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.StringWriter;
21 import java.io.UncheckedIOException;
22 import java.io.Writer;
23 import java.util.Locale;
24 import java.util.Objects;
25
26 import org.apache.commons.lang3.ArrayUtils;
27
28 /**
29 * An API for translating text.
30 * Its core use is to escape and unescape text. Because escaping and unescaping
31 * is completely contextual, the API does not present two separate signatures.
32 *
33 * @since 3.0
34 * @deprecated As of 3.6, use Apache Commons Text
35 * <a href="https://commons.apache.org/proper/commons-text/javadocs/api-release/org/apache/commons/text/translate/CharSequenceTranslator.html">
36 * CharSequenceTranslator</a> instead
37 */
38 @Deprecated
39 public abstract class CharSequenceTranslator {
40
41 static final char[] HEX_DIGITS = {'0', '1', '2', '3', '4', '5', '6', '7', '8', '9', 'A', 'B', 'C', 'D', 'E', 'F'};
42
43 /**
44 * Returns an upper case hexadecimal {@link String} for the given
45 * character.
46 *
47 * @param codePoint The code point to convert.
48 * @return An upper case hexadecimal {@link String}
49 */
50 public static String hex(final int codePoint) {
51 return Integer.toHexString(codePoint).toUpperCase(Locale.ENGLISH);
52 }
53
54 /**
55 * Constructs a new instance.
56 */
57 public CharSequenceTranslator() {
58 // empty
59 }
60
61 /**
62 * Helper for non-Writer usage.
63 * @param input CharSequence to be translated
64 * @return String output of translation
65 */
66 public final String translate(final CharSequence input) {
67 if (input == null) {
68 return null;
69 }
70 try {
71 final StringWriter writer = new StringWriter(input.length() * 2);
72 translate(input, writer);
73 return writer.toString();
74 } catch (final IOException ioe) {
75 // this should never ever happen while writing to a StringWriter
76 throw new UncheckedIOException(ioe);
77 }
78 }
79
80 /**
81 * Translate a set of code points, represented by an int index into a CharSequence,
82 * into another set of code points. The number of code points consumed must be returned,
83 * and the only IOExceptions thrown must be from interacting with the Writer so that
84 * the top level API may reliably ignore StringWriter IOExceptions.
85 *
86 * @param input CharSequence that is being translated
87 * @param index int representing the current point of translation
88 * @param out Writer to translate the text to
89 * @return int count of code points consumed
90 * @throws IOException if and only if the Writer produces an IOException
91 */
92 public abstract int translate(CharSequence input, int index, Writer out) throws IOException;
93
94 /**
95 * Translate an input onto a Writer. This is intentionally final as its algorithm is
96 * tightly coupled with the abstract method of this class.
97 *
98 * @param input CharSequence that is being translated
99 * @param writer Writer to translate the text to
100 * @throws IOException if and only if the Writer produces an IOException
101 */
102 @SuppressWarnings("resource") // Caller closes writer
103 public final void translate(final CharSequence input, final Writer writer) throws IOException {
104 Objects.requireNonNull(writer, "writer");
105 if (input == null) {
106 return;
107 }
108 int pos = 0;
109 final int len = input.length();
110 while (pos < len) {
111 final int consumed = translate(input, pos, writer);
112 if (consumed == 0) {
113 // inlined implementation of Character.toChars(Character.codePointAt(input, pos))
114 // avoids allocating temp char arrays and duplicate checks
115 final char c1 = input.charAt(pos);
116 writer.write(c1);
117 pos++;
118 if (Character.isHighSurrogate(c1) && pos < len) {
119 final char c2 = input.charAt(pos);
120 if (Character.isLowSurrogate(c2)) {
121 writer.write(c2);
122 pos++;
123 }
124 }
125 continue;
126 }
127 // contract with translators is that they have to understand code points
128 // and they just took care of a surrogate pair
129 for (int pt = 0; pt < consumed; pt++) {
130 pos += Character.charCount(Character.codePointAt(input, pos));
131 }
132 }
133 }
134
135 /**
136 * Helper method to create a merger of this translator with another set of
137 * translators. Useful in customizing the standard functionality.
138 *
139 * @param translators CharSequenceTranslator array of translators to merge with this one
140 * @return CharSequenceTranslator merging this translator with the others
141 */
142 public final CharSequenceTranslator with(final CharSequenceTranslator... translators) {
143 final CharSequenceTranslator[] newArray = new CharSequenceTranslator[translators.length + 1];
144 newArray[0] = this;
145 return new AggregateTranslator(ArrayUtils.arraycopy(translators, 0, newArray, 1, translators.length));
146 }
147
148 }