1 /*
2 * Copyright (c) 1996, 2009, Oracle and/or its affiliates. All rights reserved.
3 * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
4 *
5 * This code is free software; you can redistribute it and/or modify it
6 * under the terms of the GNU General Public License version 2 only, as
7 * published by the Free Software Foundation. Oracle designates this
8 * particular file as subject to the "Classpath" exception as provided
9 * by Oracle in the LICENSE file that accompanied this code.
10 *
11 * This code is distributed in the hope that it will be useful, but WITHOUT
12 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
13 * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
14 * version 2 for more details (a copy is included in the LICENSE file that
15 * accompanied this code).
16 *
17 * You should have received a copy of the GNU General Public License version
18 * 2 along with this work; if not, write to the Free Software Foundation,
19 * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
20 *
21 * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
22 * or visit www.oracle.com if you need additional information or have any
23 * questions.
24 */
25
26 package java.util.zip;
27
28 import java.io.InputStream;
29 import java.io.IOException;
30 import java.io.EOFException;
31 import java.io.PushbackInputStream;
32 import java.nio.charset.Charset;
33 import static java.util.zip.ZipConstants64.*;
34
35 /**
36 * This class implements an input stream filter for reading files in the
37 * ZIP file format. Includes support for both compressed and uncompressed
38 * entries.
39 *
40 * @author David Connelly
41 */
42 public
43 class ZipInputStream extends InflaterInputStream implements ZipConstants {
44 private ZipEntry entry;
45 private int flag;
46 private CRC32 crc = new CRC32();
47 private long remaining;
48 private byte[] tmpbuf = new byte[512];
49
50 private static final int STORED = ZipEntry.STORED;
51 private static final int DEFLATED = ZipEntry.DEFLATED;
52
53 private boolean closed = false;
54 // this flag is set to true after EOF has reached for
55 // one entry
56 private boolean entryEOF = false;
57
58 private ZipCoder zc;
59
60 /**
61 * Check to make sure that this stream has not been closed
62 */
63 private void ensureOpen() throws IOException {
64 if (closed) {
65 throw new IOException("Stream closed");
66 }
67 }
68
69 /**
70 * Creates a new ZIP input stream.
71 *
72 * <p>The UTF-8 {@link java.nio.charset.Charset charset} is used to
73 * decode the entry names.
74 *
75 * @param in the actual input stream
76 */
77 public ZipInputStream(InputStream in) {
78 this(in, Charset.forName("UTF-8"));
79 }
80
81 /**
82 * Creates a new ZIP input stream.
83 *
84 * @param in the actual input stream
85 *
86 * @param charset
87 * The {@linkplain java.nio.charset.Charset charset} to be
88 * used to decode the ZIP entry name (ignored if the
89 * <a href="package-summary.html#lang_encoding"> language
90 * encoding bit</a> of the ZIP entry's general purpose bit
91 * flag is set).
92 *
93 * @since 1.7
94 */
95 public ZipInputStream(InputStream in, Charset charset) {
96 super(new PushbackInputStream(in, 512), new Inflater(true), 512);
97 usesDefaultInflater = true;
98 if(in == null) {
99 throw new NullPointerException("in is null");
100 }
101 if (charset == null)
102 throw new NullPointerException("charset is null");
103 this.zc = ZipCoder.get(charset);
104 }
105
106 /**
107 * Reads the next ZIP file entry and positions the stream at the
108 * beginning of the entry data.
109 * @return the next ZIP file entry, or null if there are no more entries
110 * @exception ZipException if a ZIP file error has occurred
111 * @exception IOException if an I/O error has occurred
112 */
113 public ZipEntry getNextEntry() throws IOException {
114 ensureOpen();
115 if (entry != null) {
116 closeEntry();
117 }
118 crc.reset();
119 inf.reset();
120 if ((entry = readLOC()) == null) {
121 return null;
122 }
123 if (entry.method == STORED) {
124 remaining = entry.size;
125 }
126 entryEOF = false;
127 return entry;
128 }
129
130 /**
131 * Closes the current ZIP entry and positions the stream for reading the
132 * next entry.
133 * @exception ZipException if a ZIP file error has occurred
134 * @exception IOException if an I/O error has occurred
135 */
136 public void closeEntry() throws IOException {
137 ensureOpen();
138 while (read(tmpbuf, 0, tmpbuf.length) != -1) ;
139 entryEOF = true;
140 }
141
142 /**
143 * Returns 0 after EOF has reached for the current entry data,
144 * otherwise always return 1.
145 * <p>
146 * Programs should not count on this method to return the actual number
147 * of bytes that could be read without blocking.
148 *
149 * @return 1 before EOF and 0 after EOF has reached for current entry.
150 * @exception IOException if an I/O error occurs.
151 *
152 */
153 public int available() throws IOException {
154 ensureOpen();
155 if (entryEOF) {
156 return 0;
157 } else {
158 return 1;
159 }
160 }
161
162 /**
163 * Reads from the current ZIP entry into an array of bytes.
164 * If <code>len</code> is not zero, the method
165 * blocks until some input is available; otherwise, no
166 * bytes are read and <code>0</code> is returned.
167 * @param b the buffer into which the data is read
168 * @param off the start offset in the destination array <code>b</code>
169 * @param len the maximum number of bytes read
170 * @return the actual number of bytes read, or -1 if the end of the
171 * entry is reached
172 * @exception NullPointerException if <code>b</code> is <code>null</code>.
173 * @exception IndexOutOfBoundsException if <code>off</code> is negative,
174 * <code>len</code> is negative, or <code>len</code> is greater than
175 * <code>b.length - off</code>
176 * @exception ZipException if a ZIP file error has occurred
177 * @exception IOException if an I/O error has occurred
178 */
179 public int read(byte[] b, int off, int len) throws IOException {
180 ensureOpen();
181 if (off < 0 || len < 0 || off > b.length - len) {
182 throw new IndexOutOfBoundsException();
183 } else if (len == 0) {
184 return 0;
185 }
186
187 if (entry == null) {
188 return -1;
189 }
190 switch (entry.method) {
191 case DEFLATED:
192 len = super.read(b, off, len);
193 if (len == -1) {
194 readEnd(entry);
195 entryEOF = true;
196 entry = null;
197 } else {
198 crc.update(b, off, len);
199 }
200 return len;
201 case STORED:
202 if (remaining <= 0) {
203 entryEOF = true;
204 entry = null;
205 return -1;
206 }
207 if (len > remaining) {
208 len = (int)remaining;
209 }
210 len = in.read(b, off, len);
211 if (len == -1) {
212 throw new ZipException("unexpected EOF");
213 }
214 crc.update(b, off, len);
215 remaining -= len;
216 if (remaining == 0 && entry.crc != crc.getValue()) {
217 throw new ZipException(
218 "invalid entry CRC (expected 0x" + Long.toHexString(entry.crc) +
219 " but got 0x" + Long.toHexString(crc.getValue()) + ")");
220 }
221 return len;
222 default:
223 throw new ZipException("invalid compression method");
224 }
225 }
226
227 /**
228 * Skips specified number of bytes in the current ZIP entry.
229 * @param n the number of bytes to skip
230 * @return the actual number of bytes skipped
231 * @exception ZipException if a ZIP file error has occurred
232 * @exception IOException if an I/O error has occurred
233 * @exception IllegalArgumentException if n < 0
234 */
235 public long skip(long n) throws IOException {
236 if (n < 0) {
237 throw new IllegalArgumentException("negative skip length");
238 }
239 ensureOpen();
240 int max = (int)Math.min(n, Integer.MAX_VALUE);
241 int total = 0;
242 while (total < max) {
243 int len = max - total;
244 if (len > tmpbuf.length) {
245 len = tmpbuf.length;
246 }
247 len = read(tmpbuf, 0, len);
248 if (len == -1) {
249 entryEOF = true;
250 break;
251 }
252 total += len;
253 }
254 return total;
255 }
256
257 /**
258 * Closes this input stream and releases any system resources associated
259 * with the stream.
260 * @exception IOException if an I/O error has occurred
261 */
262 public void close() throws IOException {
263 if (!closed) {
264 super.close();
265 closed = true;
266 }
267 }
268
269 private byte[] b = new byte[256];
270
271 /*
272 * Reads local file (LOC) header for next entry.
273 */
274 private ZipEntry readLOC() throws IOException {
275 try {
276 readFully(tmpbuf, 0, LOCHDR);
277 } catch (EOFException e) {
278 return null;
279 }
280 if (get32(tmpbuf, 0) != LOCSIG) {
281 return null;
282 }
283 // get flag first, we need check EFS.
284 flag = get16(tmpbuf, LOCFLG);
285 // get the entry name and create the ZipEntry first
286 int len = get16(tmpbuf, LOCNAM);
287 int blen = b.length;
288 if (len > blen) {
289 do
290 blen = blen * 2;
291 while (len > blen);
292 b = new byte[blen];
293 }
294 readFully(b, 0, len);
295 // Force to use UTF-8 if the EFS bit is ON, even the cs is NOT UTF-8
296 ZipEntry e = createZipEntry(((flag & EFS) != 0)
297 ? zc.toStringUTF8(b, len)
298 : zc.toString(b, len));
299 // now get the remaining fields for the entry
300 if ((flag & 1) == 1) {
301 throw new ZipException("encrypted ZIP entry not supported");
302 }
303 e.method = get16(tmpbuf, LOCHOW);
304 e.time = get32(tmpbuf, LOCTIM);
305 if ((flag & 8) == 8) {
306 /* "Data Descriptor" present */
307 if (e.method != DEFLATED) {
308 throw new ZipException(
309 "only DEFLATED entries can have EXT descriptor");
310 }
311 } else {
312 e.crc = get32(tmpbuf, LOCCRC);
313 e.csize = get32(tmpbuf, LOCSIZ);
314 e.size = get32(tmpbuf, LOCLEN);
315 }
316 len = get16(tmpbuf, LOCEXT);
317 if (len > 0) {
318 byte[] bb = new byte[len];
319 readFully(bb, 0, len);
320 e.setExtra(bb);
321 // extra fields are in "HeaderID(2)DataSize(2)Data... format
322 if (e.csize == ZIP64_MAGICVAL || e.size == ZIP64_MAGICVAL) {
323 int off = 0;
324 while (off + 4 < len) {
325 int sz = get16(bb, off + 2);
326 if (get16(bb, off) == ZIP64_EXTID) {
327 off += 4;
328 // LOC extra zip64 entry MUST include BOTH original and
329 // compressed file size fields
330 if (sz < 16 || (off + sz) > len ) {
331 // Invalid zip64 extra fields, simply skip. Even it's
332 // rare, it's possible the entry size happens to be
333 // the magic value and it "accidnetly" has some bytes
334 // in extra match the id.
335 return e;
336 }
337 e.size = get64(bb, off);
338 e.csize = get64(bb, off + 8);
339 break;
340 }
341 off += (sz + 4);
342 }
343 }
344 }
345 return e;
346 }
347
348 /**
349 * Creates a new <code>ZipEntry</code> object for the specified
350 * entry name.
351 *
352 * @param name the ZIP file entry name
353 * @return the ZipEntry just created
354 */
355 protected ZipEntry createZipEntry(String name) {
356 return new ZipEntry(name);
357 }
358
359 /*
360 * Reads end of deflated entry as well as EXT descriptor if present.
361 */
362 private void readEnd(ZipEntry e) throws IOException {
363 int n = inf.getRemaining();
364 if (n > 0) {
365 ((PushbackInputStream)in).unread(buf, len - n, n);
366 }
367 if ((flag & 8) == 8) {
368 /* "Data Descriptor" present */
369 if (inf.getBytesWritten() > ZIP64_MAGICVAL ||
370 inf.getBytesRead() > ZIP64_MAGICVAL) {
371 // ZIP64 format
372 readFully(tmpbuf, 0, ZIP64_EXTHDR);
373 long sig = get32(tmpbuf, 0);
374 if (sig != EXTSIG) { // no EXTSIG present
375 e.crc = sig;
376 e.csize = get64(tmpbuf, ZIP64_EXTSIZ - ZIP64_EXTCRC);
377 e.size = get64(tmpbuf, ZIP64_EXTLEN - ZIP64_EXTCRC);
378 ((PushbackInputStream)in).unread(
379 tmpbuf, ZIP64_EXTHDR - ZIP64_EXTCRC - 1, ZIP64_EXTCRC);
380 } else {
381 e.crc = get32(tmpbuf, ZIP64_EXTCRC);
382 e.csize = get64(tmpbuf, ZIP64_EXTSIZ);
383 e.size = get64(tmpbuf, ZIP64_EXTLEN);
384 }
385 } else {
386 readFully(tmpbuf, 0, EXTHDR);
387 long sig = get32(tmpbuf, 0);
388 if (sig != EXTSIG) { // no EXTSIG present
389 e.crc = sig;
390 e.csize = get32(tmpbuf, EXTSIZ - EXTCRC);
391 e.size = get32(tmpbuf, EXTLEN - EXTCRC);
392 ((PushbackInputStream)in).unread(
393 tmpbuf, EXTHDR - EXTCRC - 1, EXTCRC);
394 } else {
395 e.crc = get32(tmpbuf, EXTCRC);
396 e.csize = get32(tmpbuf, EXTSIZ);
397 e.size = get32(tmpbuf, EXTLEN);
398 }
399 }
400 }
401 if (e.size != inf.getBytesWritten()) {
402 throw new ZipException(
403 "invalid entry size (expected " + e.size +
404 " but got " + inf.getBytesWritten() + " bytes)");
405 }
406 if (e.csize != inf.getBytesRead()) {
407 throw new ZipException(
408 "invalid entry compressed size (expected " + e.csize +
409 " but got " + inf.getBytesRead() + " bytes)");
410 }
411 if (e.crc != crc.getValue()) {
412 throw new ZipException(
413 "invalid entry CRC (expected 0x" + Long.toHexString(e.crc) +
414 " but got 0x" + Long.toHexString(crc.getValue()) + ")");
415 }
416 }
417
418 /*
419 * Reads bytes, blocking until all bytes are read.
420 */
421 private void readFully(byte[] b, int off, int len) throws IOException {
422 while (len > 0) {
423 int n = in.read(b, off, len);
424 if (n == -1) {
425 throw new EOFException();
426 }
427 off += n;
428 len -= n;
429 }
430 }
431
432 /*
433 * Fetches unsigned 16-bit value from byte array at specified offset.
434 * The bytes are assumed to be in Intel (little-endian) byte order.
435 */
436 private static final int get16(byte b[], int off) {
437 return (b[off] & 0xff) | ((b[off+1] & 0xff) << 8);
438 }
439
440 /*
441 * Fetches unsigned 32-bit value from byte array at specified offset.
442 * The bytes are assumed to be in Intel (little-endian) byte order.
443 */
444 private static final long get32(byte b[], int off) {
445 return (get16(b, off) | ((long)get16(b, off+2) << 16)) & 0xffffffffL;
446 }
447
448 /*
449 * Fetches signed 64-bit value from byte array at specified offset.
450 * The bytes are assumed to be in Intel (little-endian) byte order.
451 */
452 private static final long get64(byte b[], int off) {
453 return get32(b, off) | (get32(b, off+4) << 32);
454 }
455 }