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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301
|
/* java.util.zip.GZIPInputStream
Copyright (C) 2001 Free Software Foundation, Inc.
This file is part of GNU Classpath.
GNU Classpath is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 2, or (at your option)
any later version.
GNU Classpath 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 for more details.
You should have received a copy of the GNU General Public License
along with GNU Classpath; see the file COPYING. If not, write to the
Free Software Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA
02111-1307 USA.
As a special exception, if you link this library with other files to
produce an executable, this library does not by itself cause the
resulting executable to be covered by the GNU General Public License.
This exception does not however invalidate any other reasons why the
executable file might be covered by the GNU General Public License. */
package java.util.zip;
import java.io.InputStream;
import java.io.IOException;
import java.io.EOFException;
/**
* This filter stream is used to decompress a "GZIP" format stream.
* The "GZIP" format is described in RFC 1952.
*
* @author John Leuner
* @since JDK 1.1
*/
public class GZIPInputStream extends InflaterInputStream implements GZIPConstants {
//Variables
/** CRC-32 value for uncompressed data
*/
protected CRC32 crc;
/** Indicates end of stream */
protected boolean eos;
/**
* Creates a GZIPInputStream with the default buffer size
*
*
* @param in The stream to read compressed data from
* (in GZIP format)
*/
public GZIPInputStream(InputStream in) throws IOException
{
this(in, 4096);
}
/**
* Creates a GZIPInputStream with the specified buffer size
*
*
* @param in The stream to read compressed data from
* (in GZIP format)
* @param size Size of the buffer to use
*/
public GZIPInputStream(InputStream in, int size) throws IOException
{
super(in, new Inflater(true), size);
crc = new CRC32();
}
/**
* Closes the input stream
*
*/
public void close() throws IOException
{
super.close();
}
/**
* Reads uncompressed data into an array of bytes
*
*
* @param buf the buffer to read uncompressed data into
* @param offset the offset indicating where the data should be placed
* @param len the number of uncompressed bytes to be read
*/
public int read(byte[] buf, int offset, int len) throws IOException
{
// We first have to slurp in the GZIP header, then we feed all the
// rest of the data to the superclass.
//
// As we do that we continually update the CRC32. Once the data is
// finished, we check the CRC32
//
// This means we don't need our own buffer, as everything is done
// in the superclass.
if (!readGZIPHeader)
readHeader();
if (eos)
return -1;
// System.err.println("GZIPIS.read(byte[], off, len ... " + offset + " and len " + len);
//We don't have to read the header, so we just grab data from the superclass
int numRead = super.read(buf, offset, len);
if (numRead > 0)
crc.update(buf, offset, numRead);
if (inf.finished())
readFooter();
return numRead;
}
private void readHeader() throws IOException
{
/* 1. Check the two magic bytes */
CRC32 headCRC = new CRC32();
int magic = in.read();
if (magic < 0)
{
eos = true;
return;
}
headCRC.update(magic);
if (magic != (GZIP_MAGIC >> 8))
{
throw new IOException("Error in GZIP header, first byte doesn't match");
}
magic = in.read();
if (magic != (GZIP_MAGIC & 0xff))
{
throw new IOException("Error in GZIP header, second byte doesn't match");
}
headCRC.update(magic);
/* 2. Check the compression type (must be 8) */
int CM = in.read();
if (CM != 8)
{
throw new IOException("Error in GZIP header, data not in deflate format");
}
headCRC.update(CM);
/* 3. Check the flags */
int flags = in.read();
if (flags < 0)
throw new EOFException("Early EOF in GZIP header");
headCRC.update(flags);
/* This flag byte is divided into individual bits as follows:
bit 0 FTEXT
bit 1 FHCRC
bit 2 FEXTRA
bit 3 FNAME
bit 4 FCOMMENT
bit 5 reserved
bit 6 reserved
bit 7 reserved
*/
/* 3.1 Check the reserved bits are zero */
if ((flags & 0xd0) != 0)
{
throw new IOException("Reserved flag bits in GZIP header != 0");
}
/* 4.-6. Skip the modification time, extra flags, and OS type */
for (int i=0; i< 6; i++)
{
int readByte = in.read();
if (readByte < 0)
throw new EOFException("Early EOF in GZIP header");
headCRC.update(readByte);
}
/* 7. Read extra field */
if ((flags & FEXTRA) != 0)
{
/* Skip subfield id */
for (int i=0; i< 2; i++)
{
int readByte = in.read();
if (readByte < 0)
throw new EOFException("Early EOF in GZIP header");
headCRC.update(readByte);
}
if (in.read() < 0 || in.read() < 0)
throw new EOFException("Early EOF in GZIP header");
int len1, len2, extraLen;
len1 = in.read();
len2 = in.read();
if ((len1 < 0) || (len2 < 0))
throw new EOFException("Early EOF in GZIP header");
headCRC.update(len1);
headCRC.update(len2);
extraLen = (len1 << 8) | len2;
for (int i = 0; i < extraLen;i++)
{
int readByte = in.read();
if (readByte < 0)
throw new EOFException("Early EOF in GZIP header");
headCRC.update(readByte);
}
}
/* 8. Read file name */
if ((flags & FNAME) != 0)
{
int readByte;
while ( (readByte = in.read()) > 0)
headCRC.update(readByte);
if (readByte < 0)
throw new EOFException("Early EOF in GZIP file name");
headCRC.update(readByte);
}
/* 9. Read comment */
if ((flags & FCOMMENT) != 0)
{
int readByte;
while ( (readByte = in.read()) > 0)
headCRC.update(readByte);
if (readByte < 0)
throw new EOFException("Early EOF in GZIP comment");
headCRC.update(readByte);
}
/* 10. Read header CRC */
if ((flags & FHCRC) != 0)
{
int tempByte;
int crcval = in.read();
if (crcval < 0)
throw new EOFException("Early EOF in GZIP header");
tempByte = in.read();
if (tempByte < 0)
throw new EOFException("Early EOF in GZIP header");
crcval = (crcval << 8) | tempByte;
if (crcval != ((int) headCRC.getValue() & 0xffff))
throw new IOException("Header CRC value mismatch");
}
readGZIPHeader = true;
//System.err.println("Read GZIP header");
}
private void readFooter() throws IOException
{
byte[] footer = new byte[8];
int avail = inf.getRemaining();
if (avail > 8)
avail = 8;
System.arraycopy(buf, len - inf.getRemaining(), footer, 0, avail);
int needed = 8 - avail;
while (needed > 0)
{
int count = in.read(footer, 8-needed, needed);
if (count <= 0)
throw new EOFException("Early EOF in GZIP footer");
needed -= count; //Jewel Jan 16
}
int crcval = (footer[0] & 0xff) | ((footer[1] & 0xff) << 8)
| ((footer[2] & 0xff) << 16) | (footer[3] << 24);
if (crcval != (int) crc.getValue())
throw new IOException("GZIP crc sum mismatch, theirs \"" + Integer.toHexString(crcval) + "\" and ours \"" + Integer.toHexString( (int) crc.getValue()));
int total = (footer[4] & 0xff) | ((footer[5] & 0xff) << 8)
| ((footer[6] & 0xff) << 16) | (footer[7] << 24);
if (total != inf.getTotalOut())
throw new IOException("Number of bytes mismatch");
/* XXX Should we support multiple members.
* Difficult, since there may be some bytes still in buf
*/
eos = true;
}
/* Have we read the GZIP header yet? */
private boolean readGZIPHeader;
}
|