# Copyright (c) 2016 Rocky Bernstein """ spark grammar differences over Python 3.5 for Python 3.6. """ from __future__ import print_function from uncompyle6.parser import PythonParserSingle from spark_parser import DEFAULT_DEBUG as PARSER_DEFAULT_DEBUG from uncompyle6.parsers.parse35 import Python35Parser class Python36Parser(Python35Parser): def __init__(self, debug_parser=PARSER_DEFAULT_DEBUG): super(Python36Parser, self).__init__(debug_parser) self.customized = {} def p_36misc(self, args): """ formatted_value ::= LOAD_FAST FORMAT_VALUE str ::= LOAD_CONST joined_str ::= LOAD_CONST LOAD_ATTR format_value_or_strs BUILD_LIST CALL_FUNCTION format_value_or_strs ::= format_value_or_strs format_value_or_str format_value_or_strs ::= format_value_or_str format_value_or_str ::= format_value format_value_or_str ::= str """ class Python36ParserSingle(Python36Parser, PythonParserSingle): pass if __name__ == '__main__': # Check grammar p = Python36Parser() p.checkGrammar() from uncompyle6 import PYTHON_VERSION, IS_PYPY if PYTHON_VERSION == 3.6: lhs, rhs, tokens, right_recursive = p.checkSets() from uncompyle6.scanner import get_scanner s = get_scanner(PYTHON_VERSION, IS_PYPY) opcode_set = set(s.opc.opname).union(set( """JUMP_BACK CONTINUE RETURN_END_IF COME_FROM LOAD_GENEXPR LOAD_ASSERT LOAD_SETCOMP LOAD_DICTCOMP LOAD_CLASSNAME LAMBDA_MARKER RETURN_LAST """.split())) remain_tokens = set(tokens) - opcode_set import re remain_tokens = set([re.sub('_\d+$','', t) for t in remain_tokens]) remain_tokens = set([re.sub('_CONT$','', t) for t in remain_tokens]) remain_tokens = set(remain_tokens) - opcode_set print(remain_tokens) # print(sorted(p.rule2name.items()))