diff options
| author | _ov4 <hausemasterstream@gmail.com> | 2026-01-30 13:11:20 +0000 |
|---|---|---|
| committer | _ov4 <hausemasterstream@gmail.com> | 2026-01-30 13:11:20 +0000 |
| commit | bd799e42b40613983c6e3cb9aedf58866ac68605 (patch) | |
| tree | 03fdd0dffba45fa2a1d9b8d4b0e78f49140c07e5 /lib | |
| parent | 80420b0f92f42edc0a3cac4490a08adb8b2457dc (diff) | |
Added FUNCTION and PROCEDURE
Diffstat (limited to 'lib')
| -rw-r--r-- | lib/CodeGen/CodeGen.cc | 42 | ||||
| -rw-r--r-- | lib/CodeGen/FunctionGen.cc | 125 | ||||
| -rw-r--r-- | lib/Lexer/Lexer.cc | 20 | ||||
| -rw-r--r-- | lib/Parser/Parser.cc | 49 | ||||
| -rw-r--r-- | lib/Parser/Parser_Function.cc | 129 |
5 files changed, 354 insertions, 11 deletions
diff --git a/lib/CodeGen/CodeGen.cc b/lib/CodeGen/CodeGen.cc index 9dc88af..6358699 100644 --- a/lib/CodeGen/CodeGen.cc +++ b/lib/CodeGen/CodeGen.cc @@ -17,6 +17,8 @@ CodeGen::CodeGen() { Arrays = std::make_unique<ArrayHandler>(*TheContext, *Builder, *TheModule, NamedValues, *RuntimeChecker); + FuncGen = std::make_unique<FunctionGen>(*TheContext, *TheModule, *Builder, NamedValues); + SetupExternalFunctions(); } @@ -105,6 +107,15 @@ Value *CodeGen::emitExpr(ExprAST *Expr) { return nullptr; } } + + if (auto *Call = dynamic_cast<CallExprAST*>(Expr)) { + std::vector<Value*> Args; + for (const auto &Arg : Call->getArgs()) { + Args.push_back(emitExpr(Arg.get())); + } + return FuncGen->emitCallExpr(Call, Args); + } + return nullptr; } @@ -261,6 +272,36 @@ void CodeGen::emitStmt(StmtAST *Stmt) { return; } + if (auto *FuncDef = dynamic_cast<FunctionDefAST*>(Stmt)) { + BasicBlock *SavedBlock = Builder->GetInsertBlock(); + + FuncGen->emitFunctionDef(FuncDef, [this](StmtAST *S) { + this->emitStmt(S); + }); + + if (SavedBlock) Builder->SetInsertPoint(SavedBlock); + + return; + } + + else if (auto *Call = dynamic_cast<CallStmtAST*>(Stmt)) { + std::vector<Value*> Args; + for (const auto &ArgExpr : Call->getArgs()) { + Args.push_back(emitExpr(ArgExpr.get())); + } + FuncGen->emitCallStmt(Call, Args); + return; + } + + else if (auto *Ret = dynamic_cast<ReturnStmtAST*>(Stmt)) { + Value *RetVal = nullptr; + if (Ret->getRetVal()) { + RetVal = emitExpr(Ret->getRetVal()); + } + FuncGen->emitReturn(Ret, RetVal); + return; + } + if (auto *Decl = dynamic_cast<DeclareStmtAST*>(Stmt)) { Function *TheFunction = Builder->GetInsertBlock()->getParent(); AllocaInst *Alloca = CreateEntryBlockAlloca(TheFunction, Decl->getName()); @@ -313,4 +354,3 @@ void CodeGen::emitStmt(StmtAST *Stmt) { emitForStmt(ForStmt); } } - diff --git a/lib/CodeGen/FunctionGen.cc b/lib/CodeGen/FunctionGen.cc new file mode 100644 index 0000000..b2adc08 --- /dev/null +++ b/lib/CodeGen/FunctionGen.cc @@ -0,0 +1,125 @@ +#include "cps/FunctionGen.h" +#include "llvm/IR/Verifier.h" +#include <iostream> + +using namespace llvm; +using namespace cps; + +Type *FunctionGen::getLLVMType(const std::string &TypeName) { + if (TypeName == "INTEGER") return Type::getInt64Ty(Context); + if (TypeName == "BOOLEAN") return Type::getInt1Ty(Context); + if (TypeName == "REAL") return Type::getDoubleTy(Context); + if (TypeName == "VOID") return Type::getVoidTy(Context); + return Type::getInt64Ty(Context); +} + +void FunctionGen::createArgumentAllocas(Function *F, const std::vector<std::pair<std::string, std::string>> &Args) { + Function::arg_iterator AI = F->arg_begin(); + for (unsigned Idx = 0, E = Args.size(); Idx != E; ++Idx, ++AI) { + std::string ArgName = Args[Idx].first; + std::string ArgTypeStr = Args[Idx].second; + + Type *ArgType = getLLVMType(ArgTypeStr); + IRBuilder<> TmpB(&F->getEntryBlock(), F->getEntryBlock().begin()); + AllocaInst *Alloca = TmpB.CreateAlloca(ArgType, nullptr, ArgName); + + Value *ArgVal = &(*AI); + Builder.CreateStore(ArgVal, Alloca); + + NamedValues[ArgName] = Alloca; + } +} + +Function *FunctionGen::emitPrototype(PrototypeAST *Proto) { + std::vector<Type*> ArgTypes; + for (const auto &Arg : Proto->getArgs()) { + ArgTypes.push_back(getLLVMType(Arg.second)); + } + + Type *RetType = getLLVMType(Proto->getReturnType()); + FunctionType *FT = FunctionType::get(RetType, ArgTypes, false); + Function *F = Function::Create(FT, Function::ExternalLinkage, Proto->getName(), &Module); + + unsigned Idx = 0; + for (auto &Arg : F->args()) { + if (Idx < Proto->getArgs().size()) + Arg.setName(Proto->getArgs()[Idx++].first); + } + return F; +} + +Function *FunctionGen::emitFunctionDef(FunctionDefAST *FuncAST, + const std::function<void(StmtAST*)> &StmtEmitter) { + PrototypeAST *Proto = FuncAST->getProto(); + Function *TheFunction = Module.getFunction(Proto->getName()); + + if (!TheFunction) + TheFunction = emitPrototype(Proto); + + if (!TheFunction) return nullptr; + if (!TheFunction->empty()) { + fprintf(stderr, "Error: Function %s cannot be redefined.\n", Proto->getName().c_str()); + return nullptr; + } + + BasicBlock *BB = BasicBlock::Create(Context, "entry", TheFunction); + Builder.SetInsertPoint(BB); + + std::map<std::string, llvm::AllocaInst*> OldNamedValues = NamedValues; + NamedValues.clear(); + + createArgumentAllocas(TheFunction, Proto->getArgs()); + + for (const auto &Stmt : FuncAST->getBody()) { + StmtEmitter(Stmt.get()); + } + + if (!Builder.GetInsertBlock()->getTerminator()) { + if (Proto->getReturnType() == "VOID") + Builder.CreateRetVoid(); + else + Builder.CreateRet(Constant::getNullValue(TheFunction->getReturnType())); + } + + verifyFunction(*TheFunction); + NamedValues = OldNamedValues; + return TheFunction; +} + +static Value *GenerateCall(llvm::Module &Module, llvm::IRBuilder<> &Builder, llvm::LLVMContext &Context, + const std::string &CalleeName, const std::vector<llvm::Value*> &Args) { + Function *CalleeF = Module.getFunction(CalleeName); + if (!CalleeF) { + std::vector<Type*> ArgTypes; + for (auto *Val : Args) ArgTypes.push_back(Val->getType()); + FunctionType *FT = FunctionType::get(Type::getInt64Ty(Context), ArgTypes, false); + CalleeF = Function::Create(FT, Function::ExternalLinkage, CalleeName, &Module); + } + + if (CalleeF->arg_size() != Args.size()) { + fprintf(stderr, "Error: Incorrect # arguments passed to %s\n", CalleeName.c_str()); + return nullptr; + } + + if (CalleeF->getReturnType()->isVoidTy()) { + return Builder.CreateCall(CalleeF, Args); + } + + return Builder.CreateCall(CalleeF, Args, "calltmp"); +} + +llvm::Value *FunctionGen::emitCallExpr(CallExprAST *Call, const std::vector<llvm::Value*> &Args) { + return GenerateCall(Module, Builder, Context, Call->getCallee(), Args); +} + +void FunctionGen::emitCallStmt(CallStmtAST *Call, const std::vector<llvm::Value*> &Args) { + GenerateCall(Module, Builder, Context, Call->getCallee(), Args); +} + +void FunctionGen::emitReturn(ReturnStmtAST *Ret, llvm::Value *RetVal) { + if (RetVal) { + Builder.CreateRet(RetVal); + } else { + Builder.CreateRetVoid(); + } +} diff --git a/lib/Lexer/Lexer.cc b/lib/Lexer/Lexer.cc index 51e27dd..6854cc9 100644 --- a/lib/Lexer/Lexer.cc +++ b/lib/Lexer/Lexer.cc @@ -21,6 +21,9 @@ int Lexer::gettok() { if (IdentifierStr == "DECLARE") return tok_declare; if (IdentifierStr == "INTEGER") return tok_integer_kw; + if (IdentifierStr == "BOOLEAN") return tok_integer_kw; // TODO: implement real BOOLEAN + if (IdentifierStr == "REAL") return tok_integer_kw; // TODO: implement real REAL + if (IdentifierStr == "INPUT") return tok_input; if (IdentifierStr == "OUTPUT") return tok_output; @@ -44,6 +47,14 @@ int Lexer::gettok() { if (IdentifierStr == "ARRAY") return tok_array; if (IdentifierStr == "OF") return tok_of; + if (IdentifierStr == "FUNCTION") return tok_function; + if (IdentifierStr == "ENDFUNCTION") return tok_endfunction; + if (IdentifierStr == "PROCEDURE") return tok_procedure; + if (IdentifierStr == "ENDPROCEDURE") return tok_endprocedure; + if (IdentifierStr == "RETURN") return tok_return; + if (IdentifierStr == "RETURNS") return tok_returns; + if (IdentifierStr == "CALL") return tok_call; + return tok_identifier; } @@ -93,6 +104,15 @@ int Lexer::gettok() { return tok_colon; } + if (LastChar == '(') { LastChar = getchar(); return '('; } + if (LastChar == ')') { LastChar = getchar(); return ')'; } + if (LastChar == '[') { LastChar = getchar(); return '['; } + if (LastChar == ']') { LastChar = getchar(); return ']'; } + if (LastChar == ',') { LastChar = getchar(); return ','; } + if (LastChar == '+') { LastChar = getchar(); return '+'; } + if (LastChar == '-') { LastChar = getchar(); return '-'; } + if (LastChar == '*') { LastChar = getchar(); return '*'; } + if (LastChar == '/') { int NextChar = getchar(); if (NextChar == '/') { diff --git a/lib/Parser/Parser.cc b/lib/Parser/Parser.cc index b9396ce..563dd9b 100644 --- a/lib/Parser/Parser.cc +++ b/lib/Parser/Parser.cc @@ -1,4 +1,5 @@ #include "cps/Parser.h" +#include "cps/FunctionAST.h" using namespace cps; @@ -40,24 +41,40 @@ std::unique_ptr<ExprAST> Parser::ParseIdentifierExpr() { std::string IdName = Lex.IdentifierStr; int Line = Lex.getLine(); getNextToken(); + + if (CurTok == '(') { + getNextToken(); + std::vector<std::unique_ptr<ExprAST>> Args; + if (CurTok != ')') { + while (true) { + if (auto Arg = ParseExpression()) + Args.push_back(std::move(Arg)); + else + return nullptr; + + if (CurTok == ')') break; + + if (CurTok != ',') { + fprintf(stderr, "Error: Expected ')' or ',' in function call.\n"); + return nullptr; + } + getNextToken(); + } + } + getNextToken(); + return std::make_unique<CallExprAST>(IdName, std::move(Args)); + } if (CurTok == '[') { getNextToken(); std::vector<std::unique_ptr<ExprAST>> Indices; - while (true) { auto Exp = ParseExpression(); if (!Exp) return nullptr; Indices.push_back(std::move(Exp)); - - if (CurTok == ']') { - break; - } - if (CurTok == ',') { - getNextToken(); - continue; - } - fprintf(stderr, "Error: Expected ',' or ']' in array index\n"); + if (CurTok == ']') break; + if (CurTok == ',') { getNextToken(); continue; } + fprintf(stderr, "Error: Expected ',' or ']'\n"); return nullptr; } getNextToken(); @@ -407,6 +424,18 @@ std::unique_ptr<StmtAST> Parser::ParseStatement() { else if (CurTok == tok_for) { return ParseForStmt(); } + else if (CurTok == tok_function) { + return ParseFunction(); + } + else if (CurTok == tok_procedure) { + return ParseProcedure(); + } + else if (CurTok == tok_call) { + return ParseCallStmt(); + } + else if (CurTok == tok_return) { + return ParseReturnStmt(); + } return nullptr; } diff --git a/lib/Parser/Parser_Function.cc b/lib/Parser/Parser_Function.cc new file mode 100644 index 0000000..bdb4ee7 --- /dev/null +++ b/lib/Parser/Parser_Function.cc @@ -0,0 +1,129 @@ +#include "cps/Parser.h" +#include "cps/FunctionAST.h" + +using namespace cps; + +std::vector<std::pair<std::string, std::string>> Parser::ParsePrototypeArgs() { + std::vector<std::pair<std::string, std::string>> Args; + if (CurTok != '(') return Args; + getNextToken(); + + while (CurTok != ')') { + if (CurTok == -1000 || CurTok == -1001) getNextToken(); + + if (CurTok != tok_identifier) { + fprintf(stderr, "Error: Expected argument name\n"); + return Args; + } + std::string Name = Lex.IdentifierStr; + getNextToken(); + + if (CurTok != tok_colon) { + fprintf(stderr, "Error: Expected ':' after argument name\n"); + return Args; + } + getNextToken(); + + std::string Type = "INTEGER"; + if (CurTok == tok_integer_kw) { + getNextToken(); + } else if (CurTok == tok_identifier) { + Type = Lex.IdentifierStr; + getNextToken(); + } else { + fprintf(stderr, "Error: Expected type (e.g. INTEGER) for argument '%s'\n", Name.c_str()); + return Args; + } + + Args.push_back({Name, Type}); + + if (CurTok == ')') break; + if (CurTok != ',') { + fprintf(stderr, "Error: Expected ',' or ')'\n"); + return Args; + } + getNextToken(); + } + getNextToken(); + return Args; +} + + +std::unique_ptr<StmtAST> Parser::ParseFunction() { + getNextToken(); + std::string Name = Lex.IdentifierStr; + getNextToken(); + + auto Args = ParsePrototypeArgs(); + + std::string RetType = "INTEGER"; + if (CurTok == tok_returns) { + getNextToken(); + getNextToken(); + } + + auto Proto = std::make_unique<PrototypeAST>(Name, std::move(Args), RetType); + + std::vector<std::unique_ptr<StmtAST>> Body; + while (CurTok != tok_endfunction && CurTok != tok_eof) { + auto Stmt = ParseStatement(); + if (Stmt) Body.push_back(std::move(Stmt)); + else if (CurTok != tok_eof && CurTok != tok_endfunction) getNextToken(); + } + getNextToken(); + + return std::make_unique<FunctionDefAST>(std::move(Proto), std::move(Body)); +} + +std::unique_ptr<StmtAST> Parser::ParseProcedure() { + getNextToken(); + std::string Name = Lex.IdentifierStr; + getNextToken(); + + auto Args = ParsePrototypeArgs(); + auto Proto = std::make_unique<PrototypeAST>(Name, std::move(Args), "VOID"); + + std::vector<std::unique_ptr<StmtAST>> Body; + while (CurTok != tok_endprocedure && CurTok != tok_eof) { + auto Stmt = ParseStatement(); + if (Stmt) Body.push_back(std::move(Stmt)); + else if (CurTok != tok_eof && CurTok != tok_endprocedure) getNextToken(); + } + getNextToken(); + + return std::make_unique<FunctionDefAST>(std::move(Proto), std::move(Body)); +} + +std::unique_ptr<StmtAST> Parser::ParseCallStmt() { + getNextToken(); + std::string Callee = Lex.IdentifierStr; + getNextToken(); + + std::vector<std::unique_ptr<ExprAST>> Args; + if (CurTok == '(') { + getNextToken(); + while (CurTok != ')') { + auto Arg = ParseExpression(); + if (Arg) Args.push_back(std::move(Arg)); + + if (CurTok == ')') break; + if (CurTok != ',') { + fprintf(stderr, "Error: Expected ',' or ')' in call\n"); + return nullptr; + } + getNextToken(); + } + getNextToken(); + } + + return std::make_unique<CallStmtAST>(Callee, std::move(Args)); +} + +std::unique_ptr<StmtAST> Parser::ParseReturnStmt() { + getNextToken(); + std::unique_ptr<ExprAST> Expr = nullptr; + if (CurTok != tok_endif && CurTok != tok_else && CurTok != tok_endfunction && CurTok != tok_endprocedure) { + Expr = ParseExpression(); + } + return std::make_unique<ReturnStmtAST>(std::move(Expr)); +} |
