Coverage Report

Created: 2026-06-08 06:07

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
890k
#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
2.49M
#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
32.6k
#define mix(a,b,c) \
179
32.6k
{ \
180
32.6k
  a -= c;  a ^= rot(c, 4);  c += b; \
181
32.6k
  b -= a;  b ^= rot(a, 6);  a += c; \
182
32.6k
  c -= b;  c ^= rot(b, 8);  b += a; \
183
32.6k
  a -= c;  a ^= rot(c,16);  c += b; \
184
32.6k
  b -= a;  b ^= rot(a,19);  a += c; \
185
32.6k
  c -= b;  c ^= rot(b, 4);  b += a; \
186
32.6k
}
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
328k
#define final(a,b,c) \
216
328k
{ \
217
328k
  c ^= b; c -= rot(b,14); \
218
328k
  a ^= c; a -= rot(c,11); \
219
328k
  b ^= a; b -= rot(a,25); \
220
328k
  c ^= b; c -= rot(b,16); \
221
328k
  a ^= c; a -= rot(c,4);  \
222
328k
  b ^= a; b -= rot(a,14); \
223
328k
  c ^= b; c -= rot(b,24); \
224
328k
}
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
328k
{
257
328k
  uint32_t a,b,c; /* internal state */
258
328k
  union
259
328k
  {
260
328k
    const void *ptr;
261
328k
    size_t i;
262
328k
  } u; /* needed for Mac Powerbook G4 */
263
264
  /* Set up the internal state */
265
328k
  a = b = c = 0xdeadbeef + ((uint32_t)length) + initval;
266
267
328k
  u.ptr = key;
268
328k
  if (HASH_LITTLE_ENDIAN && ((u.i & 0x3) == 0)) {
269
212k
    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
235k
    while (length > 12)
273
23.0k
    {
274
23.0k
      a += k[0];
275
23.0k
      b += k[1];
276
23.0k
      c += k[2];
277
23.0k
      mix(a,b,c);
278
23.0k
      length -= 12;
279
23.0k
      k += 3;
280
23.0k
    }
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
212k
#endif
303
212k
#ifndef PRECISE_MEMORY_ACCESS
304
305
212k
    switch(length)
306
212k
    {
307
786
    case 12: c+=k[2]; b+=k[1]; a+=k[0]; break;
308
3.05k
    case 11: c+=k[2]&0xffffff; b+=k[1]; a+=k[0]; break;
309
4.12k
    case 10: c+=k[2]&0xffff; b+=k[1]; a+=k[0]; break;
310
27.7k
    case 9 : c+=k[2]&0xff; b+=k[1]; a+=k[0]; break;
311
43.4k
    case 8 : b+=k[1]; a+=k[0]; break;
312
17.5k
    case 7 : b+=k[1]&0xffffff; a+=k[0]; break;
313
61.6k
    case 6 : b+=k[1]&0xffff; a+=k[0]; break;
314
7.64k
    case 5 : b+=k[1]&0xff; a+=k[0]; break;
315
21.9k
    case 4 : a+=k[0]; break;
316
1.21k
    case 3 : a+=k[0]&0xffffff; break;
317
1.49k
    case 2 : a+=k[0]&0xffff; break;
318
21.2k
    case 1 : a+=k[0]&0xff; break;
319
719
    case 0 : return c; /* zero length strings require no mixing */
320
212k
    }
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
212k
  }
345
116k
  else if (HASH_LITTLE_ENDIAN && ((u.i & 0x1) == 0))
346
39.3k
  {
347
39.3k
    const uint16_t *k = (const uint16_t *)key; /* read 16-bit chunks */
348
39.3k
    const uint8_t  *k8;
349
350
    /*--------------- all but last block: aligned reads and different mixing */
351
48.8k
    while (length > 12)
352
9.52k
    {
353
9.52k
      a += k[0] + (((uint32_t)k[1])<<16);
354
9.52k
      b += k[2] + (((uint32_t)k[3])<<16);
355
9.52k
      c += k[4] + (((uint32_t)k[5])<<16);
356
9.52k
      mix(a,b,c);
357
9.52k
      length -= 12;
358
9.52k
      k += 6;
359
9.52k
    }
360
361
    /*----------------------------- handle the last (probably partial) block */
362
39.3k
    k8 = (const uint8_t *)k;
363
39.3k
    switch(length)
364
39.3k
    {
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
691
    case 8 : b+=k[2]+(((uint32_t)k[3])<<16);
376
691
       a+=k[0]+(((uint32_t)k[1])<<16);
377
691
       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
29.1k
    case 5 : b+=k8[4];                      /* fall through */
383
29.1k
    case 4 : a+=k[0]+(((uint32_t)k[1])<<16);
384
29.1k
       break;
385
0
    case 3 : a+=((uint32_t)k8[2])<<16;      /* fall through */
386
0
    case 2 : a+=k[0];
387
0
       break;
388
9.52k
    case 1 : a+=k8[0];
389
9.52k
       break;
390
0
    case 0 : return c;                     /* zero length requires no mixing */
391
39.3k
    }
392
393
39.3k
  }
394
76.9k
  else
395
76.9k
  {
396
    /* need to read the key one byte at a time */
397
76.9k
    const uint8_t *k = (const uint8_t *)key;
398
399
    /*--------------- all but the last block: affect some 32 bits of (a,b,c) */
400
76.9k
    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
76.9k
    switch(length) /* all the case statements fall through */
421
76.9k
    {
422
14.9k
    case 12: c+=((uint32_t)k[11])<<24; /* FALLTHRU */
423
14.9k
    case 11: c+=((uint32_t)k[10])<<16; /* FALLTHRU */
424
14.9k
    case 10: c+=((uint32_t)k[9])<<8; /* FALLTHRU */
425
14.9k
    case 9 : c+=k[8]; /* FALLTHRU */
426
39.4k
    case 8 : b+=((uint32_t)k[7])<<24; /* FALLTHRU */
427
39.4k
    case 7 : b+=((uint32_t)k[6])<<16; /* FALLTHRU */
428
59.8k
    case 6 : b+=((uint32_t)k[5])<<8; /* FALLTHRU */
429
59.8k
    case 5 : b+=k[4]; /* FALLTHRU */
430
76.7k
    case 4 : a+=((uint32_t)k[3])<<24; /* FALLTHRU */
431
76.9k
    case 3 : a+=((uint32_t)k[2])<<16; /* FALLTHRU */
432
76.9k
    case 2 : a+=((uint32_t)k[1])<<8; /* FALLTHRU */
433
76.9k
    case 1 : a+=k[0];
434
76.9k
       break;
435
0
    case 0 : return c;
436
76.9k
    }
437
76.9k
  }
438
439
328k
  final(a,b,c);
440
328k
  return c;
441
328k
}
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
328k
{
460
#if defined _MSC_VER || defined __MINGW32__
461
#define RANDOM_SEED_TYPE LONG
462
#else
463
328k
#define RANDOM_SEED_TYPE int
464
328k
#endif
465
328k
  static volatile RANDOM_SEED_TYPE random_seed = -1;
466
467
328k
  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
328k
  return hashlittle((const char *)k, strlen((const char *)k), (uint32_t)random_seed);
492
328k
}
493
494
int lh_char_equal(const void *k1, const void *k2)
495
221k
{
496
221k
  return (strcmp((const char *)k1, (const char *)k2) == 0);
497
221k
}
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
51.9k
{
502
51.9k
  int i;
503
51.9k
  struct lh_table *t;
504
505
  /* Allocate space for elements to avoid divisions by zero. */
506
51.9k
  assert(size > 0);
507
51.9k
  t = (struct lh_table *)calloc(1, sizeof(struct lh_table));
508
51.9k
  if (!t)
509
0
    return NULL;
510
511
51.9k
  t->count = 0;
512
51.9k
  t->size = size;
513
51.9k
  t->table = (struct lh_entry *)calloc(size, sizeof(struct lh_entry));
514
51.9k
  if (!t->table)
515
0
  {
516
0
    free(t);
517
0
    return NULL;
518
0
  }
519
51.9k
  t->free_fn = free_fn;
520
51.9k
  t->hash_fn = hash_fn;
521
51.9k
  t->equal_fn = equal_fn;
522
889k
  for (i = 0; i < size; i++)
523
837k
    t->table[i].k = LH_EMPTY;
524
51.9k
  return t;
525
51.9k
}
526
527
struct lh_table *lh_kchar_table_new(int size, lh_entry_free_fn *free_fn)
528
51.7k
{
529
51.7k
  return lh_table_new(size, free_fn, char_hash_fn, lh_char_equal);
530
51.7k
}
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
225
{
539
225
  struct lh_table *new_t;
540
225
  struct lh_entry *ent;
541
542
225
  new_t = lh_table_new(new_size, NULL, t->hash_fn, t->equal_fn);
543
225
  if (new_t == NULL)
544
0
    return -1;
545
546
3.55k
  for (ent = t->head; ent != NULL; ent = ent->next)
547
3.33k
  {
548
3.33k
    unsigned long h = lh_get_hash(new_t, ent->k);
549
3.33k
    unsigned int opts = 0;
550
3.33k
    if (ent->k_is_constant)
551
0
      opts = JSON_C_OBJECT_ADD_CONSTANT_KEY;
552
3.33k
    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
3.33k
  }
558
225
  free(t->table);
559
225
  t->table = new_t->table;
560
225
  t->size = new_size;
561
225
  t->head = new_t->head;
562
225
  t->tail = new_t->tail;
563
225
  free(new_t);
564
565
225
  return 0;
566
225
}
567
568
void lh_table_free(struct lh_table *t)
569
51.7k
{
570
51.7k
  struct lh_entry *c;
571
51.7k
  if (t->free_fn)
572
51.7k
  {
573
109k
    for (c = t->head; c != NULL; c = c->next)
574
57.3k
      t->free_fn(c);
575
51.7k
  }
576
51.7k
  free(t->table);
577
51.7k
  free(t);
578
51.7k
}
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
112k
{
583
112k
  unsigned long n;
584
585
112k
  if (t->count >= t->size * LH_LOAD_FACTOR)
586
225
  {
587
    /* Avoid signed integer overflow with large tables. */
588
225
    int new_size = (t->size > INT_MAX / 2) ? INT_MAX : (t->size * 2);
589
225
    if (t->size == INT_MAX || lh_table_resize(t, new_size) != 0)
590
0
      return -1;
591
225
  }
592
593
112k
  n = h % t->size;
594
595
125k
  while (1)
596
125k
  {
597
125k
    if (t->table[n].k == LH_EMPTY || t->table[n].k == LH_FREED)
598
112k
      break;
599
13.6k
    if ((int)++n == t->size)
600
95
      n = 0;
601
13.6k
  }
602
603
112k
  t->table[n].k = k;
604
112k
  t->table[n].k_is_constant = (opts & JSON_C_OBJECT_ADD_CONSTANT_KEY);
605
112k
  t->table[n].v = v;
606
112k
  t->count++;
607
608
112k
  if (t->head == NULL)
609
31.7k
  {
610
31.7k
    t->head = t->tail = &t->table[n];
611
31.7k
    t->table[n].next = t->table[n].prev = NULL;
612
31.7k
  }
613
80.3k
  else
614
80.3k
  {
615
80.3k
    t->tail->next = &t->table[n];
616
80.3k
    t->table[n].prev = t->tail;
617
80.3k
    t->table[n].next = NULL;
618
80.3k
    t->tail = &t->table[n];
619
80.3k
  }
620
621
112k
  return 0;
622
112k
}
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
325k
{
631
325k
  unsigned long n = h % t->size;
632
325k
  int count = 0;
633
634
352k
  while (count < t->size)
635
352k
  {
636
352k
    if (t->table[n].k == LH_EMPTY)
637
131k
      return NULL;
638
221k
    if (t->table[n].k != LH_FREED && t->equal_fn(t->table[n].k, k))
639
194k
      return &t->table[n];
640
27.2k
    if ((int)++n == t->size)
641
105
      n = 0;
642
27.2k
    count++;
643
27.2k
  }
644
0
  return NULL;
645
325k
}
646
647
struct lh_entry *lh_table_lookup_entry(struct lh_table *t, const void *k)
648
212k
{
649
212k
  return lh_table_lookup_entry_w_hash(t, k, lh_get_hash(t, k));
650
212k
}
651
652
json_bool lh_table_lookup_ex(struct lh_table *t, const void *k, void **v)
653
212k
{
654
212k
  struct lh_entry *e = lh_table_lookup_entry(t, k);
655
212k
  if (e != NULL)
656
189k
  {
657
189k
    if (v != NULL)
658
184k
      *v = lh_entry_v(e);
659
189k
    return 1; /* key found */
660
189k
  }
661
22.6k
  if (v != NULL)
662
22.0k
    *v = NULL;
663
22.6k
  return 0; /* key not found */
664
212k
}
665
666
int lh_table_delete_entry(struct lh_table *t, struct lh_entry *e)
667
51.4k
{
668
  /* CAW: fixed to be 64bit nice, still need the crazy negative case... */
669
51.4k
  ptrdiff_t n = (ptrdiff_t)(e - t->table);
670
671
51.4k
  assert(n >= 0 && n < t->size);
672
673
  /* CAW: this is bad, really bad, maybe stack goes other direction on this machine... */
674
51.4k
  if (n < 0)
675
0
  {
676
0
    return -2;
677
0
  }
678
679
51.4k
  if (t->table[n].k == LH_EMPTY || t->table[n].k == LH_FREED)
680
0
    return -1;
681
51.4k
  t->count--;
682
51.4k
  if (t->free_fn)
683
51.4k
    t->free_fn(e);
684
51.4k
  t->table[n].v = NULL;
685
51.4k
  t->table[n].k = LH_FREED;
686
51.4k
  if (t->tail == &t->table[n] && t->head == &t->table[n])
687
8.52k
  {
688
8.52k
    t->head = t->tail = NULL;
689
8.52k
  }
690
42.8k
  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
42.8k
  else if (t->tail == &t->table[n])
696
42.5k
  {
697
42.5k
    t->tail->prev->next = NULL;
698
42.5k
    t->tail = t->tail->prev;
699
42.5k
  }
700
353
  else
701
353
  {
702
353
    t->table[n].prev->next = t->table[n].next;
703
353
    t->table[n].next->prev = t->table[n].prev;
704
353
  }
705
51.4k
  t->table[n].next = t->table[n].prev = NULL;
706
51.4k
  return 0;
707
51.4k
}
708
709
int lh_table_delete_entry_to_tail(struct lh_table *t, struct lh_entry *first_entry)
710
33.3k
{
711
33.3k
  struct lh_entry *del_entry = t->tail;
712
33.3k
  do
713
50.9k
  {
714
50.9k
    struct lh_entry *prev = del_entry->prev;
715
    // Could probably micro-optimize this, but better to avoid code duplication for now
716
50.9k
    if (lh_table_delete_entry(t, del_entry) != 0)
717
0
      return -1;
718
50.9k
    if (del_entry == first_entry)
719
33.3k
      break;
720
17.6k
    del_entry = prev;
721
17.6k
  } while (del_entry != NULL);
722
33.3k
  return 0;
723
33.3k
}
724
725
int lh_table_delete(struct lh_table *t, const void *k)
726
420
{
727
420
  struct lh_entry *e = lh_table_lookup_entry(t, k);
728
420
  if (!e)
729
0
    return -1;
730
420
  return lh_table_delete_entry(t, e);
731
420
}
732
733
int lh_table_length(struct lh_table *t)
734
126k
{
735
126k
  return t->count;
736
126k
}