parserforxmlschema.java

来自「JAVA的一些源码 JAVA2 STANDARD EDITION DEVELO」· Java 代码 · 共 510 行 · 第 1/2 页

/*
 * The Apache Software License, Version 1.1
 *
 *
 * Copyright (c) 1999-2003 The Apache Software Foundation.  All rights 
 * reserved.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions
 * are met:
 *
 * 1. Redistributions of source code must retain the above copyright
 *    notice, this list of conditions and the following disclaimer. 
 *
 * 2. Redistributions in binary form must reproduce the above copyright
 *    notice, this list of conditions and the following disclaimer in
 *    the documentation and/or other materials provided with the
 *    distribution.
 *
 * 3. The end-user documentation included with the redistribution,
 *    if any, must include the following acknowledgment:  
 *       "This product includes software developed by the
 *        Apache Software Foundation (http://www.apache.org/)."
 *    Alternately, this acknowledgment may appear in the software itself,
 *    if and wherever such third-party acknowledgments normally appear.
 *
 * 4. The names "Xerces" and "Apache Software Foundation" must
 *    not be used to endorse or promote products derived from this
 *    software without prior written permission. For written 
 *    permission, please contact [e-mail].
 *
 * 5. Products derived from this software may not be called "Apache",
 *    nor may "Apache" appear in their name, without prior written
 *    permission of the Apache Software Foundation.
 *
 * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESSED OR IMPLIED
 * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
 * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
 * DISCLAIMED.  IN NO EVENT SHALL THE APACHE SOFTWARE FOUNDATION OR
 * ITS CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
 * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
 * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF
 * USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
 * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
 * OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT
 * OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
 * SUCH DAMAGE.
 * ====================================================================
 *
 * This software consists of voluntary contributions made by many
 * individuals on behalf of the Apache Software Foundation and was
 * originally based on software copyright (c) 1999, International
 * Business Machines, Inc., http://www.apache.org.  For more
 * information on the Apache Software Foundation, please see
 * <http://www.apache.org/>.
 */

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 Shema.
 *
 * @author TAMURA Kent &lt;[e-mail]&gt;
 * @version $Id: ParserForXMLSchema.java,v 1.5 2003/03/24 23:37:55 sandygao 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() != super.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;
        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.
            // 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);