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.fileupload2.core;
18
19 import java.io.IOException;
20 import java.io.OutputStream;
21
22 /**
23 */
24 final class QuotedPrintableDecoder {
25
26 /**
27 * The shift value required to create the upper nibble from the first of 2 byte values converted from ASCII hex.
28 */
29 private static final int UPPER_NIBBLE_SHIFT = Byte.SIZE / 2;
30
31 /**
32 * Decodes the encoded byte data writing it to the given output stream.
33 *
34 * @param data The array of byte data to decode.
35 * @param out The output stream used to return the decoded data.
36 *
37 * @return the number of bytes produced.
38 * @throws IOException if an IO error occurs
39 */
40 public static int decode(final byte[] data, final OutputStream out) throws IOException {
41 var off = 0;
42 final var length = data.length;
43 final var endOffset = off + length;
44 var bytesWritten = 0;
45
46 while (off < endOffset) {
47 final var ch = data[off++];
48
49 // space characters were translated to '_' on encode, so we need to translate them back.
50 if (ch == '_') {
51 out.write(' ');
52 } else if (ch == '=') {
53 // we found an encoded character. Reduce the 3 char sequence to one.
54 // but first, make sure we have two characters to work with.
55 if (off + 1 >= endOffset) {
56 throw new IOException("Invalid quoted printable encoding; truncated escape sequence");
57 }
58
59 final var b1 = data[off++];
60 final var b2 = data[off++];
61
62 // we've found an encoded carriage return. The next char needs to be a newline
63 if (b1 == '\r') {
64 if (b2 != '\n') {
65 throw new IOException("Invalid quoted printable encoding; CR must be followed by LF");
66 }
67 // this was a soft linebreak inserted by the encoding. We just toss this away
68 // on decode.
69 } else {
70 // this is a hex pair we need to convert back to a single byte.
71 final var c1 = hexToBinary(b1);
72 final var c2 = hexToBinary(b2);
73 out.write(c1 << UPPER_NIBBLE_SHIFT | c2);
74 // 3 bytes in, one byte out
75 bytesWritten++;
76 }
77 } else {
78 // simple character, just write it out.
79 out.write(ch);
80 bytesWritten++;
81 }
82 }
83
84 return bytesWritten;
85 }
86
87 /**
88 * Converts a hexadecimal digit to the binary value it represents.
89 *
90 * @param b the ASCII hexadecimal byte to convert (0-0, A-F, a-f)
91 * @return the int value of the hexadecimal byte, 0-15
92 * @throws IOException if the byte is not a valid hexadecimal digit.
93 */
94 private static int hexToBinary(final byte b) throws IOException {
95 // CHECKSTYLE IGNORE MagicNumber FOR NEXT 1 LINE
96 final var i = Character.digit((char) b, 16);
97 if (i == -1) {
98 throw new IOException("Invalid quoted printable encoding: not a valid hex digit: " + b);
99 }
100 return i;
101 }
102
103 /**
104 * Hidden constructor, this class must not be instantiated.
105 */
106 private QuotedPrintableDecoder() {
107 // do nothing
108 }
109
110 }