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