Java XMLChar.isHighSurrogate方法代码示例

import com.sun.org.apache.xerces.internal.util.XMLChar; //导入方法依赖的package包/类
/**
 * Skip the DTD if javax.xml.stream.supportDTD is false.
 *
 * @param supportDTD The value of the property javax.xml.stream.supportDTD.
 * @return true if DTD is skipped, false otherwise.
 * @throws java.io.IOException if i/o error occurs
 */
@Override
public boolean skipDTD(boolean supportDTD) throws IOException {
    if (supportDTD)
        return false;

    fStringBuffer.clear();
    while (fEntityScanner.scanData("]", fStringBuffer, 0)) {
        int c = fEntityScanner.peekChar();
        if (c != -1) {
            if (XMLChar.isHighSurrogate(c)) {
                scanSurrogates(fStringBuffer);
            }
            if (isInvalidLiteral(c)) {
                reportFatalError("InvalidCharInDTD",
                    new Object[] { Integer.toHexString(c) });
                fEntityScanner.scanChar(null);
            }
        }
    }
    fEntityScanner.fCurrentEntity.position--;
    return true;
}
 

import com.sun.org.apache.xerces.internal.util.XMLChar; //导入方法依赖的package包/类
/**
 * Scans a comment.
 * <p>
 * <pre>
 * [15] Comment ::= '&lt!--' ((Char - '-') | ('-' (Char - '-')))* '-->'
 * </pre>
 * <p>
 * <strong>Note:</strong> Called after scanning past '&lt;!--'
 * <strong>Note:</strong> This method uses fString, anything in it
 * at the time of calling is lost.
 *
 * @param text The buffer to fill in with the text.
 */
protected void scanComment(XMLStringBuffer text)
throws IOException, XNIException {

    //System.out.println( "XMLScanner#scanComment# In Scan Comment" );
    // text
    // REVISIT: handle invalid character, eof
    text.clear();
    while (fEntityScanner.scanData("--", text)) {
        int c = fEntityScanner.peekChar();

        //System.out.println( "XMLScanner#scanComment#text.toString() == " + text.toString() );
        //System.out.println( "XMLScanner#scanComment#c == " + c );

        if (c != -1) {
            if (XMLChar.isHighSurrogate(c)) {
                scanSurrogates(text);
            }
            if (isInvalidLiteral(c)) {
                reportFatalError("InvalidCharInComment",
                        new Object[] { Integer.toHexString(c) });
                        fEntityScanner.scanChar();
            }
        }
    }
    if (!fEntityScanner.skipChar('>')) {
        reportFatalError("DashDashInComment", null);
    }

}
 

import com.sun.org.apache.xerces.internal.util.XMLChar; //导入方法依赖的package包/类
protected final void surrogates(int high, int low) throws IOException{
    if (XMLChar.isHighSurrogate(high)) {
        if (!XMLChar.isLowSurrogate(low)) {
            //Invalid XML
            fatalError("The character '"+(char)low+"' is an invalid XML character");
        }
        else {
            int supplemental = XMLChar.supplemental((char)high, (char)low);
            if (!XML11Char.isXML11Valid(supplemental)) {
                //Invalid XML
                fatalError("The character '"+(char)supplemental+"' is an invalid XML character");
            }
            else {
                if (content().inCData ) {
                    _printer.printText("]]>&#x");
                    _printer.printText(Integer.toHexString(supplemental));
                    _printer.printText(";<![CDATA[");
                }
                else {
                                            printHex(supplemental);
                }
            }
        }
    } else {
        fatalError("The character '"+(char)high+"' is an invalid XML character");
    }

}
 

import com.sun.org.apache.xerces.internal.util.XMLChar; //导入方法依赖的package包/类
protected void surrogates(int high, int low) throws IOException{
    if (XMLChar.isHighSurrogate(high)) {
        if (!XMLChar.isLowSurrogate(low)) {
            //Invalid XML
            fatalError("The character '"+(char)low+"' is an invalid XML character");
        }
        else {
            int supplemental = XMLChar.supplemental((char)high, (char)low);
            if (!XMLChar.isValid(supplemental)) {
                //Invalid XML
                fatalError("The character '"+(char)supplemental+"' is an invalid XML character");
            }
            else {
                if (content().inCData ) {
                    _printer.printText("]]>&#x");
                    _printer.printText(Integer.toHexString(supplemental));
                    _printer.printText(";<![CDATA[");
                }
                else {
                    printHex(supplemental);
                }
            }
        }
    } else {
        fatalError("The character '"+(char)high+"' is an invalid XML character");
    }

}
 

import com.sun.org.apache.xerces.internal.util.XMLChar; //导入方法依赖的package包/类
/**
 * Scans a comment.
 * <p>
 * <pre>
 * [15] Comment ::= '&lt!--' ((Char - '-') | ('-' (Char - '-')))* '-->'
 * </pre>
 * <p>
 * <strong>Note:</strong> Called after scanning past '&lt;!--'
 * <strong>Note:</strong> This method uses fString, anything in it
 * at the time of calling is lost.
 *
 * @param text The buffer to fill in with the text.
 */
protected void scanComment(XMLStringBuffer text)
throws IOException, XNIException {

    //System.out.println( "XMLScanner#scanComment# In Scan Comment" );
    // text
    // REVISIT: handle invalid character, eof
    text.clear();
    while (fEntityScanner.scanData("--", text, 0)) {
        int c = fEntityScanner.peekChar();

        //System.out.println( "XMLScanner#scanComment#text.toString() == " + text.toString() );
        //System.out.println( "XMLScanner#scanComment#c == " + c );

        if (c != -1) {
            if (XMLChar.isHighSurrogate(c)) {
                scanSurrogates(text);
            }
            else if (isInvalidLiteral(c)) {
                reportFatalError("InvalidCharInComment",
                        new Object[] { Integer.toHexString(c) });
                        fEntityScanner.scanChar(NameType.COMMENT);
            }
        }
    }
    if (!fEntityScanner.skipChar('>', NameType.COMMENT)) {
        reportFatalError("DashDashInComment", null);
    }

}
 

import com.sun.org.apache.xerces.internal.util.XMLChar; //导入方法依赖的package包/类
protected final void surrogates(int high, int low, boolean inContent) throws IOException{
    if (XMLChar.isHighSurrogate(high)) {
        if (!XMLChar.isLowSurrogate(low)) {
            //Invalid XML
            fatalError("The character '"+(char)low+"' is an invalid XML character");
        }
        else {
            int supplemental = XMLChar.supplemental((char)high, (char)low);
            if (!XML11Char.isXML11Valid(supplemental)) {
                //Invalid XML
                fatalError("The character '"+(char)supplemental+"' is an invalid XML character");
            }
            else {
                if (inContent && content().inCData) {
                    _printer.printText("]]>&#x");
                    _printer.printText(Integer.toHexString(supplemental));
                    _printer.printText(";<![CDATA[");
                }
                else {
                                            printHex(supplemental);
                }
            }
        }
    }
    else {
        fatalError("The character '"+(char)high+"' is an invalid XML character");
    }

}
 

import com.sun.org.apache.xerces.internal.util.XMLChar; //导入方法依赖的package包/类
protected void surrogates(int high, int low, boolean inContent) throws IOException{
    if (XMLChar.isHighSurrogate(high)) {
        if (!XMLChar.isLowSurrogate(low)) {
            //Invalid XML
            fatalError("The character '"+(char)low+"' is an invalid XML character");
        }
        else {
            int supplemental = XMLChar.supplemental((char)high, (char)low);
            if (!XMLChar.isValid(supplemental)) {
                //Invalid XML
                fatalError("The character '"+(char)supplemental+"' is an invalid XML character");
            }
            else {
                if (inContent && content().inCData) {
                    _printer.printText("]]>&#x");
                    _printer.printText(Integer.toHexString(supplemental));
                    _printer.printText(";<![CDATA[");
                }
                else {
                    printHex(supplemental);
                }
            }
        }
    } else {
        fatalError("The character '"+(char)high+"' is an invalid XML character");
    }

}
 

import com.sun.org.apache.xerces.internal.util.XMLChar; //导入方法依赖的package包/类
/**
 * Scans a pseudo attribute.
 *
 * @param scanningTextDecl True if scanning this pseudo-attribute for a
 *                         TextDecl; false if scanning XMLDecl. This
 *                         flag is needed to report the correct type of
 *                         error.
 * @param value            The string to fill in with the attribute
 *                         value.
 *
 * @return The name of the attribute
 *
 * <strong>Note:</strong> This method uses fStringBuffer2, anything in it
 * at the time of calling is lost.
 */
public String scanPseudoAttribute(boolean scanningTextDecl,
        XMLString value)
        throws IOException, XNIException {

    String name = scanPseudoAttributeName();
    // XMLEntityManager.print(fEntityManager.getCurrentEntity());

    if (name == null) {
        reportFatalError("PseudoAttrNameExpected", null);
    }
    fEntityScanner.skipSpaces();
    if (!fEntityScanner.skipChar('=')) {
        reportFatalError(scanningTextDecl ? "EqRequiredInTextDecl"
                : "EqRequiredInXMLDecl", new Object[]{name});
    }
    fEntityScanner.skipSpaces();
    int quote = fEntityScanner.peekChar();
    if (quote != '\'' && quote != '"') {
        reportFatalError(scanningTextDecl ? "QuoteRequiredInTextDecl"
                : "QuoteRequiredInXMLDecl" , new Object[]{name});
    }
    fEntityScanner.scanChar();
    int c = fEntityScanner.scanLiteral(quote, value);
    if (c != quote) {
        fStringBuffer2.clear();
        do {
            fStringBuffer2.append(value);
            if (c != -1) {
                if (c == '&' || c == '%' || c == '<' || c == ']') {
                    fStringBuffer2.append((char)fEntityScanner.scanChar());
                } else if (XMLChar.isHighSurrogate(c)) {
                    scanSurrogates(fStringBuffer2);
                } else if (isInvalidLiteral(c)) {
                    String key = scanningTextDecl
                            ? "InvalidCharInTextDecl" : "InvalidCharInXMLDecl";
                    reportFatalError(key,
                            new Object[] {Integer.toString(c, 16)});
                            fEntityScanner.scanChar();
                }
            }
            c = fEntityScanner.scanLiteral(quote, value);
        } while (c != quote);
        fStringBuffer2.append(value);
        value.setValues(fStringBuffer2);
    }
    if (!fEntityScanner.skipChar(quote)) {
        reportFatalError(scanningTextDecl ? "CloseQuoteMissingInTextDecl"
                : "CloseQuoteMissingInXMLDecl",
                new Object[]{name});
    }

    // return
    return name;

}
 

import com.sun.org.apache.xerces.internal.util.XMLChar; //导入方法依赖的package包/类
/**
 * Scans a processing data. This is needed to handle the situation
 * where a document starts with a processing instruction whose
 * target name <em>starts with</em> "xml". (e.g. xmlfoo)
 *
 * This method would always read the whole data. We have while loop and data is buffered
 * until delimeter is encountered.
 *
 * @param target The PI target
 * @param data The string to fill in with the data
 */

//CHANGED:
//Earlier:This method uses the fStringBuffer and later buffer values are set to
//the supplied XMLString....
//Now: Changed the signature of this function to pass XMLStringBuffer.. and data would
//be appended to that buffer

protected void scanPIData(String target, XMLStringBuffer data)
throws IOException, XNIException {

    // check target
    if (target.length() == 3) {
        char c0 = Character.toLowerCase(target.charAt(0));
        char c1 = Character.toLowerCase(target.charAt(1));
        char c2 = Character.toLowerCase(target.charAt(2));
        if (c0 == 'x' && c1 == 'm' && c2 == 'l') {
            reportFatalError("ReservedPITarget", null);
        }
    }

    // spaces
    if (!fEntityScanner.skipSpaces()) {
        if (fEntityScanner.skipString("?>")) {
            // we found the end, there is no data just return
            return;
        } else {
            // if there is data there should be some space
            reportFatalError("SpaceRequiredInPI", null);
        }
    }

    // since scanData appends the parsed data to the buffer passed
    // a while loop would append the whole of parsed data to the buffer(data:XMLStringBuffer)
    //until all of the data is buffered.
    if (fEntityScanner.scanData("?>", data)) {
        do {
            int c = fEntityScanner.peekChar();
            if (c != -1) {
                if (XMLChar.isHighSurrogate(c)) {
                    scanSurrogates(data);
                } else if (isInvalidLiteral(c)) {
                    reportFatalError("InvalidCharInPI",
                            new Object[]{Integer.toHexString(c)});
                            fEntityScanner.scanChar();
                }
            }
        } while (fEntityScanner.scanData("?>", data));
    }

}
 

import com.sun.org.apache.xerces.internal.util.XMLChar; //导入方法依赖的package包/类
public void write(int c) throws IOException {
    // Check in we are encoding at high and low surrogates
    if (lastUTF16CodePoint != 0) {
        final int uc =
            (((lastUTF16CodePoint & 0x3ff) << 10) | (c & 0x3ff)) + 0x10000;

        if (uc < 0 || uc >= 0x200000) {
            throw new IOException("Atttempting to write invalid Unicode code point '" + uc + "'");
        }

        out.write(0xF0 | (uc >> 18));
        out.write(0x80 | ((uc >> 12) & 0x3F));
        out.write(0x80 | ((uc >> 6) & 0x3F));
        out.write(0x80 | (uc & 0x3F));

        lastUTF16CodePoint = 0;
        return;
    }

    // Otherwise, encode char as defined in UTF-8
    if (c < 0x80) {
        // 1 byte, 7 bits
        out.write((int) c);
    }
    else if (c < 0x800) {
        // 2 bytes, 11 bits
        out.write(0xC0 | (c >> 6));    // first 5
        out.write(0x80 | (c & 0x3F));  // second 6
    }
    else if (c <= '\uFFFF') {
        if (!XMLChar.isHighSurrogate(c) && !XMLChar.isLowSurrogate(c)) {
            // 3 bytes, 16 bits
            out.write(0xE0 | (c >> 12));   // first 4
            out.write(0x80 | ((c >> 6) & 0x3F));  // second 6
            out.write(0x80 | (c & 0x3F));  // third 6
        }
        else {
            lastUTF16CodePoint = c;
        }
    }
}
 

import com.sun.org.apache.xerces.internal.util.XMLChar; //导入方法依赖的package包/类
/**
 * Scans a pseudo attribute.
 *
 * @param scanningTextDecl True if scanning this pseudo-attribute for a
 *                         TextDecl; false if scanning XMLDecl. This
 *                         flag is needed to report the correct type of
 *                         error.
 * @param value            The string to fill in with the attribute
 *                         value.
 *
 * @return The name of the attribute
 *
 * <strong>Note:</strong> This method uses fStringBuffer2, anything in it
 * at the time of calling is lost.
 */
protected String scanPseudoAttribute(boolean scanningTextDecl,
        XMLString value)
        throws IOException, XNIException {

    String name = scanPseudoAttributeName();
    // XMLEntityManager.print(fEntityManager.getCurrentEntity());

    if (name == null) {
        reportFatalError("PseudoAttrNameExpected", null);
    }
    fEntityScanner.skipSpaces();
    if (!fEntityScanner.skipChar('=', null)) {
        reportFatalError(scanningTextDecl ? "EqRequiredInTextDecl"
                : "EqRequiredInXMLDecl", new Object[]{name});
    }
    fEntityScanner.skipSpaces();
    int quote = fEntityScanner.peekChar();
    if (quote != '\'' && quote != '"') {
        reportFatalError(scanningTextDecl ? "QuoteRequiredInTextDecl"
                : "QuoteRequiredInXMLDecl" , new Object[]{name});
    }
    fEntityScanner.scanChar(NameType.ATTRIBUTE);
    int c = fEntityScanner.scanLiteral(quote, value, false);
    if (c != quote) {
        fStringBuffer2.clear();
        do {
            fStringBuffer2.append(value);
            if (c != -1) {
                if (c == '&' || c == '%' || c == '<' || c == ']') {
                    fStringBuffer2.append((char)fEntityScanner.scanChar(NameType.ATTRIBUTE));
                } else if (XMLChar.isHighSurrogate(c)) {
                    scanSurrogates(fStringBuffer2);
                } else if (isInvalidLiteral(c)) {
                    String key = scanningTextDecl
                            ? "InvalidCharInTextDecl" : "InvalidCharInXMLDecl";
                    reportFatalError(key,
                            new Object[] {Integer.toString(c, 16)});
                            fEntityScanner.scanChar(null);
                }
            }
            c = fEntityScanner.scanLiteral(quote, value, false);
        } while (c != quote);
        fStringBuffer2.append(value);
        value.setValues(fStringBuffer2);
    }
    if (!fEntityScanner.skipChar(quote, null)) {
        reportFatalError(scanningTextDecl ? "CloseQuoteMissingInTextDecl"
                : "CloseQuoteMissingInXMLDecl",
                new Object[]{name});
    }

    // return
    return name;

}
 

import com.sun.org.apache.xerces.internal.util.XMLChar; //导入方法依赖的package包/类
/**
 * Scans a processing data. This is needed to handle the situation
 * where a document starts with a processing instruction whose
 * target name <em>starts with</em> "xml". (e.g. xmlfoo)
 *
 * This method would always read the whole data. We have while loop and data is buffered
 * until delimeter is encountered.
 *
 * @param target The PI target
 * @param data The string to fill in with the data
 */

//CHANGED:
//Earlier:This method uses the fStringBuffer and later buffer values are set to
//the supplied XMLString....
//Now: Changed the signature of this function to pass XMLStringBuffer.. and data would
//be appended to that buffer

protected void scanPIData(String target, XMLStringBuffer data)
throws IOException, XNIException {

    // check target
    if (target.length() == 3) {
        char c0 = Character.toLowerCase(target.charAt(0));
        char c1 = Character.toLowerCase(target.charAt(1));
        char c2 = Character.toLowerCase(target.charAt(2));
        if (c0 == 'x' && c1 == 'm' && c2 == 'l') {
            reportFatalError("ReservedPITarget", null);
        }
    }

    // spaces
    if (!fEntityScanner.skipSpaces()) {
        if (fEntityScanner.skipString("?>")) {
            // we found the end, there is no data just return
            return;
        } else {
            // if there is data there should be some space
            reportFatalError("SpaceRequiredInPI", null);
        }
    }

    // since scanData appends the parsed data to the buffer passed
    // a while loop would append the whole of parsed data to the buffer(data:XMLStringBuffer)
    //until all of the data is buffered.
    if (fEntityScanner.scanData("?>", data, 0)) {
        do {
            int c = fEntityScanner.peekChar();
            if (c != -1) {
                if (XMLChar.isHighSurrogate(c)) {
                    scanSurrogates(data);
                } else if (isInvalidLiteral(c)) {
                    reportFatalError("InvalidCharInPI",
                            new Object[]{Integer.toHexString(c)});
                            fEntityScanner.scanChar(null);
                }
            }
        } while (fEntityScanner.scanData("?>", data, 0));
    }

}
 

import com.sun.org.apache.xerces.internal.util.XMLChar; //导入方法依赖的package包/类
/**
 * Scans a CDATA section.
 * <p>
 * <strong>Note:</strong> This method uses the fTempString and
 * fStringBuffer variables.
 *
 * @param complete True if the CDATA section is to be scanned
 *                 completely.
 *
 * @return True if CDATA is completely scanned.
 */
//CHANGED:
protected boolean scanCDATASection(XMLStringBuffer contentBuffer, boolean complete)
throws IOException, XNIException {

    // call handler
    if (fDocumentHandler != null) {
        //fDocumentHandler.startCDATA(null);
    }

    while (true) {
        //scanData will fill the contentBuffer
        if (!fEntityScanner.scanData("]]>", contentBuffer, fChunkSize)) {
            fInCData = false;
            fCDataEnd = true;
            fMarkupDepth--;
            break ;
        } else {
            int c = fEntityScanner.peekChar();
            if (c != -1 && isInvalidLiteral(c)) {
                if (XMLChar.isHighSurrogate(c)) {
                    //contentBuffer.clear();
                    //scan surrogates if any....
                    scanSurrogates(contentBuffer);
                } else {
                    reportFatalError("InvalidCharInCDSect",
                            new Object[]{Integer.toString(c,16)});
                            fEntityScanner.scanChar(null);
                }
            } else {
                //CData partially returned due to the size limit
                break;
            }
            //by this time we have also read surrogate contents if any...
            if (fDocumentHandler != null) {
                //fDocumentHandler.characters(contentBuffer, null);
            }
        }
    }

    return true;

}
 

import com.sun.org.apache.xerces.internal.util.XMLChar; //导入方法依赖的package包/类
public void write(int c) throws IOException {
    // Check in we are encoding at high and low surrogates
    if (lastUTF16CodePoint != 0) {
        final int uc =
            (((lastUTF16CodePoint & 0x3ff) << 10) | (c & 0x3ff)) + 0x10000;

        if (uc < 0 || uc >= 0x200000) {
            throw new IOException("Atttempting to write invalid Unicode code point '" + uc + "'");
        }

        out.write(0xF0 | (uc >> 18));
        out.write(0x80 | ((uc >> 12) & 0x3F));
        out.write(0x80 | ((uc >> 6) & 0x3F));
        out.write(0x80 | (uc & 0x3F));

        lastUTF16CodePoint = 0;
        return;
    }

    // Otherwise, encode char as defined in UTF-8
    if (c < 0x80) {
        // 1 byte, 7 bits
        out.write(c);
    }
    else if (c < 0x800) {
        // 2 bytes, 11 bits
        out.write(0xC0 | (c >> 6));    // first 5
        out.write(0x80 | (c & 0x3F));  // second 6
    }
    else if (c <= '\uFFFF') {
        if (!XMLChar.isHighSurrogate(c) && !XMLChar.isLowSurrogate(c)) {
            // 3 bytes, 16 bits
            out.write(0xE0 | (c >> 12));   // first 4
            out.write(0x80 | ((c >> 6) & 0x3F));  // second 6
            out.write(0x80 | (c & 0x3F));  // third 6
        }
        else {
            lastUTF16CodePoint = c;
        }
    }
}