Skip to content

Instantly share code, notes, and snippets.

@leffuy

leffuy/CosmosTests.c

Created February 25, 2012 02:42
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save leffuy/1905432 to your computer and use it in GitHub Desktop.
Save leffuy/1905432 to your computer and use it in GitHub Desktop.
Download ZIP
Hashmap tests
Raw
CosmosTests.c
//Deprecated. The hashmap implementation started failing simple use cases.
#include <stdio.h>
#include <malloc.h>
#include <SDL.h>
#include "hashmap.h"
//map_t CosmosMap;
struct Cosmos{
struct ModelIndex* indices;
int screenX, screenY;
map_t models;
//models go here
}; //Serves as a model database
struct ModelIndex{
char* id;
struct ModelIndex* next;
};
struct Model{
char* id; //serves as pk
struct Sprite* appearance; //appearance map
int worldX, worldY; //from the world
//here is where the chipmunk actor goes
};
static struct Cosmos kosmos;
static int cosmosIts = 0;
map_t CosmosMap = 0;
void InitCosmos();
void AddToCosmos(struct Model inmodel);
void RemoveFromCosmos(char* key);
struct Model* GetFromCosmos(char* key);
SDL_Surface* RenderFromCosmos();
void InitCosmos(){
kosmos.models = hashmap_new();
}
void AddToCosmos(struct Model inmodel){
hashmap_put(kosmos.models, inmodel.id, (any_t)(&inmodel));
}
struct Model* GetFromCosmos(char* key){
struct Model* p_model = 0;
hashmap_get(kosmos.models, key, (any_t*)(&p_model));
return p_model;
}
void RemoveFromCosmos(char* key){
hashmap_remove(kosmos.models, key);
//some possible error checking here
}
//Need to test the iterator
//Quote from P-Dizzle: "Just use the iterator."
//In the future I propose we'll use some sort of space partitioning
//to only iterate over the smallest needed subset of models
//the actual iterator, this pulls data iteratively from the cosmos
//adjust as needed
int ExtractFromCosmos(any_t item, any_t data){
//this little guy gets sent in as a memory array?
int* cosbylist = (int*)(item); //This will be X World values list
//shold also be the size of element length
struct Model* amodel = (struct Model*)(data);
cosbylist[cosmosIts] = amodel->worldX;
printf("What is this model here: %d\n", amodel->worldX);
printf("What is this model here: %s\n", ((struct Model*)(data))->id);
cosmosIts += 1;
return MAP_OK;
}
void TestCosmosIteration(){
cosmosIts = 0;
int* cosmosList = (int*)malloc(sizeof(int)*hashmap_length(kosmos.models));
hashmap_iterate(kosmos.models, ExtractFromCosmos, (any_t)cosmosList);
int k = 0;
for(k = 0; k < hashmap_length(kosmos.models); k++){
printf("ScreenX @ some shit: %d\n", cosmosList[k]);
}
}
//Render out the cosmos (in relation to screen position), to a viewport sized
//surface
SDL_Surface* RenderFromCosmos(){
SDL_Surface* tmp_render = NULL;
//iterate over cosmos
//starting with a stub
return tmp_render;
}
int main (int argc, char** argv){
InitCosmos();
struct Model modelnum1;
struct Model modelnum2;
struct Model modelnum3;
modelnum1.id = "model1";
modelnum1.appearance = NULL;
modelnum1.worldX = 10;
modelnum1.worldY = 10;
modelnum2.id = "model2";
modelnum2.appearance = NULL;
modelnum2.worldX = 11;
modelnum2.worldY = 11;
modelnum3.id = "model3";
modelnum3.appearance = NULL;
modelnum3.worldX = 12;
modelnum3.worldY = 12;
//struct Model* modelnum2;
AddToCosmos(modelnum1);
AddToCosmos(modelnum2);
AddToCosmos(modelnum3);
TestCosmosIteration();
struct Model* modelnum4 = GetFromCosmos("model2");
//hashmap_put(CosmosMap, "model1", (any_t)(&modelnum1));
//hashmap_get(CosmosMap, "model1", (any_t*)(&modelnum2));
printf("WorldX value from hash: %d \n", modelnum4->worldX);
return 0;
}
Raw
CosmosUTHash.c
#include <string.h> /* strcpy */
#include <stdlib.h> /* malloc */
#include <stdio.h> /* printf */
#include <SDL.h>
#include "uthash.h"
struct Renderer{
int width, height;
SDL_Window* window;
SDL_Surface* back_buff;
SDL_Surface* screen;
Uint32 alpha_color;
int (*RenderFunc)(); //need to deprecate this
};
struct Sprite{
int frames;
int currentframe;
int width, height;
int screenX, screenY;
SDL_Surface* frame_strip;
SDL_Surface* currentFrame;
};
struct Cosmos{
int screenX, screenY;
//models go here
struct Model* model_hash;
struct Renderer* r_ptr; //Cosmos gets direct access to the renderer assets
}; //Serves as a model database
struct Model{
int id; //serves as pk
char* name;
struct Sprite* appearance; //appearance map
int worldX, worldY; //from the world
//here is where the chipmunk actor goes
UT_hash_handle hh; /* makes this structure hashable */
};
struct Cosmos kosmos;
void InitCosmos(){
kosmos.model_hash = NULL;
}
void AddCosmos(struct Model *m){
HASH_ADD_INT(kosmos.model_hash, id, m);
}
struct Model* GetCosmos(int key){
struct Model* m = NULL;
HASH_FIND_INT(kosmos.model_hash, &key, m);
return m;
}
void DelCosmos(int key){
struct Model* m = NULL;
m = GetCosmos(key);
HASH_DEL(kosmos.model_hash, m);
}
//put this back as return type after initial prototyping
//SDL_Surface*
//iterates through hash map and dumps out curent frame at current position
void RenderFromCosmos(){
struct Model *m;
int i = 0;
for(m=kosmos.model_hash; m != NULL; m=m->hh.next){
//iterate here
printf("Model %d's total animation frames: %d\n",i,m->appearance->frames);
}
//dereferencesprite
//blit to layer
} //sucks we won't be able to functional test this guy
//functional testing
int main(int argc, char** argv){
struct Model modelnum1; // = (struct Model*)malloc(sizeof(struct Model));
struct Model modelnum2; // = (struct Model*)malloc(sizeof(struct Model));
struct Model* modelptr;
struct Sprite model1sprt;
struct Sprite model2sprt;
//define some sprites here
model1sprt.frames = 0;
model2sprt.frames = 5;
modelnum1.id = 0;
modelnum1.name = "model1";
modelnum1.appearance = &model1sprt;
modelnum1.worldX = 10;
modelnum1.worldY = 10;
modelnum2.id = 1;
modelnum2.name = "model2";
modelnum2.appearance = &model2sprt;
modelnum2.worldX = 11;
modelnum2.worldY = 11;
InitCosmos();
AddCosmos(&modelnum1);
AddCosmos(&modelnum2);
int ider = 0;
modelptr = GetCosmos(ider);
printf("Model one id: %s\n", modelptr->name);
RenderFromCosmos();
return 0;
}
Raw
hashmap.c
/*
* Generic map implementation.
*/
#include "hashmap.h"
#include <stdlib.h>
#include <stdio.h>
#include <string.h>
#define INITIAL_SIZE (256)
#define MAX_CHAIN_LENGTH (8)
/* We need to keep keys and values */
typedef struct _hashmap_element{
char* key;
int in_use;
any_t data;
} hashmap_element;
/* A hashmap has some maximum size and current size,
* as well as the data to hold. */
typedef struct _hashmap_map{
int table_size;
int size;
hashmap_element *data;
} hashmap_map;
/*
* Return an empty hashmap, or NULL on failure.
*/
map_t hashmap_new() {
hashmap_map* m = (hashmap_map*) malloc(sizeof(hashmap_map));
if(!m) goto err;
m->data = (hashmap_element*) calloc(INITIAL_SIZE, sizeof(hashmap_element));
if(!m->data) goto err;
m->table_size = INITIAL_SIZE;
m->size = 0;
return m;
err:
if (m)
hashmap_free(m);
return NULL;
}
/* The implementation here was originally done by Gary S. Brown. I have
borrowed the tables directly, and made some minor changes to the
crc32-function (including changing the interface). //ylo */
/* ============================================================= */
/* COPYRIGHT (C) 1986 Gary S. Brown. You may use this program, or */
/* code or tables extracted from it, as desired without restriction. */
/* */
/* First, the polynomial itself and its table of feedback terms. The */
/* polynomial is */
/* X^32+X^26+X^23+X^22+X^16+X^12+X^11+X^10+X^8+X^7+X^5+X^4+X^2+X^1+X^0 */
/* */
/* Note that we take it "backwards" and put the highest-order term in */
/* the lowest-order bit. The X^32 term is "implied"; the LSB is the */
/* X^31 term, etc. The X^0 term (usually shown as "+1") results in */
/* the MSB being 1. */
/* */
/* Note that the usual hardware shift register implementation, which */
/* is what we're using (we're merely optimizing it by doing eight-bit */
/* chunks at a time) shifts bits into the lowest-order term. In our */
/* implementation, that means shifting towards the right. Why do we */
/* do it this way? Because the calculated CRC must be transmitted in */
/* order from highest-order term to lowest-order term. UARTs transmit */
/* characters in order from LSB to MSB. By storing the CRC this way, */
/* we hand it to the UART in the order low-byte to high-byte; the UART */
/* sends each low-bit to hight-bit; and the result is transmission bit */
/* by bit from highest- to lowest-order term without requiring any bit */
/* shuffling on our part. Reception works similarly. */
/* */
/* The feedback terms table consists of 256, 32-bit entries. Notes: */
/* */
/* The table can be generated at runtime if desired; code to do so */
/* is shown later. It might not be obvious, but the feedback */
/* terms simply represent the results of eight shift/xor opera- */
/* tions for all combinations of data and CRC register values. */
/* */
/* The values must be right-shifted by eight bits by the "updcrc" */
/* logic; the shift must be unsigned (bring in zeroes). On some */
/* hardware you could probably optimize the shift in assembler by */
/* using byte-swap instructions. */
/* polynomial $edb88320 */
/* */
/* -------------------------------------------------------------------- */
static unsigned long crc32_tab[] = {
0x00000000L, 0x77073096L, 0xee0e612cL, 0x990951baL, 0x076dc419L,
0x706af48fL, 0xe963a535L, 0x9e6495a3L, 0x0edb8832L, 0x79dcb8a4L,
0xe0d5e91eL, 0x97d2d988L, 0x09b64c2bL, 0x7eb17cbdL, 0xe7b82d07L,
0x90bf1d91L, 0x1db71064L, 0x6ab020f2L, 0xf3b97148L, 0x84be41deL,
0x1adad47dL, 0x6ddde4ebL, 0xf4d4b551L, 0x83d385c7L, 0x136c9856L,
0x646ba8c0L, 0xfd62f97aL, 0x8a65c9ecL, 0x14015c4fL, 0x63066cd9L,
0xfa0f3d63L, 0x8d080df5L, 0x3b6e20c8L, 0x4c69105eL, 0xd56041e4L,
0xa2677172L, 0x3c03e4d1L, 0x4b04d447L, 0xd20d85fdL, 0xa50ab56bL,
0x35b5a8faL, 0x42b2986cL, 0xdbbbc9d6L, 0xacbcf940L, 0x32d86ce3L,
0x45df5c75L, 0xdcd60dcfL, 0xabd13d59L, 0x26d930acL, 0x51de003aL,
0xc8d75180L, 0xbfd06116L, 0x21b4f4b5L, 0x56b3c423L, 0xcfba9599L,
0xb8bda50fL, 0x2802b89eL, 0x5f058808L, 0xc60cd9b2L, 0xb10be924L,
0x2f6f7c87L, 0x58684c11L, 0xc1611dabL, 0xb6662d3dL, 0x76dc4190L,
0x01db7106L, 0x98d220bcL, 0xefd5102aL, 0x71b18589L, 0x06b6b51fL,
0x9fbfe4a5L, 0xe8b8d433L, 0x7807c9a2L, 0x0f00f934L, 0x9609a88eL,
0xe10e9818L, 0x7f6a0dbbL, 0x086d3d2dL, 0x91646c97L, 0xe6635c01L,
0x6b6b51f4L, 0x1c6c6162L, 0x856530d8L, 0xf262004eL, 0x6c0695edL,
0x1b01a57bL, 0x8208f4c1L, 0xf50fc457L, 0x65b0d9c6L, 0x12b7e950L,
0x8bbeb8eaL, 0xfcb9887cL, 0x62dd1ddfL, 0x15da2d49L, 0x8cd37cf3L,
0xfbd44c65L, 0x4db26158L, 0x3ab551ceL, 0xa3bc0074L, 0xd4bb30e2L,
0x4adfa541L, 0x3dd895d7L, 0xa4d1c46dL, 0xd3d6f4fbL, 0x4369e96aL,
0x346ed9fcL, 0xad678846L, 0xda60b8d0L, 0x44042d73L, 0x33031de5L,
0xaa0a4c5fL, 0xdd0d7cc9L, 0x5005713cL, 0x270241aaL, 0xbe0b1010L,
0xc90c2086L, 0x5768b525L, 0x206f85b3L, 0xb966d409L, 0xce61e49fL,
0x5edef90eL, 0x29d9c998L, 0xb0d09822L, 0xc7d7a8b4L, 0x59b33d17L,
0x2eb40d81L, 0xb7bd5c3bL, 0xc0ba6cadL, 0xedb88320L, 0x9abfb3b6L,
0x03b6e20cL, 0x74b1d29aL, 0xead54739L, 0x9dd277afL, 0x04db2615L,
0x73dc1683L, 0xe3630b12L, 0x94643b84L, 0x0d6d6a3eL, 0x7a6a5aa8L,
0xe40ecf0bL, 0x9309ff9dL, 0x0a00ae27L, 0x7d079eb1L, 0xf00f9344L,
0x8708a3d2L, 0x1e01f268L, 0x6906c2feL, 0xf762575dL, 0x806567cbL,
0x196c3671L, 0x6e6b06e7L, 0xfed41b76L, 0x89d32be0L, 0x10da7a5aL,
0x67dd4accL, 0xf9b9df6fL, 0x8ebeeff9L, 0x17b7be43L, 0x60b08ed5L,
0xd6d6a3e8L, 0xa1d1937eL, 0x38d8c2c4L, 0x4fdff252L, 0xd1bb67f1L,
0xa6bc5767L, 0x3fb506ddL, 0x48b2364bL, 0xd80d2bdaL, 0xaf0a1b4cL,
0x36034af6L, 0x41047a60L, 0xdf60efc3L, 0xa867df55L, 0x316e8eefL,
0x4669be79L, 0xcb61b38cL, 0xbc66831aL, 0x256fd2a0L, 0x5268e236L,
0xcc0c7795L, 0xbb0b4703L, 0x220216b9L, 0x5505262fL, 0xc5ba3bbeL,
0xb2bd0b28L, 0x2bb45a92L, 0x5cb36a04L, 0xc2d7ffa7L, 0xb5d0cf31L,
0x2cd99e8bL, 0x5bdeae1dL, 0x9b64c2b0L, 0xec63f226L, 0x756aa39cL,
0x026d930aL, 0x9c0906a9L, 0xeb0e363fL, 0x72076785L, 0x05005713L,
0x95bf4a82L, 0xe2b87a14L, 0x7bb12baeL, 0x0cb61b38L, 0x92d28e9bL,
0xe5d5be0dL, 0x7cdcefb7L, 0x0bdbdf21L, 0x86d3d2d4L, 0xf1d4e242L,
0x68ddb3f8L, 0x1fda836eL, 0x81be16cdL, 0xf6b9265bL, 0x6fb077e1L,
0x18b74777L, 0x88085ae6L, 0xff0f6a70L, 0x66063bcaL, 0x11010b5cL,
0x8f659effL, 0xf862ae69L, 0x616bffd3L, 0x166ccf45L, 0xa00ae278L,
0xd70dd2eeL, 0x4e048354L, 0x3903b3c2L, 0xa7672661L, 0xd06016f7L,
0x4969474dL, 0x3e6e77dbL, 0xaed16a4aL, 0xd9d65adcL, 0x40df0b66L,
0x37d83bf0L, 0xa9bcae53L, 0xdebb9ec5L, 0x47b2cf7fL, 0x30b5ffe9L,
0xbdbdf21cL, 0xcabac28aL, 0x53b39330L, 0x24b4a3a6L, 0xbad03605L,
0xcdd70693L, 0x54de5729L, 0x23d967bfL, 0xb3667a2eL, 0xc4614ab8L,
0x5d681b02L, 0x2a6f2b94L, 0xb40bbe37L, 0xc30c8ea1L, 0x5a05df1bL,
0x2d02ef8dL
};
/* Return a 32-bit CRC of the contents of the buffer. */
unsigned long crc32(const unsigned char *s, unsigned int len)
{
unsigned int i;
unsigned long crc32val;
crc32val = 0;
for (i = 0; i < len; i ++)
{
crc32val =
crc32_tab[(crc32val ^ s[i]) & 0xff] ^
(crc32val >> 8);
}
return crc32val;
}
/*
* Hashing function for a string
*/
unsigned int hashmap_hash_int(hashmap_map * m, char* keystring){
unsigned long key = crc32((unsigned char*)(keystring), strlen(keystring));
/* Robert Jenkins' 32 bit Mix Function */
key += (key << 12);
key ^= (key >> 22);
key += (key << 4);
key ^= (key >> 9);
key += (key << 10);
key ^= (key >> 2);
key += (key << 7);
key ^= (key >> 12);
/* Knuth's Multiplicative Method */
key = (key >> 3) * 2654435761u;
return key % m->table_size;
}
/*
* Return the integer of the location in data
* to store the point to the item, or MAP_FULL.
*/
int hashmap_hash(map_t in, char* key){
int curr;
int i;
/* Cast the hashmap */
hashmap_map* m = (hashmap_map *) in;
/* If full, return immediately */
if(m->size >= (m->table_size/2)) return MAP_FULL;
/* Find the best index */
curr = hashmap_hash_int(m, key);
/* Linear probing */
for(i = 0; i< MAX_CHAIN_LENGTH; i++){
if(m->data[curr].in_use == 0)
return curr;
if(m->data[curr].in_use == 1 && (strcmp(m->data[curr].key,key)==0))
return curr;
curr = (curr + 1) % m->table_size;
}
return MAP_FULL;
}
/*
* Doubles the size of the hashmap, and rehashes all the elements
*/
int hashmap_rehash(map_t in){
int i;
int old_size;
hashmap_element* curr;
/* Setup the new elements */
hashmap_map *m = (hashmap_map *) in;
hashmap_element* temp = (hashmap_element *)
calloc(2 * m->table_size, sizeof(hashmap_element));
if(!temp) return MAP_OMEM;
/* Update the array */
curr = m->data;
m->data = temp;
/* Update the size */
old_size = m->table_size;
m->table_size = 2 * m->table_size;
m->size = 0;
/* Rehash the elements */
for(i = 0; i < old_size; i++){
int status;
if (curr[i].in_use == 0)
continue;
status = hashmap_put(m, curr[i].key, curr[i].data);
if (status != MAP_OK)
return status;
}
free(curr);
return MAP_OK;
}
/*
* Add a pointer to the hashmap with some key
*/
int hashmap_put(map_t in, char* key, any_t value){
int index;
hashmap_map* m;
/* Cast the hashmap */
m = (hashmap_map *) in;
/* Find a place to put our value */
index = hashmap_hash(in, key);
while(index == MAP_FULL){
if (hashmap_rehash(in) == MAP_OMEM) {
return MAP_OMEM;
}
index = hashmap_hash(in, key);
}
/* Set the data */
m->data[index].data = value;
m->data[index].key = key;
m->data[index].in_use = 1;
m->size++;
return MAP_OK;
}
/*
* Get your pointer out of the hashmap with a key
*/
int hashmap_get(map_t in, char* key, any_t *arg){
int curr;
int i;
hashmap_map* m;
/* Cast the hashmap */
m = (hashmap_map *) in;
/* Find data location */
curr = hashmap_hash_int(m, key);
/* Linear probing, if necessary */
for(i = 0; i<MAX_CHAIN_LENGTH; i++){
int in_use = m->data[curr].in_use;
if (in_use == 1){
if (strcmp(m->data[curr].key,key)==0){
*arg = (m->data[curr].data);
return MAP_OK;
}
}
curr = (curr + 1) % m->table_size;
}
*arg = NULL;
/* Not found */
return MAP_MISSING;
}
/*
* Iterate the function parameter over each element in the hashmap. The
* additional any_t argument is passed to the function as its first
* argument and the hashmap element is the second.
*/
int hashmap_iterate(map_t in, PFany f, any_t item) {
int i;
/* Cast the hashmap */
hashmap_map* m = (hashmap_map*) in;
/* On empty hashmap, return immediately */
if (hashmap_length(m) <= 0)
return MAP_MISSING;
/* Linear probing */
for(i = 0; i< m->table_size; i++)
if(m->data[i].in_use != 0) {
any_t data = (any_t) (m->data[i].data);
int status = f(item, data);
if (status != MAP_OK) {
return status;
}
}
return MAP_OK;
}
/*
* Remove an element with that key from the map
*/
int hashmap_remove(map_t in, char* key){
int i;
int curr;
hashmap_map* m;
/* Cast the hashmap */
m = (hashmap_map *) in;
/* Find key */
curr = hashmap_hash_int(m, key);
/* Linear probing, if necessary */
for(i = 0; i<MAX_CHAIN_LENGTH; i++){
int in_use = m->data[curr].in_use;
if (in_use == 1){
if (strcmp(m->data[curr].key,key)==0){
/* Blank out the fields */
m->data[curr].in_use = 0;
m->data[curr].data = NULL;
m->data[curr].key = NULL;
/* Reduce the size */
m->size--;
return MAP_OK;
}
}
curr = (curr + 1) % m->table_size;
}
/* Data not found */
return MAP_MISSING;
}
/* Deallocate the hashmap */
void hashmap_free(map_t in){
hashmap_map* m = (hashmap_map*) in;
free(m->data);
free(m);
}
/* Return the length of the hashmap */
int hashmap_length(map_t in){
hashmap_map* m = (hashmap_map *) in;
if(m != NULL) return m->size;
else return 0;
}
Raw
hashmap.h
/*
* Generic hashmap manipulation functions
*
* Originally by Elliot C Back - http://elliottback.com/wp/hashmap-implementation-in-c/
*
* Modified by Pete Warden to fix a serious performance problem, support strings as keys
* and removed thread synchronization - http://petewarden.typepad.com
*/
#ifndef __HASHMAP_H__
#define __HASHMAP_H__
#define MAP_MISSING -3 /* No such element */
#define MAP_FULL -2 /* Hashmap is full */
#define MAP_OMEM -1 /* Out of Memory */
#define MAP_OK 0 /* OK */
/*
* any_t is a pointer. This allows you to put arbitrary structures in
* the hashmap.
*/
typedef void *any_t;
/*
* PFany is a pointer to a function that can take two any_t arguments
* and return an integer. Returns status code..
*/
typedef int (*PFany)(any_t, any_t);
/*
* map_t is a pointer to an internally maintained data structure.
* Clients of this package do not need to know how hashmaps are
* represented. They see and manipulate only map_t's.
*/
typedef any_t map_t;
/*
* Return an empty hashmap. Returns NULL if empty.
*/
extern map_t hashmap_new();
/*
* Iteratively call f with argument (item, data) for
* each element data in the hashmap. The function must
* return a map status code. If it returns anything other
* than MAP_OK the traversal is terminated. f must
* not reenter any hashmap functions, or deadlock may arise.
*/
extern int hashmap_iterate(map_t in, PFany f, any_t item);
/*
* Add an element to the hashmap. Return MAP_OK or MAP_OMEM.
*/
extern int hashmap_put(map_t in, char* key, any_t value);
/*
* Get an element from the hashmap. Return MAP_OK or MAP_MISSING.
*/
extern int hashmap_get(map_t in, char* key, any_t *arg);
/*
* Remove an element from the hashmap. Return MAP_OK or MAP_MISSING.
*/
extern int hashmap_remove(map_t in, char* key);
/*
* Get any element. Return MAP_OK or MAP_MISSING.
* remove - should the element be removed from the hashmap
*/
extern int hashmap_get_one(map_t in, any_t *arg, int remove);
/*
* Free the hashmap
*/
extern void hashmap_free(map_t in);
/*
* Get the current size of a hashmap
*/
extern int hashmap_length(map_t in);
#endif //__HASHMAP_H__
Raw
Makefile
all:
gcc `sdl-config --cflags --libs` hashmap.c CosmosTests.c -o output
debug:
gcc `sdl-config --cflags --libs` -g hashmap.c CosmosTests.c -o output
clean: output
@rm -rf output
Raw
TODOS
Add cosmos set functionality.
Raw
uthash.h
/*
Copyright (c) 2003-2010, Troy D. Hanson http://uthash.sourceforge.net
All rights reserved.
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright
notice, this list of conditions and the following disclaimer.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS
IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER
OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*/
#ifndef UTHASH_H
#define UTHASH_H
#include <string.h> /* memcmp,strlen */
#include <stddef.h> /* ptrdiff_t */
/* These macros use decltype or the earlier __typeof GNU extension.
As decltype is only available in newer compilers (VS2010 or gcc 4.3+
when compiling c++ source) this code uses whatever method is needed
or, for VS2008 where neither is available, uses casting workarounds. */
#ifdef _MSC_VER /* MS compiler */
#if _MSC_VER >= 1600 && defined(__cplusplus) /* VS2010 or newer in C++ mode */
#define DECLTYPE(x) (decltype(x))
#else /* VS2008 or older (or VS2010 in C mode) */
#define NO_DECLTYPE
#define DECLTYPE(x)
#endif
#else /* GNU, Sun and other compilers */
#define DECLTYPE(x) (__typeof(x))
#endif
#ifdef NO_DECLTYPE
#define DECLTYPE_ASSIGN(dst,src) \
do { \
char **_da_dst = (char**)(&(dst)); \
*_da_dst = (char*)(src); \
} while(0)
#else
#define DECLTYPE_ASSIGN(dst,src) \
do { \
(dst) = DECLTYPE(dst)(src); \
} while(0)
#endif
/* a number of the hash function use uint32_t which isn't defined on win32 */
#ifdef _MSC_VER
typedef unsigned int uint32_t;
#else
#include <inttypes.h> /* uint32_t */
#endif
#define UTHASH_VERSION 1.9.3
#define uthash_fatal(msg) exit(-1) /* fatal error (out of memory,etc) */
#define uthash_malloc(sz) malloc(sz) /* malloc fcn */
#define uthash_free(ptr,sz) free(ptr) /* free fcn */
#define uthash_noexpand_fyi(tbl) /* can be defined to log noexpand */
#define uthash_expand_fyi(tbl) /* can be defined to log expands */
/* initial number of buckets */
#define HASH_INITIAL_NUM_BUCKETS 32 /* initial number of buckets */
#define HASH_INITIAL_NUM_BUCKETS_LOG2 5 /* lg2 of initial number of buckets */
#define HASH_BKT_CAPACITY_THRESH 10 /* expand when bucket count reaches */
/* calculate the element whose hash handle address is hhe */
#define ELMT_FROM_HH(tbl,hhp) ((void*)(((char*)(hhp)) - ((tbl)->hho)))
#define HASH_FIND(hh,head,keyptr,keylen,out) \
do { \
unsigned _hf_bkt,_hf_hashv; \
out=NULL; \
if (head) { \
HASH_FCN(keyptr,keylen, (head)->hh.tbl->num_buckets, _hf_hashv, _hf_bkt); \
if (HASH_BLOOM_TEST((head)->hh.tbl, _hf_hashv)) { \
HASH_FIND_IN_BKT((head)->hh.tbl, hh, (head)->hh.tbl->buckets[ _hf_bkt ], \
keyptr,keylen,out); \
} \
} \
} while (0)
#ifdef HASH_BLOOM
#define HASH_BLOOM_BITLEN (1ULL << HASH_BLOOM)
#define HASH_BLOOM_BYTELEN (HASH_BLOOM_BITLEN/8) + ((HASH_BLOOM_BITLEN%8) ? 1:0)
#define HASH_BLOOM_MAKE(tbl) \
do { \
(tbl)->bloom_nbits = HASH_BLOOM; \
(tbl)->bloom_bv = (uint8_t*)uthash_malloc(HASH_BLOOM_BYTELEN); \
if (!((tbl)->bloom_bv)) { uthash_fatal( "out of memory"); } \
memset((tbl)->bloom_bv, 0, HASH_BLOOM_BYTELEN); \
(tbl)->bloom_sig = HASH_BLOOM_SIGNATURE; \
} while (0);
#define HASH_BLOOM_FREE(tbl) \
do { \
uthash_free((tbl)->bloom_bv, HASH_BLOOM_BYTELEN); \
} while (0);
#define HASH_BLOOM_BITSET(bv,idx) (bv[(idx)/8] |= (1U << ((idx)%8)))
#define HASH_BLOOM_BITTEST(bv,idx) (bv[(idx)/8] & (1U << ((idx)%8)))
#define HASH_BLOOM_ADD(tbl,hashv) \
HASH_BLOOM_BITSET((tbl)->bloom_bv, (hashv & (uint32_t)((1ULL << (tbl)->bloom_nbits) - 1)))
#define HASH_BLOOM_TEST(tbl,hashv) \
HASH_BLOOM_BITTEST((tbl)->bloom_bv, (hashv & (uint32_t)((1ULL << (tbl)->bloom_nbits) - 1)))
#else
#define HASH_BLOOM_MAKE(tbl)
#define HASH_BLOOM_FREE(tbl)
#define HASH_BLOOM_ADD(tbl,hashv)
#define HASH_BLOOM_TEST(tbl,hashv) (1)
#endif
#define HASH_MAKE_TABLE(hh,head) \
do { \
(head)->hh.tbl = (UT_hash_table*)uthash_malloc( \
sizeof(UT_hash_table)); \
if (!((head)->hh.tbl)) { uthash_fatal( "out of memory"); } \
memset((head)->hh.tbl, 0, sizeof(UT_hash_table)); \
(head)->hh.tbl->tail = &((head)->hh); \
(head)->hh.tbl->num_buckets = HASH_INITIAL_NUM_BUCKETS; \
(head)->hh.tbl->log2_num_buckets = HASH_INITIAL_NUM_BUCKETS_LOG2; \
(head)->hh.tbl->hho = (char*)(&(head)->hh) - (char*)(head); \
(head)->hh.tbl->buckets = (UT_hash_bucket*)uthash_malloc( \
HASH_INITIAL_NUM_BUCKETS*sizeof(struct UT_hash_bucket)); \
if (! (head)->hh.tbl->buckets) { uthash_fatal( "out of memory"); } \
memset((head)->hh.tbl->buckets, 0, \
HASH_INITIAL_NUM_BUCKETS*sizeof(struct UT_hash_bucket)); \
HASH_BLOOM_MAKE((head)->hh.tbl); \
(head)->hh.tbl->signature = HASH_SIGNATURE; \
} while(0)
#define HASH_ADD(hh,head,fieldname,keylen_in,add) \
HASH_ADD_KEYPTR(hh,head,&add->fieldname,keylen_in,add)
#define HASH_ADD_KEYPTR(hh,head,keyptr,keylen_in,add) \
do { \
unsigned _ha_bkt; \
(add)->hh.next = NULL; \
(add)->hh.key = (char*)keyptr; \
(add)->hh.keylen = keylen_in; \
if (!(head)) { \
head = (add); \
(head)->hh.prev = NULL; \
HASH_MAKE_TABLE(hh,head); \
} else { \
(head)->hh.tbl->tail->next = (add); \
(add)->hh.prev = ELMT_FROM_HH((head)->hh.tbl, (head)->hh.tbl->tail); \
(head)->hh.tbl->tail = &((add)->hh); \
} \
(head)->hh.tbl->num_items++; \
(add)->hh.tbl = (head)->hh.tbl; \
HASH_FCN(keyptr,keylen_in, (head)->hh.tbl->num_buckets, \
(add)->hh.hashv, _ha_bkt); \
HASH_ADD_TO_BKT((head)->hh.tbl->buckets[_ha_bkt],&(add)->hh); \
HASH_BLOOM_ADD((head)->hh.tbl,(add)->hh.hashv); \
HASH_EMIT_KEY(hh,head,keyptr,keylen_in); \
HASH_FSCK(hh,head); \
} while(0)
#define HASH_TO_BKT( hashv, num_bkts, bkt ) \
do { \
bkt = ((hashv) & ((num_bkts) - 1)); \
} while(0)
/* delete "delptr" from the hash table.
* "the usual" patch-up process for the app-order doubly-linked-list.
* The use of _hd_hh_del below deserves special explanation.
* These used to be expressed using (delptr) but that led to a bug
* if someone used the same symbol for the head and deletee, like
* HASH_DELETE(hh,users,users);
* We want that to work, but by changing the head (users) below
* we were forfeiting our ability to further refer to the deletee (users)
* in the patch-up process. Solution: use scratch space to
* copy the deletee pointer, then the latter references are via that
* scratch pointer rather than through the repointed (users) symbol.
*/
#define HASH_DELETE(hh,head,delptr) \
do { \
unsigned _hd_bkt; \
struct UT_hash_handle *_hd_hh_del; \
if ( ((delptr)->hh.prev == NULL) && ((delptr)->hh.next == NULL) ) { \
uthash_free((head)->hh.tbl->buckets, \
(head)->hh.tbl->num_buckets*sizeof(struct UT_hash_bucket) ); \
HASH_BLOOM_FREE((head)->hh.tbl); \
uthash_free((head)->hh.tbl, sizeof(UT_hash_table)); \
head = NULL; \
} else { \
_hd_hh_del = &((delptr)->hh); \
if ((delptr) == ELMT_FROM_HH((head)->hh.tbl,(head)->hh.tbl->tail)) { \
(head)->hh.tbl->tail = \
(UT_hash_handle*)((char*)((delptr)->hh.prev) + \
(head)->hh.tbl->hho); \
} \
if ((delptr)->hh.prev) { \
((UT_hash_handle*)((char*)((delptr)->hh.prev) + \
(head)->hh.tbl->hho))->next = (delptr)->hh.next; \
} else { \
DECLTYPE_ASSIGN(head,(delptr)->hh.next); \
} \
if (_hd_hh_del->next) { \
((UT_hash_handle*)((char*)_hd_hh_del->next + \
(head)->hh.tbl->hho))->prev = \
_hd_hh_del->prev; \
} \
HASH_TO_BKT( _hd_hh_del->hashv, (head)->hh.tbl->num_buckets, _hd_bkt); \
HASH_DEL_IN_BKT(hh,(head)->hh.tbl->buckets[_hd_bkt], _hd_hh_del); \
(head)->hh.tbl->num_items--; \
} \
HASH_FSCK(hh,head); \
} while (0)
/* convenience forms of HASH_FIND/HASH_ADD/HASH_DEL */
#define HASH_FIND_STR(head,findstr,out) \
HASH_FIND(hh,head,findstr,strlen(findstr),out)
#define HASH_ADD_STR(head,strfield,add) \
HASH_ADD(hh,head,strfield,strlen(add->strfield),add)
#define HASH_FIND_INT(head,findint,out) \
HASH_FIND(hh,head,findint,sizeof(int),out)
#define HASH_ADD_INT(head,intfield,add) \
HASH_ADD(hh,head,intfield,sizeof(int),add)
#define HASH_FIND_PTR(head,findptr,out) \
HASH_FIND(hh,head,findptr,sizeof(void *),out)
#define HASH_ADD_PTR(head,ptrfield,add) \
HASH_ADD(hh,head,ptrfield,sizeof(void *),add)
#define HASH_DEL(head,delptr) \
HASH_DELETE(hh,head,delptr)
/* HASH_FSCK checks hash integrity on every add/delete when HASH_DEBUG is defined.
* This is for uthash developer only; it compiles away if HASH_DEBUG isn't defined.
*/
#ifdef HASH_DEBUG
#define HASH_OOPS(...) do { fprintf(stderr,__VA_ARGS__); exit(-1); } while (0)
#define HASH_FSCK(hh,head) \
do { \
unsigned _bkt_i; \
unsigned _count, _bkt_count; \
char *_prev; \
struct UT_hash_handle *_thh; \
if (head) { \
_count = 0; \
for( _bkt_i = 0; _bkt_i < (head)->hh.tbl->num_buckets; _bkt_i++) { \
_bkt_count = 0; \
_thh = (head)->hh.tbl->buckets[_bkt_i].hh_head; \
_prev = NULL; \
while (_thh) { \
if (_prev != (char*)(_thh->hh_prev)) { \
HASH_OOPS("invalid hh_prev %p, actual %p\n", \
_thh->hh_prev, _prev ); \
} \
_bkt_count++; \
_prev = (char*)(_thh); \
_thh = _thh->hh_next; \
} \
_count += _bkt_count; \
if ((head)->hh.tbl->buckets[_bkt_i].count != _bkt_count) { \
HASH_OOPS("invalid bucket count %d, actual %d\n", \
(head)->hh.tbl->buckets[_bkt_i].count, _bkt_count); \
} \
} \
if (_count != (head)->hh.tbl->num_items) { \
HASH_OOPS("invalid hh item count %d, actual %d\n", \
(head)->hh.tbl->num_items, _count ); \
} \
/* traverse hh in app order; check next/prev integrity, count */ \
_count = 0; \
_prev = NULL; \
_thh = &(head)->hh; \
while (_thh) { \
_count++; \
if (_prev !=(char*)(_thh->prev)) { \
HASH_OOPS("invalid prev %p, actual %p\n", \
_thh->prev, _prev ); \
} \
_prev = (char*)ELMT_FROM_HH((head)->hh.tbl, _thh); \
_thh = ( _thh->next ? (UT_hash_handle*)((char*)(_thh->next) + \
(head)->hh.tbl->hho) : NULL ); \
} \
if (_count != (head)->hh.tbl->num_items) { \
HASH_OOPS("invalid app item count %d, actual %d\n", \
(head)->hh.tbl->num_items, _count ); \
} \
} \
} while (0)
#else
#define HASH_FSCK(hh,head)
#endif
/* When compiled with -DHASH_EMIT_KEYS, length-prefixed keys are emitted to
* the descriptor to which this macro is defined for tuning the hash function.
* The app can #include <unistd.h> to get the prototype for write(2). */
#ifdef HASH_EMIT_KEYS
#define HASH_EMIT_KEY(hh,head,keyptr,fieldlen) \
do { \
unsigned _klen = fieldlen; \
write(HASH_EMIT_KEYS, &_klen, sizeof(_klen)); \
write(HASH_EMIT_KEYS, keyptr, fieldlen); \
} while (0)
#else
#define HASH_EMIT_KEY(hh,head,keyptr,fieldlen)
#endif
/* default to Jenkin's hash unless overridden e.g. DHASH_FUNCTION=HASH_SAX */
#ifdef HASH_FUNCTION
#define HASH_FCN HASH_FUNCTION
#else
#define HASH_FCN HASH_JEN
#endif
/* The Bernstein hash function, used in Perl prior to v5.6 */
#define HASH_BER(key,keylen,num_bkts,hashv,bkt) \
do { \
unsigned _hb_keylen=keylen; \
char *_hb_key=(char*)(key); \
(hashv) = 0; \
while (_hb_keylen--) { (hashv) = ((hashv) * 33) + *_hb_key++; } \
bkt = (hashv) & (num_bkts-1); \
} while (0)
/* SAX/FNV/OAT/JEN hash functions are macro variants of those listed at
* http://eternallyconfuzzled.com/tuts/algorithms/jsw_tut_hashing.aspx */
#define HASH_SAX(key,keylen,num_bkts,hashv,bkt) \
do { \
unsigned _sx_i; \
char *_hs_key=(char*)(key); \
hashv = 0; \
for(_sx_i=0; _sx_i < keylen; _sx_i++) \
hashv ^= (hashv << 5) + (hashv >> 2) + _hs_key[_sx_i]; \
bkt = hashv & (num_bkts-1); \
} while (0)
#define HASH_FNV(key,keylen,num_bkts,hashv,bkt) \
do { \
unsigned _fn_i; \
char *_hf_key=(char*)(key); \
hashv = 2166136261UL; \
for(_fn_i=0; _fn_i < keylen; _fn_i++) \
hashv = (hashv * 16777619) ^ _hf_key[_fn_i]; \
bkt = hashv & (num_bkts-1); \
} while(0);
#define HASH_OAT(key,keylen,num_bkts,hashv,bkt) \
do { \
unsigned _ho_i; \
char *_ho_key=(char*)(key); \
hashv = 0; \
for(_ho_i=0; _ho_i < keylen; _ho_i++) { \
hashv += _ho_key[_ho_i]; \
hashv += (hashv << 10); \
hashv ^= (hashv >> 6); \
} \
hashv += (hashv << 3); \
hashv ^= (hashv >> 11); \
hashv += (hashv << 15); \
bkt = hashv & (num_bkts-1); \
} while(0)
#define HASH_JEN_MIX(a,b,c) \
do { \
a -= b; a -= c; a ^= ( c >> 13 ); \
b -= c; b -= a; b ^= ( a << 8 ); \
c -= a; c -= b; c ^= ( b >> 13 ); \
a -= b; a -= c; a ^= ( c >> 12 ); \
b -= c; b -= a; b ^= ( a << 16 ); \
c -= a; c -= b; c ^= ( b >> 5 ); \
a -= b; a -= c; a ^= ( c >> 3 ); \
b -= c; b -= a; b ^= ( a << 10 ); \
c -= a; c -= b; c ^= ( b >> 15 ); \
} while (0)
#define HASH_JEN(key,keylen,num_bkts,hashv,bkt) \
do { \
unsigned _hj_i,_hj_j,_hj_k; \
char *_hj_key=(char*)(key); \
hashv = 0xfeedbeef; \
_hj_i = _hj_j = 0x9e3779b9; \
_hj_k = keylen; \
while (_hj_k >= 12) { \
_hj_i += (_hj_key[0] + ( (unsigned)_hj_key[1] << 8 ) \
+ ( (unsigned)_hj_key[2] << 16 ) \
+ ( (unsigned)_hj_key[3] << 24 ) ); \
_hj_j += (_hj_key[4] + ( (unsigned)_hj_key[5] << 8 ) \
+ ( (unsigned)_hj_key[6] << 16 ) \
+ ( (unsigned)_hj_key[7] << 24 ) ); \
hashv += (_hj_key[8] + ( (unsigned)_hj_key[9] << 8 ) \
+ ( (unsigned)_hj_key[10] << 16 ) \
+ ( (unsigned)_hj_key[11] << 24 ) ); \
\
HASH_JEN_MIX(_hj_i, _hj_j, hashv); \
\
_hj_key += 12; \
_hj_k -= 12; \
} \
hashv += keylen; \
switch ( _hj_k ) { \
case 11: hashv += ( (unsigned)_hj_key[10] << 24 ); \
case 10: hashv += ( (unsigned)_hj_key[9] << 16 ); \
case 9: hashv += ( (unsigned)_hj_key[8] << 8 ); \
case 8: _hj_j += ( (unsigned)_hj_key[7] << 24 ); \
case 7: _hj_j += ( (unsigned)_hj_key[6] << 16 ); \
case 6: _hj_j += ( (unsigned)_hj_key[5] << 8 ); \
case 5: _hj_j += _hj_key[4]; \
case 4: _hj_i += ( (unsigned)_hj_key[3] << 24 ); \
case 3: _hj_i += ( (unsigned)_hj_key[2] << 16 ); \
case 2: _hj_i += ( (unsigned)_hj_key[1] << 8 ); \
case 1: _hj_i += _hj_key[0]; \
} \
HASH_JEN_MIX(_hj_i, _hj_j, hashv); \
bkt = hashv & (num_bkts-1); \
} while(0)
/* The Paul Hsieh hash function */
#undef get16bits
#if (defined(__GNUC__) && defined(__i386__)) || defined(__WATCOMC__) \
|| defined(_MSC_VER) || defined (__BORLANDC__) || defined (__TURBOC__)
#define get16bits(d) (*((const uint16_t *) (d)))
#endif
#if !defined (get16bits)
#define get16bits(d) ((((uint32_t)(((const uint8_t *)(d))[1])) << 8) \
+(uint32_t)(((const uint8_t *)(d))[0]) )
#endif
#define HASH_SFH(key,keylen,num_bkts,hashv,bkt) \
do { \
char *_sfh_key=(char*)(key); \
uint32_t _sfh_tmp, _sfh_len = keylen; \
\
int _sfh_rem = _sfh_len & 3; \
_sfh_len >>= 2; \
hashv = 0xcafebabe; \
\
/* Main loop */ \
for (;_sfh_len > 0; _sfh_len--) { \
hashv += get16bits (_sfh_key); \
_sfh_tmp = (get16bits (_sfh_key+2) << 11) ^ hashv; \
hashv = (hashv << 16) ^ _sfh_tmp; \
_sfh_key += 2*sizeof (uint16_t); \
hashv += hashv >> 11; \
} \
\
/* Handle end cases */ \
switch (_sfh_rem) { \
case 3: hashv += get16bits (_sfh_key); \
hashv ^= hashv << 16; \
hashv ^= _sfh_key[sizeof (uint16_t)] << 18; \
hashv += hashv >> 11; \
break; \
case 2: hashv += get16bits (_sfh_key); \
hashv ^= hashv << 11; \
hashv += hashv >> 17; \
break; \
case 1: hashv += *_sfh_key; \
hashv ^= hashv << 10; \
hashv += hashv >> 1; \
} \
\
/* Force "avalanching" of final 127 bits */ \
hashv ^= hashv << 3; \
hashv += hashv >> 5; \
hashv ^= hashv << 4; \
hashv += hashv >> 17; \
hashv ^= hashv << 25; \
hashv += hashv >> 6; \
bkt = hashv & (num_bkts-1); \
} while(0);
#ifdef HASH_USING_NO_STRICT_ALIASING
/* The MurmurHash exploits some CPU's (e.g. x86) tolerance for unaligned reads.
* For other types of CPU's (e.g. Sparc) an unaligned read causes a bus error.
* So MurmurHash comes in two versions, the faster unaligned one and the slower
* aligned one. We only use the faster one on CPU's where we know it's safe.
*
* Note the preprocessor built-in defines can be emitted using:
*
* gcc -m64 -dM -E - < /dev/null (on gcc)
* cc -## a.c (where a.c is a simple test file) (Sun Studio)
*/
#if (defined(__i386__) || defined(__x86_64__))
#define HASH_MUR HASH_MUR_UNALIGNED
#else
#define HASH_MUR HASH_MUR_ALIGNED
#endif
/* Appleby's MurmurHash fast version for unaligned-tolerant archs like i386 */
#define HASH_MUR_UNALIGNED(key,keylen,num_bkts,hashv,bkt) \
do { \
const unsigned int _mur_m = 0x5bd1e995; \
const int _mur_r = 24; \
hashv = 0xcafebabe ^ keylen; \
char *_mur_key = (char *)(key); \
uint32_t _mur_tmp, _mur_len = keylen; \
\
for (;_mur_len >= 4; _mur_len-=4) { \
_mur_tmp = *(uint32_t *)_mur_key; \
_mur_tmp *= _mur_m; \
_mur_tmp ^= _mur_tmp >> _mur_r; \
_mur_tmp *= _mur_m; \
hashv *= _mur_m; \
hashv ^= _mur_tmp; \
_mur_key += 4; \
} \
\
switch(_mur_len) \
{ \
case 3: hashv ^= _mur_key[2] << 16; \
case 2: hashv ^= _mur_key[1] << 8; \
case 1: hashv ^= _mur_key[0]; \
hashv *= _mur_m; \
}; \
\
hashv ^= hashv >> 13; \
hashv *= _mur_m; \
hashv ^= hashv >> 15; \
\
bkt = hashv & (num_bkts-1); \
} while(0)
/* Appleby's MurmurHash version for alignment-sensitive archs like Sparc */
#define HASH_MUR_ALIGNED(key,keylen,num_bkts,hashv,bkt) \
do { \
const unsigned int _mur_m = 0x5bd1e995; \
const int _mur_r = 24; \
hashv = 0xcafebabe ^ (keylen); \
char *_mur_key = (char *)(key); \
uint32_t _mur_len = keylen; \
int _mur_align = (int)_mur_key & 3; \
\
if (_mur_align && (_mur_len >= 4)) { \
unsigned _mur_t = 0, _mur_d = 0; \
switch(_mur_align) { \
case 1: _mur_t |= _mur_key[2] << 16; \
case 2: _mur_t |= _mur_key[1] << 8; \
case 3: _mur_t |= _mur_key[0]; \
} \
_mur_t <<= (8 * _mur_align); \
_mur_key += 4-_mur_align; \
_mur_len -= 4-_mur_align; \
int _mur_sl = 8 * (4-_mur_align); \
int _mur_sr = 8 * _mur_align; \
\
for (;_mur_len >= 4; _mur_len-=4) { \
_mur_d = *(unsigned *)_mur_key; \
_mur_t = (_mur_t >> _mur_sr) | (_mur_d << _mur_sl); \
unsigned _mur_k = _mur_t; \
_mur_k *= _mur_m; \
_mur_k ^= _mur_k >> _mur_r; \
_mur_k *= _mur_m; \
hashv *= _mur_m; \
hashv ^= _mur_k; \
_mur_t = _mur_d; \
_mur_key += 4; \
} \
_mur_d = 0; \
if(_mur_len >= _mur_align) { \
switch(_mur_align) { \
case 3: _mur_d |= _mur_key[2] << 16; \
case 2: _mur_d |= _mur_key[1] << 8; \
case 1: _mur_d |= _mur_key[0]; \
} \
unsigned _mur_k = (_mur_t >> _mur_sr) | (_mur_d << _mur_sl); \
_mur_k *= _mur_m; \
_mur_k ^= _mur_k >> _mur_r; \
_mur_k *= _mur_m; \
hashv *= _mur_m; \
hashv ^= _mur_k; \
_mur_k += _mur_align; \
_mur_len -= _mur_align; \
\
switch(_mur_len) \
{ \
case 3: hashv ^= _mur_key[2] << 16; \
case 2: hashv ^= _mur_key[1] << 8; \
case 1: hashv ^= _mur_key[0]; \
hashv *= _mur_m; \
} \
} else { \
switch(_mur_len) \
{ \
case 3: _mur_d ^= _mur_key[2] << 16; \
case 2: _mur_d ^= _mur_key[1] << 8; \
case 1: _mur_d ^= _mur_key[0]; \
case 0: hashv ^= (_mur_t >> _mur_sr) | (_mur_d << _mur_sl); \
hashv *= _mur_m; \
} \
} \
\
hashv ^= hashv >> 13; \
hashv *= _mur_m; \
hashv ^= hashv >> 15; \
} else { \
for (;_mur_len >= 4; _mur_len-=4) { \
unsigned _mur_k = *(unsigned*)_mur_key; \
_mur_k *= _mur_m; \
_mur_k ^= _mur_k >> _mur_r; \
_mur_k *= _mur_m; \
hashv *= _mur_m; \
hashv ^= _mur_k; \
_mur_key += 4; \
} \
switch(_mur_len) \
{ \
case 3: hashv ^= _mur_key[2] << 16; \
case 2: hashv ^= _mur_key[1] << 8; \
case 1: hashv ^= _mur_key[0]; \
hashv *= _mur_m; \
} \
\
hashv ^= hashv >> 13; \
hashv *= _mur_m; \
hashv ^= hashv >> 15; \
} \
bkt = hashv & (num_bkts-1); \
} while(0)
#endif /* HASH_USING_NO_STRICT_ALIASING */
/* key comparison function; return 0 if keys equal */
#define HASH_KEYCMP(a,b,len) memcmp(a,b,len)
/* iterate over items in a known bucket to find desired item */
#define HASH_FIND_IN_BKT(tbl,hh,head,keyptr,keylen_in,out) \
do { \
if (head.hh_head) DECLTYPE_ASSIGN(out,ELMT_FROM_HH(tbl,head.hh_head)); \
else out=NULL; \
while (out) { \
if (out->hh.keylen == keylen_in) { \
if ((HASH_KEYCMP(out->hh.key,keyptr,keylen_in)) == 0) break; \
} \
if (out->hh.hh_next) DECLTYPE_ASSIGN(out,ELMT_FROM_HH(tbl,out->hh.hh_next)); \
else out = NULL; \
} \
} while(0)
/* add an item to a bucket */
#define HASH_ADD_TO_BKT(head,addhh) \
do { \
head.count++; \
(addhh)->hh_next = head.hh_head; \
(addhh)->hh_prev = NULL; \
if (head.hh_head) { (head).hh_head->hh_prev = (addhh); } \
(head).hh_head=addhh; \
if (head.count >= ((head.expand_mult+1) * HASH_BKT_CAPACITY_THRESH) \
&& (addhh)->tbl->noexpand != 1) { \
HASH_EXPAND_BUCKETS((addhh)->tbl); \
} \
} while(0)
/* remove an item from a given bucket */
#define HASH_DEL_IN_BKT(hh,head,hh_del) \
(head).count--; \
if ((head).hh_head == hh_del) { \
(head).hh_head = hh_del->hh_next; \
} \
if (hh_del->hh_prev) { \
hh_del->hh_prev->hh_next = hh_del->hh_next; \
} \
if (hh_del->hh_next) { \
hh_del->hh_next->hh_prev = hh_del->hh_prev; \
}
/* Bucket expansion has the effect of doubling the number of buckets
* and redistributing the items into the new buckets. Ideally the
* items will distribute more or less evenly into the new buckets
* (the extent to which this is true is a measure of the quality of
* the hash function as it applies to the key domain).
*
* With the items distributed into more buckets, the chain length
* (item count) in each bucket is reduced. Thus by expanding buckets
* the hash keeps a bound on the chain length. This bounded chain
* length is the essence of how a hash provides constant time lookup.
*
* The calculation of tbl->ideal_chain_maxlen below deserves some
* explanation. First, keep in mind that we're calculating the ideal
* maximum chain length based on the *new* (doubled) bucket count.
* In fractions this is just n/b (n=number of items,b=new num buckets).
* Since the ideal chain length is an integer, we want to calculate
* ceil(n/b). We don't depend on floating point arithmetic in this
* hash, so to calculate ceil(n/b) with integers we could write
*
* ceil(n/b) = (n/b) + ((n%b)?1:0)
*
* and in fact a previous version of this hash did just that.
* But now we have improved things a bit by recognizing that b is
* always a power of two. We keep its base 2 log handy (call it lb),
* so now we can write this with a bit shift and logical AND:
*
* ceil(n/b) = (n>>lb) + ( (n & (b-1)) ? 1:0)
*
*/
#define HASH_EXPAND_BUCKETS(tbl) \
do { \
unsigned _he_bkt; \
unsigned _he_bkt_i; \
struct UT_hash_handle *_he_thh, *_he_hh_nxt; \
UT_hash_bucket *_he_new_buckets, *_he_newbkt; \
_he_new_buckets = (UT_hash_bucket*)uthash_malloc( \
2 * tbl->num_buckets * sizeof(struct UT_hash_bucket)); \
if (!_he_new_buckets) { uthash_fatal( "out of memory"); } \
memset(_he_new_buckets, 0, \
2 * tbl->num_buckets * sizeof(struct UT_hash_bucket)); \
tbl->ideal_chain_maxlen = \
(tbl->num_items >> (tbl->log2_num_buckets+1)) + \
((tbl->num_items & ((tbl->num_buckets*2)-1)) ? 1 : 0); \
tbl->nonideal_items = 0; \
for(_he_bkt_i = 0; _he_bkt_i < tbl->num_buckets; _he_bkt_i++) \
{ \
_he_thh = tbl->buckets[ _he_bkt_i ].hh_head; \
while (_he_thh) { \
_he_hh_nxt = _he_thh->hh_next; \
HASH_TO_BKT( _he_thh->hashv, tbl->num_buckets*2, _he_bkt); \
_he_newbkt = &(_he_new_buckets[ _he_bkt ]); \
if (++(_he_newbkt->count) > tbl->ideal_chain_maxlen) { \
tbl->nonideal_items++; \
_he_newbkt->expand_mult = _he_newbkt->count / \
tbl->ideal_chain_maxlen; \
} \
_he_thh->hh_prev = NULL; \
_he_thh->hh_next = _he_newbkt->hh_head; \
if (_he_newbkt->hh_head) _he_newbkt->hh_head->hh_prev = \
_he_thh; \
_he_newbkt->hh_head = _he_thh; \
_he_thh = _he_hh_nxt; \
} \
} \
uthash_free( tbl->buckets, tbl->num_buckets*sizeof(struct UT_hash_bucket) ); \
tbl->num_buckets *= 2; \
tbl->log2_num_buckets++; \
tbl->buckets = _he_new_buckets; \
tbl->ineff_expands = (tbl->nonideal_items > (tbl->num_items >> 1)) ? \
(tbl->ineff_expands+1) : 0; \
if (tbl->ineff_expands > 1) { \
tbl->noexpand=1; \
uthash_noexpand_fyi(tbl); \
} \
uthash_expand_fyi(tbl); \
} while(0)
/* This is an adaptation of Simon Tatham's O(n log(n)) mergesort */
/* Note that HASH_SORT assumes the hash handle name to be hh.
* HASH_SRT was added to allow the hash handle name to be passed in. */
#define HASH_SORT(head,cmpfcn) HASH_SRT(hh,head,cmpfcn)
#define HASH_SRT(hh,head,cmpfcn) \
do { \
unsigned _hs_i; \
unsigned _hs_looping,_hs_nmerges,_hs_insize,_hs_psize,_hs_qsize; \
struct UT_hash_handle *_hs_p, *_hs_q, *_hs_e, *_hs_list, *_hs_tail; \
if (head) { \
_hs_insize = 1; \
_hs_looping = 1; \
_hs_list = &((head)->hh); \
while (_hs_looping) { \
_hs_p = _hs_list; \
_hs_list = NULL; \
_hs_tail = NULL; \
_hs_nmerges = 0; \
while (_hs_p) { \
_hs_nmerges++; \
_hs_q = _hs_p; \
_hs_psize = 0; \
for ( _hs_i = 0; _hs_i < _hs_insize; _hs_i++ ) { \
_hs_psize++; \
_hs_q = (UT_hash_handle*)((_hs_q->next) ? \
((void*)((char*)(_hs_q->next) + \
(head)->hh.tbl->hho)) : NULL); \
if (! (_hs_q) ) break; \
} \
_hs_qsize = _hs_insize; \
while ((_hs_psize > 0) || ((_hs_qsize > 0) && _hs_q )) { \
if (_hs_psize == 0) { \
_hs_e = _hs_q; \
_hs_q = (UT_hash_handle*)((_hs_q->next) ? \
((void*)((char*)(_hs_q->next) + \
(head)->hh.tbl->hho)) : NULL); \
_hs_qsize--; \
} else if ( (_hs_qsize == 0) || !(_hs_q) ) { \
_hs_e = _hs_p; \
_hs_p = (UT_hash_handle*)((_hs_p->next) ? \
((void*)((char*)(_hs_p->next) + \
(head)->hh.tbl->hho)) : NULL); \
_hs_psize--; \
} else if (( \
cmpfcn(DECLTYPE(head)(ELMT_FROM_HH((head)->hh.tbl,_hs_p)), \
DECLTYPE(head)(ELMT_FROM_HH((head)->hh.tbl,_hs_q))) \
) <= 0) { \
_hs_e = _hs_p; \
_hs_p = (UT_hash_handle*)((_hs_p->next) ? \
((void*)((char*)(_hs_p->next) + \
(head)->hh.tbl->hho)) : NULL); \
_hs_psize--; \
} else { \
_hs_e = _hs_q; \
_hs_q = (UT_hash_handle*)((_hs_q->next) ? \
((void*)((char*)(_hs_q->next) + \
(head)->hh.tbl->hho)) : NULL); \
_hs_qsize--; \
} \
if ( _hs_tail ) { \
_hs_tail->next = ((_hs_e) ? \
ELMT_FROM_HH((head)->hh.tbl,_hs_e) : NULL); \
} else { \
_hs_list = _hs_e; \
} \
_hs_e->prev = ((_hs_tail) ? \
ELMT_FROM_HH((head)->hh.tbl,_hs_tail) : NULL); \
_hs_tail = _hs_e; \
} \
_hs_p = _hs_q; \
} \
_hs_tail->next = NULL; \
if ( _hs_nmerges <= 1 ) { \
_hs_looping=0; \
(head)->hh.tbl->tail = _hs_tail; \
DECLTYPE_ASSIGN(head,ELMT_FROM_HH((head)->hh.tbl, _hs_list)); \
} \
_hs_insize *= 2; \
} \
HASH_FSCK(hh,head); \
} \
} while (0)
/* This function selects items from one hash into another hash.
* The end result is that the selected items have dual presence
* in both hashes. There is no copy of the items made; rather
* they are added into the new hash through a secondary hash
* hash handle that must be present in the structure. */
#define HASH_SELECT(hh_dst, dst, hh_src, src, cond) \
do { \
unsigned _src_bkt, _dst_bkt; \
void *_last_elt=NULL, *_elt; \
UT_hash_handle *_src_hh, *_dst_hh, *_last_elt_hh=NULL; \
ptrdiff_t _dst_hho = ((char*)(&(dst)->hh_dst) - (char*)(dst)); \
if (src) { \
for(_src_bkt=0; _src_bkt < (src)->hh_src.tbl->num_buckets; _src_bkt++) { \
for(_src_hh = (src)->hh_src.tbl->buckets[_src_bkt].hh_head; \
_src_hh; \
_src_hh = _src_hh->hh_next) { \
_elt = ELMT_FROM_HH((src)->hh_src.tbl, _src_hh); \
if (cond(_elt)) { \
_dst_hh = (UT_hash_handle*)(((char*)_elt) + _dst_hho); \
_dst_hh->key = _src_hh->key; \
_dst_hh->keylen = _src_hh->keylen; \
_dst_hh->hashv = _src_hh->hashv; \
_dst_hh->prev = _last_elt; \
_dst_hh->next = NULL; \
if (_last_elt_hh) { _last_elt_hh->next = _elt; } \
if (!dst) { \
DECLTYPE_ASSIGN(dst,_elt); \
HASH_MAKE_TABLE(hh_dst,dst); \
} else { \
_dst_hh->tbl = (dst)->hh_dst.tbl; \
} \
HASH_TO_BKT(_dst_hh->hashv, _dst_hh->tbl->num_buckets, _dst_bkt); \
HASH_ADD_TO_BKT(_dst_hh->tbl->buckets[_dst_bkt],_dst_hh); \
(dst)->hh_dst.tbl->num_items++; \
_last_elt = _elt; \
_last_elt_hh = _dst_hh; \
} \
} \
} \
} \
HASH_FSCK(hh_dst,dst); \
} while (0)
#define HASH_CLEAR(hh,head) \
do { \
if (head) { \
uthash_free((head)->hh.tbl->buckets, \
(head)->hh.tbl->num_buckets*sizeof(struct UT_hash_bucket)); \
uthash_free((head)->hh.tbl, sizeof(UT_hash_table)); \
(head)=NULL; \
} \
} while(0)
#ifdef NO_DECLTYPE
#define HASH_ITER(hh,head,el,tmp) \
for((el)=(head), (*(char**)(&(tmp)))=(char*)((head)?(head)->hh.next:NULL); \
el; (el)=(tmp),(*(char**)(&(tmp)))=(char*)((tmp)?(tmp)->hh.next:NULL))
#else
#define HASH_ITER(hh,head,el,tmp) \
for((el)=(head),(tmp)=DECLTYPE(el)((head)?(head)->hh.next:NULL); \
el; (el)=(tmp),(tmp)=DECLTYPE(el)((tmp)?(tmp)->hh.next:NULL))
#endif
/* obtain a count of items in the hash */
#define HASH_COUNT(head) HASH_CNT(hh,head)
#define HASH_CNT(hh,head) ((head)?((head)->hh.tbl->num_items):0)
typedef struct UT_hash_bucket {
struct UT_hash_handle *hh_head;
unsigned count;
/* expand_mult is normally set to 0. In this situation, the max chain length
* threshold is enforced at its default value, HASH_BKT_CAPACITY_THRESH. (If
* the bucket's chain exceeds this length, bucket expansion is triggered).
* However, setting expand_mult to a non-zero value delays bucket expansion
* (that would be triggered by additions to this particular bucket)
* until its chain length reaches a *multiple* of HASH_BKT_CAPACITY_THRESH.
* (The multiplier is simply expand_mult+1). The whole idea of this
* multiplier is to reduce bucket expansions, since they are expensive, in
* situations where we know that a particular bucket tends to be overused.
* It is better to let its chain length grow to a longer yet-still-bounded
* value, than to do an O(n) bucket expansion too often.
*/
unsigned expand_mult;
} UT_hash_bucket;
/* random signature used only to find hash tables in external analysis */
#define HASH_SIGNATURE 0xa0111fe1
#define HASH_BLOOM_SIGNATURE 0xb12220f2
typedef struct UT_hash_table {
UT_hash_bucket *buckets;
unsigned num_buckets, log2_num_buckets;
unsigned num_items;
struct UT_hash_handle *tail; /* tail hh in app order, for fast append */
ptrdiff_t hho; /* hash handle offset (byte pos of hash handle in element */
/* in an ideal situation (all buckets used equally), no bucket would have
* more than ceil(#items/#buckets) items. that's the ideal chain length. */
unsigned ideal_chain_maxlen;
/* nonideal_items is the number of items in the hash whose chain position
* exceeds the ideal chain maxlen. these items pay the penalty for an uneven
* hash distribution; reaching them in a chain traversal takes >ideal steps */
unsigned nonideal_items;
/* ineffective expands occur when a bucket doubling was performed, but
* afterward, more than half the items in the hash had nonideal chain
* positions. If this happens on two consecutive expansions we inhibit any
* further expansion, as it's not helping; this happens when the hash
* function isn't a good fit for the key domain. When expansion is inhibited
* the hash will still work, albeit no longer in constant time. */
unsigned ineff_expands, noexpand;
uint32_t signature; /* used only to find hash tables in external analysis */
#ifdef HASH_BLOOM
uint32_t bloom_sig; /* used only to test bloom exists in external analysis */
uint8_t *bloom_bv;
char bloom_nbits;
#endif
} UT_hash_table;
typedef struct UT_hash_handle {
struct UT_hash_table *tbl;
void *prev; /* prev element in app order */
void *next; /* next element in app order */
struct UT_hash_handle *hh_prev; /* previous hh in bucket order */
struct UT_hash_handle *hh_next; /* next hh in bucket order */
void *key; /* ptr to enclosing struct's key */
unsigned keylen; /* enclosing struct's key len */
unsigned hashv; /* result of hash-fcn(key) */
} UT_hash_handle;
#endif /* UTHASH_H */
Raw
UTSelfTests.c
#include <string.h> /* strcpy */
#include <stdlib.h> /* malloc */
#include <stdio.h> /* printf */
#include "uthash.h"
struct my_struct {
char name[10]; /* key (string is WITHIN the structure) */
int id;
UT_hash_handle hh; /* makes this structure hashable */
};
int main(int argc, char *argv[]) {
char **n, *names[] = { "joe", "bob", "betty", NULL };
struct my_struct *s, *users = NULL;
int i=0;
for (n = names; *n != NULL; n++) {
s = malloc(sizeof(struct my_struct));
strcpy(s->name, *n);
s->id = i++;
HASH_ADD_STR( users, name, s );
}
HASH_FIND_STR( users, "betty", s);
if (s) printf("betty's id is %d\n", s->id);
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment