push

Scanning.py

 import re # regex
 import string
 
-
 # class ScanDFA():
 # scans the input line by line, and char by char for each line
 # explicitly recognize whitespace when scanning, but discard whitespace tokens at the end
 
+##################### Token ##########################################
+# A Token is a pair (name, lexeme)
+class Token(){
+    def __init__(self, name, lex):
+        self.name = name
+        self.lex = lex
+}
+
 #################  Joos Token Names in 5 categoeis ##########################
 
 JoosTokens = set([
-
     # Literals:
     'INT',
     # Operants:
     '+',
-
-
     # Separators:
     'L(',
-
-
-
     # Keywords:
     'ID', '', 'SQL', 'Git', 'Tableau', 'SAS',
-
-
     ])
-##################### Token ##########################################
-# A Token is a pair (name, lexeme)
-class Token(){
-    def __init__(self, name, lex):
-        self.name = name
-        self.lex = lex
-}
 
 ##################### Transition function ############################
 
@@ -50,6 +42,14 @@ def JoosTransition(input, state):
 
 ##################### Other DFA elements ##############################
 
+JoosAccept = JoosTokens.union({'WHITESPACE', 'COMMENT'})
+JoosStates = JoosAccept.union({'START'}) #TODO: add intermediate states here
+JoosAlphabet = set(string.ascii_lowercase)
+            .union(set(string.ascii_uppercase))
+            .union(set(string.digits))
+            .union(set(list(".;,{}()[]<>!+-*/=''\"\\"))),
+             #TODO: add operand and separator characters to alphabet
+
 #########################  DFA  #######################################
 class DFA ():
     def __init__(self, states, alphabet, transition, start, accepting):
@@ -69,10 +69,7 @@ class DFA ():
 
 JoosDFA = DFA(
     states = JoosTokens,
-    alphabet = set(string.ascii_lowercase)
-                .union(set(string.ascii_uppercase))
-                .union(set(list(".;,{}()[]<>!+-*/=''\"\\"))),
-                 #TODO: add operand and separator characters to alphabet
+    alphabet = JoosAlphabet,
     start = 'START',
     accept = JoosTokens,
     transition = JoosTransition
@@ -104,5 +101,5 @@ def scan(input):
     # TODO: handle edge cases (e.g. check int range, error on ++
 
     # remove whitespace and comments
-    tokens = filter(lambda t: t.name not in ("WHITESPACE", "COMMENT"), tokens) 
+    tokens = filter(lambda t: t.name not in ("WHITESPACE", "COMMENT"), tokens)
     return tokens

test.joos

+public class A {
+  public A() {}
+  protected boolean x;
+}