1 /*
2 * Copyright (c) 1996, 2015, 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 java.nio.charset.StandardCharsets;
34 import static java.util.zip.ZipConstants64.*;
35 import static java.util.zip.ZipUtils.*;
36
37 /**
38 * This class implements an input stream filter for reading files in the
39 * ZIP file format. Includes support for both compressed and uncompressed
40 * entries.
41 *
42 * @author David Connelly
43 */
44 public
45 class ZipInputStream extends InflaterInputStream implements ZipConstants {
46 private ZipEntry entry;
47 private int flag;
48 private CRC32 crc = new CRC32();
49 private long remaining;
50 private byte[] tmpbuf = new byte[512];
51
52 private static final int STORED = ZipEntry.STORED;
53 private static final int DEFLATED = ZipEntry.DEFLATED;
54
55 private boolean closed = false;
56 // this flag is set to true after EOF has reached for
57 // one entry
58 private boolean entryEOF = false;
59
60 private ZipCoder zc;
61
62 private ZipCryption zipCryption;
63
64 /**
65 * Check to make sure that this stream has not been closed
66 */
67 private void ensureOpen() throws IOException {
68 if (closed) {
69 throw new IOException("Stream closed");
70 }
71 }
72
73 /**
74 * Creates a new ZIP input stream.
75 *
76 * <p>The UTF-8 {@link java.nio.charset.Charset charset} is used to
77 * decode the entry names.
78 *
79 * @param in the actual input stream
80 */
81 public ZipInputStream(InputStream in) {
82 this(in, StandardCharsets.UTF_8);
83 }
84
85 /**
86 * Creates a new ZIP input stream.
87 *
88 * @param in the actual input stream
89 *
90 * @param charset
91 * The {@linkplain java.nio.charset.Charset charset} to be
92 * used to decode the ZIP entry name (ignored if the
93 * <a href="package-summary.html#lang_encoding"> language
94 * encoding bit</a> of the ZIP entry's general purpose bit
95 * flag is set).
96 *
97 * @since 1.7
98 */
99 public ZipInputStream(InputStream in, Charset charset) {
100 super(new PushbackInputStream(in, 512), new Inflater(true), 512);
101 usesDefaultInflater = true;
102 if(in == null) {
103 throw new NullPointerException("in is null");
104 }
105 if (charset == null)
106 throw new NullPointerException("charset is null");
107 this.zc = ZipCoder.get(charset);
108 }
109
110 /**
111 * Reads the next ZIP file entry and positions the stream at the
112 * beginning of the entry data.
113 * @return the next ZIP file entry, or null if there are no more entries
114 * @exception ZipException if a ZIP file error has occurred
115 * @exception IOException if an I/O error has occurred
116 */
117 public ZipEntry getNextEntry() throws IOException {
118 return getNextEntry(null);
119 }
120
121 /**
122 * Reads the next ZIP file entry and positions the stream at the
123 * beginning of the entry data.
124 * @param zipCryption instance of ZipCryption
125 * @return the next ZIP file entry, or null if there are no more entries
126 * @exception ZipException if a ZIP file error has occurred
127 * @exception IOException if an I/O error has occurred
128 */
129 public ZipEntry getNextEntry(ZipCryption zipCryption) throws IOException {
130 ensureOpen();
131 if (entry != null) {
132 closeEntry();
133 }
134 crc.reset();
135 inf.reset();
136 if ((entry = readLOC(zipCryption)) == null) {
137 return null;
138 }
139 if (entry.method == STORED) {
140 remaining = entry.size;
141 }
142 entryEOF = false;
143 return entry;
144 }
145
146 /**
147 * Closes the current ZIP entry and positions the stream for reading the
148 * next entry.
149 * @exception ZipException if a ZIP file error has occurred
150 * @exception IOException if an I/O error has occurred
151 */
152 public void closeEntry() throws IOException {
153 ensureOpen();
154 while (read(tmpbuf, 0, tmpbuf.length) != -1) ;
155 entryEOF = true;
156 }
157
158 /**
159 * Returns 0 after EOF has reached for the current entry data,
160 * otherwise always return 1.
161 * <p>
162 * Programs should not count on this method to return the actual number
163 * of bytes that could be read without blocking.
164 *
165 * @return 1 before EOF and 0 after EOF has reached for current entry.
166 * @exception IOException if an I/O error occurs.
167 *
168 */
169 public int available() throws IOException {
170 ensureOpen();
171 if (entryEOF) {
172 return 0;
173 } else {
174 return 1;
175 }
176 }
177
178 /**
179 * Reads from the current ZIP entry into an array of bytes.
180 * If <code>len</code> is not zero, the method
181 * blocks until some input is available; otherwise, no
182 * bytes are read and <code>0</code> is returned.
183 * @param b the buffer into which the data is read
184 * @param off the start offset in the destination array <code>b</code>
185 * @param len the maximum number of bytes read
186 * @return the actual number of bytes read, or -1 if the end of the
187 * entry is reached
188 * @exception NullPointerException if <code>b</code> is <code>null</code>.
189 * @exception IndexOutOfBoundsException if <code>off</code> is negative,
190 * <code>len</code> is negative, or <code>len</code> is greater than
191 * <code>b.length - off</code>
192 * @exception ZipException if a ZIP file error has occurred
193 * @exception IOException if an I/O error has occurred
194 */
195 public int read(byte[] b, int off, int len) throws IOException {
196 ensureOpen();
197 if (off < 0 || len < 0 || off > b.length - len) {
198 throw new IndexOutOfBoundsException();
199 } else if (len == 0) {
200 return 0;
201 }
202
203 if (entry == null) {
204 return -1;
205 }
206 switch (entry.method) {
207 case DEFLATED:
208 len = super.read(b, off, len);
209 if (len == -1) {
210 readEnd(entry);
211 entryEOF = true;
212 entry = null;
213 } else {
214 crc.update(b, off, len);
215 }
216 return len;
217 case STORED:
218 if (remaining <= 0) {
219 entryEOF = true;
220 entry = null;
221 return -1;
222 }
223 if (len > remaining) {
224 len = (int)remaining;
225 }
226 len = in.read(b, off, len);
227 if (len == -1) {
228 throw new ZipException("unexpected EOF");
229 }
230 if (zipCryption != null) {
231 zipCryption.decryptBytes(b, off, len);
232 }
233 crc.update(b, off, len);
234 remaining -= len;
235 if (remaining == 0 && entry.crc != crc.getValue()) {
236 throw new ZipException(
237 "invalid entry CRC (expected 0x" + Long.toHexString(entry.crc) +
238 " but got 0x" + Long.toHexString(crc.getValue()) + ")");
239 }
240 return len;
241 default:
242 throw new ZipException("invalid compression method");
243 }
244 }
245
246 /**
247 * Skips specified number of bytes in the current ZIP entry.
248 * @param n the number of bytes to skip
249 * @return the actual number of bytes skipped
250 * @exception ZipException if a ZIP file error has occurred
251 * @exception IOException if an I/O error has occurred
252 * @exception IllegalArgumentException if {@code n < 0}
253 */
254 public long skip(long n) throws IOException {
255 if (n < 0) {
256 throw new IllegalArgumentException("negative skip length");
257 }
258 ensureOpen();
259 int max = (int)Math.min(n, Integer.MAX_VALUE);
260 int total = 0;
261 while (total < max) {
262 int len = max - total;
263 if (len > tmpbuf.length) {
264 len = tmpbuf.length;
265 }
266 len = read(tmpbuf, 0, len);
267 if (len == -1) {
268 entryEOF = true;
269 break;
270 }
271 total += len;
272 }
273 return total;
274 }
275
276 /**
277 * Closes this input stream and releases any system resources associated
278 * with the stream.
279 * @exception IOException if an I/O error has occurred
280 */
281 public void close() throws IOException {
282 if (!closed) {
283 super.close();
284 closed = true;
285 }
286 }
287
288 private byte[] b = new byte[256];
289
290 /*
291 * Reads local file (LOC) header for next entry.
292 */
293 private ZipEntry readLOC(ZipCryption zipCryption) throws IOException {
294 this.zipCryption = zipCryption;
295
296 try {
297 readFully(tmpbuf, 0, LOCHDR);
298 } catch (EOFException e) {
299 return null;
300 }
301 if (get32(tmpbuf, 0) != LOCSIG) {
302 return null;
303 }
304 // get flag first, we need check EFS and encryption.
305 flag = get16(tmpbuf, LOCFLG);
306 // get the entry name and create the ZipEntry first
307 int len = get16(tmpbuf, LOCNAM);
308 int blen = b.length;
309 if (len > blen) {
310 do {
311 blen = blen * 2;
312 } while (len > blen);
313 b = new byte[blen];
314 }
315 readFully(b, 0, len);
316 // Force to use UTF-8 if the EFS bit is ON, even the cs is NOT UTF-8
317 ZipEntry e = createZipEntry(((flag & EFS) != 0)
318 ? zc.toStringUTF8(b, len)
319 : zc.toString(b, len));
320 e.flag = flag;
321 // now get the remaining fields for the entry
322 if (((flag & 1) == 1) && (zipCryption == null)) {
323 throw new ZipException("ZipCryption is required.");
324 }
325 e.method = get16(tmpbuf, LOCHOW);
326 e.xdostime = get32(tmpbuf, LOCTIM);
327 if ((flag & 8) == 8) {
328 /* "Data Descriptor" present */
329 if (e.method != DEFLATED) {
330 throw new ZipException(
331 "only DEFLATED entries can have EXT descriptor");
332 }
333 } else {
334 e.crc = get32(tmpbuf, LOCCRC);
335 e.csize = get32(tmpbuf, LOCSIZ);
336 e.size = get32(tmpbuf, LOCLEN);
337 }
338 len = get16(tmpbuf, LOCEXT);
339 if (len > 0) {
340 byte[] extra = new byte[len];
341 readFully(extra, 0, len);
342 e.setExtra0(extra,
343 e.csize == ZIP64_MAGICVAL || e.size == ZIP64_MAGICVAL);
344 }
345
346 if (zipCryption != null) {
347 zipCryption.reset();
348 super.setZipCryption(zipCryption);
349
350 byte[] encryptionHeader =
351 new byte[zipCryption.getEncryptionHeaderSize()];
352 readFully(encryptionHeader, 0, encryptionHeader.length);
353 zipCryption.decryptBytes(encryptionHeader);
354
355 if (!zipCryption.isValid(e, encryptionHeader)) {
356 throw new ZipException("possibly incorrect passphrase");
357 }
358
359 }
360
361 return e;
362 }
363
364 /**
365 * Creates a new <code>ZipEntry</code> object for the specified
366 * entry name.
367 *
368 * @param name the ZIP file entry name
369 * @return the ZipEntry just created
370 */
371 protected ZipEntry createZipEntry(String name) {
372 return new ZipEntry(name);
373 }
374
375 /**
376 * Reads end of deflated entry as well as EXT descriptor if present.
377 *
378 * Local headers for DEFLATED entries may optionally be followed by a
379 * data descriptor, and that data descriptor may optionally contain a
380 * leading signature (EXTSIG).
381 *
382 * From the zip spec http://www.pkware.com/documents/casestudies/APPNOTE.TXT
383 *
384 * """Although not originally assigned a signature, the value 0x08074b50
385 * has commonly been adopted as a signature value for the data descriptor
386 * record. Implementers should be aware that ZIP files may be
387 * encountered with or without this signature marking data descriptors
388 * and should account for either case when reading ZIP files to ensure
389 * compatibility."""
390 */
391 private void readEnd(ZipEntry e) throws IOException {
392 int n = inf.getRemaining();
393 if (n > 0) {
394 ((PushbackInputStream)in).unread(
395 (zipCryption == null) ? buf : originBuf, len - n, n);
396 }
397 if ((flag & 8) == 8) {
398 /* "Data Descriptor" present */
399 if (inf.getBytesWritten() > ZIP64_MAGICVAL ||
400 inf.getBytesRead() > ZIP64_MAGICVAL) {
401 // ZIP64 format
402 readFully(tmpbuf, 0, ZIP64_EXTHDR);
403 long sig = get32(tmpbuf, 0);
404 if (sig != EXTSIG) { // no EXTSIG present
405 e.crc = sig;
406 e.csize = get64(tmpbuf, ZIP64_EXTSIZ - ZIP64_EXTCRC);
407 e.size = get64(tmpbuf, ZIP64_EXTLEN - ZIP64_EXTCRC);
408 ((PushbackInputStream)in).unread(
409 tmpbuf, ZIP64_EXTHDR - ZIP64_EXTCRC, ZIP64_EXTCRC);
410 } else {
411 e.crc = get32(tmpbuf, ZIP64_EXTCRC);
412 e.csize = get64(tmpbuf, ZIP64_EXTSIZ);
413 e.size = get64(tmpbuf, ZIP64_EXTLEN);
414 }
415 } else {
416 readFully(tmpbuf, 0, EXTHDR);
417 long sig = get32(tmpbuf, 0);
418 if (sig != EXTSIG) { // no EXTSIG present
419 e.crc = sig;
420 e.csize = get32(tmpbuf, EXTSIZ - EXTCRC);
421 e.size = get32(tmpbuf, EXTLEN - EXTCRC);
422 ((PushbackInputStream)in).unread(
423 tmpbuf, EXTHDR - EXTCRC, EXTCRC);
424 } else {
425 e.crc = get32(tmpbuf, EXTCRC);
426 e.csize = get32(tmpbuf, EXTSIZ);
427 e.size = get32(tmpbuf, EXTLEN);
428 }
429 }
430 }
431 if (e.size != inf.getBytesWritten()) {
432 throw new ZipException(
433 "invalid entry size (expected " + e.size +
434 " but got " + inf.getBytesWritten() + " bytes)");
435 }
436 if (zipCryption != null) {
437 e.csize -= zipCryption.getEncryptionHeaderSize();
438 }
439 if (e.csize != inf.getBytesRead()) {
440 throw new ZipException(
441 "invalid entry compressed size (expected " + e.csize +
442 " but got " + inf.getBytesRead() + " bytes)");
443 }
444 if (e.crc != crc.getValue()) {
445 throw new ZipException(
446 "invalid entry CRC (expected 0x" + Long.toHexString(e.crc) +
447 " but got 0x" + Long.toHexString(crc.getValue()) + ")");
448 }
449 }
450
451 /*
452 * Reads bytes, blocking until all bytes are read.
453 */
454 private void readFully(byte[] b, int off, int len) throws IOException {
455 while (len > 0) {
456 int n = in.read(b, off, len);
457 if (n == -1) {
458 throw new EOFException();
459 }
460 off += n;
461 len -= n;
462 }
463 }
464
465 }