aboutsummaryrefslogtreecommitdiff
path: root/src/lexer/lexer.c
blob: 907dc7079cc84c714f61fca726df10837518d9c2 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
/* ************************************************************************** */
/*                                                                            */
/*                                                        :::      ::::::::   */
/*   lexer.c                                            :+:      :+:    :+:   */
/*                                                    +:+ +:+         +:+     */
/*   By: nahaddac <nahaddac@student.42.fr>          +#+  +:+       +#+        */
/*                                                +#+#+#+#+#+   +#+           */
/*   Created: 2020/07/16 08:18:25 by nahaddac          #+#    #+#             */
/*   Updated: 2020/09/13 17:45:30 by charles          ###   ########.fr       */
/*                                                                            */
/* ************************************************************************** */

#include "lexer.h"

// len until meaningful character for non quoted str
int 			len_until_sep(char *input)
{
	int i;

	i = -1;
	while (input[++i])
	{
		if (input[i] == '\\')
		{
			i += 2;
			if (ft_isblank(input[i]))
				return (i + 1 + lexer_space(&input[i + 1]));
			else if (input[i] != '\'' || input[i] != '"')
				i += len_until_sep(&input[i]);
			return (i);
		}
		if (lexer_sep(input[i]))
			return (i);
		if (input[i] == '\'' || input[i] == '"')
			return (i);
		if (ft_isblank(input[i]))
			return (i + 1 + lexer_space(&input[i + 1]));
	}
	return (i);
}

// token content length
int				tok_len(char *input)
{
	int i;

	i = 0;
	if (input[i] == '\\' && lexer_sep(input[i + 1]))
	{
		i += 2;
		return (i + lexer_space(&input[i]));
	}
	if (input[i] == '(' || input[i] == ')')
		return (i + 1);
	if (lexer_sep(input[i])) // fucked on & alone
	{
		if (input[i] == input[i + 1])
			i++;
		return (i + 1 + lexer_space(&input[i + 1]));
	}
	if (input[i] == '\'' || input[i] == '"')
		return (quote_len(input, i));
	if (ft_isblank(input[i]))
		return (i + 1 + lexer_space(&input[i + 1]));
	return (len_until_sep(&input[i]));
}

/*
** \brief interate over input
**        get the number of character for the current token
**        create a token from a substring in input
**        assign a tag to the token
*/

t_tok_lst				*create_token_list(char *input, t_tok_lst **lst)
{
	t_tok_lst	*tok;
	size_t 		i;
	size_t		j;
	size_t		len;

	len = ft_strlen(input);
	i = 0;
	while (i < len)
	{
		j = tok_len(&input[i]);
		tok = tok_lst_new_until(0, input + i, j);
		tok->tag = tok_assign_tag(tok->content);
		if (tok->tag == 0)
			tok->tag = tok_assign_str(tok);
		if (!ft_isblank(tok->content[0])) // ?
			tok_lst_push_back(lst, tok);
		i += j;
	}
	return (*lst);
}

/*
** \brief        Create a token list from a string
** \param input  Input string
** \return       The created tokens or NULL on error
*/

t_tok_lst        			*lexer(char *input)
{
	t_tok_lst	*lst;

	if (!input)
		return (NULL);
	lst = NULL;
	lst = create_token_list(input, &lst);
	lst = lexer_trim_out(lst);
	return (lst);
}

/* int 					check_input_out(char *input) */
/* { */
/* 	int i; */
/* 	int j; */
/*  */
/* 	i = 0; */
/* 	while(input[i] != '\0') */
/* 	{ */
/* 		j = 0; */
/* 		j += len_until_sep(&input[i]); */
/* 		if (j != 0) */
/* 			return(j); */
/* 		i += j; */
/* 		j = check_input(&input[i]); */
/* 		return(j); */
/* 	} */
/* 	return(0); */
/* } */