Pristine copy of a subset of lib2to3 from Python 3.6.1.

For an experiment in running/bootstrapping OSH.

opy/Grammar.txt

@@ -0,0 +1,173 @@
# Grammar for 2to3. This grammar supports Python 2.x and 3.x.

# Note:  Changing the grammar specified in this file will most likely
#        require corresponding changes in the parser module
#        (../Modules/parsermodule.c).  If you can't make the changes to
#        that module yourself, please co-ordinate the required changes
#        with someone who can; ask around on python-dev for help.  Fred
#        Drake <fdrake@acm.org> will probably be listening there.

# NOTE WELL: You should also follow all the steps listed in PEP 306,
# "How to Change Python's Grammar"

# Commands for Kees Blom's railroad program
#diagram:token NAME
#diagram:token NUMBER
#diagram:token STRING
#diagram:token NEWLINE
#diagram:token ENDMARKER
#diagram:token INDENT
#diagram:output\input python.bla
#diagram:token DEDENT
#diagram:output\textwidth 20.04cm\oddsidemargin  0.0cm\evensidemargin 0.0cm
#diagram:rules

# Start symbols for the grammar:
#	file_input is a module or sequence of commands read from an input file;
#	single_input is a single interactive statement;
#	eval_input is the input for the eval() and input() functions.
# NB: compound_stmt in single_input is followed by extra NEWLINE!
file_input: (NEWLINE | stmt)* ENDMARKER
single_input: NEWLINE | simple_stmt | compound_stmt NEWLINE
eval_input: testlist NEWLINE* ENDMARKER

decorator: '@' dotted_name [ '(' [arglist] ')' ] NEWLINE
decorators: decorator+
decorated: decorators (classdef | funcdef | async_funcdef)
async_funcdef: ASYNC funcdef
funcdef: 'def' NAME parameters ['->' test] ':' suite
parameters: '(' [typedargslist] ')'
typedargslist: ((tfpdef ['=' test] ',')*
                ('*' [tname] (',' tname ['=' test])* [',' '**' tname] | '**' tname)
                | tfpdef ['=' test] (',' tfpdef ['=' test])* [','])
tname: NAME [':' test]
tfpdef: tname | '(' tfplist ')'
tfplist: tfpdef (',' tfpdef)* [',']
varargslist: ((vfpdef ['=' test] ',')*
              ('*' [vname] (',' vname ['=' test])*  [',' '**' vname] | '**' vname)
              | vfpdef ['=' test] (',' vfpdef ['=' test])* [','])
vname: NAME
vfpdef: vname | '(' vfplist ')'
vfplist: vfpdef (',' vfpdef)* [',']

stmt: simple_stmt | compound_stmt
simple_stmt: small_stmt (';' small_stmt)* [';'] NEWLINE
small_stmt: (expr_stmt | print_stmt  | del_stmt | pass_stmt | flow_stmt |
             import_stmt | global_stmt | exec_stmt | assert_stmt)
expr_stmt: testlist_star_expr (annassign | augassign (yield_expr|testlist) |
                     ('=' (yield_expr|testlist_star_expr))*)
annassign: ':' test ['=' test]
testlist_star_expr: (test|star_expr) (',' (test|star_expr))* [',']
augassign: ('+=' | '-=' | '*=' | '@=' | '/=' | '%=' | '&=' | '|=' | '^=' |
            '<<=' | '>>=' | '**=' | '//=')
# For normal and annotated assignments, additional restrictions enforced by the interpreter
print_stmt: 'print' ( [ test (',' test)* [','] ] |
                      '>>' test [ (',' test)+ [','] ] )
del_stmt: 'del' exprlist
pass_stmt: 'pass'
flow_stmt: break_stmt | continue_stmt | return_stmt | raise_stmt | yield_stmt
break_stmt: 'break'
continue_stmt: 'continue'
return_stmt: 'return' [testlist]
yield_stmt: yield_expr
raise_stmt: 'raise' [test ['from' test | ',' test [',' test]]]
import_stmt: import_name | import_from
import_name: 'import' dotted_as_names
import_from: ('from' ('.'* dotted_name | '.'+)
              'import' ('*' | '(' import_as_names ')' | import_as_names))
import_as_name: NAME ['as' NAME]
dotted_as_name: dotted_name ['as' NAME]
import_as_names: import_as_name (',' import_as_name)* [',']
dotted_as_names: dotted_as_name (',' dotted_as_name)*
dotted_name: NAME ('.' NAME)*
global_stmt: ('global' | 'nonlocal') NAME (',' NAME)*
exec_stmt: 'exec' expr ['in' test [',' test]]
assert_stmt: 'assert' test [',' test]

compound_stmt: if_stmt | while_stmt | for_stmt | try_stmt | with_stmt | funcdef | classdef | decorated | async_stmt
async_stmt: ASYNC (funcdef | with_stmt | for_stmt)
if_stmt: 'if' test ':' suite ('elif' test ':' suite)* ['else' ':' suite]
while_stmt: 'while' test ':' suite ['else' ':' suite]
for_stmt: 'for' exprlist 'in' testlist ':' suite ['else' ':' suite]
try_stmt: ('try' ':' suite
           ((except_clause ':' suite)+
	    ['else' ':' suite]
	    ['finally' ':' suite] |
	   'finally' ':' suite))
with_stmt: 'with' with_item (',' with_item)*  ':' suite
with_item: test ['as' expr]
with_var: 'as' expr
# NB compile.c makes sure that the default except clause is last
except_clause: 'except' [test [(',' | 'as') test]]
suite: simple_stmt | NEWLINE INDENT stmt+ DEDENT

# Backward compatibility cruft to support:
# [ x for x in lambda: True, lambda: False if x() ]
# even while also allowing:
# lambda x: 5 if x else 2
# (But not a mix of the two)
testlist_safe: old_test [(',' old_test)+ [',']]
old_test: or_test | old_lambdef
old_lambdef: 'lambda' [varargslist] ':' old_test

test: or_test ['if' or_test 'else' test] | lambdef
or_test: and_test ('or' and_test)*
and_test: not_test ('and' not_test)*
not_test: 'not' not_test | comparison
comparison: expr (comp_op expr)*
comp_op: '<'|'>'|'=='|'>='|'<='|'<>'|'!='|'in'|'not' 'in'|'is'|'is' 'not'
star_expr: '*' expr
expr: xor_expr ('|' xor_expr)*
xor_expr: and_expr ('^' and_expr)*
and_expr: shift_expr ('&' shift_expr)*
shift_expr: arith_expr (('<<'|'>>') arith_expr)*
arith_expr: term (('+'|'-') term)*
term: factor (('*'|'@'|'/'|'%'|'//') factor)*
factor: ('+'|'-'|'~') factor | power
power: [AWAIT] atom trailer* ['**' factor]
atom: ('(' [yield_expr|testlist_gexp] ')' |
       '[' [listmaker] ']' |
       '{' [dictsetmaker] '}' |
       '`' testlist1 '`' |
       NAME | NUMBER | STRING+ | '.' '.' '.')
listmaker: (test|star_expr) ( comp_for | (',' (test|star_expr))* [','] )
testlist_gexp: (test|star_expr) ( comp_for | (',' (test|star_expr))* [','] )
lambdef: 'lambda' [varargslist] ':' test
trailer: '(' [arglist] ')' | '[' subscriptlist ']' | '.' NAME
subscriptlist: subscript (',' subscript)* [',']
subscript: test | [test] ':' [test] [sliceop]
sliceop: ':' [test]
exprlist: (expr|star_expr) (',' (expr|star_expr))* [',']
testlist: test (',' test)* [',']
dictsetmaker: ( ((test ':' test | '**' expr)
                 (comp_for | (',' (test ':' test | '**' expr))* [','])) |
                ((test | star_expr)
		 (comp_for | (',' (test | star_expr))* [','])) )

classdef: 'class' NAME ['(' [arglist] ')'] ':' suite

arglist: argument (',' argument)* [',']

# "test '=' test" is really "keyword '=' test", but we have no such token.
# These need to be in a single rule to avoid grammar that is ambiguous
# to our LL(1) parser. Even though 'test' includes '*expr' in star_expr,
# we explicitly match '*' here, too, to give it proper precedence.
# Illegal combinations and orderings are blocked in ast.c:
# multiple (test comp_for) arguments are blocked; keyword unpackings
# that precede iterable unpackings are blocked; etc.
argument: ( test [comp_for] |
            test '=' test |
	    '**' expr |
	    star_expr )

comp_iter: comp_for | comp_if
comp_for: [ASYNC] 'for' exprlist 'in' testlist_safe [comp_iter]
comp_if: 'if' old_test [comp_iter]

testlist1: test (',' test)*

# not used in grammar, but may appear in "node" passed from Parser to Compiler
encoding_decl: NAME

yield_expr: 'yield' [yield_arg]
yield_arg: 'from' test | testlist

opy/pgen2/__init__.py

@@ -0,0 +1,4 @@
# Copyright 2004-2005 Elemental Security, Inc. All Rights Reserved.
# Licensed to PSF under a Contributor Agreement.

"""The pgen2 package."""

opy/pgen2/driver.py

@@ -0,0 +1,160 @@
# Copyright 2004-2005 Elemental Security, Inc. All Rights Reserved.
# Licensed to PSF under a Contributor Agreement.

# Modifications:
# Copyright 2006 Google, Inc. All Rights Reserved.
# Licensed to PSF under a Contributor Agreement.

"""Parser driver.

This provides a high-level interface to parse a file into a syntax tree.

"""

__author__ = "Guido van Rossum <guido@python.org>"

__all__ = ["Driver", "load_grammar"]

# Python imports
import codecs
import io
import os
import logging
import sys

# Pgen imports
from . import grammar, parse, token, tokenize, pgen


class Driver(object):

    def __init__(self, grammar, convert=None, logger=None):
        self.grammar = grammar
        if logger is None:
            logger = logging.getLogger()
        self.logger = logger
        self.convert = convert

    def parse_tokens(self, tokens, debug=False):
        """Parse a series of tokens and return the syntax tree."""
        # XXX Move the prefix computation into a wrapper around tokenize.
        p = parse.Parser(self.grammar, self.convert)
        p.setup()
        lineno = 1
        column = 0
        type = value = start = end = line_text = None
        prefix = ""
        for quintuple in tokens:
            type, value, start, end, line_text = quintuple
            if start != (lineno, column):
                assert (lineno, column) <= start, ((lineno, column), start)
                s_lineno, s_column = start
                if lineno < s_lineno:
                    prefix += "\n" * (s_lineno - lineno)
                    lineno = s_lineno
                    column = 0
                if column < s_column:
                    prefix += line_text[column:s_column]
                    column = s_column
            if type in (tokenize.COMMENT, tokenize.NL):
                prefix += value
                lineno, column = end
                if value.endswith("\n"):
                    lineno += 1
                    column = 0
                continue
            if type == token.OP:
                type = grammar.opmap[value]
            if debug:
                self.logger.debug("%s %r (prefix=%r)",
                                  token.tok_name[type], value, prefix)
            if p.addtoken(type, value, (prefix, start)):
                if debug:
                    self.logger.debug("Stop.")
                break
            prefix = ""
            lineno, column = end
            if value.endswith("\n"):
                lineno += 1
                column = 0
        else:
            # We never broke out -- EOF is too soon (how can this happen???)
            raise parse.ParseError("incomplete input",
                                   type, value, (prefix, start))
        return p.rootnode

    def parse_stream_raw(self, stream, debug=False):
        """Parse a stream and return the syntax tree."""
        tokens = tokenize.generate_tokens(stream.readline)
        return self.parse_tokens(tokens, debug)

    def parse_stream(self, stream, debug=False):
        """Parse a stream and return the syntax tree."""
        return self.parse_stream_raw(stream, debug)

    def parse_file(self, filename, encoding=None, debug=False):
        """Parse a file and return the syntax tree."""
        stream = codecs.open(filename, "r", encoding)
        try:
            return self.parse_stream(stream, debug)
        finally:
            stream.close()

    def parse_string(self, text, debug=False):
        """Parse a string and return the syntax tree."""
        tokens = tokenize.generate_tokens(io.StringIO(text).readline)
        return self.parse_tokens(tokens, debug)


def _generate_pickle_name(gt):
    head, tail = os.path.splitext(gt)
    if tail == ".txt":
        tail = ""
    return head + tail + ".".join(map(str, sys.version_info)) + ".pickle"


def load_grammar(gt="Grammar.txt", gp=None,
                 save=True, force=False, logger=None):
    """Load the grammar (maybe from a pickle)."""
    if logger is None:
        logger = logging.getLogger()
    gp = _generate_pickle_name(gt) if gp is None else gp
    if force or not _newer(gp, gt):
        logger.info("Generating grammar tables from %s", gt)
        g = pgen.generate_grammar(gt)
        if save:
            logger.info("Writing grammar tables to %s", gp)
            try:
                g.dump(gp)
            except OSError as e:
                logger.info("Writing failed: %s", e)
    else:
        g = grammar.Grammar()
        g.load(gp)
    return g


def _newer(a, b):
    """Inquire whether file a was written since file b."""
    if not os.path.exists(a):
        return False
    if not os.path.exists(b):
        return True
    return os.path.getmtime(a) >= os.path.getmtime(b)


def main(*args):
    """Main program, when run as a script: produce grammar pickle files.

    Calls load_grammar for each argument, a path to a grammar text file.
    """
    if not args:
        args = sys.argv[1:]
    logging.basicConfig(level=logging.INFO, stream=sys.stdout,
                        format='%(message)s')
    for gt in args:
        load_grammar(gt, save=True, force=True)
    return True

if __name__ == "__main__":
    sys.exit(int(not main()))