From 892994331a7ec02754e1ca168ab9abf476b86509 Mon Sep 17 00:00:00 2001 From: Sam Stevens Date: Sat, 9 Feb 2019 12:14:18 +0000 Subject: [PATCH] Added random generator and hashing library. --- .idea/codeStyles/Project.xml | 29 ---- .idea/encodings.xml | 4 + lib/MurmurHash3.c | 325 +++++++++++++++++++++++++++++++++++ lib/MurmurHash3.h | 37 ++++ src/CMakeLists.txt | 8 +- src/main.c | 12 +- src/parser.c | 2 +- src/random.c | 36 ++++ src/random.h | 15 ++ 9 files changed, 433 insertions(+), 35 deletions(-) delete mode 100644 .idea/codeStyles/Project.xml create mode 100644 .idea/encodings.xml create mode 100644 lib/MurmurHash3.c create mode 100644 lib/MurmurHash3.h create mode 100644 src/random.c create mode 100644 src/random.h diff --git a/.idea/codeStyles/Project.xml b/.idea/codeStyles/Project.xml deleted file mode 100644 index 30aa626..0000000 --- a/.idea/codeStyles/Project.xml +++ /dev/null @@ -1,29 +0,0 @@ - - - - - - - - - - - - - - \ No newline at end of file diff --git a/.idea/encodings.xml b/.idea/encodings.xml new file mode 100644 index 0000000..15a15b2 --- /dev/null +++ b/.idea/encodings.xml @@ -0,0 +1,4 @@ + + + + \ No newline at end of file diff --git a/lib/MurmurHash3.c b/lib/MurmurHash3.c new file mode 100644 index 0000000..9cbf2eb --- /dev/null +++ b/lib/MurmurHash3.c @@ -0,0 +1,325 @@ +//----------------------------------------------------------------------------- +// MurmurHash3 was written by Austin Appleby, and is placed in the public +// domain. The author hereby disclaims copyright to this source code. + +// Note - The x86 and x64 versions do _not_ produce the same results, as the +// algorithms are optimized for their respective platforms. You can still +// compile and run any of them on any platform, but your performance with the +// non-native version will be less than optimal. + +#include "MurmurHash3.h" + +//----------------------------------------------------------------------------- +// Platform-specific functions and macros + +// Microsoft Visual Studio + +#if defined(_MSC_VER) + +#define FORCE_INLINE __forceinline + +#include + +#define ROTL32(x,y) _rotl(x,y) +#define ROTL64(x,y) _rotl64(x,y) + +#define BIG_CONSTANT(x) (x) + +// Other compilers + +#else // defined(_MSC_VER) + +#define FORCE_INLINE inline __attribute__((always_inline)) + +#define ROTL32(x,r) (((x) << (r)) | ((x) >> (32 - (r)))) +#define ROTL64(x,r) (((x) << (r)) | ((x) >> (64 - (r)))) + +#define BIG_CONSTANT(x) (x##LLU) + +#endif // !defined(_MSC_VER) + +//----------------------------------------------------------------------------- +// Block read - if your platform needs to do endian-swapping or can only +// handle aligned reads, do the conversion here + +FORCE_INLINE uint32_t getblock32 ( const uint32_t * p, int i ) +{ + return p[i]; +} + +FORCE_INLINE uint64_t getblock64 ( const uint64_t * p, int i ) +{ + return p[i]; +} + +//----------------------------------------------------------------------------- +// Finalization mix - force all bits of a hash block to avalanche + +FORCE_INLINE uint32_t fmix32 ( uint32_t h ) +{ + h ^= h >> 16; + h *= 0x85ebca6b; + h ^= h >> 13; + h *= 0xc2b2ae35; + h ^= h >> 16; + + return h; +} + +//---------- + +FORCE_INLINE uint64_t fmix64 ( uint64_t k ) +{ + k ^= k >> 33; + k *= BIG_CONSTANT(0xff51afd7ed558ccd); + k ^= k >> 33; + k *= BIG_CONSTANT(0xc4ceb9fe1a85ec53); + k ^= k >> 33; + + return k; +} + +//----------------------------------------------------------------------------- + +void MurmurHash3_x86_32 ( const void * key, int len, + uint32_t seed, void * out ) +{ + const uint8_t * data = (const uint8_t*)key; + const int nblocks = len / 4; + + uint32_t h1 = seed; + + const uint32_t c1 = 0xcc9e2d51; + const uint32_t c2 = 0x1b873593; + + //---------- + // body + + const uint32_t * blocks = (const uint32_t *)(data + nblocks*4); + + for(int i = -nblocks; i; i++) + { + uint32_t k1 = getblock32(blocks,i); + + k1 *= c1; + k1 = ROTL32(k1,15); + k1 *= c2; + + h1 ^= k1; + h1 = ROTL32(h1,13); + h1 = h1*5+0xe6546b64; + } + + //---------- + // tail + + const uint8_t * tail = (const uint8_t*)(data + nblocks*4); + + uint32_t k1 = 0; + + switch(len & 3) + { + case 3: k1 ^= tail[2] << 16; + case 2: k1 ^= tail[1] << 8; + case 1: k1 ^= tail[0]; + k1 *= c1; k1 = ROTL32(k1,15); k1 *= c2; h1 ^= k1; + }; + + //---------- + // finalization + + h1 ^= len; + + h1 = fmix32(h1); + + *(uint32_t*)out = h1; +} + +//----------------------------------------------------------------------------- + +void MurmurHash3_x86_128 ( const void * key, const int len, + uint32_t seed, void * out ) +{ + const uint8_t * data = (const uint8_t*)key; + const int nblocks = len / 16; + + uint32_t h1 = seed; + uint32_t h2 = seed; + uint32_t h3 = seed; + uint32_t h4 = seed; + + const uint32_t c1 = 0x239b961b; + const uint32_t c2 = 0xab0e9789; + const uint32_t c3 = 0x38b34ae5; + const uint32_t c4 = 0xa1e38b93; + + //---------- + // body + + const uint32_t * blocks = (const uint32_t *)(data + nblocks*16); + + for(int i = -nblocks; i; i++) + { + uint32_t k1 = getblock32(blocks,i*4+0); + uint32_t k2 = getblock32(blocks,i*4+1); + uint32_t k3 = getblock32(blocks,i*4+2); + uint32_t k4 = getblock32(blocks,i*4+3); + + k1 *= c1; k1 = ROTL32(k1,15); k1 *= c2; h1 ^= k1; + + h1 = ROTL32(h1,19); h1 += h2; h1 = h1*5+0x561ccd1b; + + k2 *= c2; k2 = ROTL32(k2,16); k2 *= c3; h2 ^= k2; + + h2 = ROTL32(h2,17); h2 += h3; h2 = h2*5+0x0bcaa747; + + k3 *= c3; k3 = ROTL32(k3,17); k3 *= c4; h3 ^= k3; + + h3 = ROTL32(h3,15); h3 += h4; h3 = h3*5+0x96cd1c35; + + k4 *= c4; k4 = ROTL32(k4,18); k4 *= c1; h4 ^= k4; + + h4 = ROTL32(h4,13); h4 += h1; h4 = h4*5+0x32ac3b17; + } + + //---------- + // tail + + const uint8_t * tail = (const uint8_t*)(data + nblocks*16); + + uint32_t k1 = 0; + uint32_t k2 = 0; + uint32_t k3 = 0; + uint32_t k4 = 0; + + switch(len & 15) + { + case 15: k4 ^= tail[14] << 16; + case 14: k4 ^= tail[13] << 8; + case 13: k4 ^= tail[12] << 0; + k4 *= c4; k4 = ROTL32(k4,18); k4 *= c1; h4 ^= k4; + + case 12: k3 ^= tail[11] << 24; + case 11: k3 ^= tail[10] << 16; + case 10: k3 ^= tail[ 9] << 8; + case 9: k3 ^= tail[ 8] << 0; + k3 *= c3; k3 = ROTL32(k3,17); k3 *= c4; h3 ^= k3; + + case 8: k2 ^= tail[ 7] << 24; + case 7: k2 ^= tail[ 6] << 16; + case 6: k2 ^= tail[ 5] << 8; + case 5: k2 ^= tail[ 4] << 0; + k2 *= c2; k2 = ROTL32(k2,16); k2 *= c3; h2 ^= k2; + + case 4: k1 ^= tail[ 3] << 24; + case 3: k1 ^= tail[ 2] << 16; + case 2: k1 ^= tail[ 1] << 8; + case 1: k1 ^= tail[ 0] << 0; + k1 *= c1; k1 = ROTL32(k1,15); k1 *= c2; h1 ^= k1; + }; + + //---------- + // finalization + + h1 ^= len; h2 ^= len; h3 ^= len; h4 ^= len; + + h1 += h2; h1 += h3; h1 += h4; + h2 += h1; h3 += h1; h4 += h1; + + h1 = fmix32(h1); + h2 = fmix32(h2); + h3 = fmix32(h3); + h4 = fmix32(h4); + + h1 += h2; h1 += h3; h1 += h4; + h2 += h1; h3 += h1; h4 += h1; + + ((uint32_t*)out)[0] = h1; + ((uint32_t*)out)[1] = h2; + ((uint32_t*)out)[2] = h3; + ((uint32_t*)out)[3] = h4; +} + +//----------------------------------------------------------------------------- + +void MurmurHash3_x64_128 ( const void * key, const int len, + const uint32_t seed, void * out ) +{ + const uint8_t * data = (const uint8_t*)key; + const int nblocks = len / 16; + + uint64_t h1 = seed; + uint64_t h2 = seed; + + const uint64_t c1 = BIG_CONSTANT(0x87c37b91114253d5); + const uint64_t c2 = BIG_CONSTANT(0x4cf5ad432745937f); + + //---------- + // body + + const uint64_t * blocks = (const uint64_t *)(data); + + for(int i = 0; i < nblocks; i++) + { + uint64_t k1 = getblock64(blocks,i*2+0); + uint64_t k2 = getblock64(blocks,i*2+1); + + k1 *= c1; k1 = ROTL64(k1,31); k1 *= c2; h1 ^= k1; + + h1 = ROTL64(h1,27); h1 += h2; h1 = h1*5+0x52dce729; + + k2 *= c2; k2 = ROTL64(k2,33); k2 *= c1; h2 ^= k2; + + h2 = ROTL64(h2,31); h2 += h1; h2 = h2*5+0x38495ab5; + } + + //---------- + // tail + + const uint8_t * tail = (const uint8_t*)(data + nblocks*16); + + uint64_t k1 = 0; + uint64_t k2 = 0; + + switch(len & 15) + { + case 15: k2 ^= ((uint64_t)tail[14]) << 48; + case 14: k2 ^= ((uint64_t)tail[13]) << 40; + case 13: k2 ^= ((uint64_t)tail[12]) << 32; + case 12: k2 ^= ((uint64_t)tail[11]) << 24; + case 11: k2 ^= ((uint64_t)tail[10]) << 16; + case 10: k2 ^= ((uint64_t)tail[ 9]) << 8; + case 9: k2 ^= ((uint64_t)tail[ 8]) << 0; + k2 *= c2; k2 = ROTL64(k2,33); k2 *= c1; h2 ^= k2; + + case 8: k1 ^= ((uint64_t)tail[ 7]) << 56; + case 7: k1 ^= ((uint64_t)tail[ 6]) << 48; + case 6: k1 ^= ((uint64_t)tail[ 5]) << 40; + case 5: k1 ^= ((uint64_t)tail[ 4]) << 32; + case 4: k1 ^= ((uint64_t)tail[ 3]) << 24; + case 3: k1 ^= ((uint64_t)tail[ 2]) << 16; + case 2: k1 ^= ((uint64_t)tail[ 1]) << 8; + case 1: k1 ^= ((uint64_t)tail[ 0]) << 0; + k1 *= c1; k1 = ROTL64(k1,31); k1 *= c2; h1 ^= k1; + }; + + //---------- + // finalization + + h1 ^= len; h2 ^= len; + + h1 += h2; + h2 += h1; + + h1 = fmix64(h1); + h2 = fmix64(h2); + + h1 += h2; + h2 += h1; + + ((uint64_t*)out)[0] = h1; + ((uint64_t*)out)[1] = h2; +} + +//----------------------------------------------------------------------------- + diff --git a/lib/MurmurHash3.h b/lib/MurmurHash3.h new file mode 100644 index 0000000..e1c6d34 --- /dev/null +++ b/lib/MurmurHash3.h @@ -0,0 +1,37 @@ +//----------------------------------------------------------------------------- +// MurmurHash3 was written by Austin Appleby, and is placed in the public +// domain. The author hereby disclaims copyright to this source code. + +#ifndef _MURMURHASH3_H_ +#define _MURMURHASH3_H_ + +//----------------------------------------------------------------------------- +// Platform-specific functions and macros + +// Microsoft Visual Studio + +#if defined(_MSC_VER) && (_MSC_VER < 1600) + +typedef unsigned char uint8_t; +typedef unsigned int uint32_t; +typedef unsigned __int64 uint64_t; + +// Other compilers + +#else // defined(_MSC_VER) + +#include + +#endif // !defined(_MSC_VER) + +//----------------------------------------------------------------------------- + +void MurmurHash3_x86_32 ( const void * key, int len, uint32_t seed, void * out ); + +void MurmurHash3_x86_128 ( const void * key, int len, uint32_t seed, void * out ); + +void MurmurHash3_x64_128 ( const void * key, int len, uint32_t seed, void * out ); + +//----------------------------------------------------------------------------- + +#endif // _MURMURHASH3_H_ diff --git a/src/CMakeLists.txt b/src/CMakeLists.txt index 68b6b35..8a14030 100644 --- a/src/CMakeLists.txt +++ b/src/CMakeLists.txt @@ -1,7 +1,13 @@ include_directories(${CMAKE_CURRENT_SOURCE_DIR}/../lib) -add_library(SDBLib STATIC InputBuffer.c InputBuffer.h SQL.c SQL.h scanner.c scanner.h parser.c parser.h bplus_tree.c bplus_tree.h) +add_library(SDBLib STATIC + InputBuffer.c InputBuffer.h + SQL.c SQL.h + scanner.c scanner.h + parser.c parser.h + bplus_tree.c bplus_tree.h + ../lib/MurmurHash3.c ../lib/MurmurHash3.h random.c random.h) add_executable(SDB main.c) target_link_libraries(SDB SDBLib) \ No newline at end of file diff --git a/src/main.c b/src/main.c index 20beede..9cdb225 100644 --- a/src/main.c +++ b/src/main.c @@ -4,15 +4,16 @@ #include #include #include +#include #include "InputBuffer.h" #include "scanner.h" #include "parser.h" - -#include "bplus_tree.h" +#include "random.h" void prompt() { printf("SDB> "); + fflush(stdout); } void read_input(InputBuffer *buffer) { @@ -51,14 +52,16 @@ void parse_input(char *input) { free_scanner(scanner); free_parser(parser); - } int main() { - setbuf(stdout, 0); setbuf(stderr, 0); InputBuffer *buffer = input_buffer_new(); + if (!init_random()) { + fprintf(stderr, "Error: failed to init random device\n"); + exit(EXIT_FAILURE); + } while (true) { prompt(); @@ -72,5 +75,6 @@ int main() { } input_buffer_free(buffer); + deinit_random(); return EXIT_SUCCESS; } \ No newline at end of file diff --git a/src/parser.c b/src/parser.c index 1b7bd1a..94d1626 100644 --- a/src/parser.c +++ b/src/parser.c @@ -300,7 +300,7 @@ ParserNode *parser_parse(Parser *parser, Scanner *scanner) { } break; default: - parser_set_error(parser, "Unexpected node type", token); + parser_set_error(parser, "Unexpected input, expected start of statement", token); break; } } diff --git a/src/random.c b/src/random.c new file mode 100644 index 0000000..53e5f11 --- /dev/null +++ b/src/random.c @@ -0,0 +1,36 @@ +// +// Created by sam on 12/07/18. +// + +#include +#include +#include "random.h" + +FILE * randomFile = NULL; +bool init_random() { + randomFile = fopen("/dev/urandom", "r"); + return randomFile != NULL; +} +bool deinit_random() { + int result = 0; + if (randomFile != NULL) { + result = fclose(randomFile); + randomFile = NULL; + } + return result == 0; +} +uint32_t random_32(bool *success) { + assert(randomFile != NULL); + uint32_t output = 0; + + if (fread(&output, sizeof(uint32_t), 1, randomFile) < 1) { + if (success != NULL) { + *success = false; + } + return 0; + } + if (success != NULL) { + *success = true; + } + return output; +} \ No newline at end of file diff --git a/src/random.h b/src/random.h new file mode 100644 index 0000000..fcf8b76 --- /dev/null +++ b/src/random.h @@ -0,0 +1,15 @@ +// +// Created by sam on 12/07/18. +// + +#ifndef SDB_RANDOM_H +#define SDB_RANDOM_H + +#include +#include + +bool init_random(); +bool deinit_random(); +uint32_t random_32(bool *success); + +#endif //SDB_RANDOM_H