Experimental parser: move code gen to own class

tools/lexer_generator/transition_keys.py

 # Copyright 2013 the V8 project authors. All rights reserved.
 # Redistribution and use in source and binary forms, with or without
 # modification, are permitted provided that the following conditions are
 # met:
 #
 #     * Redistributions of source code must retain the above copyright
 #       notice, this list of conditions and the following disclaimer.
 #     * Redistributions in binary form must reproduce the above
 #       copyright notice, this list of conditions and the following
 #       disclaimer in the documentation and/or other materials provided
@@ skipping 172 matching lines @@
   def __hash__(self):
     if self.__cached_hash == None:
       initial_hash = hash((-1, TransitionKey.__upper_bound + 1))
       f = lambda acc, r: acc ^ hash(r)
       self.__cached_hash = reduce(f, self.__ranges, initial_hash)
     return self.__cached_hash
 
   def __eq__(self, other):
     return isinstance(other, self.__class__) and self.__ranges == other.__ranges
 
-  def to_code(self):
-    code = 'if ('
-    first = True
+  @staticmethod
+  def __class_name(r):
+    for name, v in TransitionKey.__class_bounds.items():
+      if r == v: return name
+    assert False
+
+  def range_iter(self):
+    assert not self == TransitionKey.epsilon() and not self.__is_unique()
     for r in self.__ranges:
-      if r[0] >= 256: # FIXME: add class checks
-        continue
-      if not first:
-        code += ' || '
-      if r[0] == r[1]:
-        code += 'yych == %s' % r[0]
-      elif r[0] == 0:
-        code += 'yych <= %s' % r[1]
-      elif r[1] == 255: # FIXME: this should depend on the char type maybe??
-        code += 'yych >= %s' % r[0]
+      if self.__is_class_range(r):
+        yield ('CLASS', TransitionKey.__class_name(r))
       else:
-        code += '(yych >= %s && yych <= %s)' % (r[0], r[1])
-      first = False
-    code += ')'
-    return code
+        yield ('LATIN_1', r)
 
   __printable_cache = {
     ord('\t') : '\\t',
     ord('\n') : '\\n',
     ord('\r') : '\\r',
   }
 
   @staticmethod
   def __range_str(r):
     if TransitionKey.__is_class_range(r):
-      for name, v in TransitionKey.__class_bounds.items():
-        if r == v: return name
-      assert False
+      return TransitionKey.__class_name(r)
     def to_str(x):
       assert TransitionKey.__in_latin_1(x)
       if not x in TransitionKey.__printable_cache:
         res = "'%s'" % chr(x) if chr(x) in printable else str(x)
         TransitionKey.__printable_cache[x] = res
       return TransitionKey.__printable_cache[x]
     if r[0] == r[1]:
       return "%s" % to_str(r[0])
     else:
       return "[%s-%s]" % (to_str(r[0]), to_str(r[1]))
@@ skipping 109 matching lines @@
       elif last[1] + 1 < r[0]:
         inverted.append((last[1] + 1, r[0] - 1))
       last = r
     upper_bound = latin_1[1]
     if last == None:
       inverted.append(latin_1)
     elif last[1] < upper_bound:
       inverted.append((last[1] + 1, upper_bound))
     inverted += list(classes)
     return inverted