change parser

src/parser/.gitignore

+lexical_analyzer_stu.l
+syntax_analyzer_stu.y

src/parser/lexical_analyzer.l

@@ -7,76 +7,61 @@
 #include "syntax_tree.h"
 #include "syntax_analyzer.h"
 
-/* #define __DEBUG_COMMENT__ */
-
-int lines = 1;
+int lines;
 int pos_start;
 int pos_end;
 
 void pass_node(char *text){
      yylval.node = new_syntax_tree_node(text);
 }
-void comment_helper(char *comment, unsigned int len) 
-{
-#ifdef __DEBUG_COMMENT__
-    printf("Get COMMENT in line<%d>: \"%s\"\n", lines, comment);
-#endif
-}
 
 /*****************声明和选项设置  end*****************/
 
 %}
 
-/* use exclusive state */
 %x COMMENT
 
-letter [a-zA-Z]
-digit [0-9]
-ID {letter}+
-INTEGER {digit}+
-FLOAT {digit}+\.|{digit}*\.{digit}+
-
-NEWLINE \r\n|\r|\n
-WHITESPACE [ \t]
-/*
-
-%token <node> _IF _ELSE _WHILE _RETURN _INT _FLOAT _VOID 
-%token <node> _ASSIGN _RELOP _ADD_OP _MUL_OP
-%token <node> _L_SQUARE _R_SQUARE _L_PARE _R_PARE _L_BRACKET _R_BRACKET
-%token <node> _SEMI _COMMA _ID _INTEGER _FLOATPOINT
-
-*/
-/* <COMMENT>.* { pos_end += yyleng; comment_helper(yytext, yyleng); } */
-
 %%
 
-<INITIAL>"/*" { BEGIN(COMMENT); pos_end += 2; }
-<COMMENT>[^*\n]*|"*"+[^*/\n]* { pos_end += yyleng; comment_helper(yytext, yyleng); }
-<COMMENT>"*/" { BEGIN(0); pos_end += 2; }
+\+ 	{pos_start = pos_end; pos_end += 1; pass_node(yytext); return ADD;}
+\-	{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;}
+\<	{pos_start = pos_end; pos_end += 1; pass_node(yytext); return LT;}
+\<=	{pos_start = pos_end; pos_end += 2; pass_node(yytext); return LTE;}
+\>	{pos_start = pos_end; pos_end += 1; pass_node(yytext); return GT;}
+\>=	{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 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;}
+\(	{pos_start = pos_end; pos_end += 1; pass_node(yytext); return LPARENTHESE;}
+\)	{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; }
 
-if { pos_start = pos_end; pos_end += 2; pass_node("if"); return _IF;}
-else { pos_start = pos_end; pos_end += 4; pass_node("else"); return _ELSE;}
-while { pos_start = pos_end; pos_end += 5; pass_node("while"); return _WHILE;}
-return { pos_start = pos_end; pos_end += 6; pass_node("return"); return _RETURN;}
-int { pos_start = pos_end; pos_end += 3; pass_node("int"); return _INT;}
-float { pos_start = pos_end; pos_end += 5; pass_node("float"); return _FLOAT;}
-void { pos_start = pos_end; pos_end += 4; pass_node("void"); return _VOID;}
-
-{ID} { pos_start = pos_end; pos_end += yyleng; pass_node(yytext); return _ID;}
-{INTEGER} { pos_start = pos_end; pos_end += yyleng; pass_node(yytext); return _INTEGER;}
-{FLOAT} { pos_start = pos_end; pos_end += yyleng; pass_node(yytext); return _FLOATPOINT;}
-
-"=" { pos_start = pos_end; pos_end += 1; pass_node("="); return _ASSIGN;}
-"<="|">="|"<"|">"|"=="|"!=" { pos_start = pos_end; pos_end += yyleng; pass_node(yytext); return _RELOP;}
-"+"|"-" { pos_start = pos_end; pos_end += 1; pass_node(yytext); return _ADD_OP;}
-"*"|"/" { pos_start = pos_end; pos_end += 1; pass_node(yytext); return _MUL_OP;}
-
-"["|"]" { pos_start = pos_end; pos_end += 1; pass_node(yytext); return yytext[0] == '[' ? _L_SQUARE : _R_SQUARE;}
-"("|")" { pos_start = pos_end; pos_end += 1; pass_node(yytext); return yytext[0] == '(' ? _L_PARE : _R_PARE;}
-"{"|"}" { pos_start = pos_end; pos_end += 1; pass_node(yytext); return yytext[0] == '{' ? _L_BRACKET : _R_BRACKET;}
-
-","|";" { pos_start = pos_end; pos_end += 1; pass_node(yytext); return yytext[0] == ',' ? _COMMA : _SEMI;}
-
-{WHITESPACE} { pos_end++; }
-<*>{NEWLINE} { lines++; pos_end = 0;}
 %%
+