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.Writer; 021 022/** 023 * Translates code points to their Unicode escaped value. 024 * 025 * @since 1.0 026 */ 027public class UnicodeEscaper extends CodePointTranslator { 028 029 /** 030 * Constructs a {@code UnicodeEscaper} above the specified value (exclusive). 031 * 032 * @param codePoint above which to escape 033 * @return The newly created {@code UnicodeEscaper} instance 034 */ 035 public static UnicodeEscaper above(final int codePoint) { 036 return outsideOf(0, codePoint); 037 } 038 /** 039 * Constructs a {@code UnicodeEscaper} below the specified value (exclusive). 040 * 041 * @param codePoint below which to escape 042 * @return The newly created {@code UnicodeEscaper} instance 043 */ 044 public static UnicodeEscaper below(final int codePoint) { 045 return outsideOf(codePoint, Integer.MAX_VALUE); 046 } 047 /** 048 * Constructs a {@code UnicodeEscaper} between the specified values (inclusive). 049 * 050 * @param codePointLow above which to escape 051 * @param codePointHigh below which to escape 052 * @return The newly created {@code UnicodeEscaper} instance 053 */ 054 public static UnicodeEscaper between(final int codePointLow, final int codePointHigh) { 055 return new UnicodeEscaper(codePointLow, codePointHigh, true); 056 } 057 058 /** 059 * Constructs a {@code UnicodeEscaper} outside of the specified values (exclusive). 060 * 061 * @param codePointLow below which to escape 062 * @param codePointHigh above which to escape 063 * @return The newly created {@code UnicodeEscaper} instance 064 */ 065 public static UnicodeEscaper outsideOf(final int codePointLow, final int codePointHigh) { 066 return new UnicodeEscaper(codePointLow, codePointHigh, false); 067 } 068 069 /** int value representing the lowest code point boundary. */ 070 private final int below; 071 072 /** int value representing the highest code point boundary. */ 073 private final int above; 074 075 /** whether to escape between the boundaries or outside them. */ 076 private final boolean between; 077 078 /** 079 * Constructs a {@code UnicodeEscaper} for all characters. 080 * 081 */ 082 public UnicodeEscaper() { 083 this(0, Integer.MAX_VALUE, true); 084 } 085 086 /** 087 * Constructs a {@code 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 hex string of the form {@code "\\uXXXX"}. 104 * 105 * @param codePoint 106 * a Unicode code point 107 * @return The hex string for the given code point 108 * 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 writer) 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 if (codePoint > 0xffff) { 128 writer.write(toUtf16Escape(codePoint)); 129 } else { 130 writer.write("\\u"); 131 writer.write(HEX_DIGITS[codePoint >> 12 & 15]); 132 writer.write(HEX_DIGITS[codePoint >> 8 & 15]); 133 writer.write(HEX_DIGITS[codePoint >> 4 & 15]); 134 writer.write(HEX_DIGITS[codePoint & 15]); 135 } 136 return true; 137 } 138}