diff options
Diffstat (limited to 'src/lexer')
| -rw-r--r-- | src/lexer/lexer.c | 178 | ||||
| -rw-r--r-- | src/lexer/lexer_utils.c | 75 | ||||
| -rw-r--r-- | src/lexer/main.c | 15 |
3 files changed, 234 insertions, 34 deletions
diff --git a/src/lexer/lexer.c b/src/lexer/lexer.c index 7332b86..92cd34a 100644 --- a/src/lexer/lexer.c +++ b/src/lexer/lexer.c @@ -1,19 +1,177 @@ - #include "lexer.h" +int len_is_not_sep(char *input) +{ + int i; + + i = -1; + while(input[++i]) + { + if (lexer_sep(input[i])) + { + if (input[i + 1] == ' ') + while(input[++i] == ' ') + ; + return(i); + } + if (input[i] == '\'' || input[i] == '"') + return(i); + if (input[i] == ' ') + { + while(input[++i] == ' ') + ; + return (i); + } + } + return(i); +} + +int check_input(char *input) +{ + int i; + + i = 0; + if (lexer_sep(input[i])) + { + while(input[i] == input[i + 1]) + i++; + i += lexe_space(&input[i + 1]); + return (i + 1); + } + if (input[i] == 39 || input[i] == '"') + return(lexer_verif_entre_cote(input, i)); + if (input[i] == ' ') + { + while(input[++i] == ' ') + ; + return (i); + } + return(len_is_not_sep(&input[i])); +} + + +int check_input_out(char *input) +{ + int i; + int j; + + i = 0; + while(input[i] != '\0') + { + j = 0; + j += len_is_not_sep(&input[i]); + if (j != 0) + return(j); + i += j; + j = check_input(&input[i]); + return(j); + } + return(0); +} + +t_token *lexer_lst_token_str(char *input, int i, int j) +{ + t_token *lst_token; + + if (!(lst_token = malloc(sizeof(t_token) * 1))) + return (NULL); + lst_token->tag = 0; + lst_token->content = NULL; + if (!(lst_token->content = malloc(sizeof(char) * j + 1))) + return(0); + if (!(ft_strlcpy(lst_token->content, &input[i], j + 1))) + { + free(lst_token); + return(0); + } + //printf("%s-\n", lst_token->content); + return (lst_token); +} + +enum e_token_tag token_verif_stick(t_token *lst_token) +{ + int i; + + i = ft_strlen(lst_token->content); + + if (lst_token->content[i - 1] == ' ') + return(lst_token->tag); + return(lst_token->tag | LTAG_STICK); +} -char **lexer(char *input) +enum e_token_tag token_str_or_cote(t_token *lst_token) { - char **out; int i; + i = 0; + while(lst_token->content[i] != '\0') + { + if(lst_token->content[i] == '\'') + { + lst_token->tag = LTAG_STR_SINGLE; + return(token_verif_stick(lst_token)); + } + if(lst_token->content[i] == '"') + { + lst_token->tag = LTAG_STR_DOUBLE; + return(token_verif_stick(lst_token)); + } + else + { + lst_token->tag = LTAG_STR; + return(token_verif_stick(lst_token)); + } + i++; + } + return(0); +} + +t_token *push_token_enum_and_trim(t_token *lst_token) +{ + enum e_token_tag tk; + + tk = ret_token(lst_token->content, 0); + if (tk == 0) + { + lst_token->tag = token_str_or_cote(lst_token); + } + /* printf("%s-, %d\n",lst_token->content, (int)lst_token->tag); */ + return (lst_token); +} + +static t_ftlst *create_token_list(char *input, t_ftlst **lst) +{ + t_token *lst_token; + t_ftlst *new; + int i; + int j; + + i = 0; + while (i < (int)ft_strlen(input)) + { + j = 0; + j += check_input(&input[i]); + lst_token = lexer_lst_token_str(input,i,j); + lst_token = push_token_enum_and_trim(lst_token); + new = ft_lstnew((void *) lst_token); + ft_lstpush_back(lst, new); + i += j; + } + return (*lst); +} + +t_ftlst *lexer(char *input) +{ + t_ftlst **lst; + /* int i; */ + if (!input) return (0); - i = lexer_count_nb_element(input); - if (!(out = malloc(sizeof(char *) * i + 1))) - return (0); - out[i + 1] = NULL; - out = lexer_malloc_len_elem(input,i, out); - return(out); - + lst = malloc(sizeof(t_ftlst *) * 1); + if (!lst) + return(0); + *lst = create_token_list(input, lst); + /* i = ft_lstsize(*lst); */ + free(lst); + return (0); } diff --git a/src/lexer/lexer_utils.c b/src/lexer/lexer_utils.c index f028113..986db50 100644 --- a/src/lexer/lexer_utils.c +++ b/src/lexer/lexer_utils.c @@ -1,13 +1,42 @@ - #include "lexer.h" -int lexer_sep(char input) +enum e_token_tag ret_token_sep_redir_append(char *input, int i) +{ + if (input[i + 1] == '>') + return(LTAG_REDIR_APPEND); + return (LTAG_REDIR_OUT); + +} + +enum e_token_tag ret_token(char *input, int i) +{ + if (input[i] == ';') + return(LTAG_AND); + if (input[i] == '&') + return(LTAG_END); + if (input[i] == '|' && input[i + 1] == '|') + return(LTAG_OR); + if(input[i] == '|') + return(LTAG_PIPE); + if (input[i] == '>') + return(ret_token_sep_redir_append(input,i)); + if (input[i] == '<') + return(LTAG_REDIR_IN); + if (input[i] == '(') + return(LTAG_PARENT_OPEN); + if (input[i] == ')') + return(LTAG_PARENT_CLOSE); + return(0); + +} + +int lexer_sep(char input) { char *sep; int i; i = 0; - sep = ";&<>|"; + sep = ";&|><()"; while(sep[i] != '\0') { if(sep[i] == input) @@ -17,12 +46,40 @@ int lexer_sep(char input) return (0); } -int lexer_verif_entre_cote(char *input, int i) +int lexe_space(char *input) { - while((input[++i] != '"' || input[i] == '\'') && (input[i] != '\0')) - ; - i++; - if(input[i] == '"' || input[i] == '\'') - return(lexer_verif_entre_cote(input, i)); + int i; + + i=0; + while(input[i] == ' ') + i++; return(i); } + +static int lex_verif_simple_cote(char *input, int i) +{ + i++; + while(input[i] != '\0') + { + ++i; + if(input[i] == '\'') + break; + } + if (input[i + 1] == ' ') + while(input[i + 1] == ' ') + i++; + return(i + 1); +} + +int lexer_verif_entre_cote(char *input, int i) +{ + if(input[i] == '\'') + return(lex_verif_simple_cote(input, i)); + i++; + while(input[i] != '"' && (input[i] != '\0')) + ++i; + if (input[i + 1] == ' ') + while(input[i + 1] == ' ') + i++; + return(i + 1); +} diff --git a/src/lexer/main.c b/src/lexer/main.c deleted file mode 100644 index b341e93..0000000 --- a/src/lexer/main.c +++ /dev/null @@ -1,15 +0,0 @@ - -#include "lexer.h" - -/* int main(void) */ -/* { */ -/* char **out; */ -/* int i = -1; */ -/* */ -/* out = lexer("\"echo\" \"* login_x\"<<AUTHORS; echo && ; salut;\"echo\"\"* login_x\""); */ -/* //out = lexer("echo * login_x << AUTHORS&&cd Desktop"); */ -/* while(out[++i]) */ -/* printf("%s\n", out[i]);; */ -/* exit(0); */ -/* return (0); */ -/* } */ |