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.UncheckedIOException; 022import java.io.Writer; 023import java.util.Locale; 024import java.util.Objects; 025 026/** 027 * An API for translating text. 028 * Its core use is to escape and unescape text. Because escaping and unescaping 029 * is completely contextual, the API does not present two separate signatures. 030 * 031 * @since 3.0 032 * @deprecated As of 3.6, use Apache Commons Text 033 * <a href="https://commons.apache.org/proper/commons-text/javadocs/api-release/org/apache/commons/text/translate/CharSequenceTranslator.html"> 034 * CharSequenceTranslator</a> instead 035 */ 036@Deprecated 037public abstract class CharSequenceTranslator { 038 039 static final char[] HEX_DIGITS = {'0', '1', '2', '3', '4', '5', '6', '7', '8', '9', 'A', 'B', 'C', 'D', 'E', 'F'}; 040 041 /** 042 * Translate a set of code points, represented by an int index into a CharSequence, 043 * into another set of code points. The number of code points consumed must be returned, 044 * and the only IOExceptions thrown must be from interacting with the Writer so that 045 * the top level API may reliably ignore StringWriter IOExceptions. 046 * 047 * @param input CharSequence that is being translated 048 * @param index int representing the current point of translation 049 * @param out Writer to translate the text to 050 * @return int count of code points consumed 051 * @throws IOException if and only if the Writer produces an IOException 052 */ 053 public abstract int translate(CharSequence input, int index, Writer out) throws IOException; 054 055 /** 056 * Helper for non-Writer usage. 057 * @param input CharSequence to be translated 058 * @return String output of translation 059 */ 060 public final String translate(final CharSequence input) { 061 if (input == null) { 062 return null; 063 } 064 try { 065 final StringWriter writer = new StringWriter(input.length() * 2); 066 translate(input, writer); 067 return writer.toString(); 068 } catch (final IOException ioe) { 069 // this should never ever happen while writing to a StringWriter 070 throw new UncheckedIOException(ioe); 071 } 072 } 073 074 /** 075 * Translate an input onto a Writer. This is intentionally final as its algorithm is 076 * tightly coupled with the abstract method of this class. 077 * 078 * @param input CharSequence that is being translated 079 * @param writer Writer to translate the text to 080 * @throws IOException if and only if the Writer produces an IOException 081 */ 082 public final void translate(final CharSequence input, final Writer writer) throws IOException { 083 Objects.requireNonNull(writer, "writer"); 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, writer); 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 writer.write(c1); 096 pos++; 097 if (Character.isHighSurrogate(c1) && pos < len) { 098 final char c2 = input.charAt(pos); 099 if (Character.isLowSurrogate(c2)) { 100 writer.write(c2); 101 pos++; 102 } 103 } 104 continue; 105 } 106 // contract with translators is that they have to understand code points 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 * Returns an upper case hexadecimal {@link String} for the given 130 * character. 131 * 132 * @param codePoint The code point to convert. 133 * @return An upper case hexadecimal {@link String} 134 */ 135 public static String hex(final int codePoint) { 136 return Integer.toHexString(codePoint).toUpperCase(Locale.ENGLISH); 137 } 138 139}