From 7e2ecc6e1f9e49439696adc72dcbefd699168e44 Mon Sep 17 00:00:00 2001
From: uvok
Date: Mon, 12 Jan 2026 19:16:17 +0100
Subject: Add first version of assembler

---
 nandgame/assembler/lexer.py | 67 +++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 67 insertions(+)
 create mode 100644 nandgame/assembler/lexer.py

(limited to 'nandgame/assembler/lexer.py')

diff --git a/nandgame/assembler/lexer.py b/nandgame/assembler/lexer.py
new file mode 100644
index 0000000..eb035f2
--- /dev/null
+++ b/nandgame/assembler/lexer.py
@@ -0,0 +1,67 @@
+
+import ply.lex as lex
+
+# List of token names.   This is always required
+tokens = (
+   'OP',
+   'JUMP',
+   'COMMA',
+   'COLON',
+   'SYMBOL',
+   'NUMBER',
+   'HEXNUMBER',
+   'DOT',
+   'REG'
+)
+
+# Regular expression rules for simple tokens
+t_COMMA   = r','
+t_COLON   = r':'
+t_DOT     = r'\.'
+
+def t_OP(t):
+    r"mov|and|dec|hlt|add|sub|inc"
+    return t
+
+def t_REG(t):
+    r"\b(AD?M?|DM?|M|_)\b"
+    return t
+
+def t_JUMP(t):
+    r"jmp|jlt|jgt|jle|jge|jeq|jne"
+    return t
+
+def t_NUMBER(t):
+    r'\#\d+'
+    t.value = int(t.value[1:])
+    return t
+
+def t_HEXNUMBER(t):
+    r'\#0x[0-9a-fA-F]+'
+    t.value = int(t.value[1:], 16)
+    return t
+
+def t_SYMBOL(t):
+    r'[a-z][A-Za-z0-9_]+'
+    return t
+
+# Define a rule so we can track line numbers
+def t_newline(t):
+    r'\n+'
+    t.lexer.lineno += len(t.value)
+
+# A string containing ignored characters (spaces and tabs)
+t_ignore  = ' \t'
+#t_ignore_COMMENT = r';.*'
+
+def t_COMMENT(t):
+    r';.*'
+    pass
+
+# Error handling rule
+def t_error(t):
+    print("!!! Illegal character '%s'" % t.value[0])
+    t.lexer.skip(1)
+
+# Build the lexer
+lexer = lex.lex()
-- 
cgit v1.2.3