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.text.translate; 018 019import java.io.IOException; 020import java.io.StringWriter; 021import java.io.UncheckedIOException; 022import java.io.Writer; 023import java.util.Locale; 024 025import org.apache.commons.lang3.Validate; 026 027/** 028 * An API for translating text. 029 * Its core use is to escape and unescape text. Because escaping and unescaping 030 * is completely contextual, the API does not present two separate signatures. 031 * 032 * @since 1.0 033 */ 034public abstract class CharSequenceTranslator { 035 036 /** 037 * Array containing the hexadecimal alphabet. 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 * Returns an upper case hexadecimal {@code String} for the given 043 * character. 044 * 045 * @param codePoint The code point to convert. 046 * @return An upper case hexadecimal {@code String} 047 */ 048 public static String hex(final int codePoint) { 049 return Integer.toHexString(codePoint).toUpperCase(Locale.ENGLISH); 050 } 051 052 /** 053 * Construct a new instance. 054 */ 055 public CharSequenceTranslator() { 056 // empty 057 } 058 059 /** 060 * Helper for non-Writer usage. 061 * @param input CharSequence to be translated 062 * @return String output of translation 063 */ 064 public final String translate(final CharSequence input) { 065 if (input == null) { 066 return null; 067 } 068 try { 069 final StringWriter writer = new StringWriter(input.length() * 2); 070 translate(input, writer); 071 return writer.toString(); 072 } catch (final IOException ioe) { 073 // this should never ever happen while writing to a StringWriter 074 throw new UncheckedIOException(ioe); 075 } 076 } 077 078 /** 079 * Translate a set of code points, represented by an int index into a CharSequence, 080 * into another set of code points. The number of code points consumed must be returned, 081 * and the only IOExceptions thrown must be from interacting with the Writer so that 082 * the top level API may reliably ignore StringWriter IOExceptions. 083 * 084 * @param input CharSequence that is being translated 085 * @param index int representing the current point of translation 086 * @param writer Writer to translate the text to 087 * @return int count of code points consumed 088 * @throws IOException if and only if the Writer produces an IOException 089 */ 090 public abstract int translate(CharSequence input, int index, Writer writer) throws IOException; 091 092 /** 093 * Translate an input onto a Writer. This is intentionally final as its algorithm is 094 * tightly coupled with the abstract method of this class. 095 * 096 * @param input CharSequence that is being translated 097 * @param writer Writer to translate the text to 098 * @throws IOException if and only if the Writer produces an IOException 099 */ 100 public final void translate(final CharSequence input, final Writer writer) throws IOException { 101 Validate.isTrue(writer != null, "The Writer must not be null"); 102 if (input == null) { 103 return; 104 } 105 int pos = 0; 106 final int len = input.length(); 107 while (pos < len) { 108 final int consumed = translate(input, pos, writer); 109 if (consumed == 0) { 110 // inlined implementation of Character.toChars(Character.codePointAt(input, pos)) 111 // avoids allocating temp char arrays and duplicate checks 112 final char c1 = input.charAt(pos); 113 writer.write(c1); 114 pos++; 115 if (Character.isHighSurrogate(c1) && pos < len) { 116 final char c2 = input.charAt(pos); 117 if (Character.isLowSurrogate(c2)) { 118 writer.write(c2); 119 pos++; 120 } 121 } 122 continue; 123 } 124 // contract with translators is that they have to understand code points 125 // and they just took care of a surrogate pair 126 for (int pt = 0; pt < consumed; pt++) { 127 pos += Character.charCount(Character.codePointAt(input, pos)); 128 } 129 } 130 } 131 132 /** 133 * Helper method to create a merger of this translator with another set of 134 * translators. Useful in customizing the standard functionality. 135 * 136 * @param translators CharSequenceTranslator array of translators to merge with this one 137 * @return CharSequenceTranslator merging this translator with the others 138 */ 139 public final CharSequenceTranslator with(final CharSequenceTranslator... translators) { 140 final CharSequenceTranslator[] newArray = new CharSequenceTranslator[translators.length + 1]; 141 newArray[0] = this; 142 System.arraycopy(translators, 0, newArray, 1, translators.length); 143 return new AggregateTranslator(newArray); 144 } 145 146}