Class: CBloomFilter
- Inherits:
-
Object
- Object
- CBloomFilter
- Defined in:
- ext/cbloomfilter/cbloomfilter.c
Class Method Summary collapse
Instance Method Summary collapse
- #b ⇒ Object
- #bitmap ⇒ Object
- #clear ⇒ Object
- #delete(key) ⇒ Object
- #include?(*args) ⇒ Boolean
- #insert(key) ⇒ Object
- #k ⇒ Object
- #load(bitmap) ⇒ Object
- #m ⇒ Object
- #merge!(other) ⇒ Object
- #num_set ⇒ Object
- #r ⇒ Object
- #to_s ⇒ Object
Class Method Details
.new(*args) ⇒ Object
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 |
# File 'ext/cbloomfilter/cbloomfilter.c', line 80
static VALUE bf_s_new(int argc, VALUE *argv, VALUE self) {
struct BloomFilter *bf;
VALUE arg1, arg2, arg3, arg4, arg5, obj;
int m, k, s, b, r, bytes;
obj = Data_Make_Struct(self, struct BloomFilter, NULL, bits_free, bf);
/* default = Fugou approach :-) */
arg1 = INT2FIX(100000000);
arg2 = INT2FIX(4);
arg3 = INT2FIX(0);
arg4 = INT2FIX(1);
arg5 = INT2FIX(0);
switch (argc) {
case 5:
if (argv[4] == Qtrue) {
arg5 = INT2FIX(1);
}
case 4:
arg4 = argv[3];
case 3:
arg3 = argv[2];
case 2:
arg2 = argv[1];
case 1:
arg1 = argv[0];
break;
}
m = FIX2INT(arg1);
k = FIX2INT(arg2);
s = FIX2INT(arg3);
b = FIX2INT(arg4);
r = FIX2INT(arg5);
if (b < 1 || b > 8)
rb_raise(rb_eArgError, "bucket size");
if (m < 1)
rb_raise(rb_eArgError, "array size");
if (k < 1)
rb_raise(rb_eArgError, "hash length");
if (s < 0)
rb_raise(rb_eArgError, "random seed");
bf->b = b;
bf->m = m;
bf->k = k;
bf->s = s;
bf->r = r;
bf->num_set = 0;
bf->bytes = ((m * b) + 15) / 8;
bf->ptr = ALLOC_N(unsigned char, bf->bytes);
/* initialize the bits with zeros */
memset(bf->ptr, 0, bf->bytes);
rb_iv_set(obj, "@hash_value", rb_hash_new());
return obj;
}
|
Instance Method Details
#b ⇒ Object
161 162 163 164 165 |
# File 'ext/cbloomfilter/cbloomfilter.c', line 161
static VALUE bf_b(VALUE self) {
struct BloomFilter *bf;
Data_Get_Struct(self, struct BloomFilter, bf);
return INT2FIX(bf->b);
}
|
#bitmap ⇒ Object
308 309 310 311 312 313 314 315 316 317 318 319 320 |
# File 'ext/cbloomfilter/cbloomfilter.c', line 308
static VALUE bf_bitmap(VALUE self) {
struct BloomFilter *bf;
Data_Get_Struct(self, struct BloomFilter, bf);
VALUE str = rb_str_new(0, bf->m);
unsigned char* ptr = (unsigned char *) RSTRING_PTR(str);
int i;
for (i = 0; i < bf->m; i++)
*ptr++ = bucket_get(bf, i);
return str;
}
|
#clear ⇒ Object
142 143 144 145 146 147 |
# File 'ext/cbloomfilter/cbloomfilter.c', line 142
static VALUE bf_clear(VALUE self) {
struct BloomFilter *bf;
Data_Get_Struct(self, struct BloomFilter, bf);
memset(bf->ptr, 0, bf->bytes);
return Qtrue;
}
|
#delete(key) ⇒ Object
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 |
# File 'ext/cbloomfilter/cbloomfilter.c', line 221
static VALUE bf_delete(VALUE self, VALUE key) {
int index, seed;
int i, len, m, k, s;
char *ckey;
VALUE skey;
struct BloomFilter *bf;
Data_Get_Struct(self, struct BloomFilter, bf);
skey = rb_obj_as_string(key);
ckey = StringValuePtr(skey);
len = (int) (RSTRING_LEN(skey)); /* length of the string in bytes */
m = bf->m;
k = bf->k;
s = bf->s;
for (i = 0; i <= k - 1; i++) {
/* seeds for hash functions */
seed = i + s;
/* hash */
index = (int) (crc32((unsigned int) (seed), ckey, len) % (unsigned int) (m));
/* set a bit at the index */
bucket_unset(bf, index);
}
bf->num_set += 1;
return Qnil;
}
|
#include?(*args) ⇒ Boolean
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 |
# File 'ext/cbloomfilter/cbloomfilter.c', line 253
static VALUE bf_include(int argc, VALUE* argv, VALUE self) {
int index, seed;
int i, len, m, k, s, tests_idx, vlen;
char *ckey;
VALUE tests, key, skey;
struct BloomFilter *bf;
rb_scan_args(argc, argv, "*", &tests);
Data_Get_Struct(self, struct BloomFilter, bf);
vlen = RARRAY_LEN(tests);
for(tests_idx = 0; tests_idx < vlen; tests_idx++) {
key = rb_ary_entry(tests, tests_idx);
skey = rb_obj_as_string(key);
ckey = StringValuePtr(skey);
len = (int) (RSTRING_LEN(skey)); /* length of the string in bytes */
m = bf->m;
k = bf->k;
s = bf->s;
for (i = 0; i <= k - 1; i++) {
/* seeds for hash functions */
seed = i + s;
/* hash */
index = (int) (crc32((unsigned int) (seed), ckey, len) % (unsigned int) (m));
/* check the bit at the index */
if (!bucket_check(bf, index)) {
return Qfalse; /* i.e., it is a new entry ; escape the loop */
}
}
return Qtrue;
}
}
|
#insert(key) ⇒ Object
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 |
# File 'ext/cbloomfilter/cbloomfilter.c', line 179
static VALUE bf_insert(VALUE self, VALUE key) {
VALUE skey;
int index, seed;
int i, len, m, k, s;
char *ckey;
struct BloomFilter *bf;
Data_Get_Struct(self, struct BloomFilter, bf);
skey = rb_obj_as_string(key);
ckey = StringValuePtr(skey);
len = (int) (RSTRING_LEN(skey)); /* length of the string in bytes */
m = bf->m;
k = bf->k;
s = bf->s;
for (i = 0; i <= k - 1; i++) {
/* seeds for hash functions */
seed = i + s;
/* hash */
index = (int) (crc32((unsigned int) (seed), ckey, len) % (unsigned int) (m));
/* set a bit at the index */
bucket_set(bf, index);
}
bf->num_set += 1;
return Qnil;
}
|
#k ⇒ Object
155 156 157 158 159 |
# File 'ext/cbloomfilter/cbloomfilter.c', line 155
static VALUE bf_k(VALUE self) {
struct BloomFilter *bf;
Data_Get_Struct(self, struct BloomFilter, bf);
return INT2FIX(bf->k);
}
|
#load(bitmap) ⇒ Object
322 323 324 325 326 327 328 329 330 331 332 333 334 |
# File 'ext/cbloomfilter/cbloomfilter.c', line 322
static VALUE bf_load(VALUE self, VALUE bitmap) {
struct BloomFilter *bf;
Data_Get_Struct(self, struct BloomFilter, bf);
unsigned char* ptr = (unsigned char *) RSTRING_PTR(bitmap);
int i;
for (i = 0; i < bf->m; i++) {
if (*ptr++)
bucket_set(bf, i);
}
return Qnil;
}
|
#m ⇒ Object
149 150 151 152 153 |
# File 'ext/cbloomfilter/cbloomfilter.c', line 149
static VALUE bf_m(VALUE self) {
struct BloomFilter *bf;
Data_Get_Struct(self, struct BloomFilter, bf);
return INT2FIX(bf->m);
}
|
#merge!(other) ⇒ Object
210 211 212 213 214 215 216 217 218 219 |
# File 'ext/cbloomfilter/cbloomfilter.c', line 210
static VALUE bf_merge(VALUE self, VALUE other) {
struct BloomFilter *bf, *target;
Data_Get_Struct(self, struct BloomFilter, bf);
Data_Get_Struct(other, struct BloomFilter, target);
int i;
for (i = 0; i < bf->bytes; i++) {
bf->ptr[i] |= target->ptr[i];
}
return Qnil;
}
|
#num_set ⇒ Object
173 174 175 176 177 |
# File 'ext/cbloomfilter/cbloomfilter.c', line 173
static VALUE bf_num_set(VALUE self) {
struct BloomFilter *bf;
Data_Get_Struct(self, struct BloomFilter, bf);
return INT2FIX(bf->num_set);
}
|
#r ⇒ Object
167 168 169 170 171 |
# File 'ext/cbloomfilter/cbloomfilter.c', line 167
static VALUE bf_r(VALUE self) {
struct BloomFilter *bf;
Data_Get_Struct(self, struct BloomFilter, bf);
return bf->r == 0 ? Qfalse : Qtrue;
}
|
#to_s ⇒ Object
292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 |
# File 'ext/cbloomfilter/cbloomfilter.c', line 292
static VALUE bf_to_s(VALUE self) {
struct BloomFilter *bf;
unsigned char *ptr;
int i;
VALUE str;
Data_Get_Struct(self, struct BloomFilter, bf);
str = rb_str_new(0, bf->m);
ptr = (unsigned char *) RSTRING_PTR(str);
for (i = 0; i < bf->m; i++)
*ptr++ = bucket_get(bf, i) ? '1' : '0';
return str;
}
|