From 373e240e857974480732adb388cf46ef3eb2e59b Mon Sep 17 00:00:00 2001
From: gazhonsepaskwa <gaz.honsepaskwa@gmail.com>
Date: Sat, 8 Feb 2025 12:37:48 +0100
Subject: [PATCH] unstick update && syntax check

---
 srcs/parsing/parser.c                       |  2 -
 srcs/parsing/syntax.c                       | 79 ++++++++++++++++++---
 srcs/parsing/tokenizer/token_and_pres.c     |  6 +-
 srcs/parsing/tokenizer/tokenizer.c          | 23 ++++++
 srcs/parsing/tokenizer/tokenizer_utils.c    | 30 ++++++--
 srcs/parsing/tokenizer/unstick_node_utils.c |  4 +-
 6 files changed, 124 insertions(+), 20 deletions(-)

diff --git a/srcs/parsing/parser.c b/srcs/parsing/parser.c
index efdb80a..bc29d78 100644
--- a/srcs/parsing/parser.c
+++ b/srcs/parsing/parser.c
@@ -46,8 +46,6 @@ t_ast_n	*parser(char *input, t_msh *msh)
 	lst = tokenize(input);
 	if (!lst)
 		return (NULL);
-	if (syntax_error(lst))
-		return (NULL);
 	if (DEBUG)
 	{
 		dio = drawio_init("ast.xml");
diff --git a/srcs/parsing/syntax.c b/srcs/parsing/syntax.c
index f783a12..120ee2e 100644
--- a/srcs/parsing/syntax.c
+++ b/srcs/parsing/syntax.c
@@ -19,35 +19,96 @@ int	only_operator(t_node *head)
 	return (0);
 }
 
-int	syntax_err_mess(char *token)
+int	syntax_err_mess(char *token_base, int selected)
 {
-	ft_fprintf(2, "minishell : syntax error near unexpected token `%s'\n",
-		token);
+	char *token;
+
+	token = ft_strdup(token_base);
+	if (selected == 0)
+		ft_fprintf(2, "minishell : syntax error : unexpected token `%s'\n",
+			token);
+	if (selected == 2)
+		ft_fprintf(2, "minishell : syntax error : unoppened token `%s'\n",
+			&token[1]);
+	token[1] = 0;
+	if (selected == 1)
+		ft_fprintf(2, "minishell : syntax error : unclosed token `%s'\n",
+			token);
+	free(token);
 	return (1);
 }
 
 int	unexpected_token(t_node *node)
 {
-	if (!ft_strncmp(node->val, "%", 1) || (!ft_strncmp(node->val, "&", 1)
-			&& ft_strncmp(node->val, "&&", 2)) || !ft_strncmp(node->val, ";", 1)
-		|| !ft_strncmp(node->val, "[", 1) || !ft_strncmp(node->val, "]", 1)
-		|| !ft_strncmp(node->val, "{", 1) || !ft_strncmp(node->val, "}", 1))
+	if ((!ft_strncmp(node->val, "&", 1) && ft_strncmp(node->val, "&&", 2))
+		|| !ft_strncmp(node->val, ";", 1) || !ft_strncmp(node->val, "[", 1)
+		|| !ft_strncmp(node->val, "]", 1) || !ft_strncmp(node->val, "{", 1)
+		|| !ft_strncmp(node->val, "}", 1))
 		return (1);
 	return (0);
 }
 
+int	check_unclosed(char *c, t_node *node)
+{
+	t_node *cpy;
+	int		count;
+
+	cpy = node;
+	count = 0;
+	while (cpy)
+	{
+		if (!ft_strncmp(&c[0], cpy->val, 1))
+			count++;
+		if (!ft_strncmp(&c[1], cpy->val, 1))
+			count--;
+		cpy = cpy->next;
+	}
+	if (count > 0)
+		return (1);
+	if (count < 0)
+		return (2);
+	return (0);
+}
+
+int check_unclosed_quote(char *c, t_node *node)
+{
+    t_node *cpy;
+    int     count;
+    int     len;
+
+    cpy = node;
+    count = 0;
+    while (cpy)
+    {
+        len = ft_strlen(cpy->val);
+        if (len > 0 && cpy->val[0] == c[0])
+        {
+            if (len == 1 || cpy->val[len - 1] != c[0])
+                count++;
+        }
+        cpy = cpy->next;
+    }
+    return (count % 2);
+}
+
 int	syntax_error(t_node *head)
 {
 	t_node	*cpy;
 
 	if (only_operator(head))
-		return (syntax_err_mess(head->val));
+		return (syntax_err_mess(head->val, 0));
 	cpy = head;
 	while (cpy)
 	{
 		if (unexpected_token(cpy))
-			return (syntax_err_mess(cpy->val));
+			return (syntax_err_mess(cpy->val, 0));
 		cpy = cpy->next;
 	}
+	if (check_unclosed("()", head) != 0)
+		return (syntax_err_mess("()", check_unclosed("()", head)));
+	if (check_unclosed_quote("\"", head) != 0)
+		return (syntax_err_mess("\"\"", 1));
+	if (check_unclosed_quote("'", head) != 0)
+		return (syntax_err_mess("'", 1)); 
 	return (0);
 }
diff --git a/srcs/parsing/tokenizer/token_and_pres.c b/srcs/parsing/tokenizer/token_and_pres.c
index fe1bf8d..5485077 100644
--- a/srcs/parsing/tokenizer/token_and_pres.c
+++ b/srcs/parsing/tokenizer/token_and_pres.c
@@ -39,9 +39,9 @@ t_token	get_token(char *str)
 {
 	t_token	token;
 
-	if (!ft_strncmp(str, "&", 1) || !ft_strncmp(str, "|", 1) || !ft_strncmp(str,
-			"(", 1) || !ft_strncmp(str, ")", 1) || !ft_strncmp(str, "<", 1)
-		|| !ft_strncmp(str, ">", 1))
+	if (!ft_strncmp(str, "&", 1) || !ft_strncmp(str, "|", 1)
+		|| !ft_strncmp(str, "(", 1) || !ft_strncmp(str, ")", 1)
+		|| !ft_strncmp(str, "<", 1) || !ft_strncmp(str, ">", 1))
 		token = OPERATOR;
 	else
 		token = WORD;
diff --git a/srcs/parsing/tokenizer/tokenizer.c b/srcs/parsing/tokenizer/tokenizer.c
index d6c587d..6cd4f5b 100644
--- a/srcs/parsing/tokenizer/tokenizer.c
+++ b/srcs/parsing/tokenizer/tokenizer.c
@@ -103,6 +103,23 @@ static int	stick_quote_node(t_node *head, char q)
 	return (1);
 }
 
+void debug_token_list(t_node* lst, char *msg)
+{
+	t_node *cpy;
+
+	cpy = lst;
+	if (DEBUG)
+	{
+		ft_debug("========================={%s}\n", msg);
+		while (cpy)
+		{
+			ft_debug("|%s|\n", cpy->val);
+			cpy = cpy->next;
+		}
+		ft_debug("=========================\n\n");
+	}
+}
+
 t_node	*tokenize(char *str)
 {
 	t_node	*head;
@@ -110,12 +127,18 @@ t_node	*tokenize(char *str)
 	head = tokenize_base(str);
 	if (!head)
 		return (NULL);
+	// debug_token_list(head, "tokenize_base");
 	if (!trim_nodes(head))
 		return (NULL);
+	// debug_token_list(head, "trim_nodes");
 	if (!unstick_nodes(head))
 		return (NULL);
+	// debug_token_list(head, "unstick_nodes");
 	stick_quote_node(head, 39);
 	stick_quote_node(head, '"');
+	debug_token_list(head, "tokenizer");
 	set_token(head);
+	if (syntax_error(head))
+		return (NULL);
 	return (head);
 }
diff --git a/srcs/parsing/tokenizer/tokenizer_utils.c b/srcs/parsing/tokenizer/tokenizer_utils.c
index 52b740a..786bd56 100644
--- a/srcs/parsing/tokenizer/tokenizer_utils.c
+++ b/srcs/parsing/tokenizer/tokenizer_utils.c
@@ -15,29 +15,49 @@
 int	is_meta(char c)
 {
 	if (c == '&' || c == '|' || c == '<' || c == '>' || c == '(' || c == ')'
-		|| c == '"' || c == 39)
+		|| c == '"' || c == 39 || c == ';' || c == '{' || c == '}' || c == '['
+		|| c == ']')
 		return (1);
 	return (0);
 }
 
+int unic(int *meta)
+{
+	int i;
+	int ref_meta;
+
+	i = -1;
+	ref_meta = meta[0];
+	while (meta[++i] != -1)
+		if (meta[i] != ref_meta)
+			return (0);
+	return (1);
+}
+
 int	is_sticked(char *val)
 {
 	int	i;
-	int	meta;
+	int	meta[100];
+	int meta_it;
 	int	unmeta;
 
 	i = 0;
-	meta = 0;
+	meta_it = 0;
+	meta[0] = -1;
 	unmeta = 0;
 	while (val[i])
 	{
 		if (is_meta(val[i]))
-			meta = 1;
+		{
+			meta[meta_it] = val[i];
+			meta_it++;
+		}
 		if (!is_meta(val[i]))
 			unmeta = 1;
 		i++;
 	}
-	if (meta && unmeta)
+	meta[meta_it] = -1;
+	if ((meta[0] != -1 && unmeta) || !unic(meta))
 		return (1);
 	return (0);
 }
diff --git a/srcs/parsing/tokenizer/unstick_node_utils.c b/srcs/parsing/tokenizer/unstick_node_utils.c
index 852ef60..a7668c5 100644
--- a/srcs/parsing/tokenizer/unstick_node_utils.c
+++ b/srcs/parsing/tokenizer/unstick_node_utils.c
@@ -17,9 +17,11 @@ char	*copy_meta_xor(char *val, int *copied, int rev)
 	int		i;
 	int		j;
 	char	*out;
+	char	ref;
 
 	i = 0;
-	while (is_meta(val[i]) ^ rev)
+	ref = val[0];
+	while ((is_meta(val[i]) && val[i] == ref) ^ rev)
 		i++;
 	*copied = i;
 	out = malloc(i + 1);