Coverage Report

Created: 2026-09-13 06:13

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
895k
#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
2.68M
#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
35.2k
#define mix(a,b,c) \
179
35.2k
{ \
180
35.2k
  a -= c;  a ^= rot(c, 4);  c += b; \
181
35.2k
  b -= a;  b ^= rot(a, 6);  a += c; \
182
35.2k
  c -= b;  c ^= rot(b, 8);  b += a; \
183
35.2k
  a -= c;  a ^= rot(c,16);  c += b; \
184
35.2k
  b -= a;  b ^= rot(a,19);  a += c; \
185
35.2k
  c -= b;  c ^= rot(b, 4);  b += a; \
186
35.2k
}
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
353k
#define final(a,b,c) \
216
353k
{ \
217
353k
  c ^= b; c -= rot(b,14); \
218
353k
  a ^= c; a -= rot(c,11); \
219
353k
  b ^= a; b -= rot(a,25); \
220
353k
  c ^= b; c -= rot(b,16); \
221
353k
  a ^= c; a -= rot(c,4);  \
222
353k
  b ^= a; b -= rot(a,14); \
223
353k
  c ^= b; c -= rot(b,24); \
224
353k
}
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
354k
{
257
354k
  uint32_t a,b,c; /* internal state */
258
354k
  union
259
354k
  {
260
354k
    const void *ptr;
261
354k
    size_t i;
262
354k
  } u; /* needed for Mac Powerbook G4 */
263
264
  /* Set up the internal state */
265
354k
  a = b = c = 0xdeadbeef + ((uint32_t)length) + initval;
266
267
354k
  u.ptr = key;
268
354k
  if (HASH_LITTLE_ENDIAN && ((u.i & 0x3) == 0)) {
269
260k
    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
285k
    while (length > 12)
273
25.0k
    {
274
25.0k
      a += k[0];
275
25.0k
      b += k[1];
276
25.0k
      c += k[2];
277
25.0k
      mix(a,b,c);
278
25.0k
      length -= 12;
279
25.0k
      k += 3;
280
25.0k
    }
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
260k
#endif
303
260k
#ifndef PRECISE_MEMORY_ACCESS
304
305
260k
    switch(length)
306
260k
    {
307
971
    case 12: c+=k[2]; b+=k[1]; a+=k[0]; break;
308
3.31k
    case 11: c+=k[2]&0xffffff; b+=k[1]; a+=k[0]; break;
309
4.67k
    case 10: c+=k[2]&0xffff; b+=k[1]; a+=k[0]; break;
310
29.8k
    case 9 : c+=k[2]&0xff; b+=k[1]; a+=k[0]; break;
311
46.7k
    case 8 : b+=k[1]; a+=k[0]; break;
312
18.8k
    case 7 : b+=k[1]&0xffffff; a+=k[0]; break;
313
66.6k
    case 6 : b+=k[1]&0xffff; a+=k[0]; break;
314
39.5k
    case 5 : b+=k[1]&0xff; a+=k[0]; break;
315
23.3k
    case 4 : a+=k[0]; break;
316
1.29k
    case 3 : a+=k[0]&0xffffff; break;
317
1.58k
    case 2 : a+=k[0]&0xffff; break;
318
23.1k
    case 1 : a+=k[0]&0xff; break;
319
716
    case 0 : return c; /* zero length strings require no mixing */
320
260k
    }
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
260k
  }
345
93.4k
  else if (HASH_LITTLE_ENDIAN && ((u.i & 0x1) == 0))
346
11.1k
  {
347
11.1k
    const uint16_t *k = (const uint16_t *)key; /* read 16-bit chunks */
348
11.1k
    const uint8_t  *k8;
349
350
    /*--------------- all but last block: aligned reads and different mixing */
351
21.4k
    while (length > 12)
352
10.2k
    {
353
10.2k
      a += k[0] + (((uint32_t)k[1])<<16);
354
10.2k
      b += k[2] + (((uint32_t)k[3])<<16);
355
10.2k
      c += k[4] + (((uint32_t)k[5])<<16);
356
10.2k
      mix(a,b,c);
357
10.2k
      length -= 12;
358
10.2k
      k += 6;
359
10.2k
    }
360
361
    /*----------------------------- handle the last (probably partial) block */
362
11.1k
    k8 = (const uint8_t *)k;
363
11.1k
    switch(length)
364
11.1k
    {
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
541
    case 9 : c+=k8[8];                      /* fall through */
375
693
    case 8 : b+=k[2]+(((uint32_t)k[3])<<16);
376
693
       a+=k[0]+(((uint32_t)k[1])<<16);
377
693
       break;
378
0
    case 7 : b+=((uint32_t)k8[6])<<16;      /* fall through */
379
0
    case 6 : b+=k[2];
380
0
       a+=k[0]+(((uint32_t)k[1])<<16);
381
0
       break;
382
0
    case 5 : b+=k8[4];                      /* fall through */
383
0
    case 4 : a+=k[0]+(((uint32_t)k[1])<<16);
384
0
       break;
385
215
    case 3 : a+=((uint32_t)k8[2])<<16;      /* fall through */
386
215
    case 2 : a+=k[0];
387
215
       break;
388
10.2k
    case 1 : a+=k8[0];
389
10.2k
       break;
390
0
    case 0 : return c;                     /* zero length requires no mixing */
391
11.1k
    }
392
393
11.1k
  }
394
82.3k
  else
395
82.3k
  {
396
    /* need to read the key one byte at a time */
397
82.3k
    const uint8_t *k = (const uint8_t *)key;
398
399
    /*--------------- all but the last block: affect some 32 bits of (a,b,c) */
400
82.3k
    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
82.3k
    switch(length) /* all the case statements fall through */
421
82.3k
    {
422
16.0k
    case 12: c+=((uint32_t)k[11])<<24; /* FALLTHRU */
423
16.0k
    case 11: c+=((uint32_t)k[10])<<16; /* FALLTHRU */
424
16.0k
    case 10: c+=((uint32_t)k[9])<<8; /* FALLTHRU */
425
16.0k
    case 9 : c+=k[8]; /* FALLTHRU */
426
42.4k
    case 8 : b+=((uint32_t)k[7])<<24; /* FALLTHRU */
427
42.4k
    case 7 : b+=((uint32_t)k[6])<<16; /* FALLTHRU */
428
64.3k
    case 6 : b+=((uint32_t)k[5])<<8; /* FALLTHRU */
429
64.3k
    case 5 : b+=k[4]; /* FALLTHRU */
430
82.3k
    case 4 : a+=((uint32_t)k[3])<<24; /* FALLTHRU */
431
82.3k
    case 3 : a+=((uint32_t)k[2])<<16; /* FALLTHRU */
432
82.3k
    case 2 : a+=((uint32_t)k[1])<<8; /* FALLTHRU */
433
82.3k
    case 1 : a+=k[0];
434
82.3k
       break;
435
0
    case 0 : return c;
436
82.3k
    }
437
82.3k
  }
438
439
353k
  final(a,b,c);
440
353k
  return c;
441
354k
}
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
354k
{
460
#if defined _MSC_VER || defined __MINGW32__
461
#define RANDOM_SEED_TYPE LONG
462
#else
463
354k
#define RANDOM_SEED_TYPE int
464
354k
#endif
465
354k
  static volatile RANDOM_SEED_TYPE random_seed = -1;
466
467
354k
  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
354k
  return hashlittle((const char *)k, strlen((const char *)k), (uint32_t)random_seed);
492
354k
}
493
494
int lh_char_equal(const void *k1, const void *k2)
495
311k
{
496
311k
  return (strcmp((const char *)k1, (const char *)k2) == 0);
497
311k
}
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
55.7k
{
502
55.7k
  int i;
503
55.7k
  struct lh_table *t;
504
505
  /* Allocate space for elements to avoid divisions by zero. */
506
55.7k
  assert(size > 0);
507
55.7k
  t = (struct lh_table *)calloc(1, sizeof(struct lh_table));
508
55.7k
  if (!t)
509
0
    return NULL;
510
511
55.7k
  t->count = 0;
512
55.7k
  t->size = size;
513
55.7k
  t->table = (struct lh_entry *)calloc(size, sizeof(struct lh_entry));
514
55.7k
  if (!t->table)
515
0
  {
516
0
    free(t);
517
0
    return NULL;
518
0
  }
519
55.7k
  t->free_fn = free_fn;
520
55.7k
  t->hash_fn = hash_fn;
521
55.7k
  t->equal_fn = equal_fn;
522
956k
  for (i = 0; i < size; i++)
523
900k
    t->table[i].k = LH_EMPTY;
524
55.7k
  return t;
525
55.7k
}
526
527
struct lh_table *lh_kchar_table_new(int size, lh_entry_free_fn *free_fn)
528
55.4k
{
529
55.4k
  return lh_table_new(size, free_fn, char_hash_fn, lh_char_equal);
530
55.4k
}
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
291
{
539
291
  struct lh_table *new_t;
540
291
  struct lh_entry *ent;
541
542
291
  new_t = lh_table_new(new_size, NULL, t->hash_fn, t->equal_fn);
543
291
  if (new_t == NULL)
544
0
    return -1;
545
546
4.62k
  for (ent = t->head; ent != NULL; ent = ent->next)
547
4.33k
  {
548
4.33k
    unsigned long h = lh_get_hash(new_t, ent->k);
549
4.33k
    unsigned int opts = 0;
550
4.33k
    if (ent->k_is_constant)
551
0
      opts = JSON_C_OBJECT_ADD_CONSTANT_KEY;
552
4.33k
    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
4.33k
  }
558
291
  free(t->table);
559
291
  t->table = new_t->table;
560
291
  t->size = new_size;
561
291
  t->head = new_t->head;
562
291
  t->tail = new_t->tail;
563
291
  free(new_t);
564
565
291
  return 0;
566
291
}
567
568
void lh_table_free(struct lh_table *t)
569
55.4k
{
570
55.4k
  struct lh_entry *c;
571
55.4k
  if (t->free_fn)
572
55.4k
  {
573
116k
    for (c = t->head; c != NULL; c = c->next)
574
60.8k
      t->free_fn(c);
575
55.4k
  }
576
55.4k
  free(t->table);
577
55.4k
  free(t);
578
55.4k
}
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
121k
{
583
121k
  unsigned long n;
584
585
121k
  if (t->count >= t->size * LH_LOAD_FACTOR)
586
291
  {
587
    /* Avoid signed integer overflow with large tables. */
588
291
    int new_size = (t->size > INT_MAX / 2) ? INT_MAX : (t->size * 2);
589
291
    if (t->size == INT_MAX || lh_table_resize(t, new_size) != 0)
590
0
      return -1;
591
291
  }
592
593
121k
  n = h % t->size;
594
595
149k
  while (1)
596
149k
  {
597
149k
    if (t->table[n].k == LH_EMPTY || t->table[n].k == LH_FREED)
598
121k
      break;
599
28.4k
    if ((int)++n == t->size)
600
306
      n = 0;
601
28.4k
  }
602
603
121k
  t->table[n].k = k;
604
121k
  t->table[n].k_is_constant = (opts & JSON_C_OBJECT_ADD_CONSTANT_KEY);
605
121k
  t->table[n].v = v;
606
121k
  t->count++;
607
608
121k
  if (t->head == NULL)
609
33.9k
  {
610
33.9k
    t->head = t->tail = &t->table[n];
611
33.9k
    t->table[n].next = t->table[n].prev = NULL;
612
33.9k
  }
613
87.1k
  else
614
87.1k
  {
615
87.1k
    t->tail->next = &t->table[n];
616
87.1k
    t->table[n].prev = t->tail;
617
87.1k
    t->table[n].next = NULL;
618
87.1k
    t->tail = &t->table[n];
619
87.1k
  }
620
621
121k
  return 0;
622
121k
}
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
349k
{
631
349k
  unsigned long n = h % t->size;
632
349k
  int count = 0;
633
634
452k
  while (count < t->size)
635
452k
  {
636
452k
    if (t->table[n].k == LH_EMPTY)
637
141k
      return NULL;
638
311k
    if (t->table[n].k != LH_FREED && t->equal_fn(t->table[n].k, k))
639
208k
      return &t->table[n];
640
102k
    if ((int)++n == t->size)
641
317
      n = 0;
642
102k
    count++;
643
102k
  }
644
0
  return NULL;
645
349k
}
646
647
struct lh_entry *lh_table_lookup_entry(struct lh_table *t, const void *k)
648
228k
{
649
228k
  return lh_table_lookup_entry_w_hash(t, k, lh_get_hash(t, k));
650
228k
}
651
652
json_bool lh_table_lookup_ex(struct lh_table *t, const void *k, void **v)
653
227k
{
654
227k
  struct lh_entry *e = lh_table_lookup_entry(t, k);
655
227k
  if (e != NULL)
656
203k
  {
657
203k
    if (v != NULL)
658
198k
      *v = lh_entry_v(e);
659
203k
    return 1; /* key found */
660
203k
  }
661
24.3k
  if (v != NULL)
662
23.7k
    *v = NULL;
663
24.3k
  return 0; /* key not found */
664
227k
}
665
666
int lh_table_delete_entry(struct lh_table *t, struct lh_entry *e)
667
55.9k
{
668
  /* CAW: fixed to be 64bit nice, still need the crazy negative case... */
669
55.9k
  ptrdiff_t n = (ptrdiff_t)(e - t->table);
670
671
55.9k
  assert(n >= 0 && n < t->size);
672
673
  /* CAW: this is bad, really bad, maybe stack goes other direction on this machine... */
674
55.9k
  if (n < 0)
675
0
  {
676
0
    return -2;
677
0
  }
678
679
55.9k
  if (t->table[n].k == LH_EMPTY || t->table[n].k == LH_FREED)
680
0
    return -1;
681
55.9k
  t->count--;
682
55.9k
  if (t->free_fn)
683
55.9k
    t->free_fn(e);
684
55.9k
  t->table[n].v = NULL;
685
55.9k
  t->table[n].k = LH_FREED;
686
55.9k
  if (t->tail == &t->table[n] && t->head == &t->table[n])
687
9.18k
  {
688
9.18k
    t->head = t->tail = NULL;
689
9.18k
  }
690
46.7k
  else if (t->head == &t->table[n])
691
5
  {
692
5
    t->head->next->prev = NULL;
693
5
    t->head = t->head->next;
694
5
  }
695
46.7k
  else if (t->tail == &t->table[n])
696
46.3k
  {
697
46.3k
    t->tail->prev->next = NULL;
698
46.3k
    t->tail = t->tail->prev;
699
46.3k
  }
700
360
  else
701
360
  {
702
360
    t->table[n].prev->next = t->table[n].next;
703
360
    t->table[n].next->prev = t->table[n].prev;
704
360
  }
705
55.9k
  t->table[n].next = t->table[n].prev = NULL;
706
55.9k
  return 0;
707
55.9k
}
708
709
int lh_table_delete_entry_to_tail(struct lh_table *t, struct lh_entry *first_entry)
710
35.9k
{
711
35.9k
  struct lh_entry *del_entry = t->tail;
712
35.9k
  do
713
55.5k
  {
714
55.5k
    struct lh_entry *prev = del_entry->prev;
715
    // Could probably micro-optimize this, but better to avoid code duplication for now
716
55.5k
    if (lh_table_delete_entry(t, del_entry) != 0)
717
0
      return -1;
718
55.5k
    if (del_entry == first_entry)
719
35.9k
      break;
720
19.5k
    del_entry = prev;
721
19.5k
  } while (del_entry != NULL);
722
35.9k
  return 0;
723
35.9k
}
724
725
int lh_table_delete(struct lh_table *t, const void *k)
726
427
{
727
427
  struct lh_entry *e = lh_table_lookup_entry(t, k);
728
427
  if (!e)
729
0
    return -1;
730
427
  return lh_table_delete_entry(t, e);
731
427
}
732
733
int lh_table_length(struct lh_table *t)
734
135k
{
735
135k
  return t->count;
736
135k
}