hash functions replaced

src/Hashtable/Hashtable.c

@@ -39,7 +39,7 @@ void Hashtable_expand(Hashtable* ht){
         uint32 arlen=Autoarr_length(ar);
         for(uint32 k=0;k<arlen;k++){
             KVPair p=Autoarr_get(ar,k);
-            uint16 newrown=ihash(p.key)%HT_HEIGHTS[ht->hein];
+            uint16 newrown=hashs_sdbm32(p.key)%HT_HEIGHTS[ht->hein];
             Autoarr(KVPair)* newar=newrows[newrown];
             Autoarr_add(newar,p);
         }
@@ -53,7 +53,7 @@ void Hashtable_expand(Hashtable* ht){
 }
 
 Autoarr(KVPair)* getrow(Hashtable* ht, char* key, bool can_expand){
-    uint32 hash=ihash(key);
+    uint32 hash=hashs_sdbm32(key);
     Autoarr(KVPair)* ar=ht->rows[hash%HT_HEIGHTS[ht->hein]];
     if(can_expand && Autoarr_length(ar)==Autoarr_max_length(ar))
         optime("expand",1,(Hashtable_expand(ht)));

src/Hashtable/hash.c

@@ -1,15 +1,110 @@
 #include "hash.h"
 
-uint32 ihash(char *str){
-    uint32 hash=5381;
-    for (char c=*str;c;c=*(++str))
-        hash=((hash<<5)+hash)+c;
+uint32 hash_sdbm32(uint32 oldhash, void* buf, uint32 len){
+    uint8* ubuf=(uint8*)buf;
+    uint32 hash=oldhash;
+    for (; len ; len--, ubuf++)
+        hash=*ubuf+(hash<<6)+(hash<<16)-hash;
     return hash;
 }
 
-uint64 lhash(char* str){
-    uint64 hash = 0;
-    for (char c=*str;c;c=*(++str))
-        hash=c+(hash<<6)+(hash<<16)-hash;
-    return hash;
+static const uint32 crc_32_tab[]={
+    0x00000000, 0x77073096, 0xee0e612c, 0x990951ba, 
+    0x076dc419, 0x706af48f, 0xe963a535, 0x9e6495a3, 
+    0x0edb8832, 0x79dcb8a4, 0xe0d5e91e, 0x97d2d988,
+    0x09b64c2b, 0x7eb17cbd, 0xe7b82d07, 0x90bf1d91, 
+    0x1db71064, 0x6ab020f2, 0xf3b97148, 0x84be41de, 
+    0x1adad47d, 0x6ddde4eb, 0xf4d4b551, 0x83d385c7,
+    0x136c9856, 0x646ba8c0, 0xfd62f97a, 0x8a65c9ec, 
+    0x14015c4f, 0x63066cd9, 0xfa0f3d63, 0x8d080df5, 
+    0x3b6e20c8, 0x4c69105e, 0xd56041e4, 0xa2677172,
+    0x3c03e4d1, 0x4b04d447, 0xd20d85fd, 0xa50ab56b, 
+    0x35b5a8fa, 0x42b2986c, 0xdbbbc9d6, 0xacbcf940, 
+    0x32d86ce3, 0x45df5c75, 0xdcd60dcf, 0xabd13d59,
+    0x26d930ac, 0x51de003a, 0xc8d75180, 0xbfd06116, 
+    0x21b4f4b5, 0x56b3c423, 0xcfba9599, 0xb8bda50f, 
+    0x2802b89e, 0x5f058808, 0xc60cd9b2, 0xb10be924,
+    0x2f6f7c87, 0x58684c11, 0xc1611dab, 0xb6662d3d, 
+    0x76dc4190, 0x01db7106, 0x98d220bc, 0xefd5102a, 
+    0x71b18589, 0x06b6b51f, 0x9fbfe4a5, 0xe8b8d433,
+    0x7807c9a2, 0x0f00f934, 0x9609a88e, 0xe10e9818, 
+    0x7f6a0dbb, 0x086d3d2d, 0x91646c97, 0xe6635c01, 
+    0x6b6b51f4, 0x1c6c6162, 0x856530d8, 0xf262004e,
+    0x6c0695ed, 0x1b01a57b, 0x8208f4c1, 0xf50fc457, 
+    0x65b0d9c6, 0x12b7e950, 0x8bbeb8ea, 0xfcb9887c, 
+    0x62dd1ddf, 0x15da2d49, 0x8cd37cf3, 0xfbd44c65,
+    0x4db26158, 0x3ab551ce, 0xa3bc0074, 0xd4bb30e2, 
+    0x4adfa541, 0x3dd895d7, 0xa4d1c46d, 0xd3d6f4fb, 
+    0x4369e96a, 0x346ed9fc, 0xad678846, 0xda60b8d0,
+    0x44042d73, 0x33031de5, 0xaa0a4c5f, 0xdd0d7cc9, 
+    0x5005713c, 0x270241aa, 0xbe0b1010, 0xc90c2086, 
+    0x5768b525, 0x206f85b3, 0xb966d409, 0xce61e49f,
+    0x5edef90e, 0x29d9c998, 0xb0d09822, 0xc7d7a8b4, 
+    0x59b33d17, 0x2eb40d81, 0xb7bd5c3b, 0xc0ba6cad, 
+    0xedb88320, 0x9abfb3b6, 0x03b6e20c, 0x74b1d29a,
+    0xead54739, 0x9dd277af, 0x04db2615, 0x73dc1683, 
+    0xe3630b12, 0x94643b84, 0x0d6d6a3e, 0x7a6a5aa8, 
+    0xe40ecf0b, 0x9309ff9d, 0x0a00ae27, 0x7d079eb1,
+    0xf00f9344, 0x8708a3d2, 0x1e01f268, 0x6906c2fe, 
+    0xf762575d, 0x806567cb, 0x196c3671, 0x6e6b06e7, 
+    0xfed41b76, 0x89d32be0, 0x10da7a5a, 0x67dd4acc,
+    0xf9b9df6f, 0x8ebeeff9, 0x17b7be43, 0x60b08ed5, 
+    0xd6d6a3e8, 0xa1d1937e, 0x38d8c2c4, 0x4fdff252, 
+    0xd1bb67f1, 0xa6bc5767, 0x3fb506dd, 0x48b2364b,
+    0xd80d2bda, 0xaf0a1b4c, 0x36034af6, 0x41047a60, 
+    0xdf60efc3, 0xa867df55, 0x316e8eef, 0x4669be79, 
+    0xcb61b38c, 0xbc66831a, 0x256fd2a0, 0x5268e236,
+    0xcc0c7795, 0xbb0b4703, 0x220216b9, 0x5505262f, 
+    0xc5ba3bbe, 0xb2bd0b28, 0x2bb45a92, 0x5cb36a04, 
+    0xc2d7ffa7, 0xb5d0cf31, 0x2cd99e8b, 0x5bdeae1d,
+    0x9b64c2b0, 0xec63f226, 0x756aa39c, 0x026d930a, 
+    0x9c0906a9, 0xeb0e363f, 0x72076785, 0x05005713, 
+    0x95bf4a82, 0xe2b87a14, 0x7bb12bae, 0x0cb61b38,
+    0x92d28e9b, 0xe5d5be0d, 0x7cdcefb7, 0x0bdbdf21, 
+    0x86d3d2d4, 0xf1d4e242, 0x68ddb3f8, 0x1fda836e, 
+    0x81be16cd, 0xf6b9265b, 0x6fb077e1, 0x18b74777,
+    0x88085ae6, 0xff0f6a70, 0x66063bca, 0x11010b5c, 
+    0x8f659eff, 0xf862ae69, 0x616bffd3, 0x166ccf45, 
+    0xa00ae278, 0xd70dd2ee, 0x4e048354, 0x3903b3c2,
+    0xa7672661, 0xd06016f7, 0x4969474d, 0x3e6e77db, 
+    0xaed16a4a, 0xd9d65adc, 0x40df0b66, 0x37d83bf0, 
+    0xa9bcae53, 0xdebb9ec5, 0x47b2cf7f, 0x30b5ffe9,
+    0xbdbdf21c, 0xcabac28a, 0x53b39330, 0x24b4a3a6, 
+    0xbad03605, 0xcdd70693, 0x54de5729, 0x23d967bf, 
+    0xb3667a2e, 0xc4614ab8, 0x5d681b02, 0x2a6f2b94,
+    0xb40bbe37, 0xc30c8ea1, 0x5a05df1b, 0x2d02ef8d
+};
+
+uint32 hash_crc32(uint32 oldhash, void* buf, uint32 len){
+    uint8* ubuf=(uint8*)buf;
+    register uint32 crc=oldhash;
+    for (; len; --len, ++ubuf)
+        crc = crc_32_tab[(crc^(*ubuf)) & 0xff] ^ (crc>>8);
+    return ~crc;
 }
+
+// bool hashf_crc32c(char *name, uint32 *crc, long *charcnt) {
+//     register FILE *fin;
+//     register uint32 oldcrc32;
+//     register int c;
+
+//     oldcrc32 = 0xFFFFFFFF; *charcnt = 0;
+//     if ((fin=fopen(name, "r"))==NULL) {
+//         perror(name);
+//         return false;
+//     }
+//     while ((c=getc(fin))!=EOF) {
+//         ++*charcnt;
+//         oldcrc32 = UPDC32(c, oldcrc32);
+//     }
+
+//     if (ferror(fin)) {
+//         perror(name);
+//         *charcnt = -1;
+//     }
+
+//     fclose(fin);
+
+//     *crc = oldcrc32 = ~oldcrc32;
+//     return true;
+// }

src/Hashtable/hash.h

@@ -6,10 +6,13 @@ extern "C" {
 
 #include "../base/base.h"
 
-// djb2 hash function from http:// www.cse.yorku.ca/~oz/hash.html
-uint32 ihash(char *str);
-// sdbm hash function
-uint64 lhash(char* str);
+uint32 hash_sdbm32(uint32 oldhash, void* buf, uint32 len);
+#define hashb_sdbm32(BUF, LEN) hash_sdbm32(0xFFFFFFFF, BUF, LEN)
+#define hashs_sdbm32(STR)      hash_sdbm32(0xFFFFFFFF, STR, cptr_length(STR))
+
+uint32 hash_crc32(uint32 oldhash, void* buf, uint32 len);
+#define hashb_crc32(BUF, LEN) hash_crc32(0xFFFFFFFF, BUF, LEN)
+#define hashs_crc32(STR)      hash_crc32(0xFFFFFFFF, STR, cptr_length(STR))
 
 #if __cplusplus
 }

tests/main.cpp

@@ -1,19 +1,20 @@
 #include "tests.h"
 
 void test_all(){
-    test_autoarr();
-    test_string();
-    test_safethrow();
-    test_searchtree();
-    test_hashtable();
-    test_dtsod();
-    test_autoarr2();
+    // test_autoarr();
+    // test_string();
+    // test_safethrow();
+    // test_searchtree();
+    // test_hashtable();
+    // test_dtsod();
+    // test_autoarr2();
+    test_hash_collisions();
     printf("\e[96m---------------------------------------\e[0m\n");
 }
 
 int main(){
     setlocale(LC_ALL, "en-US.Unicode");
-    printf("\e[92mdtsod parser in c language!\e[97m\n");
+    printf("\e[92mkerep tests are starting!\e[97m\n");
     optime("test_all",1,test_all());
     printf("\e[0m\n");
     return 0;

tests/test_hash.c

@@ -0,0 +1,37 @@
+#include "tests.h"
+#include "../src/Hashtable/hash.h"
+#include "../src/Autoarr/Autoarr.h"
+
+#define AMOUNT_OF_TESTS 400000
+
+#define test_hashf(hasht, hashf, tests_n)\
+    optime(#hashf,1,({\
+    printf("\e[94mfunction: " #hashf "\n");\
+    Autoarr(hasht)* hashes=Autoarr_create(hasht,512,32768);\
+    uint32 collisions=0;\
+    for(uint32 i=0;i<tests_n;i++){\
+        hasht h=hashf((uint8*)&i, 4);\
+        bool col=false;\
+        Autoarr_foreach(hashes,e,({\
+            if(e==h) {\
+                col=true;\
+                printf("\e[91mcollision: %lu\n", (uint64)h);\
+                break;\
+            }\
+        }));\
+        if(col) collisions++;\
+        else Autoarr_add(hashes,h);\
+    }\
+    printf("\e[92m%u collisions detected per %u numbers\n", collisions, tests_n);\
+}))
+
+void test_hash_collisions(){
+    optime("test_hash_collisions",1,({
+        printf("\e[96m--------[test_hash_collisions]--------\n");
+        char buf[]="iojihiojopijiugbjmoihftytryfdrh";
+        printf("\e[92mhashb_crc32: %x\n", hashb_crc32(buf,cptr_length(buf)));
+        printf("\e[92mhashb_sdbm32: %x\n", hashb_sdbm32(buf,cptr_length(buf)));
+        test_hashf(uint32, hashb_crc32, 20000);
+        test_hashf(uint32, hashb_sdbm32, 20000);
+    }));
+}

tests/tests.h

@@ -12,6 +12,7 @@ void test_string();
 void test_dtsod();
 void test_safethrow();
 void test_autoarr2();
+void test_hash_collisions();
 #if __cplusplus
 }
 #endif