tohtmlstream.java

来自「JAVA的一些源码 JAVA2 STANDARD EDITION DEVELO」· Java 代码 · 共 1,886 行 · 第 1/5 页

                        writer.write(makeHHString(byte1));
                        writer.write('%');
                        writer.write(makeHHString(byte2));
                        writer.write('%');
                        writer.write(makeHHString(byte3));
                        writer.write('%');
                        writer.write(makeHHString(byte4));
                    }
                    else
                    {
                        int high = (ch >> 12) | 0xE0; // top 4 bits
                        int middle = ((ch & 0x0FC0) >> 6) | 0x80;
                        // middle 6 bits
                        int low = (ch & 0x3F) | 0x80;
                        // First 6 bits, + high bit
                        writer.write('%');
                        writer.write(makeHHString(high));
                        writer.write('%');
                        writer.write(makeHHString(middle));
                        writer.write('%');
                        writer.write(makeHHString(low));
                    }

                }
                else if (escapingNotNeeded(ch))
                {
                    writer.write(ch);
                }
                else
                {
                    writer.write("&#");
                    writer.write(Integer.toString(ch));
                    writer.write(';');
                }
                // In this character range we have first written out any previously accumulated 
                // "clean" characters, then processed the current more complicated character,
                // which may have incremented "i".
                // We now we reset the next possible clean character.
                cleanStart = i + 1;
            }
            // Since http://www.ietf.org/rfc/rfc2396.txt refers to the URI grammar as
            // not allowing quotes in the URI proper syntax, nor in the fragment 
            // identifier, we believe that it's OK to double escape quotes.
            else if (ch == '"')
            {
                // If the character is a '%' number number, try to avoid double-escaping.
                // There is a question if this is legal behavior.

                // Dmitri Ilyin: to check if '%' number number is invalid. It must be checked if %xx is a sign, that would be encoded
                // The encoded signes are in Hex form. So %xx my be in form %3C that is "<" sign. I will try to change here a little.

                //        if( ((i+2) < len) && isASCIIDigit(stringArray[i+1]) && isASCIIDigit(stringArray[i+2]) )

                // We are no longer escaping '%'

                if (cleanLength > 0)
                {
                    writer.write(chars, cleanStart, cleanLength);
                    cleanLength = 0;
                }   
                
                
                // Mike Kay encodes this as &#34;, so he may know something I don't?
                if (doURLEscaping)
                    writer.write("%22");
                else
                    writer.write("&quot;"); // we have to escape this, I guess.

                // We have written out any clean characters, then the escaped '%' and now we
                // We now we reset the next possible clean character.
                cleanStart = i + 1;    
            }
            else
            {
                // no processing for this character, just count how
                // many characters in a row that we have that need no processing
                cleanLength++;
            }
        }
        
        // are there any clean characters at the end of the array
        // that we haven't processed yet?
        if (cleanLength > 1)
        {
            // if the whole string can be written out as-is do so
            // otherwise write out the clean chars at the end of the
            // array
            if (cleanStart == 0)
                writer.write(string);
            else
                writer.write(chars, cleanStart, cleanLength);
        }
        else if (cleanLength == 1)
        {
            // a little optimization for 1 clean character
            // (we could have let the previous if(...) handle them all)
            writer.write(ch);
        }
    }

    /**
     * Writes the specified <var>string</var> after substituting <VAR>specials</VAR>,
     * and UTF-16 surrogates for character references <CODE>&amp;#xnn</CODE>.
     *
     * @param   string      String to convert to XML format.
     * @param   encoding    CURRENTLY NOT IMPLEMENTED.
     *
     * @throws org.xml.sax.SAXException
     */
    public void writeAttrString(
        final java.io.Writer writer, String string, String encoding)
        throws IOException
    {
        final int end = string.length();
        if (end > m_attrBuff.length)
        {
            m_attrBuff = new char[end * 2 + 1];
        }
        string.getChars(0, end, m_attrBuff, 0);
        final char[] chars = m_attrBuff;

        

        int cleanStart = 0;
        int cleanLength = 0;

        char ch = 0;
        for (int i = 0; i < end; i++)
        {
            ch = chars[i];

            // System.out.println("SPECIALSSIZE: "+SPECIALSSIZE);
            // System.out.println("ch: "+(int)ch);
            // System.out.println("m_maxCharacter: "+(int)m_maxCharacter);
            // System.out.println("m_attrCharsMap[ch]: "+(int)m_attrCharsMap[ch]);
            if (escapingNotNeeded(ch) && (!m_charInfo.isSpecialAttrChar(ch)))
            {
                cleanLength++;
            }
            else if ('<' == ch || '>' == ch)
            {
                cleanLength++; // no escaping in this case, as specified in 15.2
            }
            else if (
                ('&' == ch) && ((i + 1) < end) && ('{' == chars[i + 1]))
            {
                cleanLength++; // no escaping in this case, as specified in 15.2
            }
            else
            {
                if (cleanLength > 0)
                {
                    writer.write(chars,cleanStart,cleanLength);
                    cleanLength = 0;
                }
                int pos = accumDefaultEntity(writer, ch, i, chars, end, false, false);

                if (i != pos)
                {
                    i = pos - 1;
                }
                else
                {
                    if (isUTF16Surrogate(ch))
                    {
 
                            writeUTF16Surrogate(ch, chars, i, end);
                            i++; // two input characters processed
                                 // this increments by one and the for()
                                 // loop itself increments by another one.
                    }

                    // The next is kind of a hack to keep from escaping in the case 
                    // of Shift_JIS and the like.

                    /*
                    else if ((ch < m_maxCharacter) && (m_maxCharacter == 0xFFFF)
                    && (ch != 160))
                    {
                    writer.write(ch);  // no escaping in this case
                    }
                    else
                    */
                    String entityName = m_charInfo.getEntityNameForChar(ch);
                    if (null != entityName)
                    {
                        writer.write('&');
                        writer.write(entityName);
                        writer.write(';');
                    }
                    else if (escapingNotNeeded(ch))
                    {
                        writer.write(ch); // no escaping in this case
                    }
                    else
                    {
                        writer.write("&#");
                        writer.write(Integer.toString(ch));
                        writer.write(';');
                    }
                }
                cleanStart = i + 1;
            }
        } // end of for()
        
        // are there any clean characters at the end of the array
        // that we haven't processed yet?
        if (cleanLength > 1)
        {
            // if the whole string can be written out as-is do so
            // otherwise write out the clean chars at the end of the
            // array
            if (cleanStart == 0)
                writer.write(string);
            else
                writer.write(chars, cleanStart, cleanLength);
        }
        else if (cleanLength == 1)
        {
            // a little optimization for 1 clean character
            // (we could have let the previous if(...) handle them all)
            writer.write(ch);
        }
    }



    /**
     * Receive notification of character data.
     *
     * <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
     * ignorableWhitespace() method rather than this one (validating
     * parsers must do so).</p>
     *
     * @param chars 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.
     * @throws org.xml.sax.SAXException Any SAX exception, possibly
     *            wrapping another exception.
     * @see #ignorableWhitespace
     * @see org.xml.sax.Locator
     *
     * @throws org.xml.sax.SAXException
     */
    public final void characters(char chars[], int start, int length)
        throws org.xml.sax.SAXException
    {

        if (m_elemContext.m_isRaw)
        {
            try
            {
                if (m_elemContext.m_startTagOpen)
                {
                    closeStartTag();
                    m_elemContext.m_startTagOpen = false;
                }
                m_ispreserve = true;
                
//              With m_ispreserve just set true it looks like shouldIndent()
//              will always return false, so drop any possible indentation.
//              if (shouldIndent())
//                  indent();

                // writer.write("<![CDATA[");
                // writer.write(chars, start, length);
                writeNormalizedChars(chars, start, length, false, m_lineSepUse);

                // writer.write("]]>");
                
                // time to generate characters event
                if (m_tracer != null)
                    super.fireCharEvent(chars, start, length);
                
                return;
            }
            catch (IOException ioe)
            {
                throw new org.xml.sax.SAXException(
                    XMLMessages.createXMLMessage(
                        XMLErrorResources.ER_OIERROR,
                        null),
                    ioe);
                //"IO error", ioe);
            }
        }
        else
        {
            super.characters(chars, start, length);
        }
    }

    /**
     *  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
     *  ignorableWhitespace() method rather than this one (validating
     *  parsers must do so).</p>
     *
     *  @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.
     *  @throws org.xml.sax.SAXException Any SAX exception, possibly
     *             wrapping another exception.
     *  @see #ignorableWhitespace
     *  @see org.xml.sax.Locator
     *
     * @throws org.xml.sax.SAXException
     */
    public final void cdata(char ch[], int start, int length)
        throws org.xml.sax.SAXException
    {

        if ((null != m_elemContext.m_elementName)
            && (m_elemContext.m_elementName.equalsIgnoreCase("SCRIPT")
                || m_elemContext.m_elementName.equalsIgnoreCase("STYLE")))
        {
            try
            {
                if (m_elemContext.m_startTagOpen)
                {
                    closeStartTag();
                    m_elemContext.m_startTagOpen = false;
                }

                m_ispreserve = true;

                if (shouldIndent())
                    indent();

                // writer.write(ch, start, length);
                writeNormalizedChars(ch, start, length, true, m_lineSepUse);
            }
            catch (IOException ioe)
            {
                throw new org.xml.sax.SAXException(
                    XMLMessages.createXMLMessage(
                        XMLErrorResources.ER_OIERROR,
                        null),
                    ioe);
                //"IO error", ioe);
            }
        }
        else
        {
            super.cdata(ch, start, length);
        }
    }

    /**
     *  Receive notification of a processing instruction.
     *
     *  @param target The processing instruction target.
     *  @param data The processing instruction data, or null if
     *         none was supplied.
     *  @throws org.xml.sax.SAXException Any SAX exception, possibly
     *             wrapping another exception.
     *