xmlscanner.java

来自「JAVA的一些源码 JAVA2 STANDARD EDITION DEVELO」· Java 代码 · 共 1,453 行 · 第 1/4 页

            reportFatalError("QuoteRequiredInPublicID", null);
            return false;
        }

        fStringBuffer.clear();
        // skip leading whitespace
        boolean skipSpace = true;
        boolean dataok = true;
        while (true) {
            int c = fEntityScanner.scanChar();
            if (c == ' ' || c == '\n' || c == '\r') {
                if (!skipSpace) {
                    // take the first whitespace as a space and skip the others
                    fStringBuffer.append(' ');
                    skipSpace = true;
                }
            }
            else if (c == quote) {
                if (skipSpace) {
                    // if we finished on a space let's trim it
                    fStringBuffer.length--;
                }
                literal.setValues(fStringBuffer);
                break;
            }
            else if (XMLChar.isPubid(c)) {
                fStringBuffer.append((char)c);
                skipSpace = false;
            }
            else if (c == -1) {
                reportFatalError("PublicIDUnterminated", null);
                return false;
            }
            else {
                dataok = false;
                reportFatalError("InvalidCharInPublicID",
                                 new Object[]{Integer.toHexString(c)});
            }
        }
        return dataok;
   }


    /**
     * Normalize whitespace in an XMLString converting all whitespace
     * characters to space characters.
     */
    protected void normalizeWhitespace(XMLString value) {
        int end = value.offset + value.length;
        for (int i = value.offset; i < end; i++) {
            int c = value.ch[i];
            // Performance: For XML 1.0 documents take advantage of 
            // the fact that the only legal characters below 0x20 
            // are 0x09 (TAB), 0x0A (LF) and 0x0D (CR). Since we've 
            // already determined the well-formedness of these
            // characters it is sufficient (and safe) to check
            // against 0x20. -- mrglavas
            if (c < 0x20) {
                value.ch[i] = ' ';
            }
        }
    }

    //
    // XMLEntityHandler methods
    //

    /**
     * This method notifies of the start of an entity. The document entity
     * has the pseudo-name of "[xml]" the DTD has the pseudo-name of "[dtd]" 
     * parameter entity names start with '%'; and general entities are just
     * specified by their name.
     * 
     * @param name     The name of the entity.
     * @param identifier The resource identifier.
     * @param encoding The auto-detected IANA encoding name of the entity
     *                 stream. This value will be null in those situations
     *                 where the entity encoding is not auto-detected (e.g.
     *                 internal entities or a document entity that is
     *                 parsed from a java.io.Reader).
     * @param augs     Additional information that may include infoset augmentations
     *
     * @throws XNIException Thrown by handler to signal an error.
     */
    public void startEntity(String name, 
                            XMLResourceIdentifier identifier,
                            String encoding, Augmentations augs) throws XNIException {

        // keep track of the entity depth
        fEntityDepth++;
        // must reset entity scanner
        fEntityScanner = fEntityManager.getEntityScanner();

    } // startEntity(String,XMLResourceIdentifier,String)

    /**
     * This method notifies the end of an entity. The document entity has
     * the pseudo-name of "[xml]" the DTD has the pseudo-name of "[dtd]" 
     * parameter entity names start with '%'; and general entities are just
     * specified by their name.
     * 
     * @param name The name of the entity.
     * @param augs Additional information that may include infoset augmentations
     *
     * @throws XNIException Thrown by handler to signal an error.
     */
    public void endEntity(String name, Augmentations augs) throws XNIException {

        // keep track of the entity depth
        fEntityDepth--;

    } // endEntity(String)

    /**
     * Scans a character reference and append the corresponding chars to the
     * specified buffer.
     *
     * <p>
     * <pre>
     * [66] CharRef ::= '&#' [0-9]+ ';' | '&#x' [0-9a-fA-F]+ ';'
     * </pre>
     *
     * <strong>Note:</strong> This method uses fStringBuffer, anything in it
     * at the time of calling is lost.
     *
     * @param buf the character buffer to append chars to
     * @param buf2 the character buffer to append non-normalized chars to
     *
     * @return the character value or (-1) on conversion failure
     */
    protected int scanCharReferenceValue(XMLStringBuffer buf, XMLStringBuffer buf2) 
        throws IOException, XNIException {

        // scan hexadecimal value
        boolean hex = false;
        if (fEntityScanner.skipChar('x')) {
            if (buf2 != null) { buf2.append('x'); }
            hex = true;
            fStringBuffer3.clear();
            boolean digit = true;
            
            int c = fEntityScanner.peekChar();
            digit = (c >= '0' && c <= '9') ||
                    (c >= 'a' && c <= 'f') ||
                    (c >= 'A' && c <= 'F');
            if (digit) {
                if (buf2 != null) { buf2.append((char)c); }
                fEntityScanner.scanChar();
                fStringBuffer3.append((char)c);
                
                do {
                    c = fEntityScanner.peekChar();
                    digit = (c >= '0' && c <= '9') ||
                            (c >= 'a' && c <= 'f') ||
                            (c >= 'A' && c <= 'F');
                    if (digit) {
                        if (buf2 != null) { buf2.append((char)c); }
                        fEntityScanner.scanChar();
                        fStringBuffer3.append((char)c);
                    }
                } while (digit);
            }
            else {
                reportFatalError("HexdigitRequiredInCharRef", null);
            }
        }

        // scan decimal value
        else {
            fStringBuffer3.clear();
            boolean digit = true;
            
            int c = fEntityScanner.peekChar();
            digit = c >= '0' && c <= '9';
            if (digit) {
                if (buf2 != null) { buf2.append((char)c); }
                fEntityScanner.scanChar();
                fStringBuffer3.append((char)c);
                
                do {
                    c = fEntityScanner.peekChar();
                    digit = c >= '0' && c <= '9';
                    if (digit) {
                        if (buf2 != null) { buf2.append((char)c); }
                        fEntityScanner.scanChar();
                        fStringBuffer3.append((char)c);
                    }
                } while (digit);
            }
            else {
                reportFatalError("DigitRequiredInCharRef", null);
            }
        }

        // end
        if (!fEntityScanner.skipChar(';')) {
            reportFatalError("SemicolonRequiredInCharRef", null);
        }
        if (buf2 != null) { buf2.append(';'); }
        
        // convert string to number
        int value = -1;
        try {
            value = Integer.parseInt(fStringBuffer3.toString(),
                                     hex ? 16 : 10);
            
            // character reference must be a valid XML character
            if (isInvalid(value)) {
            	StringBuffer errorBuf = new StringBuffer(fStringBuffer3.length + 1);
                if (hex) errorBuf.append('x');
                errorBuf.append(fStringBuffer3.ch, fStringBuffer3.offset, fStringBuffer3.length);
                reportFatalError("InvalidCharRef",
                                 new Object[]{errorBuf.toString()});
            }
        }
        catch (NumberFormatException e) {
            // Conversion failed, let -1 value drop through.
            // If we end up here, the character reference was invalid.
            StringBuffer errorBuf = new StringBuffer(fStringBuffer3.length + 1);
            if (hex) errorBuf.append('x');
            errorBuf.append(fStringBuffer3.ch, fStringBuffer3.offset, fStringBuffer3.length);
            reportFatalError("InvalidCharRef",
                             new Object[]{errorBuf.toString()});
        }

        // append corresponding chars to the given buffer
        if (!XMLChar.isSupplemental(value)) {
            buf.append((char) value);
        }
        else {
            // character is supplemental, split it into surrogate chars
            buf.append(XMLChar.highSurrogate(value));
            buf.append(XMLChar.lowSurrogate(value));
        }

        // char refs notification code
        if (fNotifyCharRefs && value != -1) {
            String literal = "#" + (hex ? "x" : "") + fStringBuffer3.toString();
            if (!fScanningAttribute) {
                fCharRefLiteral = literal;
            }
        }
                
        return value;
    }

    // returns true if the given character is not
    // valid with respect to the version of
    // XML understood by this scanner.
    protected boolean isInvalid(int value) {
        return (XMLChar.isInvalid(value)); 
    } // isInvalid(int):  boolean

    // returns true if the given character is not
    // valid or may not be used outside a character reference 
    // with respect to the version of XML understood by this scanner.
    protected boolean isInvalidLiteral(int value) {
        return (XMLChar.isInvalid(value)); 
    } // isInvalidLiteral(int):  boolean

    // returns true if the given character is 
    // a valid nameChar with respect to the version of
    // XML understood by this scanner.
    protected boolean isValidNameChar(int value) {
        return (XMLChar.isName(value)); 
    } // isValidNameChar(int):  boolean

    // returns true if the given character is 
    // a valid nameStartChar with respect to the version of
    // XML understood by this scanner.
    protected boolean isValidNameStartChar(int value) {
        return (XMLChar.isNameStart(value)); 
    } // isValidNameStartChar(int):  boolean
    
    // returns true if the given character is
    // a valid NCName character with respect to the version of
    // XML understood by this scanner.
    protected boolean isValidNCName(int value) {
        return (XMLChar.isNCName(value));
    } // isValidNCName(int):  boolean
    
    // returns true if the given character is 
    // a valid high surrogate for a nameStartChar 
    // with respect to the version of XML understood 
    // by this scanner.
    protected boolean isValidNameStartHighSurrogate(int value) {
        return false; 
    } // isValidNameStartHighSurrogate(int):  boolean
    
    protected boolean versionSupported(String version ) {
        return version.equals("1.0");
    } // version Supported
    
    // returns the error message key for unsupported
    // versions of XML with respect to the version of
    // XML understood by this scanner.
    protected String getVersionNotSupportedKey () {
        return "VersionNotSupported";
    } // getVersionNotSupportedKey: String

    /**
     * Scans surrogates and append them to the specified buffer.
     * <p>
     * <strong>Note:</strong> This assumes the current char has already been
     * identified as a high surrogate.
     *
     * @param buf The StringBuffer to append the read surrogates to.
     * @return True if it succeeded.
     */
    protected boolean scanSurrogates(XMLStringBuffer buf)
        throws IOException, XNIException {

        int high = fEntityScanner.scanChar();
        int low = fEntityScanner.peekChar();
        if (!XMLChar.isLowSurrogate(low)) {
            reportFatalError("InvalidCharInContent",
                             new Object[] {Integer.toString(high, 16)});
            return false;
        }
        fEntityScanner.scanChar();

        // convert surrogates to supplemental character
        int c = XMLChar.supplemental((char)high, (char)low);

        // supplemental character must be a valid XML character
        if (isInvalid(c)) {
            reportFatalError("InvalidCharInContent",
                             new Object[]{Integer.toString(c, 16)}); 
            return false;
        }

        // fill in the buffer
        buf.append((char)high);
        buf.append((char)low);

        return true;

    } // scanSurrogates():boolean


    /**
     * Convenience function used in all XML scanners.
     */
    protected void reportFatalError(String msgId, Object[] args)
        throws XNIException {
        fErrorReporter.reportError(XMLMessageFormatter.XML_DOMAIN,
                                   msgId, args,
                                   XMLErrorReporter.SEVERITY_FATAL_ERROR);
    }

    // private methods
    private void init() { 
        fEntityScanner = null;       
        // initialize vars
        fEntityDepth = 0;
        fReportEntity = true;
        fResourceIdentifier.clear();
    } 

} // class XMLScanner