001    /*
002     * Copyright (c) 2008-2010 Mozilla Foundation
003     *
004     * Permission is hereby granted, free of charge, to any person obtaining a 
005     * copy of this software and associated documentation files (the "Software"), 
006     * to deal in the Software without restriction, including without limitation 
007     * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
008     * and/or sell copies of the Software, and to permit persons to whom the 
009     * Software is furnished to do so, subject to the following conditions:
010     *
011     * The above copyright notice and this permission notice shall be included in 
012     * all copies or substantial portions of the Software.
013     *
014     * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
015     * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
016     * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
017     * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
018     * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
019     * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
020     * DEALINGS IN THE SOFTWARE.
021     */
022    
023    package nu.validator.htmlparser.impl;
024    
025    import nu.validator.htmlparser.annotation.NoLength;
026    
027    /**
028     * An UTF-16 buffer that knows the start and end indeces of its unconsumed
029     * content.
030     * 
031     * @version $Id$
032     * @author hsivonen
033     */
034    public final class UTF16Buffer {
035    
036        /**
037         * The backing store of the buffer. May be larger than the logical content
038         * of this <code>UTF16Buffer</code>.
039         */
040        private final @NoLength char[] buffer;
041    
042        /**
043         * The index of the first unconsumed character in the backing buffer.
044         */
045        private int start;
046    
047        /**
048         * The index of the slot immediately after the last character in the backing
049         * buffer that is part of the logical content of this
050         * <code>UTF16Buffer</code>.
051         */
052        private int end;
053    
054        /**
055         * Constructor for wrapping an existing UTF-16 code unit array.
056         * 
057         * @param buffer
058         *            the backing buffer
059         * @param start
060         *            the index of the first character to consume
061         * @param end
062         *            the index immediately after the last character to consume
063         */
064        public UTF16Buffer(@NoLength char[] buffer, int start, int end) {
065            this.buffer = buffer;
066            this.start = start;
067            this.end = end;
068        }
069    
070        /**
071         * Returns the start index.
072         * 
073         * @return the start index
074         */
075        public int getStart() {
076            return start;
077        }
078    
079        /**
080         * Sets the start index.
081         * 
082         * @param start
083         *            the start index
084         */
085        public void setStart(int start) {
086            this.start = start;
087        }
088    
089        /**
090         * Returns the backing buffer.
091         * 
092         * @return the backing buffer
093         */
094        public @NoLength char[] getBuffer() {
095            return buffer;
096        }
097    
098        /**
099         * Returns the end index.
100         * 
101         * @return the end index
102         */
103        public int getEnd() {
104            return end;
105        }
106    
107        /**
108         * Checks if the buffer has data left.
109         * 
110         * @return <code>true</code> if there's data left
111         */
112        public boolean hasMore() {
113            return start < end;
114        }
115    
116        /**
117         * Adjusts the start index to skip over the first character if it is a line
118         * feed and the previous character was a carriage return.
119         * 
120         * @param lastWasCR
121         *            whether the previous character was a carriage return
122         */
123        public void adjust(boolean lastWasCR) {
124            if (lastWasCR && buffer[start] == '\n') {
125                start++;
126            }
127        }
128    
129        /**
130         * Sets the end index.
131         * 
132         * @param end
133         *            the end index
134         */
135        public void setEnd(int end) {
136            this.end = end;
137        }
138    }