From 48221894c031bdae9967da224ab27ceddf3b91c2 Mon Sep 17 00:00:00 2001
From: hugogogo <hugogogo@protonmail.com>
Date: Tue, 28 Apr 2026 22:04:23 +0200
Subject: [PATCH] wip lexer

---
 Makefile             |   2 +-
 README.md            |  28 +++++++++++
 headers/computorv1.h |  35 +++++++++++++-
 libft                |   2 +-
 src/computorv1.c     | 107 +++++++++++++++++++++++++++++++++++++++++--
 5 files changed, 165 insertions(+), 9 deletions(-)

diff --git a/Makefile b/Makefile
index 8f664cd..9e8ae1a 100644
--- a/Makefile
+++ b/Makefile
@@ -91,7 +91,7 @@ $(NAME): $(OBJS)
 
 run: $(NAME)
 	@echo $(YELLOW)"run"$(RESET)
-	@./$(NAME)
+	@./$(NAME) "3 * x^2 + 1 * x^1 - 2 * x^0"
 
 clean:
 	$(RM_OBJS)
diff --git a/README.md b/README.md
index 8da4413..4cc5cfc 100644
--- a/README.md
+++ b/README.md
@@ -12,3 +12,31 @@ this project uses submodules (maybe recursively), so either :
 
 - `git clone --recurse-submodules <repo-url>`
 - or, after cloning : `git submodule update --init --recursive`
+
+## steps
+
+1. lexer
+    -> tokens[] :
+       {
+         PLUS -> +
+         MINUS -> -
+         VARIABLE -> x
+         NUMBER -> int or double
+         POWER -> ^
+         MULTIPLICATION -> *
+         DIVISION -> /
+         END -> null
+       }[]
+2. parser
+    -> terms[] :
+       {
+         SIGN -> + or -
+         COEFFICIENT -> double
+         EXPONENT -> double
+       }[]
+3. reduce
+4. print reduced form
+5. find degree
+6. print degree
+7. solve
+8. print solution
\ No newline at end of file
diff --git a/headers/computorv1.h b/headers/computorv1.h
index 0ca9811..f1ed01a 100644
--- a/headers/computorv1.h
+++ b/headers/computorv1.h
@@ -1,6 +1,37 @@
 #ifndef COMPUTORV1_H
-# define COMPUTORV1_H
+#define COMPUTORV1_H
 
-# include "../libft/includes/libft.h"
+#include "../libft/includes/libft.h"
+
+typedef enum
+{
+    ERROR_BASIC,         // 0
+    ERROR_UNKNOWN_TOKEN, // 1
+} program_error;
+
+typedef enum
+{
+    TOKEN_PLUS,           // +
+    TOKEN_MINUS,          // -
+    TOKEN_VARIABLE,       // x, y, etc.
+    TOKEN_NUMBER,         // int or double
+    TOKEN_POWER,          // ^ or **
+    TOKEN_MULTIPLICATION, // *
+    TOKEN_DIVISION,       // /
+    TOKEN_END             // null (end of input)
+} TokenType;
+
+typedef struct
+{
+    TokenType type;
+    union
+    {
+        double num_value; // For NUMBER
+        char var_value;   // For VARIABLE (single char, e.g., 'x')
+    };
+} t_token;
+
+#define MAX_TOKENS 100
+t_token tokens[MAX_TOKENS];
 
 #endif
\ No newline at end of file
diff --git a/libft b/libft
index 603303a..2be81d5 160000
--- a/libft
+++ b/libft
@@ -1 +1 @@
-Subproject commit 603303a21bd8485961a0159f0aeefa629604cb4c
+Subproject commit 2be81d563077fff32c96a82a5748b9de1ff89069
diff --git a/src/computorv1.c b/src/computorv1.c
index 7c7e410..b495bc6 100644
--- a/src/computorv1.c
+++ b/src/computorv1.c
@@ -1,15 +1,112 @@
 
 #include "computorv1.h"
 
-int	main(int ac, char **av)
+int stop_errors(int err)
+{
+    switch (err)
+    {
+    case -ERROR_UNKNOWN_TOKEN:
+        ft_putstr_fd("error: unknown token\n", STDERR_FILENO);
+        break;
+
+    default:
+        ft_putstr_fd("unknown error\n", STDERR_FILENO);
+        break;
+    }
+
+    exit(err);
+}
+
+int skip_whitespace(const char *input, int input_pos)
+{
+    while (ft_isspace(input[input_pos]))
+    {
+        input_pos++;
+    }
+    return input_pos;
+}
+
+int token_is_plus(const char *input, int input_pos)
+{
+    return (input[input_pos] == '+');
+}
+
+int lexerize(const char *input)
+{
+    int token_count = 0;
+    int input_pos = 0;
+    int token_size = 0;
+
+    while (input[input_pos])
+    {
+        input_pos = skip_whitespace(input, input_pos);
+
+        if (input[input_pos] == '\0')
+        {
+            break;
+        }
+
+        token_size = token_is_plus(input, input_pos);
+        if (token_size)
+        {
+            tokens[token_count].type = TOKEN_PLUS;
+            tokens[token_count].var_value = '+';
+        }
+
+        if (token_size == 0)
+        {
+            stop_errors(-ERROR_UNKNOWN_TOKEN);
+        }
+        token_count++;
+        input_pos += token_size;
+    }
+
+    // Add end token
+    tokens[token_count].type = TOKEN_END;
+    tokens[token_count].var_value = '\0';
+    return 1;
+}
+
+int main(int ac, char **av)
 {
     int i;
+    int ret;
 
+    if (ac < 2)
+    {
+        return 0;
+    }
     i = 0;
-    while(i < ac) {
-        ft_putstr_fd(av[i], STDOUT_FILENO);
-        ft_putchar_fd('\n', STDOUT_FILENO);
+    while (i < ac)
+    {
+        ft_putnbr(i);
+        ft_putstr(" : ");
+        ft_putstr(av[i]);
+        ft_putchar('\n');
         i++;
     }
-	return (0);
+
+    ret = lexerize(av[1]);
+    if (ret <= 0)
+    {
+        stop_errors(ret);
+    }
+
+    // tmp debug output
+    i = 0;
+    while (tokens[i].type != TOKEN_END)
+    {
+        ft_printf("token %i :\n  type : %i\n  value : ", i, tokens[i].type);
+        if (tokens[i].type == TOKEN_NUMBER)
+        {
+            ft_printf("%d\n", i, tokens[i].num_value);
+        }
+        else
+        {
+            ft_printf("%c\n", tokens[i].var_value);
+        }
+        i++;
+    }
+
+    return (0);
 }