new token types
This commit is contained in:
parent
bc7f8f3e8c
commit
bf59c5717e
2 changed files with 77 additions and 24 deletions
|
|
@ -14,7 +14,6 @@ static char *end_last_token;
|
|||
static ssize_t remaining_chars;
|
||||
|
||||
/* @brief: saves state for the next call the the lexer.
|
||||
*
|
||||
*/
|
||||
static void save_state(char *stream, ssize_t i)
|
||||
{
|
||||
|
|
@ -25,42 +24,84 @@ static void save_state(char *stream, ssize_t i)
|
|||
|
||||
/* @return: true if a special character from the grammar was found,
|
||||
* false otherwise.
|
||||
*
|
||||
*/
|
||||
static bool is_special_char(char c)
|
||||
{
|
||||
return c == '\'' || c == '\n' || c == ';' || c == EOF;
|
||||
if (c == EOF)
|
||||
return true;
|
||||
|
||||
char special_chars[] = "\n'\"`;#|&\\$(){}<>*";
|
||||
return strchr(special_chars, c) != NULL;
|
||||
}
|
||||
|
||||
/* @brief: if a special character is found at [begin],
|
||||
* [tok->token_type] is set accordingly
|
||||
*
|
||||
*/
|
||||
static void set_token_spechar(struct token *tok, char *begin, ssize_t size)
|
||||
{
|
||||
if (size != 1)
|
||||
return;
|
||||
if (begin[0] == EOF)
|
||||
switch (begin[0])
|
||||
{
|
||||
case EOF:
|
||||
tok->type = TOKEN_EOF;
|
||||
}
|
||||
else if (begin[0] == ';')
|
||||
{
|
||||
tok->type = TOKEN_NEWLINE;
|
||||
}
|
||||
else if (begin[0] == '\'')
|
||||
{
|
||||
tok->type = TOKEN_QUOTE;
|
||||
}
|
||||
else if (begin[0] == ';')
|
||||
{
|
||||
break;
|
||||
case ';':
|
||||
tok->type = TOKEN_SEMICOLON;
|
||||
break;
|
||||
case '\n':
|
||||
tok->type = TOKEN_NEWLINE;
|
||||
break;
|
||||
case '\'':
|
||||
tok->type = TOKEN_QUOTE;
|
||||
break;
|
||||
case '"':
|
||||
tok->type = TOKEN_DOUBLE_QUOTE;
|
||||
break;
|
||||
case '`':
|
||||
tok->type = TOKEN_GRAVE;
|
||||
break;
|
||||
case '#':
|
||||
tok->type = TOKEN_COMMENT;
|
||||
break;
|
||||
case '|':
|
||||
tok->type = TOKEN_PIPE;
|
||||
break;
|
||||
case '&':
|
||||
tok->type = TOKEN_AMPERSAND;
|
||||
break;
|
||||
case '\\':
|
||||
tok->type = TOKEN_BACKSLASH;
|
||||
break;
|
||||
case '$':
|
||||
tok->type = TOKEN_DOLLAR;
|
||||
break;
|
||||
case '(':
|
||||
tok->type = TOKEN_LEFT_PAREN;
|
||||
break;
|
||||
case ')':
|
||||
tok->type = TOKEN_RIGHT_PAREN;
|
||||
break;
|
||||
case '{':
|
||||
tok->type = TOKEN_LEFT_BRACKET;
|
||||
break;
|
||||
case '}':
|
||||
tok->type = TOKEN_RIGHT_BRACKET;
|
||||
break;
|
||||
case '<':
|
||||
tok->type = TOKEN_LESS;
|
||||
break;
|
||||
case '>':
|
||||
tok->type = TOKEN_GREATER;
|
||||
break;
|
||||
case '*':
|
||||
tok->type = TOKEN_STAR;
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
/* @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)
|
||||
{
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue