Merge branch 'lexer' into dev
This commit is contained in:
commit
2e93003745
2 changed files with 113 additions and 35 deletions
|
|
@ -3,6 +3,7 @@
|
||||||
#include <ctype.h>
|
#include <ctype.h>
|
||||||
#include <stdbool.h>
|
#include <stdbool.h>
|
||||||
#include <stddef.h>
|
#include <stddef.h>
|
||||||
|
#include <stdio.h>
|
||||||
#include <stdlib.h>
|
#include <stdlib.h>
|
||||||
#include <string.h>
|
#include <string.h>
|
||||||
|
|
||||||
|
|
@ -28,33 +29,95 @@ static void save_state(char *stream, ssize_t i)
|
||||||
*/
|
*/
|
||||||
static bool is_special_char(char c)
|
static bool is_special_char(char c)
|
||||||
{
|
{
|
||||||
return c == '\'' || c == '\n' || c == ';';
|
return c == '\'' || c == '\n' || c == ';' || c == EOF;
|
||||||
}
|
}
|
||||||
|
|
||||||
/* @return: true if a keyword from the grammar was found, false otherwise.
|
/* @brief: if a special character is found at [begin],
|
||||||
|
* [tok->token_type] is set accordingly
|
||||||
*
|
*
|
||||||
*/
|
*/
|
||||||
static bool is_keyword(char *stream, ssize_t i)
|
static void set_token_spechar(struct token *tok, char *begin, ssize_t size)
|
||||||
{
|
{
|
||||||
if (i == 2)
|
if (size != 1)
|
||||||
|
return;
|
||||||
|
if (begin[0] == EOF)
|
||||||
{
|
{
|
||||||
return strcmp(stream, "if") == 0 || strcmp(stream, "fi") == 0;
|
tok->type = TOKEN_EOF;
|
||||||
}
|
}
|
||||||
if (i == 4)
|
else if (begin[0] == ';')
|
||||||
{
|
{
|
||||||
return strcmp(stream, "then") || strcmp(stream, "else")
|
tok->type = TOKEN_NEWLINE;
|
||||||
|| strcmp(stream, "elif");
|
}
|
||||||
|
else if (begin[0] == '\'')
|
||||||
|
{
|
||||||
|
tok->type = TOKEN_QUOTE;
|
||||||
|
}
|
||||||
|
else if (begin[0] == ';')
|
||||||
|
{
|
||||||
|
tok->type = TOKEN_SEMICOLON;
|
||||||
}
|
}
|
||||||
return false;
|
|
||||||
}
|
}
|
||||||
|
|
||||||
char *new_token(char *begin, ssize_t size)
|
/* @brief: if a keyword is found at [begin],
|
||||||
|
* [tok->token_type] is set accordingly
|
||||||
|
*
|
||||||
|
*/
|
||||||
|
static void set_token_keyword(struct token *tok, char *begin, ssize_t size)
|
||||||
{
|
{
|
||||||
char *res = calloc(size + 1, sizeof(char));
|
if (tok->type != TOKEN_NULL)
|
||||||
if (res == NULL)
|
return;
|
||||||
|
if (strncmp(begin, "if", size) == 0)
|
||||||
|
{
|
||||||
|
tok->type = TOKEN_IF;
|
||||||
|
}
|
||||||
|
else if (strncmp(begin, "fi", size) == 0)
|
||||||
|
{
|
||||||
|
tok->type = TOKEN_FI;
|
||||||
|
}
|
||||||
|
else if (strncmp(begin, "then", size) == 0)
|
||||||
|
{
|
||||||
|
tok->type = TOKEN_THEN;
|
||||||
|
}
|
||||||
|
else if (strncmp(begin, "else", size) == 0)
|
||||||
|
{
|
||||||
|
tok->type = TOKEN_ELSE;
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
/* @brief: if token_type has not yet been set, then it is a TOKEN_WORD
|
||||||
|
* Also allocates the data and fills it.
|
||||||
|
*/
|
||||||
|
static void set_token_word(struct token *tok, char *begin, ssize_t size)
|
||||||
|
{
|
||||||
|
if (tok->type == TOKEN_NULL)
|
||||||
|
{
|
||||||
|
tok->data = calloc(size + 1, sizeof(char));
|
||||||
|
if (tok->data == NULL)
|
||||||
|
return;
|
||||||
|
strncpy(tok->data, begin, size);
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
struct token *new_token(char *begin, ssize_t size)
|
||||||
|
{
|
||||||
|
struct token *tok = calloc(1, sizeof(struct token));
|
||||||
|
if (tok == NULL)
|
||||||
return NULL;
|
return NULL;
|
||||||
strncpy(res, begin, size);
|
|
||||||
return res;
|
set_token_spechar(tok, begin, size);
|
||||||
|
set_token_keyword(tok, begin, size);
|
||||||
|
set_token_word(tok, begin, size);
|
||||||
|
|
||||||
|
return tok;
|
||||||
|
}
|
||||||
|
|
||||||
|
void free_token(struct token *tok)
|
||||||
|
{
|
||||||
|
if (tok == NULL)
|
||||||
|
return;
|
||||||
|
if (tok->data != NULL)
|
||||||
|
free(tok->data);
|
||||||
|
free(tok);
|
||||||
}
|
}
|
||||||
|
|
||||||
char *stream_init(void)
|
char *stream_init(void)
|
||||||
|
|
@ -77,7 +140,7 @@ char *stream_init(void)
|
||||||
return stream;
|
return stream;
|
||||||
}
|
}
|
||||||
|
|
||||||
char *peek_token(void)
|
struct token *peek_token(void)
|
||||||
{
|
{
|
||||||
char *stream = stream_init();
|
char *stream = stream_init();
|
||||||
|
|
||||||
|
|
@ -95,18 +158,13 @@ char *peek_token(void)
|
||||||
{
|
{
|
||||||
break;
|
break;
|
||||||
}
|
}
|
||||||
else if (is_keyword(stream, i))
|
|
||||||
{
|
|
||||||
i++;
|
|
||||||
break;
|
|
||||||
}
|
|
||||||
i++;
|
i++;
|
||||||
}
|
}
|
||||||
|
|
||||||
return new_token(stream, i);
|
return new_token(stream, i);
|
||||||
}
|
}
|
||||||
|
|
||||||
char *pop_token(void)
|
struct token *pop_token(void)
|
||||||
{
|
{
|
||||||
char *stream = stream_init();
|
char *stream = stream_init();
|
||||||
|
|
||||||
|
|
@ -124,11 +182,6 @@ char *pop_token(void)
|
||||||
{
|
{
|
||||||
break;
|
break;
|
||||||
}
|
}
|
||||||
else if (is_keyword(stream, i))
|
|
||||||
{
|
|
||||||
i++;
|
|
||||||
break;
|
|
||||||
}
|
|
||||||
i++;
|
i++;
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
|
||||||
|
|
@ -3,19 +3,39 @@
|
||||||
|
|
||||||
#include <sys/types.h>
|
#include <sys/types.h>
|
||||||
|
|
||||||
|
enum token_type
|
||||||
|
{
|
||||||
|
TOKEN_NULL = 0,
|
||||||
|
TOKEN_EOF,
|
||||||
|
TOKEN_WORD,
|
||||||
|
TOKEN_NEWLINE,
|
||||||
|
TOKEN_QUOTE,
|
||||||
|
TOKEN_SEMICOLON,
|
||||||
|
TOKEN_IF,
|
||||||
|
TOKEN_THEN,
|
||||||
|
TOKEN_ELSE,
|
||||||
|
TOKEN_FI
|
||||||
|
};
|
||||||
|
|
||||||
|
struct token
|
||||||
|
{
|
||||||
|
enum token_type type;
|
||||||
|
char *data;
|
||||||
|
};
|
||||||
|
|
||||||
/*
|
/*
|
||||||
* @brief: returns the next (newly allocated) token without consuming it.
|
* @brief: returns the next (newly allocated) token without consuming it.
|
||||||
* if end of input is reached, returns EOF.
|
* if end of input is reached, returns a token of type TOKEN_EOF.
|
||||||
*
|
*
|
||||||
*/
|
*/
|
||||||
char *peek_token(void);
|
struct token *peek_token(void);
|
||||||
|
|
||||||
/*
|
/*
|
||||||
* @brief: returns the next (newly allocated) token and consumes it.
|
* @brief: returns the next (newly allocated) token and consumes it.
|
||||||
* if end of input is reached, returns EOF.
|
* if end of input is reached, returns a token of type TOKEN_EOF.
|
||||||
*
|
*
|
||||||
*/
|
*/
|
||||||
char *pop_token(void);
|
struct token *pop_token(void);
|
||||||
|
|
||||||
/*
|
/*
|
||||||
* @warning: NOT IMPLEMENTED.
|
* @warning: NOT IMPLEMENTED.
|
||||||
|
|
@ -23,16 +43,21 @@ char *pop_token(void);
|
||||||
* @note: maybe usefull for subshells.
|
* @note: maybe usefull for subshells.
|
||||||
*/
|
*/
|
||||||
|
|
||||||
char *get_token_str(void);
|
struct token *get_token_str(void);
|
||||||
|
|
||||||
/*
|
/*
|
||||||
* @brief: return a newly allocated token.
|
* @brief: return a newly allocated token, with the corresponding type.
|
||||||
* This token contains [size] chars, starting from [begin].
|
* The data contains [size] char, starting from [begin].
|
||||||
*
|
*
|
||||||
* @return: NULL on error, null-terminated char* otherwise.
|
* @return: NULL on error, a token otherwise.
|
||||||
*
|
*
|
||||||
*/
|
*/
|
||||||
char *new_token(char *begin, ssize_t size);
|
struct token *new_token(char *begin, ssize_t size);
|
||||||
|
|
||||||
|
/* @brief: frees the token given in argument
|
||||||
|
*
|
||||||
|
*/
|
||||||
|
void free_token(struct token *tok);
|
||||||
|
|
||||||
/*
|
/*
|
||||||
* @brief: checks if the stream used for the last token creation is empty.
|
* @brief: checks if the stream used for the last token creation is empty.
|
||||||
|
|
|
||||||
Loading…
Add table
Add a link
Reference in a new issue