在 C 中使用递归下降解析接受等号
Accepting an Equal Sign using Recursive Descent Parsing in C
我目前正在尝试构建一个递归下降解析器来解析赋值语句,例如 a = 4 + b
。语法如下
<stmt> → id = <expr>
<expr> → <term> {(+ | -) <term>}
<term> → <factor> {(* | /) <factor>}
<factor> → id | int_constant | ( <expr> )
此语法应接受诸如 sum = sum + 100 * (a - b)
之类的语句
ddddd
djdjdjd
// THIS IS ALL TEXTBOOK CODE
/* front.c - a lexical analyzer system for simple
arithmetic expressions */
#include <stdio.h>
#include <ctype.h>
/* Global declarations */
/* Variables */
int charClass;
char lexeme [100];
char nextChar;
int lexLen;
int token;
int nextToken;
FILE *in_fp, *fopen();
/* Function declarations */
void addChar();
void getChar();
void getNonBlank();
int lex();
/* Character classes */
#define LETTER 0
#define DIGIT 1
#define UNKNOWN 99
/* Token codes */
#define INT_LIT 10
#define IDENT 11
#define ASSIGN_OP 20
#define ADD_OP 21
#define SUB_OP 22
#define MULT_OP 23
#define DIV_OP 24
#define LEFT_PAREN 25
#define RIGHT_PAREN 26
// function prototypes for just expr()
void expr();
void stmt();
// define the grammar
/*
<expr> → <term> {(+ | -) <term>}
<term> → <factor> {(* | /) <factor>}
<factor> → id | int_constant | ( <expr> )
*/
/******************************************************/
/* main driver */
int main() {
/* Open the input data file and process its contents */
if ((in_fp = fopen("front.in", "r")) == NULL)
// open the file
printf("ERROR - cannot open front.in \n");
else {
// get characters and lex()?
getChar();
do {
printf("[FROM main()] before lex() %d \n",nextToken);
lex();
printf("[FROM main()] %d \n\n", nextToken);
stmt();
} while (nextToken != EOF);
}
// seems like the tokenizer is already implemented for us
-> will need to parse as tokens come in
}
void error(){
printf("ERROR: \n");
}
// the stmt function
void stmt() {
printf("Enter <stmt>\n\n");
if (nextToken == IDENT){
printf("[FROM stmt()] found identifier. \n");
printf("[FROM stmt()] before lex() %d \n", nextChar);
lex(); //error in here
printf("[FROM stmt()] after lex() %d \n\n", nextToken);
}
//printf("[FROM stmt()] nxt token %d\n\n", nextToken);
}
void factor(){
// must choose between two RHSs
printf("Enter <factor>\n");
// determine the RHSs
if(nextToken == IDENT || nextToken == INT_LIT){
lex(); // get next token
}
// if the RHS is <expr> tell the lex to pass over the
left parenthesis and call expr and then check for right
parentheses
else {
if(nextToken == LEFT_PAREN){
lex();
expr();
if(nextToken == RIGHT_PAREN){
lex();
}else {
error(); // should exist at the very top
}
}
else {
// it wasnt an id or int or left parentheses
error();
}
}
printf("Exit <factor>\n");
}
// parse term
void term() {
printf("Enter <term>\n");
// parse the first factor
factor();
// as long as the next is * or / get the next token and parse the next factor
while (nextToken == MULT_OP || nextToken == DIV_OP){
lex(); // get the next token
factor(); // parse the next factor
}
printf("Enter <expr> \n");
}
// parse expression
void expr() {
printf("Enter <expr> \n");
// parse first term
term();
// as long as the next token is + or -, get the next token and parse the next term
while(nextToken == ADD_OP || nextToken == SUB_OP){
// updates next token
lex();
// proocesses the term
term();
}
printf("Exit <expr> \n");
}
/*****************************************************/
/* lookup - a function to lookup operators and parentheses
and return the token */
int lookup(char ch) {
switch (ch) {
case '(':
addChar();
nextToken = LEFT_PAREN;
break;
case ')':
addChar();
nextToken = RIGHT_PAREN;
break;
case '+':
addChar();
nextToken = ADD_OP;
break;
case '-':
addChar();
nextToken = SUB_OP;
break;
case '*':
addChar();
nextToken = MULT_OP;
break;
case '/':
addChar();
nextToken = DIV_OP;
break;
case '=':
// if the equal sign then set as assign op -> not sure
what add char does
printf("[FROM lookup()] found the = \n");
addChar();
nextToken = ASSIGN_OP;
default:
addChar();
nextToken = EOF;
break;
}
return nextToken;
}
/*****************************************************/
/* addChar - a function to add nextChar to lexeme */
void addChar() {
if (lexLen <= 98) {
lexeme[lexLen++] = nextChar;
lexeme[lexLen] = 0;
}
else
printf("Error - lexeme is too long \n");
}
/*****************************************************/
/* getChar - a function to get the next character of
input and determine its character class */
void getChar() {
if ((nextChar = getc(in_fp)) != EOF){
//printf("\n[FROM getChar()] nextChar = %c \n\n",nextChar);
if (isalpha(nextChar))
charClass = LETTER;
else if (isdigit(nextChar))
charClass = DIGIT;
else charClass = UNKNOWN;
}
else
charClass = EOF;
}
/*****************************************************/
/* getNonBlank - a function to call getChar until it
returns a non-whitespace character */
void getNonBlank() {
while (isspace(nextChar))
getChar();
}
/*****************************************************/
/* lex - a simple lexical analyzer for arithmetic
expressions */
int lex() {
lexLen = 0;
getNonBlank();
switch (charClass) {
/* Parse identifiers */
case LETTER:
addChar();
getChar();
while (charClass == LETTER || charClass == DIGIT) {
addChar();
getChar();
}
nextToken = IDENT;
break;
/* Parse integer literals */
case DIGIT:
addChar();
getChar();
while (charClass == DIGIT) {
addChar();
getChar();
}
nextToken = INT_LIT;
break;
/* Parentheses and operators */
case UNKNOWN:
printf("[FROM lex()] %c\n",nextChar);
lookup(nextChar);
getChar();
break;
/* EOF */
case EOF:
nextToken = EOF;
lexeme[0] = 'E';
lexeme[1] = 'O';
lexeme[2] = 'F';
lexeme[3] = 0;
break;
} /* End of switch */
printf("Next token is: %d, Next lexeme is %s\n", nextToken, lexeme);
return nextToken;
} /* End of function lex */
这段代码(在文件front.in中)的输入是:
myVar = 5
我得到的输出是:
[FROM main()] before lex() 0
Next token is: 11, Next lexeme is myVar
[FROM main()] 11
Enter <stmt>
[FROM stmt()] found identifier.
[FROM stmt()] before lex() 32
[FROM lex()] =
[FROM lookup()] found the =
Next token is: -1, Next lexeme is ==
[FROM stmt()] after lex() -1
预期输出应显示语法中每个非终结符的所有语句,例如 Enter <stmt>
和 Exit <stmt>
等。
(我看到的)主要问题是它将下一个词位定义为“==”而不是“=”,因此解析器无法识别它。
关于为什么会发生这种情况有什么想法吗?
lookup(char ch)
中switch
的情况=
没有break
。您可以尝试添加一个。
我目前正在尝试构建一个递归下降解析器来解析赋值语句,例如 a = 4 + b
。语法如下
<stmt> → id = <expr>
<expr> → <term> {(+ | -) <term>}
<term> → <factor> {(* | /) <factor>}
<factor> → id | int_constant | ( <expr> )
此语法应接受诸如 sum = sum + 100 * (a - b)
ddddd
djdjdjd
// THIS IS ALL TEXTBOOK CODE
/* front.c - a lexical analyzer system for simple
arithmetic expressions */
#include <stdio.h>
#include <ctype.h>
/* Global declarations */
/* Variables */
int charClass;
char lexeme [100];
char nextChar;
int lexLen;
int token;
int nextToken;
FILE *in_fp, *fopen();
/* Function declarations */
void addChar();
void getChar();
void getNonBlank();
int lex();
/* Character classes */
#define LETTER 0
#define DIGIT 1
#define UNKNOWN 99
/* Token codes */
#define INT_LIT 10
#define IDENT 11
#define ASSIGN_OP 20
#define ADD_OP 21
#define SUB_OP 22
#define MULT_OP 23
#define DIV_OP 24
#define LEFT_PAREN 25
#define RIGHT_PAREN 26
// function prototypes for just expr()
void expr();
void stmt();
// define the grammar
/*
<expr> → <term> {(+ | -) <term>}
<term> → <factor> {(* | /) <factor>}
<factor> → id | int_constant | ( <expr> )
*/
/******************************************************/
/* main driver */
int main() {
/* Open the input data file and process its contents */
if ((in_fp = fopen("front.in", "r")) == NULL)
// open the file
printf("ERROR - cannot open front.in \n");
else {
// get characters and lex()?
getChar();
do {
printf("[FROM main()] before lex() %d \n",nextToken);
lex();
printf("[FROM main()] %d \n\n", nextToken);
stmt();
} while (nextToken != EOF);
}
// seems like the tokenizer is already implemented for us
-> will need to parse as tokens come in
}
void error(){
printf("ERROR: \n");
}
// the stmt function
void stmt() {
printf("Enter <stmt>\n\n");
if (nextToken == IDENT){
printf("[FROM stmt()] found identifier. \n");
printf("[FROM stmt()] before lex() %d \n", nextChar);
lex(); //error in here
printf("[FROM stmt()] after lex() %d \n\n", nextToken);
}
//printf("[FROM stmt()] nxt token %d\n\n", nextToken);
}
void factor(){
// must choose between two RHSs
printf("Enter <factor>\n");
// determine the RHSs
if(nextToken == IDENT || nextToken == INT_LIT){
lex(); // get next token
}
// if the RHS is <expr> tell the lex to pass over the
left parenthesis and call expr and then check for right
parentheses
else {
if(nextToken == LEFT_PAREN){
lex();
expr();
if(nextToken == RIGHT_PAREN){
lex();
}else {
error(); // should exist at the very top
}
}
else {
// it wasnt an id or int or left parentheses
error();
}
}
printf("Exit <factor>\n");
}
// parse term
void term() {
printf("Enter <term>\n");
// parse the first factor
factor();
// as long as the next is * or / get the next token and parse the next factor
while (nextToken == MULT_OP || nextToken == DIV_OP){
lex(); // get the next token
factor(); // parse the next factor
}
printf("Enter <expr> \n");
}
// parse expression
void expr() {
printf("Enter <expr> \n");
// parse first term
term();
// as long as the next token is + or -, get the next token and parse the next term
while(nextToken == ADD_OP || nextToken == SUB_OP){
// updates next token
lex();
// proocesses the term
term();
}
printf("Exit <expr> \n");
}
/*****************************************************/
/* lookup - a function to lookup operators and parentheses
and return the token */
int lookup(char ch) {
switch (ch) {
case '(':
addChar();
nextToken = LEFT_PAREN;
break;
case ')':
addChar();
nextToken = RIGHT_PAREN;
break;
case '+':
addChar();
nextToken = ADD_OP;
break;
case '-':
addChar();
nextToken = SUB_OP;
break;
case '*':
addChar();
nextToken = MULT_OP;
break;
case '/':
addChar();
nextToken = DIV_OP;
break;
case '=':
// if the equal sign then set as assign op -> not sure
what add char does
printf("[FROM lookup()] found the = \n");
addChar();
nextToken = ASSIGN_OP;
default:
addChar();
nextToken = EOF;
break;
}
return nextToken;
}
/*****************************************************/
/* addChar - a function to add nextChar to lexeme */
void addChar() {
if (lexLen <= 98) {
lexeme[lexLen++] = nextChar;
lexeme[lexLen] = 0;
}
else
printf("Error - lexeme is too long \n");
}
/*****************************************************/
/* getChar - a function to get the next character of
input and determine its character class */
void getChar() {
if ((nextChar = getc(in_fp)) != EOF){
//printf("\n[FROM getChar()] nextChar = %c \n\n",nextChar);
if (isalpha(nextChar))
charClass = LETTER;
else if (isdigit(nextChar))
charClass = DIGIT;
else charClass = UNKNOWN;
}
else
charClass = EOF;
}
/*****************************************************/
/* getNonBlank - a function to call getChar until it
returns a non-whitespace character */
void getNonBlank() {
while (isspace(nextChar))
getChar();
}
/*****************************************************/
/* lex - a simple lexical analyzer for arithmetic
expressions */
int lex() {
lexLen = 0;
getNonBlank();
switch (charClass) {
/* Parse identifiers */
case LETTER:
addChar();
getChar();
while (charClass == LETTER || charClass == DIGIT) {
addChar();
getChar();
}
nextToken = IDENT;
break;
/* Parse integer literals */
case DIGIT:
addChar();
getChar();
while (charClass == DIGIT) {
addChar();
getChar();
}
nextToken = INT_LIT;
break;
/* Parentheses and operators */
case UNKNOWN:
printf("[FROM lex()] %c\n",nextChar);
lookup(nextChar);
getChar();
break;
/* EOF */
case EOF:
nextToken = EOF;
lexeme[0] = 'E';
lexeme[1] = 'O';
lexeme[2] = 'F';
lexeme[3] = 0;
break;
} /* End of switch */
printf("Next token is: %d, Next lexeme is %s\n", nextToken, lexeme);
return nextToken;
} /* End of function lex */
这段代码(在文件front.in中)的输入是:
myVar = 5
我得到的输出是:
[FROM main()] before lex() 0
Next token is: 11, Next lexeme is myVar
[FROM main()] 11
Enter <stmt>
[FROM stmt()] found identifier.
[FROM stmt()] before lex() 32
[FROM lex()] =
[FROM lookup()] found the =
Next token is: -1, Next lexeme is ==
[FROM stmt()] after lex() -1
预期输出应显示语法中每个非终结符的所有语句,例如 Enter <stmt>
和 Exit <stmt>
等。
(我看到的)主要问题是它将下一个词位定义为“==”而不是“=”,因此解析器无法识别它。
关于为什么会发生这种情况有什么想法吗?
lookup(char ch)
中switch
的情况=
没有break
。您可以尝试添加一个。