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 * https://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 code points to their Unicode escaped value.
24 *
25 * @since 3.0
26 * @deprecated As of <a href="https://commons.apache.org/proper/commons-lang/changes-report.html#a3.6">3.6</a>, use Apache Commons Text
27 * <a href="https://commons.apache.org/proper/commons-text/javadocs/api-release/org/apache/commons/text/translate/UnicodeEscaper.html">
28 * UnicodeEscaper</a>.
29 */
30 @Deprecated
31 public class UnicodeEscaper extends CodePointTranslator {
32
33 /**
34 * Constructs a {@link UnicodeEscaper} above the specified value (exclusive).
35 *
36 * @param codePoint above which to escape.
37 * @return The newly created {@link UnicodeEscaper} instance.
38 */
39 public static UnicodeEscaper above(final int codePoint) {
40 return outsideOf(0, codePoint);
41 }
42
43 /**
44 * Constructs a {@link UnicodeEscaper} below the specified value (exclusive).
45 *
46 * @param codePoint below which to escape.
47 * @return The newly created {@link UnicodeEscaper} instance.
48 */
49 public static UnicodeEscaper below(final int codePoint) {
50 return outsideOf(codePoint, Integer.MAX_VALUE);
51 }
52
53 /**
54 * Constructs a {@link UnicodeEscaper} between the specified values (inclusive).
55 *
56 * @param codePointLow above which to escape.
57 * @param codePointHigh below which to escape.
58 * @return The newly created {@link UnicodeEscaper} instance.
59 */
60 public static UnicodeEscaper between(final int codePointLow, final int codePointHigh) {
61 return new UnicodeEscaper(codePointLow, codePointHigh, true);
62 }
63
64 /**
65 * Constructs a {@link UnicodeEscaper} outside of the specified values (exclusive).
66 *
67 * @param codePointLow below which to escape.
68 * @param codePointHigh above which to escape.
69 * @return The newly created {@link UnicodeEscaper} instance.
70 */
71 public static UnicodeEscaper outsideOf(final int codePointLow, final int codePointHigh) {
72 return new UnicodeEscaper(codePointLow, codePointHigh, false);
73 }
74
75 private final int below;
76
77 private final int above;
78
79 private final boolean between;
80
81 /**
82 * Constructs a {@link UnicodeEscaper} for all characters.
83 */
84 public UnicodeEscaper() {
85 this(0, Integer.MAX_VALUE, true);
86 }
87
88 /**
89 * Constructs a {@link UnicodeEscaper} for the specified range. This is
90 * the underlying method for the other constructors/builders. The {@code below}
91 * and {@code above} boundaries are inclusive when {@code between} is
92 * {@code true} and exclusive when it is {@code false}.
93 *
94 * @param below int value representing the lowest code point boundary.
95 * @param above int value representing the highest code point boundary.
96 * @param between whether to escape between the boundaries or outside them.
97 */
98 protected UnicodeEscaper(final int below, final int above, final boolean between) {
99 this.below = below;
100 this.above = above;
101 this.between = between;
102 }
103
104 /**
105 * Converts the given code point to a hexadecimal string of the form {@code "\\uXXXX"}, or the
106 * surrogate pair form {@code "\\uXXXX\\uXXXX"} for a supplementary code point.
107 *
108 * @param codePoint
109 * a Unicode code point.
110 * @return The hexadecimal string for the given code point.
111 * @since 3.2
112 */
113 protected String toUtf16Escape(final int codePoint) {
114 if (Character.isBmpCodePoint(codePoint)) {
115 return "\\u" + hex(codePoint);
116 }
117 final char[] surrogatePair = Character.toChars(codePoint);
118 return "\\u" + hex(surrogatePair[0]) + "\\u" + hex(surrogatePair[1]);
119 }
120
121 /**
122 * {@inheritDoc}
123 */
124 @Override
125 public boolean translate(final int codePoint, final Writer out) throws IOException {
126 if (between) {
127 if (codePoint < below || codePoint > above) {
128 return false;
129 }
130 } else if (codePoint >= below && codePoint <= above) {
131 return false;
132 }
133
134 // TODO: Handle potential + sign per various Unicode escape implementations
135 if (codePoint > 0xffff) {
136 out.write(toUtf16Escape(codePoint));
137 } else {
138 out.write("\\u");
139 out.write(HEX_DIGITS[codePoint >> 12 & 15]);
140 out.write(HEX_DIGITS[codePoint >> 8 & 15]);
141 out.write(HEX_DIGITS[codePoint >> 4 & 15]);
142 out.write(HEX_DIGITS[codePoint & 15]);
143 }
144 return true;
145 }
146 }