From b2440780fb641afafd1ca489b177846957890441 Mon Sep 17 00:00:00 2001
From: Maieul BOYER <maieul.dev@familleboyer.net>
Date: Mon, 2 Sep 2024 17:43:53 +0200
Subject: [PATCH] Updated parser/src/scanner.c to be splitted

---
 parser/Filelist.parser.mk             |   6 +-
 parser/include/parser/inner/scanner.h |   8 +-
 parser/src/scanner.c                  | 334 --------------------------
 parser/src/scanner/heredoc.c          |  61 +++--
 parser/src/scanner/scan.c             |  47 ++++
 parser/src/scanner/scan_concat.c      |  52 ++++
 parser/src/scanner/scan_double_hash.c |  37 +++
 parser/src/scanner/scan_varname.c     | 133 ++++++++++
 parser/src/scanner/scan_word.c        |  92 +++++++
 parser/src/scanner/serialize.c        |   4 +-
 parser/src/stack/stack_summary.c      |   4 +-
 11 files changed, 415 insertions(+), 363 deletions(-)
 delete mode 100644 parser/src/scanner.c
 create mode 100644 parser/src/scanner/scan.c
 create mode 100644 parser/src/scanner/scan_concat.c
 create mode 100644 parser/src/scanner/scan_double_hash.c
 create mode 100644 parser/src/scanner/scan_varname.c
 create mode 100644 parser/src/scanner/scan_word.c

diff --git a/parser/Filelist.parser.mk b/parser/Filelist.parser.mk
index a9283fba..2d84a3fb 100644
--- a/parser/Filelist.parser.mk
+++ b/parser/Filelist.parser.mk
@@ -32,13 +32,17 @@ node/node_relevent                                                            \
 parser                                                                        \
 point/point_funcs1                                                            \
 point/point_funcs2                                                            \
-scanner                                                                       \
 scanner/advance_words                                                         \
 scanner/deserialize                                                           \
 scanner/heredoc                                                               \
 scanner/heredoc_functions                                                     \
 scanner/lifetime                                                              \
+scanner/scan                                                                  \
+scanner/scan_concat                                                           \
 scanner/scan_dollar                                                           \
+scanner/scan_double_hash                                                      \
+scanner/scan_varname                                                          \
+scanner/scan_word                                                             \
 scanner/serialize                                                             \
 stack/stack_add_link                                                          \
 stack/stack_funcs1                                                            \
diff --git a/parser/include/parser/inner/scanner.h b/parser/include/parser/inner/scanner.h
index 07c4817d..7426a6ac 100755
--- a/parser/include/parser/inner/scanner.h
+++ b/parser/include/parser/inner/scanner.h
@@ -6,7 +6,7 @@
 /*   By: maiboyer <maiboyer@student.42.fr>          +#+  +:+       +#+        */
 /*                                                +#+#+#+#+#+   +#+           */
 /*   Created: 2024/09/02 13:22:04 by maiboyer          #+#    #+#             */
-/*   Updated: 2024/09/02 13:27:44 by maiboyer         ###   ########.fr       */
+/*   Updated: 2024/09/02 17:40:15 by maiboyer         ###   ########.fr       */
 /*                                                                            */
 /* ************************************************************************** */
 
@@ -65,11 +65,17 @@ struct s_heredoc_scan_state
 typedef bool (*t_heredoc_content_func)(struct s_heredoc_scan_state *state);
 
 bool advance_word(TSLexer *lexer, t_string *unquoted_word);
+bool check_scan_concat(t_scanner *scanner, TSLexer *lexer, const bool *valid_symbols);
 bool scan(t_scanner *scanner, TSLexer *lexer, const bool *valid_symbols);
 bool scan_bare_dollar(TSLexer *lexer);
+bool scan_concat(t_scanner *scanner, TSLexer *lexer, const bool *valid_symbols);
+bool scan_double_hash(t_scanner *scanner, TSLexer *lexer, const bool *valid_symbols);
+bool scan_expansion_word(t_scanner *scanner, TSLexer *lexer, const bool *valid_symbols);
 bool scan_heredoc_content(t_scanner *scanner, TSLexer *lexer, enum e_token_type middle_type, enum e_token_type end_type);
+bool scan_heredoc_end(t_scanner *scanner, TSLexer *lexer);
 bool scan_heredoc_end_identifier(t_heredoc *heredoc, TSLexer *lexer);
 bool scan_heredoc_start(t_heredoc *heredoc, TSLexer *lexer);
+bool scan_varname(t_scanner *scanner, TSLexer *lexer, const bool *valid_symbols);
 void reset(t_scanner *scanner);
 
 #endif
diff --git a/parser/src/scanner.c b/parser/src/scanner.c
deleted file mode 100644
index 5d515557..00000000
--- a/parser/src/scanner.c
+++ /dev/null
@@ -1,334 +0,0 @@
-/* ************************************************************************** */
-/*                                                                            */
-/*                                                        :::      ::::::::   */
-/*   scanner.c                                          :+:      :+:    :+:   */
-/*                                                    +:+ +:+         +:+     */
-/*   By: maiboyer <maiboyer@student.42.fr>          +#+  +:+       +#+        */
-/*                                                +#+#+#+#+#+   +#+           */
-/*   Created: 2024/09/01 14:17:17 by maiboyer          #+#    #+#             */
-/*   Updated: 2024/09/02 16:25:19 by maiboyer         ###   ########.fr       */
-/*                                                                            */
-/* ************************************************************************** */
-
-#include "parser/inner/scanner.h"
-#include "me/char/char.h"
-#include "me/mem/mem.h"
-#include "me/string/string.h"
-#include "me/types.h"
-#include "me/vec/vec_heredoc.h"
-#include "parser/inner/heredoc.h"
-#include "parser/parser.h"
-#include <assert.h>
-
-bool scan(t_scanner *scanner, TSLexer *lexer, const bool *valid_symbols)
-{
-	if (valid_symbols[CONCAT] && !valid_symbols[ERROR_RECOVERY])
-	{
-		if (!(lexer->lookahead == 0 || me_isspace(lexer->lookahead) || lexer->lookahead == '>' || lexer->lookahead == '<' ||
-			  lexer->lookahead == ')' || lexer->lookahead == '(' || lexer->lookahead == ';' || lexer->lookahead == '&' ||
-			  lexer->lookahead == '|' || lexer->lookahead == '{' || lexer->lookahead == '}'))
-		{
-			lexer->result_symbol = CONCAT;
-			if (lexer->lookahead == '`')
-			{
-				lexer->mark_end(lexer);
-				lexer->advance(lexer, false);
-				while (lexer->lookahead != '`' && !lexer->eof(lexer))
-					lexer->advance(lexer, false);
-				if (lexer->eof(lexer))
-					return false;
-				if (lexer->lookahead == '`')
-					lexer->advance(lexer, false);
-				return me_isspace(lexer->lookahead) || lexer->eof(lexer);
-			}
-			if (lexer->lookahead == '\\')
-			{
-				lexer->mark_end(lexer);
-				lexer->advance(lexer, false);
-				if (lexer->lookahead == '"' || lexer->lookahead == '\'' || lexer->lookahead == '\\')
-					return true;
-				if (lexer->eof(lexer))
-					return false;
-			}
-			else
-				return true;
-		}
-	}
-
-	if (valid_symbols[IMMEDIATE_DOUBLE_HASH] && !valid_symbols[ERROR_RECOVERY])
-	{
-		if (lexer->lookahead == '#')
-		{
-			lexer->mark_end(lexer);
-			lexer->advance(lexer, false);
-			if (lexer->lookahead == '#')
-			{
-				lexer->advance(lexer, false);
-				if (lexer->lookahead != '}')
-				{
-					lexer->result_symbol = IMMEDIATE_DOUBLE_HASH;
-					lexer->mark_end(lexer);
-					return true;
-				}
-			}
-		}
-	}
-
-	if (valid_symbols[EMPTY_VALUE] &&
-		(me_isspace(lexer->lookahead) || lexer->eof(lexer) || lexer->lookahead == ';' || lexer->lookahead == '&'))
-		return (lexer->result_symbol = EMPTY_VALUE, true);
-
-	if ((valid_symbols[HEREDOC_BODY_BEGINNING] || valid_symbols[SIMPLE_HEREDOC_BODY]) && scanner->heredocs.len > 0 &&
-		!vec_heredoc_last(&scanner->heredocs)->started && !valid_symbols[ERROR_RECOVERY])
-		return scan_heredoc_content(scanner, lexer, HEREDOC_BODY_BEGINNING, SIMPLE_HEREDOC_BODY);
-
-	if (valid_symbols[HEREDOC_END] && scanner->heredocs.len > 0 && scan_heredoc_end_identifier(vec_heredoc_last(&scanner->heredocs), lexer))
-	{
-		t_heredoc *heredoc = vec_heredoc_last(&scanner->heredocs);
-		string_free(heredoc->current_leading_word);
-		string_free(heredoc->delimiter);
-		(void)vec_heredoc_pop(&scanner->heredocs, NULL);
-		return (lexer->result_symbol = HEREDOC_END, true);
-	}
-
-	if (valid_symbols[HEREDOC_CONTENT] && scanner->heredocs.len > 0 && vec_heredoc_last(&scanner->heredocs)->started &&
-		!valid_symbols[ERROR_RECOVERY])
-		return scan_heredoc_content(scanner, lexer, HEREDOC_CONTENT, HEREDOC_END);
-
-	if (valid_symbols[HEREDOC_START] && !valid_symbols[ERROR_RECOVERY] && scanner->heredocs.len > 0)
-		return scan_heredoc_start(vec_heredoc_last(&scanner->heredocs), lexer);
-
-	if ((valid_symbols[VARIABLE_NAME] || valid_symbols[FILE_DESCRIPTOR] || valid_symbols[HEREDOC_ARROW]) && !valid_symbols[ERROR_RECOVERY])
-	{
-		while (true)
-		{
-			if ((lexer->lookahead == ' ' || lexer->lookahead == '\t' || lexer->lookahead == '\r' ||
-				 (lexer->lookahead == '\n' && !valid_symbols[NEWLINE])) &&
-				!valid_symbols[EXPANSION_WORD])
-			{
-				lexer->advance(lexer, true);
-			}
-			else if (lexer->lookahead == '\\')
-			{
-				lexer->advance(lexer, true);
-
-				if (lexer->eof(lexer))
-				{
-					lexer->mark_end(lexer);
-					lexer->result_symbol = VARIABLE_NAME;
-					return true;
-				}
-
-				if (lexer->lookahead == '\r')
-					lexer->advance(lexer, true);
-				if (lexer->lookahead == '\n')
-					lexer->advance(lexer, true);
-				else
-				{
-					if (lexer->lookahead == '\\' && valid_symbols[EXPANSION_WORD])
-						goto expansion_word;
-					return false;
-				}
-			}
-			else
-				break;
-		}
-
-		// no '*', '@', '?', '-', '$', '0', '_'
-		if (!valid_symbols[EXPANSION_WORD] && (lexer->lookahead == '*' || lexer->lookahead == '@' || lexer->lookahead == '?' ||
-											   lexer->lookahead == '-' || lexer->lookahead == '0' || lexer->lookahead == '_'))
-		{
-			lexer->mark_end(lexer);
-			lexer->advance(lexer, false);
-			if (lexer->lookahead == '=' || lexer->lookahead == '[' || lexer->lookahead == ':' || lexer->lookahead == '-' ||
-				lexer->lookahead == '%' || lexer->lookahead == '#' || lexer->lookahead == '/')
-				return false;
-			if (valid_symbols[EXTGLOB_PATTERN] && me_isspace(lexer->lookahead))
-			{
-				lexer->mark_end(lexer);
-				lexer->result_symbol = EXTGLOB_PATTERN;
-				return true;
-			}
-		}
-
-		if (valid_symbols[HEREDOC_ARROW] && lexer->lookahead == '<')
-		{
-			lexer->advance(lexer, false);
-			if (lexer->lookahead == '<')
-			{
-				lexer->advance(lexer, false);
-				if (lexer->lookahead == '-')
-				{
-					lexer->advance(lexer, false);
-					t_heredoc heredoc = heredoc_new();
-					heredoc.allows_indent = true;
-					vec_heredoc_push(&scanner->heredocs, heredoc);
-					lexer->result_symbol = HEREDOC_ARROW_DASH;
-				}
-				else
-				{
-					t_heredoc heredoc = heredoc_new();
-					vec_heredoc_push(&scanner->heredocs, heredoc);
-					lexer->result_symbol = HEREDOC_ARROW;
-				}
-				return true;
-			}
-			return false;
-		}
-
-		bool is_number = true;
-		if (me_isdigit(lexer->lookahead))
-			lexer->advance(lexer, false);
-		else if (me_isalpha(lexer->lookahead) || lexer->lookahead == '_')
-		{
-			is_number = false;
-			lexer->advance(lexer, false);
-		}
-		else
-		{
-			if (lexer->lookahead == '{')
-				goto brace_start;
-			if (valid_symbols[EXPANSION_WORD])
-				goto expansion_word;
-			if (valid_symbols[EXTGLOB_PATTERN])
-				goto extglob_pattern;
-			return false;
-		}
-
-		while (true)
-		{
-			if (me_isdigit(lexer->lookahead))
-				lexer->advance(lexer, false);
-			else if (me_isalpha(lexer->lookahead) || lexer->lookahead == '_')
-			{
-				is_number = false;
-				lexer->advance(lexer, false);
-			}
-			else
-				break;
-		}
-
-		if (is_number && valid_symbols[FILE_DESCRIPTOR] && (lexer->lookahead == '>' || lexer->lookahead == '<'))
-		{
-			lexer->result_symbol = FILE_DESCRIPTOR;
-			return true;
-		}
-
-		if (valid_symbols[VARIABLE_NAME])
-		{
-			if (lexer->lookahead == '+')
-			{
-				lexer->mark_end(lexer);
-				lexer->advance(lexer, false);
-				if (lexer->lookahead == '=' || lexer->lookahead == ':')
-				{
-					lexer->result_symbol = VARIABLE_NAME;
-					return true;
-				}
-				return false;
-			}
-			if (lexer->lookahead == '/')
-			{
-				return false;
-			}
-			if (lexer->lookahead == '=' || lexer->lookahead == '[' || (lexer->lookahead == ':' && !valid_symbols[OPENING_PAREN]) ||
-				lexer->lookahead == '%' || (lexer->lookahead == '#' && !is_number) || lexer->lookahead == '@' || (lexer->lookahead == '-'))
-			{
-				lexer->mark_end(lexer);
-				lexer->result_symbol = VARIABLE_NAME;
-				return true;
-			}
-
-			if (lexer->lookahead == '?')
-			{
-				lexer->mark_end(lexer);
-				lexer->advance(lexer, false);
-				lexer->result_symbol = VARIABLE_NAME;
-				return me_isalpha(lexer->lookahead);
-			}
-		}
-
-		return false;
-	}
-
-	if (valid_symbols[BARE_DOLLAR] && !valid_symbols[ERROR_RECOVERY] && scan_bare_dollar(lexer))
-		return true;
-extglob_pattern:
-expansion_word:
-	if (valid_symbols[EXPANSION_WORD])
-	{
-		bool advanced_once = false;
-		bool advance_once_space = false;
-		while (true)
-		{
-			if (lexer->lookahead == '\"')
-				return false;
-			if (lexer->lookahead == '$')
-			{
-				lexer->mark_end(lexer);
-				lexer->advance(lexer, false);
-				if (lexer->lookahead == '{' || lexer->lookahead == '(' || lexer->lookahead == '\'' || me_isalnum(lexer->lookahead))
-				{
-					lexer->result_symbol = EXPANSION_WORD;
-					return advanced_once;
-				}
-				advanced_once = true;
-			}
-
-			if (lexer->lookahead == '}')
-			{
-				lexer->mark_end(lexer);
-				lexer->result_symbol = EXPANSION_WORD;
-				return advanced_once || advance_once_space;
-			}
-
-			if (lexer->lookahead == '(' && !(advanced_once || advance_once_space))
-			{
-				lexer->mark_end(lexer);
-				lexer->advance(lexer, false);
-				while (lexer->lookahead != ')' && !lexer->eof(lexer))
-				{
-					if (lexer->lookahead == '$')
-					{
-						lexer->mark_end(lexer);
-						lexer->advance(lexer, false);
-						if (lexer->lookahead == '{' || lexer->lookahead == '(' || lexer->lookahead == '\'' || me_isalnum(lexer->lookahead))
-						{
-							lexer->result_symbol = EXPANSION_WORD;
-							return advanced_once;
-						}
-						advanced_once = true;
-					}
-					else
-					{
-						advanced_once = advanced_once || !me_isspace(lexer->lookahead);
-						advance_once_space = advance_once_space || me_isspace(lexer->lookahead);
-						lexer->advance(lexer, false);
-					}
-				}
-				lexer->mark_end(lexer);
-				if (lexer->lookahead == ')')
-				{
-					advanced_once = true;
-					lexer->advance(lexer, false);
-					lexer->mark_end(lexer);
-					if (lexer->lookahead == '}')
-						return false;
-				}
-				else
-					return false;
-			}
-
-			if (lexer->lookahead == '\'')
-				return false;
-			if (lexer->eof(lexer))
-				return false;
-			advanced_once = advanced_once || !me_isspace(lexer->lookahead);
-			advance_once_space = advance_once_space || me_isspace(lexer->lookahead);
-			lexer->advance(lexer, false);
-		}
-	}
-
-brace_start:
-	return false;
-}
diff --git a/parser/src/scanner/heredoc.c b/parser/src/scanner/heredoc.c
index b2433d59..5aa4c0cd 100644
--- a/parser/src/scanner/heredoc.c
+++ b/parser/src/scanner/heredoc.c
@@ -6,44 +6,42 @@
 /*   By: maiboyer <maiboyer@student.42.fr>          +#+  +:+       +#+        */
 /*                                                +#+#+#+#+#+   +#+           */
 /*   Created: 2024/09/01 19:33:04 by maiboyer          #+#    #+#             */
-/*   Updated: 2024/09/01 20:02:49 by maiboyer         ###   ########.fr       */
+/*   Updated: 2024/09/02 17:31:02 by maiboyer         ###   ########.fr       */
 /*                                                                            */
 /* ************************************************************************** */
 
+#include "parser/inner/heredoc.h"
 #include "me/char/char.h"
 #include "me/str/str.h"
 #include "me/types.h"
 #include "me/vec/vec_heredoc.h"
-#include "parser/inner/heredoc.h"
 #include "parser/inner/scanner.h"
 #include "parser/parser.h"
 
-bool	scan_heredoc_start(t_heredoc *heredoc, TSLexer *lexer)
+bool scan_heredoc_start(t_heredoc *heredoc, TSLexer *lexer)
 {
-	bool	found_delimiter;
+	bool found_delimiter;
 
 	while (me_isspace(lexer->lookahead))
 		lexer->advance(lexer, true);
 	lexer->result_symbol = HEREDOC_START;
-	heredoc->is_raw = lexer->lookahead == '\'' || lexer->lookahead == '"'
-		|| lexer->lookahead == '\\';
+	heredoc->is_raw = lexer->lookahead == '\'' || lexer->lookahead == '"' || lexer->lookahead == '\\';
 	found_delimiter = advance_word(lexer, &heredoc->delimiter);
 	if (!found_delimiter)
 		return (string_clear(&heredoc->delimiter), false);
 	return (found_delimiter);
 }
 
-bool	scan_heredoc_end_identifier(t_heredoc *heredoc, TSLexer *lexer)
+bool scan_heredoc_end_identifier(t_heredoc *heredoc, TSLexer *lexer)
 {
-	t_i32	size;
+	t_i32 size;
 
 	size = 0;
 	string_clear(&heredoc->current_leading_word);
 	if (heredoc->delimiter.len > 0)
 	{
-		while (lexer->lookahead != '\0' && lexer->lookahead != '\n'
-			&& (t_i32)heredoc->delimiter.buf[size] == lexer->lookahead
-			&& heredoc->current_leading_word.len < heredoc->delimiter.len)
+		while (lexer->lookahead != '\0' && lexer->lookahead != '\n' && (t_i32)heredoc->delimiter.buf[size] == lexer->lookahead &&
+			   heredoc->current_leading_word.len < heredoc->delimiter.len)
 		{
 			string_push_char(&heredoc->current_leading_word, lexer->lookahead);
 			lexer->advance(lexer, false);
@@ -52,26 +50,27 @@ bool	scan_heredoc_end_identifier(t_heredoc *heredoc, TSLexer *lexer)
 	}
 	if (heredoc->delimiter.len == 0)
 		return (false);
-	return (str_compare(heredoc->current_leading_word.buf,
-			heredoc->delimiter.buf));
+	return (str_compare(heredoc->current_leading_word.buf, heredoc->delimiter.buf));
 }
 
-bool	scan_heredoc_content_nullbyte(struct s_heredoc_scan_state *state);
-bool	scan_heredoc_content_backslash(struct s_heredoc_scan_state *state);
-bool	scan_heredoc_content_dollar(struct s_heredoc_scan_state *state);
-bool	scan_heredoc_content_newline(struct s_heredoc_scan_state *state);
-bool	scan_heredoc_content_other(struct s_heredoc_scan_state *state);
+bool scan_heredoc_content_nullbyte(struct s_heredoc_scan_state *state);
+bool scan_heredoc_content_backslash(struct s_heredoc_scan_state *state);
+bool scan_heredoc_content_dollar(struct s_heredoc_scan_state *state);
+bool scan_heredoc_content_newline(struct s_heredoc_scan_state *state);
+bool scan_heredoc_content_other(struct s_heredoc_scan_state *state);
 
-bool	scan_heredoc_content(t_scanner *scanner, TSLexer *lexer,
-		enum e_token_type middle_type, enum e_token_type end_type)
+bool scan_heredoc_content(t_scanner *scanner, TSLexer *lexer, enum e_token_type middle_type, enum e_token_type end_type)
 {
-	struct s_heredoc_scan_state	state;
+	struct s_heredoc_scan_state state;
 	t_heredoc_content_func		func;
 
-	state = (struct s_heredoc_scan_state){.did_advance = false, \
-	.lexer = lexer, .heredoc = vec_heredoc_last(&scanner->heredocs), \
-	.scanner = scanner, .middle_type = middle_type, .end_type = end_type, \
-	.return_value = false};
+	state = (struct s_heredoc_scan_state){.did_advance = false,
+										  .lexer = lexer,
+										  .heredoc = vec_heredoc_last(&scanner->heredocs),
+										  .scanner = scanner,
+										  .middle_type = middle_type,
+										  .end_type = end_type,
+										  .return_value = false};
 	while (true)
 	{
 		if (lexer->lookahead == '\0')
@@ -89,3 +88,15 @@ bool	scan_heredoc_content(t_scanner *scanner, TSLexer *lexer,
 	}
 	return (false);
 }
+
+bool scan_heredoc_end(t_scanner *scanner, TSLexer *lexer)
+{
+	t_heredoc *heredoc;
+
+	heredoc = vec_heredoc_last(&scanner->heredocs);
+	string_free(heredoc->current_leading_word);
+	string_free(heredoc->delimiter);
+	vec_heredoc_pop(&scanner->heredocs, NULL);
+	lexer->result_symbol = HEREDOC_END;
+	return (true);
+}
diff --git a/parser/src/scanner/scan.c b/parser/src/scanner/scan.c
new file mode 100644
index 00000000..97854949
--- /dev/null
+++ b/parser/src/scanner/scan.c
@@ -0,0 +1,47 @@
+/* ************************************************************************** */
+/*                                                                            */
+/*                                                        :::      ::::::::   */
+/*   scan.c                                             :+:      :+:    :+:   */
+/*                                                    +:+ +:+         +:+     */
+/*   By: maiboyer <maiboyer@student.42.fr>          +#+  +:+       +#+        */
+/*                                                +#+#+#+#+#+   +#+           */
+/*   Created: 2024/09/02 17:40:46 by maiboyer          #+#    #+#             */
+/*   Updated: 2024/09/02 17:41:52 by maiboyer         ###   ########.fr       */
+/*                                                                            */
+/* ************************************************************************** */
+
+#include "me/char/char.h"
+#include "parser/inner/scanner.h"
+
+static bool scan2(t_scanner *scanner, TSLexer *lexer, const bool *valid_symbols)
+{
+	if (valid_symbols[HEREDOC_CONTENT] && scanner->heredocs.len > 0 && vec_heredoc_last(&scanner->heredocs)->started &&
+		!valid_symbols[ERROR_RECOVERY])
+		return (scan_heredoc_content(scanner, lexer, HEREDOC_CONTENT, HEREDOC_END));
+	if (valid_symbols[HEREDOC_START] && !valid_symbols[ERROR_RECOVERY] && scanner->heredocs.len > 0)
+		return (scan_heredoc_start(vec_heredoc_last(&scanner->heredocs), lexer));
+	if ((valid_symbols[VARIABLE_NAME] || valid_symbols[FILE_DESCRIPTOR] || valid_symbols[HEREDOC_ARROW]) && !valid_symbols[ERROR_RECOVERY])
+		return (scan_varname(scanner, lexer, valid_symbols));
+	if (valid_symbols[BARE_DOLLAR] && !valid_symbols[ERROR_RECOVERY] && scan_bare_dollar(lexer))
+		return (true);
+	if (valid_symbols[EXPANSION_WORD])
+		return (scan_expansion_word(scanner, lexer, valid_symbols));
+	return (false);
+}
+
+bool scan(t_scanner *scanner, TSLexer *lexer, const bool *valid_symbols)
+{
+	if (check_scan_concat(scanner, lexer, valid_symbols))
+		return (scan_concat(scanner, lexer, valid_symbols));
+	if (scan_double_hash(scanner, lexer, valid_symbols))
+		return (true);
+	if (valid_symbols[EMPTY_VALUE] &&
+		(me_isspace(lexer->lookahead) || lexer->eof(lexer) || lexer->lookahead == ';' || lexer->lookahead == '&'))
+		return (lexer->result_symbol = EMPTY_VALUE, true);
+	if ((valid_symbols[HEREDOC_BODY_BEGINNING] || valid_symbols[SIMPLE_HEREDOC_BODY]) && scanner->heredocs.len > 0 &&
+		!vec_heredoc_last(&scanner->heredocs)->started && !valid_symbols[ERROR_RECOVERY])
+		return (scan_heredoc_content(scanner, lexer, HEREDOC_BODY_BEGINNING, SIMPLE_HEREDOC_BODY));
+	if (valid_symbols[HEREDOC_END] && scanner->heredocs.len > 0 && scan_heredoc_end_identifier(vec_heredoc_last(&scanner->heredocs), lexer))
+		return (scan_heredoc_end(scanner, lexer));
+	return (scan2(scanner, lexer, valid_symbols));
+}
diff --git a/parser/src/scanner/scan_concat.c b/parser/src/scanner/scan_concat.c
new file mode 100644
index 00000000..5564c533
--- /dev/null
+++ b/parser/src/scanner/scan_concat.c
@@ -0,0 +1,52 @@
+/* ************************************************************************** */
+/*                                                                            */
+/*                                                        :::      ::::::::   */
+/*   scan_concat.c                                      :+:      :+:    :+:   */
+/*                                                    +:+ +:+         +:+     */
+/*   By: maiboyer <maiboyer@student.42.fr>          +#+  +:+       +#+        */
+/*                                                +#+#+#+#+#+   +#+           */
+/*   Created: 2024/09/02 17:37:05 by maiboyer          #+#    #+#             */
+/*   Updated: 2024/09/02 17:42:58 by maiboyer         ###   ########.fr       */
+/*                                                                            */
+/* ************************************************************************** */
+
+#include "me/char/char.h"
+#include "parser/inner/scanner.h"
+
+bool scan_concat(t_scanner *scanner, TSLexer *lexer, const bool *valid_symbols)
+{
+	(void)(scanner);
+	(void)(valid_symbols);
+	lexer->result_symbol = CONCAT;
+	if (lexer->lookahead == '`')
+	{
+		lexer->mark_end(lexer);
+		lexer->advance(lexer, false);
+		while (lexer->lookahead != '`' && !lexer->eof(lexer))
+			lexer->advance(lexer, false);
+		if (lexer->eof(lexer))
+			return (false);
+		if (lexer->lookahead == '`')
+			lexer->advance(lexer, false);
+		return (me_isspace(lexer->lookahead) || lexer->eof(lexer));
+	}
+	if (lexer->lookahead == '\\')
+	{
+		lexer->mark_end(lexer);
+		lexer->advance(lexer, false);
+		if (lexer->lookahead == '"' || lexer->lookahead == '\'' || lexer->lookahead == '\\')
+			return (true);
+		if (lexer->eof(lexer))
+			return (false);
+	}
+	return (true);
+}
+
+bool check_scan_concat(t_scanner *scanner, TSLexer *lexer, const bool *valid_symbols)
+{
+	(void)(scanner);
+	return (valid_symbols[CONCAT] && !valid_symbols[ERROR_RECOVERY]) &&
+		   (!(lexer->lookahead == 0 || me_isspace(lexer->lookahead) || lexer->lookahead == '>' || lexer->lookahead == '<' ||
+			  lexer->lookahead == ')' || lexer->lookahead == '(' || lexer->lookahead == ';' || lexer->lookahead == '&' ||
+			  lexer->lookahead == '|' || lexer->lookahead == '{' || lexer->lookahead == '}'));
+}
diff --git a/parser/src/scanner/scan_double_hash.c b/parser/src/scanner/scan_double_hash.c
new file mode 100644
index 00000000..b883889f
--- /dev/null
+++ b/parser/src/scanner/scan_double_hash.c
@@ -0,0 +1,37 @@
+/* ************************************************************************** */
+/*                                                                            */
+/*                                                        :::      ::::::::   */
+/*   scan_double_hash.c                                 :+:      :+:    :+:   */
+/*                                                    +:+ +:+         +:+     */
+/*   By: maiboyer <maiboyer@student.42.fr>          +#+  +:+       +#+        */
+/*                                                +#+#+#+#+#+   +#+           */
+/*   Created: 2024/09/02 17:32:35 by maiboyer          #+#    #+#             */
+/*   Updated: 2024/09/02 17:42:43 by maiboyer         ###   ########.fr       */
+/*                                                                            */
+/* ************************************************************************** */
+
+#include "parser/inner/scanner.h"
+
+bool scan_double_hash(t_scanner *scanner, TSLexer *lexer, const bool *valid_symbols)
+{
+	(void)(scanner);
+	if (valid_symbols[IMMEDIATE_DOUBLE_HASH] && !valid_symbols[ERROR_RECOVERY])
+	{
+		if (lexer->lookahead == '#')
+		{
+			lexer->mark_end(lexer);
+			lexer->advance(lexer, false);
+			if (lexer->lookahead == '#')
+			{
+				lexer->advance(lexer, false);
+				if (lexer->lookahead != '}')
+				{
+					lexer->result_symbol = IMMEDIATE_DOUBLE_HASH;
+					lexer->mark_end(lexer);
+					return (true);
+				}
+			}
+		}
+	}
+	return (false);
+}
diff --git a/parser/src/scanner/scan_varname.c b/parser/src/scanner/scan_varname.c
new file mode 100644
index 00000000..541531a4
--- /dev/null
+++ b/parser/src/scanner/scan_varname.c
@@ -0,0 +1,133 @@
+/* ************************************************************************** */
+/*                                                                            */
+/*                                                        :::      ::::::::   */
+/*   scan_varname.c                                     :+:      :+:    :+:   */
+/*                                                    +:+ +:+         +:+     */
+/*   By: maiboyer <maiboyer@student.42.fr>          +#+  +:+       +#+        */
+/*                                                +#+#+#+#+#+   +#+           */
+/*   Created: 2024/09/02 17:26:05 by maiboyer          #+#    #+#             */
+/*   Updated: 2024/09/02 17:28:10 by maiboyer         ###   ########.fr       */
+/*                                                                            */
+/* ************************************************************************** */
+
+#include "me/char/char.h"
+#include "parser/inner/scanner.h"
+
+bool scan_varname(t_scanner *scanner, TSLexer *lexer, const bool *valid_symbols)
+{
+	while (true)
+	{
+		if ((lexer->lookahead == ' ' || lexer->lookahead == '\t' || lexer->lookahead == '\r' ||
+			 (lexer->lookahead == '\n' && !valid_symbols[NEWLINE])) &&
+			!valid_symbols[EXPANSION_WORD])
+			lexer->advance(lexer, true);
+		else if (lexer->lookahead == '\\')
+		{
+			lexer->advance(lexer, true);
+			if (lexer->eof(lexer))
+			{
+				lexer->mark_end(lexer);
+				lexer->result_symbol = VARIABLE_NAME;
+				return (true);
+			}
+			if (lexer->lookahead == '\r')
+				lexer->advance(lexer, true);
+			if (lexer->lookahead == '\n')
+				lexer->advance(lexer, true);
+			else
+			{
+				if (lexer->lookahead == '\\' && valid_symbols[EXPANSION_WORD])
+					return (scan_expansion_word(scanner, lexer, valid_symbols));
+				return (false);
+			}
+		}
+		else
+			break;
+	}
+
+	// no '*', '@', '?', '-', '$', '0', '_'
+	if (!valid_symbols[EXPANSION_WORD] && (lexer->lookahead == '*' || lexer->lookahead == '@' || lexer->lookahead == '?' ||
+										   lexer->lookahead == '-' || lexer->lookahead == '0' || lexer->lookahead == '_'))
+	{
+		lexer->mark_end(lexer);
+		lexer->advance(lexer, false);
+		if (lexer->lookahead == '=' || lexer->lookahead == '[' || lexer->lookahead == ':' || lexer->lookahead == '-' ||
+			lexer->lookahead == '%' || lexer->lookahead == '#' || lexer->lookahead == '/')
+			return false;
+		if (valid_symbols[EXTGLOB_PATTERN] && me_isspace(lexer->lookahead))
+		{
+			lexer->mark_end(lexer);
+			lexer->result_symbol = EXTGLOB_PATTERN;
+			return true;
+		}
+	}
+
+	if (valid_symbols[HEREDOC_ARROW] && lexer->lookahead == '<')
+	{
+		lexer->advance(lexer, false);
+		if (lexer->lookahead == '<')
+		{
+			lexer->advance(lexer, false);
+			t_heredoc heredoc = heredoc_new();
+			vec_heredoc_push(&scanner->heredocs, heredoc);
+			lexer->result_symbol = HEREDOC_ARROW;
+			return (true);
+		}
+		return (false);
+	}
+
+	bool is_number = true;
+	if (me_isdigit(lexer->lookahead))
+		lexer->advance(lexer, false);
+	else if (me_isalpha(lexer->lookahead) || lexer->lookahead == '_')
+	{
+		is_number = false;
+		lexer->advance(lexer, false);
+	}
+	else
+	{
+		if (lexer->lookahead == '{')
+			return (false);
+		if (valid_symbols[EXPANSION_WORD])
+			return (scan_expansion_word(scanner, lexer, valid_symbols));
+		return (false);
+	}
+
+	while (true)
+	{
+		if (me_isdigit(lexer->lookahead))
+			lexer->advance(lexer, false);
+		else if (me_isalpha(lexer->lookahead) || lexer->lookahead == '_')
+			is_number = (lexer->advance(lexer, false), false);
+		else
+			break;
+	}
+
+	if (is_number && valid_symbols[FILE_DESCRIPTOR] && (lexer->lookahead == '>' || lexer->lookahead == '<'))
+		return (lexer->result_symbol = FILE_DESCRIPTOR, true);
+
+	if (valid_symbols[VARIABLE_NAME])
+	{
+		if (lexer->lookahead == '+')
+		{
+			lexer->mark_end(lexer);
+			lexer->advance(lexer, false);
+			if (lexer->lookahead == '=' || lexer->lookahead == ':')
+				return (lexer->result_symbol = VARIABLE_NAME, true);
+			return false;
+		}
+		if (lexer->lookahead == '/')
+			return false;
+		if (lexer->lookahead == '=' || lexer->lookahead == '[' || (lexer->lookahead == ':' && !valid_symbols[OPENING_PAREN]) ||
+			lexer->lookahead == '%' || (lexer->lookahead == '#' && !is_number) || lexer->lookahead == '@' || (lexer->lookahead == '-'))
+			return (lexer->mark_end(lexer), lexer->result_symbol = VARIABLE_NAME, true);
+		if (lexer->lookahead == '?')
+		{
+			lexer->mark_end(lexer);
+			lexer->advance(lexer, false);
+			lexer->result_symbol = VARIABLE_NAME;
+			return (me_isalpha(lexer->lookahead));
+		}
+	}
+	return (false);
+}
diff --git a/parser/src/scanner/scan_word.c b/parser/src/scanner/scan_word.c
new file mode 100644
index 00000000..bccdba06
--- /dev/null
+++ b/parser/src/scanner/scan_word.c
@@ -0,0 +1,92 @@
+/* ************************************************************************** */
+/*                                                                            */
+/*                                                        :::      ::::::::   */
+/*   scan_word.c                                        :+:      :+:    :+:   */
+/*                                                    +:+ +:+         +:+     */
+/*   By: maiboyer <maiboyer@student.42.fr>          +#+  +:+       +#+        */
+/*                                                +#+#+#+#+#+   +#+           */
+/*   Created: 2024/09/02 16:59:16 by maiboyer          #+#    #+#             */
+/*   Updated: 2024/09/02 17:22:25 by maiboyer         ###   ########.fr       */
+/*                                                                            */
+/* ************************************************************************** */
+
+#include "me/char/char.h"
+#include "parser/inner/scanner.h"
+
+bool scan_expansion_word(t_scanner *scanner, TSLexer *lexer, const bool *valid_symbols)
+{
+	bool advanced_once = false;
+	bool advance_once_space = false;
+
+	(void)(scanner);
+	(void)(lexer);
+	(void)(valid_symbols);
+	while (true)
+	{
+		if (lexer->lookahead == '\"')
+			return false;
+		if (lexer->lookahead == '$')
+		{
+			lexer->mark_end(lexer);
+			lexer->advance(lexer, false);
+			if (lexer->lookahead == '{' || lexer->lookahead == '(' || lexer->lookahead == '\'' || me_isalnum(lexer->lookahead))
+			{
+				lexer->result_symbol = EXPANSION_WORD;
+				return advanced_once;
+			}
+			advanced_once = true;
+		}
+
+		if (lexer->lookahead == '}')
+		{
+			lexer->mark_end(lexer);
+			lexer->result_symbol = EXPANSION_WORD;
+			return advanced_once || advance_once_space;
+		}
+
+		if (lexer->lookahead == '(' && !(advanced_once || advance_once_space))
+		{
+			lexer->mark_end(lexer);
+			lexer->advance(lexer, false);
+			while (lexer->lookahead != ')' && !lexer->eof(lexer))
+			{
+				if (lexer->lookahead == '$')
+				{
+					lexer->mark_end(lexer);
+					lexer->advance(lexer, false);
+					if (lexer->lookahead == '{' || lexer->lookahead == '(' || lexer->lookahead == '\'' || me_isalnum(lexer->lookahead))
+					{
+						lexer->result_symbol = EXPANSION_WORD;
+						return advanced_once;
+					}
+					advanced_once = true;
+				}
+				else
+				{
+					advanced_once = advanced_once || !me_isspace(lexer->lookahead);
+					advance_once_space = advance_once_space || me_isspace(lexer->lookahead);
+					lexer->advance(lexer, false);
+				}
+			}
+			lexer->mark_end(lexer);
+			if (lexer->lookahead == ')')
+			{
+				advanced_once = true;
+				lexer->advance(lexer, false);
+				lexer->mark_end(lexer);
+				if (lexer->lookahead == '}')
+					return false;
+			}
+			else
+				return false;
+		}
+
+		if (lexer->lookahead == '\'')
+			return false;
+		if (lexer->eof(lexer))
+			return false;
+		advanced_once = advanced_once || !me_isspace(lexer->lookahead);
+		advance_once_space = advance_once_space || me_isspace(lexer->lookahead);
+		lexer->advance(lexer, false);
+	}
+}
diff --git a/parser/src/scanner/serialize.c b/parser/src/scanner/serialize.c
index c6bc8f17..0e55b628 100644
--- a/parser/src/scanner/serialize.c
+++ b/parser/src/scanner/serialize.c
@@ -6,7 +6,7 @@
 /*   By: maiboyer <maiboyer@student.42.fr>          +#+  +:+       +#+        */
 /*                                                +#+#+#+#+#+   +#+           */
 /*   Created: 2024/09/01 15:06:56 by maiboyer          #+#    #+#             */
-/*   Updated: 2024/09/01 19:28:24 by maiboyer         ###   ########.fr       */
+/*   Updated: 2024/09/02 17:06:26 by maiboyer         ###   ########.fr       */
 /*                                                                            */
 /* ************************************************************************** */
 
@@ -22,6 +22,8 @@ t_error	serialize_heredocs(t_scanner *scanner, t_u8 *buffer, t_u32 *size,
 	t_heredoc	*heredoc;
 
 	heredoc = vec_heredoc_get(&scanner->heredocs, i);
+	if (heredoc == NULL)
+		return (ERROR);
 	if (heredoc->delimiter.len + 1 + sizeof(t_usize)
 		+ (*size) >= TREE_SITTER_SERIALIZATION_BUFFER_SIZE)
 		return (ERROR);
diff --git a/parser/src/stack/stack_summary.c b/parser/src/stack/stack_summary.c
index 0872ebba..b0a3a5cb 100644
--- a/parser/src/stack/stack_summary.c
+++ b/parser/src/stack/stack_summary.c
@@ -6,7 +6,7 @@
 /*   By: maiboyer <maiboyer@student.42.fr>          +#+  +:+       +#+        */
 /*                                                +#+#+#+#+#+   +#+           */
 /*   Created: 2024/08/31 16:50:56 by maiboyer          #+#    #+#             */
-/*   Updated: 2024/08/31 16:51:36 by maiboyer         ###   ########.fr       */
+/*   Updated: 2024/09/02 17:20:31 by maiboyer         ###   ########.fr       */
 /*                                                                            */
 /* ************************************************************************** */
 
@@ -30,6 +30,8 @@ t_stack_action	summarize_stack_callback(void *payload,
 	i = session->summary->size - 1;
 	while (i + 1 > 0)
 	{
+		if (session->summary->contents == NULL)
+			return (SActionNone);
 		entry = session->summary->contents[i--];
 		if (entry.depth < depth)
 			break ;