Initial commit from sysy-main

This commit is contained in:
Lixuanwang
2025-02-27 23:14:53 +08:00
commit cc523fd30b
1125 changed files with 257793 additions and 0 deletions

View File

@@ -0,0 +1,115 @@
/* Copyright (c) 2012-2017 The ANTLR Project. All rights reserved.
* Use of this file is governed by the BSD 3-clause license that
* can be found in the LICENSE.txt file in the project root.
*/
#include "dfa/DFASerializer.h"
#include "dfa/LexerDFASerializer.h"
#include "support/CPPUtils.h"
#include "atn/StarLoopEntryState.h"
#include "atn/ATNConfigSet.h"
#include "support/Casts.h"
#include "dfa/DFA.h"
using namespace antlr4;
using namespace antlr4::dfa;
using namespace antlrcpp;
DFA::DFA(atn::DecisionState *atnStartState) : DFA(atnStartState, 0) {
}
DFA::DFA(atn::DecisionState *atnStartState, size_t decision)
: atnStartState(atnStartState), s0(nullptr), decision(decision) {
_precedenceDfa = false;
if (atn::StarLoopEntryState::is(atnStartState)) {
if (downCast<atn::StarLoopEntryState*>(atnStartState)->isPrecedenceDecision) {
_precedenceDfa = true;
s0 = new DFAState(std::unique_ptr<atn::ATNConfigSet>(new atn::ATNConfigSet()));
s0->isAcceptState = false;
s0->requiresFullContext = false;
}
}
}
DFA::DFA(DFA &&other) : atnStartState(other.atnStartState), s0(other.s0), decision(other.decision) {
// Source states are implicitly cleared by the move.
states = std::move(other.states);
other.atnStartState = nullptr;
other.decision = 0;
other.s0 = nullptr;
_precedenceDfa = other._precedenceDfa;
other._precedenceDfa = false;
}
DFA::~DFA() {
bool s0InList = (s0 == nullptr);
for (auto *state : states) {
if (state == s0)
s0InList = true;
delete state;
}
if (!s0InList) {
delete s0;
}
}
bool DFA::isPrecedenceDfa() const {
return _precedenceDfa;
}
DFAState* DFA::getPrecedenceStartState(int precedence) const {
assert(_precedenceDfa); // Only precedence DFAs may contain a precedence start state.
auto iterator = s0->edges.find(precedence);
if (iterator == s0->edges.end())
return nullptr;
return iterator->second;
}
void DFA::setPrecedenceStartState(int precedence, DFAState *startState) {
if (!isPrecedenceDfa()) {
throw IllegalStateException("Only precedence DFAs may contain a precedence start state.");
}
if (precedence < 0) {
return;
}
s0->edges[precedence] = startState;
}
std::vector<DFAState *> DFA::getStates() const {
std::vector<DFAState *> result;
for (auto *state : states)
result.push_back(state);
std::sort(result.begin(), result.end(), [](DFAState *o1, DFAState *o2) -> bool {
return o1->stateNumber < o2->stateNumber;
});
return result;
}
std::string DFA::toString(const Vocabulary &vocabulary) const {
if (s0 == nullptr) {
return "";
}
DFASerializer serializer(this, vocabulary);
return serializer.toString();
}
std::string DFA::toLexerString() const {
if (s0 == nullptr) {
return "";
}
LexerDFASerializer serializer(this);
return serializer.toString();
}

View File

@@ -0,0 +1,96 @@
/* Copyright (c) 2012-2017 The ANTLR Project. All rights reserved.
* Use of this file is governed by the BSD 3-clause license that
* can be found in the LICENSE.txt file in the project root.
*/
#pragma once
#include "dfa/DFAState.h"
namespace antlr4 {
namespace dfa {
class ANTLR4CPP_PUBLIC DFA final {
private:
struct DFAStateHasher final {
size_t operator()(const DFAState *dfaState) const {
return dfaState->hashCode();
}
};
struct DFAStateComparer final {
bool operator()(const DFAState *lhs, const DFAState *rhs) const {
return lhs == rhs || *lhs == *rhs;
}
};
public:
/// A set of all DFA states. Use a map so we can get old state back.
/// Set only allows you to see if it's there.
/// From which ATN state did we create this DFA?
atn::DecisionState *atnStartState;
std::unordered_set<DFAState*, DFAStateHasher, DFAStateComparer> states; // States are owned by this class.
DFAState *s0;
size_t decision;
explicit DFA(atn::DecisionState *atnStartState);
DFA(atn::DecisionState *atnStartState, size_t decision);
DFA(const DFA &other) = delete;
DFA(DFA &&other);
~DFA();
/**
* Gets whether this DFA is a precedence DFA. Precedence DFAs use a special
* start state {@link #s0} which is not stored in {@link #states}. The
* {@link DFAState#edges} array for this start state contains outgoing edges
* supplying individual start states corresponding to specific precedence
* values.
*
* @return {@code true} if this is a precedence DFA; otherwise,
* {@code false}.
* @see Parser#getPrecedence()
*/
bool isPrecedenceDfa() const;
/**
* Get the start state for a specific precedence value.
*
* @param precedence The current precedence.
* @return The start state corresponding to the specified precedence, or
* {@code null} if no start state exists for the specified precedence.
*
* @throws IllegalStateException if this is not a precedence DFA.
* @see #isPrecedenceDfa()
*/
DFAState* getPrecedenceStartState(int precedence) const;
/**
* Set the start state for a specific precedence value.
*
* @param precedence The current precedence.
* @param startState The start state corresponding to the specified
* precedence.
*
* @throws IllegalStateException if this is not a precedence DFA.
* @see #isPrecedenceDfa()
*/
void setPrecedenceStartState(int precedence, DFAState *startState);
/// Return a list of all states in this DFA, ordered by state number.
std::vector<DFAState *> getStates() const;
std::string toString(const Vocabulary &vocabulary) const;
std::string toLexerString() const;
private:
/**
* {@code true} if this DFA is for a precedence decision; otherwise,
* {@code false}. This is the backing field for {@link #isPrecedenceDfa}.
*/
bool _precedenceDfa;
};
} // namespace atn
} // namespace antlr4

View File

@@ -0,0 +1,60 @@
/* Copyright (c) 2012-2017 The ANTLR Project. All rights reserved.
* Use of this file is governed by the BSD 3-clause license that
* can be found in the LICENSE.txt file in the project root.
*/
#include "dfa/DFA.h"
#include "Vocabulary.h"
#include "dfa/DFASerializer.h"
using namespace antlr4::dfa;
DFASerializer::DFASerializer(const DFA *dfa, const Vocabulary &vocabulary) : _dfa(dfa), _vocabulary(vocabulary) {
}
std::string DFASerializer::toString() const {
if (_dfa->s0 == nullptr) {
return "";
}
std::stringstream ss;
std::vector<DFAState *> states = _dfa->getStates();
for (auto *s : states) {
for (size_t i = 0; i < s->edges.size(); i++) {
DFAState *t = s->edges[i];
if (t != nullptr && t->stateNumber != INT32_MAX) {
ss << getStateString(s);
std::string label = getEdgeLabel(i);
ss << "-" << label << "->" << getStateString(t) << "\n";
}
}
}
return ss.str();
}
std::string DFASerializer::getEdgeLabel(size_t i) const {
return _vocabulary.getDisplayName(i); // ml: no longer needed -1 as we use a map for edges, without offset.
}
std::string DFASerializer::getStateString(DFAState *s) const {
size_t n = s->stateNumber;
const std::string baseStateStr = std::string(s->isAcceptState ? ":" : "") + "s" + std::to_string(n) +
(s->requiresFullContext ? "^" : "");
if (s->isAcceptState) {
if (!s->predicates.empty()) {
std::string buf;
for (size_t i = 0; i < s->predicates.size(); i++) {
buf.append(s->predicates[i].toString());
}
return baseStateStr + "=>" + buf;
} else {
return baseStateStr + "=>" + std::to_string(s->prediction);
}
} else {
return baseStateStr;
}
}

View File

@@ -0,0 +1,32 @@
/* Copyright (c) 2012-2017 The ANTLR Project. All rights reserved.
* Use of this file is governed by the BSD 3-clause license that
* can be found in the LICENSE.txt file in the project root.
*/
#pragma once
#include "Vocabulary.h"
namespace antlr4 {
namespace dfa {
/// A DFA walker that knows how to dump them to serialized strings.
class ANTLR4CPP_PUBLIC DFASerializer {
public:
DFASerializer(const DFA *dfa, const Vocabulary &vocabulary);
virtual ~DFASerializer() = default;
std::string toString() const;
protected:
virtual std::string getEdgeLabel(size_t i) const;
std::string getStateString(DFAState *s) const;
private:
const DFA *_dfa;
const Vocabulary &_vocabulary;
};
} // namespace atn
} // namespace antlr4

View File

@@ -0,0 +1,59 @@
/* Copyright (c) 2012-2017 The ANTLR Project. All rights reserved.
* Use of this file is governed by the BSD 3-clause license that
* can be found in the LICENSE.txt file in the project root.
*/
#include "atn/ATNConfigSet.h"
#include "atn/SemanticContext.h"
#include "atn/ATNConfig.h"
#include "misc/MurmurHash.h"
#include "dfa/DFAState.h"
using namespace antlr4::dfa;
using namespace antlr4::atn;
std::string DFAState::PredPrediction::toString() const {
return std::string("(") + pred->toString() + ", " + std::to_string(alt) + ")";
}
std::set<size_t> DFAState::getAltSet() const {
std::set<size_t> alts;
if (configs != nullptr) {
for (size_t i = 0; i < configs->size(); i++) {
alts.insert(configs->get(i)->alt);
}
}
return alts;
}
size_t DFAState::hashCode() const {
return configs != nullptr ? configs->hashCode() : 0;
}
bool DFAState::equals(const DFAState &other) const {
if (this == std::addressof(other)) {
return true;
}
return configs == other.configs ||
(configs != nullptr && other.configs != nullptr && *configs == *other.configs);
}
std::string DFAState::toString() const {
std::stringstream ss;
ss << stateNumber;
if (configs) {
ss << ":" << configs->toString();
}
if (isAcceptState) {
ss << "=>";
if (!predicates.empty()) {
for (size_t i = 0; i < predicates.size(); i++) {
ss << predicates[i].toString();
}
} else {
ss << prediction;
}
}
return ss.str();
}

View File

@@ -0,0 +1,154 @@
/* Copyright (c) 2012-2017 The ANTLR Project. All rights reserved.
* Use of this file is governed by the BSD 3-clause license that
* can be found in the LICENSE.txt file in the project root.
*/
#pragma once
#include "antlr4-common.h"
#include "atn/ATNConfigSet.h"
#include "FlatHashMap.h"
namespace antlr4 {
namespace dfa {
/// <summary>
/// A DFA state represents a set of possible ATN configurations.
/// As Aho, Sethi, Ullman p. 117 says "The DFA uses its state
/// to keep track of all possible states the ATN can be in after
/// reading each input symbol. That is to say, after reading
/// input a1a2..an, the DFA is in a state that represents the
/// subset T of the states of the ATN that are reachable from the
/// ATN's start state along some path labeled a1a2..an."
/// In conventional NFA->DFA conversion, therefore, the subset T
/// would be a bitset representing the set of states the
/// ATN could be in. We need to track the alt predicted by each
/// state as well, however. More importantly, we need to maintain
/// a stack of states, tracking the closure operations as they
/// jump from rule to rule, emulating rule invocations (method calls).
/// I have to add a stack to simulate the proper lookahead sequences for
/// the underlying LL grammar from which the ATN was derived.
/// <p/>
/// I use a set of ATNConfig objects not simple states. An ATNConfig
/// is both a state (ala normal conversion) and a RuleContext describing
/// the chain of rules (if any) followed to arrive at that state.
/// <p/>
/// A DFA state may have multiple references to a particular state,
/// but with different ATN contexts (with same or different alts)
/// meaning that state was reached via a different set of rule invocations.
/// </summary>
class ANTLR4CPP_PUBLIC DFAState final {
public:
struct ANTLR4CPP_PUBLIC PredPrediction final {
public:
Ref<const atn::SemanticContext> pred; // never null; at least SemanticContext.NONE
int alt;
PredPrediction() = delete;
PredPrediction(const PredPrediction&) = default;
PredPrediction(PredPrediction&&) = default;
PredPrediction(Ref<const atn::SemanticContext> pred, int alt) : pred(std::move(pred)), alt(alt) {}
PredPrediction& operator=(const PredPrediction&) = default;
PredPrediction& operator=(PredPrediction&&) = default;
std::string toString() const;
};
std::unique_ptr<atn::ATNConfigSet> configs;
/// {@code edges[symbol]} points to target of symbol. Shift up by 1 so (-1)
/// <seealso cref="Token#EOF"/> maps to {@code edges[0]}.
// ml: this is a sparse list, so we use a map instead of a vector.
// Watch out: we no longer have the -1 offset, as it isn't needed anymore.
FlatHashMap<size_t, DFAState*> edges;
/// if accept state, what ttype do we match or alt do we predict?
/// This is set to <seealso cref="ATN#INVALID_ALT_NUMBER"/> when <seealso cref="#predicates"/>{@code !=null} or
/// <seealso cref="#requiresFullContext"/>.
size_t prediction = 0;
Ref<const atn::LexerActionExecutor> lexerActionExecutor;
/// <summary>
/// During SLL parsing, this is a list of predicates associated with the
/// ATN configurations of the DFA state. When we have predicates,
/// <seealso cref="#requiresFullContext"/> is {@code false} since full context prediction evaluates predicates
/// on-the-fly. If this is not null, then <seealso cref="#prediction"/> is
/// <seealso cref="ATN#INVALID_ALT_NUMBER"/>.
/// <p/>
/// We only use these for non-<seealso cref="#requiresFullContext"/> but conflicting states. That
/// means we know from the context (it's $ or we don't dip into outer
/// context) that it's an ambiguity not a conflict.
/// <p/>
/// This list is computed by <seealso cref="ParserATNSimulator#predicateDFAState"/>.
/// </summary>
std::vector<PredPrediction> predicates;
int stateNumber = -1;
bool isAcceptState = false;
/// <summary>
/// Indicates that this state was created during SLL prediction that
/// discovered a conflict between the configurations in the state. Future
/// <seealso cref="ParserATNSimulator#execATN"/> invocations immediately jumped doing
/// full context prediction if this field is true.
/// </summary>
bool requiresFullContext = false;
/// Map a predicate to a predicted alternative.
DFAState() = default;
explicit DFAState(int stateNumber) : stateNumber(stateNumber) {}
explicit DFAState(std::unique_ptr<atn::ATNConfigSet> configs) : configs(std::move(configs)) {}
/// <summary>
/// Get the set of all alts mentioned by all ATN configurations in this
/// DFA state.
/// </summary>
std::set<size_t> getAltSet() const;
size_t hashCode() const;
/// Two DFAState instances are equal if their ATN configuration sets
/// are the same. This method is used to see if a state already exists.
///
/// Because the number of alternatives and number of ATN configurations are
/// finite, there is a finite number of DFA states that can be processed.
/// This is necessary to show that the algorithm terminates.
///
/// Cannot test the DFA state numbers here because in
/// ParserATNSimulator#addDFAState we need to know if any other state
/// exists that has this exact set of ATN configurations. The
/// stateNumber is irrelevant.
bool equals(const DFAState &other) const;
std::string toString() const;
};
inline bool operator==(const DFAState &lhs, const DFAState &rhs) {
return lhs.equals(rhs);
}
inline bool operator!=(const DFAState &lhs, const DFAState &rhs) {
return !operator==(lhs, rhs);
}
} // namespace dfa
} // namespace antlr4
namespace std {
template <>
struct hash<::antlr4::dfa::DFAState> {
size_t operator()(const ::antlr4::dfa::DFAState &dfaState) const {
return dfaState.hashCode();
}
};
} // namespace std

View File

@@ -0,0 +1,17 @@
/* Copyright (c) 2012-2017 The ANTLR Project. All rights reserved.
* Use of this file is governed by the BSD 3-clause license that
* can be found in the LICENSE.txt file in the project root.
*/
#include "Vocabulary.h"
#include "dfa/LexerDFASerializer.h"
using namespace antlr4::dfa;
LexerDFASerializer::LexerDFASerializer(const DFA *dfa) : DFASerializer(dfa, Vocabulary()) {
}
std::string LexerDFASerializer::getEdgeLabel(size_t i) const {
return std::string("'") + static_cast<char>(i) + "'";
}

View File

@@ -0,0 +1,22 @@
/* Copyright (c) 2012-2017 The ANTLR Project. All rights reserved.
* Use of this file is governed by the BSD 3-clause license that
* can be found in the LICENSE.txt file in the project root.
*/
#pragma once
#include "dfa/DFASerializer.h"
namespace antlr4 {
namespace dfa {
class ANTLR4CPP_PUBLIC LexerDFASerializer final : public DFASerializer {
public:
explicit LexerDFASerializer(const DFA *dfa);
protected:
std::string getEdgeLabel(size_t i) const override;
};
} // namespace atn
} // namespace antlr4