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.Writer; 021 022/** 023 * Translates code points to their Unicode escaped value. 024 * 025 * @since 3.0 026 * @deprecated As of <a href="https://commons.apache.org/proper/commons-lang/changes-report.html#a3.6">3.6</a>, use Apache Commons Text 027 * <a href="https://commons.apache.org/proper/commons-text/javadocs/api-release/org/apache/commons/text/translate/UnicodeEscaper.html"> 028 * UnicodeEscaper</a>. 029 */ 030@Deprecated 031public class UnicodeEscaper extends CodePointTranslator { 032 033 /** 034 * Constructs a {@link UnicodeEscaper} above the specified value (exclusive). 035 * 036 * @param codePoint above which to escape 037 * @return the newly created {@link UnicodeEscaper} instance 038 */ 039 public static UnicodeEscaper above(final int codePoint) { 040 return outsideOf(0, codePoint); 041 } 042 /** 043 * Constructs a {@link UnicodeEscaper} below the specified value (exclusive). 044 * 045 * @param codePoint below which to escape 046 * @return the newly created {@link UnicodeEscaper} instance 047 */ 048 public static UnicodeEscaper below(final int codePoint) { 049 return outsideOf(codePoint, Integer.MAX_VALUE); 050 } 051 /** 052 * Constructs a {@link UnicodeEscaper} between the specified values (inclusive). 053 * 054 * @param codePointLow above which to escape 055 * @param codePointHigh below which to escape 056 * @return the newly created {@link UnicodeEscaper} instance 057 */ 058 public static UnicodeEscaper between(final int codePointLow, final int codePointHigh) { 059 return new UnicodeEscaper(codePointLow, codePointHigh, true); 060 } 061 062 /** 063 * Constructs a {@link UnicodeEscaper} outside of the specified values (exclusive). 064 * 065 * @param codePointLow below which to escape 066 * @param codePointHigh above which to escape 067 * @return the newly created {@link UnicodeEscaper} instance 068 */ 069 public static UnicodeEscaper outsideOf(final int codePointLow, final int codePointHigh) { 070 return new UnicodeEscaper(codePointLow, codePointHigh, false); 071 } 072 073 private final int below; 074 075 private final int above; 076 077 private final boolean between; 078 079 /** 080 * Constructs a {@link UnicodeEscaper} for all characters. 081 */ 082 public UnicodeEscaper() { 083 this(0, Integer.MAX_VALUE, true); 084 } 085 086 /** 087 * Constructs a {@link UnicodeEscaper} for the specified range. This is 088 * the underlying method for the other constructors/builders. The {@code below} 089 * and {@code above} boundaries are inclusive when {@code between} is 090 * {@code true} and exclusive when it is {@code false}. 091 * 092 * @param below int value representing the lowest code point boundary 093 * @param above int value representing the highest code point boundary 094 * @param between whether to escape between the boundaries or outside them 095 */ 096 protected UnicodeEscaper(final int below, final int above, final boolean between) { 097 this.below = below; 098 this.above = above; 099 this.between = between; 100 } 101 102 /** 103 * Converts the given code point to a hexadecimal string of the form {@code "\\uXXXX"} 104 * 105 * @param codePoint 106 * a Unicode code point 107 * @return the hexadecimal string for the given code point 108 * @since 3.2 109 */ 110 protected String toUtf16Escape(final int codePoint) { 111 return "\\u" + hex(codePoint); 112 } 113 114 /** 115 * {@inheritDoc} 116 */ 117 @Override 118 public boolean translate(final int codePoint, final Writer out) throws IOException { 119 if (between) { 120 if (codePoint < below || codePoint > above) { 121 return false; 122 } 123 } else if (codePoint >= below && codePoint <= above) { 124 return false; 125 } 126 127 // TODO: Handle potential + sign per various Unicode escape implementations 128 if (codePoint > 0xffff) { 129 out.write(toUtf16Escape(codePoint)); 130 } else { 131 out.write("\\u"); 132 out.write(HEX_DIGITS[codePoint >> 12 & 15]); 133 out.write(HEX_DIGITS[codePoint >> 8 & 15]); 134 out.write(HEX_DIGITS[codePoint >> 4 & 15]); 135 out.write(HEX_DIGITS[codePoint & 15]); 136 } 137 return true; 138 } 139}