| Classes in this File | Line Coverage | Branch Coverage | Complexity | ||||
| UnicodeEscaper |
|
| 2.375;2.375 |
| 1 | /* | |
| 2 | * Licensed to the Apache Software Foundation (ASF) under one or more | |
| 3 | * contributor license agreements. See the NOTICE file distributed with | |
| 4 | * this work for additional information regarding copyright ownership. | |
| 5 | * The ASF licenses this file to You under the Apache License, Version 2.0 | |
| 6 | * (the "License"); you may not use this file except in compliance with | |
| 7 | * the License. You may obtain a copy of the License at | |
| 8 | * | |
| 9 | * http://www.apache.org/licenses/LICENSE-2.0 | |
| 10 | * | |
| 11 | * Unless required by applicable law or agreed to in writing, software | |
| 12 | * distributed under the License is distributed on an "AS IS" BASIS, | |
| 13 | * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. | |
| 14 | * See the License for the specific language governing permissions and | |
| 15 | * limitations under the License. | |
| 16 | */ | |
| 17 | package org.apache.commons.lang3.text.translate; | |
| 18 | ||
| 19 | import java.io.IOException; | |
| 20 | import java.io.Writer; | |
| 21 | ||
| 22 | /** | |
| 23 | * Translates codepoints to their Unicode escaped value. | |
| 24 | * | |
| 25 | * @since 3.0 | |
| 26 | * @version $Id: UnicodeEscaper.java 1448287 2013-02-20 16:47:42Z tn $ | |
| 27 | */ | |
| 28 | public class UnicodeEscaper extends CodePointTranslator { | |
| 29 | ||
| 30 | private final int below; | |
| 31 | private final int above; | |
| 32 | private final boolean between; | |
| 33 | ||
| 34 | /** | |
| 35 | * <p>Constructs a <code>UnicodeEscaper</code> for all characters. </p> | |
| 36 | */ | |
| 37 | public UnicodeEscaper(){ | |
| 38 | 0 | this(0, Integer.MAX_VALUE, true); |
| 39 | 0 | } |
| 40 | ||
| 41 | /** | |
| 42 | * <p>Constructs a <code>UnicodeEscaper</code> for the specified range. This is | |
| 43 | * the underlying method for the other constructors/builders. The <code>below</code> | |
| 44 | * and <code>above</code> boundaries are inclusive when <code>between</code> is | |
| 45 | * <code>true</code> and exclusive when it is <code>false</code>. </p> | |
| 46 | * | |
| 47 | * @param below int value representing the lowest codepoint boundary | |
| 48 | * @param above int value representing the highest codepoint boundary | |
| 49 | * @param between whether to escape between the boundaries or outside them | |
| 50 | */ | |
| 51 | 5 | protected UnicodeEscaper(final int below, final int above, final boolean between) { |
| 52 | 5 | this.below = below; |
| 53 | 5 | this.above = above; |
| 54 | 5 | this.between = between; |
| 55 | 5 | } |
| 56 | ||
| 57 | /** | |
| 58 | * <p>Constructs a <code>UnicodeEscaper</code> below the specified value (exclusive). </p> | |
| 59 | * | |
| 60 | * @param codepoint below which to escape | |
| 61 | * @return the newly created {@code UnicodeEscaper} instance | |
| 62 | */ | |
| 63 | public static UnicodeEscaper below(final int codepoint) { | |
| 64 | 1 | return outsideOf(codepoint, Integer.MAX_VALUE); |
| 65 | } | |
| 66 | ||
| 67 | /** | |
| 68 | * <p>Constructs a <code>UnicodeEscaper</code> above the specified value (exclusive). </p> | |
| 69 | * | |
| 70 | * @param codepoint above which to escape | |
| 71 | * @return the newly created {@code UnicodeEscaper} instance | |
| 72 | */ | |
| 73 | public static UnicodeEscaper above(final int codepoint) { | |
| 74 | 1 | return outsideOf(0, codepoint); |
| 75 | } | |
| 76 | ||
| 77 | /** | |
| 78 | * <p>Constructs a <code>UnicodeEscaper</code> outside of the specified values (exclusive). </p> | |
| 79 | * | |
| 80 | * @param codepointLow below which to escape | |
| 81 | * @param codepointHigh above which to escape | |
| 82 | * @return the newly created {@code UnicodeEscaper} instance | |
| 83 | */ | |
| 84 | public static UnicodeEscaper outsideOf(final int codepointLow, final int codepointHigh) { | |
| 85 | 2 | return new UnicodeEscaper(codepointLow, codepointHigh, false); |
| 86 | } | |
| 87 | ||
| 88 | /** | |
| 89 | * <p>Constructs a <code>UnicodeEscaper</code> between the specified values (inclusive). </p> | |
| 90 | * | |
| 91 | * @param codepointLow above which to escape | |
| 92 | * @param codepointHigh below which to escape | |
| 93 | * @return the newly created {@code UnicodeEscaper} instance | |
| 94 | */ | |
| 95 | public static UnicodeEscaper between(final int codepointLow, final int codepointHigh) { | |
| 96 | 1 | return new UnicodeEscaper(codepointLow, codepointHigh, true); |
| 97 | } | |
| 98 | ||
| 99 | /** | |
| 100 | * {@inheritDoc} | |
| 101 | */ | |
| 102 | @Override | |
| 103 | public boolean translate(final int codepoint, final Writer out) throws IOException { | |
| 104 | 4318 | if (between) { |
| 105 | 5 | if (codepoint < below || codepoint > above) { |
| 106 | 3 | return false; |
| 107 | } | |
| 108 | } else { | |
| 109 | 4313 | if (codepoint >= below && codepoint <= above) { |
| 110 | 3719 | return false; |
| 111 | } | |
| 112 | } | |
| 113 | ||
| 114 | // TODO: Handle potential + sign per various Unicode escape implementations | |
| 115 | 596 | if (codepoint > 0xffff) { |
| 116 | 12 | out.write(toUtf16Escape(codepoint)); |
| 117 | 584 | } else if (codepoint > 0xfff) { |
| 118 | 97 | out.write("\\u" + hex(codepoint)); |
| 119 | 487 | } else if (codepoint > 0xff) { |
| 120 | 436 | out.write("\\u0" + hex(codepoint)); |
| 121 | 51 | } else if (codepoint > 0xf) { |
| 122 | 49 | out.write("\\u00" + hex(codepoint)); |
| 123 | } else { | |
| 124 | 2 | out.write("\\u000" + hex(codepoint)); |
| 125 | } | |
| 126 | 596 | return true; |
| 127 | } | |
| 128 | ||
| 129 | /** | |
| 130 | * Converts the given codepoint to a hex string of the form {@code "\\uXXXX"} | |
| 131 | * | |
| 132 | * @param codepoint | |
| 133 | * a Unicode code point | |
| 134 | * @return the hex string for the given codepoint | |
| 135 | */ | |
| 136 | protected String toUtf16Escape(final int codepoint) { | |
| 137 | 0 | return "\\u" + hex(codepoint); |
| 138 | } | |
| 139 | } |