1 /*
2 * Copyright (c) 2017, Oracle and/or its affiliates. All rights reserved.
3 */
4 /*
5 * Licensed to the Apache Software Foundation (ASF) under one or more
6 * contributor license agreements. See the NOTICE file distributed with
7 * this work for additional information regarding copyright ownership.
8 * The ASF licenses this file to You under the Apache License, Version 2.0
9 * (the "License"); you may not use this file except in compliance with
10 * the License. You may obtain a copy of the License at
11 *
12 * http://www.apache.org/licenses/LICENSE-2.0
13 *
14 * Unless required by applicable law or agreed to in writing, software
15 * distributed under the License is distributed on an "AS IS" BASIS,
16 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
17 * See the License for the specific language governing permissions and
18 * limitations under the License.
19 */
20
21 package com.sun.org.apache.xerces.internal.impl.dv.util;
22
23 /**
24 * This class provides encode/decode for RFC 2045 Base64 as
25 * defined by RFC 2045, N. Freed and N. Borenstein.
26 * RFC 2045: Multipurpose Internet Mail Extensions (MIME)
27 * Part One: Format of Internet Message Bodies. Reference
28 * 1996 Available at: http://www.ietf.org/rfc/rfc2045.txt
29 * This class is used by XML Schema binary format validation
30 *
31 * This implementation does not encode/decode streaming
32 * data. You need the data that you will encode/decode
33 * already on a byte arrray.
34 *
35 * @xerces.internal
36 *
37 * @author Jeffrey Rodriguez
38 * @author Sandy Gao
39 * @LastModified: Nov 2017
40 */
41 public final class Base64 {
42
43 static private final int BASELENGTH = 128;
44 static private final int LOOKUPLENGTH = 64;
45 static private final int TWENTYFOURBITGROUP = 24;
46 static private final int EIGHTBIT = 8;
47 static private final int SIXTEENBIT = 16;
48 static private final int SIXBIT = 6;
49 static private final int FOURBYTE = 4;
50 static private final int SIGN = -128;
51 static private final char PAD = '=';
52 static private final boolean fDebug = false;
53 static final private byte [] base64Alphabet = new byte[BASELENGTH];
54 static final private char [] lookUpBase64Alphabet = new char[LOOKUPLENGTH];
55
56 static {
57
58 for (int i = 0; i < BASELENGTH; ++i) {
59 base64Alphabet[i] = -1;
60 }
61 for (int i = 'Z'; i >= 'A'; i--) {
62 base64Alphabet[i] = (byte) (i-'A');
63 }
64 for (int i = 'z'; i>= 'a'; i--) {
65 base64Alphabet[i] = (byte) ( i-'a' + 26);
66 }
67
68 for (int i = '9'; i >= '0'; i--) {
69 base64Alphabet[i] = (byte) (i-'0' + 52);
70 }
71
72 base64Alphabet['+'] = 62;
73 base64Alphabet['/'] = 63;
74
75 for (int i = 0; i<=25; i++)
76 lookUpBase64Alphabet[i] = (char)('A'+i);
77
78 for (int i = 26, j = 0; i<=51; i++, j++)
79 lookUpBase64Alphabet[i] = (char)('a'+ j);
80
81 for (int i = 52, j = 0; i<=61; i++, j++)
82 lookUpBase64Alphabet[i] = (char)('0' + j);
83 lookUpBase64Alphabet[62] = '+';
84 lookUpBase64Alphabet[63] = '/';
85
86 }
87
88 protected static boolean isWhiteSpace(char octect) {
89 return (octect == 0x20 || octect == 0xd || octect == 0xa || octect == 0x9);
90 }
91
92 protected static boolean isPad(char octect) {
93 return (octect == PAD);
94 }
95
96 protected static boolean isData(char octect) {
97 return (octect < BASELENGTH && base64Alphabet[octect] != -1);
98 }
99
100 protected static boolean isBase64(char octect) {
101 return (isWhiteSpace(octect) || isPad(octect) || isData(octect));
102 }
103
104 /**
105 * Encodes hex octects into Base64
106 *
107 * @param binaryData Array containing binaryData
108 * @return Encoded Base64 array
109 */
110 public static String encode(byte[] binaryData) {
111
112 if (binaryData == null)
113 return null;
114
115 int lengthDataBits = binaryData.length*EIGHTBIT;
116 if (lengthDataBits == 0) {
117 return "";
118 }
119
120 int fewerThan24bits = lengthDataBits%TWENTYFOURBITGROUP;
121 int numberTriplets = lengthDataBits/TWENTYFOURBITGROUP;
122 int numberQuartet = fewerThan24bits != 0 ? numberTriplets+1 : numberTriplets;
123 char encodedData[] = null;
124
125 encodedData = new char[numberQuartet*4];
126
127 byte k=0, l=0, b1=0,b2=0,b3=0;
128
129 int encodedIndex = 0;
130 int dataIndex = 0;
131 if (fDebug) {
132 System.out.println("number of triplets = " + numberTriplets );
133 }
134
135 for (int i=0; i<numberTriplets; i++) {
136 b1 = binaryData[dataIndex++];
137 b2 = binaryData[dataIndex++];
138 b3 = binaryData[dataIndex++];
139
140 if (fDebug) {
141 System.out.println( "b1= " + b1 +", b2= " + b2 + ", b3= " + b3 );
142 }
143
144 l = (byte)(b2 & 0x0f);
145 k = (byte)(b1 & 0x03);
146
147 byte val1 = ((b1 & SIGN)==0)?(byte)(b1>>2):(byte)((b1)>>2^0xc0);
148
149 byte val2 = ((b2 & SIGN)==0)?(byte)(b2>>4):(byte)((b2)>>4^0xf0);
150 byte val3 = ((b3 & SIGN)==0)?(byte)(b3>>6):(byte)((b3)>>6^0xfc);
151
152 if (fDebug) {
153 System.out.println( "val2 = " + val2 );
154 System.out.println( "k4 = " + (k<<4));
155 System.out.println( "vak = " + (val2 | (k<<4)));
156 }
157
158 encodedData[encodedIndex++] = lookUpBase64Alphabet[ val1 ];
159 encodedData[encodedIndex++] = lookUpBase64Alphabet[ val2 | ( k<<4 )];
160 encodedData[encodedIndex++] = lookUpBase64Alphabet[ (l <<2 ) | val3 ];
161 encodedData[encodedIndex++] = lookUpBase64Alphabet[ b3 & 0x3f ];
162 }
163
164 // form integral number of 6-bit groups
165 if (fewerThan24bits == EIGHTBIT) {
166 b1 = binaryData[dataIndex];
167 k = (byte) ( b1 &0x03 );
168 if (fDebug) {
169 System.out.println("b1=" + b1);
170 System.out.println("b1<<2 = " + (b1>>2) );
171 }
172 byte val1 = ((b1 & SIGN)==0)?(byte)(b1>>2):(byte)((b1)>>2^0xc0);
173 encodedData[encodedIndex++] = lookUpBase64Alphabet[ val1 ];
174 encodedData[encodedIndex++] = lookUpBase64Alphabet[ k<<4 ];
175 encodedData[encodedIndex++] = PAD;
176 encodedData[encodedIndex++] = PAD;
177 } else if (fewerThan24bits == SIXTEENBIT) {
178 b1 = binaryData[dataIndex];
179 b2 = binaryData[dataIndex +1 ];
180 l = ( byte ) ( b2 &0x0f );
181 k = ( byte ) ( b1 &0x03 );
182
183 byte val1 = ((b1 & SIGN)==0)?(byte)(b1>>2):(byte)((b1)>>2^0xc0);
184 byte val2 = ((b2 & SIGN)==0)?(byte)(b2>>4):(byte)((b2)>>4^0xf0);
185
186 encodedData[encodedIndex++] = lookUpBase64Alphabet[ val1 ];
187 encodedData[encodedIndex++] = lookUpBase64Alphabet[ val2 | ( k<<4 )];
188 encodedData[encodedIndex++] = lookUpBase64Alphabet[ l<<2 ];
189 encodedData[encodedIndex++] = PAD;
190 }
191
192 return new String(encodedData);
193 }
194
195 /**
196 * Decodes Base64 data into octects
197 *
198 * @param encoded string containing Base64 data
199 * @return Array containind decoded data.
200 */
201 public static byte[] decode(String encoded) {
202
203 if (encoded == null)
204 return null;
205
206 char[] base64Data = encoded.toCharArray();
207 // remove white spaces
208 int len = removeWhiteSpace(base64Data);
209
210 if (len%FOURBYTE != 0) {
211 return null;//should be divisible by four
212 }
213
214 int numberQuadruple = (len/FOURBYTE );
215
216 if (numberQuadruple == 0)
217 return new byte[0];
218
219 byte decodedData[] = null;
220 byte b1=0,b2=0,b3=0,b4=0;
221 char d1=0,d2=0,d3=0,d4=0;
222
223 int i = 0;
224 int encodedIndex = 0;
225 int dataIndex = 0;
226 decodedData = new byte[ (numberQuadruple)*3];
227
228 for (; i<numberQuadruple-1; i++) {
229
230 if (!isData( (d1 = base64Data[dataIndex++]) )||
231 !isData( (d2 = base64Data[dataIndex++]) )||
232 !isData( (d3 = base64Data[dataIndex++]) )||
233 !isData( (d4 = base64Data[dataIndex++]) ))
234 return null;//if found "no data" just return null
235
236 b1 = base64Alphabet[d1];
237 b2 = base64Alphabet[d2];
238 b3 = base64Alphabet[d3];
239 b4 = base64Alphabet[d4];
240
241 decodedData[encodedIndex++] = (byte)( b1 <<2 | b2>>4 ) ;
242 decodedData[encodedIndex++] = (byte)(((b2 & 0xf)<<4 ) |( (b3>>2) & 0xf) );
243 decodedData[encodedIndex++] = (byte)( b3<<6 | b4 );
244 }
245
246 if (!isData( (d1 = base64Data[dataIndex++]) ) ||
247 !isData( (d2 = base64Data[dataIndex++]) )) {
248 return null;//if found "no data" just return null
249 }
250
251 b1 = base64Alphabet[d1];
252 b2 = base64Alphabet[d2];
253
254 d3 = base64Data[dataIndex++];
255 d4 = base64Data[dataIndex++];
256 if (!isData( (d3 ) ) ||
257 !isData( (d4 ) )) {//Check if they are PAD characters
258 if (isPad( d3 ) && isPad( d4)) { //Two PAD e.g. 3c[Pad][Pad]
259 if ((b2 & 0xf) != 0)//last 4 bits should be zero
260 return null;
261 byte[] tmp = new byte[ i*3 + 1 ];
262 System.arraycopy( decodedData, 0, tmp, 0, i*3 );
263 tmp[encodedIndex] = (byte)( b1 <<2 | b2>>4 ) ;
264 return tmp;
265 } else if (!isPad( d3) && isPad(d4)) { //One PAD e.g. 3cQ[Pad]
266 b3 = base64Alphabet[ d3 ];
267 if ((b3 & 0x3 ) != 0)//last 2 bits should be zero
268 return null;
269 byte[] tmp = new byte[ i*3 + 2 ];
270 System.arraycopy( decodedData, 0, tmp, 0, i*3 );
271 tmp[encodedIndex++] = (byte)( b1 <<2 | b2>>4 );
272 tmp[encodedIndex] = (byte)(((b2 & 0xf)<<4 ) |( (b3>>2) & 0xf) );
273 return tmp;
274 } else {
275 return null;//an error like "3c[Pad]r", "3cdX", "3cXd", "3cXX" where X is non data
276 }
277 } else { //No PAD e.g 3cQl
278 b3 = base64Alphabet[ d3 ];
279 b4 = base64Alphabet[ d4 ];
280 decodedData[encodedIndex++] = (byte)( b1 <<2 | b2>>4 ) ;
281 decodedData[encodedIndex++] = (byte)(((b2 & 0xf)<<4 ) |( (b3>>2) & 0xf) );
282 decodedData[encodedIndex++] = (byte)( b3<<6 | b4 );
283
284 }
285
286 return decodedData;
287 }
288
289 /**
290 * remove WhiteSpace from MIME containing encoded Base64 data.
291 *
292 * @param data the byte array of base64 data (with WS)
293 * @return the new length
294 */
295 protected static int removeWhiteSpace(char[] data) {
296 if (data == null)
297 return 0;
298
299 // count characters that's not whitespace
300 int newSize = 0;
301 int len = data.length;
302 for (int i = 0; i < len; i++) {
303 if (!isWhiteSpace(data[i]))
304 data[newSize++] = data[i];
305 }
306 return newSize;
307 }
308 }