001 /*
002 * Licensed to the Apache Software Foundation (ASF) under one or more
003 * contributor license agreements. See the NOTICE file distributed with
004 * this work for additional information regarding copyright ownership.
005 * The ASF licenses this file to You under the Apache License, Version 2.0
006 * (the "License"); you may not use this file except in compliance with
007 * the License. You may obtain a copy of the License at
008 *
009 * http://www.apache.org/licenses/LICENSE-2.0
010 *
011 * Unless required by applicable law or agreed to in writing, software
012 * distributed under the License is distributed on an "AS IS" BASIS,
013 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
014 * See the License for the specific language governing permissions and
015 * limitations under the License.
016 */
017 package org.apache.commons.lang3.text.translate;
018
019 import java.io.IOException;
020 import java.io.StringWriter;
021 import java.io.Writer;
022 import java.util.Locale;
023
024 /**
025 * An API for translating text.
026 * Its core use is to escape and unescape text. Because escaping and unescaping
027 * is completely contextual, the API does not present two separate signatures.
028 *
029 * @since 3.0
030 * @version $Id: CharSequenceTranslator.java 1139924 2011-06-26 19:32:14Z mbenson $
031 */
032 public abstract class CharSequenceTranslator {
033
034 /**
035 * Translate a set of codepoints, represented by an int index into a CharSequence,
036 * into another set of codepoints. The number of codepoints consumed must be returned,
037 * and the only IOExceptions thrown must be from interacting with the Writer so that
038 * the top level API may reliable ignore StringWriter IOExceptions.
039 *
040 * @param input CharSequence that is being translated
041 * @param index int representing the current point of translation
042 * @param out Writer to translate the text to
043 * @return int count of codepoints consumed
044 * @throws IOException if and only if the Writer produces an IOException
045 */
046 public abstract int translate(CharSequence input, int index, Writer out) throws IOException;
047
048 /**
049 * Helper for non-Writer usage.
050 * @param input CharSequence to be translated
051 * @return String output of translation
052 */
053 public final String translate(CharSequence input) {
054 if (input == null) {
055 return null;
056 }
057 try {
058 StringWriter writer = new StringWriter(input.length() * 2);
059 translate(input, writer);
060 return writer.toString();
061 } catch (IOException ioe) {
062 // this should never ever happen while writing to a StringWriter
063 throw new RuntimeException(ioe);
064 }
065 }
066
067 /**
068 * Translate an input onto a Writer. This is intentionally final as its algorithm is
069 * tightly coupled with the abstract method of this class.
070 *
071 * @param input CharSequence that is being translated
072 * @param out Writer to translate the text to
073 * @throws IOException if and only if the Writer produces an IOException
074 */
075 public final void translate(CharSequence input, Writer out) throws IOException {
076 if (out == null) {
077 throw new IllegalArgumentException("The Writer must not be null");
078 }
079 if (input == null) {
080 return;
081 }
082 int sz = Character.codePointCount(input, 0, input.length());
083 for (int i = 0; i < sz; i++) {
084
085 // consumed is the number of codepoints consumed
086 int consumed = translate(input, i, out);
087
088 if (consumed == 0) {
089 out.write(Character.toChars(Character.codePointAt(input, i)));
090 } else {
091 // contract with translators is that they have to understand codepoints
092 // and they just took care of a surrogate pair
093 for (int j = 0; j < consumed; j++) {
094 if (i < sz - 2) {
095 i += Character.charCount(Character.codePointAt(input, i));
096 } else {
097 // If the String ends with a high surrogate, just add the 1 and don't worry about such things
098 i++;
099 }
100 }
101 // for loop will increment 1 anyway, so remove 1 to account for that
102 i--;
103 }
104 }
105 }
106
107 /**
108 * Helper method to create a merger of this translator with another set of
109 * translators. Useful in customizing the standard functionality.
110 *
111 * @param translators CharSequenceTranslator array of translators to merge with this one
112 * @return CharSequenceTranslator merging this translator with the others
113 */
114 public final CharSequenceTranslator with(CharSequenceTranslator... translators) {
115 CharSequenceTranslator[] newArray = new CharSequenceTranslator[translators.length + 1];
116 newArray[0] = this;
117 System.arraycopy(translators, 0, newArray, 1, translators.length);
118 return new AggregateTranslator(newArray);
119 }
120
121 /**
122 * <p>Returns an upper case hexadecimal <code>String</code> for the given
123 * character.</p>
124 *
125 * @param codepoint The codepoint to convert.
126 * @return An upper case hexadecimal <code>String</code>
127 */
128 public static String hex(int codepoint) {
129 return Integer.toHexString(codepoint).toUpperCase(Locale.ENGLISH);
130 }
131
132 }