Test vectors for MurmurHash3

MurmurHash3Test.cpp

#include "MurmurHash3.h"
#include "doctest.h"
#include <string>
#include <vector>

static void TestString(const std::string& s, uint32_t seed, uint32_t expected)
{
	uint32_t hash;
	MurmurHash3_x86_32(s.c_str(), s.length(), seed, &hash);
	CHECK(hash == expected);
}

static void TestArray(const std::vector<uint8_t>& s, uint32_t seed, uint32_t expected)
{
	uint32_t hash;
	MurmurHash3_x86_32(s.data(), s.size(), seed, &hash);
	CHECK(hash == expected);
}

TEST_CASE("MurmurHash3")
{
	TestArray({}, 0, 0);	// with zero data and zero seed, everything becomes zero
	TestArray({}, 1, 0x514E28B7);	// ignores nearly all the math
	TestArray({}, 0xffffffff, 0x81F16F39);	// make sure your seed uses unsigned 32-bit math
	TestArray({ 0xff, 0xff, 0xff, 0xff }, 0, 0x76293B50);	// make sure 4-byte chunks use unsigned math
	TestArray({ 0x21, 0x43, 0x65, 0x87 }, 0, 0xF55B516B);	// Endian order. UInt32 should end up as 0x87654321
	TestArray({ 0x21, 0x43, 0x65, 0x87  }, 0x5082EDEE, 0x2362F9DE);	// Special seed value eliminates initial key with xor
	TestArray({ 0x21, 0x43, 0x65 }, 0, 0x7E4A8634);	// Only three bytes. Should end up as 0x654321
	TestArray({ 0x21, 0x43 }, 0, 0xA0F7B07A);	// Only two bytes. Should end up as 0x4321
	TestArray({ 0x21 }, 0, 0x72661CF4);	// Only one byte. Should end up as 0x21
	TestArray({ 0x00, 0x00, 0x00, 0x00 }, 0, 0x2362F9DE);	// Make sure compiler doesn't see zero and convert to null
	TestArray({ 0x00, 0x00, 0x00 }, 0, 0x85F0B427);
	TestArray({ 0x00, 0x00 }, 0, 0x30F4C306);
	TestArray({ 0x00 }, 0, 0x514E28B7);

	TestString("", 0, 0); // empty string with zero seed should give zero
	TestString("", 1, 0x514E28B7);
	TestString("", 0xffffffff, 0x81F16F39); // make sure seed value is handled unsigned

	TestString("aaaa", 0x9747b28c, 0x5A97808A); // one full chunk
	TestString("aaa", 0x9747b28c, 0x283E0130); // three characters
	TestString("aa", 0x9747b28c, 0x5D211726); // two characters
	TestString("a", 0x9747b28c, 0x7FA09EA6); // one character

	// Endian order within the chunks
	TestString("abcd", 0x9747b28c, 0xF0478627); // one full chunk
	TestString("abc", 0x9747b28c, 0xC84A62DD);
	TestString("ab", 0x9747b28c, 0x74875592);
	TestString("a", 0x9747b28c, 0x7FA09EA6);

	TestString("Hello, world!", 0x9747b28c, 0x24884CBA);
	TestString("aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa" \
		"aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa" \
		"aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa" \
		"aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa", 0x9747b28c, 0x37405BDC);

	TestString("abc", 0, 0xB3DD93FA);
	TestString("abcdbcdecdefdefgefghfghighijhijkijkljklmklmnlmnomnopnopq", 0, 0xEE925B90);

	TestString("The quick brown fox jumps over the lazy dog", 0x9747b28c, 0x2FA826CD);
}