forked from openjdk/jdk
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathZipCoder.java
More file actions
246 lines (214 loc) · 7.91 KB
/
Copy pathZipCoder.java
File metadata and controls
246 lines (214 loc) · 7.91 KB
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
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
/*
* Copyright (c) 2009, 2020, Oracle and/or its affiliates. All rights reserved.
* DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
*
* This code is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License version 2 only, as
* published by the Free Software Foundation. Oracle designates this
* particular file as subject to the "Classpath" exception as provided
* by Oracle in the LICENSE file that accompanied this code.
*
* This code is distributed in the hope that it will be useful, but WITHOUT
* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
* version 2 for more details (a copy is included in the LICENSE file that
* accompanied this code).
*
* You should have received a copy of the GNU General Public License version
* 2 along with this work; if not, write to the Free Software Foundation,
* Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
*
* Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
* or visit www.oracle.com if you need additional information or have any
* questions.
*/
package java.util.zip;
import java.nio.ByteBuffer;
import java.nio.CharBuffer;
import java.nio.charset.Charset;
import java.nio.charset.CharsetDecoder;
import java.nio.charset.CharsetEncoder;
import java.nio.charset.CharacterCodingException;
import java.nio.charset.CodingErrorAction;
import java.util.Arrays;
import sun.nio.cs.UTF_8;
/**
* Utility class for zipfile name and comment decoding and encoding
*/
class ZipCoder {
private static final jdk.internal.access.JavaLangAccess JLA =
jdk.internal.access.SharedSecrets.getJavaLangAccess();
// Encoding/decoding is stateless, so make it singleton.
static final UTF8ZipCoder UTF8 = new UTF8ZipCoder(UTF_8.INSTANCE);
public static ZipCoder get(Charset charset) {
if (charset == UTF_8.INSTANCE) {
return UTF8;
}
return new ZipCoder(charset);
}
String toString(byte[] ba, int off, int length) {
try {
return decoder().decode(ByteBuffer.wrap(ba, off, length)).toString();
} catch (CharacterCodingException x) {
throw new IllegalArgumentException(x);
}
}
String toString(byte[] ba, int length) {
return toString(ba, 0, length);
}
String toString(byte[] ba) {
return toString(ba, 0, ba.length);
}
byte[] getBytes(String s) {
try {
ByteBuffer bb = encoder().encode(CharBuffer.wrap(s));
int pos = bb.position();
int limit = bb.limit();
if (bb.hasArray() && pos == 0 && limit == bb.capacity()) {
return bb.array();
}
byte[] bytes = new byte[bb.limit() - bb.position()];
bb.get(bytes);
return bytes;
} catch (CharacterCodingException x) {
throw new IllegalArgumentException(x);
}
}
static String toStringUTF8(byte[] ba, int len) {
return UTF8.toString(ba, 0, len);
}
static String toStringUTF8(byte[] ba, int off, int len) {
return UTF8.toString(ba, off, len);
}
boolean isUTF8() {
return false;
}
// Hash code functions for ZipFile entry names. We generate the hash as-if
// we first decoded the byte sequence to a String, then appended '/' if no
// trailing slash was found, then called String.hashCode(). This
// normalization ensures we can simplify and speed up lookups.
int normalizedHash(byte[] a, int off, int len) {
if (len == 0) {
return 0;
}
return normalizedHashDecode(0, a, off, off + len);
}
// Matching normalized hash code function for Strings
static int normalizedHash(String name) {
int hsh = name.hashCode();
int len = name.length();
if (len > 0 && name.charAt(len - 1) != '/') {
hsh = hsh * 31 + '/';
}
return hsh;
}
boolean hasTrailingSlash(byte[] a, int end) {
byte[] slashBytes = slashBytes();
return end >= slashBytes.length &&
Arrays.mismatch(a, end - slashBytes.length, end, slashBytes, 0, slashBytes.length) == -1;
}
// Implements normalizedHash by decoding byte[] to char[] and then computing
// the hash. This is a slow-path used for non-UTF8 charsets and also when
// aborting the ASCII fast-path in the UTF8 implementation, so {@code h}
// might be a partially calculated hash code
int normalizedHashDecode(int h, byte[] a, int off, int end) {
try {
// cb will be a newly allocated CharBuffer with pos == 0,
// arrayOffset == 0, backed by an array.
CharBuffer cb = decoder().decode(ByteBuffer.wrap(a, off, end - off));
int limit = cb.limit();
char[] decoded = cb.array();
for (int i = 0; i < limit; i++) {
h = 31 * h + decoded[i];
}
if (limit > 0 && decoded[limit - 1] != '/') {
h = 31 * h + '/';
}
} catch (CharacterCodingException cce) {
// Ignore - return the hash code generated so far.
}
return h;
}
private byte[] slashBytes;
private final Charset cs;
protected CharsetDecoder dec;
private CharsetEncoder enc;
private ZipCoder(Charset cs) {
this.cs = cs;
}
protected CharsetDecoder decoder() {
if (dec == null) {
dec = cs.newDecoder()
.onMalformedInput(CodingErrorAction.REPORT)
.onUnmappableCharacter(CodingErrorAction.REPORT);
}
return dec;
}
private CharsetEncoder encoder() {
if (enc == null) {
enc = cs.newEncoder()
.onMalformedInput(CodingErrorAction.REPORT)
.onUnmappableCharacter(CodingErrorAction.REPORT);
}
return enc;
}
// This method produces an array with the bytes that will correspond to a
// trailing '/' in the chosen character encoding.
//
// While in most charsets a trailing slash will be encoded as the byte
// value of '/', this does not hold in the general case. E.g., in charsets
// such as UTF-16 and UTF-32 it will be represented by a sequence of 2 or 4
// bytes, respectively.
private byte[] slashBytes() {
if (slashBytes == null) {
// Take into account charsets that produce a BOM, e.g., UTF-16
byte[] slash = "/".getBytes(cs);
byte[] doubleSlash = "//".getBytes(cs);
slashBytes = Arrays.copyOfRange(doubleSlash, slash.length, doubleSlash.length);
}
return slashBytes;
}
static final class UTF8ZipCoder extends ZipCoder {
private UTF8ZipCoder(Charset utf8) {
super(utf8);
}
@Override
boolean isUTF8() {
return true;
}
@Override
String toString(byte[] ba, int off, int length) {
return JLA.newStringUTF8NoRepl(ba, off, length);
}
@Override
byte[] getBytes(String s) {
return JLA.getBytesUTF8NoRepl(s);
}
@Override
int normalizedHash(byte[] a, int off, int len) {
if (len == 0) {
return 0;
}
int end = off + len;
int h = 0;
while (off < end) {
byte b = a[off];
if (b < 0) {
// Non-ASCII, fall back to decoder loop
return normalizedHashDecode(h, a, off, end);
} else {
h = 31 * h + b;
off++;
}
}
if (a[end - 1] != '/') {
h = 31 * h + '/';
}
return h;
}
@Override
boolean hasTrailingSlash(byte[] a, int end) {
return end > 0 && a[end - 1] == '/';
}
}
}