summaryrefslogtreecommitdiff
path: root/lib/content_encoding.c
blob: 97f834177437f5956b42dcc98d9d175fbc64e255 (plain)
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
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
/***************************************************************************
 *                                  _   _ ____  _
 *  Project                     ___| | | |  _ \| |
 *                             / __| | | | |_) | |
 *                            | (__| |_| |  _ <| |___
 *                             \___|\___/|_| \_\_____|
 *
 * Copyright (C) 1998 - 2006, Daniel Stenberg, <daniel@haxx.se>, et al.
 *
 * This software is licensed as described in the file COPYING, which
 * you should have received as part of this distribution. The terms
 * are also available at http://curl.haxx.se/docs/copyright.html.
 *
 * You may opt to use, copy, modify, merge, publish, distribute and/or sell
 * copies of the Software, and permit persons to whom the Software is
 * furnished to do so, under the terms of the COPYING file.
 *
 * This software is distributed on an "AS IS" basis, WITHOUT WARRANTY OF ANY
 * KIND, either express or implied.
 *
 * $Id$
 ***************************************************************************/

#include "setup.h"

#ifdef HAVE_LIBZ

#include <stdlib.h>
#include <string.h>

#include "urldata.h"
#include <curl/curl.h>
#include "sendf.h"
#include "content_encoding.h"
#include "memory.h"

#include "memdebug.h"

/* Comment this out if zlib is always going to be at least ver. 1.2.0.4
   (doing so will reduce code size slightly). */
#define OLD_ZLIB_SUPPORT 1

#define DSIZ 0x10000             /* buffer size for decompressed data */

#define GZIP_MAGIC_0 0x1f
#define GZIP_MAGIC_1 0x8b

/* gzip flag byte */
#define ASCII_FLAG   0x01 /* bit 0 set: file probably ascii text */
#define HEAD_CRC     0x02 /* bit 1 set: header CRC present */
#define EXTRA_FIELD  0x04 /* bit 2 set: extra field present */
#define ORIG_NAME    0x08 /* bit 3 set: original file name present */
#define COMMENT      0x10 /* bit 4 set: file comment present */
#define RESERVED     0xE0 /* bits 5..7: reserved */

enum zlibState {
  ZLIB_UNINIT,          /* uninitialized */
  ZLIB_INIT,            /* initialized */
  ZLIB_GZIP_HEADER,     /* reading gzip header */
  ZLIB_GZIP_INFLATING,  /* inflating gzip stream */
  ZLIB_INIT_GZIP        /* initialized in transparent gzip mode */
};

static CURLcode
process_zlib_error(struct connectdata *conn, z_stream *z)
{
  struct SessionHandle *data = conn->data;
  if (z->msg)
    failf (data, "Error while processing content unencoding: %s",
           z->msg);
  else
    failf (data, "Error while processing content unencoding: "
           "Unknown failure within decompression software.");

  return CURLE_BAD_CONTENT_ENCODING;
}

static CURLcode
exit_zlib(z_stream *z, bool *zlib_init, CURLcode result)
{
  inflateEnd(z);
  *zlib_init = ZLIB_UNINIT;
  return result;
}

static CURLcode
inflate_stream(struct connectdata *conn,
               struct Curl_transfer_keeper *k)
{
  int allow_restart = 1;
  z_stream *z = &k->z;          /* zlib state structure */
  uInt nread = z->avail_in;
  Bytef *orig_in = z->next_in;
  int status;                   /* zlib status */
  CURLcode result = CURLE_OK;   /* Curl_client_write status */
  char *decomp;                 /* Put the decompressed data here. */

  /* Dynamically allocate a buffer for decompression because it's uncommonly
     large to hold on the stack */
  decomp = (char*)malloc(DSIZ);
  if (decomp == NULL) {
    return exit_zlib(z, &k->zlib_init, CURLE_OUT_OF_MEMORY);
  }

  /* because the buffer size is fixed, iteratively decompress and transfer to
     the client via client_write. */
  for (;;) {
    /* (re)set buffer for decompressed output for every iteration */
    z->next_out = (Bytef *)decomp;
    z->avail_out = DSIZ;

    status = inflate(z, Z_SYNC_FLUSH);
    if (status == Z_OK || status == Z_STREAM_END) {
      allow_restart = 0;
      if(DSIZ - z->avail_out) {
        result = Curl_client_write(conn, CLIENTWRITE_BODY, decomp,
                                   DSIZ - z->avail_out);
        /* if !CURLE_OK, clean up, return */
        if (result) {
          free(decomp);
          return exit_zlib(z, &k->zlib_init, result);
        }
      }

      /* Done? clean up, return */
      if (status == Z_STREAM_END) {
        free(decomp);
        if (inflateEnd(z) == Z_OK)
          return exit_zlib(z, &k->zlib_init, result);
        else
          return exit_zlib(z, &k->zlib_init, process_zlib_error(conn, z));
      }

      /* Done with these bytes, exit */
      if (status == Z_OK && z->avail_in == 0) {
        free(decomp);
        return result;
      }
    }
    else if (allow_restart && status == Z_DATA_ERROR) {
      /* some servers seem to not generate zlib headers, so this is an attempt
         to fix and continue anyway */

      inflateReset(z);
      if (inflateInit2(z, -MAX_WBITS) != Z_OK) {
        return process_zlib_error(conn, z);
      }
      z->next_in = orig_in;
      z->avail_in = nread;
      allow_restart = 0;
      continue;
    }
    else {                      /* Error; exit loop, handle below */
      free(decomp);
      return exit_zlib(z, &k->zlib_init, process_zlib_error(conn, z));
    }
  }
  /* Will never get here */
}

CURLcode
Curl_unencode_deflate_write(struct connectdata *conn,
                            struct Curl_transfer_keeper *k,
                            ssize_t nread)
{
  z_stream *z = &k->z;          /* zlib state structure */

  /* Initialize zlib? */
  if (k->zlib_init == ZLIB_UNINIT) {
    z->zalloc = (alloc_func)Z_NULL;
    z->zfree = (free_func)Z_NULL;
    z->opaque = 0;
    z->next_in = NULL;
    z->avail_in = 0;
    if (inflateInit(z) != Z_OK)
      return process_zlib_error(conn, z);
    k->zlib_init = ZLIB_INIT;
  }

  /* Set the compressed input when this function is called */
  z->next_in = (Bytef *)k->str;
  z->avail_in = (uInt)nread;

  /* Now uncompress the data */
  return inflate_stream(conn, k);
}

#ifdef OLD_ZLIB_SUPPORT
/* Skip over the gzip header */
static enum {
  GZIP_OK,
  GZIP_BAD,
  GZIP_UNDERFLOW
} check_gzip_header(unsigned char const *data, ssize_t len, ssize_t *headerlen)
{
  int method, flags;
  const ssize_t totallen = len;

  /* The shortest header is 10 bytes */
  if (len < 10)
    return GZIP_UNDERFLOW;

  if ((data[0] != GZIP_MAGIC_0) || (data[1] != GZIP_MAGIC_1))
    return GZIP_BAD;

  method = data[2];
  flags = data[3];

  if (method != Z_DEFLATED || (flags & RESERVED) != 0) {
    /* Can't handle this compression method or unknown flag */
    return GZIP_BAD;
  }

  /* Skip over time, xflags, OS code and all previous bytes */
  len -= 10;
  data += 10;

  if (flags & EXTRA_FIELD) {
    ssize_t extra_len;

    if (len < 2)
      return GZIP_UNDERFLOW;

    extra_len = (data[1] << 8) | data[0];

    if (len < (extra_len+2))
      return GZIP_UNDERFLOW;

    len -= (extra_len + 2);
    data += (extra_len + 2);
  }

  if (flags & ORIG_NAME) {
    /* Skip over NUL-terminated file name */
    while (len && *data) {
      --len;
      ++data;
    }
    if (!len || *data)
      return GZIP_UNDERFLOW;

    /* Skip over the NUL */
    --len;
    ++data;
  }

  if (flags & COMMENT) {
    /* Skip over NUL-terminated comment */
    while (len && *data) {
      --len;
      ++data;
    }
    if (!len || *data)
      return GZIP_UNDERFLOW;

    /* Skip over the NUL */
    --len;
    ++data;
  }

  if (flags & HEAD_CRC) {
    if (len < 2)
      return GZIP_UNDERFLOW;

    len -= 2;
    data += 2;
  }

  *headerlen = totallen - len;
  return GZIP_OK;
}
#endif

CURLcode
Curl_unencode_gzip_write(struct connectdata *conn,
                         struct Curl_transfer_keeper *k,
                         ssize_t nread)
{
  z_stream *z = &k->z;          /* zlib state structure */

  /* Initialize zlib? */
  if (k->zlib_init == ZLIB_UNINIT) {
    z->zalloc = (alloc_func)Z_NULL;
    z->zfree = (free_func)Z_NULL;
    z->opaque = 0;
    z->next_in = NULL;
    z->avail_in = 0;

    if (strcmp(zlibVersion(), "1.2.0.4") >= 0) {
        /* zlib ver. >= 1.2.0.4 supports transparent gzip decompressing */
        if (inflateInit2(z, MAX_WBITS+32) != Z_OK) {
          return process_zlib_error(conn, z);
        }
        k->zlib_init = ZLIB_INIT_GZIP; /* Transparent gzip decompress state */

    } else {
        /* we must parse the gzip header ourselves */
        if (inflateInit2(z, -MAX_WBITS) != Z_OK) {
          return process_zlib_error(conn, z);
        }
        k->zlib_init = ZLIB_INIT;   /* Initial call state */
    }
  }

  if (k->zlib_init == ZLIB_INIT_GZIP) {
     /* Let zlib handle the gzip decompression entirely */
     z->next_in = (Bytef *)k->str;
     z->avail_in = (uInt)nread;
     /* Now uncompress the data */
     return inflate_stream(conn, k);
  }

#ifndef OLD_ZLIB_SUPPORT
  /* Support for old zlib versions is compiled away and we are running with
     an old version, so return an error. */
  return exit_zlib(z, &k->zlib_init, CURLE_FUNCTION_NOT_FOUND);

#else
  /* This next mess is to get around the potential case where there isn't
   * enough data passed in to skip over the gzip header.  If that happens, we
   * malloc a block and copy what we have then wait for the next call.  If
   * there still isn't enough (this is definitely a worst-case scenario), we
   * make the block bigger, copy the next part in and keep waiting.
   *
   * This is only required with zlib versions < 1.2.0.4 as newer versions
   * can handle the gzip header themselves.
   */

  switch (k->zlib_init) {
  /* Skip over gzip header? */
  case ZLIB_INIT:
  {
    /* Initial call state */
    ssize_t hlen;

    switch (check_gzip_header((unsigned char *)k->str, nread, &hlen)) {
    case GZIP_OK:
      z->next_in = (Bytef *)k->str + hlen;
      z->avail_in = (uInt)(nread - hlen);
      k->zlib_init = ZLIB_GZIP_INFLATING; /* Inflating stream state */
      break;

    case GZIP_UNDERFLOW:
      /* We need more data so we can find the end of the gzip header.  It's
       * possible that the memory block we malloc here will never be freed if
       * the transfer abruptly aborts after this point.  Since it's unlikely
       * that circumstances will be right for this code path to be followed in
       * the first place, and it's even more unlikely for a transfer to fail
       * immediately afterwards, it should seldom be a problem.
       */
      z->avail_in = (uInt)nread;
      z->next_in = malloc(z->avail_in);
      if (z->next_in == NULL) {
        return exit_zlib(z, &k->zlib_init, CURLE_OUT_OF_MEMORY);
      }
      memcpy(z->next_in, k->str, z->avail_in);
      k->zlib_init = ZLIB_GZIP_HEADER;   /* Need more gzip header data state */
      /* We don't have any data to inflate yet */
      return CURLE_OK;

    case GZIP_BAD:
    default:
      return exit_zlib(z, &k->zlib_init, process_zlib_error(conn, z));
    }

  }
  break;

  case ZLIB_GZIP_HEADER:
  {
    /* Need more gzip header data state */
    ssize_t hlen;
    unsigned char *oldblock = z->next_in;

    z->avail_in += nread;
    z->next_in = realloc(z->next_in, z->avail_in);
    if (z->next_in == NULL) {
      free(oldblock);
      return exit_zlib(z, &k->zlib_init, CURLE_OUT_OF_MEMORY);
    }
    /* Append the new block of data to the previous one */
    memcpy(z->next_in + z->avail_in - nread, k->str, nread);

    switch (check_gzip_header(z->next_in, z->avail_in, &hlen)) {
    case GZIP_OK:
      /* This is the zlib stream data */
      free(z->next_in);
      /* Don't point into the malloced block since we just freed it */
      z->next_in = (Bytef *)k->str + hlen + nread - z->avail_in;
      z->avail_in = (uInt)(z->avail_in - hlen);
      k->zlib_init = ZLIB_GZIP_INFLATING;   /* Inflating stream state */
      break;

    case GZIP_UNDERFLOW:
      /* We still don't have any data to inflate! */
      return CURLE_OK;

    case GZIP_BAD:
    default:
      free(z->next_in);
      return exit_zlib(z, &k->zlib_init, process_zlib_error(conn, z));
    }

  }
  break;

  case ZLIB_GZIP_INFLATING:
  default:
    /* Inflating stream state */
    z->next_in = (Bytef *)k->str;
    z->avail_in = (uInt)nread;
    break;
  }

  if (z->avail_in == 0) {
    /* We don't have any data to inflate; wait until next time */
    return CURLE_OK;
  }

  /* We've parsed the header, now uncompress the data */
  return inflate_stream(conn, k);
#endif
}
#endif /* HAVE_LIBZ */