[基本完成，有个小bug，估计没人发现hh...]
[只实现了一部分的语法分析...实在是太多了]
目前能识别的C语法：
char c;
void add(int a);
int sum(int a,int b)
{
return a+b;
}
//This is comment.
int main(){
int a = (1+1)/1.23-1;
a = add(a);
a = sum(a,1);
double nums[10];
nums[0] = 1;
if ( a > 1 ) {
a+=2;
} else {
a-=2;
}
for (int i=1;i++;i<10)
{}
while (1)
{}
return 0;
}
int add(int a)
{
a++;
return a;
}
实现代码
执行脚本：
#!/bin/bash
if (( $# != 1 ));then
echo "输入参数不正确"
exit 1
fi
flex -o C-lexical-analyzer.yy.c C-lexical-analyzer.l
echo "flex编译完成"
bison -o C-Parser.tab.h C-Parser.y
echo "bison编译完成"
gcc -o C-Parser -w C-Parser.tab.* C-lexical-analyzer.yy.c -lfl
echo "gcc编译完成"
rm C-Parser.tab.* C-lexical-analyzer.yy.c
echo "正在运行:(没有错误便说明通过)"
./C-Parser < $1
echo "运行结束"
rm C-Parser
bison：
/*
*file: C-Parser.y
*auther: jin1ming
*system: manjaro
*/
%{
#include
#include
#define YYSTYPE char*
%}
%token identifier AUTO BREAK CASE CHAR
%token CONST CONTINUE DEFAULT DO DOUBLE
%token ELSE ENUM EXTERN FLOAT FOR GOTO
%token IF INT LONG REGISTER RETURN AND_NOT
%token SHORT SIGNED SIZEOF STATIC STRUCT
%token SWITCH TYPEDEF UNSIGNED UNION
%token DEC INC LPAREN NOT RPAREN SEMICOLON
%token VOID VOLATILE WHILE number array
%token LBRACE RBRACE RBRACK LBRACK
%token COMMA AND_NOT_ASSIGN PERIOD
%token RBRAEN COLON POT DQUA SQUA
%left ASSIGN ADD_ASSIGN SUB_ASSIGN MUL_ASSIGN QUO_ASSIGN REM_ASSIGN AND_ASSIGN OR_ASSIGN XOR_ASSIGN SHL_ASSIGN SHR_ASSIGN AND_NOASSIGN
/*条件运算符?:还未实现*/
/*以下操作符有优先级，顺序不可改变*/
%left LOR
%left LAND
%left OR
%left XOR
%left AND
%left NEQ EQL
%left LSS GTR LEQ GEQ
%left SHR SHL
%left ADD SUB
%left MUL QUO REM
/*单目运算符未声明*/
%start translation_unit
%%
/*C代码入口*/
translation_unit:
external_declaration
| translation_unit external_declaration
;
/*
*代码块
*分为函数块、变量块
*/
external_declaration
: function_definition
| declaration
;
/*
*函数块
*分为4种情况：
* 1. int print(int a, int b){int a = 0;}
* 2. int print();
* 3. int print(){int a = 0;}
* 4. int print(int a, int b);
*/
function_definition
: type_specifier identifier LPAREN parameter_list RPAREN compound_statement
| type_specifier identifier LPAREN RPAREN compound_statement
| type_specifier identifier LPAREN parameter_list RPAREN SEMICOLON
| type_specifier identifier LPAREN RPAREN SEMICOLON
;
/*变量块*/
declaration
: type_specifier declarator SEMICOLON
| type_specifier assignmenexpression SEMICOLON
;
/*参数列表*/
parameter_list
: parameter_declaration
| parameter_list COMMA parameter_declaration
;
/*参数声明*/
parameter_declaration
: type_specifier declarator
;
/*变量*/
declarator
: identifier
| array
;
/*函数实现块*/
compound_statement
: LBRACE RBRACE
| LBRACE block_item_list RBRACE
;
/*C语句块列表*/
block_item_list
: block_item
| block_item_list block_item
;
/*C语句块
*分为声明语句和操作语句
*/
block_item
: declaration
| statement
| RETURN arithmetic_expression_list SEMICOLON
| RETURN conditional_expression_list SEMICOLON
;
/*操作语句*/
statement
: compound_statement
| expression_statement
| selection_statement
| iteration_statement
;
/*操作语句：多条语句*/
expression_statement
: SEMICOLON
| expression SEMICOLON
;
/*
*操作语句：选择
*分成两个，以消除偏移/规约冲突
*/
selection_statement
: IF LPAREN expression RPAREN statement statement
| IF LPAREN expression RPAREN statement ELSE statement
| SWITCH LPAREN expression RPAREN statement
;
/*操作语句：迭代循环*/
iteration_statement
: WHILE LPAREN expression RPAREN statement
| DO statement WHILE LPAREN expression RPAREN SEMICOLON
| FOR LPAREN expression_statement expression_statement RPAREN statement
| FOR LPAREN expression_statement expression_statement expression RPAREN statement
| FOR LPAREN declaration expression_statement RPAREN statement
| FOR LPAREN declaration expression_statement expression RPAREN statement
;
/*
*表达式
*分为条件表达式、赋值表达式、算数表达式
*/
expression
: conditional_expression_list
| assignmenexpression
| arithmetic_expression_list
;
/*赋值表达式*/
assignmenexpression
: declarator assignmenoperator expression
;
/*
*算数表达式
* 拆分成两个，以消除偏移/规约冲突
*/
arithmetic_expression_list
: arithmetic_expression_list arithmetic_operator arithmetic_expression
| arithmetic_expression_list arithmetic_operator LPAREN arithmetic_expression_list RPAREN
| arithmetic_expression
| LPAREN arithmetic_expression_list RPAREN
;
arithmetic_expression
: value
| identifier INC
| identifier DEC
| ADD identifier
| SUB identifier
/*
*函数调用
*特性与算数表达式比较类似
*/
| identifier LPAREN RPAREN
| identifier LPAREN value_list RPAREN
;
/*传参*/
value_list
: value
| value COMMA value
/*
*值
*分为标识符和数字(这里变量只实现数字)
*/
value
: number
| declarator
;
/*
*条件表达式
*拆分成两个，以消除偏移/规约冲突
*/
conditional_expression_list
: conditional_expression
| conditional_expression logical_operator conditional_expression
conditional_expression
;
conditional_expression
: arithmetic_expression relational_operator arithmetic_expression
| NOT conditional_expression
;
/*算数/位运算符*/
arithmetic_operator
: ADD
| SUB
| MUL
| QUO
| REM
| AND
| OR
| XOR
| SHL
| SHR
| AND_NOT
;
/*逻辑运算符*/
logical_operator
: LAND
| LOR
;
//NOT是单目运算符比较特殊
/*关系运算符*/
relational_operator
: EQL
| LSS
| GTR
| NEQ
| LEQ
| GEQ
;
/*赋值符号*/
assignmenoperator
: ASSIGN
| ADD_ASSIGN
| SUB_ASSIGN
| MUL_ASSIGN
| QUO_ASSIGN
| REM_ASSIGN
| AND_ASSIGN
| OR_ASSIGN
| XOR_ASSIGN
| SHL_ASSIGN
| SHR_ASSIGN
| AND_NOASSIGN
;
/*类型*/
type_specifier
: VOID
| CHAR
| SHORT
| INT
| LONG
| FLOAT
| DOUBLE
| SIGNED
| UNSIGNED
;
%%
main(int argc,char **argv){
yyparse();
}
yyerror(char *s)
{
fprintf(stderr,"error: %s\n",s);
}
flex:
/*
*file: C-lexical-analyzer.l
*auther: jin1ming
*system: manjaro
*/
%option yylineno
%{
#include
#include
#include"C-Parser.tab.h"
extern int yylineno;
%}
/*数字定义*/
/*科学计数表示*/
science {decimal}(\.[0-9]+)?([Ee][-+]?[0-9]+)?
/*十进制*/
decimal 0|[1-9][0-9]*
/*十六进制*/
hexadecimal 0[xX][a-fA-F0-9]+
/*二进制*/
binary 0[bB][01]+
/*八进制*/
octal 0[0-7]+
/*总表示*/
number ({hexadecimal}|{binary}|{science}|{octal})(([uU]?[Ll]?)|([Ll]?[Uu]?)|([fF]?))
/*注意浮点数总是有符号，不需要Uu后缀，所以在接下来单做一个浮点数异常处理*/
/*数字异常处理*/
floatexcption {decimal}\.[0-9]+([Ee]?[-+]?[0-9]+)?[Uu]
excption [0-9][0-9a-zA-Z\.]+
/*关键字*/
AUTO auto
BREAK break
CASE case
CHAR char
CONST const
CONTINUE continue
DEFAULT default
DO do
DOUBLE double
ELSE else
ENUM enum
EXTERN extern
FLOAT float
FOR for
GOTO goto
IF if
INT int
LONG long
REGISTER register
RETURN return
SHORT short
SIGNED signed
SIZEOF sizeof
STATIC static
STRUCT struct
SWITCH switch
TYPEDEF typedef
UNSIGNED unsigned
UNION union
VOID void
VOLATILE volatile
WHILE while
/*注释*/
COMMENT (\/\/.*)|(\/\*(.|\n)*\/)
/*数组*/
array {identifier}\[(0|([1-9][0-9]*))\]
/*标识符定义*/
identifier [a-z_A-Z][a-z_A-Z0-9]*
/*其它字符*/
whitespace [ \t\n\r\f\v]+
errno .
/*运算符*/
/*算术运算符*/
ADD \+
SUB \-
MUL \*
QUO \/
REM %
INC \+\+
DEC \-\-
/*赋值运算符*/
ASSIGN =
ADD_ASSIGN \+=
SUB_ASSIGN \-=
MUL_ASSIGN \*=
QUO_ASSIGN \/=
REM_ASSIGN %=
AND_ASSIGN \&=
OR_ASSIGN \|=
XOR_ASSIGN \^=
SHL_ASSIGN <<=
SHR_ASSIGN >>=
AND_NOT_ASSIGN ~=
/*位运算符*/
AND &
OR \|
XOR \^
SHL <<
SHR >>
AND_NOT ~
/*逻辑运算符*/
LAND &&
LOR \|\|
NOT \!
/*关系运算符*/
EQL ==
LSS <
GTR >
NEQ !=
LEQ <=
GEQ >=
/*标点符号*/
LPAREN \(
LBRACK \[
LBRACE \{
COMMA ,
PERIOD \.
RPAREN \)
RBRACK \]
RBRACE \}
SEMICOLON ;
COLON :
POT \->
DQUA \"
SQUA \'
%%
/*关键字*/
{AUTO} {return AUTO;}
{BREAK} {return BREAK;}
{CASE} {return CASE;}
{CHAR} {return CHAR;}
{CONST} {return CONST;}
{CONTINUE} {return CONTINUE;}
{DEFAULT} {return DEFAULT;}
{DO} {return DO;}
{DOUBLE} {return DOUBLE;}
{ELSE} {return ELSE;}
{ENUM} {return ENUM;}
{EXTERN} {return EXTERN;}
{FLOAT} {return FLOAT;}
{FOR} {return FOR;}
{GOTO} {return GOTO;}
{IF} {return IF;}
{INT} {return INT;}
{LONG} {return LONG;}
{REGISTER} {return REGISTER;}
{RETURN} {return RETURN;}
{SHORT} {return SHORT;}
{SIGNED} {return SIGNED;}
{SIZEOF} {return SIZEOF;}
{STATIC} {return STATIC;}
{STRUCT} {return STRUCT;}
{SWITCH} {return SWITCH;}
{TYPEDEF} {return TYPEDEF;}
{UNSIGNED} {return UNSIGNED;}
{UNION} {return UNION;}
{VOID} {return VOID;}
{VOLATILE} {return VOLATILE;}
{WHILE} {return WHILE;}
/*提前处理浮点数+uU的异常*/
{floatexcption} {printf("Float Execption: %s\n",yytext);}
/*数字表示*/
{number} {return number;}
/*数组*/
{array} {return array;}
/*异常数字处理*/
{excption} {printf("Number Execption: %s\n",yytext);}
/*跳过空白和注释*/
{whitespace} {}
{COMMENT} {}
/*运算符*/
/*算术运算符*/
{ADD} {return ADD;}
{SUB} {return SUB;}
{MUL} {return MUL;}
{QUO} {return QUO;}
{REM} {return REM;}
{INC} {return INC;}
{DEC} {return DEC;}
/*逻辑运算符*/
{LAND} {return LAND;}
{LOR} {return LOR;}
{NOT} {return NOT;}
/*赋值运算符*/
{ASSIGN} {return ASSIGN;}
{ADD_ASSIGN} {return ADD_ASSIGN;}
{SUB_ASSIGN} {return SUB_ASSIGN;}
{MUL_ASSIGN} {return MUL_ASSIGN;}
{QUO_ASSIGN} {return QUO_ASSIGN;}
{REM_ASSIGN} {return REM_ASSIGN;}
{AND_ASSIGN} {return AND_ASSIGN;}
{OR_ASSIGN} {return OR_ASSIGN;}
{XOR_ASSIGN} {return XOR_ASSIGN;}
{SHL_ASSIGN} {return SHL_ASSIGN;}
{SHR_ASSIGN} {return SHR_ASSIGN;}
{AND_NOT_ASSIGN} {return AND_NOT_ASSIGN;}
/*位运算符*/
{AND} {return AND;}
{OR} {return OR;}
{XOR} {return XOR;}
{SHL} {return SHL;}
{SHR} {return SHR;}
{AND_NOT} {return AND_NOT;}
/*关系运算符*/
{EQL} {return EQL;}
{LSS} {return LSS;}
{GTR} {return GTR;}
{NEQ} {return NEQ;}
{LEQ} {return LEQ;}
{GEQ} {return GEQ;}
/*标点符号*/
{LPAREN} {return LPAREN;}
{LBRACK} {return LBRACK;}
{LBRACE} {return LBRACE;}
{COMMA} {return COMMA;}
{PERIOD} {return PERIOD;}
{RPAREN} {return RPAREN;}
{RBRACK} {return RBRAEN;}
{RBRACE} {return RBRACE;}
{SEMICOLON} {return SEMICOLON;}
{COLON} {return COLON;}
{POT} {return POT;}
{DQUA} {return DQUA;}
{SQUA} {return SQUA;}
{identifier} {return identifier;}
{errno} {fprintf(stderr,"Mystery character: %s\n",yytext);}
%%
%%
一个真正的语法分析器离不开符号表，如果有时间我将加入符号表到语法分析器中，符号表设计思路：
符号表应该包括：变量符号表、函数符号表、数组符号表、结构体符号表
(1) 变量符号表应该包括：类型、变量名、作用域、指针
(之前我觉得应该使用union保存值，现在认为并不需要保存)
(2) 函数符号表应该包括：函数名、函数类型、返回值类型、形参个数、指针(考虑函数指针)
(3) 数组符号表应该包括：数组名、数组类型、指针
(4) 结构体符号表应该包括：结构体名、指针，以及用一个变量符号表链表来保存结构体成员变量。