parserforxmlschema.java

java1.6众多例子参考

/*
 * Copyright 1999-2005 The Apache Software Foundation.
 * 
 * Licensed under the Apache License, Version 2.0 (the "License");
 * you may not use this file except in compliance with the License.
 * You may obtain a copy of the License at
 * 
 *      http://www.apache.org/licenses/LICENSE-2.0
 * 
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */

package com.sun.org.apache.xerces.internal.impl.xpath.regex;

import java.util.Hashtable;
import java.util.Locale;

/**
 * A regular expression parser for the XML Schema.
 * 
 * @xerces.internal
 *
 * @author TAMURA Kent <[e-mail]>
 * @version $Id: ParserForXMLSchema.java,v 1.2.6.1 2005/09/06 11:46:32 neerajbj Exp $
 */
class ParserForXMLSchema extends RegexParser {

    public ParserForXMLSchema() {
        //this.setLocale(Locale.getDefault());
    }
    public ParserForXMLSchema(Locale locale) {
        //this.setLocale(locale);
    }

    Token processCaret() throws ParseException {
        this.next();
        return Token.createChar('^');
    }
    Token processDollar() throws ParseException {
        this.next();
        return Token.createChar('$');
     }
    Token processLookahead() throws ParseException {
        throw ex("parser.process.1", this.offset);
    }
    Token processNegativelookahead() throws ParseException {
        throw ex("parser.process.1", this.offset);
    }
    Token processLookbehind() throws ParseException {
        throw ex("parser.process.1", this.offset);
    }
    Token processNegativelookbehind() throws ParseException {
        throw ex("parser.process.1", this.offset);
    }
    Token processBacksolidus_A() throws ParseException {
        throw ex("parser.process.1", this.offset);
    }
    Token processBacksolidus_Z() throws ParseException {
        throw ex("parser.process.1", this.offset);
    }
    Token processBacksolidus_z() throws ParseException {
        throw ex("parser.process.1", this.offset);
    }
    Token processBacksolidus_b() throws ParseException {
        throw ex("parser.process.1", this.offset);
    }
    Token processBacksolidus_B() throws ParseException {
        throw ex("parser.process.1", this.offset);
    }
    Token processBacksolidus_lt() throws ParseException {
        throw ex("parser.process.1", this.offset);
    }
    Token processBacksolidus_gt() throws ParseException {
        throw ex("parser.process.1", this.offset);
    }
    Token processStar(Token tok) throws ParseException {
        this.next();
        return Token.createClosure(tok);
    }
    Token processPlus(Token tok) throws ParseException {
        // X+ -> XX*
        this.next();
        return Token.createConcat(tok, Token.createClosure(tok));
    }
    Token processQuestion(Token tok) throws ParseException {
        // X? -> X|
        this.next();
        Token par = Token.createUnion();
        par.addChild(tok);
        par.addChild(Token.createEmpty());
        return par;
    }
    boolean checkQuestion(int off) {
        return false;
    }
    Token processParen() throws ParseException {
        this.next();
        Token tok = Token.createParen(this.parseRegex(), 0);
        if (this.read() != T_RPAREN)  throw ex("parser.factor.1", this.offset-1);
        this.next();                            // Skips ')'
        return tok;
    }
    Token processParen2() throws ParseException {
        throw ex("parser.process.1", this.offset);
    }
    Token processCondition() throws ParseException {
        throw ex("parser.process.1", this.offset);
    }
    Token processModifiers() throws ParseException {
        throw ex("parser.process.1", this.offset);
    }
    Token processIndependent() throws ParseException {
        throw ex("parser.process.1", this.offset);
    }
    Token processBacksolidus_c() throws ParseException {
        this.next();
        return this.getTokenForShorthand('c');
    }
    Token processBacksolidus_C() throws ParseException {
        this.next();
        return this.getTokenForShorthand('C');
    }
    Token processBacksolidus_i() throws ParseException {
        this.next();
        return this.getTokenForShorthand('i');
    }
    Token processBacksolidus_I() throws ParseException {
        this.next();
        return this.getTokenForShorthand('I');
    }
    Token processBacksolidus_g() throws ParseException {
        throw this.ex("parser.process.1", this.offset-2);
    }
    Token processBacksolidus_X() throws ParseException {
        throw ex("parser.process.1", this.offset-2);
    }
    Token processBackreference() throws ParseException {
        throw ex("parser.process.1", this.offset-4);
    }

    int processCIinCharacterClass(RangeToken tok, int c) {
        tok.mergeRanges(this.getTokenForShorthand(c));
        return -1;
    }


    /**
     * Parses a character-class-expression, not a character-class-escape.
     *
     * c-c-expression   ::= '[' c-group ']'
     * c-group          ::= positive-c-group | negative-c-group | c-c-subtraction
     * positive-c-group ::= (c-range | c-c-escape)+
     * negative-c-group ::= '^' positive-c-group
     * c-c-subtraction  ::= (positive-c-group | negative-c-group) subtraction
     * subtraction      ::= '-' c-c-expression
     * c-range          ::= single-range | from-to-range
     * single-range     ::= multi-c-escape | category-c-escape | block-c-escape | <any XML char>
     * cc-normal-c      ::= <any character except [, ], \>
     * from-to-range    ::= cc-normal-c '-' cc-normal-c
     *
     * @param useNrage Ignored.
     * @return This returns no NrageToken.
     */
    protected RangeToken parseCharacterClass(boolean useNrange) throws ParseException {
        this.setContext(S_INBRACKETS);
        this.next();                            // '['
        boolean nrange = false;
        boolean wasDecoded = false;     		// used to detect if the last - was escaped.
        RangeToken base = null;
        RangeToken tok;
        if (this.read() == T_CHAR && this.chardata == '^') {
            nrange = true;
            this.next();                        // '^'
            base = Token.createRange();
            base.addRange(0, Token.UTF16_MAX);
            tok = Token.createRange();
        } else {
            tok = Token.createRange();
        }
        int type;
        boolean firstloop = true;
        while ((type = this.read()) != T_EOF) { // Don't use 'cotinue' for this loop.
        	
        	wasDecoded = false;
            // single-range | from-to-range | subtraction
            if (type == T_CHAR && this.chardata == ']' && !firstloop) {
                if (nrange) {
                    base.subtractRanges(tok);
                    tok = base;
                }
                break;
            }
            int c = this.chardata;
            boolean end = false;
            if (type == T_BACKSOLIDUS) {
                switch (c) {
                  case 'd':  case 'D':
                  case 'w':  case 'W':
                  case 's':  case 'S':
                    tok.mergeRanges(this.getTokenForShorthand(c));
                    end = true;
                    break;

                  case 'i':  case 'I':
                  case 'c':  case 'C':
                    c = this.processCIinCharacterClass(tok, c);
                    if (c < 0)  end = true;
                    break;
                    
                  case 'p':
                  case 'P':
                    int pstart = this.offset;
                    RangeToken tok2 = this.processBacksolidus_pP(c);
                    if (tok2 == null)  throw this.ex("parser.atom.5", pstart);
                    tok.mergeRanges(tok2);
                    end = true;
                    break;
                   
                 case '-':
                 	c = this.decodeEscaped();
                 	wasDecoded = true;
                 	break;

                  default:
                    c = this.decodeEscaped();
                } // \ + c
            } // backsolidus
            else if (type == T_XMLSCHEMA_CC_SUBTRACTION && !firstloop) {
                                                // Subraction
                if (nrange) {
                    base.subtractRanges(tok);
                    tok = base;
                }
                RangeToken range2 = this.parseCharacterClass(false);
                tok.subtractRanges(range2);
                if (this.read() != T_CHAR || this.chardata != ']')
                    throw this.ex("parser.cc.5", this.offset);
                break;                          // Exit this loop
            }