//===--- StringMap.h - String Hash table map interface ----------*- C++ -*-===// // // The LLVM Compiler Infrastructure // // This file is distributed under the University of Illinois Open Source // License. See LICENSE.TXT for details. // //===----------------------------------------------------------------------===// // // This file defines the StringMap class. // //===----------------------------------------------------------------------===// #ifndef LLVM_ADT_STRINGMAP_H #define LLVM_ADT_STRINGMAP_H #include "llvm/Support/Allocator.h" #include #include namespace llvm { template class StringMapConstIterator; template class StringMapIterator; template class StringMapEntry; /// StringMapEntryInitializer - This datatype can be partially specialized for /// various datatypes in a stringmap to allow them to be initialized when an /// entry is default constructed for the map. template class StringMapEntryInitializer { public: template static void Initialize(StringMapEntry &T, InitTy InitVal) { } }; /// StringMapEntryBase - Shared base class of StringMapEntry instances. class StringMapEntryBase { unsigned StrLen; public: explicit StringMapEntryBase(unsigned Len) : StrLen(Len) {} unsigned getKeyLength() const { return StrLen; } }; /// StringMapImpl - This is the base class of StringMap that is shared among /// all of its instantiations. class StringMapImpl { public: /// ItemBucket - The hash table consists of an array of these. If Item is /// non-null, this is an extant entry, otherwise, it is a hole. struct ItemBucket { /// FullHashValue - This remembers the full hash value of the key for /// easy scanning. unsigned FullHashValue; /// Item - This is a pointer to the actual item object. StringMapEntryBase *Item; }; protected: ItemBucket *TheTable; unsigned NumBuckets; unsigned NumItems; unsigned NumTombstones; unsigned ItemSize; protected: explicit StringMapImpl(unsigned itemSize) : ItemSize(itemSize) { // Initialize the map with zero buckets to allocation. TheTable = 0; NumBuckets = 0; NumItems = 0; NumTombstones = 0; } StringMapImpl(unsigned InitSize, unsigned ItemSize); void RehashTable(); /// ShouldRehash - Return true if the table should be rehashed after a new /// element was recently inserted. bool ShouldRehash() const { // If the hash table is now more than 3/4 full, or if fewer than 1/8 of // the buckets are empty (meaning that many are filled with tombstones), // grow the table. return NumItems*4 > NumBuckets*3 || NumBuckets-(NumItems+NumTombstones) < NumBuckets/8; } /// LookupBucketFor - Look up the bucket that the specified string should end /// up in. If it already exists as a key in the map, the Item pointer for the /// specified bucket will be non-null. Otherwise, it will be null. In either /// case, the FullHashValue field of the bucket will be set to the hash value /// of the string. unsigned LookupBucketFor(const char *KeyStart, const char *KeyEnd); /// FindKey - Look up the bucket that contains the specified key. If it exists /// in the map, return the bucket number of the key. Otherwise return -1. /// This does not modify the map. int FindKey(const char *KeyStart, const char *KeyEnd) const; /// RemoveKey - Remove the specified StringMapEntry from the table, but do not /// delete it. This aborts if the value isn't in the table. void RemoveKey(StringMapEntryBase *V); /// RemoveKey - Remove the StringMapEntry for the specified key from the /// table, returning it. If the key is not in the table, this returns null. StringMapEntryBase *RemoveKey(const char *KeyStart, const char *KeyEnd); private: void init(unsigned Size); public: static StringMapEntryBase *getTombstoneVal() { return (StringMapEntryBase*)-1; } unsigned getNumBuckets() const { return NumBuckets; } unsigned getNumItems() const { return NumItems; } bool empty() const { return NumItems == 0; } unsigned size() const { return NumItems; } }; /// StringMapEntry - This is used to represent one value that is inserted into /// a StringMap. It contains the Value itself and the key: the string length /// and data. template class StringMapEntry : public StringMapEntryBase { public: ValueTy second; explicit StringMapEntry(unsigned strLen) : StringMapEntryBase(strLen), second() {} StringMapEntry(unsigned strLen, const ValueTy &V) : StringMapEntryBase(strLen), second(V) {} const ValueTy &getValue() const { return second; } ValueTy &getValue() { return second; } void setValue(const ValueTy &V) { second = V; } /// getKeyData - Return the start of the string data that is the key for this /// value. The string data is always stored immediately after the /// StringMapEntry object. const char *getKeyData() const {return reinterpret_cast(this+1);} const char *first() const { return getKeyData(); } /// Create - Create a StringMapEntry for the specified key and default /// construct the value. template static StringMapEntry *Create(const char *KeyStart, const char *KeyEnd, AllocatorTy &Allocator, InitType InitVal) { unsigned KeyLength = static_cast(KeyEnd-KeyStart); // Okay, the item doesn't already exist, and 'Bucket' is the bucket to fill // in. Allocate a new item with space for the string at the end and a null // terminator. unsigned AllocSize = static_cast(sizeof(StringMapEntry))+ KeyLength+1; unsigned Alignment = alignof(); StringMapEntry *NewItem = static_cast(Allocator.Allocate(AllocSize,Alignment)); // Default construct the value. new (NewItem) StringMapEntry(KeyLength); // Copy the string information. char *StrBuffer = const_cast(NewItem->getKeyData()); memcpy(StrBuffer, KeyStart, KeyLength); StrBuffer[KeyLength] = 0; // Null terminate for convenience of clients. // Initialize the value if the client wants to. StringMapEntryInitializer::Initialize(*NewItem, InitVal); return NewItem; } template static StringMapEntry *Create(const char *KeyStart, const char *KeyEnd, AllocatorTy &Allocator) { return Create(KeyStart, KeyEnd, Allocator, (void*)0); } /// Create - Create a StringMapEntry with normal malloc/free. template static StringMapEntry *Create(const char *KeyStart, const char *KeyEnd, InitType InitVal) { MallocAllocator A; return Create(KeyStart, KeyEnd, A, InitVal); } static StringMapEntry *Create(const char *KeyStart, const char *KeyEnd) { return Create(KeyStart, KeyEnd, (void*)0); } /// GetStringMapEntryFromValue - Given a value that is known to be embedded /// into a StringMapEntry, return the StringMapEntry itself. static StringMapEntry &GetStringMapEntryFromValue(ValueTy &V) { StringMapEntry *EPtr = 0; char *Ptr = reinterpret_cast(&V) - (reinterpret_cast(&EPtr->second) - reinterpret_cast(EPtr)); return *reinterpret_cast(Ptr); } static const StringMapEntry &GetStringMapEntryFromValue(const ValueTy &V) { return GetStringMapEntryFromValue(const_cast(V)); } /// Destroy - Destroy this StringMapEntry, releasing memory back to the /// specified allocator. template void Destroy(AllocatorTy &Allocator) { // Free memory referenced by the item. this->~StringMapEntry(); Allocator.Deallocate(this); } /// Destroy this object, releasing memory back to the malloc allocator. void Destroy() { MallocAllocator A; Destroy(A); } }; /// StringMap - This is an unconventional map that is specialized for handling /// keys that are "strings", which are basically ranges of bytes. This does some /// funky memory allocation and hashing things to make it extremely efficient, /// storing the string data *after* the value in the map. template class StringMap : public StringMapImpl { AllocatorTy Allocator; typedef StringMapEntry MapEntryTy; public: StringMap() : StringMapImpl(static_cast(sizeof(MapEntryTy))) {} explicit StringMap(unsigned InitialSize) : StringMapImpl(InitialSize, static_cast(sizeof(MapEntryTy))) {} AllocatorTy &getAllocator() { return Allocator; } const AllocatorTy &getAllocator() const { return Allocator; } typedef const char* key_type; typedef ValueTy mapped_type; typedef StringMapEntry value_type; typedef size_t size_type; typedef StringMapConstIterator const_iterator; typedef StringMapIterator iterator; iterator begin() { return iterator(TheTable, NumBuckets == 0); } iterator end() { return iterator(TheTable+NumBuckets, true); } const_iterator begin() const { return const_iterator(TheTable, NumBuckets == 0); } const_iterator end() const { return const_iterator(TheTable+NumBuckets, true); } iterator find(const char *KeyStart, const char *KeyEnd) { int Bucket = FindKey(KeyStart, KeyEnd); if (Bucket == -1) return end(); return iterator(TheTable+Bucket); } iterator find(const char *Key) { return find(Key, Key + strlen(Key)); } iterator find(const std::string &Key) { const char* key_start = (Key.empty() ? NULL : &Key[0]); return find(key_start, key_start + Key.size()); } const_iterator find(const char *KeyStart, const char *KeyEnd) const { int Bucket = FindKey(KeyStart, KeyEnd); if (Bucket == -1) return end(); return const_iterator(TheTable+Bucket); } const_iterator find(const char *Key) const { return find(Key, Key + strlen(Key)); } const_iterator find(const std::string &Key) const { const char* key_start = (Key.empty() ? NULL : &Key[0]); return find(key_start, key_start + Key.size()); } ValueTy& operator[](const char *Key) { value_type& entry = GetOrCreateValue(Key, Key + strlen(Key)); return entry.getValue(); } ValueTy& operator[](const std::string &Key) { const char* key_start = (Key.empty() ? NULL : &Key[0]); value_type& entry = GetOrCreateValue(key_start, key_start + Key.size()); return entry.getValue(); } size_type count(const char *KeyStart, const char *KeyEnd) const { return find(KeyStart, KeyEnd) == end() ? 0 : 1; } size_type count(const char *Key) const { return count(Key, Key + strlen(Key)); } size_type count(const std::string &Key) const { const char* key_start = (Key.empty() ? NULL : &Key[0]); return count(key_start, key_start + Key.size()); } /// insert - Insert the specified key/value pair into the map. If the key /// already exists in the map, return false and ignore the request, otherwise /// insert it and return true. bool insert(MapEntryTy *KeyValue) { unsigned BucketNo = LookupBucketFor(KeyValue->getKeyData(), KeyValue->getKeyData()+KeyValue->getKeyLength()); ItemBucket &Bucket = TheTable[BucketNo]; if (Bucket.Item && Bucket.Item != getTombstoneVal()) return false; // Already exists in map. if (Bucket.Item == getTombstoneVal()) --NumTombstones; Bucket.Item = KeyValue; ++NumItems; if (ShouldRehash()) RehashTable(); return true; } // clear - Empties out the StringMap void clear() { if (empty()) return; // Zap all values, resetting the keys back to non-present (not tombstone), // which is safe because we're removing all elements. for (ItemBucket *I = TheTable, *E = TheTable+NumBuckets; I != E; ++I) { if (I->Item && I->Item != getTombstoneVal()) { static_cast(I->Item)->Destroy(Allocator); I->Item = 0; } } } /// GetOrCreateValue - Look up the specified key in the table. If a value /// exists, return it. Otherwise, default construct a value, insert it, and /// return. template StringMapEntry &GetOrCreateValue(const char *KeyStart, const char *KeyEnd, InitTy Val) { unsigned BucketNo = LookupBucketFor(KeyStart, KeyEnd); ItemBucket &Bucket = TheTable[BucketNo]; if (Bucket.Item && Bucket.Item != getTombstoneVal()) return *static_cast(Bucket.Item); MapEntryTy *NewItem = MapEntryTy::Create(KeyStart, KeyEnd, Allocator, Val); if (Bucket.Item == getTombstoneVal()) --NumTombstones; ++NumItems; // Fill in the bucket for the hash table. The FullHashValue was already // filled in by LookupBucketFor. Bucket.Item = NewItem; if (ShouldRehash()) RehashTable(); return *NewItem; } StringMapEntry &GetOrCreateValue(const char *KeyStart, const char *KeyEnd) { return GetOrCreateValue(KeyStart, KeyEnd, (void*)0); } /// remove - Remove the specified key/value pair from the map, but do not /// erase it. This aborts if the key is not in the map. void remove(MapEntryTy *KeyValue) { RemoveKey(KeyValue); } void erase(iterator I) { MapEntryTy &V = *I; remove(&V); V.Destroy(Allocator); } bool erase(const char *Key) { iterator I = find(Key); if (I == end()) return false; erase(I); return true; } bool erase(const std::string &Key) { iterator I = find(Key); if (I == end()) return false; erase(I); return true; } ~StringMap() { clear(); free(TheTable); } private: StringMap(const StringMap &); // FIXME: Implement. void operator=(const StringMap &); // FIXME: Implement. }; template class StringMapConstIterator { protected: StringMapImpl::ItemBucket *Ptr; public: explicit StringMapConstIterator(StringMapImpl::ItemBucket *Bucket, bool NoAdvance = false) : Ptr(Bucket) { if (!NoAdvance) AdvancePastEmptyBuckets(); } const StringMapEntry &operator*() const { return *static_cast*>(Ptr->Item); } const StringMapEntry *operator->() const { return static_cast*>(Ptr->Item); } bool operator==(const StringMapConstIterator &RHS) const { return Ptr == RHS.Ptr; } bool operator!=(const StringMapConstIterator &RHS) const { return Ptr != RHS.Ptr; } inline StringMapConstIterator& operator++() { // Preincrement ++Ptr; AdvancePastEmptyBuckets(); return *this; } StringMapConstIterator operator++(int) { // Postincrement StringMapConstIterator tmp = *this; ++*this; return tmp; } private: void AdvancePastEmptyBuckets() { while (Ptr->Item == 0 || Ptr->Item == StringMapImpl::getTombstoneVal()) ++Ptr; } }; template class StringMapIterator : public StringMapConstIterator { public: explicit StringMapIterator(StringMapImpl::ItemBucket *Bucket, bool NoAdvance = false) : StringMapConstIterator(Bucket, NoAdvance) { } StringMapEntry &operator*() const { return *static_cast*>(this->Ptr->Item); } StringMapEntry *operator->() const { return static_cast*>(this->Ptr->Item); } }; } #endif