1 /*
2 * Copyright (c) 2015, Oracle and/or its affiliates. All rights reserved.
3 */
4 /*
5 * Licensed to the Apache Software Foundation (ASF) under one or more
6 * contributor license agreements. See the NOTICE file distributed with
7 * this work for additional information regarding copyright ownership.
8 * The ASF licenses this file to You under the Apache License, Version 2.0
9 * (the "License"); you may not use this file except in compliance with
10 * the License. You may obtain a copy of the License at
11 *
12 * http://www.apache.org/licenses/LICENSE-2.0
13 *
14 * Unless required by applicable law or agreed to in writing, software
15 * distributed under the License is distributed on an "AS IS" BASIS,
16 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
17 * See the License for the specific language governing permissions and
18 * limitations under the License.
19 */
20
21 package com.sun.org.apache.xerces.internal.impl.xpath.regex;
22
23 import java.util.HashMap;
24 import java.util.Locale;
25 import java.util.Map;
26
27 /**
28 * A regular expression parser for the XML Schema.
29 *
30 * @xerces.internal
31 *
32 * @author TAMURA Kent <kent@trl.ibm.co.jp>
33 * @version $Id: ParserForXMLSchema.java,v 1.9 2010-11-12 18:09:45 joehw Exp $
34 */
35 class ParserForXMLSchema extends RegexParser {
36
37 public ParserForXMLSchema() {
38 //this.setLocale(Locale.getDefault());
39 }
40 public ParserForXMLSchema(Locale locale) {
41 super(locale);
42 }
43
44 Token processCaret() throws ParseException {
45 this.next();
46 return Token.createChar('^');
47 }
48 Token processDollar() throws ParseException {
49 this.next();
50 return Token.createChar('$');
51 }
52 Token processLookahead() throws ParseException {
53 throw ex("parser.process.1", this.offset);
54 }
55 Token processNegativelookahead() throws ParseException {
56 throw ex("parser.process.1", this.offset);
57 }
58 Token processLookbehind() throws ParseException {
59 throw ex("parser.process.1", this.offset);
60 }
61 Token processNegativelookbehind() throws ParseException {
62 throw ex("parser.process.1", this.offset);
63 }
64 Token processBacksolidus_A() throws ParseException {
65 throw ex("parser.process.1", this.offset);
66 }
67 Token processBacksolidus_Z() throws ParseException {
68 throw ex("parser.process.1", this.offset);
69 }
70 Token processBacksolidus_z() throws ParseException {
71 throw ex("parser.process.1", this.offset);
72 }
73 Token processBacksolidus_b() throws ParseException {
74 throw ex("parser.process.1", this.offset);
75 }
76 Token processBacksolidus_B() throws ParseException {
77 throw ex("parser.process.1", this.offset);
78 }
79 Token processBacksolidus_lt() throws ParseException {
80 throw ex("parser.process.1", this.offset);
81 }
82 Token processBacksolidus_gt() throws ParseException {
83 throw ex("parser.process.1", this.offset);
84 }
85 Token processStar(Token tok) throws ParseException {
86 this.next();
87 return Token.createClosure(tok);
88 }
89 Token processPlus(Token tok) throws ParseException {
90 // X+ -> XX*
91 this.next();
92 return Token.createConcat(tok, Token.createClosure(tok));
93 }
94 Token processQuestion(Token tok) throws ParseException {
95 // X? -> X|
96 this.next();
97 Token par = Token.createUnion();
98 par.addChild(tok);
99 par.addChild(Token.createEmpty());
100 return par;
101 }
102 boolean checkQuestion(int off) {
103 return false;
104 }
105 Token processParen() throws ParseException {
106 this.next();
107 Token tok = Token.createParen(this.parseRegex(), 0);
108 if (this.read() != T_RPAREN) throw ex("parser.factor.1", this.offset-1);
109 this.next(); // Skips ')'
110 return tok;
111 }
112 Token processParen2() throws ParseException {
113 throw ex("parser.process.1", this.offset);
114 }
115 Token processCondition() throws ParseException {
116 throw ex("parser.process.1", this.offset);
117 }
118 Token processModifiers() throws ParseException {
119 throw ex("parser.process.1", this.offset);
120 }
121 Token processIndependent() throws ParseException {
122 throw ex("parser.process.1", this.offset);
123 }
124 Token processBacksolidus_c() throws ParseException {
125 this.next();
126 return this.getTokenForShorthand('c');
127 }
128 Token processBacksolidus_C() throws ParseException {
129 this.next();
130 return this.getTokenForShorthand('C');
131 }
132 Token processBacksolidus_i() throws ParseException {
133 this.next();
134 return this.getTokenForShorthand('i');
135 }
136 Token processBacksolidus_I() throws ParseException {
137 this.next();
138 return this.getTokenForShorthand('I');
139 }
140 Token processBacksolidus_g() throws ParseException {
141 throw this.ex("parser.process.1", this.offset-2);
142 }
143 Token processBacksolidus_X() throws ParseException {
144 throw ex("parser.process.1", this.offset-2);
145 }
146 Token processBackreference() throws ParseException {
147 throw ex("parser.process.1", this.offset-4);
148 }
149
150 int processCIinCharacterClass(RangeToken tok, int c) {
151 tok.mergeRanges(this.getTokenForShorthand(c));
152 return -1;
153 }
154
155
156 /**
157 * Parses a character-class-expression, not a character-class-escape.
158 *
159 * c-c-expression ::= '[' c-group ']'
160 * c-group ::= positive-c-group | negative-c-group | c-c-subtraction
161 * positive-c-group ::= (c-range | c-c-escape)+
162 * negative-c-group ::= '^' positive-c-group
163 * c-c-subtraction ::= (positive-c-group | negative-c-group) subtraction
164 * subtraction ::= '-' c-c-expression
165 * c-range ::= single-range | from-to-range
166 * single-range ::= multi-c-escape | category-c-escape | block-c-escape | <any XML char>
167 * cc-normal-c ::= <any character except [, ], \>
168 * from-to-range ::= cc-normal-c '-' cc-normal-c
169 *
170 * @param useNrage Ignored.
171 * @return This returns no NrageToken.
172 */
173 protected RangeToken parseCharacterClass(boolean useNrange) throws ParseException {
174 this.setContext(S_INBRACKETS);
175 this.next(); // '['
176 boolean nrange = false;
177 boolean wasDecoded = false; // used to detect if the last - was escaped.
178 RangeToken base = null;
179 RangeToken tok;
180 if (this.read() == T_CHAR && this.chardata == '^') {
181 nrange = true;
182 this.next(); // '^'
183 base = Token.createRange();
184 base.addRange(0, Token.UTF16_MAX);
185 tok = Token.createRange();
186 } else {
187 tok = Token.createRange();
188 }
189 int type;
190 boolean firstloop = true;
191 while ((type = this.read()) != T_EOF) { // Don't use 'cotinue' for this loop.
192
193 wasDecoded = false;
194 // single-range | from-to-range | subtraction
195 if (type == T_CHAR && this.chardata == ']' && !firstloop) {
196 if (nrange) {
197 base.subtractRanges(tok);
198 tok = base;
199 }
200 break;
201 }
202 int c = this.chardata;
203 boolean end = false;
204 if (type == T_BACKSOLIDUS) {
205 switch (c) {
206 case 'd': case 'D':
207 case 'w': case 'W':
208 case 's': case 'S':
209 tok.mergeRanges(this.getTokenForShorthand(c));
210 end = true;
211 break;
212
213 case 'i': case 'I':
214 case 'c': case 'C':
215 c = this.processCIinCharacterClass(tok, c);
216 if (c < 0) end = true;
217 break;
218
219 case 'p':
220 case 'P':
221 int pstart = this.offset;
222 RangeToken tok2 = this.processBacksolidus_pP(c);
223 if (tok2 == null) throw this.ex("parser.atom.5", pstart);
224 tok.mergeRanges(tok2);
225 end = true;
226 break;
227
228 case '-':
229 c = this.decodeEscaped();
230 wasDecoded = true;
231 break;
232
233 default:
234 c = this.decodeEscaped();
235 } // \ + c
236 } // backsolidus
237 else if (type == T_XMLSCHEMA_CC_SUBTRACTION && !firstloop) {
238 // Subraction
239 if (nrange) {
240 base.subtractRanges(tok);
241 tok = base;
242 }
243 RangeToken range2 = this.parseCharacterClass(false);
244 tok.subtractRanges(range2);
245 if (this.read() != T_CHAR || this.chardata != ']')
246 throw this.ex("parser.cc.5", this.offset);
247 break; // Exit this loop
248 }
249 this.next();
250 if (!end) { // if not shorthands...
251 if (type == T_CHAR) {
252 if (c == '[') throw this.ex("parser.cc.6", this.offset-2);
253 if (c == ']') throw this.ex("parser.cc.7", this.offset-2);
254 if (c == '-' && this.chardata != ']' && !firstloop) throw this.ex("parser.cc.8", this.offset-2); // if regex = '[-]' then invalid
255 }
256 if (this.read() != T_CHAR || this.chardata != '-' || c == '-' && firstloop) { // Here is no '-'.
257 if (!this.isSet(RegularExpression.IGNORE_CASE) || c > 0xffff) {
258 tok.addRange(c, c);
259 }
260 else {
261 addCaseInsensitiveChar(tok, c);
262 }
263 } else { // Found '-'
264 // Is this '-' is a from-to token??
265 this.next(); // Skips '-'
266 if ((type = this.read()) == T_EOF) throw this.ex("parser.cc.2", this.offset);
267 // c '-' ']' -> '-' is a single-range.
268 if(type == T_CHAR && this.chardata == ']') { // if - is at the last position of the group
269 if (!this.isSet(RegularExpression.IGNORE_CASE) || c > 0xffff) {
270 tok.addRange(c, c);
271 }
272 else {
273 addCaseInsensitiveChar(tok, c);
274 }
275 tok.addRange('-', '-');
276 }
277 else if (type == T_XMLSCHEMA_CC_SUBTRACTION) {
278 throw this.ex("parser.cc.8", this.offset-1);
279 } else {
280
281 int rangeend = this.chardata;
282 if (type == T_CHAR) {
283 if (rangeend == '[') throw this.ex("parser.cc.6", this.offset-1);
284 if (rangeend == ']') throw this.ex("parser.cc.7", this.offset-1);
285 if (rangeend == '-') throw this.ex("parser.cc.8", this.offset-2);
286 }
287 else if (type == T_BACKSOLIDUS)
288 rangeend = this.decodeEscaped();
289 this.next();
290
291 if (c > rangeend) throw this.ex("parser.ope.3", this.offset-1);
292 if (!this.isSet(RegularExpression.IGNORE_CASE) ||
293 (c > 0xffff && rangeend > 0xffff)) {
294 tok.addRange(c, rangeend);
295 }
296 else {
297 addCaseInsensitiveCharRange(tok, c, rangeend);
298 }
299 }
300 }
301 }
302 firstloop = false;
303 }
304 if (this.read() == T_EOF)
305 throw this.ex("parser.cc.2", this.offset);
306 tok.sortRanges();
307 tok.compactRanges();
308 //tok.dumpRanges();
309 this.setContext(S_NORMAL);
310 this.next(); // Skips ']'
311
312 return tok;
313 }
314
315 protected RangeToken parseSetOperations() throws ParseException {
316 throw this.ex("parser.process.1", this.offset);
317 }
318
319 Token getTokenForShorthand(int ch) {
320 switch (ch) {
321 case 'd':
322 return ParserForXMLSchema.getRange("xml:isDigit", true);
323 case 'D':
324 return ParserForXMLSchema.getRange("xml:isDigit", false);
325 case 'w':
326 return ParserForXMLSchema.getRange("xml:isWord", true);
327 case 'W':
328 return ParserForXMLSchema.getRange("xml:isWord", false);
329 case 's':
330 return ParserForXMLSchema.getRange("xml:isSpace", true);
331 case 'S':
332 return ParserForXMLSchema.getRange("xml:isSpace", false);
333 case 'c':
334 return ParserForXMLSchema.getRange("xml:isNameChar", true);
335 case 'C':
336 return ParserForXMLSchema.getRange("xml:isNameChar", false);
337 case 'i':
338 return ParserForXMLSchema.getRange("xml:isInitialNameChar", true);
339 case 'I':
340 return ParserForXMLSchema.getRange("xml:isInitialNameChar", false);
341 default:
342 throw new RuntimeException("Internal Error: shorthands: \\u"+Integer.toString(ch, 16));
343 }
344 }
345 int decodeEscaped() throws ParseException {
346 if (this.read() != T_BACKSOLIDUS) throw ex("parser.next.1", this.offset-1);
347 int c = this.chardata;
348 switch (c) {
349 case 'n': c = '\n'; break; // LINE FEED U+000A
350 case 'r': c = '\r'; break; // CRRIAGE RETURN U+000D
351 case 't': c = '\t'; break; // HORIZONTAL TABULATION U+0009
352 case '\\':
353 case '|':
354 case '.':
355 case '^':
356 case '-':
357 case '?':
358 case '*':
359 case '+':
360 case '{':
361 case '}':
362 case '(':
363 case ')':
364 case '[':
365 case ']':
366 break; // return actucal char
367 default:
368 throw ex("parser.process.1", this.offset-2);
369 }
370 return c;
371 }
372
373 static private Map<String, Token> ranges = null;
374 static private Map<String, Token> ranges2 = null;
375 static synchronized protected RangeToken getRange(String name, boolean positive) {
376 if (ranges == null) {
377 ranges = new HashMap<>();
378 ranges2 = new HashMap<>();
379
380 Token tok = Token.createRange();
381 setupRange(tok, SPACES);
382 ranges.put("xml:isSpace", tok);
383 ranges2.put("xml:isSpace", Token.complementRanges(tok));
384
385 tok = Token.createRange();
386 setupRange(tok, DIGITS);
387 setupRange(tok, DIGITS_INT);
388 ranges.put("xml:isDigit", tok);
389 ranges2.put("xml:isDigit", Token.complementRanges(tok));
390
391 tok = Token.createRange();
392 setupRange(tok, LETTERS);
393 setupRange(tok, LETTERS_INT);
394 tok.mergeRanges(ranges.get("xml:isDigit"));
395 ranges.put("xml:isWord", tok);
396 ranges2.put("xml:isWord", Token.complementRanges(tok));
397
398 tok = Token.createRange();
399 setupRange(tok, NAMECHARS);
400 ranges.put("xml:isNameChar", tok);
401 ranges2.put("xml:isNameChar", Token.complementRanges(tok));
402
403 tok = Token.createRange();
404 setupRange(tok, LETTERS);
405 tok.addRange('_', '_');
406 tok.addRange(':', ':');
407 ranges.put("xml:isInitialNameChar", tok);
408 ranges2.put("xml:isInitialNameChar", Token.complementRanges(tok));
409 }
410 RangeToken tok = positive ? (RangeToken)ranges.get(name)
411 : (RangeToken)ranges2.get(name);
412 return tok;
413 }
414
415 static void setupRange(Token range, String src) {
416 int len = src.length();
417 for (int i = 0; i < len; i += 2)
418 range.addRange(src.charAt(i), src.charAt(i+1));
419 }
420
421 static void setupRange(Token range, int[] src) {
422 int len = src.length;
423 for (int i = 0; i < len; i += 2)
424 range.addRange(src[i], src[i+1]);
425 }
426
427 private static final String SPACES = "\t\n\r\r ";
428 private static final String NAMECHARS =
429 "\u002d\u002e\u0030\u003a\u0041\u005a\u005f\u005f\u0061\u007a\u00b7\u00b7\u00c0\u00d6"
430 +"\u00d8\u00f6\u00f8\u0131\u0134\u013e\u0141\u0148\u014a\u017e\u0180\u01c3\u01cd\u01f0"
431 +"\u01f4\u01f5\u01fa\u0217\u0250\u02a8\u02bb\u02c1\u02d0\u02d1\u0300\u0345\u0360\u0361"
432 +"\u0386\u038a\u038c\u038c\u038e\u03a1\u03a3\u03ce\u03d0\u03d6\u03da\u03da\u03dc\u03dc"
433 +"\u03de\u03de\u03e0\u03e0\u03e2\u03f3\u0401\u040c\u040e\u044f\u0451\u045c\u045e\u0481"
434 +"\u0483\u0486\u0490\u04c4\u04c7\u04c8\u04cb\u04cc\u04d0\u04eb\u04ee\u04f5\u04f8\u04f9"
435 +"\u0531\u0556\u0559\u0559\u0561\u0586\u0591\u05a1\u05a3\u05b9\u05bb\u05bd\u05bf\u05bf"
436 +"\u05c1\u05c2\u05c4\u05c4\u05d0\u05ea\u05f0\u05f2\u0621\u063a\u0640\u0652\u0660\u0669"
437 +"\u0670\u06b7\u06ba\u06be\u06c0\u06ce\u06d0\u06d3\u06d5\u06e8\u06ea\u06ed\u06f0\u06f9"
438 +"\u0901\u0903\u0905\u0939\u093c\u094d\u0951\u0954\u0958\u0963\u0966\u096f\u0981\u0983"
439 +"\u0985\u098c\u098f\u0990\u0993\u09a8\u09aa\u09b0\u09b2\u09b2\u09b6\u09b9\u09bc\u09bc"
440 +"\u09be\u09c4\u09c7\u09c8\u09cb\u09cd\u09d7\u09d7\u09dc\u09dd\u09df\u09e3\u09e6\u09f1"
441 +"\u0a02\u0a02\u0a05\u0a0a\u0a0f\u0a10\u0a13\u0a28\u0a2a\u0a30\u0a32\u0a33\u0a35\u0a36"
442 +"\u0a38\u0a39\u0a3c\u0a3c\u0a3e\u0a42\u0a47\u0a48\u0a4b\u0a4d\u0a59\u0a5c\u0a5e\u0a5e"
443 +"\u0a66\u0a74\u0a81\u0a83\u0a85\u0a8b\u0a8d\u0a8d\u0a8f\u0a91\u0a93\u0aa8\u0aaa\u0ab0"
444 +"\u0ab2\u0ab3\u0ab5\u0ab9\u0abc\u0ac5\u0ac7\u0ac9\u0acb\u0acd\u0ae0\u0ae0\u0ae6\u0aef"
445 +"\u0b01\u0b03\u0b05\u0b0c\u0b0f\u0b10\u0b13\u0b28\u0b2a\u0b30\u0b32\u0b33\u0b36\u0b39"
446 +"\u0b3c\u0b43\u0b47\u0b48\u0b4b\u0b4d\u0b56\u0b57\u0b5c\u0b5d\u0b5f\u0b61\u0b66\u0b6f"
447 +"\u0b82\u0b83\u0b85\u0b8a\u0b8e\u0b90\u0b92\u0b95\u0b99\u0b9a\u0b9c\u0b9c\u0b9e\u0b9f"
448 +"\u0ba3\u0ba4\u0ba8\u0baa\u0bae\u0bb5\u0bb7\u0bb9\u0bbe\u0bc2\u0bc6\u0bc8\u0bca\u0bcd"
449 +"\u0bd7\u0bd7\u0be7\u0bef\u0c01\u0c03\u0c05\u0c0c\u0c0e\u0c10\u0c12\u0c28\u0c2a\u0c33"
450 +"\u0c35\u0c39\u0c3e\u0c44\u0c46\u0c48\u0c4a\u0c4d\u0c55\u0c56\u0c60\u0c61\u0c66\u0c6f"
451 +"\u0c82\u0c83\u0c85\u0c8c\u0c8e\u0c90\u0c92\u0ca8\u0caa\u0cb3\u0cb5\u0cb9\u0cbe\u0cc4"
452 +"\u0cc6\u0cc8\u0cca\u0ccd\u0cd5\u0cd6\u0cde\u0cde\u0ce0\u0ce1\u0ce6\u0cef\u0d02\u0d03"
453 +"\u0d05\u0d0c\u0d0e\u0d10\u0d12\u0d28\u0d2a\u0d39\u0d3e\u0d43\u0d46\u0d48\u0d4a\u0d4d"
454 +"\u0d57\u0d57\u0d60\u0d61\u0d66\u0d6f\u0e01\u0e2e\u0e30\u0e3a\u0e40\u0e4e\u0e50\u0e59"
455 +"\u0e81\u0e82\u0e84\u0e84\u0e87\u0e88\u0e8a\u0e8a\u0e8d\u0e8d\u0e94\u0e97\u0e99\u0e9f"
456 +"\u0ea1\u0ea3\u0ea5\u0ea5\u0ea7\u0ea7\u0eaa\u0eab\u0ead\u0eae\u0eb0\u0eb9\u0ebb\u0ebd"
457 +"\u0ec0\u0ec4\u0ec6\u0ec6\u0ec8\u0ecd\u0ed0\u0ed9\u0f18\u0f19\u0f20\u0f29\u0f35\u0f35"
458 +"\u0f37\u0f37\u0f39\u0f39\u0f3e\u0f47\u0f49\u0f69\u0f71\u0f84\u0f86\u0f8b\u0f90\u0f95"
459 +"\u0f97\u0f97\u0f99\u0fad\u0fb1\u0fb7\u0fb9\u0fb9\u10a0\u10c5\u10d0\u10f6\u1100\u1100"
460 +"\u1102\u1103\u1105\u1107\u1109\u1109\u110b\u110c\u110e\u1112\u113c\u113c\u113e\u113e"
461 +"\u1140\u1140\u114c\u114c\u114e\u114e\u1150\u1150\u1154\u1155\u1159\u1159\u115f\u1161"
462 +"\u1163\u1163\u1165\u1165\u1167\u1167\u1169\u1169\u116d\u116e\u1172\u1173\u1175\u1175"
463 +"\u119e\u119e\u11a8\u11a8\u11ab\u11ab\u11ae\u11af\u11b7\u11b8\u11ba\u11ba\u11bc\u11c2"
464 +"\u11eb\u11eb\u11f0\u11f0\u11f9\u11f9\u1e00\u1e9b\u1ea0\u1ef9\u1f00\u1f15\u1f18\u1f1d"
465 +"\u1f20\u1f45\u1f48\u1f4d\u1f50\u1f57\u1f59\u1f59\u1f5b\u1f5b\u1f5d\u1f5d\u1f5f\u1f7d"
466 +"\u1f80\u1fb4\u1fb6\u1fbc\u1fbe\u1fbe\u1fc2\u1fc4\u1fc6\u1fcc\u1fd0\u1fd3\u1fd6\u1fdb"
467 +"\u1fe0\u1fec\u1ff2\u1ff4\u1ff6\u1ffc\u20d0\u20dc\u20e1\u20e1\u2126\u2126\u212a\u212b"
468 +"\u212e\u212e\u2180\u2182\u3005\u3005\u3007\u3007\u3021\u302f\u3031\u3035\u3041\u3094"
469 +"\u3099\u309a\u309d\u309e\u30a1\u30fa\u30fc\u30fe\u3105\u312c\u4e00\u9fa5\uac00\ud7a3"
470 +"";
471 private static final String LETTERS =
472 "\u0041\u005a\u0061\u007a\u00c0\u00d6\u00d8\u00f6\u00f8\u0131\u0134\u013e\u0141\u0148"
473 +"\u014a\u017e\u0180\u01f0\u01f4\u01f5\u01fa\u0217\u0250\u02a8\u02bb\u02c1"
474 +"\u02b0\u02d1"
475 +"\u0386\u0386\u0388\u038a\u038c\u038c\u038e\u03a1\u03a3\u03ce\u03d0\u03d6\u03da\u03da"
476 +"\u03dc\u03dc\u03de\u03de\u03e0\u03e0\u03e2\u03f3\u0401\u040c\u040e\u044f\u0451\u045c"
477 +"\u045e\u0481\u0490\u04c4\u04c7\u04c8\u04cb\u04cc\u04d0\u04eb\u04ee\u04f5\u04f8\u04f9"
478 +"\u0531\u0556\u0559\u0559\u0561\u0586\u05d0\u05ea\u05f0\u05f2\u0621\u063a\u0641\u064a"
479 +"\u0671\u06b7\u06ba\u06be\u06c0\u06ce\u06d0\u06d3\u06d5\u06d5\u06e5\u06e6\u0905\u0939"
480 +"\u093d\u093d\u0958\u0961\u0985\u098c\u098f\u0990\u0993\u09a8\u09aa\u09b0\u09b2\u09b2"
481 +"\u09b6\u09b9\u09dc\u09dd\u09df\u09e1\u09f0\u09f1\u0a05\u0a0a\u0a0f\u0a10\u0a13\u0a28"
482 +"\u0a2a\u0a30\u0a32\u0a33\u0a35\u0a36\u0a38\u0a39\u0a59\u0a5c\u0a5e\u0a5e\u0a72\u0a74"
483 +"\u0a85\u0a8b\u0a8d\u0a8d\u0a8f\u0a91\u0a93\u0aa8\u0aaa\u0ab0\u0ab2\u0ab3\u0ab5\u0ab9"
484 +"\u0abd\u0abd\u0ae0\u0ae0\u0b05\u0b0c\u0b0f\u0b10\u0b13\u0b28\u0b2a\u0b30\u0b32\u0b33"
485 +"\u0b36\u0b39\u0b3d\u0b3d\u0b5c\u0b5d\u0b5f\u0b61\u0b85\u0b8a\u0b8e\u0b90\u0b92\u0b95"
486 +"\u0b99\u0b9a\u0b9c\u0b9c\u0b9e\u0b9f\u0ba3\u0ba4\u0ba8\u0baa\u0bae\u0bb5\u0bb7\u0bb9"
487 +"\u0c05\u0c0c\u0c0e\u0c10\u0c12\u0c28\u0c2a\u0c33\u0c35\u0c39\u0c60\u0c61\u0c85\u0c8c"
488 +"\u0c8e\u0c90\u0c92\u0ca8\u0caa\u0cb3\u0cb5\u0cb9\u0cde\u0cde\u0ce0\u0ce1\u0d05\u0d0c"
489 +"\u0d0e\u0d10\u0d12\u0d28\u0d2a\u0d39\u0d60\u0d61\u0e01\u0e2e\u0e30\u0e30\u0e32\u0e33"
490 +"\u0e40\u0e45\u0e81\u0e82\u0e84\u0e84\u0e87\u0e88\u0e8a\u0e8a\u0e8d\u0e8d\u0e94\u0e97"
491 +"\u0e99\u0e9f\u0ea1\u0ea3\u0ea5\u0ea5\u0ea7\u0ea7\u0eaa\u0eab\u0ead\u0eae\u0eb0\u0eb0"
492 +"\u0eb2\u0eb3\u0ebd\u0ebd\u0ec0\u0ec4\u0f40\u0f47\u0f49\u0f69\u10a0\u10c5\u10d0\u10f6"
493 +"\u1100\u1100\u1102\u1103\u1105\u1107\u1109\u1109\u110b\u110c\u110e\u1112\u113c\u113c"
494 +"\u113e\u113e\u1140\u1140\u114c\u114c\u114e\u114e\u1150\u1150\u1154\u1155\u1159\u1159"
495 +"\u115f\u1161\u1163\u1163\u1165\u1165\u1167\u1167\u1169\u1169\u116d\u116e\u1172\u1173"
496 +"\u1175\u1175\u119e\u119e\u11a8\u11a8\u11ab\u11ab\u11ae\u11af\u11b7\u11b8\u11ba\u11ba"
497 +"\u11bc\u11c2\u11eb\u11eb\u11f0\u11f0\u11f9\u11f9\u1e00\u1e9b\u1ea0\u1ef9\u1f00\u1f15"
498 +"\u1f18\u1f1d\u1f20\u1f45\u1f48\u1f4d\u1f50\u1f57\u1f59\u1f59\u1f5b\u1f5b\u1f5d\u1f5d"
499 +"\u1f5f\u1f7d\u1f80\u1fb4\u1fb6\u1fbc\u1fbe\u1fbe\u1fc2\u1fc4\u1fc6\u1fcc\u1fd0\u1fd3"
500 +"\u1fd6\u1fdb\u1fe0\u1fec\u1ff2\u1ff4\u1ff6\u1ffc\u2126\u2126\u212a\u212b\u212e\u212e"
501 +"\u2180\u2182\u3007\u3007\u3021\u3029\u3041\u3094\u30a1\u30fa\u3105\u312c\u4e00\u9fa5"
502 +"\uac00\ud7a3\uff66\uff9f";
503
504 private static final int[] LETTERS_INT = {0x1d790, 0x1d7a8, 0x1d7aa, 0x1d7c9, 0x2fa1b, 0x2fa1d};
505
506 private static final String DIGITS =
507 "\u0030\u0039\u0660\u0669\u06F0\u06F9\u0966\u096F\u09E6\u09EF\u0A66\u0A6F\u0AE6\u0AEF"
508 +"\u0B66\u0B6F\u0BE7\u0BEF\u0C66\u0C6F\u0CE6\u0CEF\u0D66\u0D6F\u0E50\u0E59\u0ED0\u0ED9"
509 +"\u0F20\u0F29\u1040\u1049\u1369\u1371\u17E0\u17E9\u1810\u1819\uFF10\uFF19";
510
511 private static final int[] DIGITS_INT = {0x1D7CE, 0x1D7FF};
512
513 }