Merge branch 'master' of https://git.uwaterloo.ca/x299yang/cs444

Scanning.py

@@ -61,29 +61,29 @@ def idsToTokens(tokens):
 
 # a set that contains keywords that are in Java but not in Joos
 wrongJavaKeyWordDict = {
-    'assert', 
-    'break', 
-    'case', 
-    'catch', 
-    'const', 
-    'continue', 
-    'default', 
-    'do', 
-    'double', 
-    'enum', 
-    'finally', 
-    'float', 
-    'goto', 
-    'long', 
-    'private', 
-    'strictfp', 
-    'super', 
-    'switch', 
-    'synchronized', 
-    'throw', 
-    'throws', 
-    'transient', 
-    'try', 
+    'assert',
+    'break',
+    'case',
+    'catch',
+    'const',
+    'continue',
+    'default',
+    'do',
+    'double',
+    'enum',
+    'finally',
+    'float',
+    'goto',
+    'long',
+    'private',
+    'strictfp',
+    'super',
+    'switch',
+    'synchronized',
+    'throw',
+    'throws',
+    'transient',
+    'try',
     'volatile',
     '_',
     'this',
@@ -92,7 +92,7 @@ wrongJavaKeyWordDict = {
     'Float'
 }
 
-# a set that contains unsed operators or seperators 
+# a set that contains unsed operators or seperators
 wrongJavaOpDict = {
     'ELLIPSIS',
     'ARROW'
@@ -103,13 +103,13 @@ wrongJavaOpDict = {
 #################  Joos DFA Tokens ###################################
 JoosDFATokens = set([
     # Identifiers or Keywords (keywords are mapped to their token name in idToTokenDict above)
-    'ID',             
+    'ID',
 
     # Literals and names (note: 'this' is considered as a keyword)
     'NUM',            # number (excludes 0)
-    'ZERO',           # 0 
+    'ZERO',           # 0
     'LITERALBOOL',    # true or false
-    'LITERALCHAR',    # character e.g. 'c', includes escape characters? 
+    'LITERALCHAR',    # character e.g. 'c', includes escape characters?
     'LITERALSTRING',  # string e.g. "hello", includes escape sequences
     'NULL',           # null
     'COMPID',         # compound ids e.g. java.util.vectors
@@ -170,7 +170,7 @@ def JoosTransition(input, state):
         if input == '\n':
             return 'NEWLINE'
         return None
-    
+
     elif (state == 'START'):
         if (input.isalpha() or input == '_' or input == '$'):
             return 'ID'
@@ -231,7 +231,7 @@ def JoosTransition(input, state):
             return 'COMMA'
         if (input == '.'):
             return 'PERIOD'
-        
+
         # literals
         if (input == '\"'):
             return 'LSTRING'
@@ -262,7 +262,7 @@ def JoosTransition(input, state):
             return 'OPDISCARD'
         return None
 
-            
+
     elif (state == 'ID'):
         # dealing with compound names
         if input == '.':
@@ -270,7 +270,7 @@ def JoosTransition(input, state):
         if (input.isalpha() or input.isdigit() or input == '_' or input == '$'):
             return 'ID'
         return None
-    
+
     # Compound names
     elif state == 'HALFCOMP':
         if input.isalpha():
@@ -286,7 +286,7 @@ def JoosTransition(input, state):
         if input.isalpha() or input.isdigit():
             return 'COMPID'
         return None
-   
+
     elif (state == 'NUM'):
         if(input.isdigit()):
             return 'NUM'
@@ -304,6 +304,8 @@ def JoosTransition(input, state):
     elif (state == 'STRINGESC'):
         if input == 'u':
             return 'UNICODE' #going to be discarded
+        if input not in ('n', 'r', 't', 'v', '\\','\'', '"', '?', 'b' ):
+            return None
         return 'LSTRING'
 
     # char literal
@@ -312,6 +314,8 @@ def JoosTransition(input, state):
             return 'CHARESC'
         return 'CHAREND'
     elif (state == 'CHARESC'):
+        if input not in ('n', 'r', 't', 'v', '\\','\'', '"', '?', 'b' ):
+            return None
         return 'CHAREND'
     elif (state == 'CHAREND'):
         if (input == '\''):
@@ -352,7 +356,7 @@ def JoosTransition(input, state):
             return 'OPDISCARD'
         return None
 
-      
+
     # Comments
     elif(state == 'DIV'):
         if (input == '/'):
@@ -392,14 +396,14 @@ def JoosTransition(input, state):
         if(input == '.'):
             return 'ELLIPSIS'
         return None
-    
+
     # Handling hexidecimal literals (error case)
     elif state == 'ZERO':
         if input == 'x':
             return 'HEXLITERAL'
         elif input == '.':
             return 'FLOAT'
-    
+
     else:
         return None
 
@@ -460,7 +464,7 @@ def scan(input):
     # Handling error in munching
     if (tokens is None):
         return (None, "Error on Scanning character: " + str(result[1]))
-    
+
     if (tokens):
         # Handle erroneous tokens (return None and error string)
         multiLineCommentFlag = False
@@ -499,8 +503,8 @@ def scan(input):
                 multiLineCommentFlag = True
             if token.name == 'RCOMMENT':
                 multiLineCommentFlag = False
-            
-            
+
+
 
         # Checking for missing closing */ for multi line comments
         if multiLineCommentFlag is True: