mirror of
https://github.com/OpenMW/openmw.git
synced 2025-04-11 11:06:43 +00:00
Changes based on review comments, including:
* replace murmurhash with std::unordered_map * plug potential leak from unique_ptr release * replacing some sections with cleaner code
This commit is contained in:
parent
ee3361a118
commit
fd67ebde25
10 changed files with 39 additions and 650 deletions
|
@ -536,7 +536,6 @@ endif (CMAKE_CXX_COMPILER_ID STREQUAL GNU OR CMAKE_CXX_COMPILER_ID STREQUAL Clan
|
||||||
add_subdirectory (extern/osg-ffmpeg-videoplayer)
|
add_subdirectory (extern/osg-ffmpeg-videoplayer)
|
||||||
add_subdirectory (extern/oics)
|
add_subdirectory (extern/oics)
|
||||||
add_subdirectory (extern/Base64)
|
add_subdirectory (extern/Base64)
|
||||||
add_subdirectory (extern/murmurhash)
|
|
||||||
if (BUILD_OPENCS)
|
if (BUILD_OPENCS)
|
||||||
add_subdirectory (extern/osgQt)
|
add_subdirectory (extern/osgQt)
|
||||||
endif()
|
endif()
|
||||||
|
|
|
@ -226,7 +226,6 @@ target_link_libraries(openmw-cs
|
||||||
${OSGTEXT_LIBRARIES}
|
${OSGTEXT_LIBRARIES}
|
||||||
${OSG_LIBRARIES}
|
${OSG_LIBRARIES}
|
||||||
${EXTERN_OSGQT_LIBRARY}
|
${EXTERN_OSGQT_LIBRARY}
|
||||||
${MURMURHASH_LIBRARIES}
|
|
||||||
${Boost_SYSTEM_LIBRARY}
|
${Boost_SYSTEM_LIBRARY}
|
||||||
${Boost_FILESYSTEM_LIBRARY}
|
${Boost_FILESYSTEM_LIBRARY}
|
||||||
${Boost_PROGRAM_OPTIONS_LIBRARY}
|
${Boost_PROGRAM_OPTIONS_LIBRARY}
|
||||||
|
|
|
@ -99,8 +99,8 @@ void CSMWorld::InfoCollection::load (const Info& record, bool base)
|
||||||
int CSMWorld::InfoCollection::getInfoIndex (const std::string& id, const std::string& topic) const
|
int CSMWorld::InfoCollection::getInfoIndex (const std::string& id, const std::string& topic) const
|
||||||
{
|
{
|
||||||
// find the topic first
|
// find the topic first
|
||||||
std::map<StringHash, std::vector<std::pair<std::string, int> > >::const_iterator iter
|
std::unordered_map<std::string, std::vector<std::pair<std::string, int> > >::const_iterator iter
|
||||||
= mInfoIndex.find(StringHash(std::make_shared<std::string>(Misc::StringUtils::lowerCase(topic))));
|
= mInfoIndex.find(Misc::StringUtils::lowerCase(topic));
|
||||||
|
|
||||||
if (iter == mInfoIndex.end())
|
if (iter == mInfoIndex.end())
|
||||||
return -1;
|
return -1;
|
||||||
|
@ -187,16 +187,10 @@ bool CSMWorld::InfoCollection::reorderRows (int baseIndex, const std::vector<int
|
||||||
|
|
||||||
// adjust index
|
// adjust index
|
||||||
int size = static_cast<int>(newOrder.size());
|
int size = static_cast<int>(newOrder.size());
|
||||||
for (std::map<StringHash, std::vector<std::pair<std::string, int> > >::iterator iter
|
for (auto& [hash, infos] : mInfoIndex)
|
||||||
= mInfoIndex.begin(); iter != mInfoIndex.end(); ++iter)
|
for (auto& [a, b] : infos)
|
||||||
{
|
if (b >= baseIndex && b < baseIndex + size)
|
||||||
for (std::vector<std::pair<std::string, int> >::iterator it = iter->second.begin();
|
b = newOrder.at(b - baseIndex) + baseIndex;
|
||||||
it != iter->second.end(); ++it)
|
|
||||||
{
|
|
||||||
if (it->second >= baseIndex && it->second < baseIndex+size)
|
|
||||||
it->second = newOrder.at(it->second-baseIndex)+baseIndex;
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
return true;
|
return true;
|
||||||
}
|
}
|
||||||
|
@ -244,8 +238,8 @@ CSMWorld::InfoCollection::Range CSMWorld::InfoCollection::getTopicRange (const s
|
||||||
std::string lowerTopic = Misc::StringUtils::lowerCase (topic);
|
std::string lowerTopic = Misc::StringUtils::lowerCase (topic);
|
||||||
|
|
||||||
// find the topic
|
// find the topic
|
||||||
std::map<StringHash, std::vector<std::pair<std::string, int> > >::const_iterator iter
|
std::unordered_map<std::string, std::vector<std::pair<std::string, int> > >::const_iterator iter
|
||||||
= mInfoIndex.find(StringHash(std::make_shared<std::string>(lowerTopic)));
|
= mInfoIndex.find(lowerTopic);
|
||||||
|
|
||||||
if (iter == mInfoIndex.end())
|
if (iter == mInfoIndex.end())
|
||||||
return Range (getRecords().end(), getRecords().end());
|
return Range (getRecords().end(), getRecords().end());
|
||||||
|
@ -310,7 +304,7 @@ void CSMWorld::InfoCollection::removeRows (int index, int count)
|
||||||
{
|
{
|
||||||
Collection<Info, IdAccessor<Info> >::removeRows(index, count); // erase records only
|
Collection<Info, IdAccessor<Info> >::removeRows(index, count); // erase records only
|
||||||
|
|
||||||
for (std::map<StringHash, std::vector<std::pair<std::string, int> > >::iterator iter
|
for (std::unordered_map<std::string, std::vector<std::pair<std::string, int> > >::iterator iter
|
||||||
= mInfoIndex.begin(); iter != mInfoIndex.end();)
|
= mInfoIndex.begin(); iter != mInfoIndex.end();)
|
||||||
{
|
{
|
||||||
for (std::vector<std::pair<std::string, int> >::iterator it = iter->second.begin();
|
for (std::vector<std::pair<std::string, int> >::iterator it = iter->second.begin();
|
||||||
|
@ -383,7 +377,7 @@ void CSMWorld::InfoCollection::insertRecord (std::unique_ptr<RecordBase> record,
|
||||||
// adjust index
|
// adjust index
|
||||||
if (index < size-1)
|
if (index < size-1)
|
||||||
{
|
{
|
||||||
for (std::map<StringHash, std::vector<std::pair<std::string, int> > >::iterator iter
|
for (std::unordered_map<std::string, std::vector<std::pair<std::string, int> > >::iterator iter
|
||||||
= mInfoIndex.begin(); iter != mInfoIndex.end(); ++iter)
|
= mInfoIndex.begin(); iter != mInfoIndex.end(); ++iter)
|
||||||
{
|
{
|
||||||
for (std::vector<std::pair<std::string, int> >::iterator it = iter->second.begin();
|
for (std::vector<std::pair<std::string, int> >::iterator it = iter->second.begin();
|
||||||
|
@ -397,9 +391,9 @@ void CSMWorld::InfoCollection::insertRecord (std::unique_ptr<RecordBase> record,
|
||||||
|
|
||||||
// get iterator for existing topic or a new topic
|
// get iterator for existing topic or a new topic
|
||||||
std::string lowerId = Misc::StringUtils::lowerCase(id);
|
std::string lowerId = Misc::StringUtils::lowerCase(id);
|
||||||
std::pair<std::map<StringHash, std::vector<std::pair<std::string, int> > >::iterator, bool> res
|
std::pair<std::unordered_map<std::string, std::vector<std::pair<std::string, int> > >::iterator, bool> res
|
||||||
= mInfoIndex.insert(
|
= mInfoIndex.insert(
|
||||||
std::make_pair(StringHash(std::make_shared<std::string>(lowerId.substr(0, separator))),
|
std::make_pair(lowerId.substr(0, separator),
|
||||||
std::vector<std::pair<std::string, int> >())); // empty vector
|
std::vector<std::pair<std::string, int> >())); // empty vector
|
||||||
|
|
||||||
// insert info and index
|
// insert info and index
|
||||||
|
|
|
@ -1,8 +1,6 @@
|
||||||
#ifndef CSM_WOLRD_INFOCOLLECTION_H
|
#ifndef CSM_WOLRD_INFOCOLLECTION_H
|
||||||
#define CSM_WOLRD_INFOCOLLECTION_H
|
#define CSM_WOLRD_INFOCOLLECTION_H
|
||||||
|
|
||||||
#include <extern/murmurhash/MurmurHash2.h>
|
|
||||||
|
|
||||||
#include "collection.hpp"
|
#include "collection.hpp"
|
||||||
#include "info.hpp"
|
#include "info.hpp"
|
||||||
|
|
||||||
|
@ -11,37 +9,6 @@ namespace ESM
|
||||||
struct Dialogue;
|
struct Dialogue;
|
||||||
}
|
}
|
||||||
|
|
||||||
namespace CSMWorld
|
|
||||||
{
|
|
||||||
struct StringHash
|
|
||||||
{
|
|
||||||
uint64_t mHash;
|
|
||||||
std::shared_ptr<std::string> mString;
|
|
||||||
|
|
||||||
StringHash (std::shared_ptr<std::string> str) : mString(str)
|
|
||||||
{
|
|
||||||
mHash = MurmurHash64A(str->c_str(), str->size(), /*seed*/1);
|
|
||||||
}
|
|
||||||
};
|
|
||||||
}
|
|
||||||
|
|
||||||
namespace std
|
|
||||||
{
|
|
||||||
template<> struct less<CSMWorld::StringHash>
|
|
||||||
{
|
|
||||||
bool operator() (const CSMWorld::StringHash& lhs, const CSMWorld::StringHash& rhs) const
|
|
||||||
{
|
|
||||||
if (lhs.mHash < rhs.mHash)
|
|
||||||
return true;
|
|
||||||
|
|
||||||
if (lhs.mHash > rhs.mHash)
|
|
||||||
return false;
|
|
||||||
|
|
||||||
return *lhs.mString < *rhs.mString;
|
|
||||||
}
|
|
||||||
};
|
|
||||||
}
|
|
||||||
|
|
||||||
namespace CSMWorld
|
namespace CSMWorld
|
||||||
{
|
{
|
||||||
template<>
|
template<>
|
||||||
|
@ -69,8 +36,8 @@ namespace CSMWorld
|
||||||
// each topic has a small number of infos, which allows the use of vectors for
|
// each topic has a small number of infos, which allows the use of vectors for
|
||||||
// iterating through them without too much penalty.
|
// iterating through them without too much penalty.
|
||||||
//
|
//
|
||||||
// NOTE: hashed topic string as well as id string are stored in lower case.
|
// NOTE: topic string as well as id string are stored in lower case.
|
||||||
std::map<StringHash, std::vector<std::pair<std::string, int> > > mInfoIndex;
|
std::unordered_map<std::string, std::vector<std::pair<std::string, int> > > mInfoIndex;
|
||||||
|
|
||||||
void load (const Info& record, bool base);
|
void load (const Info& record, bool base);
|
||||||
|
|
||||||
|
|
|
@ -1,5 +1,7 @@
|
||||||
#include "refcollection.hpp"
|
#include "refcollection.hpp"
|
||||||
|
|
||||||
|
#include <charconv>
|
||||||
|
|
||||||
#include <components/esm/loadcell.hpp>
|
#include <components/esm/loadcell.hpp>
|
||||||
|
|
||||||
#include "ref.hpp"
|
#include "ref.hpp"
|
||||||
|
@ -120,9 +122,9 @@ void CSMWorld::RefCollection::load (ESM::ESMReader& reader, int cellIndex, bool
|
||||||
}
|
}
|
||||||
else
|
else
|
||||||
{
|
{
|
||||||
std::unique_ptr<Record<CellRef> > record2(new Record<CellRef>(getRecord(index)));
|
std::unique_ptr<Record<CellRef> > record(new Record<CellRef>(getRecord(index)));
|
||||||
record2->mState = RecordBase::State_Deleted;
|
record->mState = RecordBase::State_Deleted;
|
||||||
setRecord(index, std::move(record2));
|
setRecord(index, std::move(record));
|
||||||
}
|
}
|
||||||
|
|
||||||
continue;
|
continue;
|
||||||
|
@ -181,14 +183,19 @@ std::string CSMWorld::RefCollection::getNewId()
|
||||||
return "ref#" + std::to_string(mNextId++);
|
return "ref#" + std::to_string(mNextId++);
|
||||||
}
|
}
|
||||||
|
|
||||||
unsigned int CSMWorld::RefCollection::extractIdNum (const std::string& id) const
|
unsigned int CSMWorld::RefCollection::extractIdNum(std::string_view id) const
|
||||||
{
|
{
|
||||||
std::string::size_type separator = id.find_last_of('#');
|
const auto separator = id.find_last_of('#');
|
||||||
|
|
||||||
if (separator == std::string::npos)
|
if (separator == std::string_view::npos)
|
||||||
throw std::runtime_error("invalid ref ID: " + id);
|
throw std::runtime_error("invalid ref ID: " + std::string(id));
|
||||||
|
|
||||||
return static_cast<unsigned int>(std::stoi(id.substr(separator+1)));
|
const std::string_view number = id.substr(separator + 1);
|
||||||
|
unsigned int result;
|
||||||
|
if (std::from_chars(number.data(), number.data() + number.size(), result).ec != std::errc())
|
||||||
|
throw std::runtime_error("invalid ref ID number: " + std::string(number));
|
||||||
|
|
||||||
|
return result;
|
||||||
}
|
}
|
||||||
|
|
||||||
int CSMWorld::RefCollection::getIntIndex (unsigned int id) const
|
int CSMWorld::RefCollection::getIntIndex (unsigned int id) const
|
||||||
|
@ -235,15 +242,15 @@ void CSMWorld::RefCollection::removeRows (int index, int count)
|
||||||
|
|
||||||
void CSMWorld::RefCollection::appendBlankRecord (const std::string& id, UniversalId::Type type)
|
void CSMWorld::RefCollection::appendBlankRecord (const std::string& id, UniversalId::Type type)
|
||||||
{
|
{
|
||||||
std::unique_ptr<Record<CellRef> > record2(new Record<CellRef>);
|
std::unique_ptr<Record<CellRef> > record(new Record<CellRef>);
|
||||||
|
|
||||||
record2->mState = Record<CellRef>::State_ModifiedOnly;
|
record->mState = Record<CellRef>::State_ModifiedOnly;
|
||||||
record2->mModified.blank();
|
record->mModified.blank();
|
||||||
|
|
||||||
record2->get().mId = id;
|
record->get().mId = id;
|
||||||
record2->get().mIdNum = extractIdNum(id);
|
record->get().mIdNum = extractIdNum(id);
|
||||||
|
|
||||||
Collection<CellRef, IdAccessor<CellRef> >::appendRecord(std::move(record2));
|
Collection<CellRef, IdAccessor<CellRef> >::appendRecord(std::move(record));
|
||||||
}
|
}
|
||||||
|
|
||||||
void CSMWorld::RefCollection::cloneRecord (const std::string& origin,
|
void CSMWorld::RefCollection::cloneRecord (const std::string& origin,
|
||||||
|
|
|
@ -29,7 +29,7 @@ namespace CSMWorld
|
||||||
|
|
||||||
int mNextId;
|
int mNextId;
|
||||||
|
|
||||||
unsigned int extractIdNum(const std::string& id) const;
|
unsigned int extractIdNum(std::string_view id) const;
|
||||||
|
|
||||||
int getIntIndex (unsigned int id) const;
|
int getIntIndex (unsigned int id) const;
|
||||||
|
|
||||||
|
|
|
@ -94,13 +94,13 @@ namespace CSMWorld
|
||||||
template<typename RecordT>
|
template<typename RecordT>
|
||||||
void RefIdDataContainer<RecordT>::insertRecord(std::unique_ptr<RecordBase> record)
|
void RefIdDataContainer<RecordT>::insertRecord(std::unique_ptr<RecordBase> record)
|
||||||
{
|
{
|
||||||
Record<RecordT> *tmp = dynamic_cast<Record<RecordT>*>(record.get());
|
// convert base pointer to record type pointer first
|
||||||
if(tmp != nullptr)
|
if(Record<RecordT> *tmp = dynamic_cast<Record<RecordT>*>(record.get()))
|
||||||
{
|
{
|
||||||
record.release();
|
|
||||||
std::unique_ptr<Record<RecordT> > newRecord;
|
std::unique_ptr<Record<RecordT> > newRecord;
|
||||||
newRecord.reset(tmp);
|
newRecord.reset(tmp);
|
||||||
mContainer.push_back(std::move(newRecord));
|
mContainer.push_back(std::move(newRecord));
|
||||||
|
record.release();
|
||||||
}
|
}
|
||||||
else
|
else
|
||||||
throw std::runtime_error ("invalid record for RefIdDataContainer");
|
throw std::runtime_error ("invalid record for RefIdDataContainer");
|
||||||
|
|
17
extern/murmurhash/CMakeLists.txt
vendored
17
extern/murmurhash/CMakeLists.txt
vendored
|
@ -1,17 +0,0 @@
|
||||||
cmake_minimum_required(VERSION 2.8)
|
|
||||||
|
|
||||||
# This is NOT intended as a stand-alone build system! Instead, you should include this from the main CMakeLists of your project.
|
|
||||||
|
|
||||||
set(MURMURHASH_LIBRARY "murmurhash")
|
|
||||||
|
|
||||||
# Sources
|
|
||||||
set(SOURCE_FILES
|
|
||||||
MurmurHash2.cpp
|
|
||||||
)
|
|
||||||
|
|
||||||
add_library(${MURMURHASH_LIBRARY} STATIC ${SOURCE_FILES})
|
|
||||||
|
|
||||||
set(MURMURHASH_LIBRARIES ${MURMURHASH_LIBRARY})
|
|
||||||
|
|
||||||
link_directories(${CMAKE_CURRENT_BINARY_DIR})
|
|
||||||
set(MURMURHASH_LIBRARIES ${MURMURHASH_LIBRARIES} PARENT_SCOPE)
|
|
522
extern/murmurhash/MurmurHash2.cpp
vendored
522
extern/murmurhash/MurmurHash2.cpp
vendored
|
@ -1,522 +0,0 @@
|
||||||
//-----------------------------------------------------------------------------
|
|
||||||
// MurmurHash2 was written by Austin Appleby, and is placed in the public
|
|
||||||
// domain. The author hereby disclaims copyright to this source code.
|
|
||||||
|
|
||||||
// Note - This code makes a few assumptions about how your machine behaves -
|
|
||||||
|
|
||||||
// 1. We can read a 4-byte value from any address without crashing
|
|
||||||
// 2. sizeof(int) == 4
|
|
||||||
|
|
||||||
// And it has a few limitations -
|
|
||||||
|
|
||||||
// 1. It will not work incrementally.
|
|
||||||
// 2. It will not produce the same results on little-endian and big-endian
|
|
||||||
// machines.
|
|
||||||
|
|
||||||
#include "MurmurHash2.h"
|
|
||||||
|
|
||||||
//-----------------------------------------------------------------------------
|
|
||||||
// Platform-specific functions and macros
|
|
||||||
|
|
||||||
// Microsoft Visual Studio
|
|
||||||
|
|
||||||
#if defined(_MSC_VER)
|
|
||||||
|
|
||||||
#define BIG_CONSTANT(x) (x)
|
|
||||||
|
|
||||||
// Other compilers
|
|
||||||
|
|
||||||
#else // defined(_MSC_VER)
|
|
||||||
|
|
||||||
#define BIG_CONSTANT(x) (x##LLU)
|
|
||||||
|
|
||||||
#endif // !defined(_MSC_VER)
|
|
||||||
|
|
||||||
//-----------------------------------------------------------------------------
|
|
||||||
|
|
||||||
uint32_t MurmurHash2 ( const void * key, int len, uint32_t seed )
|
|
||||||
{
|
|
||||||
// 'm' and 'r' are mixing constants generated offline.
|
|
||||||
// They're not really 'magic', they just happen to work well.
|
|
||||||
|
|
||||||
const uint32_t m = 0x5bd1e995;
|
|
||||||
const int r = 24;
|
|
||||||
|
|
||||||
// Initialize the hash to a 'random' value
|
|
||||||
|
|
||||||
uint32_t h = seed ^ len;
|
|
||||||
|
|
||||||
// Mix 4 bytes at a time into the hash
|
|
||||||
|
|
||||||
const unsigned char * data = (const unsigned char *)key;
|
|
||||||
|
|
||||||
while(len >= 4)
|
|
||||||
{
|
|
||||||
uint32_t k = *(uint32_t*)data;
|
|
||||||
|
|
||||||
k *= m;
|
|
||||||
k ^= k >> r;
|
|
||||||
k *= m;
|
|
||||||
|
|
||||||
h *= m;
|
|
||||||
h ^= k;
|
|
||||||
|
|
||||||
data += 4;
|
|
||||||
len -= 4;
|
|
||||||
}
|
|
||||||
|
|
||||||
// Handle the last few bytes of the input array
|
|
||||||
|
|
||||||
switch(len)
|
|
||||||
{
|
|
||||||
case 3: h ^= data[2] << 16;
|
|
||||||
case 2: h ^= data[1] << 8;
|
|
||||||
case 1: h ^= data[0];
|
|
||||||
h *= m;
|
|
||||||
};
|
|
||||||
|
|
||||||
// Do a few final mixes of the hash to ensure the last few
|
|
||||||
// bytes are well-incorporated.
|
|
||||||
|
|
||||||
h ^= h >> 13;
|
|
||||||
h *= m;
|
|
||||||
h ^= h >> 15;
|
|
||||||
|
|
||||||
return h;
|
|
||||||
}
|
|
||||||
|
|
||||||
//-----------------------------------------------------------------------------
|
|
||||||
// MurmurHash2, 64-bit versions, by Austin Appleby
|
|
||||||
|
|
||||||
// The same caveats as 32-bit MurmurHash2 apply here - beware of alignment
|
|
||||||
// and endian-ness issues if used across multiple platforms.
|
|
||||||
|
|
||||||
// 64-bit hash for 64-bit platforms
|
|
||||||
|
|
||||||
uint64_t MurmurHash64A ( const void * key, int len, uint64_t seed )
|
|
||||||
{
|
|
||||||
const uint64_t m = BIG_CONSTANT(0xc6a4a7935bd1e995);
|
|
||||||
const int r = 47;
|
|
||||||
|
|
||||||
uint64_t h = seed ^ (len * m);
|
|
||||||
|
|
||||||
const uint64_t * data = (const uint64_t *)key;
|
|
||||||
const uint64_t * end = data + (len/8);
|
|
||||||
|
|
||||||
while(data != end)
|
|
||||||
{
|
|
||||||
uint64_t k = *data++;
|
|
||||||
|
|
||||||
k *= m;
|
|
||||||
k ^= k >> r;
|
|
||||||
k *= m;
|
|
||||||
|
|
||||||
h ^= k;
|
|
||||||
h *= m;
|
|
||||||
}
|
|
||||||
|
|
||||||
const unsigned char * data2 = (const unsigned char*)data;
|
|
||||||
|
|
||||||
switch(len & 7)
|
|
||||||
{
|
|
||||||
case 7: h ^= uint64_t(data2[6]) << 48;
|
|
||||||
case 6: h ^= uint64_t(data2[5]) << 40;
|
|
||||||
case 5: h ^= uint64_t(data2[4]) << 32;
|
|
||||||
case 4: h ^= uint64_t(data2[3]) << 24;
|
|
||||||
case 3: h ^= uint64_t(data2[2]) << 16;
|
|
||||||
case 2: h ^= uint64_t(data2[1]) << 8;
|
|
||||||
case 1: h ^= uint64_t(data2[0]);
|
|
||||||
h *= m;
|
|
||||||
};
|
|
||||||
|
|
||||||
h ^= h >> r;
|
|
||||||
h *= m;
|
|
||||||
h ^= h >> r;
|
|
||||||
|
|
||||||
return h;
|
|
||||||
}
|
|
||||||
|
|
||||||
|
|
||||||
// 64-bit hash for 32-bit platforms
|
|
||||||
|
|
||||||
uint64_t MurmurHash64B ( const void * key, int len, uint64_t seed )
|
|
||||||
{
|
|
||||||
const uint32_t m = 0x5bd1e995;
|
|
||||||
const int r = 24;
|
|
||||||
|
|
||||||
uint32_t h1 = uint32_t(seed) ^ len;
|
|
||||||
uint32_t h2 = uint32_t(seed >> 32);
|
|
||||||
|
|
||||||
const uint32_t * data = (const uint32_t *)key;
|
|
||||||
|
|
||||||
while(len >= 8)
|
|
||||||
{
|
|
||||||
uint32_t k1 = *data++;
|
|
||||||
k1 *= m; k1 ^= k1 >> r; k1 *= m;
|
|
||||||
h1 *= m; h1 ^= k1;
|
|
||||||
len -= 4;
|
|
||||||
|
|
||||||
uint32_t k2 = *data++;
|
|
||||||
k2 *= m; k2 ^= k2 >> r; k2 *= m;
|
|
||||||
h2 *= m; h2 ^= k2;
|
|
||||||
len -= 4;
|
|
||||||
}
|
|
||||||
|
|
||||||
if(len >= 4)
|
|
||||||
{
|
|
||||||
uint32_t k1 = *data++;
|
|
||||||
k1 *= m; k1 ^= k1 >> r; k1 *= m;
|
|
||||||
h1 *= m; h1 ^= k1;
|
|
||||||
len -= 4;
|
|
||||||
}
|
|
||||||
|
|
||||||
switch(len)
|
|
||||||
{
|
|
||||||
case 3: h2 ^= ((unsigned char*)data)[2] << 16;
|
|
||||||
case 2: h2 ^= ((unsigned char*)data)[1] << 8;
|
|
||||||
case 1: h2 ^= ((unsigned char*)data)[0];
|
|
||||||
h2 *= m;
|
|
||||||
};
|
|
||||||
|
|
||||||
h1 ^= h2 >> 18; h1 *= m;
|
|
||||||
h2 ^= h1 >> 22; h2 *= m;
|
|
||||||
h1 ^= h2 >> 17; h1 *= m;
|
|
||||||
h2 ^= h1 >> 19; h2 *= m;
|
|
||||||
|
|
||||||
uint64_t h = h1;
|
|
||||||
|
|
||||||
h = (h << 32) | h2;
|
|
||||||
|
|
||||||
return h;
|
|
||||||
}
|
|
||||||
|
|
||||||
//-----------------------------------------------------------------------------
|
|
||||||
// MurmurHash2A, by Austin Appleby
|
|
||||||
|
|
||||||
// This is a variant of MurmurHash2 modified to use the Merkle-Damgard
|
|
||||||
// construction. Bulk speed should be identical to Murmur2, small-key speed
|
|
||||||
// will be 10%-20% slower due to the added overhead at the end of the hash.
|
|
||||||
|
|
||||||
// This variant fixes a minor issue where null keys were more likely to
|
|
||||||
// collide with each other than expected, and also makes the function
|
|
||||||
// more amenable to incremental implementations.
|
|
||||||
|
|
||||||
#define mmix(h,k) { k *= m; k ^= k >> r; k *= m; h *= m; h ^= k; }
|
|
||||||
|
|
||||||
uint32_t MurmurHash2A ( const void * key, int len, uint32_t seed )
|
|
||||||
{
|
|
||||||
const uint32_t m = 0x5bd1e995;
|
|
||||||
const int r = 24;
|
|
||||||
uint32_t l = len;
|
|
||||||
|
|
||||||
const unsigned char * data = (const unsigned char *)key;
|
|
||||||
|
|
||||||
uint32_t h = seed;
|
|
||||||
|
|
||||||
while(len >= 4)
|
|
||||||
{
|
|
||||||
uint32_t k = *(uint32_t*)data;
|
|
||||||
|
|
||||||
mmix(h,k);
|
|
||||||
|
|
||||||
data += 4;
|
|
||||||
len -= 4;
|
|
||||||
}
|
|
||||||
|
|
||||||
uint32_t t = 0;
|
|
||||||
|
|
||||||
switch(len)
|
|
||||||
{
|
|
||||||
case 3: t ^= data[2] << 16;
|
|
||||||
case 2: t ^= data[1] << 8;
|
|
||||||
case 1: t ^= data[0];
|
|
||||||
};
|
|
||||||
|
|
||||||
mmix(h,t);
|
|
||||||
mmix(h,l);
|
|
||||||
|
|
||||||
h ^= h >> 13;
|
|
||||||
h *= m;
|
|
||||||
h ^= h >> 15;
|
|
||||||
|
|
||||||
return h;
|
|
||||||
}
|
|
||||||
|
|
||||||
//-----------------------------------------------------------------------------
|
|
||||||
// CMurmurHash2A, by Austin Appleby
|
|
||||||
|
|
||||||
// This is a sample implementation of MurmurHash2A designed to work
|
|
||||||
// incrementally.
|
|
||||||
|
|
||||||
// Usage -
|
|
||||||
|
|
||||||
// CMurmurHash2A hasher
|
|
||||||
// hasher.Begin(seed);
|
|
||||||
// hasher.Add(data1,size1);
|
|
||||||
// hasher.Add(data2,size2);
|
|
||||||
// ...
|
|
||||||
// hasher.Add(dataN,sizeN);
|
|
||||||
// uint32_t hash = hasher.End()
|
|
||||||
|
|
||||||
class CMurmurHash2A
|
|
||||||
{
|
|
||||||
public:
|
|
||||||
|
|
||||||
void Begin ( uint32_t seed = 0 )
|
|
||||||
{
|
|
||||||
m_hash = seed;
|
|
||||||
m_tail = 0;
|
|
||||||
m_count = 0;
|
|
||||||
m_size = 0;
|
|
||||||
}
|
|
||||||
|
|
||||||
void Add ( const unsigned char * data, int len )
|
|
||||||
{
|
|
||||||
m_size += len;
|
|
||||||
|
|
||||||
MixTail(data,len);
|
|
||||||
|
|
||||||
while(len >= 4)
|
|
||||||
{
|
|
||||||
uint32_t k = *(uint32_t*)data;
|
|
||||||
|
|
||||||
mmix(m_hash,k);
|
|
||||||
|
|
||||||
data += 4;
|
|
||||||
len -= 4;
|
|
||||||
}
|
|
||||||
|
|
||||||
MixTail(data,len);
|
|
||||||
}
|
|
||||||
|
|
||||||
uint32_t End ( void )
|
|
||||||
{
|
|
||||||
mmix(m_hash,m_tail);
|
|
||||||
mmix(m_hash,m_size);
|
|
||||||
|
|
||||||
m_hash ^= m_hash >> 13;
|
|
||||||
m_hash *= m;
|
|
||||||
m_hash ^= m_hash >> 15;
|
|
||||||
|
|
||||||
return m_hash;
|
|
||||||
}
|
|
||||||
|
|
||||||
private:
|
|
||||||
|
|
||||||
static const uint32_t m = 0x5bd1e995;
|
|
||||||
static const int r = 24;
|
|
||||||
|
|
||||||
void MixTail ( const unsigned char * & data, int & len )
|
|
||||||
{
|
|
||||||
while( len && ((len<4) || m_count) )
|
|
||||||
{
|
|
||||||
m_tail |= (*data++) << (m_count * 8);
|
|
||||||
|
|
||||||
m_count++;
|
|
||||||
len--;
|
|
||||||
|
|
||||||
if(m_count == 4)
|
|
||||||
{
|
|
||||||
mmix(m_hash,m_tail);
|
|
||||||
m_tail = 0;
|
|
||||||
m_count = 0;
|
|
||||||
}
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
uint32_t m_hash;
|
|
||||||
uint32_t m_tail;
|
|
||||||
uint32_t m_count;
|
|
||||||
uint32_t m_size;
|
|
||||||
};
|
|
||||||
|
|
||||||
//-----------------------------------------------------------------------------
|
|
||||||
// MurmurHashNeutral2, by Austin Appleby
|
|
||||||
|
|
||||||
// Same as MurmurHash2, but endian- and alignment-neutral.
|
|
||||||
// Half the speed though, alas.
|
|
||||||
|
|
||||||
uint32_t MurmurHashNeutral2 ( const void * key, int len, uint32_t seed )
|
|
||||||
{
|
|
||||||
const uint32_t m = 0x5bd1e995;
|
|
||||||
const int r = 24;
|
|
||||||
|
|
||||||
uint32_t h = seed ^ len;
|
|
||||||
|
|
||||||
const unsigned char * data = (const unsigned char *)key;
|
|
||||||
|
|
||||||
while(len >= 4)
|
|
||||||
{
|
|
||||||
uint32_t k;
|
|
||||||
|
|
||||||
k = data[0];
|
|
||||||
k |= data[1] << 8;
|
|
||||||
k |= data[2] << 16;
|
|
||||||
k |= data[3] << 24;
|
|
||||||
|
|
||||||
k *= m;
|
|
||||||
k ^= k >> r;
|
|
||||||
k *= m;
|
|
||||||
|
|
||||||
h *= m;
|
|
||||||
h ^= k;
|
|
||||||
|
|
||||||
data += 4;
|
|
||||||
len -= 4;
|
|
||||||
}
|
|
||||||
|
|
||||||
switch(len)
|
|
||||||
{
|
|
||||||
case 3: h ^= data[2] << 16;
|
|
||||||
case 2: h ^= data[1] << 8;
|
|
||||||
case 1: h ^= data[0];
|
|
||||||
h *= m;
|
|
||||||
};
|
|
||||||
|
|
||||||
h ^= h >> 13;
|
|
||||||
h *= m;
|
|
||||||
h ^= h >> 15;
|
|
||||||
|
|
||||||
return h;
|
|
||||||
}
|
|
||||||
|
|
||||||
//-----------------------------------------------------------------------------
|
|
||||||
// MurmurHashAligned2, by Austin Appleby
|
|
||||||
|
|
||||||
// Same algorithm as MurmurHash2, but only does aligned reads - should be safer
|
|
||||||
// on certain platforms.
|
|
||||||
|
|
||||||
// Performance will be lower than MurmurHash2
|
|
||||||
|
|
||||||
#define MIX(h,k,m) { k *= m; k ^= k >> r; k *= m; h *= m; h ^= k; }
|
|
||||||
|
|
||||||
|
|
||||||
uint32_t MurmurHashAligned2 ( const void * key, int len, uint32_t seed )
|
|
||||||
{
|
|
||||||
const uint32_t m = 0x5bd1e995;
|
|
||||||
const int r = 24;
|
|
||||||
|
|
||||||
const unsigned char * data = (const unsigned char *)key;
|
|
||||||
|
|
||||||
uint32_t h = seed ^ len;
|
|
||||||
|
|
||||||
int align = (uint64_t)data & 3;
|
|
||||||
|
|
||||||
if(align && (len >= 4))
|
|
||||||
{
|
|
||||||
// Pre-load the temp registers
|
|
||||||
|
|
||||||
uint32_t t = 0, d = 0;
|
|
||||||
|
|
||||||
switch(align)
|
|
||||||
{
|
|
||||||
case 1: t |= data[2] << 16;
|
|
||||||
case 2: t |= data[1] << 8;
|
|
||||||
case 3: t |= data[0];
|
|
||||||
}
|
|
||||||
|
|
||||||
t <<= (8 * align);
|
|
||||||
|
|
||||||
data += 4-align;
|
|
||||||
len -= 4-align;
|
|
||||||
|
|
||||||
int sl = 8 * (4-align);
|
|
||||||
int sr = 8 * align;
|
|
||||||
|
|
||||||
// Mix
|
|
||||||
|
|
||||||
while(len >= 4)
|
|
||||||
{
|
|
||||||
d = *(uint32_t *)data;
|
|
||||||
t = (t >> sr) | (d << sl);
|
|
||||||
|
|
||||||
uint32_t k = t;
|
|
||||||
|
|
||||||
MIX(h,k,m);
|
|
||||||
|
|
||||||
t = d;
|
|
||||||
|
|
||||||
data += 4;
|
|
||||||
len -= 4;
|
|
||||||
}
|
|
||||||
|
|
||||||
// Handle leftover data in temp registers
|
|
||||||
|
|
||||||
d = 0;
|
|
||||||
|
|
||||||
if(len >= align)
|
|
||||||
{
|
|
||||||
switch(align)
|
|
||||||
{
|
|
||||||
case 3: d |= data[2] << 16;
|
|
||||||
case 2: d |= data[1] << 8;
|
|
||||||
case 1: d |= data[0];
|
|
||||||
}
|
|
||||||
|
|
||||||
uint32_t k = (t >> sr) | (d << sl);
|
|
||||||
MIX(h,k,m);
|
|
||||||
|
|
||||||
data += align;
|
|
||||||
len -= align;
|
|
||||||
|
|
||||||
//----------
|
|
||||||
// Handle tail bytes
|
|
||||||
|
|
||||||
switch(len)
|
|
||||||
{
|
|
||||||
case 3: h ^= data[2] << 16;
|
|
||||||
case 2: h ^= data[1] << 8;
|
|
||||||
case 1: h ^= data[0];
|
|
||||||
h *= m;
|
|
||||||
};
|
|
||||||
}
|
|
||||||
else
|
|
||||||
{
|
|
||||||
switch(len)
|
|
||||||
{
|
|
||||||
case 3: d |= data[2] << 16;
|
|
||||||
case 2: d |= data[1] << 8;
|
|
||||||
case 1: d |= data[0];
|
|
||||||
case 0: h ^= (t >> sr) | (d << sl);
|
|
||||||
h *= m;
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
h ^= h >> 13;
|
|
||||||
h *= m;
|
|
||||||
h ^= h >> 15;
|
|
||||||
|
|
||||||
return h;
|
|
||||||
}
|
|
||||||
else
|
|
||||||
{
|
|
||||||
while(len >= 4)
|
|
||||||
{
|
|
||||||
uint32_t k = *(uint32_t *)data;
|
|
||||||
|
|
||||||
MIX(h,k,m);
|
|
||||||
|
|
||||||
data += 4;
|
|
||||||
len -= 4;
|
|
||||||
}
|
|
||||||
|
|
||||||
//----------
|
|
||||||
// Handle tail bytes
|
|
||||||
|
|
||||||
switch(len)
|
|
||||||
{
|
|
||||||
case 3: h ^= data[2] << 16;
|
|
||||||
case 2: h ^= data[1] << 8;
|
|
||||||
case 1: h ^= data[0];
|
|
||||||
h *= m;
|
|
||||||
};
|
|
||||||
|
|
||||||
h ^= h >> 13;
|
|
||||||
h *= m;
|
|
||||||
h ^= h >> 15;
|
|
||||||
|
|
||||||
return h;
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
//-----------------------------------------------------------------------------
|
|
38
extern/murmurhash/MurmurHash2.h
vendored
38
extern/murmurhash/MurmurHash2.h
vendored
|
@ -1,38 +0,0 @@
|
||||||
//-----------------------------------------------------------------------------
|
|
||||||
// MurmurHash2 was written by Austin Appleby, and is placed in the public
|
|
||||||
// domain. The author hereby disclaims copyright to this source code.
|
|
||||||
|
|
||||||
#ifndef _MURMURHASH2_H_
|
|
||||||
#define _MURMURHASH2_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 <stdint.h>
|
|
||||||
|
|
||||||
#endif // !defined(_MSC_VER)
|
|
||||||
|
|
||||||
//-----------------------------------------------------------------------------
|
|
||||||
|
|
||||||
uint32_t MurmurHash2 ( const void * key, int len, uint32_t seed );
|
|
||||||
uint64_t MurmurHash64A ( const void * key, int len, uint64_t seed );
|
|
||||||
uint64_t MurmurHash64B ( const void * key, int len, uint64_t seed );
|
|
||||||
uint32_t MurmurHash2A ( const void * key, int len, uint32_t seed );
|
|
||||||
uint32_t MurmurHashNeutral2 ( const void * key, int len, uint32_t seed );
|
|
||||||
uint32_t MurmurHashAligned2 ( const void * key, int len, uint32_t seed );
|
|
||||||
|
|
||||||
//-----------------------------------------------------------------------------
|
|
||||||
|
|
||||||
#endif // _MURMURHASH2_H_
|
|
Loading…
Reference in a new issue