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
18 package org.apache.commons.text.translate;
19
20 import java.io.IOException;
21 import java.io.StringWriter;
22 import java.io.UncheckedIOException;
23 import java.io.Writer;
24 import java.util.Locale;
25
26 import org.apache.commons.lang3.Validate;
27
28 /**
29 * An API for translating text. Its core use is to escape and unescape text. Because escaping and unescaping is completely contextual, the API does not present
30 * two separate signatures.
31 *
32 * @since 1.0
33 */
34 public abstract class CharSequenceTranslator {
35
36 /**
37 * Array containing the hexadecimal alphabet.
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 {@code String} for the given character.
43 *
44 * @param codePoint The code point to convert.
45 * @return An upper case hexadecimal {@code String}
46 */
47 public static String hex(final int codePoint) {
48 return Integer.toHexString(codePoint).toUpperCase(Locale.ENGLISH);
49 }
50
51 /**
52 * Construct a new instance.
53 */
54 public CharSequenceTranslator() {
55 // empty
56 }
57
58 /**
59 * Translates an input. This is intentionally final as its algorithm is tightly coupled with the abstract method of this class.
60 *
61 * @param input CharSequence to be translated.
62 * @return String output of translation.
63 */
64 public final String translate(final CharSequence input) {
65 if (input == null) {
66 return null;
67 }
68 try {
69 final StringWriter writer = new StringWriter(input.length() * 2);
70 translate(input, writer);
71 return writer.toString();
72 } catch (final IOException ioe) {
73 // this should never ever happen while writing to a StringWriter
74 throw new UncheckedIOException(ioe);
75 }
76 }
77
78 /**
79 * Translates a set of code points, represented by an int index into a CharSequence, into another set of code points. The number of code points consumed
80 * must be returned, and the only IOExceptions thrown must be from interacting with the Writer so that the top level API may reliably ignore StringWriter
81 * IOExceptions.
82 *
83 * @param input CharSequence that is being translated.
84 * @param index int representing the current point of translation.
85 * @param writer Writer to translate the text to.
86 * @return int count of code points consumed.
87 * @throws IOException Thrown if and only if the Writer produces an IOException.
88 */
89 public abstract int translate(CharSequence input, int index, Writer writer) throws IOException;
90
91 /**
92 * Translates an input onto a Writer. This is intentionally final as its algorithm is tightly coupled with the abstract method of this class.
93 *
94 * @param input CharSequence that is being translated.
95 * @param writer Writer to translate the text to.
96 * @throws IOException Thrown if and only if the Writer produces an IOException.
97 */
98 public final void translate(final CharSequence input, final Writer writer) throws IOException {
99 Validate.isTrue(writer != null, "The Writer must not be null");
100 if (input == null) {
101 return;
102 }
103 int pos = 0;
104 final int len = input.length();
105 while (pos < len) {
106 final int consumed = translate(input, pos, writer);
107 if (consumed == 0) {
108 // inlined implementation of Character.toChars(Character.codePointAt(input, pos))
109 // avoids allocating temp char arrays and duplicate checks
110 final char c1 = input.charAt(pos);
111 writer.write(c1);
112 pos++;
113 if (Character.isHighSurrogate(c1) && pos < len) {
114 final char c2 = input.charAt(pos);
115 if (Character.isLowSurrogate(c2)) {
116 writer.write(c2);
117 pos++;
118 }
119 }
120 continue;
121 }
122 // contract with translators is that they have to understand code points
123 // and they just took care of a surrogate pair
124 for (int pt = 0; pt < consumed; pt++) {
125 pos += Character.charCount(Character.codePointAt(input, pos));
126 }
127 }
128 }
129
130 /**
131 * Creates a merger of this translator with another set of translators. Useful in customizing the standard functionality.
132 *
133 * @param translators CharSequenceTranslator array of translators to merge with this one.
134 * @return CharSequenceTranslator merging this translator with the others.
135 */
136 public final CharSequenceTranslator with(final CharSequenceTranslator... translators) {
137 final CharSequenceTranslator[] newArray = new CharSequenceTranslator[translators.length + 1];
138 newArray[0] = this;
139 System.arraycopy(translators, 0, newArray, 1, translators.length);
140 return new AggregateTranslator(newArray);
141 }
142 }