1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
|
/*
* 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.lang3.text.translate;
import java.io.IOException;
import java.io.StringWriter;
import java.io.UncheckedIOException;
import java.io.Writer;
import java.util.Locale;
import java.util.Objects;
/**
* An API for translating text.
* Its core use is to escape and unescape text. Because escaping and unescaping
* is completely contextual, the API does not present two separate signatures.
*
* @since 3.0
* @deprecated As of 3.6, use Apache Commons Text
* <a href="https://commons.apache.org/proper/commons-text/javadocs/api-release/org/apache/commons/text/translate/CharSequenceTranslator.html">
* CharSequenceTranslator</a> instead
*/
@Deprecated
public abstract class CharSequenceTranslator {
static final char[] HEX_DIGITS = {'0', '1', '2', '3', '4', '5', '6', '7', '8', '9', 'A', 'B', 'C', 'D', 'E', 'F'};
/**
* Translate a set of code points, represented by an int index into a CharSequence,
* into another set of code points. The number of code points consumed must be returned,
* and the only IOExceptions thrown must be from interacting with the Writer so that
* the top level API may reliably ignore StringWriter IOExceptions.
*
* @param input CharSequence that is being translated
* @param index int representing the current point of translation
* @param out Writer to translate the text to
* @return int count of code points consumed
* @throws IOException if and only if the Writer produces an IOException
*/
public abstract int translate(CharSequence input, int index, Writer out) throws IOException;
/**
* Helper for non-Writer usage.
* @param input CharSequence to be translated
* @return String output of translation
*/
public final String translate(final CharSequence input) {
if (input == null) {
return null;
}
try {
final StringWriter writer = new StringWriter(input.length() * 2);
translate(input, writer);
return writer.toString();
} catch (final IOException ioe) {
// this should never ever happen while writing to a StringWriter
throw new UncheckedIOException(ioe);
}
}
/**
* Translate an input onto a Writer. This is intentionally final as its algorithm is
* tightly coupled with the abstract method of this class.
*
* @param input CharSequence that is being translated
* @param writer Writer to translate the text to
* @throws IOException if and only if the Writer produces an IOException
*/
public final void translate(final CharSequence input, final Writer writer) throws IOException {
Objects.requireNonNull(writer, "writer");
if (input == null) {
return;
}
int pos = 0;
final int len = input.length();
while (pos < len) {
final int consumed = translate(input, pos, writer);
if (consumed == 0) {
// inlined implementation of Character.toChars(Character.codePointAt(input, pos))
// avoids allocating temp char arrays and duplicate checks
final char c1 = input.charAt(pos);
writer.write(c1);
pos++;
if (Character.isHighSurrogate(c1) && pos < len) {
final char c2 = input.charAt(pos);
if (Character.isLowSurrogate(c2)) {
writer.write(c2);
pos++;
}
}
continue;
}
// contract with translators is that they have to understand code points
// and they just took care of a surrogate pair
for (int pt = 0; pt < consumed; pt++) {
pos += Character.charCount(Character.codePointAt(input, pos));
}
}
}
/**
* Helper method to create a merger of this translator with another set of
* translators. Useful in customizing the standard functionality.
*
* @param translators CharSequenceTranslator array of translators to merge with this one
* @return CharSequenceTranslator merging this translator with the others
*/
public final CharSequenceTranslator with(final CharSequenceTranslator... translators) {
final CharSequenceTranslator[] newArray = new CharSequenceTranslator[translators.length + 1];
newArray[0] = this;
System.arraycopy(translators, 0, newArray, 1, translators.length);
return new AggregateTranslator(newArray);
}
/**
* Returns an upper case hexadecimal {@link String} for the given
* character.
*
* @param codePoint The code point to convert.
* @return An upper case hexadecimal {@link String}
*/
public static String hex(final int codePoint) {
return Integer.toHexString(codePoint).toUpperCase(Locale.ENGLISH);
}
}
|
