| Classes in this File | Line Coverage | Branch Coverage | Complexity | ||||
| UnicodeUnescaper |
|
| 13.0;13 |
| 1 | /* | |
| 2 | * Licensed to the Apache Software Foundation (ASF) under one or more | |
| 3 | * contributor license agreements. See the NOTICE file distributed with | |
| 4 | * this work for additional information regarding copyright ownership. | |
| 5 | * The ASF licenses this file to You under the Apache License, Version 2.0 | |
| 6 | * (the "License"); you may not use this file except in compliance with | |
| 7 | * the License. You may obtain a copy of the License at | |
| 8 | * | |
| 9 | * http://www.apache.org/licenses/LICENSE-2.0 | |
| 10 | * | |
| 11 | * Unless required by applicable law or agreed to in writing, software | |
| 12 | * distributed under the License is distributed on an "AS IS" BASIS, | |
| 13 | * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. | |
| 14 | * See the License for the specific language governing permissions and | |
| 15 | * limitations under the License. | |
| 16 | */ | |
| 17 | package org.apache.commons.lang3.text.translate; | |
| 18 | ||
| 19 | import java.io.IOException; | |
| 20 | import java.io.Writer; | |
| 21 | ||
| 22 | /** | |
| 23 | * Translates escaped Unicode values of the form \\u+\d\d\d\d back to | |
| 24 | * Unicode. It supports multiple 'u' characters and will work with or | |
| 25 | * without the +. | |
| 26 | * | |
| 27 | * @since 3.0 | |
| 28 | * @version $Id: UnicodeUnescaper.java 1436770 2013-01-22 07:09:45Z ggregory $ | |
| 29 | */ | |
| 30 | 4 | public class UnicodeUnescaper extends CharSequenceTranslator { |
| 31 | ||
| 32 | /** | |
| 33 | * {@inheritDoc} | |
| 34 | */ | |
| 35 | @Override | |
| 36 | public int translate(final CharSequence input, final int index, final Writer out) throws IOException { | |
| 37 | 85 | if (input.charAt(index) == '\\' && index + 1 < input.length() && input.charAt(index + 1) == 'u') { |
| 38 | // consume optional additional 'u' chars | |
| 39 | 12 | int i = 2; |
| 40 | 19 | while (index + i < input.length() && input.charAt(index + i) == 'u') { |
| 41 | 7 | i++; |
| 42 | } | |
| 43 | ||
| 44 | 12 | if (index + i < input.length() && input.charAt(index + i) == '+') { |
| 45 | 1 | i++; |
| 46 | } | |
| 47 | ||
| 48 | 12 | if (index + i + 4 <= input.length()) { |
| 49 | // Get 4 hex digits | |
| 50 | 11 | final CharSequence unicode = input.subSequence(index + i, index + i + 4); |
| 51 | ||
| 52 | try { | |
| 53 | 11 | final int value = Integer.parseInt(unicode.toString(), 16); |
| 54 | 10 | out.write((char) value); |
| 55 | 1 | } catch (final NumberFormatException nfe) { |
| 56 | 1 | throw new IllegalArgumentException("Unable to parse unicode value: " + unicode, nfe); |
| 57 | 10 | } |
| 58 | 10 | return i + 4; |
| 59 | } else { | |
| 60 | 1 | throw new IllegalArgumentException("Less than 4 hex digits in unicode value: '" + input.subSequence(index, input.length()) |
| 61 | + "' due to end of CharSequence"); | |
| 62 | } | |
| 63 | } | |
| 64 | 73 | return 0; |
| 65 | } | |
| 66 | } |