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