Began refactoring of lalr_analysis -> grammar_analysis

lark/parsers/lalr_analysis.py

@@ -57,58 +57,11 @@ def update_set(set1, set2):
     set1 |= set2
     return set1 != copy
 
-class GrammarAnalyzer(object):
-    def __init__(self, rule_tuples, start_symbol, debug=False):
-        self.start_symbol = start_symbol
-        self.debug = debug
-        rule_tuples = list(rule_tuples)
-        rule_tuples.append(('$root', [start_symbol, '$end']))
-        rule_tuples = [(t[0], t[1], None) if len(t)==2 else t for t in rule_tuples]
-
-        self.rules = set()
-        self.rules_by_origin = {o: [] for o, _x, _a in rule_tuples}
-        for origin, exp, alias in rule_tuples:
-            r =  Rule( origin, exp, alias )
-            self.rules.add(r)
-            self.rules_by_origin[origin].append(r)
-
-        for r in self.rules:
-            for sym in r.expansion:
-                if not (is_terminal(sym) or sym in self.rules_by_origin):
-                    raise GrammarError("Using an undefined rule: %s" % sym)
-
-        self.init_state = self.expand_rule(start_symbol)
-
-    def expand_rule(self, rule):
-        "Returns all init_ptrs accessible by rule (recursive)"
-        init_ptrs = set()
-        def _expand_rule(rule):
-            assert not is_terminal(rule)
-
-            for r in self.rules_by_origin[rule]:
-                init_ptr = RulePtr(r, 0)
-                init_ptrs.add(init_ptr)
-
-                if r.expansion: # if not empty rule
-                    new_r = init_ptr.next
-                    if not is_terminal(new_r):
-                        yield new_r
-
-        _ = list(bfs([rule], _expand_rule))
-
-        return fzset(init_ptrs)
-
-    def _first(self, r):
-        if is_terminal(r):
-            return {r}
-        else:
-            return {rp.next for rp in self.expand_rule(r) if is_terminal(rp.next)}
-
-    def _calc(self):
+def calculate_sets(rules):
     """Calculate FOLLOW sets.
 
     Adapted from: http://lara.epfl.ch/w/cc09:algorithm_for_first_and_follow_sets"""
-        symbols = {sym for rule in self.rules for sym in rule.expansion} | {rule.origin for rule in self.rules}
+    symbols = {sym for rule in rules for sym in rule.expansion} | {rule.origin for rule in rules}
     symbols.add('$root')    # what about other unused rules?
 
     # foreach grammar rule X ::= Y(1) ... Y(k)
@@ -135,7 +88,7 @@ class GrammarAnalyzer(object):
     while changed:
         changed = False
 
-            for rule in self.rules:
+        for rule in rules:
             if set(rule.expansion) <= NULLABLE:
                 if update_set(NULLABLE, {rule.origin}):
                     changed = True
@@ -153,10 +106,59 @@ class GrammarAnalyzer(object):
                         if update_set(FOLLOW[sym], FIRST[rule.expansion[j]]):
                             changed = True
 
-        self.FOLLOW = FOLLOW
+    return FIRST, FOLLOW, NULLABLE
+
+
+class GrammarAnalyzer(object):
+    def __init__(self, rule_tuples, start_symbol, debug=False):
+        self.start_symbol = start_symbol
+        self.debug = debug
+        rule_tuples = list(rule_tuples)
+        rule_tuples.append(('$root', [start_symbol, '$end']))
+        rule_tuples = [(t[0], t[1], None) if len(t)==2 else t for t in rule_tuples]
+
+        self.rules = set()
+        self.rules_by_origin = {o: [] for o, _x, _a in rule_tuples}
+        for origin, exp, alias in rule_tuples:
+            r =  Rule( origin, exp, alias )
+            self.rules.add(r)
+            self.rules_by_origin[origin].append(r)
+
+        for r in self.rules:
+            for sym in r.expansion:
+                if not (is_terminal(sym) or sym in self.rules_by_origin):
+                    raise GrammarError("Using an undefined rule: %s" % sym)
+
+        self.init_state = self.expand_rule(start_symbol)
+
+        self.FIRST, self.FOLLOW, self.NULLABLE = calculate_sets(self.rules)
+
+    def expand_rule(self, rule):
+        "Returns all init_ptrs accessible by rule (recursive)"
+        init_ptrs = set()
+        def _expand_rule(rule):
+            assert not is_terminal(rule)
+
+            for r in self.rules_by_origin[rule]:
+                init_ptr = RulePtr(r, 0)
+                init_ptrs.add(init_ptr)
+
+                if r.expansion: # if not empty rule
+                    new_r = init_ptr.next
+                    if not is_terminal(new_r):
+                        yield new_r
+
+        _ = list(bfs([rule], _expand_rule))
+
+        return fzset(init_ptrs)
+
+    def _first(self, r):
+        if is_terminal(r):
+            return {r}
+        else:
+            return {rp.next for rp in self.expand_rule(r) if is_terminal(rp.next)}
 
     def analyze(self):
-        self._calc()
 
         self.states = {}
         def step(state):