Merge pull request #407 from Chasmiccoder/in-402

Fixed issue 402. Now simc programs with unbalanced brackets will raise an error.

simc/lexical_analyzer.py

@@ -288,6 +288,7 @@ def get_raw_tokens(source_code,i,line_num):
         i += 1
         line_num += 1
 
+
 def lexical_analyze(filename, table):
     """
     Generate tokens from source code
@@ -338,6 +339,10 @@ def lexical_analyze(filename, table):
     # This is to presently differentiate between bitwise and
     # and address of operations.
     got_num_or_var = False
+
+    # To check if the brackets are balanced:
+    top = -1
+    balanced_brackets_stack = [ ]
 
     while source_code[i] != "\0":
 
@@ -346,8 +351,8 @@ def lexical_analyze(filename, table):
             raw_tokens,i,line_num = get_raw_tokens(source_code,i,line_num)
             tokens.extend(raw_tokens)
             raw_c = False
-            got_num_or_var = False
-            
+            got_num_or_var = False        
+
         # If a digit appears, call numeric_val function and add the numeric token to list,
         # if it was correct
         if is_digit(source_code[i]):
@@ -397,13 +402,31 @@ def lexical_analyze(filename, table):
 
         # Identifying left paren token
         elif source_code[i] == "(":
+            # To check if brackets are balanced:
+            top += 1
+            balanced_brackets_stack.append( '(' )
+
             parantheses_count += 1
             tokens.append(Token("left_paren", "", line_num))
             i += 1
             got_num_or_var = False
 
         # Identifying right paren token
         elif source_code[i] == ")":
+            # To check if brackets are balanced:
+            if top == -1:
+                # If at any time there is underflow, there are too many closing brackets.
+                top -= 1
+                balanced_brackets_stack = balanced_brackets_stack[ :-1]
+                error( "Too many closing parentheses", line_num )
+            elif balanced_brackets_stack[ top ] != '(':
+                error( "Unbalanced parentheses error", line_num )
+
+
+            else:
+                top -= 1
+                balanced_brackets_stack = balanced_brackets_stack[ :-1]
+
             if parantheses_count > 0:
                 parantheses_count -= 1
                 tokens.append(Token("right_paren", "", line_num))
@@ -417,7 +440,7 @@ def lexical_analyze(filename, table):
                     tokens.append(Token("call_end", "", line_num))
 
             else:
-               error("Parentheses does not match.", line_num);
+               error("Parentheses does not match", line_num)
 
             got_num_or_var = False
             i += 1
@@ -427,30 +450,64 @@ def lexical_analyze(filename, table):
             if parantheses_count == 0:
                 tokens.append(Token("newline", "", line_num))
             else:
-                error("Parentheses does not match.", line_num);
+                error("Parentheses does not match.", line_num)
 
             i += 1
             line_num += 1
 
         # Identifying left brace token
         elif source_code[i] == "{":
+            # To check if brackets are balanced:
+            top += 1
+            balanced_brackets_stack.append( '{' )
+
             tokens.append(Token("left_brace", "", line_num))
             i += 1
             got_num_or_var = False
 
         # Identifying right brace token
         elif source_code[i] == "}":
+            # To check if brackets are balanced:
+            if top == -1:
+                # If at any time there is underflow, there are too many closing brackets.
+                top -= 1
+                balanced_brackets_stack = balanced_brackets_stack[ :-1]
+                error( "Too many closing braces", line_num )
+            elif balanced_brackets_stack[ top ] != '{':
+                error( "Unbalanced braces error", line_num )
+
+            else:
+                top -= 1
+                balanced_brackets_stack = balanced_brackets_stack[ :-1]
+
             tokens.append(Token("right_brace", "", line_num))
             i += 1
             got_num_or_var = False
 
         # Identifying left bracket token
         elif source_code[i] == "[":
+            # To check if brackets are balanced:
+            top += 1
+            balanced_brackets_stack.append( '[' )
+
             tokens.append(Token("left_bracket", "", line_num))
             i += 1
 
         # Identifying right bracket token
         elif source_code[i] == "]":
+            # To check if brackets are balanced:
+            if top == -1:
+                # If at any time there is underflow, there are too many closing brackets.
+                top -= 1
+                balanced_brackets_stack = balanced_brackets_stack[ :-1]
+                error( "Too many closing brackets", line_num )
+            elif balanced_brackets_stack[ top ] != '[':
+                error( "Unbalanced brackets error", line_num )
+
+            else:
+                top -= 1
+                balanced_brackets_stack = balanced_brackets_stack[ :-1]
+
             tokens.append(Token("right_bracket", "", line_num))
             i += 1
 
@@ -632,6 +689,10 @@ def lexical_analyze(filename, table):
         # Otherwise increment the index
         else:
             i += 1
-
+
+    # By the end, if stack is not empty, there are extra opening brackets
+    if top != -1:
+        error( "Unbalanced parenthesis error", line_num )
+
     # Return the generated tokens
     return tokens, module_source_paths