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 * https://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 */ 017package org.apache.commons.lang3.text.translate; 018 019import java.io.IOException; 020import java.io.StringWriter; 021import java.io.UncheckedIOException; 022import java.io.Writer; 023import java.util.Locale; 024import java.util.Objects; 025 026import org.apache.commons.lang3.ArrayUtils; 027 028/** 029 * An API for translating text. 030 * Its core use is to escape and unescape text. Because escaping and unescaping 031 * is completely contextual, the API does not present two separate signatures. 032 * 033 * @since 3.0 034 * @deprecated As of <a href="https://commons.apache.org/proper/commons-lang/changes-report.html#a3.6">3.6</a>, use Apache Commons Text 035 * <a href="https://commons.apache.org/proper/commons-text/javadocs/api-release/org/apache/commons/text/translate/CharSequenceTranslator.html"> 036 * CharSequenceTranslator</a>. 037 */ 038@Deprecated 039public abstract class CharSequenceTranslator { 040 041 static final char[] HEX_DIGITS = {'0', '1', '2', '3', '4', '5', '6', '7', '8', '9', 'A', 'B', 'C', 'D', 'E', 'F'}; 042 043 /** 044 * Returns an upper case hexadecimal {@link String} for the given 045 * character. 046 * 047 * @param codePoint The code point to convert. 048 * @return An upper case hexadecimal {@link String}. 049 */ 050 public static String hex(final int codePoint) { 051 return Integer.toHexString(codePoint).toUpperCase(Locale.ENGLISH); 052 } 053 054 /** 055 * Constructs a new instance. 056 */ 057 public CharSequenceTranslator() { 058 // empty 059 } 060 061 /** 062 * Helper for non-Writer usage. 063 * 064 * @param input CharSequence to be translated. 065 * @return String output of translation. 066 */ 067 public final String translate(final CharSequence input) { 068 if (input == null) { 069 return null; 070 } 071 try { 072 final StringWriter writer = new StringWriter(input.length() * 2); 073 translate(input, writer); 074 return writer.toString(); 075 } catch (final IOException ioe) { 076 // this should never ever happen while writing to a StringWriter 077 throw new UncheckedIOException(ioe); 078 } 079 } 080 081 /** 082 * Translate a set of code points, represented by an int index into a CharSequence, 083 * into another set of code points. The number of code points consumed must be returned, 084 * and the only IOExceptions thrown must be from interacting with the Writer so that 085 * the top level API may reliably ignore StringWriter IOExceptions. 086 * 087 * @param input CharSequence that is being translated. 088 * @param index int representing the current point of translation. 089 * @param out Writer to translate the text to. 090 * @return int count of code points consumed. 091 * @throws IOException if and only if the Writer produces an IOException. 092 */ 093 public abstract int translate(CharSequence input, int index, Writer out) throws IOException; 094 095 /** 096 * Translate an input onto a Writer. This is intentionally final as its algorithm is 097 * tightly coupled with the abstract method of this class. 098 * 099 * @param input CharSequence that is being translated. 100 * @param writer Writer to translate the text to. 101 * @throws IOException if and only if the Writer produces an IOException. 102 */ 103 @SuppressWarnings("resource") // Caller closes writer 104 public final void translate(final CharSequence input, final Writer writer) throws IOException { 105 Objects.requireNonNull(writer, "writer"); 106 if (input == null) { 107 return; 108 } 109 int pos = 0; 110 final int len = input.length(); 111 while (pos < len) { 112 final int consumed = translate(input, pos, writer); 113 if (consumed == 0) { 114 // inlined implementation of Character.toChars(Character.codePointAt(input, pos)) 115 // avoids allocating temp char arrays and duplicate checks 116 final char c1 = input.charAt(pos); 117 writer.write(c1); 118 pos++; 119 if (Character.isHighSurrogate(c1) && pos < len) { 120 final char c2 = input.charAt(pos); 121 if (Character.isLowSurrogate(c2)) { 122 writer.write(c2); 123 pos++; 124 } 125 } 126 continue; 127 } 128 // contract with translators is that they have to understand code points 129 // and they just took care of a surrogate pair 130 for (int pt = 0; pt < consumed; pt++) { 131 pos += Character.charCount(Character.codePointAt(input, pos)); 132 } 133 } 134 } 135 136 /** 137 * Helper method to create a merger of this translator with another set of 138 * translators. Useful in customizing the standard functionality. 139 * 140 * @param translators CharSequenceTranslator array of translators to merge with this one. 141 * @return CharSequenceTranslator merging this translator with the others. 142 */ 143 public final CharSequenceTranslator with(final CharSequenceTranslator... translators) { 144 final CharSequenceTranslator[] newArray = new CharSequenceTranslator[translators.length + 1]; 145 newArray[0] = this; 146 return new AggregateTranslator(ArrayUtils.arraycopy(translators, 0, newArray, 1, translators.length)); 147 } 148 149}