logistic-bot/minishell
1
0
Fork 0
mirror of https://codeberg.org/la-chouette/minishell.git synced 2025-12-06 07:28:09 +01:00
Code Issues Projects Releases Packages Wiki Activity Actions

wordsplit: increment index + rename rules

Browse source
This commit is contained in:
Khaïs COLIN 2025-02-19 18:48:20 +01:00
parent 6c8dd312c0
commit b23eb0f244
Signed by: logistic-bot
SSH key fingerprint: SHA256:RlpiqKeXpcPFZZ4y9Ou4xi2M8OhRJovIwDlbCaMsuAo
4 changed files with 43 additions and 32 deletions
Download patch file Download diff file Expand all files Collapse all files

16
src/parser/wordsplit/tokenizing_1_5.c
View file

@ -6,7 +6,7 @@
/* By: jguelen <marvin@42.fr> +#+ +:+ +#+ */
/* +#+#+#+#+#+ +#+ */
/* Created: 2025/02/19 13:20:01 by jguelen #+# #+# */
/* Updated: 2025/02/19 18:38:33 by khais ### ########.fr */
/* Updated: 2025/02/19 18:46:49 by khais ### ########.fr */
/* */
/* ************************************************************************** */
@ -21,7 +21,7 @@
** 1. If the end of input is recognized, the current token (if any) shall be
** delimited.
*/
bool token_rule_1(t_token_build *token_build, char *original)
bool rule_eof(t_token_build *token_build, char *original)
{
if (original[token_build->current_index] == '\0')
{
@ -36,12 +36,13 @@ bool token_rule_1(t_token_build *token_build, char *original)
** character is not quoted and can be used with the previous characters to form
** an operator, it shall be used as part of that (operator) token.
*/
bool token_rule_2(t_token_build *token_build, char *original)
bool rule_combine_operator(t_token_build *token_build, char *original)
{
if (token_build->currently_in_operator && token_build->quote == '\0'
&& is_operator_combo(token_build->cur_token->buffer, original[token_build->current_index]))
{
push_char(token_build, original[token_build->current_index]);
token_build->current_index++;
return (true);
}
return (false);
@ -52,7 +53,7 @@ bool token_rule_2(t_token_build *token_build, char *original)
** character cannot be used with the previous characters to form an operator,
** the operator containing the previous character shall be delimited.
*/
bool token_rule_3(t_token_build *token_build, char *original)
bool rule_operator_end(t_token_build *token_build, char *original)
{
if (token_build->currently_in_operator && token_build->quote == '\0'
&& !is_operator_combo(token_build->cur_token->buffer, original[token_build->current_index]))
@ -71,12 +72,13 @@ bool token_rule_3(t_token_build *token_build, char *original)
** operators, between the <quotation-mark> and the end of the quoted text. The
** token shall not be delimited by the end of the quoted field.
*/
bool token_rule_4(t_token_build *token_build, char *original)
bool rule_quote(t_token_build *token_build, char *original)
{
if (original[token_build->current_index] == '\'' || original[token_build->current_index] == '"')
{
quote_flip(token_build, original[token_build->current_index]);
return (true);
quote_flip(token_build, original[token_build->current_index]);
token_build->current_index++;
return (true);
}
return (false);

14
src/parser/wordsplit/tokenizing_6_10.c
View file

@ -6,7 +6,7 @@
/* By: jguelen <marvin@42.fr> +#+ +:+ +#+ */
/* +#+#+#+#+#+ +#+ */
/* Created: 2025/02/19 13:21:18 by jguelen #+# #+# */
/* Updated: 2025/02/19 18:37:05 by khais ### ########.fr */
/* Updated: 2025/02/19 18:48:03 by khais ### ########.fr */
/* */
/* ************************************************************************** */
@ -23,11 +23,12 @@
** The current character shall be used as the beginning of the next (operator)
** token.
*/
bool token_rule_6(t_token_build *token_build, char *original)
bool rule_new_operator(t_token_build *token_build, char *original)
{
if (token_build->quote == '\0' && is_operator_start(original[token_build->current_index]))
{
operator_start(token_build, original[token_build->current_index]);
token_build->current_index++;
return (true);
}
return (false);
@ -37,11 +38,12 @@ bool token_rule_6(t_token_build *token_build, char *original)
** 7. If the current character is an unquoted <blank>, any token containing the
** previous character is delimited and the current character shall be discarded.
*/
bool token_rule_7(t_token_build *token_build, char *original)
bool rule_delimit_blank(t_token_build *token_build, char *original)
{
if (is_blank(original[token_build->current_index]) && token_build->quote == '\0')
{
delimit(token_build);
token_build->current_index++;
return (true);
}
return (false);
@ -51,11 +53,12 @@ bool token_rule_7(t_token_build *token_build, char *original)
** 8. If the previous character was part of a word, the current character shall
** be appended to that word.
*/
bool token_rule_8(t_token_build *token_build, char *original)
bool rule_combine_word(t_token_build *token_build, char *original)
{
if (token_build->currently_in_word)
{
push_char(token_build, original[token_build->current_index]);
token_build->current_index++;
return (true);
}
return (false);
@ -64,8 +67,9 @@ bool token_rule_8(t_token_build *token_build, char *original)
/*
** 10. The current character is used as the start of a new word.
*/
bool token_rule_10(t_token_build *token_build, char *original)
bool rule_new_word(t_token_build *token_build, char *original)
{
new_word(token_build, original[token_build->current_index]);
token_build->current_index++;
return (true);
}

25
src/parser/wordsplit/wordsplit.c
View file

@ -5,14 +5,19 @@
/* +:+ +:+ +:+ */
/* By: khais <marvin@42.fr> +#+ +:+ +#+ */
/* +#+#+#+#+#+ +#+ */
/* Created: 2025/02/19 18:41/00 by khais #+# #+# */
/* Updated: 2025/02/19 18:41:00 by khais ### ########.fr */
/* Created: 2025/02/19 18:53/51 by khais #+# #+# */
/* Updated: 2025/02/19 18:53:51 by khais ### ########.fr */
/* */
/* ************************************************************************** */
#include "wordsplit.h"
#include "libft.h"
/*
** TODO: set flags
** TODO: rule 5 ($)
*/
/*
** split a string into words, respecting quotes etc.
**
@ -28,23 +33,23 @@ t_wordlist *minishell_wordsplit(char *original)
t_token_build token_build;
ft_bzero(&token_build, sizeof(t_token_build));
while (!token_rule_1(&token_build, original))
while (!rule_eof(&token_build, original))
{
if (token_rule_2(&token_build, original))
if (rule_combine_operator(&token_build, original))
continue ;
if (token_rule_3(&token_build, original))
if (rule_operator_end(&token_build, original))
continue ;
if (token_rule_4(&token_build, original))
if (rule_quote(&token_build, original))
continue ;
/* if (token_rule_5(&token_build, original)) */
/* continue ; */
if (token_rule_6(&token_build, original))
if (rule_new_operator(&token_build, original))
continue ;
if (token_rule_7(&token_build, original))
if (rule_delimit_blank(&token_build, original))
continue ;
if (token_rule_8(&token_build, original))
if (rule_combine_word(&token_build, original))
continue ;
token_rule_10(&token_build, original);
rule_new_word(&token_build, original);
}
if (token_build.quote != '\0')
return (wordlist_destroy(token_build.wordlist), NULL);

20
src/parser/wordsplit/wordsplit.h
View file

@ -5,8 +5,8 @@
/* +:+ +:+ +:+ */
/* By: khais <marvin@42.fr> +#+ +:+ +#+ */
/* +#+#+#+#+#+ +#+ */
/* Created: 2025/02/19 18:37/59 by khais #+# #+# */
/* Updated: 2025/02/19 18:37:59 by khais ### ########.fr */
/* Created: 2025/02/19 18:48/03 by khais #+# #+# */
/* Updated: 2025/02/19 18:48:03 by khais ### ########.fr */
/* */
/* ************************************************************************** */
@ -36,15 +36,15 @@ void push_char(t_token_build *token_build, char c);
void new_word(t_token_build *token_build, char c);
void quote_flip(t_token_build *token_build, char c);
void operator_start(t_token_build *token_build, char c);
bool token_rule_1(t_token_build *token_build, char *original);
bool token_rule_2(t_token_build *token_build, char *original);
bool token_rule_3(t_token_build *token_build, char *original);
bool token_rule_4(t_token_build *token_build, char *original);
bool rule_eof(t_token_build *token_build, char *original);
bool rule_combine_operator(t_token_build *token_build, char *original);
bool rule_operator_end(t_token_build *token_build, char *original);
bool rule_quote(t_token_build *token_build, char *original);
bool token_rule_5(t_token_build *token_build, char *original);
bool token_rule_6(t_token_build *token_build, char *original);
bool token_rule_7(t_token_build *token_build, char *original);
bool token_rule_8(t_token_build *token_build, char *original);
bool token_rule_10(t_token_build *token_build, char *original);
bool rule_new_operator(t_token_build *token_build, char *original);
bool rule_delimit_blank(t_token_build *token_build, char *original);
bool rule_combine_word(t_token_build *token_build, char *original);
bool rule_new_word(t_token_build *token_build, char *original);
t_wordlist *minishell_wordsplit(char *original);