # official names, which are always invariant, and we only set it and
431 # look at it at during :full lookups, so is unaffected by any other
432 # scoped options. I put this in to maintain parity with the older
433 # version. If desired, a %short_names cache could also be made, as well
434 # as one for each script, say in %script_names_cache, with each key
435 # being a hash for a script named in a 'use charnames' statement. I
436 # decided not to do that for now, just because it's added complication,
437 # and because I'm just trying to maintain parity, not extend it.
439 # Designed so that test decimal first, and then hex. Leading zeros
440 # imply non-decimal, as do non-[0-9]
441 my $decimal_qr = qr/^[1-9]\d*$/;
443 # Returns the hex number in $1.
444 my $hex_qr = qr/^(?:[Uu]\+|0[xX])?([[:xdigit:]]+)$/;
448 require Carp; goto &Carp::croak;
453 require Carp; goto &Carp::carp;
456 sub alias (@) # Set up a single alias
458 my $alias = ref $_[0] ? $_[0] : { @_ };
459 foreach my $name (keys %$alias) {
460 my $value = $alias->{$name};
461 next unless defined $value; # Omit if screwed up.
463 # Is slightly slower to just after this statement see if it is
464 # decimal, since we already know it is after having converted from
465 # hex, but makes the code easier to maintain, and is called
466 # infrequently, only at compile-time
467 if ($value !~ $decimal_qr && $value =~ $hex_qr) {
468 $value = CORE::hex $1;
470 if ($value =~ $decimal_qr) {
471 no warnings 'utf8'; # Allow even illegal characters
472 $^H{charnames_ord_aliases}{$name} = pack("U", $value);
474 # Use a canonical form.
475 $^H{charnames_inverse_ords}{sprintf("%05X", $value)} = $name;
478 # XXX validate syntax when deprecation cycle complete. ie. start
479 # with an alpha only, etc.
480 $^H{charnames_name_aliases}{$name} = $value;
485 sub not_legal_use_bytes_msg {
486 my ($name, $utf8) = @_;
489 if (length($utf8) == 1) {
490 $return = sprintf("Character 0x%04x with name '%s' is", ord $utf8, $name);
492 $return = sprintf("String with name '%s' (and ordinals %s) contains character(s)", $name, join(" ", map { sprintf "0x%04X", ord $_ } split(//, $utf8)));
494 return $return . " above 0xFF with 'use bytes' in effect";
497 sub alias_file ($) # Reads a file containing alias definitions
499 my ($arg, $file) = @_;
500 if (-f $arg && File::Spec->file_name_is_absolute ($arg)) {
503 elsif ($arg =~ m/^\w+$/) {
504 $file = "unicore/${arg}_alias.pl";
507 croak "Charnames alias files can only have identifier characters";
509 if (my @alias = do $file) {
510 @alias == 1 && !defined $alias[0] and
511 croak "$file cannot be used as alias file for charnames";
513 croak "$file did not return a (valid) list of alias pairs";
520 # For use when don't import anything. This structure must be kept in
521 # sync with the one that import() fills up.
523 charnames_stringified_names => "",
524 charnames_stringified_ords => "",
525 charnames_scripts => "",
527 charnames_short => 0,
531 sub lookup_name ($$$) {
532 my ($name, $wants_ord, $runtime) = @_;
534 # Lookup the name or sequence $name in the tables. If $wants_ord is false,
535 # returns the string equivalent of $name; if true, returns the ordinal value
536 # instead, but in this case $name must not be a sequence; otherwise undef is
537 # returned and a warning raised. $runtime is 0 if compiletime, otherwise
538 # gives the number of stack frames to go back to get the application caller
540 # If $name is not found, returns undef in runtime with no warning; and in
541 # compiletime, the Unicode replacement character, with a warning.
543 # It looks first in the aliases, then in the large table of official Unicode
546 my $utf8; # The string result
551 my $hints_ref = (caller($runtime))[10];
553 # If we didn't import anything (which happens with 'use charnames ()',
554 # substitute a dummy structure.
555 $hints_ref = \%dummy_H if ! defined $hints_ref
556 || ! defined $hints_ref->{charnames_full};
558 # At runtime, but currently not at compile time, $^H gets
559 # stringified, so un-stringify back to the original data structures.
560 # These get thrown away by perl before the next invocation
561 # Also fill in the hash with the non-stringified data.
562 # N.B. New fields must be also added to %dummy_H
564 %{$^H{charnames_name_aliases}} = split ',',
565 $hints_ref->{charnames_stringified_names};
566 %{$^H{charnames_ord_aliases}} = split ',',
567 $hints_ref->{charnames_stringified_ords};
568 $^H{charnames_scripts} = $hints_ref->{charnames_scripts};
569 $^H{charnames_full} = $hints_ref->{charnames_full};
570 $^H{charnames_short} = $hints_ref->{charnames_short};
573 # User alias should be checked first or else can't override ours, and if we
574 # were to add any, could conflict with theirs.
575 if (exists $^H{charnames_ord_aliases}{$name}) {
576 $utf8 = $^H{charnames_ord_aliases}{$name};
578 elsif (exists $^H{charnames_name_aliases}{$name}) {
579 $name = $^H{charnames_name_aliases}{$name};
580 $save_input = $name; # Cache the result for any error message
582 elsif (exists $system_aliases{$name}) {
583 $utf8 = $system_aliases{$name};
585 elsif (exists $deprecated_aliases{$name}) {
587 warnings::warnif('deprecated', "Unicode character name \"$name\" is deprecated, use \"" . viacode(ord $deprecated_aliases{$name}) . "\" instead");
588 $utf8 = $deprecated_aliases{$name};
593 if (! defined $utf8) {
595 # See if has looked this input up earlier.
596 if ($^H{charnames_full} && exists $full_names_cache{$name}) {
597 $utf8 = $full_names_cache{$name};
601 ## Suck in the code/name list as a big string.
603 ## "00052\tLATIN CAPITAL LETTER R\n"
605 # "0052 0303\tLATIN CAPITAL LETTER R WITH TILDE\n"
606 $txt = do "unicore/Name.pl" unless $txt;
608 ## @off will hold the index into the code/name string of the start and
609 ## end of the name as we find it.
611 ## If :full, look for the name exactly; runtime implies full
612 my $found_full_in_table = 0; # Tells us if can cache the result
613 if ($^H{charnames_full}) {
615 # See if the name is one which is algorithmically determinable.
616 # The subroutine is included in Name.pl. The table contained in
617 # $txt doesn't contain these. Experiments show that checking
618 # for these before checking for the regular names has no
619 # noticeable impact on performance for the regular names, but
620 # the other way around slows down finding these immensely.
621 # Algorithmically determinables are not placed in the cache (that
622 # $found_full_in_table indicates) because that uses up memory,
623 # and finding these again is fast.
624 if (defined (my $ord = name_to_code_point_special($name))) {
625 $utf8 = pack("U", $ord);
629 # Not algorthmically determinable; look up in the table.
630 if ($txt =~ /\t\Q$name\E$/m) {
631 @off = ($-[0] + 1, $+[0]); # The 1 is for the tab
632 $found_full_in_table = 1;
637 # If we didn't get it above, keep looking
638 if (! $found_full_in_table && ! defined $utf8) {
640 # If :short is allowed, see if input is like "greek:Sigma".
642 if (($^H{charnames_short})
643 && $name =~ /^ \s* (.+?) \s* : \s* (.+?) \s* $ /xs)
645 $scripts_trie = "\U\Q$1";
648 else { # Otherwise look in allowed scripts
649 $scripts_trie = $^H{charnames_scripts};
652 my $case = $name =~ /[[:upper:]]/ ? "CAPITAL" : "SMALL";
654 /\t (?: $scripts_trie ) \ (?:$case\ )? LETTER \ \U\Q$name\E $/xm)
656 # Here we still don't have it, give up.
659 # May have zapped input name, get it again.
660 $name = (defined $save_input) ? $save_input : $_[0];
661 carp "Unknown charname '$name'";
662 return ($wants_ord) ? 0xFFFD : pack("U", 0xFFFD);
665 @off = ($-[0] + 1, $+[0]); # The 1 is for the tab
668 if (! defined $utf8) {
670 # Here, we haven't set up the output, but we know where in the string
671 # the name starts. The string is set up so that for single characters
672 # (and not named sequences), the name is preceeded immediately by a
673 # tab and 5 hex digits for its code, with a \n before those. Named
674 # sequences won't have the 7th preceeding character be a \n.
675 # (Actually, for the very first entry in the table this isn't strictly
676 # true: subtracting 7 will yield -1, and the substr below will
677 # therefore yield the very last character in the table, which should
678 # also be a \n, so the statement works anyway.)
679 if (substr($txt, $off[0] - 7, 1) eq "\n") {
680 $utf8 = pack("U", CORE::hex substr($txt, $off[0] - 6, 5));
684 # Here, is a named sequence. Need to go looking for the beginning,
685 # which is just after the \n from the previous entry in the table.
686 # The +1 skips past that newline, or, if the rindex() fails, to put
687 # us to an offset of zero.
688 my $charstart = rindex($txt, "\n", $off[0] - 7) + 1;
689 $utf8 = pack("U*", map { CORE::hex }
690 split " ", substr($txt, $charstart, $off[0] - $charstart - 1));
694 # Cache the input so as to not have to search the large table
695 # again, but only if it came from the one search that we cache.
696 $full_names_cache{$name} = $utf8 if $found_full_in_table;
701 # Here, have the utf8. If the return is to be an ord, must be any single
704 return ord($utf8) if length $utf8 == 1;
708 # Here, wants string output. If utf8 is acceptable, just return what
709 # we've got; otherwise attempt to convert it to non-utf8 and return that.
710 my $in_bytes = ($runtime)
711 ? (caller $runtime)[8] & $bytes::hint_bits
712 : $^H & $bytes::hint_bits;
713 return $utf8 if (! $in_bytes || utf8::downgrade($utf8, 1)) # The 1 arg
714 # means don't die on failure
717 # Here, there is an error: either there are too many characters, or the
718 # result string needs to be non-utf8, and at least one character requires
719 # utf8. Prefer any official name over the input one for the error message.
721 $name = substr($txt, $off[0], $off[1] - $off[0]) if @off;
724 $name = (defined $save_input) ? $save_input : $_[0];
728 # Only way to get here in this case is if result too long. Message
729 # assumes that our only caller that requires single char result is
731 carp "charnames::vianame() doesn't handle named sequences ($name). Use charnames::string_vianame() instead";
735 # Only other possible failure here is from use bytes.
737 carp not_legal_use_bytes_msg($name, $utf8);
740 croak not_legal_use_bytes_msg($name, $utf8);
747 # For \N{...}. Looks up the character name and returns the string
748 # representation of it.
750 # The first 0 arg means wants a string returned; the second that we are in
752 return lookup_name($_[0], 0, 0);
757 shift; ## ignore class name
760 carp("`use charnames' needs explicit imports list");
762 $^H{charnames} = \&charnames ;
763 $^H{charnames_ord_aliases} = {};
764 $^H{charnames_name_aliases} = {};
765 $^H{charnames_inverse_ords} = {};
766 # New fields must be added to %dummy_H, and the code in lookup_name()
767 # that copies fields from the runtime structure
770 ## fill %h keys with our @_ args.
772 my ($promote, %h, @args) = (0);
773 while (my $arg = shift) {
774 if ($arg eq ":alias") {
776 croak ":alias needs an argument in charnames";
779 ref $alias eq "HASH" or
780 croak "Only HASH reference supported as argument to :alias";
784 if ($alias =~ m{:(\w+)$}) {
785 $1 eq "full" || $1 eq "short" and
786 croak ":alias cannot use existing pragma :$1 (reversed order?)";
787 alias_file ($1) and $promote = 1;
793 if (substr($arg, 0, 1) eq ':' and ! ($arg eq ":full" || $arg eq ":short")) {
794 warn "unsupported special '$arg' in charnames";
799 @args == 0 && $promote and @args = (":full");
800 @h{@args} = (1) x @args;
802 $^H{charnames_full} = delete $h{':full'} || 0; # Don't leave undefined,
805 $^H{charnames_short} = delete $h{':short'} || 0;
806 my @scripts = map uc, keys %h;
809 ## If utf8? warnings are enabled, and some scripts were given,
810 ## see if at least we can find one letter from each script.
812 if (warnings::enabled('utf8') && @scripts) {
813 $txt = do "unicore/Name.pl" unless $txt;
815 for my $script (@scripts) {
816 if (not $txt =~ m/\t$script (?:CAPITAL |SMALL )?LETTER /) {
817 warnings::warn('utf8', "No such script: '$script'");
818 $script = quotemeta $script; # Escape it, for use in the re.
823 # %^H gets stringified, so serialize it ourselves so can extract the
824 # real data back later.
825 $^H{charnames_stringified_ords} = join ",", %{$^H{charnames_ord_aliases}};
826 $^H{charnames_stringified_names} = join ",", %{$^H{charnames_name_aliases}};
827 $^H{charnames_stringified_inverse_ords} = join ",", %{$^H{charnames_inverse_ords}};
828 $^H{charnames_scripts} = join "|", @scripts; # Stringifiy them as a trie
831 # Cache of already looked-up values. This is set to only contain
832 # official values, and user aliases can't override them, so scoping is
838 # Returns the name of the code point argument
841 carp "charnames::viacode() expects one argument";
847 # This is derived from Unicode::UCD, where it is nearly the same as the
848 # function _getcode(), but here it makes sure that even a hex argument
849 # has the proper number of leading zeros, which is critical in
850 # matching against $txt below
851 # Must check if decimal first; see comments at that definition
853 if ($arg =~ $decimal_qr) {
854 $hex = sprintf "%05X", $arg;
855 } elsif ($arg =~ $hex_qr) {
856 # Below is the line that differs from the _getcode() source
857 $hex = sprintf "%05X", hex $1;
859 carp("unexpected arg \"$arg\" to charnames::viacode()");
863 return $viacode{$hex} if exists $viacode{$hex};
865 # If the code point is above the max in the table, there's no point
866 # looking through it. Checking the length first is slightly faster
867 if (length($hex) <= 5 || CORE::hex($hex) <= 0x10FFFF) {
868 $txt = do "unicore/Name.pl" unless $txt;
870 # See if the name is algorithmically determinable.
871 my $algorithmic = code_point_to_name_special(CORE::hex $hex);
872 if (defined $algorithmic) {
873 $viacode{$hex} = $algorithmic;
877 # Return the official name, if exists. It's unclear to me (khw) at
878 # this juncture if it is better to return a user-defined override, so
879 # leaving it as is for now.
880 if ($txt =~ m/^$hex\t/m) {
882 # The name starts with the next character and goes up to the
883 # next new-line. Using capturing parentheses above instead of
884 # @+ more than doubles the execution time in Perl 5.13
885 $viacode{$hex} = substr($txt, $+[0], index($txt, "\n", $+[0]) - $+[0]);
886 return $viacode{$hex};
890 # See if there is a user name for it, before giving up completely.
891 # First get the scoped aliases, give up if have none.
892 my $H_ref = (caller(0))[10];
893 return if ! defined $H_ref
894 || ! exists $H_ref->{charnames_stringified_inverse_ords};
896 my %code_point_aliases = split ',',
897 $H_ref->{charnames_stringified_inverse_ords};
898 if (! exists $code_point_aliases{$hex}) {
899 if (CORE::hex($hex) > 0x10FFFF) {
900 carp "Unicode characters only allocated up to U+10FFFF (you asked for U+$hex)";
905 return $code_point_aliases{$hex};
911 carp "charnames::vianame() expects one name argument";
915 # Looks up the character name and returns its ordinal if
916 # found, undef otherwise.
920 if ($arg =~ /^U\+([0-9a-fA-F]+)$/) {
922 # khw claims that this is poor interface design. The function should
923 # return either a an ord or a chr for all inputs; not be bipolar. But
924 # can't change it because of backward compatibility. New code can use
925 # string_vianame() instead.
926 my $ord = CORE::hex $1;
927 return chr $ord if $ord <= 255 || ! ((caller 0)[8] & $bytes::hint_bits);
928 carp not_legal_use_bytes_msg($arg, chr $ord);
932 # The first 1 arg means wants an ord returned; the second that we are in
933 # runtime, and this is the first level routine called from the user
934 return lookup_name($arg, 1, 1);
939 # Looks up the character name and returns its string representation if
940 # found, undef otherwise.
943 carp "charnames::string_vianame() expects one name argument";
949 if ($arg =~ /^U\+([0-9a-fA-F]+)$/) {
951 my $ord = CORE::hex $1;
952 return chr $ord if $ord <= 255 || ! ((caller 0)[8] & $bytes::hint_bits);
954 carp not_legal_use_bytes_msg($arg, chr $ord);
958 # The 0 arg means wants a string returned; the 1 arg means that we are in
959 # runtime, and this is the first level routine called from the user
960 return lookup_name($arg, 0, 1);
970 charnames - access to Unicode character names and named character sequences; also define character names
974 use charnames ':full';
975 print "\N{GREEK SMALL LETTER SIGMA} is called sigma.\n";
976 print "\N{LATIN CAPITAL LETTER E WITH VERTICAL LINE BELOW}",
977 " is an officially named sequence of two Unicode characters\n";
979 use charnames ':short';
980 print "\N{greek:Sigma} is an upper-case sigma.\n";
982 use charnames qw(cyrillic greek);
983 print "\N{sigma} is Greek sigma, and \N{be} is Cyrillic b.\n";
985 use charnames ":full", ":alias" => {
986 e_ACUTE => "LATIN SMALL LETTER E WITH ACUTE",
987 mychar => 0xE8000, # Private use area
989 print "\N{e_ACUTE} is a small letter e with an acute.\n";
990 print "\\N{mychar} allows me to name private use characters.\n";
993 print charnames::viacode(0x1234); # prints "ETHIOPIC SYLLABLE SEE"
994 printf "%04X", charnames::vianame("GOTHIC LETTER AHSA"); # prints
996 print charnames::vianame("LATIN CAPITAL LETTER A"); # prints 65 on
999 print charnames::string_vianame("LATIN CAPITAL LETTER A"); # prints "A"
1003 Pragma C<use charnames> is used to gain access to the names of the
1004 Unicode characters and named character sequences, and to allow you to define
1005 your own character and character sequence names.
1007 All forms of the pragma enable use of the following 3 functions:
1013 L</charnames::string_vianame(I<name>)> for run-time lookup of a
1014 either a character name or a named character sequence, returning its string
1019 L</charnames::vianame(I<name>)> for run-time lookup of a
1020 character name (but not a named character sequence) to get its ordinal value
1025 L</charnames::viacode(I<code>)> for run-time lookup of a code point to get its
1030 All forms other than C<S<"use charnames ();">> also enable the use of
1031 C<\N{I<CHARNAME>}> sequences to compile a Unicode character into a
1032 string, based on its name.
1034 Note that C<\N{U+I<...>}>, where the I<...> is a hexadecimal number,
1035 also inserts a character into a string, but doesn't require the use of
1036 this pragma. The character it inserts is the one whose code point
1037 (ordinal value) is equal to the number. For example, C<"\N{U+263a}"> is
1038 the Unicode (white background, black foreground) smiley face; it doesn't
1039 require this pragma, whereas the equivalent, C<"\N{WHITE SMILING FACE}">
1041 Also, C<\N{I<...>}> can mean a regex quantifier instead of a character
1042 name, when the I<...> is a number (or comma separated pair of numbers
1043 (see L<perlreref/QUANTIFIERS>), and is not related to this pragma.
1045 The C<charnames> pragma supports arguments C<:full>, C<:short>, script
1046 names and customized aliases. If C<:full> is present, for expansion of
1047 C<\N{I<CHARNAME>}>, the string I<CHARNAME> is first looked up in the list of
1048 standard Unicode character names. If C<:short> is present, and
1049 I<CHARNAME> has the form C<I<SCRIPT>:I<CNAME>>, then I<CNAME> is looked up
1050 as a letter in script I<SCRIPT>. If C<use charnames> is used
1051 with script name arguments, then for C<\N{I<CHARNAME>}> the name
1052 I<CHARNAME> is looked up as a letter in the given scripts (in the
1053 specified order). Customized aliases can override these, and are explained in
1056 For lookup of I<CHARNAME> inside a given script I<SCRIPTNAME>
1057 this pragma looks for the names
1059 SCRIPTNAME CAPITAL LETTER CHARNAME
1060 SCRIPTNAME SMALL LETTER CHARNAME
1061 SCRIPTNAME LETTER CHARNAME
1063 in the table of standard Unicode names. If I<CHARNAME> is lowercase,
1064 then the C<CAPITAL> variant is ignored, otherwise the C<SMALL> variant
1067 Note that C<\N{...}> is compile-time; it's a special form of string
1068 constant used inside double-quotish strings; this means that you cannot
1069 use variables inside the C<\N{...}>. If you want similar run-time
1071 L<charnames::string_vianame()|/charnames::string_vianame(I<name>)>.
1073 For the C0 and C1 control characters (U+0000..U+001F, U+0080..U+009F)
1074 there are no official Unicode names but you can use instead the ISO 6429
1075 names (LINE FEED, ESCAPE, and so forth, and their abbreviations, LF,
1076 ESC, ...). In Unicode 3.2 (as of Perl 5.8) some naming changes took
1077 place, and ISO 6429 was updated, see L</ALIASES>.
1079 If the input name is unknown, C<\N{NAME}> raises a warning and
1080 substitutes the Unicode REPLACEMENT CHARACTER (U+FFFD).
1082 For C<\N{NAME}>, it is a fatal error if C<use bytes> is in effect and the
1083 input name is that of a character that won't fit into a byte (i.e., whose
1084 ordinal is above 255).
1086 Otherwise, any string that includes a C<\N{I<charname>}> or
1087 C<S<\N{U+I<code point>}>> will automatically have Unicode semantics (see
1088 L<perlunicode/Byte and Character Semantics>).
1092 A few aliases have been defined for convenience: instead of having
1093 to use the official names
1097 CARRIAGE RETURN (CR)
1100 (yes, with parentheses), one can use
1111 All the other standard abbreviations for the controls, such as C<ACK> for
1112 C<ACKNOWLEDGE> also can be used.
1119 and these abbreviations
1121 Abbreviation Full Name
1123 CGJ COMBINING GRAPHEME JOINER
1124 FVS1 MONGOLIAN FREE VARIATION SELECTOR ONE
1125 FVS2 MONGOLIAN FREE VARIATION SELECTOR TWO
1126 FVS3 MONGOLIAN FREE VARIATION SELECTOR THREE
1127 LRE LEFT-TO-RIGHT EMBEDDING
1128 LRM LEFT-TO-RIGHT MARK
1129 LRO LEFT-TO-RIGHT OVERRIDE
1130 MMSP MEDIUM MATHEMATICAL SPACE
1131 MVS MONGOLIAN VOWEL SEPARATOR
1133 NNBSP NARROW NO-BREAK SPACE
1134 PDF POP DIRECTIONAL FORMATTING
1135 RLE RIGHT-TO-LEFT EMBEDDING
1136 RLM RIGHT-TO-LEFT MARK
1137 RLO RIGHT-TO-LEFT OVERRIDE
1139 VS1 VARIATION SELECTOR-1
1143 VS256 VARIATION SELECTOR-256
1145 ZWJ ZERO WIDTH JOINER
1146 ZWNJ ZERO WIDTH NON-JOINER
1147 ZWSP ZERO WIDTH SPACE
1149 For backward compatibility one can use the old names for
1150 certain C0 and C1 controls
1154 FILE SEPARATOR INFORMATION SEPARATOR FOUR
1155 GROUP SEPARATOR INFORMATION SEPARATOR THREE
1156 HORIZONTAL TABULATION CHARACTER TABULATION
1157 HORIZONTAL TABULATION SET CHARACTER TABULATION SET
1158 HORIZONTAL TABULATION WITH JUSTIFICATION CHARACTER TABULATION
1160 PARTIAL LINE DOWN PARTIAL LINE FORWARD
1161 PARTIAL LINE UP PARTIAL LINE BACKWARD
1162 RECORD SEPARATOR INFORMATION SEPARATOR TWO
1163 REVERSE INDEX REVERSE LINE FEED
1164 UNIT SEPARATOR INFORMATION SEPARATOR ONE
1165 VERTICAL TABULATION LINE TABULATION
1166 VERTICAL TABULATION SET LINE TABULATION SET
1168 but the old names in addition to giving the character
1169 will also give a warning about being deprecated.
1171 And finally, certain published variants are usable, including some for
1172 controls that have no Unicode names:
1176 END OF PROTECTED AREA END OF GUARDED AREA, U+0097
1177 HIGH OCTET PRESET U+0081
1182 PADDING CHARACTER U+0080
1183 PRIVATE USE 1 PRIVATE USE ONE, U+0091
1184 PRIVATE USE 2 PRIVATE USE TWO, U+0092
1186 SINGLE GRAPHIC CHARACTER INTRODUCER U+0099
1187 SINGLE-SHIFT 2 SINGLE SHIFT TWO, U+008E
1188 SINGLE-SHIFT 3 SINGLE SHIFT THREE, U+008F
1189 START OF PROTECTED AREA START OF GUARDED AREA, U+0096
1191 =head1 CUSTOM ALIASES
1193 You can add customized aliases to standard (C<:full>) Unicode naming
1194 conventions. The aliases override any standard definitions, so, if
1195 you're twisted enough, you can change C<"\N{LATIN CAPITAL LETTER A}"> to
1198 Note that an alias should not be something that is a legal curly
1199 brace-enclosed quantifier (see L<perlreref/QUANTIFIERS>). For example
1200 C<\N{123}> means to match 123 non-newline characters, and is not treated as a
1201 charnames alias. Aliases are discouraged from beginning with anything
1202 other than an alphabetic character and from containing anything other
1203 than alphanumerics, spaces, dashes, parentheses, and underscores.
1204 Currently they must be ASCII.
1206 An alias can map to either an official Unicode character name or to a
1207 numeric code point (ordinal). The latter is useful for assigning names
1208 to code points in Unicode private use areas such as U+E800 through
1210 A numeric code point must be a non-negative integer or a string beginning
1211 with C<"U+"> or C<"0x"> with the remainder considered to be a
1212 hexadecimal integer. A literal numeric constant must be unsigned; it
1213 will be interpreted as hex if it has a leading zero or contains
1214 non-decimal hex digits; otherwise it will be interpreted as decimal.
1216 Aliases are added either by the use of anonymous hashes:
1218 use charnames ":alias" => {
1219 e_ACUTE => "LATIN SMALL LETTER E WITH ACUTE",
1222 my $str = "\N{e_ACUTE}";
1224 or by using a file containing aliases:
1226 use charnames ":alias" => "pro";
1228 This will try to read C<"unicore/pro_alias.pl"> from the C<@INC> path. This
1229 file should return a list in plain perl:
1232 A_GRAVE => "LATIN CAPITAL LETTER A WITH GRAVE",
1233 A_CIRCUM => "LATIN CAPITAL LETTER A WITH CIRCUMFLEX",
1234 A_DIAERES => "LATIN CAPITAL LETTER A WITH DIAERESIS",
1235 A_TILDE => "LATIN CAPITAL LETTER A WITH TILDE",
1236 A_BREVE => "LATIN CAPITAL LETTER A WITH BREVE",
1237 A_RING => "LATIN CAPITAL LETTER A WITH RING ABOVE",
1238 A_MACRON => "LATIN CAPITAL LETTER A WITH MACRON",
1239 mychar2 => "U+E8001",
1242 Both these methods insert C<":full"> automatically as the first argument (if no
1243 other argument is given), and you can give the C<":full"> explicitly as
1246 use charnames ":full", ":alias" => "pro";
1248 Also, both these methods currently allow only a single character to be named.
1249 To name a sequence of characters, use a
1250 L<custom translator|/CUSTOM TRANSLATORS> (described below).
1252 =head1 charnames::viacode(I<code>)
1254 Returns the full name of the character indicated by the numeric code.
1257 print charnames::viacode(0x2722);
1259 prints "FOUR TEARDROP-SPOKED ASTERISK".
1261 The name returned is the official name for the code point, if
1262 available; otherwise your custom alias for it. This means that your
1263 alias will only be returned for code points that don't have an official
1264 Unicode name (nor Unicode version 1 name), such as private use code
1265 points, and the 4 control characters U+0080, U+0081, U+0084, and U+0099.
1266 If you define more than one name for the code point, it is indeterminate
1267 which one will be returned.
1269 The function returns C<undef> if no name is known for the code point.
1270 In Unicode the proper name of these is the empty string, which
1271 C<undef> stringifies to. (If you ask for a code point past the legal
1272 Unicode maximum of U+10FFFF that you haven't assigned an alias to, you
1273 get C<undef> plus a warning.)
1275 The input number must be a non-negative integer or a string beginning
1276 with C<"U+"> or C<"0x"> with the remainder considered to be a
1277 hexadecimal integer. A literal numeric constant must be unsigned; it
1278 will be interpreted as hex if it has a leading zero or contains
1279 non-decimal hex digits; otherwise it will be interpreted as decimal.
1281 Notice that the name returned for of U+FEFF is "ZERO WIDTH NO-BREAK
1282 SPACE", not "BYTE ORDER MARK".
1284 =head1 charnames::string_vianame(I<name>)
1286 This is a runtime equivalent to C<\N{...}>. I<name> can be any expression
1287 that evaluates to a name accepted by C<\N{...}> under the L<C<:full>
1288 option|/DESCRIPTION> to C<charnames>. In addition, any other options for the
1289 controlling C<"use charnames"> in the same scope apply, like any L<script
1290 list, C<:short> option|/DESCRIPTION>, or L<custom aliases|/CUSTOM ALIASES> you
1293 The only difference is that if the input name is unknown, C<string_vianame>
1294 returns C<undef> instead of the REPLACEMENT CHARACTER and does not raise a
1297 =head1 charnames::vianame(I<name>)
1299 This is similar to C<string_vianame>. The main difference is that under most
1300 circumstances (see L</BUGS> for the others), vianame returns an ordinal code
1301 point, whereas C<string_vianame> returns a string. For example,
1303 printf "U+%04X", charnames::vianame("FOUR TEARDROP-SPOKED ASTERISK");
1307 This leads to the other two differences. Since a single code point is
1308 returned, the function can't handle named character sequences, as these are
1309 composed of multiple characters. And, the code point can be that of any
1310 character, even ones that aren't legal under the C<S<use bytes>> pragma,
1312 =head1 CUSTOM TRANSLATORS
1314 The mechanism of translation of C<\N{...}> escapes is general and not
1315 hardwired into F<charnames.pm>. A module can install custom
1316 translations (inside the scope which C<use>s the module) with the
1317 following magic incantation:
1321 $^H{charnames} = \&translator;
1324 Here translator() is a subroutine which takes I<CHARNAME> as an
1325 argument, and returns text to insert into the string instead of the
1326 C<\N{I<CHARNAME>}> escape. Since the text to insert should be different
1327 in C<bytes> mode and out of it, the function should check the current
1328 state of C<bytes>-flag as in:
1330 use bytes (); # for $bytes::hint_bits
1332 if ($^H & $bytes::hint_bits) {
1333 return bytes_translator(@_);
1336 return utf8_translator(@_);
1340 See L</CUSTOM ALIASES> above for restrictions on I<CHARNAME>.
1342 Of course, C<vianame> and C<viacode> would need to be overridden as
1347 vianame normally returns an ordinal code point, but when the input name is of
1348 the form C<U+...>, it returns a chr instead. In this case, if C<use bytes> is
1349 in effect and the character won't fit into a byte, it returns C<undef> and
1352 Names must be ASCII characters only, which means that you are out of luck if
1353 you want to create aliases in a language where some or all the characters of
1354 the desired aliases are non-ASCII.
1356 Since evaluation of the translation function (see L</CUSTOM
1357 TRANSLATORS>) happens in the middle of compilation (of a string
1358 literal), the translation function should not do any C<eval>s or
1359 C<require>s. This restriction should be lifted (but is low priority) in
1360 a future version of Perl.
1364 # ex: set ts=8 sts=2 sw=2 et: