From 0195a84bfdfda84d56c2def09626a18cf06199ab Mon Sep 17 00:00:00 2001
From: LordBaryhobal <lordbaryhobal@gmail.com>
Date: Thu, 5 Feb 2026 03:34:35 +0100
Subject: [PATCH] feat(lexer): add identifiers and keywords

---
 main.py        |  5 ++++-
 src/keyword.py | 14 ++++++++++++++
 src/lexer.py   | 11 +++++++++++
 3 files changed, 29 insertions(+), 1 deletion(-)
 create mode 100644 src/keyword.py

diff --git a/main.py b/main.py
index 2f1bbe5..c77e80b 100644
--- a/main.py
+++ b/main.py
@@ -10,8 +10,11 @@ def main():
     123
     "This is
      another string" """
+    path: str = "examples/05_loop.peb"
+    with open(path, "r") as f:
+        source = f.read()
     lexer: Lexer = Lexer()
-    tokens: list[Token] = lexer.process(source)
+    tokens: list[Token] = lexer.process(source, path)
     print(tokens)
 
 if __name__ == '__main__':
diff --git a/src/keyword.py b/src/keyword.py
new file mode 100644
index 0000000..68ca011
--- /dev/null
+++ b/src/keyword.py
@@ -0,0 +1,14 @@
+from src.token import TokenType
+
+KEYWORDS: dict[str, TokenType] = {
+    "let": TokenType.LET,
+    "and": TokenType.AND,
+    "or": TokenType.OR,
+    "if": TokenType.IF,
+    "else": TokenType.ELSE,
+    "for": TokenType.FOR,
+    "while": TokenType.WHILE,
+    "from": TokenType.FROM,
+    "to": TokenType.TO,
+    "by": TokenType.BY
+}
diff --git a/src/lexer.py b/src/lexer.py
index 40f600c..8a6c6ec 100644
--- a/src/lexer.py
+++ b/src/lexer.py
@@ -1,5 +1,6 @@
 from typing import Optional, Any
 
+from src.keyword import KEYWORDS
 from src.position import Position
 from src.token import Token, TokenType
 
@@ -129,6 +130,8 @@ class Lexer:
             case _:
                 if char.isdigit():
                     self.scan_number()
+                elif char.isalpha():
+                    self.scan_identifier()
                 else:
                     self.error("Unexpected character")
         return None
@@ -158,3 +161,11 @@ class Lexer:
 
         value: float = float(self.source[self.start:self.idx])
         self.add_token(TokenType.NUMBER, value)
+
+    def scan_identifier(self):
+        while self.peek().isalnum() or self.peek() == "_":
+            self.advance()
+
+        lexeme: str = self.source[self.start:self.idx]
+        token_type: TokenType = KEYWORDS.get(lexeme, TokenType.IDENTIFIER)
+        self.add_token(token_type)