This is a live mirror of the Perl 5 development currently hosted at https://github.com/perl/perl5
charnames: Split into two modules
[perl5.git] / lib / _charnames.pm
CommitLineData
e7a078a0
KW
1# !!!!!!! INTERNAL PERL USE ONLY !!!!!!!
2# This helper module is for internal use by core Perl only. This module is
3# subject to change or removal at any time without notice. Don't use it
4# directly. Use the public <charnames> module instead.
5
6package _charnames;
7use strict;
8use warnings;
9use File::Spec;
10our $VERSION = '1.28';
11use unicore::Name; # mktables-generated algorithmically-defined names
12
13use bytes (); # for $bytes::hint_bits
14use re "/aa"; # Everything in here should be ASCII
15
16$Carp::Internal{ (__PACKAGE__) } = 1;
17
18# Translate between Unicode character names and their code points. This is a
19# submodule of package <charnames>, used to allow \N{...} to be autoloaded,
20# but it was decided not to autoload the various functions in charnames; the
21# splitting allows this behavior.
22#
23# The official names with their code points are stored in a table in
24# lib/unicore/Name.pl which is read in as a large string (almost 3/4 Mb in
25# Unicode 6.0). Each code point/name combination is separated by a \n in the
26# string. (Some of the CJK and the Hangul syllable names are determined
27# instead algorithmically via subroutines stored instead in
28# lib/unicore/Name.pm). Because of the large size of this table, it isn't
29# converted into hashes for faster lookup.
30#
31# But, user defined aliases are stored in their own hashes, as are Perl
32# extensions to the official names. These are checked first before looking at
33# the official table.
34#
35# Basically, the table is grepped for the input code point (viacode()) or
36# name (the other functions), and the corresponding value on the same line is
37# returned. The grepping is done by turning the input into a regular
38# expression. Thus, the same table does double duty, used by both name and
39# code point lookup. (If we were to have hashes, we would need two, one for
40# each lookup direction.)
41#
42# For loose name matching, the logical thing would be to have a table
43# with all the ignorable characters squeezed out, and then grep it with the
44# similiarly-squeezed input name. (And this is in fact how the lookups are
45# done with the small Perl extension hashes.) But since we need to be able to
46# go from code point to official name, the original table would still need to
47# exist. Due to the large size of the table, it was decided to not read
48# another very large string into memory for a second table. Instead, the
49# regular expression of the input name is modified to have optional spaces and
50# dashes between characters. For example, in strict matching, the regular
51# expression would be:
52# qr/\tDIGIT ONE$/m
53# Under loose matching, the blank would be squeezed out, and the re would be:
54# qr/\tD[- ]?I[- ]?G[- ]?I[- ]?T[- ]?O[- ]?N[- ]?E$/m
55# which matches a blank or dash between any characters in the official table.
56#
57# This is also how script lookup is done. Basically the re looks like
58# qr/ (?:LATIN|GREEK|CYRILLIC) (?:SMALL )?LETTER $name/
59# where $name is the loose or strict regex for the remainder of the name.
60
61# The hashes are stored as utf8 strings. This makes it easier to deal with
62# sequences. I (khw) also tried making Name.pl utf8, but it slowed things
63# down by a factor of 7. I then tried making Name.pl store the ut8
64# equivalents but not calling them utf8. That led to similar speed as leaving
65# it alone, but since that is harder for a human to parse, I left it as-is.
66
67my %system_aliases = (
68 # Synonyms for the icky 3.2 names that have parentheses.
69 'LINE FEED' => pack("U", 0x0A), # LINE FEED (LF)
70 'FORM FEED' => pack("U", 0x0C), # FORM FEED (FF)
71 'CARRIAGE RETURN' => pack("U", 0x0D), # CARRIAGE RETURN (CR)
72 'NEXT LINE' => pack("U", 0x85), # NEXT LINE (NEL)
73
74 # Some variant names from Wikipedia
75 'SINGLE-SHIFT 2' => pack("U", 0x8E),
76 'SINGLE-SHIFT 3' => pack("U", 0x8F),
77 'PRIVATE USE 1' => pack("U", 0x91),
78 'PRIVATE USE 2' => pack("U", 0x92),
79 'START OF PROTECTED AREA' => pack("U", 0x96),
80 'END OF PROTECTED AREA' => pack("U", 0x97),
81
82 # Convenience. Standard abbreviations for the controls
83 'NUL' => pack("U", 0x00), # NULL
84 'SOH' => pack("U", 0x01), # START OF HEADING
85 'STX' => pack("U", 0x02), # START OF TEXT
86 'ETX' => pack("U", 0x03), # END OF TEXT
87 'EOT' => pack("U", 0x04), # END OF TRANSMISSION
88 'ENQ' => pack("U", 0x05), # ENQUIRY
89 'ACK' => pack("U", 0x06), # ACKNOWLEDGE
90 'BEL' => pack("U", 0x07), # ALERT; formerly BELL
91 'BS' => pack("U", 0x08), # BACKSPACE
92 'HT' => pack("U", 0x09), # HORIZONTAL TABULATION
93 'LF' => pack("U", 0x0A), # LINE FEED (LF)
94 'VT' => pack("U", 0x0B), # VERTICAL TABULATION
95 'FF' => pack("U", 0x0C), # FORM FEED (FF)
96 'CR' => pack("U", 0x0D), # CARRIAGE RETURN (CR)
97 'SO' => pack("U", 0x0E), # SHIFT OUT
98 'SI' => pack("U", 0x0F), # SHIFT IN
99 'DLE' => pack("U", 0x10), # DATA LINK ESCAPE
100 'DC1' => pack("U", 0x11), # DEVICE CONTROL ONE
101 'DC2' => pack("U", 0x12), # DEVICE CONTROL TWO
102 'DC3' => pack("U", 0x13), # DEVICE CONTROL THREE
103 'DC4' => pack("U", 0x14), # DEVICE CONTROL FOUR
104 'NAK' => pack("U", 0x15), # NEGATIVE ACKNOWLEDGE
105 'SYN' => pack("U", 0x16), # SYNCHRONOUS IDLE
106 'ETB' => pack("U", 0x17), # END OF TRANSMISSION BLOCK
107 'CAN' => pack("U", 0x18), # CANCEL
108 'EOM' => pack("U", 0x19), # END OF MEDIUM
109 'SUB' => pack("U", 0x1A), # SUBSTITUTE
110 'ESC' => pack("U", 0x1B), # ESCAPE
111 'FS' => pack("U", 0x1C), # FILE SEPARATOR
112 'GS' => pack("U", 0x1D), # GROUP SEPARATOR
113 'RS' => pack("U", 0x1E), # RECORD SEPARATOR
114 'US' => pack("U", 0x1F), # UNIT SEPARATOR
115 'DEL' => pack("U", 0x7F), # DELETE
116 'BPH' => pack("U", 0x82), # BREAK PERMITTED HERE
117 'NBH' => pack("U", 0x83), # NO BREAK HERE
118 'NEL' => pack("U", 0x85), # NEXT LINE (NEL)
119 'SSA' => pack("U", 0x86), # START OF SELECTED AREA
120 'ESA' => pack("U", 0x87), # END OF SELECTED AREA
121 'HTS' => pack("U", 0x88), # CHARACTER TABULATION SET
122 'HTJ' => pack("U", 0x89), # CHARACTER TABULATION WITH JUSTIFICATION
123 'VTS' => pack("U", 0x8A), # LINE TABULATION SET
124 'PLD' => pack("U", 0x8B), # PARTIAL LINE FORWARD
125 'PLU' => pack("U", 0x8C), # PARTIAL LINE BACKWARD
126 'RI' => pack("U", 0x8D), # REVERSE LINE FEED
127 'SS2' => pack("U", 0x8E), # SINGLE SHIFT TWO
128 'SS3' => pack("U", 0x8F), # SINGLE SHIFT THREE
129 'DCS' => pack("U", 0x90), # DEVICE CONTROL STRING
130 'PU1' => pack("U", 0x91), # PRIVATE USE ONE
131 'PU2' => pack("U", 0x92), # PRIVATE USE TWO
132 'STS' => pack("U", 0x93), # SET TRANSMIT STATE
133 'CCH' => pack("U", 0x94), # CANCEL CHARACTER
134 'MW' => pack("U", 0x95), # MESSAGE WAITING
135 'SPA' => pack("U", 0x96), # START OF GUARDED AREA
136 'EPA' => pack("U", 0x97), # END OF GUARDED AREA
137 'SOS' => pack("U", 0x98), # START OF STRING
138 'SCI' => pack("U", 0x9A), # SINGLE CHARACTER INTRODUCER
139 'CSI' => pack("U", 0x9B), # CONTROL SEQUENCE INTRODUCER
140 'ST' => pack("U", 0x9C), # STRING TERMINATOR
141 'OSC' => pack("U", 0x9D), # OPERATING SYSTEM COMMAND
142 'PM' => pack("U", 0x9E), # PRIVACY MESSAGE
143 'APC' => pack("U", 0x9F), # APPLICATION PROGRAM COMMAND
144
145 # There are no names for these in the Unicode standard; perhaps should be
146 # deprecated, but then again there are no alternative names, so am not
147 # deprecating. And if did, the code would have to change to not recommend
148 # an alternative for these.
149 'PADDING CHARACTER' => pack("U", 0x80),
150 'PAD' => pack("U", 0x80),
151 'HIGH OCTET PRESET' => pack("U", 0x81),
152 'HOP' => pack("U", 0x81),
153 'INDEX' => pack("U", 0x84),
154 'IND' => pack("U", 0x84),
155 'SINGLE GRAPHIC CHARACTER INTRODUCER' => pack("U", 0x99),
156 'SGC' => pack("U", 0x99),
157
158 # More convenience. For further convenience, it is suggested some way of
159 # using the NamesList aliases be implemented, but there are ambiguities in
160 # NamesList.txt
161 'BOM' => pack("U", 0xFEFF), # BYTE ORDER MARK
162 'BYTE ORDER MARK'=> pack("U", 0xFEFF),
163 'CGJ' => pack("U", 0x034F), # COMBINING GRAPHEME JOINER
164 'FVS1' => pack("U", 0x180B), # MONGOLIAN FREE VARIATION SELECTOR ONE
165 'FVS2' => pack("U", 0x180C), # MONGOLIAN FREE VARIATION SELECTOR TWO
166 'FVS3' => pack("U", 0x180D), # MONGOLIAN FREE VARIATION SELECTOR THREE
167 'LRE' => pack("U", 0x202A), # LEFT-TO-RIGHT EMBEDDING
168 'LRM' => pack("U", 0x200E), # LEFT-TO-RIGHT MARK
169 'LRO' => pack("U", 0x202D), # LEFT-TO-RIGHT OVERRIDE
170 'MMSP' => pack("U", 0x205F), # MEDIUM MATHEMATICAL SPACE
171 'MVS' => pack("U", 0x180E), # MONGOLIAN VOWEL SEPARATOR
172 'NBSP' => pack("U", 0x00A0), # NO-BREAK SPACE
173 'NNBSP' => pack("U", 0x202F), # NARROW NO-BREAK SPACE
174 'PDF' => pack("U", 0x202C), # POP DIRECTIONAL FORMATTING
175 'RLE' => pack("U", 0x202B), # RIGHT-TO-LEFT EMBEDDING
176 'RLM' => pack("U", 0x200F), # RIGHT-TO-LEFT MARK
177 'RLO' => pack("U", 0x202E), # RIGHT-TO-LEFT OVERRIDE
178 'SHY' => pack("U", 0x00AD), # SOFT HYPHEN
179 'VS1' => pack("U", 0xFE00), # VARIATION SELECTOR-1
180 'VS2' => pack("U", 0xFE01), # VARIATION SELECTOR-2
181 'VS3' => pack("U", 0xFE02), # VARIATION SELECTOR-3
182 'VS4' => pack("U", 0xFE03), # VARIATION SELECTOR-4
183 'VS5' => pack("U", 0xFE04), # VARIATION SELECTOR-5
184 'VS6' => pack("U", 0xFE05), # VARIATION SELECTOR-6
185 'VS7' => pack("U", 0xFE06), # VARIATION SELECTOR-7
186 'VS8' => pack("U", 0xFE07), # VARIATION SELECTOR-8
187 'VS9' => pack("U", 0xFE08), # VARIATION SELECTOR-9
188 'VS10' => pack("U", 0xFE09), # VARIATION SELECTOR-10
189 'VS11' => pack("U", 0xFE0A), # VARIATION SELECTOR-11
190 'VS12' => pack("U", 0xFE0B), # VARIATION SELECTOR-12
191 'VS13' => pack("U", 0xFE0C), # VARIATION SELECTOR-13
192 'VS14' => pack("U", 0xFE0D), # VARIATION SELECTOR-14
193 'VS15' => pack("U", 0xFE0E), # VARIATION SELECTOR-15
194 'VS16' => pack("U", 0xFE0F), # VARIATION SELECTOR-16
195 'VS17' => pack("U", 0xE0100), # VARIATION SELECTOR-17
196 'VS18' => pack("U", 0xE0101), # VARIATION SELECTOR-18
197 'VS19' => pack("U", 0xE0102), # VARIATION SELECTOR-19
198 'VS20' => pack("U", 0xE0103), # VARIATION SELECTOR-20
199 'VS21' => pack("U", 0xE0104), # VARIATION SELECTOR-21
200 'VS22' => pack("U", 0xE0105), # VARIATION SELECTOR-22
201 'VS23' => pack("U", 0xE0106), # VARIATION SELECTOR-23
202 'VS24' => pack("U", 0xE0107), # VARIATION SELECTOR-24
203 'VS25' => pack("U", 0xE0108), # VARIATION SELECTOR-25
204 'VS26' => pack("U", 0xE0109), # VARIATION SELECTOR-26
205 'VS27' => pack("U", 0xE010A), # VARIATION SELECTOR-27
206 'VS28' => pack("U", 0xE010B), # VARIATION SELECTOR-28
207 'VS29' => pack("U", 0xE010C), # VARIATION SELECTOR-29
208 'VS30' => pack("U", 0xE010D), # VARIATION SELECTOR-30
209 'VS31' => pack("U", 0xE010E), # VARIATION SELECTOR-31
210 'VS32' => pack("U", 0xE010F), # VARIATION SELECTOR-32
211 'VS33' => pack("U", 0xE0110), # VARIATION SELECTOR-33
212 'VS34' => pack("U", 0xE0111), # VARIATION SELECTOR-34
213 'VS35' => pack("U", 0xE0112), # VARIATION SELECTOR-35
214 'VS36' => pack("U", 0xE0113), # VARIATION SELECTOR-36
215 'VS37' => pack("U", 0xE0114), # VARIATION SELECTOR-37
216 'VS38' => pack("U", 0xE0115), # VARIATION SELECTOR-38
217 'VS39' => pack("U", 0xE0116), # VARIATION SELECTOR-39
218 'VS40' => pack("U", 0xE0117), # VARIATION SELECTOR-40
219 'VS41' => pack("U", 0xE0118), # VARIATION SELECTOR-41
220 'VS42' => pack("U", 0xE0119), # VARIATION SELECTOR-42
221 'VS43' => pack("U", 0xE011A), # VARIATION SELECTOR-43
222 'VS44' => pack("U", 0xE011B), # VARIATION SELECTOR-44
223 'VS45' => pack("U", 0xE011C), # VARIATION SELECTOR-45
224 'VS46' => pack("U", 0xE011D), # VARIATION SELECTOR-46
225 'VS47' => pack("U", 0xE011E), # VARIATION SELECTOR-47
226 'VS48' => pack("U", 0xE011F), # VARIATION SELECTOR-48
227 'VS49' => pack("U", 0xE0120), # VARIATION SELECTOR-49
228 'VS50' => pack("U", 0xE0121), # VARIATION SELECTOR-50
229 'VS51' => pack("U", 0xE0122), # VARIATION SELECTOR-51
230 'VS52' => pack("U", 0xE0123), # VARIATION SELECTOR-52
231 'VS53' => pack("U", 0xE0124), # VARIATION SELECTOR-53
232 'VS54' => pack("U", 0xE0125), # VARIATION SELECTOR-54
233 'VS55' => pack("U", 0xE0126), # VARIATION SELECTOR-55
234 'VS56' => pack("U", 0xE0127), # VARIATION SELECTOR-56
235 'VS57' => pack("U", 0xE0128), # VARIATION SELECTOR-57
236 'VS58' => pack("U", 0xE0129), # VARIATION SELECTOR-58
237 'VS59' => pack("U", 0xE012A), # VARIATION SELECTOR-59
238 'VS60' => pack("U", 0xE012B), # VARIATION SELECTOR-60
239 'VS61' => pack("U", 0xE012C), # VARIATION SELECTOR-61
240 'VS62' => pack("U", 0xE012D), # VARIATION SELECTOR-62
241 'VS63' => pack("U", 0xE012E), # VARIATION SELECTOR-63
242 'VS64' => pack("U", 0xE012F), # VARIATION SELECTOR-64
243 'VS65' => pack("U", 0xE0130), # VARIATION SELECTOR-65
244 'VS66' => pack("U", 0xE0131), # VARIATION SELECTOR-66
245 'VS67' => pack("U", 0xE0132), # VARIATION SELECTOR-67
246 'VS68' => pack("U", 0xE0133), # VARIATION SELECTOR-68
247 'VS69' => pack("U", 0xE0134), # VARIATION SELECTOR-69
248 'VS70' => pack("U", 0xE0135), # VARIATION SELECTOR-70
249 'VS71' => pack("U", 0xE0136), # VARIATION SELECTOR-71
250 'VS72' => pack("U", 0xE0137), # VARIATION SELECTOR-72
251 'VS73' => pack("U", 0xE0138), # VARIATION SELECTOR-73
252 'VS74' => pack("U", 0xE0139), # VARIATION SELECTOR-74
253 'VS75' => pack("U", 0xE013A), # VARIATION SELECTOR-75
254 'VS76' => pack("U", 0xE013B), # VARIATION SELECTOR-76
255 'VS77' => pack("U", 0xE013C), # VARIATION SELECTOR-77
256 'VS78' => pack("U", 0xE013D), # VARIATION SELECTOR-78
257 'VS79' => pack("U", 0xE013E), # VARIATION SELECTOR-79
258 'VS80' => pack("U", 0xE013F), # VARIATION SELECTOR-80
259 'VS81' => pack("U", 0xE0140), # VARIATION SELECTOR-81
260 'VS82' => pack("U", 0xE0141), # VARIATION SELECTOR-82
261 'VS83' => pack("U", 0xE0142), # VARIATION SELECTOR-83
262 'VS84' => pack("U", 0xE0143), # VARIATION SELECTOR-84
263 'VS85' => pack("U", 0xE0144), # VARIATION SELECTOR-85
264 'VS86' => pack("U", 0xE0145), # VARIATION SELECTOR-86
265 'VS87' => pack("U", 0xE0146), # VARIATION SELECTOR-87
266 'VS88' => pack("U", 0xE0147), # VARIATION SELECTOR-88
267 'VS89' => pack("U", 0xE0148), # VARIATION SELECTOR-89
268 'VS90' => pack("U", 0xE0149), # VARIATION SELECTOR-90
269 'VS91' => pack("U", 0xE014A), # VARIATION SELECTOR-91
270 'VS92' => pack("U", 0xE014B), # VARIATION SELECTOR-92
271 'VS93' => pack("U", 0xE014C), # VARIATION SELECTOR-93
272 'VS94' => pack("U", 0xE014D), # VARIATION SELECTOR-94
273 'VS95' => pack("U", 0xE014E), # VARIATION SELECTOR-95
274 'VS96' => pack("U", 0xE014F), # VARIATION SELECTOR-96
275 'VS97' => pack("U", 0xE0150), # VARIATION SELECTOR-97
276 'VS98' => pack("U", 0xE0151), # VARIATION SELECTOR-98
277 'VS99' => pack("U", 0xE0152), # VARIATION SELECTOR-99
278 'VS100' => pack("U", 0xE0153), # VARIATION SELECTOR-100
279 'VS101' => pack("U", 0xE0154), # VARIATION SELECTOR-101
280 'VS102' => pack("U", 0xE0155), # VARIATION SELECTOR-102
281 'VS103' => pack("U", 0xE0156), # VARIATION SELECTOR-103
282 'VS104' => pack("U", 0xE0157), # VARIATION SELECTOR-104
283 'VS105' => pack("U", 0xE0158), # VARIATION SELECTOR-105
284 'VS106' => pack("U", 0xE0159), # VARIATION SELECTOR-106
285 'VS107' => pack("U", 0xE015A), # VARIATION SELECTOR-107
286 'VS108' => pack("U", 0xE015B), # VARIATION SELECTOR-108
287 'VS109' => pack("U", 0xE015C), # VARIATION SELECTOR-109
288 'VS110' => pack("U", 0xE015D), # VARIATION SELECTOR-110
289 'VS111' => pack("U", 0xE015E), # VARIATION SELECTOR-111
290 'VS112' => pack("U", 0xE015F), # VARIATION SELECTOR-112
291 'VS113' => pack("U", 0xE0160), # VARIATION SELECTOR-113
292 'VS114' => pack("U", 0xE0161), # VARIATION SELECTOR-114
293 'VS115' => pack("U", 0xE0162), # VARIATION SELECTOR-115
294 'VS116' => pack("U", 0xE0163), # VARIATION SELECTOR-116
295 'VS117' => pack("U", 0xE0164), # VARIATION SELECTOR-117
296 'VS118' => pack("U", 0xE0165), # VARIATION SELECTOR-118
297 'VS119' => pack("U", 0xE0166), # VARIATION SELECTOR-119
298 'VS120' => pack("U", 0xE0167), # VARIATION SELECTOR-120
299 'VS121' => pack("U", 0xE0168), # VARIATION SELECTOR-121
300 'VS122' => pack("U", 0xE0169), # VARIATION SELECTOR-122
301 'VS123' => pack("U", 0xE016A), # VARIATION SELECTOR-123
302 'VS124' => pack("U", 0xE016B), # VARIATION SELECTOR-124
303 'VS125' => pack("U", 0xE016C), # VARIATION SELECTOR-125
304 'VS126' => pack("U", 0xE016D), # VARIATION SELECTOR-126
305 'VS127' => pack("U", 0xE016E), # VARIATION SELECTOR-127
306 'VS128' => pack("U", 0xE016F), # VARIATION SELECTOR-128
307 'VS129' => pack("U", 0xE0170), # VARIATION SELECTOR-129
308 'VS130' => pack("U", 0xE0171), # VARIATION SELECTOR-130
309 'VS131' => pack("U", 0xE0172), # VARIATION SELECTOR-131
310 'VS132' => pack("U", 0xE0173), # VARIATION SELECTOR-132
311 'VS133' => pack("U", 0xE0174), # VARIATION SELECTOR-133
312 'VS134' => pack("U", 0xE0175), # VARIATION SELECTOR-134
313 'VS135' => pack("U", 0xE0176), # VARIATION SELECTOR-135
314 'VS136' => pack("U", 0xE0177), # VARIATION SELECTOR-136
315 'VS137' => pack("U", 0xE0178), # VARIATION SELECTOR-137
316 'VS138' => pack("U", 0xE0179), # VARIATION SELECTOR-138
317 'VS139' => pack("U", 0xE017A), # VARIATION SELECTOR-139
318 'VS140' => pack("U", 0xE017B), # VARIATION SELECTOR-140
319 'VS141' => pack("U", 0xE017C), # VARIATION SELECTOR-141
320 'VS142' => pack("U", 0xE017D), # VARIATION SELECTOR-142
321 'VS143' => pack("U", 0xE017E), # VARIATION SELECTOR-143
322 'VS144' => pack("U", 0xE017F), # VARIATION SELECTOR-144
323 'VS145' => pack("U", 0xE0180), # VARIATION SELECTOR-145
324 'VS146' => pack("U", 0xE0181), # VARIATION SELECTOR-146
325 'VS147' => pack("U", 0xE0182), # VARIATION SELECTOR-147
326 'VS148' => pack("U", 0xE0183), # VARIATION SELECTOR-148
327 'VS149' => pack("U", 0xE0184), # VARIATION SELECTOR-149
328 'VS150' => pack("U", 0xE0185), # VARIATION SELECTOR-150
329 'VS151' => pack("U", 0xE0186), # VARIATION SELECTOR-151
330 'VS152' => pack("U", 0xE0187), # VARIATION SELECTOR-152
331 'VS153' => pack("U", 0xE0188), # VARIATION SELECTOR-153
332 'VS154' => pack("U", 0xE0189), # VARIATION SELECTOR-154
333 'VS155' => pack("U", 0xE018A), # VARIATION SELECTOR-155
334 'VS156' => pack("U", 0xE018B), # VARIATION SELECTOR-156
335 'VS157' => pack("U", 0xE018C), # VARIATION SELECTOR-157
336 'VS158' => pack("U", 0xE018D), # VARIATION SELECTOR-158
337 'VS159' => pack("U", 0xE018E), # VARIATION SELECTOR-159
338 'VS160' => pack("U", 0xE018F), # VARIATION SELECTOR-160
339 'VS161' => pack("U", 0xE0190), # VARIATION SELECTOR-161
340 'VS162' => pack("U", 0xE0191), # VARIATION SELECTOR-162
341 'VS163' => pack("U", 0xE0192), # VARIATION SELECTOR-163
342 'VS164' => pack("U", 0xE0193), # VARIATION SELECTOR-164
343 'VS165' => pack("U", 0xE0194), # VARIATION SELECTOR-165
344 'VS166' => pack("U", 0xE0195), # VARIATION SELECTOR-166
345 'VS167' => pack("U", 0xE0196), # VARIATION SELECTOR-167
346 'VS168' => pack("U", 0xE0197), # VARIATION SELECTOR-168
347 'VS169' => pack("U", 0xE0198), # VARIATION SELECTOR-169
348 'VS170' => pack("U", 0xE0199), # VARIATION SELECTOR-170
349 'VS171' => pack("U", 0xE019A), # VARIATION SELECTOR-171
350 'VS172' => pack("U", 0xE019B), # VARIATION SELECTOR-172
351 'VS173' => pack("U", 0xE019C), # VARIATION SELECTOR-173
352 'VS174' => pack("U", 0xE019D), # VARIATION SELECTOR-174
353 'VS175' => pack("U", 0xE019E), # VARIATION SELECTOR-175
354 'VS176' => pack("U", 0xE019F), # VARIATION SELECTOR-176
355 'VS177' => pack("U", 0xE01A0), # VARIATION SELECTOR-177
356 'VS178' => pack("U", 0xE01A1), # VARIATION SELECTOR-178
357 'VS179' => pack("U", 0xE01A2), # VARIATION SELECTOR-179
358 'VS180' => pack("U", 0xE01A3), # VARIATION SELECTOR-180
359 'VS181' => pack("U", 0xE01A4), # VARIATION SELECTOR-181
360 'VS182' => pack("U", 0xE01A5), # VARIATION SELECTOR-182
361 'VS183' => pack("U", 0xE01A6), # VARIATION SELECTOR-183
362 'VS184' => pack("U", 0xE01A7), # VARIATION SELECTOR-184
363 'VS185' => pack("U", 0xE01A8), # VARIATION SELECTOR-185
364 'VS186' => pack("U", 0xE01A9), # VARIATION SELECTOR-186
365 'VS187' => pack("U", 0xE01AA), # VARIATION SELECTOR-187
366 'VS188' => pack("U", 0xE01AB), # VARIATION SELECTOR-188
367 'VS189' => pack("U", 0xE01AC), # VARIATION SELECTOR-189
368 'VS190' => pack("U", 0xE01AD), # VARIATION SELECTOR-190
369 'VS191' => pack("U", 0xE01AE), # VARIATION SELECTOR-191
370 'VS192' => pack("U", 0xE01AF), # VARIATION SELECTOR-192
371 'VS193' => pack("U", 0xE01B0), # VARIATION SELECTOR-193
372 'VS194' => pack("U", 0xE01B1), # VARIATION SELECTOR-194
373 'VS195' => pack("U", 0xE01B2), # VARIATION SELECTOR-195
374 'VS196' => pack("U", 0xE01B3), # VARIATION SELECTOR-196
375 'VS197' => pack("U", 0xE01B4), # VARIATION SELECTOR-197
376 'VS198' => pack("U", 0xE01B5), # VARIATION SELECTOR-198
377 'VS199' => pack("U", 0xE01B6), # VARIATION SELECTOR-199
378 'VS200' => pack("U", 0xE01B7), # VARIATION SELECTOR-200
379 'VS201' => pack("U", 0xE01B8), # VARIATION SELECTOR-201
380 'VS202' => pack("U", 0xE01B9), # VARIATION SELECTOR-202
381 'VS203' => pack("U", 0xE01BA), # VARIATION SELECTOR-203
382 'VS204' => pack("U", 0xE01BB), # VARIATION SELECTOR-204
383 'VS205' => pack("U", 0xE01BC), # VARIATION SELECTOR-205
384 'VS206' => pack("U", 0xE01BD), # VARIATION SELECTOR-206
385 'VS207' => pack("U", 0xE01BE), # VARIATION SELECTOR-207
386 'VS208' => pack("U", 0xE01BF), # VARIATION SELECTOR-208
387 'VS209' => pack("U", 0xE01C0), # VARIATION SELECTOR-209
388 'VS210' => pack("U", 0xE01C1), # VARIATION SELECTOR-210
389 'VS211' => pack("U", 0xE01C2), # VARIATION SELECTOR-211
390 'VS212' => pack("U", 0xE01C3), # VARIATION SELECTOR-212
391 'VS213' => pack("U", 0xE01C4), # VARIATION SELECTOR-213
392 'VS214' => pack("U", 0xE01C5), # VARIATION SELECTOR-214
393 'VS215' => pack("U", 0xE01C6), # VARIATION SELECTOR-215
394 'VS216' => pack("U", 0xE01C7), # VARIATION SELECTOR-216
395 'VS217' => pack("U", 0xE01C8), # VARIATION SELECTOR-217
396 'VS218' => pack("U", 0xE01C9), # VARIATION SELECTOR-218
397 'VS219' => pack("U", 0xE01CA), # VARIATION SELECTOR-219
398 'VS220' => pack("U", 0xE01CB), # VARIATION SELECTOR-220
399 'VS221' => pack("U", 0xE01CC), # VARIATION SELECTOR-221
400 'VS222' => pack("U", 0xE01CD), # VARIATION SELECTOR-222
401 'VS223' => pack("U", 0xE01CE), # VARIATION SELECTOR-223
402 'VS224' => pack("U", 0xE01CF), # VARIATION SELECTOR-224
403 'VS225' => pack("U", 0xE01D0), # VARIATION SELECTOR-225
404 'VS226' => pack("U", 0xE01D1), # VARIATION SELECTOR-226
405 'VS227' => pack("U", 0xE01D2), # VARIATION SELECTOR-227
406 'VS228' => pack("U", 0xE01D3), # VARIATION SELECTOR-228
407 'VS229' => pack("U", 0xE01D4), # VARIATION SELECTOR-229
408 'VS230' => pack("U", 0xE01D5), # VARIATION SELECTOR-230
409 'VS231' => pack("U", 0xE01D6), # VARIATION SELECTOR-231
410 'VS232' => pack("U", 0xE01D7), # VARIATION SELECTOR-232
411 'VS233' => pack("U", 0xE01D8), # VARIATION SELECTOR-233
412 'VS234' => pack("U", 0xE01D9), # VARIATION SELECTOR-234
413 'VS235' => pack("U", 0xE01DA), # VARIATION SELECTOR-235
414 'VS236' => pack("U", 0xE01DB), # VARIATION SELECTOR-236
415 'VS237' => pack("U", 0xE01DC), # VARIATION SELECTOR-237
416 'VS238' => pack("U", 0xE01DD), # VARIATION SELECTOR-238
417 'VS239' => pack("U", 0xE01DE), # VARIATION SELECTOR-239
418 'VS240' => pack("U", 0xE01DF), # VARIATION SELECTOR-240
419 'VS241' => pack("U", 0xE01E0), # VARIATION SELECTOR-241
420 'VS242' => pack("U", 0xE01E1), # VARIATION SELECTOR-242
421 'VS243' => pack("U", 0xE01E2), # VARIATION SELECTOR-243
422 'VS244' => pack("U", 0xE01E3), # VARIATION SELECTOR-244
423 'VS245' => pack("U", 0xE01E4), # VARIATION SELECTOR-245
424 'VS246' => pack("U", 0xE01E5), # VARIATION SELECTOR-246
425 'VS247' => pack("U", 0xE01E6), # VARIATION SELECTOR-247
426 'VS248' => pack("U", 0xE01E7), # VARIATION SELECTOR-248
427 'VS249' => pack("U", 0xE01E8), # VARIATION SELECTOR-249
428 'VS250' => pack("U", 0xE01E9), # VARIATION SELECTOR-250
429 'VS251' => pack("U", 0xE01EA), # VARIATION SELECTOR-251
430 'VS252' => pack("U", 0xE01EB), # VARIATION SELECTOR-252
431 'VS253' => pack("U", 0xE01EC), # VARIATION SELECTOR-253
432 'VS254' => pack("U", 0xE01ED), # VARIATION SELECTOR-254
433 'VS255' => pack("U", 0xE01EE), # VARIATION SELECTOR-255
434 'VS256' => pack("U", 0xE01EF), # VARIATION SELECTOR-256
435 'WJ' => pack("U", 0x2060), # WORD JOINER
436 'ZWJ' => pack("U", 0x200D), # ZERO WIDTH JOINER
437 'ZWNJ' => pack("U", 0x200C), # ZERO WIDTH NON-JOINER
438 'ZWSP' => pack("U", 0x200B), # ZERO WIDTH SPACE
439);
440
441# These are the aliases above that differ under :loose and :full matching
442# because the :full versions have blanks or hyphens in them.
443my %loose_system_aliases = (
444 'LINEFEED' => pack("U", 0x0A),
445 'FORMFEED' => pack("U", 0x0C),
446 'CARRIAGERETURN' => pack("U", 0x0D),
447 'NEXTLINE' => pack("U", 0x85),
448 'SINGLESHIFT2' => pack("U", 0x8E),
449 'SINGLESHIFT3' => pack("U", 0x8F),
450 'PRIVATEUSE1' => pack("U", 0x91),
451 'PRIVATEUSE2' => pack("U", 0x92),
452 'STARTOFPROTECTEDAREA' => pack("U", 0x96),
453 'ENDOFPROTECTEDAREA' => pack("U", 0x97),
454 'PADDINGCHARACTER' => pack("U", 0x80),
455 'HIGHOCTETPRESET' => pack("U", 0x81),
456 'SINGLEGRAPHICCHARACTERINTRODUCER' => pack("U", 0x99),
457 'BYTEORDERMARK' => pack("U", 0xFEFF),
458);
459
460my %deprecated_aliases = (
461 # Pre-3.2 compatibility (only for the first 256 characters).
462 # Use of these gives deprecated message.
463 'HORIZONTAL TABULATION' => pack("U", 0x09), # CHARACTER TABULATION
464 'VERTICAL TABULATION' => pack("U", 0x0B), # LINE TABULATION
465 'FILE SEPARATOR' => pack("U", 0x1C), # INFORMATION SEPARATOR FOUR
466 'GROUP SEPARATOR' => pack("U", 0x1D), # INFORMATION SEPARATOR THREE
467 'RECORD SEPARATOR' => pack("U", 0x1E), # INFORMATION SEPARATOR TWO
468 'UNIT SEPARATOR' => pack("U", 0x1F), # INFORMATION SEPARATOR ONE
469 'HORIZONTAL TABULATION SET' => pack("U", 0x88), # CHARACTER TABULATION SET
470 'HORIZONTAL TABULATION WITH JUSTIFICATION' => pack("U", 0x89), # CHARACTER TABULATION WITH JUSTIFICATION
471 'PARTIAL LINE DOWN' => pack("U", 0x8B), # PARTIAL LINE FORWARD
472 'PARTIAL LINE UP' => pack("U", 0x8C), # PARTIAL LINE BACKWARD
473 'VERTICAL TABULATION SET' => pack("U", 0x8A), # LINE TABULATION SET
474 'REVERSE INDEX' => pack("U", 0x8D), # REVERSE LINE FEED
475
476 # Unicode 6.0 co-opted this for U+1F514, so deprecate it for now.
477 'BELL' => pack("U", 0x07),
478);
479
480my %loose_deprecated_aliases = (
481 'HORIZONTALTABULATION' => pack("U", 0x09),
482 'VERTICALTABULATION' => pack("U", 0x0B),
483 'FILESEPARATOR' => pack("U", 0x1C),
484 'GROUPSEPARATOR' => pack("U", 0x1D),
485 'RECORDSEPARATOR' => pack("U", 0x1E),
486 'UNITSEPARATOR' => pack("U", 0x1F),
487 'HORIZONTALTABULATIONSET' => pack("U", 0x88),
488 'HORIZONTALTABULATIONWITHJUSTIFICATION' => pack("U", 0x89),
489 'PARTIALLINEDOWN' => pack("U", 0x8B),
490 'PARTIALLINEUP' => pack("U", 0x8C),
491 'VERTICALTABULATIONSET' => pack("U", 0x8A),
492 'REVERSEINDEX' => pack("U", 0x8D),
493);
494
495# These are special cased in :loose matching, differing only in a medial
496# hyphen
497my $HANGUL_JUNGSEONG_O_E_utf8 = pack("U", 0x1180);
498my $HANGUL_JUNGSEONG_OE_utf8 = pack("U", 0x116C);
499
500
501my $txt; # The table of official character names
502
503my %full_names_cache; # Holds already-looked-up names, so don't have to
504# re-look them up again. The previous versions of charnames had scoping
505# bugs. For example if we use script A in one scope and find and cache
506# what Z resolves to, we can't use that cache in a different scope that
507# uses script B instead of A, as Z might be an entirely different letter
508# there; or there might be different aliases in effect in different
509# scopes, or :short may be in effect or not effect in different scopes,
510# or various combinations thereof. This was solved in this version
511# mostly by moving things to %^H. But some things couldn't be moved
512# there. One of them was the cache of runtime looked-up names, in part
513# because %^H is read-only at runtime. I (khw) don't know why the cache
514# was run-time only in the previous versions: perhaps oversight; perhaps
515# that compile time looking doesn't happen in a loop so didn't think it
516# was worthwhile; perhaps not wanting to make the cache too large. But
517# I decided to make it compile time as well; this could easily be
518# changed.
519# Anyway, this hash is not scoped, and is added to at runtime. It
520# doesn't have scoping problems because the data in it is restricted to
521# official names, which are always invariant, and we only set it and
522# look at it at during :full lookups, so is unaffected by any other
523# scoped options. I put this in to maintain parity with the older
524# version. If desired, a %short_names cache could also be made, as well
525# as one for each script, say in %script_names_cache, with each key
526# being a hash for a script named in a 'use charnames' statement. I
527# decided not to do that for now, just because it's added complication,
528# and because I'm just trying to maintain parity, not extend it.
529
530# Like %full_names_cache, but for use when :loose is in effect. There needs
531# to be two caches because :loose may not be in effect for a scope, and a
532# loose name could inappropriately be returned when only exact matching is
533# called for.
534my %loose_names_cache;
535
536# Designed so that test decimal first, and then hex. Leading zeros
537# imply non-decimal, as do non-[0-9]
538my $decimal_qr = qr/^[1-9]\d*$/;
539
540# Returns the hex number in $1.
541my $hex_qr = qr/^(?:[Uu]\+|0[xX])?([[:xdigit:]]+)$/;
542
543sub croak
544{
545 require Carp; goto &Carp::croak;
546} # croak
547
548sub carp
549{
550 require Carp; goto &Carp::carp;
551} # carp
552
553sub alias (@) # Set up a single alias
554{
555 my $alias = ref $_[0] ? $_[0] : { @_ };
556 foreach my $name (keys %$alias) {
557 my $value = $alias->{$name};
558 next unless defined $value; # Omit if screwed up.
559
560 # Is slightly slower to just after this statement see if it is
561 # decimal, since we already know it is after having converted from
562 # hex, but makes the code easier to maintain, and is called
563 # infrequently, only at compile-time
564 if ($value !~ $decimal_qr && $value =~ $hex_qr) {
565 $value = CORE::hex $1;
566 }
567 if ($value =~ $decimal_qr) {
568 no warnings qw(non_unicode surrogate nonchar); # Allow any non-malformed
569 $^H{charnames_ord_aliases}{$name} = pack("U", $value);
570
571 # Use a canonical form.
572 $^H{charnames_inverse_ords}{sprintf("%05X", $value)} = $name;
573 }
574 else {
575 # XXX validate syntax when deprecation cycle complete. ie. start
576 # with an alpha only, etc.
577 $^H{charnames_name_aliases}{$name} = $value;
578 }
579 }
580} # alias
581
582sub not_legal_use_bytes_msg {
583 my ($name, $utf8) = @_;
584 my $return;
585
586 if (length($utf8) == 1) {
587 $return = sprintf("Character 0x%04x with name '%s' is", ord $utf8, $name);
588 } else {
589 $return = sprintf("String with name '%s' (and ordinals %s) contains character(s)", $name, join(" ", map { sprintf "0x%04X", ord $_ } split(//, $utf8)));
590 }
591 return $return . " above 0xFF with 'use bytes' in effect";
592}
593
594sub alias_file ($) # Reads a file containing alias definitions
595{
596 my ($arg, $file) = @_;
597 if (-f $arg && File::Spec->file_name_is_absolute ($arg)) {
598 $file = $arg;
599 }
600 elsif ($arg =~ m/^\w+$/) {
601 $file = "unicore/${arg}_alias.pl";
602 }
603 else {
604 croak "Charnames alias files can only have identifier characters";
605 }
606 if (my @alias = do $file) {
607 @alias == 1 && !defined $alias[0] and
608 croak "$file cannot be used as alias file for charnames";
609 @alias % 2 and
610 croak "$file did not return a (valid) list of alias pairs";
611 alias (@alias);
612 return (1);
613 }
614 0;
615} # alias_file
616
617# For use when don't import anything. This structure must be kept in
618# sync with the one that import() fills up.
619my %dummy_H = (
620 charnames_stringified_names => "",
621 charnames_stringified_ords => "",
622 charnames_scripts => "",
623 charnames_full => 1,
624 charnames_loose => 0,
625 charnames_short => 0,
626 );
627
628
629sub lookup_name ($$$) {
630 my ($name, $wants_ord, $runtime) = @_;
631
632 # Lookup the name or sequence $name in the tables. If $wants_ord is false,
633 # returns the string equivalent of $name; if true, returns the ordinal value
634 # instead, but in this case $name must not be a sequence; otherwise undef is
635 # returned and a warning raised. $runtime is 0 if compiletime, otherwise
636 # gives the number of stack frames to go back to get the application caller
637 # info.
638 # If $name is not found, returns undef in runtime with no warning; and in
639 # compiletime, the Unicode replacement character, with a warning.
640
641 # It looks first in the aliases, then in the large table of official Unicode
642 # names.
643
644 my $utf8; # The string result
645 my $save_input;
646
647 if ($runtime) {
648
649 my $hints_ref = (caller($runtime))[10];
650
651 # If we didn't import anything (which happens with 'use charnames ()',
652 # substitute a dummy structure.
653 $hints_ref = \%dummy_H if ! defined $hints_ref
654 || (! defined $hints_ref->{charnames_full}
655 && ! defined $hints_ref->{charnames_loose});
656
657 # At runtime, but currently not at compile time, $^H gets
658 # stringified, so un-stringify back to the original data structures.
659 # These get thrown away by perl before the next invocation
660 # Also fill in the hash with the non-stringified data.
661 # N.B. New fields must be also added to %dummy_H
662
663 %{$^H{charnames_name_aliases}} = split ',',
664 $hints_ref->{charnames_stringified_names};
665 %{$^H{charnames_ord_aliases}} = split ',',
666 $hints_ref->{charnames_stringified_ords};
667 $^H{charnames_scripts} = $hints_ref->{charnames_scripts};
668 $^H{charnames_full} = $hints_ref->{charnames_full};
669 $^H{charnames_loose} = $hints_ref->{charnames_loose};
670 $^H{charnames_short} = $hints_ref->{charnames_short};
671 }
672
673 my $loose = $^H{charnames_loose};
674 my $lookup_name; # Input name suitably modified for grepping for in the
675 # table
676
677 # User alias should be checked first or else can't override ours, and if we
678 # were to add any, could conflict with theirs.
679 if (exists $^H{charnames_ord_aliases}{$name}) {
680 $utf8 = $^H{charnames_ord_aliases}{$name};
681 }
682 elsif (exists $^H{charnames_name_aliases}{$name}) {
683 $name = $^H{charnames_name_aliases}{$name};
684 $save_input = $lookup_name = $name; # Cache the result for any error
685 # message
686 # The aliases are documented to not match loosely, so change loose match
687 # into full.
688 if ($loose) {
689 $loose = 0;
690 $^H{charnames_full} = 1;
691 }
692 }
693 else {
694
695 # Here, not a user alias. That means that loose matching may be in
696 # effect; will have to modify the input name.
697 $lookup_name = $name;
698 if ($loose) {
699 $lookup_name = uc $lookup_name;
700
701 # Squeeze out all underscores
702 $lookup_name =~ s/_//g;
703
704 # Remove all medial hyphens
705 $lookup_name =~ s/ (?<= \S ) - (?= \S )//gx;
706
707 # Squeeze out all spaces
708 $lookup_name =~ s/\s//g;
709 }
710
711 # Here, $lookup_name has been modified as necessary for looking in the
712 # hashes. Check the system alias files next. Most of these aliases are
713 # the same for both strict and loose matching. To save space, the ones
714 # which differ are in their own separate hash, which is checked if loose
715 # matching is selected and the regular match fails. To save time, the
716 # loose hashes could be expanded to include all aliases, and there would
717 # only have to be one check. But if someone specifies :loose, they are
718 # interested in convenience over speed, and the time for this second check
719 # is miniscule compared to the rest of the routine.
720 if (exists $system_aliases{$lookup_name}) {
721 $utf8 = $system_aliases{$lookup_name};
722 }
723 elsif ($loose && exists $loose_system_aliases{$lookup_name}) {
724 $utf8 = $loose_system_aliases{$lookup_name};
725 }
726 elsif (exists $deprecated_aliases{$lookup_name}) {
727 require warnings;
728 warnings::warnif('deprecated',
729 "Unicode character name \"$name\" is deprecated, use \""
730 . viacode(ord $deprecated_aliases{$lookup_name})
731 . "\" instead");
732 $utf8 = $deprecated_aliases{$lookup_name};
733 }
734 elsif ($loose && exists $loose_deprecated_aliases{$lookup_name}) {
735 require warnings;
736 warnings::warnif('deprecated',
737 "Unicode character name \"$name\" is deprecated, use \""
738 . viacode(ord $loose_deprecated_aliases{$lookup_name})
739 . "\" instead");
740 $utf8 = $loose_deprecated_aliases{$lookup_name};
741 }
742 }
743
744 my @off; # Offsets into table of pattern match begin and end
745
746 # If haven't found it yet...
747 if (! defined $utf8) {
748
749 # See if has looked this input up earlier.
750 if (! $loose && $^H{charnames_full} && exists $full_names_cache{$name}) {
751 $utf8 = $full_names_cache{$name};
752 }
753 elsif ($loose && exists $loose_names_cache{$name}) {
754 $utf8 = $loose_names_cache{$name};
755 }
756 else { # Here, must do a look-up
757
758 # If full or loose matching succeeded, points to where to cache the
759 # result
760 my $cache_ref;
761
762 ## Suck in the code/name list as a big string.
763 ## Lines look like:
764 ## "00052\tLATIN CAPITAL LETTER R\n"
765 # or
766 # "0052 0303\tLATIN CAPITAL LETTER R WITH TILDE\n"
767 $txt = do "unicore/Name.pl" unless $txt;
768
769 ## @off will hold the index into the code/name string of the start and
770 ## end of the name as we find it.
771
772 ## If :loose, look for a loose match; if :full, look for the name
773 ## exactly
774 # First, see if the name is one which is algorithmically determinable.
775 # The subroutine is included in Name.pl. The table contained in
776 # $txt doesn't contain these. Experiments show that checking
777 # for these before checking for the regular names has no
778 # noticeable impact on performance for the regular names, but
779 # the other way around slows down finding these immensely.
780 # Algorithmically determinables are not placed in the cache because
781 # that uses up memory, and finding these again is fast.
782 if (($loose || $^H{charnames_full})
783 && (defined (my $ord = charnames::name_to_code_point_special($lookup_name, $loose))))
784 {
785 $utf8 = pack("U", $ord);
786 }
787 else {
788
789 # Not algorithmically determinable; look up in the table. The name
790 # will be turned into a regex, so quote any meta characters.
791 $lookup_name = quotemeta $lookup_name;
792
793 if ($loose) {
794
795 # For loose matches, $lookup_name has already squeezed out the
796 # non-essential characters. We have to add in code to make the
797 # squeezed version match the non-squeezed equivalent in the table.
798 # The only remaining hyphens are ones that start or end a word in
799 # the original. They have been quoted in $lookup_name so they look
800 # like "\-". Change all other characters except the backslash
801 # quotes for any metacharacters, and the final character, so that
802 # e.g., COLON gets transformed into: /C[- ]?O[- ]?L[- ]?O[- ]?N/
803 $lookup_name =~ s/ (?! \\ -) # Don't do this to the \- sequence
804 ( [^-\\] ) # Nor the "-" within that sequence,
805 # nor the "\" that quotes metachars,
806 # but otherwise put the char into $1
807 (?=.) # And don't do it for the final char
808 /$1\[- \]?/gx; # And add an optional blank or
809 # '-' after each $1 char
810
811 # Those remaining hyphens were originally at the beginning or end of
812 # a word, so they can match either a blank before or after, but not
813 # both. (Keep in mind that they have been quoted, so are a '\-'
814 # sequence)
815 $lookup_name =~ s/\\ -/(?:- | -)/xg;
816 }
817
818 # Do the lookup in the full table if asked for, and if succeeds
819 # save the offsets and set where to cache the result.
820 if (($loose || $^H{charnames_full}) && $txt =~ /\t$lookup_name$/m) {
821 @off = ($-[0] + 1, $+[0]); # The 1 is for the tab
822 $cache_ref = ($loose) ? \%loose_names_cache : \%full_names_cache;
823 }
824 else {
825
826 # Here, didn't look for, or didn't find the name.
827 # If :short is allowed, see if input is like "greek:Sigma".
828 # Keep in mind that $lookup_name has had the metas quoted.
829 my $scripts_trie = "";
830 my $name_has_uppercase;
831 if (($^H{charnames_short})
832 && $lookup_name =~ /^ (?: \\ \s)* # Quoted space
833 (.+?) # $1 = the script
834 (?: \\ \s)*
835 \\ : # Quoted colon
836 (?: \\ \s)*
837 (.+?) # $2 = the name
838 (?: \\ \s)* $
839 /xs)
840 {
841 # Even in non-loose matching, the script traditionally has been
842 # case insensitve
843 $scripts_trie = "\U$1";
844 $lookup_name = $2;
845
846 # Use original name to find its input casing, but ignore the
847 # script part of that to make the determination.
848 $save_input = $name if ! defined $save_input;
849 $name =~ s/.*?://;
850 $name_has_uppercase = $name =~ /[[:upper:]]/;
851 }
852 else { # Otherwise look in allowed scripts
853 $scripts_trie = $^H{charnames_scripts};
854
855 # Use original name to find its input casing
856 $name_has_uppercase = $name =~ /[[:upper:]]/;
857 }
858
859 my $case = $name_has_uppercase ? "CAPITAL" : "SMALL";
860 if (! $scripts_trie
861 || $txt !~
862 /\t (?: $scripts_trie ) \ (?:$case\ )? LETTER \ \U$lookup_name $/xm)
863 {
864 # Here we still don't have it, give up.
865 return if $runtime;
866
867 # May have zapped input name, get it again.
868 $name = (defined $save_input) ? $save_input : $_[0];
869 carp "Unknown charname '$name'";
870 return ($wants_ord) ? 0xFFFD : pack("U", 0xFFFD);
871 }
872
873 # Here have found the input name in the table.
874 @off = ($-[0] + 1, $+[0]); # The 1 is for the tab
875 }
876
877 # Here, the input name has been found; we haven't set up the output,
878 # but we know where in the string
879 # the name starts. The string is set up so that for single characters
880 # (and not named sequences), the name is preceded immediately by a
881 # tab and 5 hex digits for its code, with a \n before those. Named
882 # sequences won't have the 7th preceding character be a \n.
883 # (Actually, for the very first entry in the table this isn't strictly
884 # true: subtracting 7 will yield -1, and the substr below will
885 # therefore yield the very last character in the table, which should
886 # also be a \n, so the statement works anyway.)
887 if (substr($txt, $off[0] - 7, 1) eq "\n") {
888 $utf8 = pack("U", CORE::hex substr($txt, $off[0] - 6, 5));
889
890 # Handle the single loose matching special case, in which two names
891 # differ only by a single medial hyphen. If the original had a
892 # hyphen (or more) in the right place, then it is that one.
893 $utf8 = $HANGUL_JUNGSEONG_O_E_utf8
894 if $loose
895 && $utf8 eq $HANGUL_JUNGSEONG_OE_utf8
896 && $name =~ m/O \s* - [-\s]* E/ix;
897 # Note that this wouldn't work if there were a 2nd
898 # OE in the name
899 }
900 else {
901
902 # Here, is a named sequence. Need to go looking for the beginning,
903 # which is just after the \n from the previous entry in the table.
904 # The +1 skips past that newline, or, if the rindex() fails, to put
905 # us to an offset of zero.
906 my $charstart = rindex($txt, "\n", $off[0] - 7) + 1;
907 $utf8 = pack("U*", map { CORE::hex }
908 split " ", substr($txt, $charstart, $off[0] - $charstart - 1));
909 }
910 }
911
912 # Cache the input so as to not have to search the large table
913 # again, but only if it came from the one search that we cache.
914 # (Haven't bothered with the pain of sorting out scoping issues for the
915 # scripts searches.)
916 $cache_ref->{$name} = $utf8 if defined $cache_ref;
917 }
918 }
919
920
921 # Here, have the utf8. If the return is to be an ord, must be any single
922 # character.
923 if ($wants_ord) {
924 return ord($utf8) if length $utf8 == 1;
925 }
926 else {
927
928 # Here, wants string output. If utf8 is acceptable, just return what
929 # we've got; otherwise attempt to convert it to non-utf8 and return that.
930 my $in_bytes = ($runtime)
931 ? (caller $runtime)[8] & $bytes::hint_bits
932 : $^H & $bytes::hint_bits;
933 return $utf8 if (! $in_bytes || utf8::downgrade($utf8, 1)) # The 1 arg
934 # means don't die on failure
935 }
936
937 # Here, there is an error: either there are too many characters, or the
938 # result string needs to be non-utf8, and at least one character requires
939 # utf8. Prefer any official name over the input one for the error message.
940 if (@off) {
941 $name = substr($txt, $off[0], $off[1] - $off[0]) if @off;
942 }
943 else {
944 $name = (defined $save_input) ? $save_input : $_[0];
945 }
946
947 if ($wants_ord) {
948 # Only way to get here in this case is if result too long. Message
949 # assumes that our only caller that requires single char result is
950 # vianame.
951 carp "charnames::vianame() doesn't handle named sequences ($name). Use charnames::string_vianame() instead";
952 return;
953 }
954
955 # Only other possible failure here is from use bytes.
956 if ($runtime) {
957 carp not_legal_use_bytes_msg($name, $utf8);
958 return;
959 } else {
960 croak not_legal_use_bytes_msg($name, $utf8);
961 }
962
963} # lookup_name
964
965sub charnames {
966
967 # For \N{...}. Looks up the character name and returns the string
968 # representation of it.
969
970 # The first 0 arg means wants a string returned; the second that we are in
971 # compile time
972 return lookup_name($_[0], 0, 0);
973}
974
975sub import
976{
977 shift; ## ignore class name
978
979 if (not @_) {
980 carp("'use charnames' needs explicit imports list");
981 }
982 $^H{charnames} = \&charnames ;
983 $^H{charnames_ord_aliases} = {};
984 $^H{charnames_name_aliases} = {};
985 $^H{charnames_inverse_ords} = {};
986 # New fields must be added to %dummy_H, and the code in lookup_name()
987 # that copies fields from the runtime structure
988
989 ##
990 ## fill %h keys with our @_ args.
991 ##
992 my ($promote, %h, @args) = (0);
993 while (my $arg = shift) {
994 if ($arg eq ":alias") {
995 @_ or
996 croak ":alias needs an argument in charnames";
997 my $alias = shift;
998 if (ref $alias) {
999 ref $alias eq "HASH" or
1000 croak "Only HASH reference supported as argument to :alias";
1001 alias ($alias);
1002 next;
1003 }
1004 if ($alias =~ m{:(\w+)$}) {
1005 $1 eq "full" || $1 eq "loose" || $1 eq "short" and
1006 croak ":alias cannot use existing pragma :$1 (reversed order?)";
1007 alias_file ($1) and $promote = 1;
1008 next;
1009 }
1010 alias_file ($alias);
1011 next;
1012 }
1013 if (substr($arg, 0, 1) eq ':'
1014 and ! ($arg eq ":full" || $arg eq ":short" || $arg eq ":loose"))
1015 {
1016 warn "unsupported special '$arg' in charnames";
1017 next;
1018 }
1019 push @args, $arg;
1020 }
1021
1022 @args == 0 && $promote and @args = (":full");
1023 @h{@args} = (1) x @args;
1024
1025 # Don't leave these undefined as are tested for in lookup_names
1026 $^H{charnames_full} = delete $h{':full'} || 0;
1027 $^H{charnames_loose} = delete $h{':loose'} || 0;
1028 $^H{charnames_short} = delete $h{':short'} || 0;
1029 my @scripts = map { uc quotemeta } keys %h;
1030
1031 ##
1032 ## If utf8? warnings are enabled, and some scripts were given,
1033 ## see if at least we can find one letter from each script.
1034 ##
1035 if (warnings::enabled('utf8') && @scripts) {
1036 $txt = do "unicore/Name.pl" unless $txt;
1037
1038 for my $script (@scripts) {
1039 if (not $txt =~ m/\t$script (?:CAPITAL |SMALL )?LETTER /) {
1040 warnings::warn('utf8', "No such script: '$script'");
1041 $script = quotemeta $script; # Escape it, for use in the re.
1042 }
1043 }
1044 }
1045
1046 # %^H gets stringified, so serialize it ourselves so can extract the
1047 # real data back later.
1048 $^H{charnames_stringified_ords} = join ",", %{$^H{charnames_ord_aliases}};
1049 $^H{charnames_stringified_names} = join ",", %{$^H{charnames_name_aliases}};
1050 $^H{charnames_stringified_inverse_ords} = join ",", %{$^H{charnames_inverse_ords}};
1051
1052 # Modify the input script names for loose name matching if that is also
1053 # specified, similar to the way the base character name is prepared. They
1054 # don't (currently, and hopefully never will) have dashes. These go into a
1055 # regex, and have already been uppercased and quotemeta'd. Squeeze out all
1056 # input underscores, blanks, and dashes. Then convert so will match a blank
1057 # between any characters.
1058 if ($^H{charnames_loose}) {
1059 for (my $i = 0; $i < @scripts; $i++) {
1060 $scripts[$i] =~ s/[_ -]//g;
1061 $scripts[$i] =~ s/ ( [^\\] ) (?= . ) /$1\\ ?/gx;
1062 }
1063 }
1064
1065 $^H{charnames_scripts} = join "|", @scripts; # Stringifiy them as a trie
1066} # import
1067
1068# Cache of already looked-up values. This is set to only contain
1069# official values, and user aliases can't override them, so scoping is
1070# not an issue.
1071my %viacode;
1072
1073sub viacode {
1074
1075 # Returns the name of the code point argument
1076
1077 if (@_ != 1) {
1078 carp "charnames::viacode() expects one argument";
1079 return;
1080 }
1081
1082 my $arg = shift;
1083
1084 # This is derived from Unicode::UCD, where it is nearly the same as the
1085 # function _getcode(), but here it makes sure that even a hex argument
1086 # has the proper number of leading zeros, which is critical in
1087 # matching against $txt below
1088 # Must check if decimal first; see comments at that definition
1089 my $hex;
1090 if ($arg =~ $decimal_qr) {
1091 $hex = sprintf "%05X", $arg;
1092 } elsif ($arg =~ $hex_qr) {
1093 # Below is the line that differs from the _getcode() source
1094 $hex = sprintf "%05X", hex $1;
1095 } else {
1096 carp("unexpected arg \"$arg\" to charnames::viacode()");
1097 return;
1098 }
1099
1100 return $viacode{$hex} if exists $viacode{$hex};
1101
1102 # If the code point is above the max in the table, there's no point
1103 # looking through it. Checking the length first is slightly faster
1104 if (length($hex) <= 5 || CORE::hex($hex) <= 0x10FFFF) {
1105 $txt = do "unicore/Name.pl" unless $txt;
1106
1107 # See if the name is algorithmically determinable.
1108 my $algorithmic = charnames::code_point_to_name_special(CORE::hex $hex);
1109 if (defined $algorithmic) {
1110 $viacode{$hex} = $algorithmic;
1111 return $algorithmic;
1112 }
1113
1114 # Return the official name, if exists. It's unclear to me (khw) at
1115 # this juncture if it is better to return a user-defined override, so
1116 # leaving it as is for now.
1117 if ($txt =~ m/^$hex\t/m) {
1118
1119 # The name starts with the next character and goes up to the
1120 # next new-line. Using capturing parentheses above instead of
1121 # @+ more than doubles the execution time in Perl 5.13
1122 $viacode{$hex} = substr($txt, $+[0], index($txt, "\n", $+[0]) - $+[0]);
1123 return $viacode{$hex};
1124 }
1125 }
1126
1127 # See if there is a user name for it, before giving up completely.
1128 # First get the scoped aliases, give up if have none.
1129 my $H_ref = (caller(1))[10];
1130 return if ! defined $H_ref
1131 || ! exists $H_ref->{charnames_stringified_inverse_ords};
1132
1133 my %code_point_aliases = split ',',
1134 $H_ref->{charnames_stringified_inverse_ords};
1135 if (! exists $code_point_aliases{$hex}) {
1136 if (CORE::hex($hex) > 0x10FFFF) {
1137 carp "Unicode characters only allocated up to U+10FFFF (you asked for U+$hex)";
1138 }
1139 return;
1140 }
1141
1142 return $code_point_aliases{$hex};
1143} # _viacode
1144
11451;
1146
1147# ex: set ts=8 sts=2 sw=2 et: