4:52
 5Ú    # Copyright 2004-2005 Elemental Security, Inc. All Rights Reserved.
# Licensed to PSF under a Contributor Agreement.

# Pgen imports
from . import grammar, token, tokenize

class PgenGrammar(grammar.Grammar):
    pass

class ParserGenerator(object):

    def __init__(self, filename, stream=None):
        close_stream = None
        if stream is None:
            stream = open(filename)
            close_stream = stream.close
        self.filename = filename
        self.stream = stream
        self.generator = tokenize.generate_tokens(stream.readline)
        self.gettoken() # Initialize lookahead
        self.dfas, self.startsymbol = self.parse()
        if close_stream is not None:
            close_stream()
        self.first = {} # map from symbol name to set of tokens
        self.addfirstsets()

    def make_grammar(self):
        c = PgenGrammar()
        names = self.dfas.keys()
        names.sort()
        names.remove(self.startsymbol)
        names.insert(0, self.startsymbol)
        for name in names:
            i = 256 + len(c.symbol2number)
            c.symbol2number[name] = i
            c.number2symbol[i] = name
        for name in names:
            dfa = self.dfas[name]
            states = []
            for state in dfa:
                arcs = []
                for label, next in state.arcs.iteritems():
                    arcs.append((self.make_label(c, label), dfa.index(next)))
                if state.isfinal:
                    arcs.append((0, dfa.index(state)))
                states.append(arcs)
            c.states.append(states)
            c.dfas[c.symbol2number[name]] = (states, self.make_first(c, name))
        c.start = c.symbol2number[self.startsymbol]
        return c

    def make_first(self, c, name):
        rawfirst = self.first[name]
        first = {}
        for label in rawfirst:
            ilabel = self.make_label(c, label)
            ##assert ilabel not in first # XXX failed on <> ... !=
            first[ilabel] = 1
        return first

    def make_label(self, c, label):
        # XXX Maybe this should be a method on a subclass of converter?
        ilabel = len(c.labels)
        if label[0].isalpha():
            # Either a symbol name or a named token
            if label in c.symbol2number:
                # A symbol name (a non-terminal)
                if label in c.symbol2label:
                    return c.symbol2label[label]
                else:
                    c.labels.append((c.symbol2number[label], None))
                    c.symbol2label[label] = ilabel
                    return ilabel
            else:
                # A named token (NAME, NUMBER, STRING)
                itoken = getattr(token, label, None)
                assert isinstance(itoken, int), label
                assert itoken in token.tok_name, label
                if itoken in c.tokens:
                    return c.tokens[itoken]
                else:
                    c.labels.append((itoken, None))
                    c.tokens[itoken] = ilabel
                    return ilabel
        else:
            # Either a keyword or an operator
            assert label[0] in ('"', "'"), label
            value = eval(label)
            if value[0].isalpha():
                # A keyword
                if value in c.keywords:
                    return c.keywords[value]
                else:
                    c.labels.append((token.NAME, value))
                    c.keywords[value] = ilabel
                    return ilabel
            else:
                # An operator (any non-numeric token)
                itoken = grammar.opmap[value] # Fails if unknown token
                if itoken in c.tokens:
                    return c.tokens[itoken]
                else:
                    c.labels.append((itoken, None))
                    c.tokens[itoken] = ilabel
                    return ilabel

    def addfirstsets(self):
        names = self.dfas.keys()
        names.sort()
        for name in names:
            if name not in self.first:
                self.calcfirs