UnicodeUnescaper.java
/*
* Licensed to the Apache Software Foundation (ASF) under one or more
* contributor license agreements. See the NOTICE file distributed with
* this work for additional information regarding copyright ownership.
* The ASF licenses this file to You under the Apache License, Version 2.0
* (the "License"); you may not use this file except in compliance with
* the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package org.apache.commons.text.translate;
import java.io.IOException;
import java.io.Writer;
/**
* Translates escaped Unicode values of the form \\u+\d\d\d\d back to
* Unicode. It supports multiple 'u' characters and will work with or
* without the +.
*
* @since 1.0
*/
public class UnicodeUnescaper extends CharSequenceTranslator {
/**
* Constructs a new instance.
*/
public UnicodeUnescaper() {
// empty
}
/**
* {@inheritDoc}
*/
@Override
public int translate(final CharSequence input, final int index, final Writer writer) throws IOException {
if (input.charAt(index) == '\\' && index + 1 < input.length() && input.charAt(index + 1) == 'u') {
// consume optional additional 'u' chars
int i = 2;
while (index + i < input.length() && input.charAt(index + i) == 'u') {
i++;
}
if (index + i < input.length() && input.charAt(index + i) == '+') {
i++;
}
if (index + i + 4 <= input.length()) {
// Get 4 hex digits
final CharSequence unicode = input.subSequence(index + i, index + i + 4);
try {
final int value = Integer.parseInt(unicode.toString(), 16);
writer.write((char) value);
} catch (final NumberFormatException nfe) {
throw new IllegalArgumentException("Unable to parse unicode value: " + unicode, nfe);
}
return i + 4;
}
throw new IllegalArgumentException("Less than 4 hex digits in unicode value: '"
+ input.subSequence(index, input.length())
+ "' due to end of CharSequence");
}
return 0;
}
}