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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344
|
/*
* $Id$
*
* Copyright (C) 2006 iptelorg GmbH
*
* Permission to use, copy, modify, and distribute this software for any
* purpose with or without fee is hereby granted, provided that the above
* copyright notice and this permission notice appear in all copies.
*
* THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
* WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
* MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
* ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
* WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
* ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
* OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
*/
/*
* History:
* --------
* 2006-02-02 created by andrei
* 2006-11-24 added numeric string optimized hash function (andrei)
* 2006-12-13 split into hashes.h (more generic) and str_hash.h (andrei)
* 2007-02-22 added case insensitive versions (andrei)
*/
#ifndef _hashes_h
#define _hashes_h
#include "str.h"
/* internal use: hash update
* params: char* s - string start,
* char* end - end
* char* p, and unsigned v temporary vars (used)
* unsigned h - result
* h should be initialized (e.g. set it to 0), the result in h */
#define hash_update_str(s, end, p, v, h) \
do{ \
for ((p)=(s); (p)<=((end)-4); (p)+=4){ \
(v)=(*(p)<<24)+((p)[1]<<16)+((p)[2]<<8)+(p)[3]; \
(h)+=(v)^((v)>>3); \
} \
switch((end)-(p)){\
case 3: \
(v)=(*(p)<<16)+((p)[1]<<8)+(p)[2]; break; \
case 2: \
(v)=(*(p)<<8)+p[1]; break; \
case 1: \
(v)=*p; break; \
default: \
(v)=0; break; \
} \
(h)+=(v)^((v)>>3); \
}while(0)
/* like hash_update_str, but case insensitive
* params: char* s - string start,
* char* end - end
* char* p, and unsigned v temporary vars (used)
* unsigned h - result
* h should be initialized (e.g. set it to 0), the result in h */
#define hash_update_case_str(s, end, p, v, h) \
do{ \
for ((p)=(s); (p)<=((end)-4); (p)+=4){ \
(v)=((*(p)<<24)+((p)[1]<<16)+((p)[2]<<8)+(p)[3])|0x20202020; \
(h)+=(v)^((v)>>3); \
} \
(v)=0; \
for (;(p)<(end); (p)++){ (v)<<=8; (v)+=*(p)|0x20;} \
(h)+=(v)^((v)>>3); \
}while(0)
/* internal use: call it to adjust the h from hash_update_str */
#define hash_finish(h) (((h)+((h)>>11))+(((h)>>13)+((h)>>23)))
/* "raw" 2 strings hash
* returns an unsigned int (which you can use modulo table_size as hash value)
*/
inline static unsigned int get_hash2_raw(const str* key1, const str* key2)
{
char* p;
register unsigned v;
register unsigned h;
h=0;
hash_update_str(key1->s, key1->s+key1->len, p, v, h);
hash_update_str(key2->s, key2->s+key2->len, p, v, h);
return hash_finish(h);
}
/* "raw" 1 string hash
* returns an unsigned int (which you can use modulo table_size as hash value)
*/
inline static unsigned int get_hash1_raw(const char* s, int len)
{
const char* p;
register unsigned v;
register unsigned h;
h=0;
hash_update_str(s, s+len, p, v, h);
return hash_finish(h);
}
/* a little slower than hash_* , but better distribution for
* numbers and about the same for strings */
#define hash_update_str2(s, end, p, v, h) \
do{ \
for ((p)=(s); (p)<=((end)-4); (p)+=4){ \
(v)=(*(p)*16777213)+((p)[1]*65537)+((p)[2]*257)+(p)[3]; \
(h)=16777259*(h)+((v)^((v)<<17)); \
} \
(v)=0; \
for (;(p)<(end); (p)++){ (v)*=251; (v)+=*(p);} \
(h)=16777259*(h)+((v)^((v)<<17)); \
}while(0)
/* like hash_update_str2 but case insensitive */
#define hash_update_case_str2(s, end, p, v, h) \
do{ \
for ((p)=(s); (p)<=((end)-4); (p)+=4){ \
(v)=((*(p)|0x20)*16777213)+(((p)[1]|0x20)*65537)+\
(((p)[2]|0x20)*257)+((p)[3]|0x20); \
(h)=16777259*(h)+((v)^((v)<<17)); \
} \
(v)=0; \
for (;(p)<(end); (p)++){ (v)*=251; (v)+=*(p)|0x20;} \
(h)=16777259*(h)+((v)^((v)<<17)); \
}while(0)
/* internal use: call it to adjust the h from hash_update_str */
#define hash_finish2(h) (((h)+((h)>>7))+(((h)>>13)+((h)>>23)))
/* a little slower than get_hash1_raw() , but better distribution for
* numbers and about the same for strings */
inline static unsigned int get_hash1_raw2(const char* s, int len)
{
const char* p;
register unsigned v;
register unsigned h;
h=0;
hash_update_str2(s, s+len, p, v, h);
return hash_finish2(h);
}
/* "raw" 2 strings hash optimized for numeric strings (see above)
* returns an unsigned int (which you can use modulo table_size as hash value)
*/
inline static unsigned int get_hash2_raw2(const str* key1, const str* key2)
{
char* p;
register unsigned v;
register unsigned h;
h=0;
hash_update_str2(key1->s, key1->s+key1->len, p, v, h);
hash_update_str2(key2->s, key2->s+key2->len, p, v, h);
return hash_finish2(h);
}
/* "raw" 2 strings case insensitive hash (like get_hash2_raw but case
* insensitive)
* returns an unsigned int (which you can use modulo table_size as hash value)
*/
inline static unsigned int get_hash2_case_raw(const str* key1, const str* key2)
{
char* p;
register unsigned v;
register unsigned h;
h=0;
hash_update_case_str(key1->s, key1->s+key1->len, p, v, h);
hash_update_case_str(key2->s, key2->s+key2->len, p, v, h);
return hash_finish(h);
}
/* "raw" 1 string case insensitive hash
* returns an unsigned int (which you can use modulo table_size as hash value)
*/
inline static unsigned int get_hash1_case_raw(const char* s, int len)
{
const char* p;
register unsigned v;
register unsigned h;
h=0;
hash_update_case_str(s, s+len, p, v, h);
return hash_finish(h);
}
/* same as get_hash1_raw2, but case insensitive and slower
* returns an unsigned int (which you can use modulo table_size as hash value)
*/
inline static unsigned int get_hash1_case_raw2(const char* s, int len)
{
const char* p;
register unsigned v;
register unsigned h;
h=0;
hash_update_case_str2(s, s+len, p, v, h);
return hash_finish2(h);
}
/* "raw" 2 strings hash optimized for numeric strings (see above)
* same as get_hash2_raw2 but case insensitive and slower
* returns an unsigned int (which you can use modulo table_size as hash value)
*/
inline static unsigned int get_hash2_case_raw2(const str* key1,
const str* key2)
{
char* p;
register unsigned v;
register unsigned h;
h=0;
hash_update_case_str2(key1->s, key1->s+key1->len, p, v, h);
hash_update_case_str2(key2->s, key2->s+key2->len, p, v, h);
return hash_finish2(h);
}
/*
* generic hashing - from the intial origins of ser
*/
#define ch_h_inc h+=v^(v>>3)
#define ch_icase(_c) (((_c)>='A'&&(_c)<='Z')?((_c)|0x20):(_c))
/*
* case sensitive hashing
* - s1 - str to hash
* - s2 - optional - continue hashing over s2
* - size - optional - size of hash table (must be power of 1); if set (!=0),
* instead of hash id, returned value is slot index
* return computed hash id or hash table slot index
*/
static inline unsigned int core_hash(const str *s1, const str *s2,
const unsigned int size)
{
char *p, *end;
register unsigned v;
register unsigned h;
h=0;
end=s1->s+s1->len;
for ( p=s1->s ; p<=(end-4) ; p+=4 ){
v=(*p<<24)+(p[1]<<16)+(p[2]<<8)+p[3];
ch_h_inc;
}
v=0;
for (; p<end ; p++){ v<<=8; v+=*p;}
ch_h_inc;
if (s2) {
end=s2->s+s2->len;
for (p=s2->s; p<=(end-4); p+=4){
v=(*p<<24)+(p[1]<<16)+(p[2]<<8)+p[3];
ch_h_inc;
}
v=0;
for (; p<end ; p++){ v<<=8; v+=*p;}
ch_h_inc;
}
h=((h)+(h>>11))+((h>>13)+(h>>23));
return size?((h)&(size-1)):h;
}
/*
* case insensitive hashing
* - s1 - str to hash
* - s2 - optional - continue hashing over s2
* - size - optional - size of hash table (must be power of 1); if set (!=0),
* instead of hash id, returned value is slot index
* return computed hash id or hash table slot index
*/
static inline unsigned int core_case_hash( str *s1, str *s2,
unsigned int size)
{
char *p, *end;
register unsigned v;
register unsigned h;
h=0;
end=s1->s+s1->len;
for ( p=s1->s ; p<=(end-4) ; p+=4 ){
v=(ch_icase(*p)<<24)+(ch_icase(p[1])<<16)+(ch_icase(p[2])<<8)
+ ch_icase(p[3]);
ch_h_inc;
}
v=0;
for (; p<end ; p++){ v<<=8; v+=ch_icase(*p);}
ch_h_inc;
if (s2) {
end=s2->s+s2->len;
for (p=s2->s; p<=(end-4); p+=4){
v=(ch_icase(*p)<<24)+(ch_icase(p[1])<<16)+(ch_icase(p[2])<<8)
+ ch_icase(p[3]);
ch_h_inc;
}
v=0;
for (; p<end ; p++){ v<<=8; v+=ch_icase(*p);}
ch_h_inc;
}
h=((h)+(h>>11))+((h>>13)+(h>>23));
return size?((h)&(size-1)):h;
}
#endif
|