Coverage Report

Created: 2025-12-14 06:35

next uncovered line (L), next uncovered region (R), next uncovered branch (B)
/src/json-c/linkhash.c
Line
Count
Source
1
/*
2
 * $Id: linkhash.c,v 1.4 2006/01/26 02:16:28 mclark Exp $
3
 *
4
 * Copyright (c) 2004, 2005 Metaparadigm Pte. Ltd.
5
 * Michael Clark <michael@metaparadigm.com>
6
 * Copyright (c) 2009 Hewlett-Packard Development Company, L.P.
7
 *
8
 * This library is free software; you can redistribute it and/or modify
9
 * it under the terms of the MIT license. See COPYING for details.
10
 *
11
 */
12
13
#include "config.h"
14
15
#include <assert.h>
16
#include <limits.h>
17
#include <stdarg.h>
18
#include <stddef.h>
19
#include <stdio.h>
20
#include <stdlib.h>
21
#include <string.h>
22
23
#ifdef HAVE_ENDIAN_H
24
#include <endian.h> /* attempt to define endianness */
25
#endif
26
27
#if defined(_MSC_VER) || defined(__MINGW32__)
28
#ifndef WIN32_LEAN_AND_MEAN
29
#define WIN32_LEAN_AND_MEAN
30
#endif
31
#include <windows.h> /* Get InterlockedCompareExchange */
32
#endif
33
34
#include "linkhash.h"
35
#include "random_seed.h"
36
37
/* hash functions */
38
static unsigned long lh_char_hash(const void *k);
39
static unsigned long lh_perllike_str_hash(const void *k);
40
static lh_hash_fn *char_hash_fn = lh_char_hash;
41
42
/* comparison functions */
43
int lh_char_equal(const void *k1, const void *k2);
44
int lh_ptr_equal(const void *k1, const void *k2);
45
46
int json_global_set_string_hash(const int h)
47
0
{
48
0
  switch (h)
49
0
  {
50
0
  case JSON_C_STR_HASH_DFLT: char_hash_fn = lh_char_hash; break;
51
0
  case JSON_C_STR_HASH_PERLLIKE: char_hash_fn = lh_perllike_str_hash; break;
52
0
  default: return -1;
53
0
  }
54
0
  return 0;
55
0
}
56
57
static unsigned long lh_ptr_hash(const void *k)
58
0
{
59
  /* CAW: refactored to be 64bit nice */
60
0
  return (unsigned long)((((ptrdiff_t)k * LH_PRIME) >> 4) & ULONG_MAX);
61
0
}
62
63
int lh_ptr_equal(const void *k1, const void *k2)
64
0
{
65
0
  return (k1 == k2);
66
0
}
67
68
/*
69
 * hashlittle from lookup3.c, by Bob Jenkins, May 2006, Public Domain.
70
 * https://burtleburtle.net/bob/c/lookup3.c
71
 * minor modifications to make functions static so no symbols are exported
72
 * minor modifications to compile with -Werror
73
 */
74
75
/*
76
-------------------------------------------------------------------------------
77
lookup3.c, by Bob Jenkins, May 2006, Public Domain.
78
79
These are functions for producing 32-bit hashes for hash table lookup.
80
hashword(), hashlittle(), hashlittle2(), hashbig(), mix(), and final()
81
are externally useful functions.  Routines to test the hash are included
82
if SELF_TEST is defined.  You can use this free for any purpose.  It's in
83
the public domain.  It has no warranty.
84
85
You probably want to use hashlittle().  hashlittle() and hashbig()
86
hash byte arrays.  hashlittle() is faster than hashbig() on
87
little-endian machines.  Intel and AMD are little-endian machines.
88
On second thought, you probably want hashlittle2(), which is identical to
89
hashlittle() except it returns two 32-bit hashes for the price of one.
90
You could implement hashbig2() if you wanted but I haven't bothered here.
91
92
If you want to find a hash of, say, exactly 7 integers, do
93
  a = i1;  b = i2;  c = i3;
94
  mix(a,b,c);
95
  a += i4; b += i5; c += i6;
96
  mix(a,b,c);
97
  a += i7;
98
  final(a,b,c);
99
then use c as the hash value.  If you have a variable length array of
100
4-byte integers to hash, use hashword().  If you have a byte array (like
101
a character string), use hashlittle().  If you have several byte arrays, or
102
a mix of things, see the comments above hashlittle().
103
104
Why is this so big?  I read 12 bytes at a time into 3 4-byte integers,
105
then mix those integers.  This is fast (you can do a lot more thorough
106
mixing with 12*3 instructions on 3 integers than you can with 3 instructions
107
on 1 byte), but shoehorning those bytes into integers efficiently is messy.
108
-------------------------------------------------------------------------------
109
*/
110
111
/*
112
 * My best guess at if you are big-endian or little-endian.  This may
113
 * need adjustment.
114
 */
115
#if (defined(__BYTE_ORDER) && defined(__LITTLE_ENDIAN) && __BYTE_ORDER == __LITTLE_ENDIAN) || \
116
    (defined(i386) || defined(__i386__) || defined(__i486__) || defined(__i586__) ||          \
117
     defined(__i686__) || defined(vax) || defined(MIPSEL))
118
1.14M
#define HASH_LITTLE_ENDIAN 1
119
#define HASH_BIG_ENDIAN 0
120
#elif (defined(__BYTE_ORDER) && defined(__BIG_ENDIAN) && __BYTE_ORDER == __BIG_ENDIAN) || \
121
    (defined(sparc) || defined(POWERPC) || defined(mc68000) || defined(sel))
122
#define HASH_LITTLE_ENDIAN 0
123
#define HASH_BIG_ENDIAN 1
124
#else
125
#define HASH_LITTLE_ENDIAN 0
126
#define HASH_BIG_ENDIAN 0
127
#endif
128
129
#define hashsize(n) ((uint32_t)1 << (n))
130
#define hashmask(n) (hashsize(n) - 1)
131
2.89M
#define rot(x, k) (((x) << (k)) | ((x) >> (32 - (k))))
132
133
/*
134
-------------------------------------------------------------------------------
135
mix -- mix 3 32-bit values reversibly.
136
137
This is reversible, so any information in (a,b,c) before mix() is
138
still in (a,b,c) after mix().
139
140
If four pairs of (a,b,c) inputs are run through mix(), or through
141
mix() in reverse, there are at least 32 bits of the output that
142
are sometimes the same for one pair and different for another pair.
143
This was tested for:
144
* pairs that differed by one bit, by two bits, in any combination
145
  of top bits of (a,b,c), or in any combination of bottom bits of
146
  (a,b,c).
147
* "differ" is defined as +, -, ^, or ~^.  For + and -, I transformed
148
  the output delta to a Gray code (a^(a>>1)) so a string of 1's (as
149
  is commonly produced by subtraction) look like a single 1-bit
150
  difference.
151
* the base values were pseudorandom, all zero but one bit set, or
152
  all zero plus a counter that starts at zero.
153
154
Some k values for my "a-=c; a^=rot(c,k); c+=b;" arrangement that
155
satisfy this are
156
    4  6  8 16 19  4
157
    9 15  3 18 27 15
158
   14  9  3  7 17  3
159
Well, "9 15 3 18 27 15" didn't quite get 32 bits diffing
160
for "differ" defined as + with a one-bit base and a two-bit delta.  I
161
used https://burtleburtle.net/bob/hash/avalanche.html to choose
162
the operations, constants, and arrangements of the variables.
163
164
This does not achieve avalanche.  There are input bits of (a,b,c)
165
that fail to affect some output bits of (a,b,c), especially of a.  The
166
most thoroughly mixed value is c, but it doesn't really even achieve
167
avalanche in c.
168
169
This allows some parallelism.  Read-after-writes are good at doubling
170
the number of bits affected, so the goal of mixing pulls in the opposite
171
direction as the goal of parallelism.  I did what I could.  Rotates
172
seem to cost as much as shifts on every machine I could lay my hands
173
on, and rotates are much kinder to the top and bottom bits, so I used
174
rotates.
175
-------------------------------------------------------------------------------
176
*/
177
/* clang-format off */
178
32.0k
#define mix(a,b,c) \
179
32.0k
{ \
180
32.0k
  a -= c;  a ^= rot(c, 4);  c += b; \
181
32.0k
  b -= a;  b ^= rot(a, 6);  a += c; \
182
32.0k
  c -= b;  c ^= rot(b, 8);  b += a; \
183
32.0k
  a -= c;  a ^= rot(c,16);  c += b; \
184
32.0k
  b -= a;  b ^= rot(a,19);  a += c; \
185
32.0k
  c -= b;  c ^= rot(b, 4);  b += a; \
186
32.0k
}
187
/* clang-format on */
188
189
/*
190
-------------------------------------------------------------------------------
191
final -- final mixing of 3 32-bit values (a,b,c) into c
192
193
Pairs of (a,b,c) values differing in only a few bits will usually
194
produce values of c that look totally different.  This was tested for
195
* pairs that differed by one bit, by two bits, in any combination
196
  of top bits of (a,b,c), or in any combination of bottom bits of
197
  (a,b,c).
198
* "differ" is defined as +, -, ^, or ~^.  For + and -, I transformed
199
  the output delta to a Gray code (a^(a>>1)) so a string of 1's (as
200
  is commonly produced by subtraction) look like a single 1-bit
201
  difference.
202
* the base values were pseudorandom, all zero but one bit set, or
203
  all zero plus a counter that starts at zero.
204
205
These constants passed:
206
 14 11 25 16 4 14 24
207
 12 14 25 16 4 14 24
208
and these came close:
209
  4  8 15 26 3 22 24
210
 10  8 15 26 3 22 24
211
 11  8 15 26 3 22 24
212
-------------------------------------------------------------------------------
213
*/
214
/* clang-format off */
215
386k
#define final(a,b,c) \
216
386k
{ \
217
386k
  c ^= b; c -= rot(b,14); \
218
386k
  a ^= c; a -= rot(c,11); \
219
386k
  b ^= a; b -= rot(a,25); \
220
386k
  c ^= b; c -= rot(b,16); \
221
386k
  a ^= c; a -= rot(c,4);  \
222
386k
  b ^= a; b -= rot(a,14); \
223
386k
  c ^= b; c -= rot(b,24); \
224
386k
}
225
/* clang-format on */
226
227
/*
228
-------------------------------------------------------------------------------
229
hashlittle() -- hash a variable-length key into a 32-bit value
230
  k       : the key (the unaligned variable-length array of bytes)
231
  length  : the length of the key, counting by bytes
232
  initval : can be any 4-byte value
233
Returns a 32-bit value.  Every bit of the key affects every bit of
234
the return value.  Two keys differing by one or two bits will have
235
totally different hash values.
236
237
The best hash table sizes are powers of 2.  There is no need to do
238
mod a prime (mod is sooo slow!).  If you need less than 32 bits,
239
use a bitmask.  For example, if you need only 10 bits, do
240
  h = (h & hashmask(10));
241
In which case, the hash table should have hashsize(10) elements.
242
243
If you are hashing n strings (uint8_t **)k, do it like this:
244
  for (i=0, h=0; i<n; ++i) h = hashlittle( k[i], len[i], h);
245
246
By Bob Jenkins, 2006.  bob_jenkins@burtleburtle.net.  You may use this
247
code any way you wish, private, educational, or commercial.  It's free.
248
249
Use for hash table lookup, or anything where one collision in 2^^32 is
250
acceptable.  Do NOT use for cryptographic purposes.
251
-------------------------------------------------------------------------------
252
*/
253
254
/* clang-format off */
255
static uint32_t hashlittle(const void *key, size_t length, uint32_t initval)
256
386k
{
257
386k
  uint32_t a,b,c; /* internal state */
258
386k
  union
259
386k
  {
260
386k
    const void *ptr;
261
386k
    size_t i;
262
386k
  } u; /* needed for Mac Powerbook G4 */
263
264
  /* Set up the internal state */
265
386k
  a = b = c = 0xdeadbeef + ((uint32_t)length) + initval;
266
267
386k
  u.ptr = key;
268
386k
  if (HASH_LITTLE_ENDIAN && ((u.i & 0x3) == 0)) {
269
201k
    const uint32_t *k = (const uint32_t *)key; /* read 32-bit chunks */
270
271
    /*------ all but last block: aligned reads and affect 32 bits of (a,b,c) */
272
221k
    while (length > 12)
273
20.4k
    {
274
20.4k
      a += k[0];
275
20.4k
      b += k[1];
276
20.4k
      c += k[2];
277
20.4k
      mix(a,b,c);
278
20.4k
      length -= 12;
279
20.4k
      k += 3;
280
20.4k
    }
281
282
    /*----------------------------- handle the last (probably partial) block */
283
    /*
284
     * "k[2]&0xffffff" actually reads beyond the end of the string, but
285
     * then masks off the part it's not allowed to read.  Because the
286
     * string is aligned, the masked-off tail is in the same word as the
287
     * rest of the string.  Every machine with memory protection I've seen
288
     * does it on word boundaries, so is OK with this.  But VALGRIND will
289
     * still catch it and complain.  The masking trick does make the hash
290
     * noticeably faster for short strings (like English words).
291
     * AddressSanitizer is similarly picky about overrunning
292
     * the buffer. (https://clang.llvm.org/docs/AddressSanitizer.html)
293
     */
294
#ifdef VALGRIND
295
#define PRECISE_MEMORY_ACCESS 1
296
#elif defined(__SANITIZE_ADDRESS__) /* GCC's ASAN */
297
#define PRECISE_MEMORY_ACCESS 1
298
#elif defined(__has_feature)
299
#if __has_feature(address_sanitizer) /* Clang's ASAN */
300
#define PRECISE_MEMORY_ACCESS 1
301
#endif
302
201k
#endif
303
201k
#ifndef PRECISE_MEMORY_ACCESS
304
305
201k
    switch(length)
306
201k
    {
307
582
    case 12: c+=k[2]; b+=k[1]; a+=k[0]; break;
308
3.68k
    case 11: c+=k[2]&0xffffff; b+=k[1]; a+=k[0]; break;
309
3.82k
    case 10: c+=k[2]&0xffff; b+=k[1]; a+=k[0]; break;
310
33.4k
    case 9 : c+=k[2]&0xff; b+=k[1]; a+=k[0]; break;
311
51.0k
    case 8 : b+=k[1]; a+=k[0]; break;
312
20.9k
    case 7 : b+=k[1]&0xffffff; a+=k[0]; break;
313
26.8k
    case 6 : b+=k[1]&0xffff; a+=k[0]; break;
314
8.88k
    case 5 : b+=k[1]&0xff; a+=k[0]; break;
315
23.7k
    case 4 : a+=k[0]; break;
316
1.27k
    case 3 : a+=k[0]&0xffffff; break;
317
1.27k
    case 2 : a+=k[0]&0xffff; break;
318
25.2k
    case 1 : a+=k[0]&0xff; break;
319
726
    case 0 : return c; /* zero length strings require no mixing */
320
201k
    }
321
322
#else /* make valgrind happy */
323
324
    const uint8_t  *k8 = (const uint8_t *)k;
325
    switch(length)
326
    {
327
    case 12: c+=k[2]; b+=k[1]; a+=k[0]; break;
328
    case 11: c+=((uint32_t)k8[10])<<16;  /* fall through */
329
    case 10: c+=((uint32_t)k8[9])<<8;    /* fall through */
330
    case 9 : c+=k8[8];                   /* fall through */
331
    case 8 : b+=k[1]; a+=k[0]; break;
332
    case 7 : b+=((uint32_t)k8[6])<<16;   /* fall through */
333
    case 6 : b+=((uint32_t)k8[5])<<8;    /* fall through */
334
    case 5 : b+=k8[4];                   /* fall through */
335
    case 4 : a+=k[0]; break;
336
    case 3 : a+=((uint32_t)k8[2])<<16;   /* fall through */
337
    case 2 : a+=((uint32_t)k8[1])<<8;    /* fall through */
338
    case 1 : a+=k8[0]; break;
339
    case 0 : return c;
340
    }
341
342
#endif /* !valgrind */
343
344
201k
  }
345
185k
  else if (HASH_LITTLE_ENDIAN && ((u.i & 0x1) == 0))
346
58.4k
  {
347
58.4k
    const uint16_t *k = (const uint16_t *)key; /* read 16-bit chunks */
348
58.4k
    const uint8_t  *k8;
349
350
    /*--------------- all but last block: aligned reads and different mixing */
351
70.0k
    while (length > 12)
352
11.6k
    {
353
11.6k
      a += k[0] + (((uint32_t)k[1])<<16);
354
11.6k
      b += k[2] + (((uint32_t)k[3])<<16);
355
11.6k
      c += k[4] + (((uint32_t)k[5])<<16);
356
11.6k
      mix(a,b,c);
357
11.6k
      length -= 12;
358
11.6k
      k += 6;
359
11.6k
    }
360
361
    /*----------------------------- handle the last (probably partial) block */
362
58.4k
    k8 = (const uint8_t *)k;
363
58.4k
    switch(length)
364
58.4k
    {
365
0
    case 12: c+=k[4]+(((uint32_t)k[5])<<16);
366
0
       b+=k[2]+(((uint32_t)k[3])<<16);
367
0
       a+=k[0]+(((uint32_t)k[1])<<16);
368
0
       break;
369
0
    case 11: c+=((uint32_t)k8[10])<<16;     /* fall through */
370
26
    case 10: c+=k[4];
371
26
       b+=k[2]+(((uint32_t)k[3])<<16);
372
26
       a+=k[0]+(((uint32_t)k[1])<<16);
373
26
       break;
374
0
    case 9 : c+=k8[8];                      /* fall through */
375
0
    case 8 : b+=k[2]+(((uint32_t)k[3])<<16);
376
0
       a+=k[0]+(((uint32_t)k[1])<<16);
377
0
       break;
378
0
    case 7 : b+=((uint32_t)k8[6])<<16;      /* fall through */
379
46.8k
    case 6 : b+=k[2];
380
46.8k
       a+=k[0]+(((uint32_t)k[1])<<16);
381
46.8k
       break;
382
4
    case 5 : b+=k8[4];                      /* fall through */
383
4
    case 4 : a+=k[0]+(((uint32_t)k[1])<<16);
384
4
       break;
385
0
    case 3 : a+=((uint32_t)k8[2])<<16;      /* fall through */
386
0
    case 2 : a+=k[0];
387
0
       break;
388
11.5k
    case 1 : a+=k8[0];
389
11.5k
       break;
390
0
    case 0 : return c;                     /* zero length requires no mixing */
391
58.4k
    }
392
393
58.4k
  }
394
126k
  else
395
126k
  {
396
    /* need to read the key one byte at a time */
397
126k
    const uint8_t *k = (const uint8_t *)key;
398
399
    /*--------------- all but the last block: affect some 32 bits of (a,b,c) */
400
126k
    while (length > 12)
401
8
    {
402
8
      a += k[0];
403
8
      a += ((uint32_t)k[1])<<8;
404
8
      a += ((uint32_t)k[2])<<16;
405
8
      a += ((uint32_t)k[3])<<24;
406
8
      b += k[4];
407
8
      b += ((uint32_t)k[5])<<8;
408
8
      b += ((uint32_t)k[6])<<16;
409
8
      b += ((uint32_t)k[7])<<24;
410
8
      c += k[8];
411
8
      c += ((uint32_t)k[9])<<8;
412
8
      c += ((uint32_t)k[10])<<16;
413
8
      c += ((uint32_t)k[11])<<24;
414
8
      mix(a,b,c);
415
8
      length -= 12;
416
8
      k += 12;
417
8
    }
418
419
    /*-------------------------------- last block: affect all 32 bits of (c) */
420
126k
    switch(length) /* all the case statements fall through */
421
126k
    {
422
18.0k
    case 12: c+=((uint32_t)k[11])<<24; /* FALLTHRU */
423
18.0k
    case 11: c+=((uint32_t)k[10])<<16; /* FALLTHRU */
424
18.0k
    case 10: c+=((uint32_t)k[9])<<8; /* FALLTHRU */
425
18.0k
    case 9 : c+=k[8]; /* FALLTHRU */
426
47.8k
    case 8 : b+=((uint32_t)k[7])<<24; /* FALLTHRU */
427
47.8k
    case 7 : b+=((uint32_t)k[6])<<16; /* FALLTHRU */
428
72.2k
    case 6 : b+=((uint32_t)k[5])<<8; /* FALLTHRU */
429
107k
    case 5 : b+=k[4]; /* FALLTHRU */
430
126k
    case 4 : a+=((uint32_t)k[3])<<24; /* FALLTHRU */
431
126k
    case 3 : a+=((uint32_t)k[2])<<16; /* FALLTHRU */
432
126k
    case 2 : a+=((uint32_t)k[1])<<8; /* FALLTHRU */
433
126k
    case 1 : a+=k[0];
434
126k
       break;
435
0
    case 0 : return c;
436
126k
    }
437
126k
  }
438
439
386k
  final(a,b,c);
440
386k
  return c;
441
386k
}
442
/* clang-format on */
443
444
/* a simple hash function similar to what perl does for strings.
445
 * for good results, the string should not be excessively large.
446
 */
447
static unsigned long lh_perllike_str_hash(const void *k)
448
0
{
449
0
  const char *rkey = (const char *)k;
450
0
  unsigned hashval = 1;
451
452
0
  while (*rkey)
453
0
    hashval = hashval * 33 + *rkey++;
454
455
0
  return hashval;
456
0
}
457
458
static unsigned long lh_char_hash(const void *k)
459
386k
{
460
#if defined _MSC_VER || defined __MINGW32__
461
#define RANDOM_SEED_TYPE LONG
462
#else
463
386k
#define RANDOM_SEED_TYPE int
464
386k
#endif
465
386k
  static volatile RANDOM_SEED_TYPE random_seed = -1;
466
467
386k
  if (random_seed == -1)
468
1
  {
469
1
    RANDOM_SEED_TYPE seed;
470
    /* we can't use -1 as it is the uninitialized sentinel */
471
1
    while ((seed = json_c_get_random_seed()) == -1) {}
472
#if SIZEOF_INT == 8 && defined __GCC_HAVE_SYNC_COMPARE_AND_SWAP_8
473
#define USE_SYNC_COMPARE_AND_SWAP 1
474
#endif
475
1
#if SIZEOF_INT == 4 && defined __GCC_HAVE_SYNC_COMPARE_AND_SWAP_4
476
1
#define USE_SYNC_COMPARE_AND_SWAP 1
477
1
#endif
478
#if SIZEOF_INT == 2 && defined __GCC_HAVE_SYNC_COMPARE_AND_SWAP_2
479
#define USE_SYNC_COMPARE_AND_SWAP 1
480
#endif
481
1
#if defined USE_SYNC_COMPARE_AND_SWAP
482
1
    (void)__sync_val_compare_and_swap(&random_seed, -1, seed);
483
#elif defined _MSC_VER || defined __MINGW32__
484
    InterlockedCompareExchange(&random_seed, seed, -1);
485
#else
486
    //#warning "racy random seed initialization if used by multiple threads"
487
    random_seed = seed; /* potentially racy */
488
#endif
489
1
  }
490
491
386k
  return hashlittle((const char *)k, strlen((const char *)k), (uint32_t)random_seed);
492
386k
}
493
494
int lh_char_equal(const void *k1, const void *k2)
495
298k
{
496
298k
  return (strcmp((const char *)k1, (const char *)k2) == 0);
497
298k
}
498
499
struct lh_table *lh_table_new(int size, lh_entry_free_fn *free_fn, lh_hash_fn *hash_fn,
500
                              lh_equal_fn *equal_fn)
501
61.5k
{
502
61.5k
  int i;
503
61.5k
  struct lh_table *t;
504
505
  /* Allocate space for elements to avoid divisions by zero. */
506
61.5k
  assert(size > 0);
507
61.5k
  t = (struct lh_table *)calloc(1, sizeof(struct lh_table));
508
61.5k
  if (!t)
509
0
    return NULL;
510
511
61.5k
  t->count = 0;
512
61.5k
  t->size = size;
513
61.5k
  t->table = (struct lh_entry *)calloc(size, sizeof(struct lh_entry));
514
61.5k
  if (!t->table)
515
0
  {
516
0
    free(t);
517
0
    return NULL;
518
0
  }
519
61.5k
  t->free_fn = free_fn;
520
61.5k
  t->hash_fn = hash_fn;
521
61.5k
  t->equal_fn = equal_fn;
522
1.05M
  for (i = 0; i < size; i++)
523
989k
    t->table[i].k = LH_EMPTY;
524
61.5k
  return t;
525
61.5k
}
526
527
struct lh_table *lh_kchar_table_new(int size, lh_entry_free_fn *free_fn)
528
61.4k
{
529
61.4k
  return lh_table_new(size, free_fn, char_hash_fn, lh_char_equal);
530
61.4k
}
531
532
struct lh_table *lh_kptr_table_new(int size, lh_entry_free_fn *free_fn)
533
0
{
534
0
  return lh_table_new(size, free_fn, lh_ptr_hash, lh_ptr_equal);
535
0
}
536
537
int lh_table_resize(struct lh_table *t, int new_size)
538
167
{
539
167
  struct lh_table *new_t;
540
167
  struct lh_entry *ent;
541
542
167
  new_t = lh_table_new(new_size, NULL, t->hash_fn, t->equal_fn);
543
167
  if (new_t == NULL)
544
0
    return -1;
545
546
2.60k
  for (ent = t->head; ent != NULL; ent = ent->next)
547
2.44k
  {
548
2.44k
    unsigned long h = lh_get_hash(new_t, ent->k);
549
2.44k
    unsigned int opts = 0;
550
2.44k
    if (ent->k_is_constant)
551
0
      opts = JSON_C_OBJECT_ADD_CONSTANT_KEY;
552
2.44k
    if (lh_table_insert_w_hash(new_t, ent->k, ent->v, h, opts) != 0)
553
0
    {
554
0
      lh_table_free(new_t);
555
0
      return -1;
556
0
    }
557
2.44k
  }
558
167
  free(t->table);
559
167
  t->table = new_t->table;
560
167
  t->size = new_size;
561
167
  t->head = new_t->head;
562
167
  t->tail = new_t->tail;
563
167
  free(new_t);
564
565
167
  return 0;
566
167
}
567
568
void lh_table_free(struct lh_table *t)
569
61.4k
{
570
61.4k
  struct lh_entry *c;
571
61.4k
  if (t->free_fn)
572
61.4k
  {
573
185k
    for (c = t->head; c != NULL; c = c->next)
574
124k
      t->free_fn(c);
575
61.4k
  }
576
61.4k
  free(t->table);
577
61.4k
  free(t);
578
61.4k
}
579
580
int lh_table_insert_w_hash(struct lh_table *t, const void *k, const void *v, const unsigned long h,
581
                           const unsigned opts)
582
127k
{
583
127k
  unsigned long n;
584
585
127k
  if (t->count >= t->size * LH_LOAD_FACTOR)
586
167
  {
587
    /* Avoid signed integer overflow with large tables. */
588
167
    int new_size = (t->size > INT_MAX / 2) ? INT_MAX : (t->size * 2);
589
167
    if (t->size == INT_MAX || lh_table_resize(t, new_size) != 0)
590
0
      return -1;
591
167
  }
592
593
127k
  n = h % t->size;
594
595
156k
  while (1)
596
156k
  {
597
156k
    if (t->table[n].k == LH_EMPTY || t->table[n].k == LH_FREED)
598
127k
      break;
599
28.7k
    if ((int)++n == t->size)
600
8.12k
      n = 0;
601
28.7k
  }
602
603
127k
  t->table[n].k = k;
604
127k
  t->table[n].k_is_constant = (opts & JSON_C_OBJECT_ADD_CONSTANT_KEY);
605
127k
  t->table[n].v = v;
606
127k
  t->count++;
607
608
127k
  if (t->head == NULL)
609
36.9k
  {
610
36.9k
    t->head = t->tail = &t->table[n];
611
36.9k
    t->table[n].next = t->table[n].prev = NULL;
612
36.9k
  }
613
90.4k
  else
614
90.4k
  {
615
90.4k
    t->tail->next = &t->table[n];
616
90.4k
    t->table[n].prev = t->tail;
617
90.4k
    t->table[n].next = NULL;
618
90.4k
    t->tail = &t->table[n];
619
90.4k
  }
620
621
127k
  return 0;
622
127k
}
623
int lh_table_insert(struct lh_table *t, const void *k, const void *v)
624
0
{
625
0
  return lh_table_insert_w_hash(t, k, v, lh_get_hash(t, k), 0);
626
0
}
627
628
struct lh_entry *lh_table_lookup_entry_w_hash(struct lh_table *t, const void *k,
629
                                              const unsigned long h)
630
384k
{
631
384k
  unsigned long n = h % t->size;
632
384k
  int count = 0;
633
634
451k
  while (count < t->size)
635
451k
  {
636
451k
    if (t->table[n].k == LH_EMPTY)
637
152k
      return NULL;
638
298k
    if (t->table[n].k != LH_FREED && t->equal_fn(t->table[n].k, k))
639
231k
      return &t->table[n];
640
66.8k
    if ((int)++n == t->size)
641
14.2k
      n = 0;
642
66.8k
    count++;
643
66.8k
  }
644
0
  return NULL;
645
384k
}
646
647
struct lh_entry *lh_table_lookup_entry(struct lh_table *t, const void *k)
648
256k
{
649
256k
  return lh_table_lookup_entry_w_hash(t, k, lh_get_hash(t, k));
650
256k
}
651
652
json_bool lh_table_lookup_ex(struct lh_table *t, const void *k, void **v)
653
255k
{
654
255k
  struct lh_entry *e = lh_table_lookup_entry(t, k);
655
255k
  if (e != NULL)
656
228k
  {
657
228k
    if (v != NULL)
658
222k
      *v = lh_entry_v(e);
659
228k
    return 1; /* key found */
660
228k
  }
661
27.5k
  if (v != NULL)
662
26.8k
    *v = NULL;
663
27.5k
  return 0; /* key not found */
664
255k
}
665
666
int lh_table_delete_entry(struct lh_table *t, struct lh_entry *e)
667
400
{
668
  /* CAW: fixed to be 64bit nice, still need the crazy negative case... */
669
400
  ptrdiff_t n = (ptrdiff_t)(e - t->table);
670
671
  /* CAW: this is bad, really bad, maybe stack goes other direction on this machine... */
672
400
  if (n < 0)
673
0
  {
674
0
    return -2;
675
0
  }
676
677
400
  if (t->table[n].k == LH_EMPTY || t->table[n].k == LH_FREED)
678
0
    return -1;
679
400
  t->count--;
680
400
  if (t->free_fn)
681
400
    t->free_fn(e);
682
400
  t->table[n].v = NULL;
683
400
  t->table[n].k = LH_FREED;
684
400
  if (t->tail == &t->table[n] && t->head == &t->table[n])
685
0
  {
686
0
    t->head = t->tail = NULL;
687
0
  }
688
400
  else if (t->head == &t->table[n])
689
5
  {
690
5
    t->head->next->prev = NULL;
691
5
    t->head = t->head->next;
692
5
  }
693
395
  else if (t->tail == &t->table[n])
694
48
  {
695
48
    t->tail->prev->next = NULL;
696
48
    t->tail = t->tail->prev;
697
48
  }
698
347
  else
699
347
  {
700
347
    t->table[n].prev->next = t->table[n].next;
701
347
    t->table[n].next->prev = t->table[n].prev;
702
347
  }
703
400
  t->table[n].next = t->table[n].prev = NULL;
704
400
  return 0;
705
400
}
706
707
int lh_table_delete(struct lh_table *t, const void *k)
708
400
{
709
400
  struct lh_entry *e = lh_table_lookup_entry(t, k);
710
400
  if (!e)
711
0
    return -1;
712
400
  return lh_table_delete_entry(t, e);
713
400
}
714
715
int lh_table_length(struct lh_table *t)
716
11.8k
{
717
11.8k
  return t->count;
718
11.8k
}