001/*
002 * Licensed to the Apache Software Foundation (ASF) under one or more
003 * contributor license agreements.  See the NOTICE file distributed with
004 * this work for additional information regarding copyright ownership.
005 * The ASF licenses this file to You under the Apache License, Version 2.0
006 * (the "License"); you may not use this file except in compliance with
007 * the License.  You may obtain a copy of the License at
008 *
009 *      http://www.apache.org/licenses/LICENSE-2.0
010 *
011 * Unless required by applicable law or agreed to in writing, software
012 * distributed under the License is distributed on an "AS IS" BASIS,
013 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
014 * See the License for the specific language governing permissions and
015 * limitations under the License.
016 */
017package org.apache.commons.lang3.text.translate;
018
019import java.io.IOException;
020import java.io.Writer;
021
022/**
023 * Translates codepoints to their Unicode escaped value.
024 *
025 * @since 3.0
026 */
027public class UnicodeEscaper extends CodePointTranslator {
028
029    private final int below;
030    private final int above;
031    private final boolean between;
032
033    /**
034     * <p>Constructs a <code>UnicodeEscaper</code> for all characters. </p>
035     */
036    public UnicodeEscaper(){
037        this(0, Integer.MAX_VALUE, true);
038    }
039
040    /**
041     * <p>Constructs a <code>UnicodeEscaper</code> for the specified range. This is
042     * the underlying method for the other constructors/builders. The <code>below</code>
043     * and <code>above</code> boundaries are inclusive when <code>between</code> is
044     * <code>true</code> and exclusive when it is <code>false</code>. </p>
045     *
046     * @param below int value representing the lowest codepoint boundary
047     * @param above int value representing the highest codepoint boundary
048     * @param between whether to escape between the boundaries or outside them
049     */
050    protected UnicodeEscaper(final int below, final int above, final boolean between) {
051        this.below = below;
052        this.above = above;
053        this.between = between;
054    }
055
056    /**
057     * <p>Constructs a <code>UnicodeEscaper</code> below the specified value (exclusive). </p>
058     *
059     * @param codepoint below which to escape
060     * @return the newly created {@code UnicodeEscaper} instance
061     */
062    public static UnicodeEscaper below(final int codepoint) {
063        return outsideOf(codepoint, Integer.MAX_VALUE);
064    }
065
066    /**
067     * <p>Constructs a <code>UnicodeEscaper</code> above the specified value (exclusive). </p>
068     *
069     * @param codepoint above which to escape
070     * @return the newly created {@code UnicodeEscaper} instance
071     */
072    public static UnicodeEscaper above(final int codepoint) {
073        return outsideOf(0, codepoint);
074    }
075
076    /**
077     * <p>Constructs a <code>UnicodeEscaper</code> outside of the specified values (exclusive). </p>
078     *
079     * @param codepointLow below which to escape
080     * @param codepointHigh above which to escape
081     * @return the newly created {@code UnicodeEscaper} instance
082     */
083    public static UnicodeEscaper outsideOf(final int codepointLow, final int codepointHigh) {
084        return new UnicodeEscaper(codepointLow, codepointHigh, false);
085    }
086
087    /**
088     * <p>Constructs a <code>UnicodeEscaper</code> between the specified values (inclusive). </p>
089     *
090     * @param codepointLow above which to escape
091     * @param codepointHigh below which to escape
092     * @return the newly created {@code UnicodeEscaper} instance
093     */
094    public static UnicodeEscaper between(final int codepointLow, final int codepointHigh) {
095        return new UnicodeEscaper(codepointLow, codepointHigh, true);
096    }
097
098    /**
099     * {@inheritDoc}
100     */
101    @Override
102    public boolean translate(final int codepoint, final Writer out) throws IOException {
103        if (between) {
104            if (codepoint < below || codepoint > above) {
105                return false;
106            }
107        } else {
108            if (codepoint >= below && codepoint <= above) {
109                return false;
110            }
111        }
112
113        // TODO: Handle potential + sign per various Unicode escape implementations
114        if (codepoint > 0xffff) {
115            out.write(toUtf16Escape(codepoint));
116        } else {
117          out.write("\\u");
118          out.write(HEX_DIGITS[(codepoint >> 12) & 15]);
119          out.write(HEX_DIGITS[(codepoint >> 8) & 15]);
120          out.write(HEX_DIGITS[(codepoint >> 4) & 15]);
121          out.write(HEX_DIGITS[(codepoint) & 15]);
122        }
123        return true;
124    }
125
126    /**
127     * Converts the given codepoint to a hex string of the form {@code "\\uXXXX"}
128     * 
129     * @param codepoint
130     *            a Unicode code point
131     * @return the hex string for the given codepoint
132     *
133     * @since 3.2
134     */
135    protected String toUtf16Escape(final int codepoint) {
136        return "\\u" + hex(codepoint);
137    }
138}