We can now do excel cell references (only in if statements for now)

Author: JessicaTegner

code_generator.py

@@ -94,5 +94,8 @@ def generate_AssignmentNode(self, node):
     def generate_IdentifierNode(self, node):
         return node.value
 
+    def generate_CellReferenceNode(self, node):
+        return f"sheet['{node.value}'].value"
+    
 
 

custom_parser.py

@@ -1,6 +1,6 @@
 import logging
 from dictionary import Dictionary
-from parser_nodes import AssignmentNode, ExpressionNode, NumberNode, IfNode
+from parser_nodes import AssignmentNode, ExpressionNode, NumberNode, IfNode, CellReferenceNode
 
 logger = logging.getLogger(__name__)
 
@@ -71,6 +71,8 @@ def parse_primary(self, tokens):
         token = tokens[0]
         if token.type == Dictionary.INTEGER:
             return NumberNode(token.value), 1
+        elif token.type == Dictionary.CELL:
+            return self.parse_cell_reference(token), 1
         elif token.type == Dictionary.LEFT_PARENTHESES:
             # Find matching parenthesis to handle nested cases
             count = 1
@@ -150,6 +152,28 @@ def parse_assignment(self, line):
         # otherwise, parse the expression
         expression = self.parse_expression(variable_value)
         return AssignmentNode(variable, expression)
+    
+    def parse_cell_reference(self, token):
+        """Parse a cell reference."""
+        # token.value should be any amount of alphabetic characters followed by any amount of numeric characters
+        # if there are no numeric characters, raise an error
+        # if there are no alphabetic characters, raise an error
+        # if there are any other characters, raise an error
+        if not token.value:
+            raise ValueError("Empty cell reference")
+        if not any(char in token.value for char in Dictionary.NUMERIC_CHARACTERS):
+            raise ValueError("Invalid cell reference")
+        if not any(char in token.value for char in Dictionary.ALPHABETIC_CHARACTERS):
+            raise ValueError("Invalid cell reference")
+        if any(char not in Dictionary.NUMERIC_CHARACTERS + Dictionary.ALPHABETIC_CHARACTERS for char in token.value):
+            raise ValueError("Invalid cell reference")
+        # there can be no numeric characters before the alphabetic characters. SO go through the string until we find a numeric character, and then check if the rest of the string is numeric
+        i = 0
+        while i < len(token.value) and token.value[i] not in Dictionary.NUMERIC_CHARACTERS:
+            i += 1
+        if not token.value[i:].isnumeric():
+            raise ValueError("Invalid cell reference")
+        return CellReferenceNode(token.value)
 
 
 

dictionary.py

@@ -8,6 +8,7 @@ class Dictionary:
     # TOKEN TYPES
     INTEGER                     = 'INT'
     FLOAT                       = 'FLOAT'
+    CELL                        = 'CELL'
     PLUS                        = 'PLUS'
     MINUS                       = 'MINUS'
     MULTIPLICATION              = 'MULT'

lexer.py

@@ -101,6 +101,8 @@ def keyword_tokenize(self):
         # Return appropriate token
         if alphanumerical_string == "is":
             return self.handle_multi_word_operator(alphanumerical_string)
+        elif alphanumerical_string == "cell":
+            return self.handle_excel_cell()
         elif alphanumerical_string in Dictionary.KEYWORDS:
             return Token(Dictionary.KEYWORD, alphanumerical_string)
         # It wasn't a keyword, so it must be an identifier   
@@ -113,6 +115,18 @@ def peek(self):
             return self.input_string[self.position.index + 1]
         else:
             return None
+        
+    # Handle Excel cell references (e.g. 'A1', 'B2', 'C3')
+    def handle_excel_cell(self):
+        cell_reference = self.peek_word_ahead()
+        self.advance_n(len(cell_reference))
+        cell_reference = cell_reference.strip()
+        # an excel cell reference is any amount of alphabetic characters followed by any amount of numeric characters
+        # validating this will be handled in the parser
+        # advance the focus to the end of the cell reference
+        return Token(Dictionary.CELL, cell_reference)
+
+        
 
     # TODO: Could potentially be made more bullet-proof in regards to syntax errors
     # Check for multi-word operators (e.g. 'is equal to', 'is greater than')

parser_nodes.py

@@ -56,4 +56,14 @@ def __repr__(self):
 
     def __str__(self):
         return self.__repr__()
-    
+    
+class CellReferenceNode(Node):
+    """Class for nodes that represent cell references."""
+    def __init__(self, value):
+        self.value = value
+
+    def __repr__(self):
+        return f"CellReferenceNode({self.value})"
+    
+    def __str__(self):
+        return self.__repr__()

text_input.txt

@@ -1,3 +1,3 @@
 (2+3)*2
-if 1 is not equal to 1
-	hello is yes
+if cell a1  is not equal to 1
+	hello is yes