简单实现了一个词法分析器，可以解析
money > 45
money >= 45
两条语句
enum token_enum_states{
Init = 0,
Id,//abc_
IntLiteral,//1123
GT,//>
GE,//>=
ERR
}token_enum_state = Init;
typedef void Fun_append(char ch);
typedef struct token{
enum token_enum_states type;
char text[20];
Fun_append* append;
}Token;
Token new_token;
static char index = 0;
void my_append(char ch){
new_token.text[index] = ch;
index++;
}
void init_index(){
char i;
index = 0;
for(i = 0; i < 20; i++){
new_token.text[i] = 0;
}
}
#define bool char
#define TRUE 1
#define FALSE 0
bool is_alpha(char ch){
if((ch >= 'a' && ch <= 'z') || (ch >= 'A' && ch <= 'Z') || ch == '_'){
return TRUE;
}
return FALSE;
}
bool is_digit(char ch){
if(ch >= '0' && ch <= '9'){
return TRUE;
}
return FALSE;
}
const char* const token_string[] = {
"Init",
"Id",//abc_
"IntLiteral",//1123
"GT",//>
"GE",//>=
};
enum token_enum_states initToken(char ch){
if(new_token.type != Init){
printf("%s %s\r\n",token_string[new_token.type],new_token.text);
}
init_index();
if(is_alpha(ch)){//第一个字符是字母
new_token.type = Id;
new_token.append(ch);
}else if(is_digit(ch)){//第一个字符是数字
new_token.type = IntLiteral;
new_token.append(ch);
}else if(ch == '>'){
new_token.type = GT;
new_token.append(ch);
}else{
new_token.type = Init;
}
return new_token.type;
}
char get_token_string(){
static int tokens_index = 0;
char ch;
char my_tokens[] = "age >= 45";
ch = my_tokens[tokens_index++];
if(ch == 0){
return -1;
}
return ch;
}
int main(){
char ch ;
new_token.append = &my_append;
while(1){
ch = get_token_string();
switch (token_enum_state){
case Init:
token_enum_state = initToken(ch);
break;
case Id:
if(is_alpha(ch) || is_digit(ch)){
new_token.append(ch);
}else{
token_enum_state = initToken(ch);
}
break;
case GT:
if(ch == '='){
new_token.type = GE;
new_token.append(ch);
}else{
token_enum_state = initToken(ch);
}
break;
case GE:
token_enum_state = initToken(ch);
break;
case IntLiteral:
if(is_digit(ch)){
new_token.append(ch);
}else{
token_enum_state = initToken(ch);
}
break;
}
if(ch < 0){
return 1;
}
}
}

#define Id_LENGTH 20
enum token_enum_states{
Init = 0,
Id,//abc_
IntLiteral,//1123
GT,//>
GE,//>=
ERR
}token_enum_state = Init;
typedef void Fun_append(char ch);
typedef struct token{
enum token_enum_states type;
char text[Id_LENGTH];
Fun_append* append;
}Token;
Token new_token;
static char index = 0;
void my_append(char ch){
new_token.text[index] = ch;
index++;
}
void init_index(){
char i;
index = 0;
for(i = 0; i < Id_LENGTH; i++){
new_token.text[i] = 0;
}
}
#define bool char
#define TRUE 1
#define FALSE 0
bool is_alpha(char ch){
if((ch >= 'a' && ch <= 'z') || (ch >= 'A' && ch <= 'Z') || ch == '_'){
return TRUE;
}
return FALSE;
}
bool is_digit(char ch){
if(ch >= '0' && ch <= '9'){
return TRUE;
}
return FALSE;
}
const char* const token_string[] = {
"Init",
"Id",//abc_
"IntLiteral",//1123
"GT",//>
"GE",//>=
};
enum token_enum_states initToken(char ch){
if(new_token.type != Init){
printf("%s %s\r\n",token_string[new_token.type],&new_token.text);
}
init_index();
if(is_alpha(ch)){//第一个字符是字母
new_token.type = Id;
new_token.append(ch);
}else if(is_digit(ch)){//第一个字符是数字
new_token.type = IntLiteral;
new_token.append(ch);
}else if(ch == '>'){
new_token.type = GT;
new_token.append(ch);
}else{
new_token.type = Init;
}
return new_token.type;
}
char get_token_string(){
static int tokens_index = 0;
char ch;
char my_tokens[] = "money > 45;age >= 45;";
//char my_tokens[] = "money >= 45";
ch = my_tokens[tokens_index++];
if(ch == 0){
return -1;
}
return ch;
}
int main(){
char ch ;
new_token.append = &my_append;
while(1){
ch = get_token_string();
switch (token_enum_state){
case Init:
token_enum_state = initToken(ch);
break;
case Id:
if(is_alpha(ch) || is_digit(ch)){
new_token.append(ch);
}else{
token_enum_state = initToken(ch);
}
break;
case GT:
if(ch == '='){
new_token.type = GE;
new_token.append(ch);
}else{
token_enum_state = initToken(ch);
}
break;
case GE:
token_enum_state = initToken(ch);
break;
case IntLiteral:
if(is_digit(ch)){
new_token.append(ch);
}else{
token_enum_state = initToken(ch);
}
break;
}
if(ch < 0){
return 1;
}
}
}

加入表达式 加减乘除 和关键字 char的判断
#include<stdio.h>
//===========================================================================================
const char* const token_string[] = {
"Init",
"Id",//abc_
"IntLiteral",//1123
"GT",//>
"GE",//>=
"Assignment",//=
"Plus",//+
"Minus",//-
"Star",//*
"Slash",// /
"CHAR",//char
};
#define Id_LENGTH 20
enum token_enum_states{
Init = 0,
Id,//abc_
IntLiteral,//1123
GT,//>
GE,//>=
Assignment,//=
Plus,//+
Minus,//-
Star,//*
Slash,// /
CHAR,//char
ERR,
CHAR_H,
CHAR_A,
CHAR_R,
}token_enum_state = Init;
typedef void Fun_append(char ch);
typedef struct token{
enum token_enum_states type;
char text[Id_LENGTH];
Fun_append* append;
}Token;
Token new_token;
static char index = 0;
void my_append(char ch){
new_token.text[index] = ch;
index++;
}
void init_index(){
char i;
index = 0;
for(i = 0; i < Id_LENGTH; i++){
new_token.text[i] = 0;
}
}
#define bool char
#define TRUE 1
#define FALSE 0
bool is_alpha(char ch){
if((ch >= 'a' && ch <= 'z') || (ch >= 'A' && ch <= 'Z') || ch == '_'){
return TRUE;
}
return FALSE;
}
bool is_digit(char ch){
if(ch >= '0' && ch <= '9'){
return TRUE;
}
return FALSE;
}
void save_tokens(){
if(new_token.type != Init){
printf("%s %s\r\n",token_string[new_token.type],&new_token.text);
}
}
enum token_enum_states initToken(char ch){
save_tokens();
init_index();
if(is_alpha(ch)){//第一个字符是字母
if(ch == 'c'){
new_token.type = CHAR_H;
}else{
new_token.type = Id;
}
new_token.append(ch);
}else if(is_digit(ch)){//第一个字符是数字
new_token.type = IntLiteral;
new_token.append(ch);
}else if(ch == '>'){
new_token.type = GT;
new_token.append(ch);
}else if(ch == '='){
new_token.type = Assignment;
new_token.append(ch);
}else if(ch == '+'){
new_token.type = Plus;
new_token.append(ch);
}else if(ch == '-'){
new_token.type = Minus;
new_token.append(ch);
}else if(ch == '*'){
new_token.type = Star;
new_token.append(ch);
}else if(ch == '/'){
new_token.type = Slash;
new_token.append(ch);
}else{
new_token.type = Init;
}
return new_token.type;
}
char get_token_string(){
static int tokens_index = 0;
char ch;
char my_tokens[] = "\
money > 45;\
age >= 45;\
char abc = 1+2-3*4/5;\
";
//char my_tokens[] = "money >= 45";
ch = my_tokens[tokens_index++];
if(ch == 0){
return -1;
}
return ch;
}
int Lexical_analyzer(){
char ch ;
new_token.append = &my_append;
while(1){
ch = get_token_string();
switch (token_enum_state){
case Init:
token_enum_state = initToken(ch);
break;
case Id:
if(is_alpha(ch) || is_digit(ch)){
new_token.append(ch);
}else{
token_enum_state = initToken(ch);
}
break;
case GT:
if(ch == '='){
new_token.type = GE;
new_token.append(ch);
}else{
token_enum_state = initToken(ch);
}
break;
case GE:
token_enum_state = initToken(ch);
break;
case IntLiteral:
if(is_digit(ch)){
new_token.append(ch);
}else{
token_enum_state = initToken(ch);
}
break;
case Assignment:
case Plus:
case Minus:
case Star:
case Slash:
token_enum_state = initToken(ch);
break;
case CHAR_H:
if (ch == 'h') {
token_enum_state = CHAR_A;
new_token.append(ch);
}else if(is_alpha(ch) || is_digit(ch)){
new_token.type = Id;
new_token.append(ch);
token_enum_state = Id;
}else{
token_enum_state = initToken(ch);
}
break;
case CHAR_A:
if (ch == 'a') {
token_enum_state = CHAR_R;
new_token.append(ch);
}else if(is_alpha(ch) || is_digit(ch)){
new_token.type = Id;
new_token.append(ch);
token_enum_state = Id;
}else{
token_enum_state = initToken(ch);
}
break;
case CHAR_R:
if (ch == 'r') {
token_enum_state = CHAR;
new_token.append(ch);
}else if(is_alpha(ch) || is_digit(ch)){
new_token.type = Id;
new_token.append(ch);
token_enum_state = Id;
}else{
token_enum_state = initToken(ch);
}
break;
case CHAR:
if(is_alpha(ch) || is_digit(ch)){
new_token.type = Id;
new_token.append(ch);
token_enum_state = Id;
}else{
new_token.type = CHAR;
token_enum_state = initToken(ch);
}
break;
}
if(ch < 0){
return 1;
}
}
}
int main(){
Lexical_analyzer();
}