Save This Page
Home » xmlbeans-2.4.0-src » org.apache.xmlbeans.impl.regex » [javadoc | source]
    1   /*   Copyright 2004 The Apache Software Foundation
    2    *
    3    *   Licensed under the Apache License, Version 2.0 (the "License");
    4    *   you may not use this file except in compliance with the License.
    5    *   You may obtain a copy of the License at
    6    *
    7    *       http://www.apache.org/licenses/LICENSE-2.0
    8    *
    9    *   Unless required by applicable law or agreed to in writing, software
   10    *   distributed under the License is distributed on an "AS IS" BASIS,
   11    *   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
   12    *   See the License for the specific language governing permissions and
   13    *  limitations under the License.
   14    */
   15   
   16   package org.apache.xmlbeans.impl.regex;
   17   
   18   import java.util.Hashtable;
   19   import java.util.Locale;
   20   
   21   /**
   22    * A regular expression parser for the XML Shema.
   23    *
   24    * @author TAMURA Kent <kent@trl.ibm.co.jp>
   25    */
   26   class ParserForXMLSchema extends RegexParser {
   27   
   28       public ParserForXMLSchema() {
   29           //this.setLocale(Locale.getDefault());
   30       }
   31       public ParserForXMLSchema(Locale locale) {
   32           //this.setLocale(locale);
   33       }
   34   
   35       Token processCaret() throws ParseException {
   36           this.next();
   37           return Token.createChar('^');
   38       }
   39       Token processDollar() throws ParseException {
   40           this.next();
   41           return Token.createChar('$');
   42        }
   43       Token processLookahead() throws ParseException {
   44           throw ex("parser.process.1", this.offset);
   45       }
   46       Token processNegativelookahead() throws ParseException {
   47           throw ex("parser.process.1", this.offset);
   48       }
   49       Token processLookbehind() throws ParseException {
   50           throw ex("parser.process.1", this.offset);
   51       }
   52       Token processNegativelookbehind() throws ParseException {
   53           throw ex("parser.process.1", this.offset);
   54       }
   55       Token processBacksolidus_A() throws ParseException {
   56           throw ex("parser.process.1", this.offset);
   57       }
   58       Token processBacksolidus_Z() throws ParseException {
   59           throw ex("parser.process.1", this.offset);
   60       }
   61       Token processBacksolidus_z() throws ParseException {
   62           throw ex("parser.process.1", this.offset);
   63       }
   64       Token processBacksolidus_b() throws ParseException {
   65           throw ex("parser.process.1", this.offset);
   66       }
   67       Token processBacksolidus_B() throws ParseException {
   68           throw ex("parser.process.1", this.offset);
   69       }
   70       Token processBacksolidus_lt() throws ParseException {
   71           throw ex("parser.process.1", this.offset);
   72       }
   73       Token processBacksolidus_gt() throws ParseException {
   74           throw ex("parser.process.1", this.offset);
   75       }
   76       Token processStar(Token tok) throws ParseException {
   77           this.next();
   78           return Token.createClosure(tok);
   79       }
   80       Token processPlus(Token tok) throws ParseException {
   81           // X+ -> XX*
   82           this.next();
   83           return Token.createConcat(tok, Token.createClosure(tok));
   84       }
   85       Token processQuestion(Token tok) throws ParseException {
   86           // X? -> X|
   87           this.next();
   88           Token par = Token.createUnion();
   89           par.addChild(tok);
   90           par.addChild(Token.createEmpty());
   91           return par;
   92       }
   93       boolean checkQuestion(int off) {
   94           return false;
   95       }
   96       Token processParen() throws ParseException {
   97           this.next();
   98           Token tok = Token.createParen(this.parseRegex(), 0);
   99           if (this.read() != super.T_RPAREN)  throw ex("parser.factor.1", this.offset-1);
  100           this.next();                            // Skips ')'
  101           return tok;
  102       }
  103       Token processParen2() throws ParseException {
  104           throw ex("parser.process.1", this.offset);
  105       }
  106       Token processCondition() throws ParseException {
  107           throw ex("parser.process.1", this.offset);
  108       }
  109       Token processModifiers() throws ParseException {
  110           throw ex("parser.process.1", this.offset);
  111       }
  112       Token processIndependent() throws ParseException {
  113           throw ex("parser.process.1", this.offset);
  114       }
  115       Token processBacksolidus_c() throws ParseException {
  116           this.next();
  117           return this.getTokenForShorthand('c');
  118       }
  119       Token processBacksolidus_C() throws ParseException {
  120           this.next();
  121           return this.getTokenForShorthand('C');
  122       }
  123       Token processBacksolidus_i() throws ParseException {
  124           this.next();
  125           return this.getTokenForShorthand('i');
  126       }
  127       Token processBacksolidus_I() throws ParseException {
  128           this.next();
  129           return this.getTokenForShorthand('I');
  130       }
  131       Token processBacksolidus_g() throws ParseException {
  132           throw this.ex("parser.process.1", this.offset-2);
  133       }
  134       Token processBacksolidus_X() throws ParseException {
  135           throw ex("parser.process.1", this.offset-2);
  136       }
  137       Token processBackreference() throws ParseException {
  138           throw ex("parser.process.1", this.offset-4);
  139       }
  140   
  141       int processCIinCharacterClass(RangeToken tok, int c) {
  142           tok.mergeRanges(this.getTokenForShorthand(c));
  143           return -1;
  144       }
  145   
  146   
  147       /**
  148        * Parses a character-class-expression, not a character-class-escape.
  149        *
  150        * c-c-expression   ::= '[' c-group ']'
  151        * c-group          ::= positive-c-group | negative-c-group | c-c-subtraction
  152        * positive-c-group ::= (c-range | c-c-escape)+
  153        * negative-c-group ::= '^' positive-c-group
  154        * c-c-subtraction  ::= (positive-c-group | negative-c-group) subtraction
  155        * subtraction      ::= '-' c-c-expression
  156        * c-range          ::= single-range | from-to-range
  157        * single-range     ::= multi-c-escape | category-c-escape | block-c-escape | <any XML char>
  158        * cc-normal-c      ::= <any character except [, ], \>
  159        * from-to-range    ::= cc-normal-c '-' cc-normal-c
  160        *
  161        * @param useNrage Ignored.
  162        * @return This returns no NrageToken.
  163        */
  164       protected RangeToken parseCharacterClass(boolean useNrange) throws ParseException {
  165           this.setContext(S_INBRACKETS);
  166           this.next();                            // '['
  167           boolean nrange = false;
  168           RangeToken base = null;
  169           RangeToken tok;
  170           if (this.read() == T_CHAR && this.chardata == '^') {
  171               nrange = true;
  172               this.next();                        // '^'
  173               base = Token.createRange();
  174               base.addRange(0, Token.UTF16_MAX);
  175               tok = Token.createRange();
  176           } else {
  177               tok = Token.createRange();
  178           }
  179           int type;
  180           boolean firstloop = true;
  181           while ((type = this.read()) != T_EOF) { // Don't use 'cotinue' for this loop.
  182               // single-range | from-to-range | subtraction
  183               if (type == T_CHAR && this.chardata == ']' && !firstloop) {
  184                   if (nrange) {
  185                       base.subtractRanges(tok);
  186                       tok = base;
  187                   }
  188                   break;
  189               }
  190               int c = this.chardata;
  191               boolean end = false;
  192               if (type == T_BACKSOLIDUS) {
  193                   switch (c) {
  194                     case 'd':  case 'D':
  195                     case 'w':  case 'W':
  196                     case 's':  case 'S':
  197                       tok.mergeRanges(this.getTokenForShorthand(c));
  198                       end = true;
  199                       break;
  200   
  201                     case 'i':  case 'I':
  202                     case 'c':  case 'C':
  203                       c = this.processCIinCharacterClass(tok, c);
  204                       if (c < 0)  end = true;
  205                       break;
  206                       
  207                     case 'p':
  208                     case 'P':
  209                       int pstart = this.offset;
  210                       RangeToken tok2 = this.processBacksolidus_pP(c);
  211                       if (tok2 == null)  throw this.ex("parser.atom.5", pstart);
  212                       tok.mergeRanges(tok2);
  213                       end = true;
  214                       break;
  215   
  216                     default:
  217                       c = this.decodeEscaped();
  218                   } // \ + c
  219               } // backsolidus
  220               else if (type == T_XMLSCHEMA_CC_SUBTRACTION && !firstloop) {
  221                                                   // Subraction
  222                   if (nrange) {
  223                       base.subtractRanges(tok);
  224                       tok = base;
  225                   }
  226                   RangeToken range2 = this.parseCharacterClass(false);
  227                   tok.subtractRanges(range2);
  228                   if (this.read() != T_CHAR || this.chardata != ']')
  229                       throw this.ex("parser.cc.5", this.offset);
  230                   break;                          // Exit this loop
  231               }
  232               this.next();
  233               if (!end) {                         // if not shorthands...
  234                   if (type == T_CHAR) {
  235                       if (c == '[')  throw this.ex("parser.cc.6", this.offset-2);
  236                       if (c == ']')  throw this.ex("parser.cc.7", this.offset-2);
  237                       // (radup) XMLSchema 1.0 allows the '-' as the first character of a range,
  238                       // but it looks like XMLSchema 1.1 will prohibit it - track this
  239                       if (c == '-' && !firstloop)  throw this.ex("parser.cc.8", this.offset-2);
  240                   }
  241                   if (this.read() != T_CHAR || this.chardata != '-') { // Here is no '-'.
  242                       tok.addRange(c, c);
  243                   } else {                        // Found '-'
  244                                                   // Is this '-' is a from-to token??
  245                       this.next(); // Skips '-'
  246                       if ((type = this.read()) == T_EOF)  throw this.ex("parser.cc.2", this.offset);
  247                                                   // c '-' ']' -> '-' is a single-range.
  248                       if ((type == T_CHAR && this.chardata == ']')
  249                           || type == T_XMLSCHEMA_CC_SUBTRACTION) {
  250                           throw this.ex("parser.cc.8", this.offset-1);
  251                       } else {
  252                           int rangeend = this.chardata;
  253                           if (type == T_CHAR) {
  254                               if (rangeend == '[')  throw this.ex("parser.cc.6", this.offset-1);
  255                               if (rangeend == ']')  throw this.ex("parser.cc.7", this.offset-1);
  256                               if (rangeend == '-')  throw this.ex("parser.cc.8", this.offset-2);
  257                           }
  258                           else if (type == T_BACKSOLIDUS)
  259                               rangeend = this.decodeEscaped();
  260                           this.next();
  261   
  262                           if (c > rangeend)  throw this.ex("parser.ope.3", this.offset-1);
  263                           tok.addRange(c, rangeend);
  264                       }
  265                   }
  266               }
  267               firstloop = false;
  268           }
  269           if (this.read() == T_EOF)
  270               throw this.ex("parser.cc.2", this.offset);
  271           tok.sortRanges();
  272           tok.compactRanges();
  273           //tok.dumpRanges();
  274           this.setContext(S_NORMAL);
  275           this.next();                    // Skips ']'
  276   
  277           return tok;
  278       }
  279   
  280       protected RangeToken parseSetOperations() throws ParseException {
  281           throw this.ex("parser.process.1", this.offset);
  282       }
  283    
  284       Token getTokenForShorthand(int ch) {
  285           switch (ch) {
  286             case 'd':
  287               return ParserForXMLSchema.getRange("xml:isDigit", true);
  288             case 'D':
  289               return ParserForXMLSchema.getRange("xml:isDigit", false);
  290             case 'w':
  291               return ParserForXMLSchema.getRange("xml:isWord", true);
  292             case 'W':
  293               return ParserForXMLSchema.getRange("xml:isWord", false);
  294             case 's':
  295               return ParserForXMLSchema.getRange("xml:isSpace", true);
  296             case 'S':
  297               return ParserForXMLSchema.getRange("xml:isSpace", false);
  298             case 'c':
  299               return ParserForXMLSchema.getRange("xml:isNameChar", true);
  300             case 'C':
  301               return ParserForXMLSchema.getRange("xml:isNameChar", false);
  302             case 'i':
  303               return ParserForXMLSchema.getRange("xml:isInitialNameChar", true);
  304             case 'I':
  305               return ParserForXMLSchema.getRange("xml:isInitialNameChar", false);
  306             default:
  307               throw new RuntimeException("Internal Error: shorthands: \\u"+Integer.toString(ch, 16));
  308           }
  309       }
  310       int decodeEscaped() throws ParseException {
  311           if (this.read() != T_BACKSOLIDUS)  throw ex("parser.next.1", this.offset-1);
  312           int c = this.chardata;
  313           switch (c) {
  314             case 'n':  c = '\n';  break; // LINE FEED U+000A
  315             case 'r':  c = '\r';  break; // CRRIAGE RETURN U+000D
  316             case 't':  c = '\t';  break; // HORIZONTAL TABULATION U+0009
  317             case '\\':
  318             case '|':
  319             case '.':
  320             case '^':
  321             case '-':
  322             case '?':
  323             case '*':
  324             case '+':
  325             case '{':
  326             case '}':
  327             case '(':
  328             case ')':
  329             case '[':
  330             case ']':
  331               break; // return actucal char
  332             default:
  333               throw ex("parser.process.1", this.offset-2);
  334           }
  335           return c;
  336       }
  337   
  338       static private Hashtable ranges = null;
  339       static private Hashtable ranges2 = null;
  340       static synchronized protected RangeToken getRange(String name, boolean positive) {
  341           if (ranges == null) {
  342               ranges = new Hashtable();
  343               ranges2 = new Hashtable();
  344   
  345               Token tok = Token.createRange();
  346               setupRange(tok, SPACES);
  347               ranges.put("xml:isSpace", tok);
  348               ranges2.put("xml:isSpace", Token.complementRanges(tok));
  349   
  350               tok = Token.createRange();
  351               setupRange(tok, DIGITS);
  352               ranges.put("xml:isDigit", tok);
  353               ranges2.put("xml:isDigit", Token.complementRanges(tok));
  354   
  355               tok = Token.createRange();
  356               setupRange(tok, DIGITS);
  357               ranges.put("xml:isDigit", tok);
  358               ranges2.put("xml:isDigit", Token.complementRanges(tok));
  359   
  360               tok = Token.createRange();
  361               setupRange(tok, LETTERS);
  362               tok.mergeRanges((Token)ranges.get("xml:isDigit"));
  363               ranges.put("xml:isWord", tok);
  364               ranges2.put("xml:isWord", Token.complementRanges(tok));
  365   
  366               tok = Token.createRange();
  367               setupRange(tok, NAMECHARS);
  368               ranges.put("xml:isNameChar", tok);
  369               ranges2.put("xml:isNameChar", Token.complementRanges(tok));
  370   
  371               tok = Token.createRange();
  372               setupRange(tok, LETTERS);
  373               tok.addRange('_', '_');
  374               tok.addRange(':', ':');
  375               ranges.put("xml:isInitialNameChar", tok);
  376               ranges2.put("xml:isInitialNameChar", Token.complementRanges(tok));
  377           }
  378           RangeToken tok = positive ? (RangeToken)ranges.get(name)
  379               : (RangeToken)ranges2.get(name);
  380           return tok;
  381       }
  382   
  383       static void setupRange(Token range, String src) {
  384           int len = src.length();
  385           for (int i = 0;  i < len;  i += 2)
  386               range.addRange(src.charAt(i), src.charAt(i+1));
  387       }
  388   
  389       private static final String SPACES = "\t\n\r\r  ";
  390       private static final String NAMECHARS =
  391           "\u002d\u002e\u0030\u003a\u0041\u005a\u005f\u005f\u0061\u007a\u00b7\u00b7\u00c0\u00d6"
  392           +"\u00d8\u00f6\u00f8\u0131\u0134\u013e\u0141\u0148\u014a\u017e\u0180\u01c3\u01cd\u01f0"
  393           +"\u01f4\u01f5\u01fa\u0217\u0250\u02a8\u02bb\u02c1\u02d0\u02d1\u0300\u0345\u0360\u0361"
  394           +"\u0386\u038a\u038c\u038c\u038e\u03a1\u03a3\u03ce\u03d0\u03d6\u03da\u03da\u03dc\u03dc"
  395           +"\u03de\u03de\u03e0\u03e0\u03e2\u03f3\u0401\u040c\u040e\u044f\u0451\u045c\u045e\u0481"
  396           +"\u0483\u0486\u0490\u04c4\u04c7\u04c8\u04cb\u04cc\u04d0\u04eb\u04ee\u04f5\u04f8\u04f9"
  397           +"\u0531\u0556\u0559\u0559\u0561\u0586\u0591\u05a1\u05a3\u05b9\u05bb\u05bd\u05bf\u05bf"
  398           +"\u05c1\u05c2\u05c4\u05c4\u05d0\u05ea\u05f0\u05f2\u0621\u063a\u0640\u0652\u0660\u0669"
  399           +"\u0670\u06b7\u06ba\u06be\u06c0\u06ce\u06d0\u06d3\u06d5\u06e8\u06ea\u06ed\u06f0\u06f9"
  400           +"\u0901\u0903\u0905\u0939\u093c\u094d\u0951\u0954\u0958\u0963\u0966\u096f\u0981\u0983"
  401           +"\u0985\u098c\u098f\u0990\u0993\u09a8\u09aa\u09b0\u09b2\u09b2\u09b6\u09b9\u09bc\u09bc"
  402           +"\u09be\u09c4\u09c7\u09c8\u09cb\u09cd\u09d7\u09d7\u09dc\u09dd\u09df\u09e3\u09e6\u09f1"
  403           +"\u0a02\u0a02\u0a05\u0a0a\u0a0f\u0a10\u0a13\u0a28\u0a2a\u0a30\u0a32\u0a33\u0a35\u0a36"
  404           +"\u0a38\u0a39\u0a3c\u0a3c\u0a3e\u0a42\u0a47\u0a48\u0a4b\u0a4d\u0a59\u0a5c\u0a5e\u0a5e"
  405           +"\u0a66\u0a74\u0a81\u0a83\u0a85\u0a8b\u0a8d\u0a8d\u0a8f\u0a91\u0a93\u0aa8\u0aaa\u0ab0"
  406           +"\u0ab2\u0ab3\u0ab5\u0ab9\u0abc\u0ac5\u0ac7\u0ac9\u0acb\u0acd\u0ae0\u0ae0\u0ae6\u0aef"
  407           +"\u0b01\u0b03\u0b05\u0b0c\u0b0f\u0b10\u0b13\u0b28\u0b2a\u0b30\u0b32\u0b33\u0b36\u0b39"
  408           +"\u0b3c\u0b43\u0b47\u0b48\u0b4b\u0b4d\u0b56\u0b57\u0b5c\u0b5d\u0b5f\u0b61\u0b66\u0b6f"
  409           +"\u0b82\u0b83\u0b85\u0b8a\u0b8e\u0b90\u0b92\u0b95\u0b99\u0b9a\u0b9c\u0b9c\u0b9e\u0b9f"
  410           +"\u0ba3\u0ba4\u0ba8\u0baa\u0bae\u0bb5\u0bb7\u0bb9\u0bbe\u0bc2\u0bc6\u0bc8\u0bca\u0bcd"
  411           +"\u0bd7\u0bd7\u0be7\u0bef\u0c01\u0c03\u0c05\u0c0c\u0c0e\u0c10\u0c12\u0c28\u0c2a\u0c33"
  412           +"\u0c35\u0c39\u0c3e\u0c44\u0c46\u0c48\u0c4a\u0c4d\u0c55\u0c56\u0c60\u0c61\u0c66\u0c6f"
  413           +"\u0c82\u0c83\u0c85\u0c8c\u0c8e\u0c90\u0c92\u0ca8\u0caa\u0cb3\u0cb5\u0cb9\u0cbe\u0cc4"
  414           +"\u0cc6\u0cc8\u0cca\u0ccd\u0cd5\u0cd6\u0cde\u0cde\u0ce0\u0ce1\u0ce6\u0cef\u0d02\u0d03"
  415           +"\u0d05\u0d0c\u0d0e\u0d10\u0d12\u0d28\u0d2a\u0d39\u0d3e\u0d43\u0d46\u0d48\u0d4a\u0d4d"
  416           +"\u0d57\u0d57\u0d60\u0d61\u0d66\u0d6f\u0e01\u0e2e\u0e30\u0e3a\u0e40\u0e4e\u0e50\u0e59"
  417           +"\u0e81\u0e82\u0e84\u0e84\u0e87\u0e88\u0e8a\u0e8a\u0e8d\u0e8d\u0e94\u0e97\u0e99\u0e9f"
  418           +"\u0ea1\u0ea3\u0ea5\u0ea5\u0ea7\u0ea7\u0eaa\u0eab\u0ead\u0eae\u0eb0\u0eb9\u0ebb\u0ebd"
  419           +"\u0ec0\u0ec4\u0ec6\u0ec6\u0ec8\u0ecd\u0ed0\u0ed9\u0f18\u0f19\u0f20\u0f29\u0f35\u0f35"
  420           +"\u0f37\u0f37\u0f39\u0f39\u0f3e\u0f47\u0f49\u0f69\u0f71\u0f84\u0f86\u0f8b\u0f90\u0f95"
  421           +"\u0f97\u0f97\u0f99\u0fad\u0fb1\u0fb7\u0fb9\u0fb9\u10a0\u10c5\u10d0\u10f6\u1100\u1100"
  422           +"\u1102\u1103\u1105\u1107\u1109\u1109\u110b\u110c\u110e\u1112\u113c\u113c\u113e\u113e"
  423           +"\u1140\u1140\u114c\u114c\u114e\u114e\u1150\u1150\u1154\u1155\u1159\u1159\u115f\u1161"
  424           +"\u1163\u1163\u1165\u1165\u1167\u1167\u1169\u1169\u116d\u116e\u1172\u1173\u1175\u1175"
  425           +"\u119e\u119e\u11a8\u11a8\u11ab\u11ab\u11ae\u11af\u11b7\u11b8\u11ba\u11ba\u11bc\u11c2"
  426           +"\u11eb\u11eb\u11f0\u11f0\u11f9\u11f9\u1e00\u1e9b\u1ea0\u1ef9\u1f00\u1f15\u1f18\u1f1d"
  427           +"\u1f20\u1f45\u1f48\u1f4d\u1f50\u1f57\u1f59\u1f59\u1f5b\u1f5b\u1f5d\u1f5d\u1f5f\u1f7d"
  428           +"\u1f80\u1fb4\u1fb6\u1fbc\u1fbe\u1fbe\u1fc2\u1fc4\u1fc6\u1fcc\u1fd0\u1fd3\u1fd6\u1fdb"
  429           +"\u1fe0\u1fec\u1ff2\u1ff4\u1ff6\u1ffc\u20d0\u20dc\u20e1\u20e1\u2126\u2126\u212a\u212b"
  430           +"\u212e\u212e\u2180\u2182\u3005\u3005\u3007\u3007\u3021\u302f\u3031\u3035\u3041\u3094"
  431           +"\u3099\u309a\u309d\u309e\u30a1\u30fa\u30fc\u30fe\u3105\u312c\u4e00\u9fa5\uac00\ud7a3"
  432           +"";
  433       private static final String LETTERS =
  434           "\u0041\u005a\u0061\u007a\u00c0\u00d6\u00d8\u00f6\u00f8\u0131\u0134\u013e\u0141\u0148"
  435           +"\u014a\u017e\u0180\u01c3\u01cd\u01f0\u01f4\u01f5\u01fa\u0217\u0250\u02a8\u02bb\u02c1"
  436           +"\u0386\u0386\u0388\u038a\u038c\u038c\u038e\u03a1\u03a3\u03ce\u03d0\u03d6\u03da\u03da"
  437           +"\u03dc\u03dc\u03de\u03de\u03e0\u03e0\u03e2\u03f3\u0401\u040c\u040e\u044f\u0451\u045c"
  438           +"\u045e\u0481\u0490\u04c4\u04c7\u04c8\u04cb\u04cc\u04d0\u04eb\u04ee\u04f5\u04f8\u04f9"
  439           +"\u0531\u0556\u0559\u0559\u0561\u0586\u05d0\u05ea\u05f0\u05f2\u0621\u063a\u0641\u064a"
  440           +"\u0671\u06b7\u06ba\u06be\u06c0\u06ce\u06d0\u06d3\u06d5\u06d5\u06e5\u06e6\u0905\u0939"
  441           +"\u093d\u093d\u0958\u0961\u0985\u098c\u098f\u0990\u0993\u09a8\u09aa\u09b0\u09b2\u09b2"
  442           +"\u09b6\u09b9\u09dc\u09dd\u09df\u09e1\u09f0\u09f1\u0a05\u0a0a\u0a0f\u0a10\u0a13\u0a28"
  443           +"\u0a2a\u0a30\u0a32\u0a33\u0a35\u0a36\u0a38\u0a39\u0a59\u0a5c\u0a5e\u0a5e\u0a72\u0a74"
  444           +"\u0a85\u0a8b\u0a8d\u0a8d\u0a8f\u0a91\u0a93\u0aa8\u0aaa\u0ab0\u0ab2\u0ab3\u0ab5\u0ab9"
  445           +"\u0abd\u0abd\u0ae0\u0ae0\u0b05\u0b0c\u0b0f\u0b10\u0b13\u0b28\u0b2a\u0b30\u0b32\u0b33"
  446           +"\u0b36\u0b39\u0b3d\u0b3d\u0b5c\u0b5d\u0b5f\u0b61\u0b85\u0b8a\u0b8e\u0b90\u0b92\u0b95"
  447           +"\u0b99\u0b9a\u0b9c\u0b9c\u0b9e\u0b9f\u0ba3\u0ba4\u0ba8\u0baa\u0bae\u0bb5\u0bb7\u0bb9"
  448           +"\u0c05\u0c0c\u0c0e\u0c10\u0c12\u0c28\u0c2a\u0c33\u0c35\u0c39\u0c60\u0c61\u0c85\u0c8c"
  449           +"\u0c8e\u0c90\u0c92\u0ca8\u0caa\u0cb3\u0cb5\u0cb9\u0cde\u0cde\u0ce0\u0ce1\u0d05\u0d0c"
  450           +"\u0d0e\u0d10\u0d12\u0d28\u0d2a\u0d39\u0d60\u0d61\u0e01\u0e2e\u0e30\u0e30\u0e32\u0e33"
  451           +"\u0e40\u0e45\u0e81\u0e82\u0e84\u0e84\u0e87\u0e88\u0e8a\u0e8a\u0e8d\u0e8d\u0e94\u0e97"
  452           +"\u0e99\u0e9f\u0ea1\u0ea3\u0ea5\u0ea5\u0ea7\u0ea7\u0eaa\u0eab\u0ead\u0eae\u0eb0\u0eb0"
  453           +"\u0eb2\u0eb3\u0ebd\u0ebd\u0ec0\u0ec4\u0f40\u0f47\u0f49\u0f69\u10a0\u10c5\u10d0\u10f6"
  454           +"\u1100\u1100\u1102\u1103\u1105\u1107\u1109\u1109\u110b\u110c\u110e\u1112\u113c\u113c"
  455           +"\u113e\u113e\u1140\u1140\u114c\u114c\u114e\u114e\u1150\u1150\u1154\u1155\u1159\u1159"
  456           +"\u115f\u1161\u1163\u1163\u1165\u1165\u1167\u1167\u1169\u1169\u116d\u116e\u1172\u1173"
  457           +"\u1175\u1175\u119e\u119e\u11a8\u11a8\u11ab\u11ab\u11ae\u11af\u11b7\u11b8\u11ba\u11ba"
  458           +"\u11bc\u11c2\u11eb\u11eb\u11f0\u11f0\u11f9\u11f9\u1e00\u1e9b\u1ea0\u1ef9\u1f00\u1f15"
  459           +"\u1f18\u1f1d\u1f20\u1f45\u1f48\u1f4d\u1f50\u1f57\u1f59\u1f59\u1f5b\u1f5b\u1f5d\u1f5d"
  460           +"\u1f5f\u1f7d\u1f80\u1fb4\u1fb6\u1fbc\u1fbe\u1fbe\u1fc2\u1fc4\u1fc6\u1fcc\u1fd0\u1fd3"
  461           +"\u1fd6\u1fdb\u1fe0\u1fec\u1ff2\u1ff4\u1ff6\u1ffc\u2126\u2126\u212a\u212b\u212e\u212e"
  462           +"\u2180\u2182\u3007\u3007\u3021\u3029\u3041\u3094\u30a1\u30fa\u3105\u312c\u4e00\u9fa5"
  463           +"\uac00\ud7a3";
  464       private static final String DIGITS =
  465           "\u0030\u0039\u0660\u0669\u06F0\u06F9\u0966\u096F\u09E6\u09EF\u0A66\u0A6F\u0AE6\u0AEF"
  466           +"\u0B66\u0B6F\u0BE7\u0BEF\u0C66\u0C6F\u0CE6\u0CEF\u0D66\u0D6F\u0E50\u0E59\u0ED0\u0ED9"
  467           +"\u0F20\u0F29";
  468   }

Save This Page
Home » xmlbeans-2.4.0-src » org.apache.xmlbeans.impl.regex » [javadoc | source]