lab1&lab2

include/cminusfc/cminusf_builder.hpp

@@ -24,12 +24,12 @@ class Scope {
     // push a name to scope
     // return true if successful
     // return false if this name already exits
-    bool push(const std::string& name, Value *val) {
+    bool push(const std::string &name, Value *val) {
         auto result = inner[inner.size() - 1].insert({name, val});
         return result.second;
     }
 
-    Value *find(const std::string& name) {
+    Value *find(const std::string &name) {
         for (auto s = inner.rbegin(); s != inner.rend(); s++) {
             auto iter = s->find(name);
             if (iter != s->end()) {
@@ -62,11 +62,13 @@ class CminusfBuilder : public ASTVisitor {
         std::vector<Type *> output_params;
         output_params.push_back(TyInt32);
         auto *output_type = FunctionType::get(TyVoid, output_params);
-        auto *output_fun = Function::create(output_type, "output", module.get());
+        auto *output_fun =
+            Function::create(output_type, "output", module.get());
 
         std::vector<Type *> output_float_params;
         output_float_params.push_back(TyFloat);
-        auto *output_float_type = FunctionType::get(TyVoid, output_float_params);
+        auto *output_float_type =
+            FunctionType::get(TyVoid, output_float_params);
         auto *output_float_fun =
             Function::create(output_float_type, "outputFloat", module.get());
 
@@ -106,8 +108,11 @@ class CminusfBuilder : public ASTVisitor {
     std::unique_ptr<Module> module;
 
     struct {
+        // whether require lvalue
+        bool require_lvalue = false;
         // function that is being built
         Function *func = nullptr;
-        // TODO: you should add more fields to store state
+        // detect scope pre-enter (for elegance only)
+        bool pre_enter_scope = false;
     } context;
 };

src/common/ast.cpp

@@ -34,6 +34,7 @@ ASTNode *AST::transform_node_iter(syntax_tree_node *n) {
   */
   if (_STR_EQ(n->name, "program")) {
     auto node = new ASTProgram();
+
     // flatten declaration list
     std::stack<syntax_tree_node *>
         s; // 为什么这里要用stack呢？如果用其他数据结构应该如何实现
@@ -96,23 +97,34 @@ ASTNode *AST::transform_node_iter(syntax_tree_node *n) {
     // id 字段填充
     node->id = n->children[1]->name;
 
-    /*
-        params 字段填充
-        注意这里的params是一个列表，每个元素都是一个ASTParam，需要flatten
-        params -> param-list | void
-        param-list -> param-list , param | param
-    */
-    // TODO: 1.fill in the fields of ASTFunDeclaration
-    // 1.1 flatten params
+    // flatten params
+    std::stack<syntax_tree_node *> s;
+    auto list_ptr = n->children[3]->children[0];
+    if (list_ptr->children_num != 0) {
+      if (list_ptr->children_num == 3) {
+        while (list_ptr->children_num == 3) {
+          s.push(list_ptr->children[2]);
+          list_ptr = list_ptr->children[0];
+        }
+      }
+      s.push(list_ptr->children[0]);
 
-    // 1.2 compound_stmt 字段填充
+      while (!s.empty()) {
+        auto child_node = static_cast<ASTParam *>(transform_node_iter(s.top()));
+        auto child_node_shared = std::shared_ptr<ASTParam>(child_node);
+        node->params.push_back(child_node_shared);
+        s.pop();
+      }
+    }
 
+    auto stmt_node =
+        static_cast<ASTCompoundStmt *>(transform_node_iter(n->children[5]));
+    node->compound_stmt = std::shared_ptr<ASTCompoundStmt>(stmt_node);
     return node;
   } else if (_STR_EQ(n->name, "param")) {
     // param -> type-specifier ID | type-specifier ID [ ]
     // ASTParam的结构 主要需要填充的属性有 type, id, isarray
     auto node = new ASTParam();
-    // type, id, isarray
     if (_STR_EQ(n->children[0]->children[0]->name, "int"))
       node->type = TYPE_INT;
     else
@@ -123,19 +135,41 @@ ASTNode *AST::transform_node_iter(syntax_tree_node *n) {
     return node;
   } else if (_STR_EQ(n->name, "compound-stmt")) {
     auto node = new ASTCompoundStmt();
-    // TODO: 2.fill in the fields of ASTCompoundStmt
-    /*
-      文法表达式如下
-      compound-stmt -> { local-declarations statement-list }
-      local-declarations -> local-declarations var-declaration | empty
-      statement-list -> statement-list statement | empty
-    */
-    // local declarations
-    // 2.1 flatten local declarations
-
-    // statement list
-    // 2.2 flatten statement-list
+    if (n->children[1]->children_num == 2) {
+      // flatten local declarations
+      auto list_ptr = n->children[1];
+      std::stack<syntax_tree_node *> s;
+      while (list_ptr->children_num == 2) {
+        s.push(list_ptr->children[1]);
+        list_ptr = list_ptr->children[0];
+      }
+
+      while (!s.empty()) {
+        auto decl_node =
+            static_cast<ASTVarDeclaration *>(transform_node_iter(s.top()));
+        auto decl_node_ptr = std::shared_ptr<ASTVarDeclaration>(decl_node);
+        node->local_declarations.push_back(decl_node_ptr);
+        s.pop();
+      }
+    }
+
+    if (n->children[2]->children_num == 2) {
+      // flatten statement-list
+      auto list_ptr = n->children[2];
+      std::stack<syntax_tree_node *> s;
+      while (list_ptr->children_num == 2) {
+        s.push(list_ptr->children[1]);
+        list_ptr = list_ptr->children[0];
+      }
 
+      while (!s.empty()) {
+        auto stmt_node =
+            static_cast<ASTStatement *>(transform_node_iter(s.top()));
+        auto stmt_node_ptr = std::shared_ptr<ASTStatement>(stmt_node);
+        node->statement_list.push_back(stmt_node_ptr);
+        s.pop();
+      }
+    }
     return node;
   } else if (_STR_EQ(n->name, "statement")) {
     return transform_node_iter(n->children[0]);
@@ -151,18 +185,25 @@ ASTNode *AST::transform_node_iter(syntax_tree_node *n) {
     return node;
   } else if (_STR_EQ(n->name, "selection-stmt")) {
     auto node = new ASTSelectionStmt();
-    // TODO: 5.fill in the fields of ASTSelectionStmt
-    /*
-      selection-stmt -> if ( expression ) statement | if ( expression )
-      statement else statement ASTSelectionStmt的结构，需要填充的字段有
-      expression, if_statement, else_statement
-    */
-    // 5.1 expresstion
 
-    // 5.2 if statement
+    auto expr_node =
+        static_cast<ASTExpression *>(transform_node_iter(n->children[2]));
+    auto expr_node_ptr = std::shared_ptr<ASTExpression>(expr_node);
+    node->expression = expr_node_ptr;
+
+    auto if_stmt_node =
+        static_cast<ASTStatement *>(transform_node_iter(n->children[4]));
+    auto if_stmt_node_ptr = std::shared_ptr<ASTStatement>(if_stmt_node);
+    node->if_statement = if_stmt_node_ptr;
 
     // check whether this selection statement contains
-    // 5.3 else structure
+    // else structure
+    if (n->children_num == 7) {
+      auto else_stmt_node =
+          static_cast<ASTStatement *>(transform_node_iter(n->children[6]));
+      auto else_stmt_node_ptr = std::shared_ptr<ASTStatement>(else_stmt_node);
+      node->else_statement = else_stmt_node_ptr;
+    }
 
     return node;
   } else if (_STR_EQ(n->name, "iteration-stmt")) {
@@ -242,13 +283,20 @@ ASTNode *AST::transform_node_iter(syntax_tree_node *n) {
   } else if (_STR_EQ(n->name, "additive-expression")) {
     auto node = new ASTAdditiveExpression();
     if (n->children_num == 3) {
-      // TODO: 4.fill in the fields of ASTAdditiveExpression
-      /*
-        文法表达式如下
-        additive-expression -> additive-expression addop term | term 
-      */
-      // additive_expression, term, op
+      auto add_expr_node = static_cast<ASTAdditiveExpression *>(
+          transform_node_iter(n->children[0]));
+      node->additive_expression =
+          std::shared_ptr<ASTAdditiveExpression>(add_expr_node);
+
+      auto op_name = n->children[1]->children[0]->name;
+      if (_STR_EQ(op_name, "+"))
+        node->op = OP_PLUS;
+      else if (_STR_EQ(op_name, "-"))
+        node->op = OP_MINUS;
 
+      auto term_node =
+          static_cast<ASTTerm *>(transform_node_iter(n->children[2]));
+      node->term = std::shared_ptr<ASTTerm>(term_node);
     } else {
       auto term_node =
           static_cast<ASTTerm *>(transform_node_iter(n->children[0]));
@@ -287,19 +335,12 @@ ASTNode *AST::transform_node_iter(syntax_tree_node *n) {
       return transform_node_iter(n->children[i]);
     else {
       auto num_node = new ASTNum();
-      // TODO: 3.fill in the fields of ASTNum
-      /*
-        文法表达式如下
-        factor -> ( expression ) | var | call | integer | float
-        float -> FLOATPOINT
-        integer -> INTEGER
-      */
       if (_STR_EQ(name, "integer")) {
-        // 3.1
-
+        num_node->type = TYPE_INT;
+        num_node->i_val = std::stoi(n->children[i]->children[0]->name);
       } else if (_STR_EQ(name, "float")) {
-        // 3.2
-
+        num_node->type = TYPE_FLOAT;
+        num_node->f_val = std::stof(n->children[i]->children[0]->name);
       } else {
         _AST_NODE_ERROR_
       }

src/parser/lexical_analyzer.l

@@ -25,6 +25,9 @@ void pass_node(char *text){
  /* to do for students */
  /* two cases for you, pass_node will send flex's token to bison */
 \+ 	{pos_start = pos_end; pos_end += 1; pass_node(yytext); return ADD;}
+
+ /****请在此补全所有flex的模式与动作  end******/
+
 \-	{pos_start = pos_end; pos_end += 1; pass_node(yytext); return SUB;}
 \*	{pos_start = pos_end; pos_end += 1; pass_node(yytext); return MUL;}
 \/	{pos_start = pos_end; pos_end += 1; pass_node(yytext); return DIV;}
@@ -34,13 +37,34 @@ void pass_node(char *text){
 \>=	{pos_start = pos_end; pos_end += 2; pass_node(yytext); return GTE;}
 ==	{pos_start = pos_end; pos_end += 2; pass_node(yytext); return EQ;}
 !=	{pos_start = pos_end; pos_end += 2; pass_node(yytext); return NEQ;}
-=	{pos_start = pos_end; pos_end += 1; pass_node(yytext); return ASSIGN;}
+=	{pos_start = pos_end; pos_end += 1; pass_node(yytext); return ASSIN;}
 ;	{pos_start = pos_end; pos_end += 1; pass_node(yytext); return SEMICOLON;}
 ,	{pos_start = pos_end; pos_end += 1; pass_node(yytext); return COMMA;}
- /* TODO: phase1. 请在这里补充其他的词法规则 */
+\(	{pos_start = pos_end; pos_end += 1; pass_node(yytext); return LPARENTHESE;}
+\)	{pos_start = pos_end; pos_end += 1; pass_node(yytext); return RPARENTHESE;}
+\[	{pos_start = pos_end; pos_end += 1; pass_node(yytext); return LBRACKET;}
+\]	{pos_start = pos_end; pos_end += 1; pass_node(yytext); return RBRACKET;}
+\{	{pos_start = pos_end; pos_end += 1; pass_node(yytext); return LBRACE;}
+\}	{pos_start = pos_end; pos_end += 1; pass_node(yytext); return RBRACE;}
+else	{pos_start = pos_end; pos_end += 4; pass_node(yytext); return ELSE;}
+if	{pos_start = pos_end; pos_end += 2; pass_node(yytext); return IF;}
+int	{pos_start = pos_end; pos_end += 3; pass_node(yytext); return INT;}
+float   {pos_start = pos_end; pos_end += 5; pass_node(yytext); return FLOAT;}
+return 	{pos_start = pos_end; pos_end += 6; pass_node(yytext); return RETURN;}
+void 	{pos_start = pos_end; pos_end += 4; pass_node(yytext); return VOID;}
+while 	{pos_start = pos_end; pos_end += 5; pass_node(yytext); return WHILE;}
+[a-zA-Z]+	{pos_start = pos_end; pos_end += strlen(yytext); pass_node(yytext); return IDENTIFIER;}
+[0-9]+	{pos_start = pos_end; pos_end += strlen(yytext); pass_node(yytext); return INTEGER;}
+[0-9]+\.[0-9]*|[0-9]*\.[0-9]+ { pos_start = pos_end; pos_end += strlen(yytext); pass_node(yytext); return FLOATPOINT;}
 
+\n 	{lines++; pos_start = 1; pos_end = 1;}
+[ \t] 	{pos_start = pos_end; pos_end += 1;}
+
+"/*"             { pos_start = pos_end; pos_end += 2; BEGIN(COMMENT); }
+<COMMENT>"*/"    { pos_start = pos_end; pos_end += 2; BEGIN(INITIAL); }
+<COMMENT>.  { pos_start = pos_end; pos_start += 1; }
+<COMMENT>\n { pos_start = 1; pos_end = 1; lines++; }
 
 . { pos_start = pos_end; pos_end++; return ERROR; }
 
- /****请在此补全所有flex的模式与动作  end******/
 %%

src/parser/syntax_analyzer.y

@@ -28,15 +28,13 @@ void yyerror(const char *s);
 syntax_tree_node *node(const char *node_name, int children_num, ...);
 %}
 
-/* Complete this definition.
-   Hint: See pass_node(), node(), and syntax_tree.h.
-         Use forward declaring. */
+/* TODO: Complete this definition. */
 %union {
      struct _syntax_tree_node * node;
 	 char * name;
 }
 
-/* Your tokens here. */
+/* TODO: Your tokens here. */
 %token <node> ERROR
 %token <node> ADD
 %token <node> SUB
@@ -48,7 +46,7 @@ syntax_tree_node *node(const char *node_name, int children_num, ...);
 %token <node> GTE
 %token <node> EQ
 %token <node> NEQ
-%token <node> ASSIGN
+%token <node> ASSIN
 %token <node> SEMICOLON
 %token <node> COMMA
 %token <node> LPARENTHESE
@@ -65,8 +63,8 @@ syntax_tree_node *node(const char *node_name, int children_num, ...);
 %token <node> WHILE
 %token <node> IDENTIFIER
 %token <node> INTEGER
-%token <node> FLOAT             // 这个token 对应float 关键字
-%token <node> FLOATPOINT        // 这个token 对应 浮点数值, 如果分不清的同学可以参考type-specifier的文法和对应产生式规则
+%token <node> FLOAT
+%token <node> FLOATPOINT	// 这个是 float 类型的 token
 //%token <node> EOL
 //%token <node> BLANK
 //%token <node> COMMENT
@@ -76,7 +74,7 @@ syntax_tree_node *node(const char *node_name, int children_num, ...);
 %start program
 
 %%
-/* Your rules here. TA has completed many */
+/* TODO: Your rules here. */
 
 program : 	declaration-list {$$ = node( "program", 1, $1); gt->root = $$;}
 		;
@@ -122,8 +120,91 @@ local-declarations 	: 	local-declarations var-declaration {$$ = node( "local-dec
 
 statement-list 	: 	statement-list statement {$$ = node( "statement-list", 2, $1, $2);}
 | 	{$$ = node( "statement-list",0);}
-                    ;
-// TODO: phase1. 补充其他的文法产生式逻辑
+				;
+
+statement 	: 	expression-stmt {$$ = node( "statement", 1, $1);}
+            | 	compound-stmt {$$ = node( "statement", 1, $1);}
+			| 	selection-stmt {$$ = node( "statement", 1, $1);}
+			| 	iteration-stmt {$$ = node( "statement", 1, $1);}
+			| 	return-stmt {$$ = node( "statement", 1, $1);}
+			;
+
+expression-stmt : 	expression SEMICOLON {$$ = node( "expression-stmt", 2, $1, $2);}
+				| 	SEMICOLON {$$ = node( "expression-stmt", 1, $1);}
+				;
+
+selection-stmt 	: 	IF LPARENTHESE expression RPARENTHESE statement {$$ = node( "selection-stmt", 5, $1, $2, $3, $4, $5);}
+				| 	IF LPARENTHESE expression RPARENTHESE statement ELSE statement {$$ = node( "selection-stmt", 7, $1, $2, $3, $4, $5, $6, $7);}
+				;
+
+iteration-stmt 	: 	WHILE LPARENTHESE expression RPARENTHESE statement {$$ = node( "iteration-stmt", 5, $1, $2, $3, $4, $5);}
+				;
+
+return-stmt : 	RETURN SEMICOLON {$$ = node( "return-stmt", 2, $1, $2);}
+			| 	RETURN expression SEMICOLON {$$ = node( "return-stmt", 3, $1, $2, $3);}
+			;
+
+expression 	: 	var ASSIN expression {$$ = node( "expression", 3, $1, $2, $3);}
+			| 	simple-expression {$$ = node( "expression", 1, $1);}
+			;
+
+var : 	IDENTIFIER {$$ = node( "var", 1, $1);}
+    | 	IDENTIFIER LBRACKET expression RBRACKET {$$ = node( "var", 4, $1, $2, $3, $4);}
+    ;
+
+simple-expression 	: 	additive-expression relop additive-expression {$$ = node( "simple-expression", 3, $1, $2, $3);}
+					| 	additive-expression {$$ = node( "simple-expression", 1, $1);}
+					;
+
+relop 	: 	LT {$$ = node( "relop", 1, $1);}
+		| 	LTE {$$ = node( "relop", 1, $1);}
+		| 	GT {$$ = node( "relop", 1, $1);}
+		| 	GTE {$$ = node( "relop", 1, $1);}
+		| 	EQ {$$ = node( "relop", 1, $1);}
+		| 	NEQ {$$ = node( "relop", 1, $1);}
+		;
+
+additive-expression : 	additive-expression addop term  {$$ = node( "additive-expression", 3, $1, $2, $3);}
+					| 	term {$$ = node( "additive-expression", 1, $1);}
+					;
+
+addop 	: 	ADD {$$ = node( "addop", 1, $1);}
+		|	SUB {$$ = node( "addop", 1, $1);}
+		;
+
+term 	: 	term mulop factor {$$ = node( "term", 3, $1, $2, $3);}
+		| 	factor {$$ = node( "term", 1, $1);}
+		;
+
+mulop 	: 	MUL {$$ = node( "mulop", 1, $1);}
+		|	DIV {$$ = node( "mulop", 1, $1);}
+		;
+
+factor 	: 	LPARENTHESE expression RPARENTHESE {$$ = node( "factor", 3, $1, $2, $3);}
+		|	var {$$ = node( "factor", 1, $1);}
+		|	call {$$ = node( "factor", 1, $1);}
+		|	integer {$$ = node( "factor", 1, $1);}
+		|	float {$$ = node( "factor", 1, $1);}
+		;
+
+integer 	: 	INTEGER {$$ = node( "integer", 1, $1);}
+		;
+
+float 	: 	FLOATPOINT {$$ = node( "float", 1, $1);}
+		;
+
+call 	: 	IDENTIFIER LPARENTHESE args RPARENTHESE {$$ = node( "call", 4, $1, $2, $3, $4);}
+		;
+
+args 	: 	arg-list {$$ = node( "args", 1, $1);}
+| 	{$$ = node( "args", 0);}
+		;
+
+arg-list 	: 	arg-list COMMA expression {$$ = node( "arg-list", 3, $1, $2, $3);}
+			| 	expression {$$ = node( "arg-list", 1, $1);}
+			;
+
+
 
 %%
 
@@ -164,7 +245,7 @@ syntax_tree_node *node(const char *name, int children_num, ...)
 {
     syntax_tree_node *p = new_syntax_tree_node(name);
     syntax_tree_node *child;
-    // 这里表示 epsilon结点是通过 children_num == 0 来判断的
+	// 这里表示 epsilon结点是通过 children_num == 0 来判断的
     if (children_num == 0) {
         child = new_syntax_tree_node("epsilon");
         syntax_tree_add_child(p, child);