update: normed stuff

This commit is contained in:
maix0 2024-10-06 13:53:30 +02:00
parent 71d9a201b5
commit b058348d35
20 changed files with 388 additions and 193 deletions

View file

@ -6,7 +6,7 @@
/* By: maiboyer <maiboyer@student.42.fr> +#+ +:+ +#+ */
/* +#+#+#+#+#+ +#+ */
/* Created: 2024/10/02 19:04:32 by maiboyer #+# #+# */
/* Updated: 2024/10/05 18:56:12 by maiboyer ### ########.fr */
/* Updated: 2024/10/06 13:51:52 by maiboyer ### ########.fr */
/* */
/* ************************************************************************** */
@ -26,50 +26,53 @@ void push_token_and_create_new_chr(\
void push_token_and_set_new_chr(\
t_vec_token *tokens, t_token *tok, enum e_token ttype, char c);
static bool _dquote_inner2(t_token *ctok, t_token*out, char c)
{
if (me_isspace(c))
{
if (ctok->type == TOK_NONE)
*ctok = token_new(TOK_WHITESPACE);
if (ctok->type != TOK_WHITESPACE)
{
vec_token_push(&out->subtokens, *ctok);
*ctok = token_new(TOK_WHITESPACE);
}
string_push_char(&ctok->string, c);
}
else if (c == '$')
push_token_and_create_new(&out->subtokens, ctok, TOK_DOLLAR, "$");
else if (c == '(')
push_token_and_create_new(&out->subtokens, ctok, TOK_LPAREN, "(");
else if (c == ')')
push_token_and_create_new(&out->subtokens, ctok, TOK_RPAREN, ")");
else if (!(me_isalnum(c) || c == '_'))
push_token_and_create_new_chr(&out->subtokens, ctok, TOK_NALPHANUM, c);
else
return (false);
return (true);
}
t_error _parse_dquote_inner(t_token dquote, t_vec_token *append)
{
t_token ctok;
t_token out;
t_usize i;
char c;
out = token_new_meta(TOK_DQUOTE);
i = 0;
ctok = token_new_none();
while (dquote.string.buf[i] != '\0')
{
c = dquote.string.buf[i++];
if (me_isspace(c))
{
if (ctok.type == TOK_NONE)
ctok = token_new(TOK_WHITESPACE);
if (ctok.type != TOK_WHITESPACE)
{
vec_token_push(&out.subtokens, ctok);
ctok = token_new(TOK_WHITESPACE);
}
string_push_char(&ctok.string, c);
}
else if (c == '$')
push_token_and_create_new(&out.subtokens, &ctok, TOK_DOLLAR, "$");
else if (c == '(')
push_token_and_create_new(&out.subtokens, &ctok, TOK_LPAREN, "(");
else if (c == ')')
push_token_and_create_new(&out.subtokens, &ctok, TOK_RPAREN, ")");
else if (!(me_isalnum(c) || c == '_'))
push_token_and_create_new_chr(&out.subtokens, &ctok, TOK_NALPHANUM, c);
else
if (!_dquote_inner2(&ctok, &out, dquote.string.buf[i++]))
{
if (ctok.type == TOK_NONE)
ctok = token_new(TOK_NQUOTE);
if (ctok.type != TOK_NQUOTE)
{
vec_token_push(&out.subtokens, ctok);
ctok = token_new(TOK_NQUOTE);
}
string_push_char(&ctok.string, c);
ctok = (vec_token_push(&out.subtokens, ctok), \
token_new(TOK_NQUOTE));
string_push_char(&ctok.string, dquote.string.buf[i - 1]);
}
};
}
if (ctok.type != TOK_NONE)
vec_token_push(&out.subtokens, ctok);
if (ts_dq_apply_passes(out.subtokens, &out.subtokens))
@ -99,7 +102,7 @@ t_error ts_double_string_pass(t_vec_token input, t_vec_token *output)
if (_parse_dquote_inner(input.buffer[i], &out))
return (vec_token_free(input), ERROR);
}
else
else
vec_token_push(&out, token_clone(&input.buffer[i]));
i++;
}

View file

@ -6,7 +6,7 @@
/* By: maiboyer <maiboyer@student.42.fr> +#+ +:+ +#+ */
/* +#+#+#+#+#+ +#+ */
/* Created: 2024/10/02 19:04:32 by maiboyer #+# #+# */
/* Updated: 2024/10/04 19:09:45 by rparodi ### ########.fr */
/* Updated: 2024/10/06 13:42:09 by maiboyer ### ########.fr */
/* */
/* ************************************************************************** */
@ -38,7 +38,7 @@ t_error ts_double_amp(t_vec_token input, t_vec_token *output)
if (i + 1 >= input.len)
vec_token_push(&out, token_clone(&input.buffer[i]));
else if (input.buffer[i].type == TOK_AMP
&& input.buffer[i + 1].type == TOK_AMP)
&& input.buffer[i + 1].type == TOK_AMP)
{
vec_token_push(&out, token_new(TOK_AND));
i++;

View file

@ -6,7 +6,7 @@
/* By: maiboyer <maiboyer@student.42.fr> +#+ +:+ +#+ */
/* +#+#+#+#+#+ +#+ */
/* Created: 2024/10/02 19:04:32 by maiboyer #+# #+# */
/* Updated: 2024/10/04 19:09:30 by rparodi ### ########.fr */
/* Updated: 2024/10/06 13:42:24 by maiboyer ### ########.fr */
/* */
/* ************************************************************************** */
@ -38,7 +38,7 @@ t_error ts_double_lcarret(t_vec_token input, t_vec_token *output)
if (i + 1 >= input.len)
vec_token_push(&out, token_clone(&input.buffer[i]));
else if (input.buffer[i].type == TOK_LCARRET
&& input.buffer[i + 1].type == TOK_LCARRET)
&& input.buffer[i + 1].type == TOK_LCARRET)
{
vec_token_push(&out, token_new(TOK_DLCARRET));
i++;
@ -63,7 +63,7 @@ t_error ts_double_rcarret(t_vec_token input, t_vec_token *output)
if (i + 1 >= input.len)
vec_token_push(&out, token_clone(&input.buffer[i]));
else if (input.buffer[i].type == TOK_RCARRET
&& input.buffer[i + 1].type == TOK_RCARRET)
&& input.buffer[i + 1].type == TOK_RCARRET)
{
vec_token_push(&out, token_new(TOK_DRCARRET));
i++;

View file

@ -6,7 +6,7 @@
/* By: maiboyer <maiboyer@student.42.fr> +#+ +:+ +#+ */
/* +#+#+#+#+#+ +#+ */
/* Created: 2024/10/02 19:04:32 by maiboyer #+# #+# */
/* Updated: 2024/10/05 18:43:52 by maiboyer ### ########.fr */
/* Updated: 2024/10/06 13:40:36 by maiboyer ### ########.fr */
/* */
/* ************************************************************************** */
@ -16,6 +16,15 @@
#include "me/vec/vec_token.h"
#include "parser/token.h"
static void _fold_parens_helper(t_vec_token *v, enum e_token ty, t_const_str s)
{
t_token tmp;
tmp = token_new(ty);
string_push(&tmp.string, s);
vec_token_push(v, tmp);
}
/// This is a sample pass
///
/// There is a few rules the rest of the tokenizer machinery assumes
@ -31,7 +40,6 @@ t_error ts_double_lparen(t_vec_token input, t_vec_token *output)
{
t_vec_token out;
t_usize i;
t_token tmp;
i = 0;
out = vec_token_new(input.len, token_free);
@ -40,11 +48,9 @@ t_error ts_double_lparen(t_vec_token input, t_vec_token *output)
if (i + 1 >= input.len)
vec_token_push(&out, token_clone(&input.buffer[i]));
else if (input.buffer[i].type == TOK_LPAREN
&& input.buffer[i + 1].type == TOK_LPAREN)
&& input.buffer[i + 1].type == TOK_LPAREN)
{
tmp = token_new(TOK_DLPAREN);
string_push(&tmp.string, "((");
vec_token_push(&out, tmp);
_fold_parens_helper(&out, TOK_DLPAREN, "((");
i++;
}
else
@ -59,7 +65,6 @@ t_error ts_double_rparen(t_vec_token input, t_vec_token *output)
{
t_vec_token out;
t_usize i;
t_token tmp;
i = 0;
out = vec_token_new(input.len, token_free);
@ -68,11 +73,9 @@ t_error ts_double_rparen(t_vec_token input, t_vec_token *output)
if (i + 1 >= input.len)
vec_token_push(&out, token_clone(&input.buffer[i]));
else if (input.buffer[i].type == TOK_RPAREN
&& input.buffer[i + 1].type == TOK_RPAREN)
&& input.buffer[i + 1].type == TOK_RPAREN)
{
tmp = token_new(TOK_DRPAREN);
string_push(&tmp.string, "))");
vec_token_push(&out, tmp);
_fold_parens_helper(&out, TOK_DRPAREN, "))");
i++;
}
else

View file

@ -6,7 +6,7 @@
/* By: maiboyer <maiboyer@student.42.fr> +#+ +:+ +#+ */
/* +#+#+#+#+#+ +#+ */
/* Created: 2024/10/02 19:04:32 by maiboyer #+# #+# */
/* Updated: 2024/10/04 19:08:48 by rparodi ### ########.fr */
/* Updated: 2024/10/06 13:42:02 by maiboyer ### ########.fr */
/* */
/* ************************************************************************** */
@ -38,7 +38,7 @@ t_error ts_double_pipe(t_vec_token input, t_vec_token *output)
if (i + 1 >= input.len)
vec_token_push(&out, token_clone(&input.buffer[i]));
else if (input.buffer[i].type == TOK_PIPE
&& input.buffer[i + 1].type == TOK_PIPE)
&& input.buffer[i + 1].type == TOK_PIPE)
{
vec_token_push(&out, token_new(TOK_OR));
i++;

View file

@ -6,7 +6,7 @@
/* By: maiboyer <maiboyer@student.42.fr> +#+ +:+ +#+ */
/* +#+#+#+#+#+ +#+ */
/* Created: 2024/10/02 19:04:32 by maiboyer #+# #+# */
/* Updated: 2024/10/05 13:19:33 by maiboyer ### ########.fr */
/* Updated: 2024/10/06 13:43:38 by maiboyer ### ########.fr */
/* */
/* ************************************************************************** */
@ -16,7 +16,7 @@
#include "parser/passes.h"
#include "parser/token.h"
bool _can_be_varname(t_token *tok)
bool _can_be_varname(t_token *tok)
{
if (tok->type == TOK_DOLLAR)
return (true);
@ -35,7 +35,7 @@ bool _can_be_varname(t_token *tok)
/// thus it shouldn't be freed in case of error
/// - the output tokens may not be direct copy of the input tokens,
/// but need to be cloned (different allocations for stuff)
t_error ts_fold_expension(t_vec_token input, t_vec_token *output)
t_error ts_fold_expension(t_vec_token input, t_vec_token *output)
{
t_vec_token out;
t_usize i;
@ -49,10 +49,10 @@ t_error ts_fold_expension(t_vec_token input, t_vec_token *output)
vec_token_push(&out, token_clone(&input.buffer[i]));
else if (input.buffer[i].type == TOK_DOLLAR \
&& (input.buffer[i + 1].type == TOK_NQUOTE \
|| _can_be_varname(&input.buffer[i+1])))
|| _can_be_varname(&input.buffer[i + 1])))
{
tmp = token_clone(&input.buffer[++i]);
tmp.type= TOK_EXPENSION;
tmp.type = TOK_EXPENSION;
vec_token_push(&out, tmp);
}
else

View file

@ -6,7 +6,7 @@
/* By: maiboyer <maiboyer@student.42.fr> +#+ +:+ +#+ */
/* +#+#+#+#+#+ +#+ */
/* Created: 2024/10/02 19:04:32 by maiboyer #+# #+# */
/* Updated: 2024/10/05 18:05:49 by maiboyer ### ########.fr */
/* Updated: 2024/10/06 13:41:08 by maiboyer ### ########.fr */
/* */
/* ************************************************************************** */
@ -42,7 +42,8 @@ t_error ts_fold_no_quote(t_vec_token input, t_vec_token *output)
{
j = 0;
tmp = token_new(TOK_NQUOTE);
while (i + j < input.len && token_is_noquote(input.buffer[i + j].type))
while (i + j < input.len \
&& token_is_noquote(input.buffer[i + j].type))
string_push(&tmp.string, input.buffer[i + j++].string.buf);
vec_token_push(&out, tmp);
i += j;

View file

@ -6,7 +6,7 @@
/* By: maiboyer <maiboyer@student.42.fr> +#+ +:+ +#+ */
/* +#+#+#+#+#+ +#+ */
/* Created: 2024/10/02 19:04:32 by maiboyer #+# #+# */
/* Updated: 2024/10/05 18:02:25 by maiboyer ### ########.fr */
/* Updated: 2024/10/06 13:43:02 by maiboyer ### ########.fr */
/* */
/* ************************************************************************** */
@ -15,9 +15,12 @@
#include "me/vec/vec_token.h"
#include "parser/token.h"
bool _is_token_carret(enum e_token ttype)
bool _is_token_carret(enum e_token ttype)
{
return (ttype == TOK_LCARRET || ttype == TOK_DLCARRET || ttype == TOK_RCARRET || ttype == TOK_DRCARRET);
return (ttype == TOK_LCARRET \
|| ttype == TOK_DLCARRET \
|| ttype == TOK_RCARRET \
|| ttype == TOK_DRCARRET);
}
/// This is a sample pass
@ -41,14 +44,18 @@ t_error ts_fold_redir(t_vec_token input, t_vec_token *output)
out = vec_token_new(input.len, token_free);
while (i < input.len)
{
if (vec_token_get(&input, i + 1) != NULL && _is_token_carret(vec_token_get(&input, i)->type) && vec_token_get(&input, i + 1)->type == TOK_WORD)
if (vec_token_get(&input, i + 1) != NULL \
&& _is_token_carret(vec_token_get(&input, i)->type) \
&& vec_token_get(&input, i + 1)->type == TOK_WORD)
{
tmp = token_new_meta(TOK_REDIR);
vec_token_push(&tmp.subtokens, token_clone(vec_token_get(&input, i++)));
vec_token_push(&tmp.subtokens, token_clone(vec_token_get(&input, i++)));
vec_token_push(&tmp.subtokens, \
token_clone(vec_token_get(&input, i++)));
vec_token_push(&tmp.subtokens, \
token_clone(vec_token_get(&input, i++)));
vec_token_push(&out, tmp);
}
else
else
vec_token_push(&out, token_clone(&input.buffer[i++]));
}
vec_token_free(input);

View file

@ -6,7 +6,7 @@
/* By: maiboyer <maiboyer@student.42.fr> +#+ +:+ +#+ */
/* +#+#+#+#+#+ +#+ */
/* Created: 2024/10/02 19:04:32 by maiboyer #+# #+# */
/* Updated: 2024/10/04 18:32:00 by maiboyer ### ########.fr */
/* Updated: 2024/10/06 13:34:58 by maiboyer ### ########.fr */
/* */
/* ************************************************************************** */
@ -38,7 +38,7 @@ t_error ts_fold_whitespace(t_vec_token input, t_vec_token *output)
if (i + 1 >= input.len)
vec_token_push(&out, token_clone(&input.buffer[i]));
else if (input.buffer[i].type == TOK_WHITESPACE
&& input.buffer[i + 1].type == TOK_WHITESPACE)
&& input.buffer[i + 1].type == TOK_WHITESPACE)
;
else
vec_token_push(&out, token_clone(&input.buffer[i]));

View file

@ -0,0 +1,58 @@
/* ************************************************************************** */
/* */
/* ::: :::::::: */
/* paren_to_nquote.c :+: :+: :+: */
/* +:+ +:+ +:+ */
/* By: maiboyer <maiboyer@student.42.fr> +#+ +:+ +#+ */
/* +#+#+#+#+#+ +#+ */
/* Created: 2024/10/02 19:04:32 by maiboyer #+# #+# */
/* Updated: 2024/10/06 13:37:07 by maiboyer ### ########.fr */
/* */
/* ************************************************************************** */
#include "me/string/string.h"
#include "parser/passes.h"
#include "me/types.h"
#include "me/vec/vec_token.h"
#include "parser/token.h"
static void _paren_to_nquote_helper(t_vec_token *v, char c)
{
t_token tmp;
tmp = token_new(TOK_NQUOTE);
string_push_char(&tmp.string, c);
vec_token_push(v, tmp);
}
/// This is a sample pass
///
/// There is a few rules the rest of the tokenizer machinery assumes
/// theses function follows:
/// - the input vec WILL be freed when the function return, even in
/// case of error
/// - the output vector isn't populated if the function returns an error,
/// thus it shouldn't be freed in case of error
/// - the output tokens may not be direct copy of the input tokens,
/// but need to be cloned (different allocations for stuff)
t_error ts_paren_to_noquote(t_vec_token input, t_vec_token *output)
{
t_vec_token out;
t_usize i;
i = 0;
out = vec_token_new(input.len, token_free);
while (i < input.len)
{
if (input.buffer[i].type == TOK_LPAREN)
_paren_to_nquote_helper(&out, '(');
else if (input.buffer[i].type == TOK_RPAREN)
_paren_to_nquote_helper(&out, ')');
else
vec_token_push(&out, token_clone(&input.buffer[i]));
i++;
}
vec_token_free(input);
return (*output = out, NO_ERROR);
}

View file

@ -0,0 +1,64 @@
/* ************************************************************************** */
/* */
/* ::: :::::::: */
/* split_double_paren.c :+: :+: :+: */
/* +:+ +:+ +:+ */
/* By: maiboyer <maiboyer@student.42.fr> +#+ +:+ +#+ */
/* +#+#+#+#+#+ +#+ */
/* Created: 2024/10/02 19:04:32 by maiboyer #+# #+# */
/* Updated: 2024/10/06 13:38:43 by maiboyer ### ########.fr */
/* */
/* ************************************************************************** */
#include "me/string/string.h"
#include "parser/passes.h"
#include "me/types.h"
#include "me/vec/vec_token.h"
#include "parser/token.h"
static void _split_parens_helper(t_vec_token *v, enum e_token ty, char c)
{
t_token tmp;
tmp = token_new(ty);
string_push_char(&tmp.string, c);
vec_token_push(v, tmp);
}
/// This is a sample pass
///
/// There is a few rules the rest of the tokenizer machinery assumes
/// theses function follows:
/// - the input vec WILL be freed when the function return, even in
/// case of error
/// - the output vector isn't populated if the function returns an error,
/// thus it shouldn't be freed in case of error
/// - the output tokens may not be direct copy of the input tokens,
/// but need to be cloned (different allocations for stuff)
t_error ts_split_paren(t_vec_token input, t_vec_token *output)
{
t_vec_token out;
t_usize i;
i = 0;
out = vec_token_new(input.len, token_free);
while (i < input.len)
{
if (input.buffer[i].type == TOK_DLPAREN)
{
_split_parens_helper(&out, TOK_LPAREN, '(');
_split_parens_helper(&out, TOK_LPAREN, '(');
}
else if (input.buffer[i].type == TOK_DRPAREN)
{
_split_parens_helper(&out, TOK_RPAREN, ')');
_split_parens_helper(&out, TOK_RPAREN, ')');
}
else
vec_token_push(&out, token_clone(&input.buffer[i]));
i++;
}
vec_token_free(input);
return (*output = out, NO_ERROR);
}