Initial commit: Basic interpreter structure

docs/README.md

@@ -0,0 +1,3 @@
+# Femcode
+
+A femboy-themed programming language.

examples/hello_world.fem

@@ -0,0 +1 @@
+UwU Boy "Hello, Femboy World!"

src/interpreter.py

@@ -0,0 +1,18 @@
+class Interpreter:
+    def __init__(self, ast):
+        self.ast = ast
+
+    def interpret(self):
+        for node in self.ast:
+            self.visit(node)
+
+    def visit(self, node):
+        method_name = f'visit_{type(node).__name__}'
+        method = getattr(self, method_name, self.no_visit_method)
+        return method(node)
+
+    def no_visit_method(self, node):
+        raise Exception(f'No visit_{type(node).__name__} method defined')
+
+    def visit_Print(self, node):
+        print(node.value)

src/lexer.py

@@ -0,0 +1,51 @@
+import re
+
+class Token:
+    def __init__(self, type, value):
+        self.type = type
+        self.value = value
+
+    def __repr__(self):
+        return f'Token({self.type}, {self.value!r})'
+
+class Lexer:
+    def __init__(self, text):
+        self.text = text
+        self.pos = 0
+
+    def error(self):
+        raise Exception('Invalid character')
+
+    def get_next_token(self):
+        if self.pos > len(self.text) - 1:
+            return Token('EOF', None)
+
+        current_char = self.text[self.pos]
+
+        if current_char.isspace():
+            self.pos += 1
+            return self.get_next_token()
+
+        if current_char == '"':
+            self.pos += 1
+            string_end = self.text.find('"', self.pos)
+            if string_end == -1:
+                self.error()
+            string = self.text[self.pos:string_end]
+            self.pos = string_end + 1
+            return Token('STRING', string)
+
+        if re.match(r'\bUwU Boy\b', self.text[self.pos:]):
+            self.pos += 7
+            return Token('PRINT', 'UwU Boy')
+
+        self.error()
+
+    def tokenize(self):
+        tokens = []
+        while True:
+            token = self.get_next_token()
+            tokens.append(token)
+            if token.type == 'EOF':
+                break
+        return tokens

src/main.py

@@ -0,0 +1,19 @@
+from lexer import Lexer
+from parser import Parser
+from interpreter import Interpreter
+
+def main():
+    with open('../examples/hello_world.fem', 'r') as f:
+        text = f.read()
+
+    lexer = Lexer(text)
+    tokens = lexer.tokenize()
+
+    parser = Parser(tokens)
+    ast = parser.parse()
+
+    interpreter = Interpreter(ast)
+    interpreter.interpret()
+
+if __name__ == '__main__':
+    main()

src/parser.py

@@ -0,0 +1,36 @@
+class AST:
+    pass
+
+class Print(AST):
+    def __init__(self, value):
+        self.value = value
+
+class Parser:
+    def __init__(self, tokens):
+        self.tokens = tokens
+        self.pos = 0
+
+    def get_next_token(self):
+        if self.pos < len(self.tokens):
+            token = self.tokens[self.pos]
+            self.pos += 1
+            return token
+        return None
+
+    def parse(self):
+        statements = []
+        while True:
+            token = self.get_next_token()
+            if token is None or token.type == 'EOF':
+                break
+
+            if token.type == 'PRINT':
+                next_token = self.get_next_token()
+                if next_token.type == 'STRING':
+                    statements.append(Print(next_token.value))
+                else:
+                    raise Exception("Expected a string after 'UwU Boy'")
+            else:
+                raise Exception(f"Unexpected token: {token.type}")
+
+        return statements