//===- StringMap.h - String Hash table map interface ------------*- C++ -*-===// // // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions. // See https://llvm.org/LICENSE.txt for license information. // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception // //===----------------------------------------------------------------------===// /// /// \file /// This file defines the StringMap class. /// //===----------------------------------------------------------------------===// #ifndef LLVM_ADT_STRINGMAP_H #define LLVM_ADT_STRINGMAP_H #include "llvm/ADT/EpochTracker.h" #include "llvm/ADT/StringMapEntry.h" #include "llvm/ADT/iterator.h" #include "llvm/Support/AllocatorBase.h" #include "llvm/Support/Compiler.h" #include "llvm/Support/PointerLikeTypeTraits.h" #include #include #include namespace llvm { template class StringMapIterBase; template class StringMapKeyIterator; /// StringMapImpl - This is the base class of StringMap that is shared among /// all of its instantiations. class StringMapImpl : public DebugEpochBase { protected: // Array of NumBuckets pointers to entries, null pointers are holes. // TheTable[NumBuckets] contains a sentinel value for easy iteration. Followed // by an array of the actual hash values as unsigned integers. StringMapEntryBase **TheTable = nullptr; unsigned NumBuckets = 0; unsigned NumItems = 0; unsigned ItemSize; protected: explicit StringMapImpl(unsigned itemSize) : ItemSize(itemSize) {} StringMapImpl(StringMapImpl &&RHS) : TheTable(RHS.TheTable), NumBuckets(RHS.NumBuckets), NumItems(RHS.NumItems), ItemSize(RHS.ItemSize) { RHS.TheTable = nullptr; RHS.NumBuckets = 0; RHS.NumItems = 0; } LLVM_ABI StringMapImpl(unsigned InitSize, unsigned ItemSize); ~StringMapImpl() { free(TheTable); } LLVM_ABI unsigned RehashTable(unsigned BucketNo = 0); /// 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(StringRef Key) { return LookupBucketFor(Key, hash(Key)); } /// Overload that explicitly takes precomputed hash(Key). LLVM_ABI unsigned LookupBucketFor(StringRef Key, uint32_t FullHashValue); /// 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(StringRef Key) const { return FindKey(Key, hash(Key)); } /// Overload that explicitly takes precomputed hash(Key). LLVM_ABI int FindKey(StringRef Key, uint32_t FullHashValue) const; /// RemoveKey - Remove the specified StringMapEntry from the table, but do not /// delete it. This aborts if the value isn't in the table. LLVM_ABI 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. LLVM_ABI StringMapEntryBase *RemoveKey(StringRef Key); /// Remove the entry pointer at the given (live) bucket without destroying /// the entry, and close the hole via Algorithm R backward shifting. LLVM_ABI void removeBucket(unsigned Bucket); /// Allocate the table with the specified number of buckets and otherwise /// setup the map as empty. LLVM_ABI void init(unsigned Size); iterator_range buckets() { return make_range(TheTable, TheTable + NumBuckets); } public: [[nodiscard]] unsigned getNumBuckets() const { return NumBuckets; } [[nodiscard]] unsigned getNumItems() const { return NumItems; } [[nodiscard]] bool empty() const { return NumItems == 0; } [[nodiscard]] unsigned size() const { return NumItems; } /// Returns the hash value that will be used for the given string. /// This allows precomputing the value and passing it explicitly /// to some of the functions. /// The implementation of this function is not guaranteed to be stable /// and may change. [[nodiscard]] LLVM_ABI static uint32_t hash(StringRef Key); void swap(StringMapImpl &Other) { incrementEpoch(); Other.incrementEpoch(); std::swap(TheTable, Other.TheTable); std::swap(NumBuckets, Other.NumBuckets); std::swap(NumItems, Other.NumItems); } }; /// 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 LLVM_ALLOCATORHOLDER_EMPTYBASE StringMap : public StringMapImpl, private detail::AllocatorHolder { using AllocTy = detail::AllocatorHolder; public: using MapEntryTy = StringMapEntry; StringMap() : StringMapImpl(static_cast(sizeof(MapEntryTy))) {} explicit StringMap(unsigned InitialSize) : StringMapImpl(InitialSize, static_cast(sizeof(MapEntryTy))) {} explicit StringMap(AllocatorTy A) : StringMapImpl(static_cast(sizeof(MapEntryTy))), AllocTy(A) {} StringMap(unsigned InitialSize, AllocatorTy A) : StringMapImpl(InitialSize, static_cast(sizeof(MapEntryTy))), AllocTy(A) {} StringMap(std::initializer_list> List) : StringMapImpl(List.size(), static_cast(sizeof(MapEntryTy))) { insert(List); } StringMap(StringMap &&RHS) : StringMapImpl(std::move(RHS)), AllocTy(std::move(RHS.getAllocator())) {} StringMap(const StringMap &RHS) : StringMapImpl(static_cast(sizeof(MapEntryTy))), AllocTy(RHS.getAllocator()) { if (RHS.empty()) return; // Allocate TheTable of the same size as RHS's TheTable, and set the // sentinel appropriately (and NumBuckets). init(RHS.NumBuckets); unsigned *HashTable = (unsigned *)(TheTable + NumBuckets + 1), *RHSHashTable = (unsigned *)(RHS.TheTable + NumBuckets + 1); NumItems = RHS.NumItems; // Copy the bucket layout verbatim. Preserving each entry's slot keeps // the probe-sequence invariant intact without re-probing. for (unsigned I = 0, E = NumBuckets; I != E; ++I) { StringMapEntryBase *Bucket = RHS.TheTable[I]; if (!Bucket) continue; TheTable[I] = MapEntryTy::create( static_cast(Bucket)->getKey(), getAllocator(), static_cast(Bucket)->getValue()); HashTable[I] = RHSHashTable[I]; } } StringMap &operator=(StringMap RHS) { StringMapImpl::swap(RHS); std::swap(getAllocator(), RHS.getAllocator()); return *this; } ~StringMap() { // Delete all the elements in the map, but don't reset the elements // to default values. This is a copy of clear(), but avoids unnecessary // work not required in the destructor. if (!empty()) { for (StringMapEntryBase *Bucket : buckets()) { if (Bucket) { static_cast(Bucket)->Destroy(getAllocator()); } } } } using AllocTy::getAllocator; using key_type = const char *; using mapped_type = ValueTy; using value_type = StringMapEntry; using size_type = size_t; using const_iterator = StringMapIterBase; using iterator = StringMapIterBase; [[nodiscard]] iterator begin() { return iterator(this, TheTable, NumBuckets != 0); } [[nodiscard]] iterator end() { return iterator(this, TheTable + NumBuckets); } [[nodiscard]] const_iterator begin() const { return const_iterator(this, TheTable, NumBuckets != 0); } [[nodiscard]] const_iterator end() const { return const_iterator(this, TheTable + NumBuckets); } [[nodiscard]] iterator_range> keys() const { return make_range(StringMapKeyIterator(begin()), StringMapKeyIterator(end())); } [[nodiscard]] iterator find(StringRef Key) { return find(Key, hash(Key)); } [[nodiscard]] iterator find(StringRef Key, uint32_t FullHashValue) { int Bucket = FindKey(Key, FullHashValue); if (Bucket == -1) return end(); return iterator(this, TheTable + Bucket); } [[nodiscard]] const_iterator find(StringRef Key) const { return find(Key, hash(Key)); } [[nodiscard]] const_iterator find(StringRef Key, uint32_t FullHashValue) const { int Bucket = FindKey(Key, FullHashValue); if (Bucket == -1) return end(); return const_iterator(this, TheTable + Bucket); } /// lookup - Return the entry for the specified key, or a default /// constructed value if no such entry exists. [[nodiscard]] ValueTy lookup(StringRef Key) const { const_iterator Iter = find(Key); if (Iter != end()) return Iter->second; return ValueTy(); } /// at - Return the entry for the specified key, or abort if no such /// entry exists. [[nodiscard]] const ValueTy &at(StringRef Val) const { auto Iter = this->find(Val); assert(Iter != this->end() && "StringMap::at failed due to a missing key"); return Iter->second; } /// Lookup the ValueTy for the \p Key, or create a default constructed value /// if the key is not in the map. ValueTy &operator[](StringRef Key) { return try_emplace(Key).first->second; } /// contains - Return true if the element is in the map, false otherwise. [[nodiscard]] bool contains(StringRef Key) const { return find(Key) != end(); } /// count - Return 1 if the element is in the map, 0 otherwise. [[nodiscard]] size_type count(StringRef Key) const { return contains(Key) ? 1 : 0; } template [[nodiscard]] size_type count(const StringMapEntry &MapEntry) const { return count(MapEntry.getKey()); } /// equal - check whether both of the containers are equal. [[nodiscard]] bool operator==(const StringMap &RHS) const { if (size() != RHS.size()) return false; for (const auto &KeyValue : *this) { auto FindInRHS = RHS.find(KeyValue.getKey()); if (FindInRHS == RHS.end()) return false; if constexpr (!std::is_same_v) { if (!(KeyValue.getValue() == FindInRHS->getValue())) return false; } } return true; } [[nodiscard]] bool operator!=(const StringMap &RHS) const { return !(*this == RHS); } /// 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->getKey()); StringMapEntryBase *&Bucket = TheTable[BucketNo]; if (Bucket) return false; // Already exists in map. incrementEpoch(); Bucket = KeyValue; ++NumItems; assert(NumItems <= NumBuckets); RehashTable(); return true; } /// insert - Inserts the specified key/value pair into the map if the key /// isn't already in the map. The bool component of the returned pair is true /// if and only if the insertion takes place, and the iterator component of /// the pair points to the element with key equivalent to the key of the pair. std::pair insert(std::pair KV) { return try_emplace_with_hash(KV.first, hash(KV.first), std::move(KV.second)); } std::pair insert(std::pair KV, uint32_t FullHashValue) { return try_emplace_with_hash(KV.first, FullHashValue, std::move(KV.second)); } /// Inserts elements from range [first, last). If multiple elements in the /// range have keys that compare equivalent, it is unspecified which element /// is inserted . template void insert(InputIt First, InputIt Last) { for (InputIt It = First; It != Last; ++It) insert(*It); } /// Inserts elements from initializer list ilist. If multiple elements in /// the range have keys that compare equivalent, it is unspecified which /// element is inserted void insert(std::initializer_list> List) { insert(List.begin(), List.end()); } /// Inserts an element or assigns to the current element if the key already /// exists. The return type is the same as try_emplace. template std::pair insert_or_assign(StringRef Key, V &&Val) { auto Ret = try_emplace(Key, std::forward(Val)); if (!Ret.second) Ret.first->second = std::forward(Val); return Ret; } /// Emplace a new element for the specified key into the map if the key isn't /// already in the map. The bool component of the returned pair is true /// if and only if the insertion takes place, and the iterator component of /// the pair points to the element with key equivalent to the key of the pair. template std::pair try_emplace(StringRef Key, ArgsTy &&...Args) { return try_emplace_with_hash(Key, hash(Key), std::forward(Args)...); } template std::pair try_emplace_with_hash(StringRef Key, uint32_t FullHashValue, ArgsTy &&...Args) { unsigned BucketNo = LookupBucketFor(Key, FullHashValue); StringMapEntryBase *&Bucket = TheTable[BucketNo]; if (Bucket) return {iterator(this, TheTable + BucketNo), false}; // Already in map. incrementEpoch(); Bucket = MapEntryTy::create(Key, getAllocator(), std::forward(Args)...); ++NumItems; assert(NumItems <= NumBuckets); BucketNo = RehashTable(BucketNo); return {iterator(this, TheTable + BucketNo), true}; } // clear - Empties out the StringMap void clear() { incrementEpoch(); if (empty()) return; // Zap all values, resetting the keys back to non-present, which is safe // because we're removing all elements. for (StringMapEntryBase *&Bucket : buckets()) { if (Bucket) { static_cast(Bucket)->Destroy(getAllocator()); } Bucket = nullptr; } NumItems = 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) { incrementEpoch(); RemoveKey(KeyValue); } void erase(iterator I) { MapEntryTy &V = *I; remove(&V); V.Destroy(getAllocator()); } bool erase(StringRef Key) { iterator I = find(Key); if (I == end()) return false; erase(I); return true; } /// Remove entries that match the given predicate. \p Pred is invoked with a /// reference to each live entry and must not access the map being modified. /// This is the safe replacement for erase-while-iterating. /// /// Returns whether anything was removed. If so, all iterators and references /// into the map are invalidated. template bool remove_if(Predicate Pred) { bool Removed = false; for (unsigned I = 0; I != NumBuckets;) { StringMapEntryBase *Bucket = TheTable[I]; if (!Bucket) { ++I; continue; } auto *Entry = static_cast(Bucket); if (!Pred(*Entry)) { ++I; continue; } Entry->Destroy(getAllocator()); // This may relocate a following entry into this slot to close the hole, // so re-examine the same index rather than advancing past it. removeBucket(I); Removed = true; } if (Removed) incrementEpoch(); return Removed; } }; template class StringMapIterBase : DebugEpochBase::HandleBase { friend class StringMapIterBase; friend class StringMapIterBase; StringMapEntryBase **Ptr = nullptr; public: using iterator_category = std::forward_iterator_tag; using value_type = StringMapEntry; using difference_type = std::ptrdiff_t; using pointer = std::conditional_t; using reference = std::conditional_t; StringMapIterBase() = default; explicit StringMapIterBase(const DebugEpochBase *Epoch, StringMapEntryBase **Bucket, bool Advance = false) : DebugEpochBase::HandleBase(Epoch), Ptr(Bucket) { if (Advance) AdvancePastEmptyBuckets(); } // Converting ctor from non-const to const iterators. SFINAE'd out for const // sources so it doesn't shadow the implicit copy constructor. template > StringMapIterBase(const StringMapIterBase &I) : DebugEpochBase::HandleBase(I), Ptr(I.Ptr) {} [[nodiscard]] reference operator*() const { assert(isHandleInSync() && "invalid iterator access!"); return *static_cast(*Ptr); } [[nodiscard]] pointer operator->() const { assert(isHandleInSync() && "invalid iterator access!"); return static_cast(*Ptr); } StringMapIterBase &operator++() { // Preincrement assert(isHandleInSync() && "invalid iterator access!"); ++Ptr; AdvancePastEmptyBuckets(); return *this; } StringMapIterBase operator++(int) { // Post-increment StringMapIterBase Tmp(*this); ++*this; return Tmp; } friend bool operator==(const StringMapIterBase &LHS, const StringMapIterBase &RHS) { assert((!LHS.getEpochAddress() || LHS.isHandleInSync()) && "handle not in sync!"); assert((!RHS.getEpochAddress() || RHS.isHandleInSync()) && "handle not in sync!"); return LHS.Ptr == RHS.Ptr; } friend bool operator!=(const StringMapIterBase &LHS, const StringMapIterBase &RHS) { return !(LHS == RHS); } private: void AdvancePastEmptyBuckets() { while (*Ptr == nullptr) ++Ptr; } }; template class StringMapKeyIterator : public iterator_adaptor_base, StringMapIterBase, std::forward_iterator_tag, StringRef> { using base = iterator_adaptor_base, StringMapIterBase, std::forward_iterator_tag, StringRef>; public: StringMapKeyIterator() = default; explicit StringMapKeyIterator(StringMapIterBase Iter) : base(std::move(Iter)) {} StringRef operator*() const { return this->wrapped()->getKey(); } }; } // end namespace llvm #endif // LLVM_ADT_STRINGMAP_H