tostream.java

来自「JAVA 所有包」· Java 代码 · 共 2,016 行 · 第 1/5 页

     *        none of these applies.
     * @param value A string representing the attribute's default value,
     *        or null if there is none.
     * @exception SAXException The application may raise an exception.
     */
    public void attributeDecl(
        String eName,
        String aName,
        String type,
        String valueDefault,
        String value)
        throws SAXException
    {
        // Do not inline external DTD
        if (m_inExternalDTD)
            return;
        try
        {
            final java.io.Writer writer = m_writer;
            DTDprolog();

            writer.write("<!ATTLIST ");
            writer.write(eName);
            writer.write(' ');

            writer.write(aName);
            writer.write(' ');
            writer.write(type);
            if (valueDefault != null)
            {
                writer.write(' ');
                writer.write(valueDefault);
            }

            //writer.write(" ");
            //writer.write(value);
            writer.write('>');
            writer.write(m_lineSep, 0, m_lineSepLen);
        }
        catch (IOException e)
        {
            throw new SAXException(e);
        }
    }

    /**
     * Get the character stream where the events will be serialized to.
     *
     * @return Reference to the result Writer, or null.
     */
    public Writer getWriter()
    {
        return m_writer;
    }

    /**
     * Report a parsed external entity declaration.
     *
     * <p>Only the effective (first) declaration for each entity
     * will be reported.</p>
     *
     * @param name The name of the entity.  If it is a parameter
     *        entity, the name will begin with '%'.
     * @param publicId The declared public identifier of the entity, or
     *        null if none was declared.
     * @param systemId The declared system identifier of the entity.
     * @exception SAXException The application may raise an exception.
     * @see #internalEntityDecl
     * @see org.xml.sax.DTDHandler#unparsedEntityDecl
     */
    public void externalEntityDecl(
        String name,
        String publicId,
        String systemId)
        throws SAXException
    {
        try {
            DTDprolog();
            
            m_writer.write("<!ENTITY ");            
            m_writer.write(name);
            if (publicId != null) {
                m_writer.write(" PUBLIC \"");
                m_writer.write(publicId);
  
            }
            else {
                m_writer.write(" SYSTEM \"");
                m_writer.write(systemId);
            }
            m_writer.write("\" >");
            m_writer.write(m_lineSep, 0, m_lineSepLen);
        } catch (IOException e) {
            // TODO Auto-generated catch block
            e.printStackTrace();
        }

    }

    /**
     * Tell if this character can be written without escaping.
     */
    protected boolean escapingNotNeeded(char ch)
    {
        final boolean ret;
        if (ch < 127)
        {
            // This is the old/fast code here, but is this 
            // correct for all encodings?
            if (ch >= 0x20 || (0x0A == ch || 0x0D == ch || 0x09 == ch))
                ret= true;
            else
                ret = false;
        }
        else {            
            ret = m_encodingInfo.isInEncoding(ch);
        }
        return ret;        
    }
    
    /**
     * Once a surrogate has been detected, write out the pair of
     * characters if it is in the encoding, or if there is no
     * encoding, otherwise write out an entity reference
     * of the value of the unicode code point of the character
     * represented by the high/low surrogate pair.
     * <p>
     * An exception is thrown if there is no low surrogate in the pair,
     * because the array ends unexpectely, or if the low char is there
     * but its value is such that it is not a low surrogate.
     *
     * @param c the first (high) part of the surrogate, which
     * must be confirmed before calling this method.
     * @param ch Character array.
     * @param i position Where the surrogate was detected.
     * @param end The end index of the significant characters.
     * @return 0 if the pair of characters was written out as-is,
     * the unicode code point of the character represented by
     * the surrogate pair if an entity reference with that value
     * was written out. 
     * 
     * @throws IOException
     * @throws org.xml.sax.SAXException if invalid UTF-16 surrogate detected.
     */
    protected int writeUTF16Surrogate(char c, char ch[], int i, int end)
        throws IOException
    {
        int codePoint = 0;
        if (i + 1 >= end)
        {
            throw new IOException(
                Utils.messages.createMessage(
                    MsgKey.ER_INVALID_UTF16_SURROGATE,
                    new Object[] { Integer.toHexString((int) c)}));
        }
        
        final char high = c;
        final char low = ch[i+1];
        if (!Encodings.isLowUTF16Surrogate(low)) {
            throw new IOException(
                Utils.messages.createMessage(
                    MsgKey.ER_INVALID_UTF16_SURROGATE,
                    new Object[] {
                        Integer.toHexString((int) c)
                            + " "
                            + Integer.toHexString(low)}));
        }

        final java.io.Writer writer = m_writer;
                
        // If we make it to here we have a valid high, low surrogate pair
        if (m_encodingInfo.isInEncoding(c,low)) {
            // If the character formed by the surrogate pair
            // is in the encoding, so just write it out
            writer.write(ch,i,2);
        }
        else {
            // Don't know what to do with this char, it is
            // not in the encoding and not a high char in
            // a surrogate pair, so write out as an entity ref
            final String encoding = getEncoding();
            if (encoding != null) {
                /* The output encoding is known, 
                 * so somthing is wrong.
                  */
                codePoint = Encodings.toCodePoint(high, low);
                // not in the encoding, so write out a character reference
                writer.write('&');
                writer.write('#');
                writer.write(Integer.toString(codePoint));
                writer.write(';');
            } else {
                /* The output encoding is not known,
                 * so just write it out as-is.
                 */
                writer.write(ch, i, 2);
            }
        }
        // non-zero only if character reference was written out.
        return codePoint;
    }

    /**
     * Handle one of the default entities, return false if it
     * is not a default entity.
     *
     * @param ch character to be escaped.
     * @param i index into character array.
     * @param chars non-null reference to character array.
     * @param len length of chars.
     * @param fromTextNode true if the characters being processed
     * are from a text node, false if they are from an attribute value
     * @param escLF true if the linefeed should be escaped.
     *
     * @return i+1 if the character was written, else i.
     *
     * @throws java.io.IOException
     */
    protected int accumDefaultEntity(
        java.io.Writer writer,
        char ch,
        int i,
        char[] chars,
        int len,
        boolean fromTextNode,
        boolean escLF)
        throws IOException
    {

        if (!escLF && CharInfo.S_LINEFEED == ch)
        {
            writer.write(m_lineSep, 0, m_lineSepLen);
        }
        else
        {
            // if this is text node character and a special one of those,
            // or if this is a character from attribute value and a special one of those
            if ((fromTextNode && m_charInfo.isSpecialTextChar(ch)) || (!fromTextNode && m_charInfo.isSpecialAttrChar(ch)))
            {
                String outputStringForChar = m_charInfo.getOutputStringForChar(ch);

                if (null != outputStringForChar)
                {
                    writer.write(outputStringForChar);
                }
                else
                    return i;
            }
            else
                return i;
        }

        return i + 1;

    }
    /**
     * Normalize the characters, but don't escape.
     *
     * @param ch The characters from the XML document.
     * @param start The start position in the array.
     * @param length The number of characters to read from the array.
     * @param isCData true if a CDATA block should be built around the characters.
     * @param useSystemLineSeparator true if the operating systems 
     * end-of-line separator should be output rather than a new-line character.
     *
     * @throws IOException
     * @throws org.xml.sax.SAXException
     */
    void writeNormalizedChars(
        char ch[],
        int start,
        int length,
        boolean isCData,
        boolean useSystemLineSeparator)
        throws IOException, org.xml.sax.SAXException
    {
        final java.io.Writer writer = m_writer;
        int end = start + length;

        for (int i = start; i < end; i++)
        {
            char c = ch[i];

            if (CharInfo.S_LINEFEED == c && useSystemLineSeparator)
            {
                writer.write(m_lineSep, 0, m_lineSepLen);
            }
            else if (isCData && (!escapingNotNeeded(c)))
            {
                //                if (i != 0)
                if (m_cdataTagOpen)
                    closeCDATA();

                // This needs to go into a function... 
                if (Encodings.isHighUTF16Surrogate(c))
                {
                    writeUTF16Surrogate(c, ch, i, end);
                    i++ ; // process two input characters
                }
                else
                {
                    writer.write("&#");

                    String intStr = Integer.toString((int) c);

                    writer.write(intStr);
                    writer.write(';');
                }

                //                if ((i != 0) && (i < (end - 1)))
                //                if (!m_cdataTagOpen && (i < (end - 1)))
                //                {
                //                    writer.write(CDATA_DELIMITER_OPEN);
                //                    m_cdataTagOpen = true;
                //                }
            }
            else if (
                isCData
                    && ((i < (end - 2))
                        && (']' == c)
                        && (']' == ch[i + 1])
                        && ('>' == ch[i + 2])))
            {
                writer.write(CDATA_CONTINUE);

                i += 2;
            }
            else
            {
                if (escapingNotNeeded(c))
                {
                    if (isCData && !m_cdataTagOpen)
                    {
                        writer.write(CDATA_DELIMITER_OPEN);
                        m_cdataTagOpen = true;
                    }
                    writer.write(c);
                }

                // This needs to go into a function... 
                else if (Encodings.isHighUTF16Surrogate(c))
                {
                    if (m_cdataTagOpen)
                        closeCDATA();
                    writeUTF16Surrogate(c, ch, i, end);
                    i++; // process two input characters
                }
                else
                {
                    if (m_cdataTagOpen)
                        closeCDATA();
                    writer.write("&#");

                    String intStr = Integer.toString((int) c);

                    writer.write(intStr);
                    writer.write(';');
                }
            }
        }

    }

    /**
     * Ends an un-escaping section.
     *
     * @see #startNonEscaping
     *
     * @throws org.xml.sax.SAXException
     */
    public void endNonEscaping() throws org.xml.sax.SAXException
    {
        m_disableOutputEscapingStates.pop();
    }

    /**
     * Starts an un-escaping section. All characters printed within an un-
     * escaping section are printed as is, without escaping special characters
     * into entity references. Only XML and HTML serializers need to support
     * this method.
     * <p> The contents of the un-escaping section will be delivered through the
     * regular <tt>characters</tt> event.
     *
     * @throws org.xml.sax.SAXException
     */
    public void startNonEscaping() throws org.xml.sax.SAXException
    {
        m_disableOutputEscapingStates.push(true);
    }

    /**
     * Receive notification of cdata.
     *
     * <p>The Parser will call this method to report each chunk of
     * character data.  SAX parsers may return all contiguous character
     * data in a single chunk, or they may split it into several
     * chunks; however, all of the characters in any single event
     * must come from the same external entity, so that the Locator
     * provides useful information.</p>
     *
     * <p>The application must not attempt to read from the array
     * outside of the specified range.</p>
     *
     * <p>Note that some parsers will report whitespace using the