feat(control-flow): implement ordered CASE OF matching

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

4 files changed, 53 insertions, 7 deletions

diff --git a/include/cps/AST.h b/include/cps/AST.h
index e3c6bc5..87c9341 100644
--- a/include/cps/AST.h
+++ b/include/cps/AST.h
@@ -168,6 +168,22 @@ public:
     const std::vector<std::unique_ptr<ExprAST>> &getExprs() const { return Exprs; }
 };
 
+struct CaseBranch {
+    std::unique_ptr<ExprAST> Lower, Upper; // Null Lower denotes OTHERWISE.
+    std::vector<std::unique_ptr<StmtAST>> Body;
+    int Line;
+};
+
+class CaseStmtAST : public StmtAST {
+    std::string Selector;
+    std::vector<CaseBranch> Branches;
+public:
+    CaseStmtAST(std::string Selector, std::vector<CaseBranch> Branches)
+        : Selector(std::move(Selector)), Branches(std::move(Branches)) {}
+    const std::string &getSelector() const { return Selector; }
+    const std::vector<CaseBranch> &getBranches() const { return Branches; }
+};
+
 class IfStmtAST : public StmtAST {
     std::unique_ptr<ExprAST> Cond;
     std::vector<std::unique_ptr<StmtAST>> ThenStmts;
diff --git a/include/cps/CodeGen.h b/include/cps/CodeGen.h
index 72b96c6..4259d63 100644
--- a/include/cps/CodeGen.h
+++ b/include/cps/CodeGen.h
@@ -70,13 +70,17 @@ class CodeGen {
     llvm::Value *convertNumericValue(llvm::Value *Val, const TypeInfo *Source,
                                      const TypeInfo *Target);
     llvm::Value *emitCast(CastExprAST *Cast);
-    llvm::Value *emitCBinaryOp(BinaryExprAST *Bin, const TypeInfo *Left, const TypeInfo *Right);
+    llvm::Value *emitBinaryOp(int Op, llvm::Value *L, const TypeInfo *LT,
+                              llvm::Value *R, const TypeInfo *RT, int Line);
+    llvm::Value *emitCBinaryOp(int Op, llvm::Value *L, const TypeInfo *Left,
+                               llvm::Value *R, const TypeInfo *Right, int Line);
     void emitCOutput(llvm::Value *Val, const TypeInfo *Info, bool AppendNewline);
     void emitCInput(const SymbolInfo *Symbol, const TypeInfo *Info);
 
     // TYPE-system registration (Designator.cc) and operators (TypeCheckGen.cc).
     void runTypePrePass(const std::vector<std::unique_ptr<StmtAST>> &Statements);
-    llvm::Value *emitUserKindBinaryOp(BinaryExprAST *Bin, const TypeInfo *LT, const TypeInfo *RT);
+    llvm::Value *emitUserKindBinaryOp(int Op, llvm::Value *L, const TypeInfo *LT,
+                                      llvm::Value *R, const TypeInfo *RT, int Line);
 
     // An addressable location and the pseudocode type stored there.
     struct LValueInfo {
@@ -95,6 +99,7 @@ class CodeGen {
     void emitDeclareStmt(DeclareStmtAST *Stmt);
     void emitOutputValue(llvm::Value *Val, const TypeInfo *TypeInfo, bool AppendNewline = true);
 
+    void emitCaseStmt(CaseStmtAST *Stmt);
     void emitIfStmt(IfStmtAST *Stmt);
     void emitTryStmt(TryStmtAST *Stmt);
     void emitWhileStmt(WhileStmtAST *Stmt);
diff --git a/include/cps/Lexer.h b/include/cps/Lexer.h
index 2f6f231..7f3d5b5 100644
--- a/include/cps/Lexer.h
+++ b/include/cps/Lexer.h
@@ -2,6 +2,7 @@
 #include <istream>
 #include <string>
 #include <cstdint>
+#include <deque>
 
 namespace cps {
 
@@ -13,6 +14,10 @@ enum Token {
     tok_input = -4,
     tok_output = -5,
     
+    tok_case = -40,
+    tok_endcase = -41,
+    tok_otherwise = -42,
+
     tok_if = -6,
     tok_then = -7,
     tok_else = -8,
@@ -105,18 +110,32 @@ class Lexer {
     std::istream &Input;
     int LastChar = ' ';
     int CurrentLine = 1;
+    int TokenLine = 1;
     bool HadError = false;
+    struct TokenData {
+        int Kind, Line;
+        std::string Identifier, String;
+        int64_t Integer;
+        double Real;
+        char Character;
+    };
+    std::deque<TokenData> Lookahead;
+    int readToken();
+    TokenData captureToken(int Kind) const;
+    void restoreToken(const TokenData &Token);
 public:
     explicit Lexer(std::istream &Input) : Input(Input) {}
 
     std::string IdentifierStr;
     std::string StringVal;
-    int64_t NumVal;
-    double RealVal;
+    int64_t NumVal = 0;
+    double RealVal = 0;
     char CharVal = '\0';
 
     int gettok();
-    int getLine() const { return CurrentLine; }
+    int peekToken(unsigned Offset = 0);
+    int peekLine(unsigned Offset = 0);
+    int getLine() const { return TokenLine; }
     bool hadError() const { return HadError; }
 };
 
diff --git a/include/cps/Parser.h b/include/cps/Parser.h
index 5713587..921480d 100644
--- a/include/cps/Parser.h
+++ b/include/cps/Parser.h
@@ -16,7 +16,10 @@ namespace cps {
 
 class Parser {
     Lexer &Lex;
-    int CurTok;
+    int CurTok = tok_eof;
+    bool StartsLine = true;
+    bool ParsingCaseLabel = false;
+    std::vector<unsigned> CaseBodyDepths;
     unsigned NumErrors = 0;
     unsigned BlockDepth = 0; // ParseBlock nesting; 1 = top level
 
@@ -41,7 +44,10 @@ class Parser {
 
     std::unique_ptr<StmtAST> ParseStatement();
     std::unique_ptr<StmtAST> ParseStatementImpl();
-    std::vector<std::unique_ptr<StmtAST>> ParseBlock(std::initializer_list<int> Terminators);
+    std::vector<std::unique_ptr<StmtAST>> ParseBlock(std::initializer_list<int> Terminators, bool CaseBody = false);
+    bool isCaseLabel();
+    bool atCaseBoundary();
+    std::unique_ptr<StmtAST> ParseCaseStmt();
     std::optional<std::vector<std::unique_ptr<ExprAST>>> ParseExprList(char CloseDelim, bool AllowEmpty);
     void syncToStatementStart();
     std::unique_ptr<StmtAST> ParseIfStmt();