Split to several files

AST.py

@@ -0,0 +1,149 @@
+from enum import Enum
+
+class NodeType(Enum):
+    INTEGER = 1
+    STRING = 2
+    NOTE = 3
+    BLOCK = 4
+    ARGUMENTS = 5
+    IDENTIFIER = 6
+    ASSIGN = 7
+    PROGRAM = 8
+    ASTERISK = 9
+    COLON = 10
+    FUNCTION_CALL = 11
+    COMMA = 12
+    PERCENT = 13
+
+class Node:
+    def __init__(self):
+        self.children = []            
+        
+    def __repr__(self):
+        return self.__str__()
+    
+    def __len__(self):
+        return len(self.children)
+        
+    def __getitem__(self, index):
+        return self.children[index]
+  
+    def append(self, node):
+        self.children.append(node)
+        
+    def pop(self, index):
+        return self.children.pop(index)
+
+class Program(Node):
+    def __init__(self):
+        Node.__init__(self)
+        self.type =  NodeType.PROGRAM        
+    
+    def __str__(self):
+        return "Program:\n" + "\n".join([str(e) for e in self.children])
+    
+
+class BlockNode(Node):
+    def __init__(self):      
+        Node.__init__(self)
+        self.type = NodeType.BLOCK        
+    
+    def __str__(self):
+        return "B{\n" + "\n".join([str(e) for e in self.children]) + "\n}"
+
+
+class ArgumentsNode(Node):
+    def __init__(self):
+        Node.__init__(self)
+        self.type = NodeType.ARGUMENTS        
+    
+    def __str__(self):
+        return "@(" + ", ".join([str(e) for e in self.children]) + ")"      
+        
+class IdentifierNode(Node):
+    def __init__(self, identifier):
+        self.type = NodeType.IDENTIFIER
+        self.identifier = identifier
+    
+    def __str__(self):
+        return f"L'{self.identifier}'"
+        
+class AssignExpression(Node):
+    def __init__(self, target, value):
+        self.type = NodeType.ASSIGN
+        self.target = target
+        self.value = value
+        
+    def __str__(self):
+        return f"A[{self.target} = {self.value}]"
+   
+class AsteriskStatementNode(Node):
+    def __init__(self, iterator, statement):
+        self.type = NodeType.ASTERISK
+        self.iterator = iterator
+        self.statement = statement
+        
+    def __str__(self):
+        return f"*({self.iterator}: {self.statement})"
+   
+class ColonNode(Node):
+    def __init__(self, a, b):
+        self.type = NodeType.COLON
+        self.a = a
+        self.b = b
+        
+    def __str__(self):
+        return f":({self.a}, {self.b})"
+   
+class ExpressionNode(Node):
+    def __str__(self):
+        return f"{self.__class__.__name__}('{self.value}')"
+
+
+class IntegerLiteralNode(ExpressionNode):
+    def __init__(self, value):
+        self.type = NodeType.INTEGER
+        self.value = value        
+    
+    def __str__(self):
+        return f"i'{self.value}'"
+
+class StringLiteralNode(ExpressionNode):
+    def __init__(self, value):
+        self.type = NodeType.STRING
+        self.value = value
+
+    def __str__(self):
+        return f"s'{self.value}'"
+    
+class NoteLiteralNode(ExpressionNode):
+    def __init__(self, value):
+        self.type = NodeType.NOTE
+        self.value = value
+        
+    def __str__(self):
+        return f"n'{self.value}'"
+
+class FunctionCallNode(Node):
+    def __init__(self, identifier, arguments):
+        self.type = NodeType.FUNCTION_CALL
+        self.identifier = identifier
+        self.arguments = arguments
+        
+    def __str__(self):
+        return f"F({self.identifier}: {self.arguments})"
+
+class CommaNode(Node):
+    def __init__(self):
+        self.type = NodeType.COMMA
+        
+    def __str__(self):
+        return "[,]"
+
+class PercentNode(Node):
+    def __init__(self, value):
+        self.type = NodeType.PERCENT
+        self.value = value
+        
+    def __str__(self):
+        return f"%'{self.value}'"

parser.py

@@ -1,178 +1,20 @@
-from enum import Enum
 from tokenizer import *
 from note import *
-import json
+from AST import *
 
 class ParseError(Exception):
     pass
 
-class NodeType(Enum):
-    INTEGER = 1
-    STRING = 2
-    NOTE = 3
-    BLOCK = 4
-    ARGUMENTS = 5
-    IDENTIFIER = 6
-    ASSIGN = 7
-    PROGRAM = 8
-    ASTERISK = 9
-    COLON = 10
-    FUNCTION_CALL = 11
-    COMMA = 12
-    PERCENT = 13
-
-class Node:
-    def __init__(self):
-        self.children = []            
-        
-    def __repr__(self):
-        return self.__str__()
-    
-    def __len__(self):
-        return len(self.children)
-        
-    def __getitem__(self, index):
-        return self.children[index]
-  
-    def append(self, node):
-        self.children.append(node)
-        
-    def pop(self, index):
-        return self.children.pop(index)
-
-class Program(Node):
-    def __init__(self):
-        Node.__init__(self)
-        self.type =  NodeType.PROGRAM        
-    
-    def __str__(self):
-        return "Program:\n" + "\n".join([str(e) for e in self.children])
-    
-
-class BlockNode(Node):
-    def __init__(self):      
-        Node.__init__(self)
-        self.type = NodeType.BLOCK        
-    
-    def __str__(self):
-        return "B{\n" + "\n".join([str(e) for e in self.children]) + "\n}"
-
-
-class ArgumentsNode(Node):
-    def __init__(self):
-        Node.__init__(self)
-        self.type = NodeType.ARGUMENTS        
-    
-    def __str__(self):
-        return "@(" + ", ".join([str(e) for e in self.children]) + ")"      
-        
-class IdentifierNode(Node):
-    def __init__(self, identifier):
-        self.type = NodeType.IDENTIFIER
-        self.identifier = identifier
-    
-    def __str__(self):
-        return f"L'{self.identifier}'"
-        
-class AssignExpression(Node):
-    def __init__(self, target, value):
-        self.type = NodeType.ASSIGN
-        self.target = target
-        self.value = value
-        
-    def __str__(self):
-        return f"A[{self.target} = {self.value}]"
-   
-class AsteriskStatementNode(Node):
-    def __init__(self, iterator, statement):
-        self.type = NodeType.ASTERISK
-        self.iterator = iterator
-        self.statement = statement
-        
-    def __str__(self):
-        return f"*({self.iterator}: {self.statement})"
-   
-class ColonNode(Node):
-    def __init__(self, a, b):
-        self.type = NodeType.COLON
-        self.a = a
-        self.b = b
-        
-    def __str__(self):
-        return f":({self.a}, {self.b})"
-   
-class ExpressionNode(Node):
-    def __str__(self):
-        return f"{self.__class__.__name__}('{self.value}')"
-
-
-class IntegerLiteralNode(ExpressionNode):
-    def __init__(self, value):
-        self.type = NodeType.INTEGER
-        self.value = value        
-    
-    def __str__(self):
-        return f"i'{self.value}'"
-
-class StringLiteralNode(ExpressionNode):
-    def __init__(self, value):
-        self.type = NodeType.STRING
-        self.value = value
-
-    def __str__(self):
-        return f"s'{self.value}'"
-    
-class NoteLiteralNode(ExpressionNode):
-    def __init__(self, value):
-        self.type = NodeType.NOTE
-        self.value = value
-        
-    def __str__(self):
-        return f"n'{self.value}'"
-
-class FunctionCallNode(Node):
-    def __init__(self, identifier, arguments):
-        self.type = NodeType.FUNCTION_CALL
-        self.identifier = identifier
-        self.arguments = arguments
-        
-    def __str__(self):
-        return f"F({self.identifier}: {self.arguments})"
-
-class CommaNode(Node):
-    def __init__(self):
-        self.type = NodeType.COMMA
-        
-    def __str__(self):
-        return "[,]"
-
-class PercentNode(Node):
-    def __init__(self, value):
-        self.type = NodeType.PERCENT
-        self.value = value
-        
-    def __str__(self):
-        return f"%'{self.value}'"
-
 def expectedFound(expected, found):
     raise ParseError(f"Expected: {expected}, found: {found}")
 
 def parseInteger(input, parent):
-    if input[0].type != TokenType.INTEGER:
-        expectedFound(TokenType.INTEGER, input[0].type)
-    
     return IntegerLiteralNode(int(input.pop(0).value))
     
 def parseString(input, parent):    
-    if input[0].type != TokenType.STRING:
-        expectedFound(TokenType.STRING, input[0].type)
-        
     return StringLiteralNode(input.pop(0).value[1:-1])
     
 def parseNote(input, parent): 
-    if input[0].type != TokenType.NOTE:
-        expectedFound(TokenType.NOTE, input[0].type)
-    
     value = input.pop(0).value
     consumedChars = 1
     notePitch = value[consumedChars]
@@ -196,21 +38,20 @@ def parseNote(input, parent):
     return NoteLiteralNode(Note(notePitch, octave, duration))
 
 def parseComma(input, parent):
-    if input[0].type != TokenType.COMMA:
-        expectedFound(TokenType.COMMA, input[0].type)
     input.pop(0)
     return CommaNode()
 
 def parseArguments(input, parent):    
-    if input[0].type != TokenType.OPEN_PAREN:
+   #import pdb; pdb.set_trace()
-        expectedFound(TokenType.OPEN_PAREN, input[0].type)
-        
     input.pop(0)
     
     arguments = ArgumentsNode()
     
     while input[0].type != TokenType.CLOSE_PAREN:  
-        arguments.append(parseArrayElement(input, arguments)) #TODO: parseExpression
+        argument = parseArrayElement(input, arguments)
+        if argument is None:
+            raise ParseError(f"Line: {input[0].pos[0]+1}, col: {input[0].pos[1]+1}: Invalid function argument '{input[0].value}'")
+        arguments.append(argument) #TODO: parseExpression
     
     if input[0].type != TokenType.CLOSE_PAREN:
         expectedFound(TokenType.CLOSE_PAREN, input[0].type)
@@ -219,9 +60,6 @@ def parseArguments(input, parent):
     return arguments
             
 def parseBlock(input, parent):
-    if input[0].type != TokenType.OPEN_BRACKET:
-        expectedFound(TokenType.OPEN_BRACKET, input[0].type)
-        
     input.pop(0)
     
     block = BlockNode()
@@ -235,27 +73,8 @@ def parseBlock(input, parent):
     
     return block
 
-def parseIdentifier(input, parent):
-    if input[0].type != TokenType.IDENTIFIER:
-        expectedFound(TokenType.IDENTIFIER, input[0].type)
-    
-    return IdentifierNode(input.pop(0).value)
-
-def parseAssign(input, parent):
-    if input[0].type != TokenType.ASSIGN:
-        expectedFound(TokenType.ASSIGN, input[0].type)
-        
-    input.pop(0)
-    
-    target = parent.pop(-1)
-    value = parseExpression(input, parent) #TODO: only expressions!
-    
-    return AssignExpression(target, value)
 
 def parseAsterisk(input, parent):
-    if input[0].type != TokenType.ASTERISK:
-        expectedFound(TokenType.ASTERISK, input[0].type)
-        
     input.pop(0)
     
     iterator = parent.pop(-1)
@@ -264,9 +83,6 @@ def parseAsterisk(input, parent):
     return AsteriskStatementNode(iterator, value)        
    
 def parseColon(input, parent):    
-    if input[0].type != TokenType.COLON:
-        expectedFound(TokenType.COLON, input[0].type)
-    
     input.pop(0)
     
     a = parent.pop(-1)
@@ -274,21 +90,22 @@ def parseColon(input, parent):
     
     return ColonNode(a, b)
    
-def parseFunctionCallOrIdentifier(input, parent):
+def parseFunctionCallOrAssignOrIdentifier(input, parent):
-    if input[0].type != TokenType.IDENTIFIER:
+    #import pdb; pdb.set_trace()
-        expectedFound(TokenType.IDENTIFIER, input[0].type)
+    identifier = IdentifierNode(input.pop(0).value)
-    
+    # Function call
-    if input[1].type == TokenType.OPEN_PAREN:
+    if len(input) > 0 and input[0].type == TokenType.OPEN_PAREN:            
-        identifier = parseIdentifier(input, parent)
         arguments = parseArguments(input, parent)        
         return FunctionCallNode(identifier, arguments)
+    # Assign
+    if len(input) > 1 and input[0].type == TokenType.ASSIGN:          
+        input.pop(0)            
+        value = parseExpression(input, parent) #TODO: only expressions!
+        return AssignExpression(identifier, value)
         
-    return parseIdentifier(input, parent)
+    return identifier
 
 def parsePercent(input, parent):
-    if input[0].type != TokenType.PERCENT:
-        expectedFound(TokenType.PERCENT, input[0].type)
-        
     input.pop(0)
     
     value = parent.pop(-1)
@@ -304,13 +121,11 @@ def parseExpression(input, parent):
     if type == TokenType.NOTE:
         return parseNote(input, parent)    
     if type == TokenType.IDENTIFIER:
-        return parseFunctionCallOrIdentifier(input, parent)
+        return parseFunctionCallOrAssignOrIdentifier(input, parent)
     if type == TokenType.PERCENT:
         return parsePercent(input, parent)
     if type == TokenType.OPEN_PAREN:
         return parseArguments(input, parent)
-    if type == TokenType.ASSIGN:
-        return parseAssign(input, parent)
     if type == TokenType.COLON:
         return parseColon(input, parent)    
  
@@ -330,12 +145,11 @@ def parseStatement(input, parent):
     return parseExpression(input, parent)
     
 def parseToken(input, parent):      
-    type = input[0].type    
+    #import pdb; pdb.set_trace()
-    
     return parseStatement(input, parent)    
     
   
-def parseProgram(input):    
+def parse(input):    
     root = Program()
     while len(input) > 0:
         root.append(parseToken(input, root))
@@ -343,12 +157,12 @@ def parseProgram(input):
   
 def test():
     try:
-        with open('test2.lit', 'r') as source:
+        with open(sys.argv[1], 'r') as source:
             lines = [line.rstrip('\n') for line in source.readlines()]
             
         tokens = [token for token in tokenize(lines) if token.type != TokenType.COMMENT]
         
-        ast = parseProgram(tokens)
+        ast = parse(tokens)
         
         print(ast)
     except TokenizerError as e: