basemarkupserializer.java

uPortal是开放源码的Portal门户产品

            int          index;
            int          saveIndent;

            // Print a CDATA section. The text is not escaped, but ']]>'
            // appearing in the code must be identified and dealt with.
            // The contents of a text node is considered space preserving.
            buffer = new StringBuffer( text.length() );
            if ( ! state.inCData ) {
                buffer.append( "<![CDATA[" );
                state.inCData = true;
            }
            index = text.indexOf( "]]>" );
            while ( index >= 0 ) {
                buffer.append( text.substring( 0, index + 2 ) ).append( "]]><![CDATA[" );
                text = text.substring( index + 2 );
                index = text.indexOf( "]]>" );
            }
            buffer.append( text );
            saveIndent = _printer.getNextIndent();
            _printer.setNextIndent( 0 );
            printText( buffer.toString(), true, true );
            _printer.setNextIndent( saveIndent );

        } else {

            int saveIndent;

            if ( state.preserveSpace ) {
                // If preserving space then hold of indentation so no
                // excessive spaces are printed at line breaks, escape
                // the text content without replacing spaces and print
                // the text breaking only at line breaks.
                saveIndent = _printer.getNextIndent();
                _printer.setNextIndent( 0 );
                printText( text, true, state.unescaped );
                _printer.setNextIndent( saveIndent );
            } else {
                printText( text, false, state.unescaped );
            }
        }
    }


    /**
     * Returns the suitable entity reference for this character value,
     * or null if no such entity exists. Calling this method with <tt>'&amp;'</tt>
     * will return <tt>"&amp;amp;"</tt>.
     *
     * @param ch Character value
     * @return Character entity name, or null
     */
    protected abstract String getEntityRef( int ch );


    /**
     * Called to serializee the DOM element. The element is serialized based on
     * the serializer's method (XML, HTML, XHTML).
     *
     * @param elem The element to serialize
     * @throws IOException An I/O exception occured while
     *   serializing
     */
    protected abstract void serializeElement( Element elem )
        throws IOException;


    /**
     * Comments and PIs cannot be serialized before the root element,
     * because the root element serializes the document type, which
     * generally comes first. Instead such PIs and comments are
     * accumulated inside a vector and serialized by calling this
     * method. Will be called when the root element is serialized
     * and when the document finished serializing.
     *
     * @throws IOException An I/O exception occured while
     *   serializing
     */
    protected void serializePreRoot()
        throws IOException
    {
        int i;

        if ( _preRoot != null ) {
            for ( i = 0 ; i < _preRoot.size() ; ++i ) {
                printText( (String) _preRoot.elementAt( i ), true, true );
                if ( _indenting )
                _printer.breakLine();
            }
            _preRoot.removeAllElements();
        }
    }


    //---------------------------------------------//
    // Text pretty printing and formatting methods //
    //---------------------------------------------//


    /**
     * Called to print additional text with whitespace handling.
     * If spaces are preserved, the text is printed as if by calling
     * {@link #printText(String, boolean, boolean)} with a call to breakLine()
     * for each new line. If spaces are not preserved, the text is
     * broken at space boundaries if longer than the line width;
     * Multiple spaces are printed as such, but spaces at beginning
     * of line are removed.
     *
     * @param preserveSpace Space preserving flag
     * @param unescaped Print unescaped
     */
    protected final void printText( char[] chars, int start, int length,
                                    boolean preserveSpace, boolean unescaped )
        throws IOException
    {
        int index;
        char ch;

        if ( preserveSpace ) {
            // Preserving spaces: the text must print exactly as it is,
            // without breaking when spaces appear in the text and without
            // consolidating spaces. If a line terminator is used, a line
            // break will occur.
            while ( length-- > 0 ) {
                ch = chars[ start ];
                ++start;
                if ( ch == '\n' || ch == '\r' || unescaped )
                    _printer.printText( ch );
                else
                    printEscaped( ch );
            }
        } else {
            // Not preserving spaces: print one part at a time, and
            // use spaces between parts to break them into different
            // lines. Spaces at beginning of line will be stripped
            // by printing mechanism. Line terminator is treated
            // no different than other text part.
            while ( length-- > 0 ) {
                ch = chars[ start ];
                ++start;
                if ( ch == ' ' || ch == '\f' || ch == '\t' || ch == '\n' || ch == '\r' )
                    _printer.printSpace();
                else if ( unescaped )
                    _printer.printText( ch );
                else
                    printEscaped( ch );
            }
        }
    }


    protected final void printText( String text, boolean preserveSpace, boolean unescaped )
        throws IOException
    {
        int index;
        char ch;

        if ( preserveSpace ) {
            // Preserving spaces: the text must print exactly as it is,
            // without breaking when spaces appear in the text and without
            // consolidating spaces. If a line terminator is used, a line
            // break will occur.
            for ( index = 0 ; index < text.length() ; ++index ) {
                ch = text.charAt( index );
                if ( ch == '\n' || ch == '\r' || unescaped )
                    _printer.printText( ch );
                else
                    printEscaped( ch );
            }
        } else {
            // Not preserving spaces: print one part at a time, and
            // use spaces between parts to break them into different
            // lines. Spaces at beginning of line will be stripped
            // by printing mechanism. Line terminator is treated
            // no different than other text part.
            for ( index = 0 ; index < text.length() ; ++index ) {
                ch = text.charAt( index );
                if ( ch == ' ' || ch == '\f' || ch == '\t' || ch == '\n' || ch == '\r' )
                    _printer.printSpace();
                else if ( unescaped )
                    _printer.printText( ch );
                else
                    printEscaped( ch );
            }
        }
    }


    /**
     * Print a document type public or system identifier URL.
     * Encapsulates the URL in double quotes, escapes non-printing
     * characters and print it equivalent to {@link #printText(char[], int, int, boolean, boolean)}.
     *
     * @param url The document type url to print
     */
    protected void printDoctypeURL( String url )
        throws IOException
    {
        int                i;

        _printer.printText( '"' );
        for( i = 0 ; i < url.length() ; ++i ) {
            if ( url.charAt( i ) == '"' ||  url.charAt( i ) < 0x20 || url.charAt( i ) > 0x7F ) {
                _printer.printText( '%' );
                _printer.printText( Integer.toHexString( url.charAt( i ) ) );
            } else
                _printer.printText( url.charAt( i ) );
        }
        _printer.printText( '"' );
    }


    protected void printEscaped( int ch )
        throws IOException
    {
        String charRef;

        // If there is a suitable entity reference for this
        // character, print it. The list of available entity
        // references is almost but not identical between
        // XML and HTML.
        charRef = getEntityRef( ch );
        if ( charRef != null ) {
            _printer.printText( '&' );
            _printer.printText( charRef );
            _printer.printText( ';' );
        } else if ( ( ch >= ' ' && _encodingInfo.isPrintable(ch) && ch != 0xF7 ) ||
                    ch == '\n' || ch == '\r' || ch == '\t' ) {
            // If the character is not printable, print as character reference.
            // Non printables are below ASCII space but not tab or line
            // terminator, ASCII delete, or above a certain Unicode threshold.
            if (ch < 0x10000) {
                _printer.printText((char)ch );
            } else {
                _printer.printText((char)(((ch-0x10000)>>10)+0xd800));
                _printer.printText((char)(((ch-0x10000)&0x3ff)+0xdc00));
            }

        } else {
            _printer.printText( "&#x" );
            _printer.printText(Integer.toHexString(ch));
            _printer.printText( ';' );
        }
    }


    /**
     * Escapes a string so it may be printed as text content or attribute
     * value. Non printable characters are escaped using character references.
     * Where the format specifies a deault entity reference, that reference
     * is used (e.g. <tt>&amp;lt;</tt>).
     *
     * @param source The string to escape
     */
    protected void printEscaped( String source )
        throws IOException
    {
        for ( int i = 0 ; i < source.length() ; ++i ) {
            int ch = source.charAt(i);
            if ((ch & 0xfc00) == 0xd800 && i+1 < source.length()) {
                int lowch = source.charAt(i+1);
                if ((lowch & 0xfc00) == 0xdc00) {
                    ch = 0x10000 + ((ch-0xd800)<<10) + lowch-0xdc00;
                    i++;
                }
            }
            printEscaped(ch);
        }
    }


    //--------------------------------//
    // Element state handling methods //
    //--------------------------------//


    /**
     * Return the state of the current element.
     *
     * @return Current element state
     */
    protected ElementState getElementState()
    {
        return _elementStates[ _elementStateCount ];
    }


    /**
     * Enter a new element state for the specified element.
     * Tag name and space preserving is specified, element
     * state is initially empty.
     *
     * @return Current element state, or null
     */
    protected ElementState enterElementState( String namespaceURI, String localName,
                                              String rawName, boolean preserveSpace )
    {
        ElementState state;

        if ( _elementStateCount + 1 == _elementStates.length ) {
            ElementState[] newStates;

            // Need to create a larger array of states. This does not happen
            // often, unless the document is really deep.
            newStates = new ElementState[ _elementStates.length + 10 ];
            for ( int i = 0 ; i < _elementStates.length ; ++i )
                newStates[ i ] = _elementStates[ i ];
            for ( int i = _elementStates.length ; i < newStates.length ; ++i )
                newStates[ i ] = new ElementState();
            _elementStates = newStates;
        }

        ++_elementStateCount;
        state = _elementStates[ _elementStateCount ];
        state.namespaceURI = namespaceURI;
        state.localName = localName;
        state.rawName = rawName;
        state.preserveSpace = preserveSpace;
        state.empty = true;
        state.afterElement = false;
        state.afterComment = false;
        state.doCData = state.inCData = false;
        state.unescaped = false;
        state.prefixes = _prefixes;

        _prefixes = null;
        return state;
    }


    /**
     * Leave the current element state and return to the
     * state of the parent element. If this was the root
     * element, return to the state of the document.
     *
     * @return Previous element state
     */
    protected ElementState leaveElementState()
    {
        if ( _elementStateCount > 0 ) {
            /*Corrected by David Blondeau ([e-mail])*/
		_prefixes = null;
		//_prefixes = _elementStates[ _elementStateCount ].prefixes;
            -- _elementStateCount;
            return _elementStates[ _elementStateCount ];
        } else
            throw new IllegalStateException( "Internal error: element state is zero" );
    }


    /**
     * Returns true if in the state of the document.
     * Returns true before entering any element and after
     * leaving the root element.
     *
     * @return True if in the state of the document
     */
    protected boolean isDocumentState()
    {
        return _elementStateCount == 0;
    }


    /**
     * Returns the namespace prefix for the specified URI.
     * If the URI has been mapped to a prefix, returns the
     * prefix, otherwise returns null.
     *
     * @param namespaceURI The namespace URI
     * @return The namespace prefix if known, or null
     */
    protected String getPrefix( String namespaceURI )
    {
        String    prefix;

        if ( _prefixes != null ) {
            prefix = (String) _prefixes.get( namespaceURI );
            if ( prefix != null )
                return prefix;
        }
        if ( _elementStateCount == 0 )
            return null;
        else {
            for ( int i = _elementStateCount ; i > 0 ; --i ) {
                if ( _elementStates[ i ].prefixes != null ) {
                    prefix = (String) _elementStates[ i ].prefixes.get( namespaceURI );
                    if ( prefix != null )
                        return prefix;
                }
            }
        }
        return null;
    }


}