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
| // Implements a dictionary's functionality
#include <stdbool.h>
#include <stdio.h>
#include <stdlib.h>
#include <ctype.h>
#include <string.h>
#include "dictionary.h"
// Represents a node in a hash table
typedef struct node
{
char word[LENGTH + 1];
struct node *next;
}
node;
// Number of buckets in hash table
const unsigned int N = 65536;
// Hash table
node *table[N];
unsigned int word_count = 0;
///
uint32_t
murmurhash (const char *key, uint32_t len, uint32_t seed) {
uint32_t c1 = 0xcc9e2d51;
uint32_t c2 = 0x1b873593;
uint32_t r1 = 15;
uint32_t r2 = 13;
uint32_t m = 5;
uint32_t n = 0xe6546b64;
uint32_t h = 0;
uint32_t k = 0;
uint8_t *d = (uint8_t *) key; // 32 bit extract from `key'
const uint32_t *chunks = NULL;
const uint8_t *tail = NULL; // tail - last 8 bytes
int i = 0;
int l = len / 4; // chunk length
h = seed;
chunks = (const uint32_t *) (d + l * 4); // body
tail = (const uint8_t *) (d + l * 4); // last 8 byte chunk of `key'
// for each 4 byte chunk of `key'
for (i = -l; i != 0; ++i) {
// next 4 byte chunk of `key'
k = chunks[i];
// encode next 4 byte chunk of `key'
k *= c1;
k = (k << r1) | (k >> (32 - r1));
k *= c2;
// append to hash
h ^= k;
h = (h << r2) | (h >> (32 - r2));
h = h * m + n;
}
k = 0;
// remainder
switch (len & 3) { // `len % 4'
case 3: k ^= (tail[2] << 16);
case 2: k ^= (tail[1] << 8);
case 1:
k ^= tail[0];
k *= c1;
k = (k << r1) | (k >> (32 - r1));
k *= c2;
h ^= k;
}
h ^= len;
h ^= (h >> 16);
h *= 0x85ebca6b;
h ^= (h >> 13);
h *= 0xc2b2ae35;
h ^= (h >> 16);
return h;
}
///
// Returns true if word is in dictionary else false
bool check(const char *word)
{
char word_lower[LENGTH + 1];
int word_len = strlen(word) + 1;
for (int i = 0; i < word_len; i++)
{
word_lower[i] = tolower(word[i]);
}
unsigned int word_hash = hash(word_lower);
if (table[word_hash] == NULL)
{
return false;
}
else if (strcmp(table[word_hash]->word, word_lower) == 0)
{
return true;
}
else
{
for (node *tmp = table[word_hash]->next; tmp != NULL; tmp = tmp->next)
{
if (strcmp(tmp->word, word_lower) == 0)
{
return true;
}
}
}
return false;
}
// Hashes word to a number
unsigned int hash(const char *word)
{
return murmurhash(word, strlen(word), 0) >> 16;
}
// Loads dictionary into memory, returning true if successful else false
bool load(const char *dictionary)
{
static node nodes[200000];
memset(nodes, 0, sizeof(node) * 200000);
char buff[LENGTH + 1] = {'\0'};
FILE *fp;
fp = fopen(dictionary, "r");
if (fp == NULL)
{
return false;
}
else
{
while (fscanf(fp, "%s", buff) != EOF)
{
unsigned int buff_hash = hash(buff);
if (table[buff_hash] == NULL)
{
table[buff_hash] = &nodes[word_count];
memcpy(table[buff_hash]->word, buff, LENGTH + 1);
table[buff_hash]->next = NULL;
word_count++;
}
else
{
node *n = &nodes[word_count];
memcpy(n->word, buff, LENGTH + 1);
n->next = table[buff_hash];
table[buff_hash] = n;
word_count++;
}
}
fclose(fp);
return true;
}
return false;
}
// Returns number of words in dictionary if loaded else 0 if not yet loaded
unsigned int size(void)
{
return word_count;
}
// Unloads dictionary from memory, returning true if successful else false
bool unload(void)
{
return true;
}
|
Jason's Blog