diff --git a/llvm/include/llvm/Support/Automaton.h b/llvm/include/llvm/Support/Automaton.h --- a/llvm/include/llvm/Support/Automaton.h +++ b/llvm/include/llvm/Support/Automaton.h @@ -154,12 +154,26 @@ }; } // namespace internal +// Type representing a transition in the DFA state. +// The action type can be a custom type. +template struct TransitionType { + using StateT = unsigned; + StateT FromDfaState; // The transitioned-from DFA state. + ActionT Action; // The input symbol that causes this transition. + StateT ToDfaState; // The transitioned-to DFA state. + unsigned InfoIdx; // Start index into TransitionInfo. +}; + /// A deterministic finite-state automaton. The automaton is defined in /// TableGen; this object drives an automaton defined by tblgen-emitted tables. /// /// An automaton accepts a sequence of input tokens ("actions"). This class is /// templated on the type of these actions. template class Automaton { + using TransitionT = TransitionType; + using TransitionKeyT = std::pair; + using StateT = typename TransitionT::StateT; /// Map from {State, Action} to {NewState, TransitionInfoIdx}. /// TransitionInfoIdx is used by the DfaTranscriber to analyze the transition. /// FIXME: This uses a std::map because ActionT can be a pair type including @@ -167,16 +181,20 @@ /// DenseMap here. /// This is a shared_ptr to allow very quick copy-construction of Automata; this /// state is immutable after construction so this is safe. - using MapTy = std::map, std::pair>; - std::shared_ptr M; + ArrayRef TransitionMap; /// An optional transcription object. This uses much more state than simply /// traversing the DFA for acceptance, so is heap allocated. std::shared_ptr Transcriber; /// The initial DFA state is 1. - uint64_t State = 1; + StateT State = 1; /// True if we should transcribe and false if not (even if Transcriber is defined). bool Transcribe; + static bool transitionLessThan(const TransitionT &A, + const TransitionKeyT &B) { + return std::make_pair(A.FromDfaState, A.Action) < B; + } + public: /// Create an automaton. /// \param Transitions The Transitions table as created by TableGen. Note that @@ -189,21 +207,24 @@ /// NFA taken by the DFA. NOTE: This is substantially more work than simply /// driving the DFA, so unless you require the getPaths() method leave this /// empty. - template - Automaton(ArrayRef Transitions, + Automaton(ArrayRef Transitions, ArrayRef TranscriptionTable = {}) { if (!TranscriptionTable.empty()) Transcriber = std::make_shared(TranscriptionTable); Transcribe = Transcriber != nullptr; - M = std::make_shared(); - for (const auto &I : Transitions) - // Greedily read and cache the transition table. - M->emplace(std::make_pair(I.FromDfaState, I.Action), - std::make_pair(I.ToDfaState, I.InfoIdx)); + TransitionMap = Transitions; + assert(std::is_sorted(TransitionMap.begin(), TransitionMap.end(), + [](const TransitionT &A, const TransitionT &B) { + return std::make_pair(A.FromDfaState, A.Action) < + std::make_pair(B.FromDfaState, B.Action); + }) && + "The transitions array is expected to be sorted by FromDfaState and " + "Action"); } Automaton(const Automaton &Other) - : M(Other.M), State(Other.State), Transcribe(Other.Transcribe) { + : TransitionMap(Other.TransitionMap), State(Other.State), + Transcribe(Other.Transcribe) { // Transcriber is not thread-safe, so create a new instance on copy. if (Other.Transcriber) Transcriber = std::make_shared( @@ -233,19 +254,22 @@ /// If this function returns false, all methods are undefined until reset() is /// called. bool add(const ActionT &A) { - auto I = M->find({State, A}); - if (I == M->end()) + auto I = lower_bound(TransitionMap.begin(), TransitionMap.end(), + std::make_pair(State, A), transitionLessThan); + if (I == TransitionMap.end() || State != I->FromDfaState || A != I->Action) return false; if (Transcriber && Transcribe) - Transcriber->transition(I->second.second); - State = I->second.first; + Transcriber->transition(I->InfoIdx); + State = I->ToDfaState; return true; } /// Return true if the automaton can be transitioned based on input symbol A. bool canAdd(const ActionT &A) { - auto I = M->find({State, A}); - return I != M->end(); + auto I = lower_bound(TransitionMap.begin(), TransitionMap.end(), + std::make_pair(State, A), transitionLessThan); + return I != TransitionMap.end() && State == I->FromDfaState && + A == I->Action; } /// Obtain a set of possible paths through the input nondeterministic diff --git a/llvm/utils/TableGen/DFAEmitter.cpp b/llvm/utils/TableGen/DFAEmitter.cpp --- a/llvm/utils/TableGen/DFAEmitter.cpp +++ b/llvm/utils/TableGen/DFAEmitter.cpp @@ -131,15 +131,9 @@ OS << "}};\n\n"; OS << "// A transition in the generated " << Name << " DFA.\n"; - OS << "struct " << Name << "Transition {\n"; - OS << " unsigned FromDfaState; // The transitioned-from DFA state.\n"; - OS << " "; + OS << "using " << Name << "Transition = TransitionType<"; printActionType(OS); - OS << " Action; // The input symbol that causes this transition.\n"; - OS << " unsigned ToDfaState; // The transitioned-to DFA state.\n"; - OS << " unsigned InfoIdx; // Start index into " << Name - << "TransitionInfo.\n"; - OS << "};\n\n"; + OS << ">;\n\n"; OS << "// A table of DFA transitions, ordered by {FromDfaState, Action}.\n"; OS << "// The initial state is 1, not zero.\n";