Compare commits

...

44 Commits

Author SHA1 Message Date
rocky
9e37495493 Sync with master 2017-10-10 23:06:22 -04:00
rocky
77b93c5f21 Sync with master 2017-10-10 23:04:25 -04:00
rocky
0b198ee881 Sync with master 2017-10-10 23:02:20 -04:00
rocky
9e0c65881d Sync with master 2017-10-10 22:52:07 -04:00
rocky
c796d6a799 Merge commit '1d7a3c6444eab5a02d899f789f2a57cfdcbc5a84' into python-2.4 2017-10-10 22:50:28 -04:00
rocky
3892fb533a Misc bugs 2017-10-10 16:12:02 -04:00
rocky
2ea7487ca7 One more test 2017-10-05 11:19:36 -04:00
rocky
d4f6cec3d0 Sync with master 2017-10-05 11:17:49 -04:00
rocky
b1705e283d handle newer parser reduction behavior 2017-10-03 11:54:24 -04:00
rocky
eee751e22a Go over table-semantics description yet again 2017-10-03 05:44:55 -04:00
rocky
2b0fefb95f Sync with master 2017-10-02 03:12:26 -04:00
rocky
1d7a3c6444 Document hacky customize arg count better. 2017-09-30 18:02:35 -04:00
rocky
e7778f83f2 Word hacking 2017-09-26 10:35:00 -04:00
rocky
b51039ac1e Get ready for release 2.12.0 2017-09-26 09:59:55 -04:00
rocky
1a627ba207 Annotation field can be unicode...
When deparsing Python 3.x from Python 2.
2017-09-26 09:53:26 -04:00
rocky
f73f0ba41c No unicode in Python3.
but we need it in Python2. The bug was probably introduced
as a result of recent Python code type unteroperability canonicalization
2017-09-26 09:43:01 -04:00
rocky
114f979555 Pyton 3.1 Annotation args can be unicode? 2017-09-26 09:31:04 -04:00
rocky
ea75bcf47e Require xdis 3.6.0 or greater 2017-09-25 20:11:53 -04:00
rocky
6c6dcab857 Merge branch 'python-2.4' of github.com:rocky/python-uncompyle6 into python-2.4 2017-09-25 20:09:04 -04:00
rocky
0654aed6c8 Get ready for release 2.12.0 2017-09-25 20:08:50 -04:00
rocky
7b38d2f1f8 Adjust for xdis opcode JUMP_OPS. release 2.12.0 2017-09-25 20:01:31 -04:00
rocky
dfbd60231b Get ready for release 2.12.0 2017-09-25 19:11:25 -04:00
rocky
8b67f2ccd0 Python 3 compatibility 2017-09-21 11:47:42 -04:00
rocky
3447ca0767 Unit test for format-specifiers 2017-09-21 11:29:17 -04:00
rocky
aadea7224d Unit test for format-specifiers
And in the process we catch some small bugs
2017-09-21 11:25:51 -04:00
rocky
1e858efafd Tidy pysource and fragments 2017-09-20 19:08:41 -04:00
rocky
da7421da1c Tidy pysource and fragments a little more 2017-09-20 19:02:56 -04:00
rocky
ce88a72ea1 Tidy/regularize table entry formatting 2017-09-20 17:52:48 -04:00
rocky
96ca68a6fe Tidy/regularize table entry formatting 2017-09-20 17:47:56 -04:00
rocky
147b6e1cfe Small fixes
test_pyenvlib.py: it is sys.exit(), not exit()
pysource.py: reinstate nod type of async_func_call
2017-09-20 11:32:42 -04:00
rocky
7725b8e7de small fixes...
test_pythonlib.py: it is sys.exit not exit
pysource.py: restore node type on async_call function
2017-09-20 11:30:50 -04:00
rocky
d7b12f4da1 More small doc changes 2017-09-20 02:49:14 -04:00
rocky
62ddbe320d Start pysource unit test 2017-09-20 01:15:37 -04:00
rocky
c7b9e54e59 Update Table-driven info...
Start a pysource unit test.
2017-09-20 00:06:50 -04:00
rocky
a694601264 emgine -> template_engine 2017-09-17 12:03:49 -04:00
rocky
3003070acb engine -> template_engine 2017-09-17 11:56:51 -04:00
rocky
19d6dedcf5 Need weak-verification on 3.4 for now 2017-09-13 01:09:04 -04:00
rocky
51ad3fb36e Revert one of the changes pending a better fix 2017-09-10 03:01:19 -04:00
rocky
f017acce21 More semantic action cleanup 2017-09-10 02:56:47 -04:00
rocky
5bef5683e4 Match Python 3.4's terms a little names better 2017-09-10 00:48:54 -04:00
rocky
4e1467adc8 Revert last revert 2017-09-09 08:08:40 -04:00
rocky
7cdf0abb43 Revert last change 2017-09-09 08:03:04 -04:00
rocky
9b336251a7 New-style Python classes only, please. 2017-09-09 07:47:21 -04:00
rocky
7844456e1e Skeletal support for Python 3.7
Largely failing though.
2017-08-31 10:12:09 -04:00
55 changed files with 969 additions and 522 deletions

3
.gitignore vendored
View File

@@ -17,4 +17,5 @@
__pycache__
build
/.venv*
/.idea
/.idea
/.hypothesis

View File

@@ -1,3 +1,95 @@
2017-10-10 rocky <rb@dustyfeet.com>
* uncompyle6/parsers/parse24.py, uncompyle6/scanners/scanner3.py:
Misc bugs
2017-10-05 rocky <rb@dustyfeet.com>
* test/simple_source/branching/02_ifelse_lambda.py: One more test
2017-10-05 rocky <rb@dustyfeet.com>
* .gitignore, pytest/test_grammar.py, uncompyle6/parser.py,
uncompyle6/parsers/parse26.py, uncompyle6/parsers/parse27.py,
uncompyle6/parsers/parse3.py, uncompyle6/semantics/consts.py,
uncompyle6/semantics/pysource.py: Sync with master
2017-10-03 rocky <rb@dustyfeet.com>
* uncompyle6/parsers/parse2.py, uncompyle6/parsers/parse24.py,
uncompyle6/parsers/parse26.py: handle newer parser reduction
behavior
2017-10-03 rocky <rb@dustyfeet.com>
* uncompyle6/semantics/fragments.py,
uncompyle6/semantics/pysource.py: Go over table-semantics
description yet again
2017-10-02 rocky <rb@dustyfeet.com>
* uncompyle6/parsers/parse2.py, uncompyle6/parsers/parse3.py: Sync
with master
2017-09-26 rocky <rb@dustyfeet.com>
* uncompyle6/parsers/parse3.py: Annotation field can be unicode... When deparsing Python 3.x from Python 2.
2017-09-25 rocky <rb@dustyfeet.com>
* __pkginfo__.py: Require xdis 3.6.0 or greater
2017-09-25 rocky <rb@dustyfeet.com>
* : commit 0654aed6c823d0bb20abdc866481ca5950db72f7 Author: rocky
<rb@dustyfeet.com> Date: Thu Sep 21 11:29:17 2017 -0400
2017-09-21 rocky <rb@dustyfeet.com>
* pytest/test_pysource.py, uncompyle6/semantics/consts.py,
uncompyle6/semantics/fragments.py, uncompyle6/semantics/pysource.py:
Unit test for format-specifiers
2017-09-20 rocky <rb@dustyfeet.com>
* uncompyle6/semantics/fragments.py,
uncompyle6/semantics/pysource.py: Tidy pysource and fragments
2017-09-20 rocky <rb@dustyfeet.com>
* uncompyle6/semantics/consts.py: Tidy/regularize table entry
formatting
2017-09-20 rocky <rb@dustyfeet.com>
* test/test_pythonlib.py, uncompyle6/semantics/pysource.py: small
fixes... test_pythonlib.py: it is sys.exit not exit pysource.py: restore node
type on async_call function
2017-09-20 rocky <rb@dustyfeet.com>
* pytest/test_pysource.py, uncompyle6/semantics/pysource.py: Start
pysource unit test
2017-09-17 rocky <rb@dustyfeet.com>
* uncompyle6/semantics/fragments.py,
uncompyle6/semantics/pysource.py: emgine -> template_engine
2017-08-31 rocky <rb@dustyfeet.com>
* : commit 356ea6c7705a557cb3e725d1aca8589dd62b5cdf Author: rocky
<rb@dustyfeet.com> Date: Thu Aug 31 09:50:48 2017 -0400
2017-08-31 rocky <rb@dustyfeet.com>
* : commit 4d5843851543bfb3c97fc3c49036f1a971fc1d66 Author: rocky
<rb@dustyfeet.com> Date: Thu Aug 31 08:53:58 2017 -0400
2017-08-15 rocky <rb@dustyfeet.com>
* Makefile: 3.7 support
2017-08-15 rocky <rb@dustyfeet.com>
* : commit c54a47b15f85be50d2278aa79fd514eb08580e65 Author: rocky

18
NEWS
View File

@@ -1,3 +1,21 @@
uncompyle6 2.13.0 2017-10-10
- Fixes in deparsing lambda expressions
- Improve table-semantics descriptions
- Document hacky customize arg count better (until we can remove it)
- Update to use xdis 3.7.0 or greater
uncompyle6 2.12.0 2017-09-26
- Use xdis 3.6.0 or greater now
- Small semantic table cleanups
- Python 3.4's terms a little names better
- Slightly more Python 3.7, but still failing a lot
uncompyle6 2.11.5 2017-08-31
- Skeletal support for Python 3.7
uncompyle6 2.11.4 2017-08-15
* scanner and parser now allow 3-part version string lookups,

View File

@@ -4,7 +4,7 @@ uncompyle6
==========
A native Python cross-version Decompiler and Fragment Decompiler.
Follows in the tradition of decompyle, uncompyle, and uncompyle2.
The successor to decompyle, uncompyle, and uncompyle2.
Introduction

View File

@@ -39,8 +39,8 @@ entry_points = {
'pydisassemble=uncompyle6.bin.pydisassemble:main',
]}
ftp_url = None
install_requires = ['spark-parser >= 1.6.1, < 1.7.0',
'xdis >= 3.5.5, < 3.6.0']
install_requires = ['spark-parser >= 1.7.0, < 1.8.0',
'xdis >= 3.6.0, < 3.7.0']
license = 'MIT'
mailing_list = 'python-debugger@googlegroups.com'
modname = 'uncompyle6'

View File

@@ -11,15 +11,16 @@ def test_grammar():
remain_tokens = set([re.sub('_CONT$','', t) for t in remain_tokens])
remain_tokens = set(remain_tokens) - opcode_set
assert remain_tokens == set([]), \
"Remaining tokens %s\n====\n%s" % (remain_tokens, p.dumpGrammar())
"Remaining tokens %s\n====\n%s" % (remain_tokens, p.dump_grammar())
p = get_python_parser(PYTHON_VERSION, is_pypy=IS_PYPY)
lhs, rhs, tokens, right_recursive = p.checkSets()
lhs, rhs, tokens, right_recursive = p.check_sets()
expect_lhs = set(['expr1024', 'pos_arg'])
unused_rhs = set(['build_list', 'call_function', 'mkfunc',
'mklambda',
'unpack', 'unpack_list'])
expect_right_recursive = [['designList', ('designator', 'DUP_TOP', 'designList')]]
expect_right_recursive = frozenset([('designList',
('designator', 'DUP_TOP', 'designList'))])
if PYTHON3:
expect_lhs.add('load_genexpr')
@@ -39,13 +40,14 @@ def test_grammar():
s = get_scanner(PYTHON_VERSION, IS_PYPY)
ignore_set = set(
"""
JUMP_BACK CONTINUE RETURN_END_IF
JUMP_BACK CONTINUE
COME_FROM COME_FROM_EXCEPT
COME_FROM_EXCEPT_CLAUSE
COME_FROM_LOOP COME_FROM_WITH
COME_FROM_FINALLY ELSE
LOAD_GENEXPR LOAD_ASSERT LOAD_SETCOMP LOAD_DICTCOMP
LAMBDA_MARKER RETURN_LAST
LAMBDA_MARKER
RETURN_END_IF RETURN_END_IF_LAMBDA RETURN_VALUE_LAMBDA RETURN_LAST
""".split())
if 2.6 <= PYTHON_VERSION <= 2.7:
opcode_set = set(s.opc.opname).union(ignore_set)

164
pytest/test_pysource.py Normal file
View File

@@ -0,0 +1,164 @@
from uncompyle6 import PYTHON3
from uncompyle6.semantics.consts import (
escape, NONE,
# RETURN_NONE, PASS, RETURN_LOCALS
)
if PYTHON3:
from io import StringIO
else:
from StringIO import StringIO
from uncompyle6.semantics.pysource import SourceWalker as SourceWalker
def test_template_engine():
s = StringIO()
sw = SourceWalker(2.7, s, None)
sw.ast = NONE
sw.template_engine(('--%c--', 0), NONE)
print(sw.f.getvalue())
assert sw.f.getvalue() == '--None--'
# FIXME: and so on...
from uncompyle6.semantics.consts import (
TABLE_R, TABLE_DIRECT,
)
from uncompyle6.semantics.fragments import (
TABLE_DIRECT_FRAGMENT,
)
skip_for_now = "DELETE_DEREF".split()
def test_tables():
for t, name, fragment in (
(TABLE_DIRECT, 'TABLE_DIRECT', False),
(TABLE_R, 'TABLE_R', False),
(TABLE_DIRECT_FRAGMENT, 'TABLE_DIRECT_FRAGMENT', True)):
for k, entry in t.iteritems():
if k in skip_for_now:
continue
fmt = entry[0]
arg = 1
i = 0
m = escape.search(fmt)
print("%s[%s]" % (name, k))
while m:
i = m.end()
typ = m.group('type') or '{'
if typ in frozenset(['%', '+', '-', '|', ',', '{']):
# No args
pass
elif typ in frozenset(['c', 'p', 'P', 'C', 'D']):
# One arg - should be int or tuple of int
if typ == 'c':
assert isinstance(entry[arg], int), (
"%s[%s][%d] type %s is '%s' should be an int but is %s. "
"Full entry: %s" %
(name, k, arg, typ, entry[arg], type(entry[arg]), entry)
)
elif typ in frozenset(['C', 'D']):
tup = entry[arg]
assert isinstance(tup, tuple), (
"%s[%s][%d] type %s is %s should be an tuple but is %s. "
"Full entry: %s" %
(name, k, arg, typ, entry[arg], type(entry[arg]), entry)
)
assert len(tup) == 3
for j, x in enumerate(tup[:-1]):
assert isinstance(x, int), (
"%s[%s][%d][%d] type %s is %s should be an tuple but is %s. "
"Full entry: %s" %
(name, k, arg, j, typ, x, type(x), entry)
)
assert isinstance(tup[-1], str) or tup[-1] is None, (
"%s[%s][%d][%d] sep type %s is %s should be an string but is %s. "
"Full entry: %s" %
(name, k, arg, j, typ, tup[-1], type(x), entry)
)
elif typ == 'P':
tup = entry[arg]
assert isinstance(tup, tuple), (
"%s[%s][%d] type %s is %s should be an tuple but is %s. "
"Full entry: %s" %
(name, k, arg, typ, entry[arg], type(entry[arg]), entry)
)
assert len(tup) == 4
for j, x in enumerate(tup[:-2]):
assert isinstance(x, int), (
"%s[%s][%d][%d] type %s is '%s' should be an tuple but is %s. "
"Full entry: %s" %
(name, k, arg, j, typ, x, type(x), entry)
)
assert isinstance(tup[-2], str), (
"%s[%s][%d][%d] sep type %s is '%s' should be an string but is %s. "
"Full entry: %s" %
(name, k, arg, j, typ, x, type(x), entry)
)
assert isinstance(tup[1], int), (
"%s[%s][%d][%d] prec type %s is '%s' should be an int but is %s. "
"Full entry: %s" %
(name, k, arg, j, typ, x, type(x), entry)
)
else:
# Should be a tuple which contains only ints
tup = entry[arg]
assert isinstance(tup, tuple), (
"%s[%s][%d] type %s is '%s' should be an tuple but is %s. "
"Full entry: %s" %
(name, k, arg, typ, entry[arg], type(entry[arg]), entry)
)
assert len(tup) == 2
for j, x in enumerate(tup):
assert isinstance(x, int), (
"%s[%s][%d][%d] type '%s' is '%s should be an int but is %s. Full entry: %s" %
(name, k, arg, j, typ, x, type(x), entry)
)
pass
arg += 1
elif typ in frozenset(['r']) and fragment:
pass
elif typ == 'b' and fragment:
assert isinstance(entry[arg], int), (
"%s[%s][%d] type %s is '%s' should be an int but is %s. "
"Full entry: %s" %
(name, k, arg, typ, entry[arg], type(entry[arg]), entry)
)
arg += 1
elif typ == 'x' and fragment:
tup = entry[arg]
assert isinstance(tup, tuple), (
"%s[%s][%d] type %s is '%s' should be an tuple but is %s. "
"Full entry: %s" %
(name, k, arg, typ, entry[arg], type(entry[arg]), entry)
)
assert len(tup) == 2
assert isinstance(tup[0], int), (
"%s[%s][%d] source type %s is '%s' should be an int but is %s. "
"Full entry: %s" %
(name, k, arg, typ, entry[arg], type(entry[arg]), entry)
)
assert isinstance(tup[1], tuple), (
"%s[%s][%d] dest type %s is '%s' should be an tuple but is %s. "
"Full entry: %s" %
(name, k, arg, typ, entry[arg], type(entry[arg]), entry)
)
for j, x in enumerate(tup[1]):
assert isinstance(x, int), (
"%s[%s][%d][%d] type %s is %s should be an int but is %s. Full entry: %s" %
(name, k, arg, j, typ, x, type(x), entry)
)
arg += 1
pass
else:
assert False, (
"%s[%s][%d] type %s is not known. Full entry: %s" %
(name, k, arg, typ, entry)
)
m = escape.search(fmt, i)
pass
assert arg == len(entry), (
"%s[%s] arg %d should be length of entry %d. Full entry: %s" %
(name, k, arg, len(entry), entry))

View File

@@ -39,7 +39,7 @@ check-3.3: check-bytecode
#: Run working tests from Python 3.4
check-3.4: check-bytecode check-3.4-ok check-2.7-ok
$(PYTHON) test_pythonlib.py --bytecode-3.4 --verify $(COMPILE)
$(PYTHON) test_pythonlib.py --bytecode-3.4 --weak-verify $(COMPILE)
#: Run working tests from Python 3.5
check-3.5: check-bytecode

View File

@@ -0,0 +1,5 @@
# We have to do contortions here because
# lambda's have to be more or less on a line
f = lambda x: 1 if x<2 else 3
f(5)

View File

@@ -169,13 +169,13 @@ def do_tests(src_dir, obj_patterns, target_dir, opts):
main(src_dir, target_dir, files, [],
do_verify=opts['do_verify'])
if failed_files != 0:
exit(2)
sys.exit(2)
elif failed_verify != 0:
exit(3)
sys.exit(3)
except (KeyboardInterrupt, OSError):
print()
exit(1)
sys.exit(1)
if test_opts['rmtree']:
parent_dir = os.path.dirname(target_dir)
print("Everything good, removing %s" % parent_dir)

View File

@@ -42,21 +42,25 @@ class PythonParser(GenericASTBuilder):
else:
return self.ast_first_offset(ast[0])
def add_unique_rule(self, rule, opname, count, customize):
def add_unique_rule(self, rule, opname, arg_count, customize):
"""Add rule to grammar, but only if it hasn't been added previously
opname and count are used in the customize() semantic the actions
to add the semantic action rule. Often, count is not used.
opname and stack_count are used in the customize() semantic
the actions to add the semantic action rule. Stack_count is
used in custom opcodes like MAKE_FUNCTION to indicate how
many arguments it has. Often it is not used.
"""
if rule not in self.new_rules:
# print("XXX ", rule) # debug
self.new_rules.add(rule)
self.addRule(rule, nop_func)
customize[opname] = count
customize[opname] = arg_count
pass
return
def add_unique_rules(self, rules, customize):
"""Add rules (a list of string) to grammar
"""Add rules (a list of string) to grammar. Note that
the rules must not be those that set arg_count in the
custom dictionary.
"""
for rule in rules:
if len(rule) == 0:
@@ -66,7 +70,9 @@ class PythonParser(GenericASTBuilder):
return
def add_unique_doc_rules(self, rules_str, customize):
"""Add rules (a docstring-like list of rules) to grammar
"""Add rules (a docstring-like list of rules) to grammar.
Note that the rules must not be those that set arg_count in the
custom dictionary.
"""
rules = [r.strip() for r in rules_str.split("\n")]
self.add_unique_rules(rules, customize)
@@ -83,17 +89,14 @@ class PythonParser(GenericASTBuilder):
for i in dir(self):
setattr(self, i, None)
def debug_reduce(self, rule, tokens, parent, i):
def debug_reduce(self, rule, tokens, parent, last_token_pos):
"""Customized format and print for our kind of tokens
which gets called in debugging grammar reduce rules
"""
def fix(c):
s = str(c)
i = s.find('_')
if i == -1:
return s
else:
return s[:i]
last_token_pos = s.find('_')
return s if last_token_pos == -1 else s[:last_token_pos]
prefix = ''
if parent and tokens:
@@ -105,13 +108,13 @@ class PythonParser(GenericASTBuilder):
if hasattr(p_token, 'offset'):
prefix += "%3s" % fix(p_token.offset)
if len(rule[1]) > 1:
prefix += '-%-3s ' % fix(tokens[i-1].offset)
prefix += '-%-3s ' % fix(tokens[last_token_pos-1].offset)
else:
prefix += ' '
else:
prefix = ' '
print("%s%s ::= %s" % (prefix, rule[0], ' '.join(rule[1])))
print("%s%s ::= %s (%d)" % (prefix, rule[0], ' '.join(rule[1]), last_token_pos))
def error(self, instructions, index):
# Find the last line boundary
@@ -132,7 +135,7 @@ class PythonParser(GenericASTBuilder):
raise ParserError(err_token, err_token.offset)
def typestring(self, token):
return token.type
return token.kind
def nonterminal(self, nt, args):
if nt in self.collect and len(args) > 1:
@@ -254,8 +257,11 @@ class PythonParser(GenericASTBuilder):
stmt ::= return_stmt
return_stmt ::= ret_expr RETURN_VALUE
return_stmt_lambda ::= ret_expr RETURN_VALUE_LAMBDA
return_stmts ::= return_stmt
return_stmts ::= _stmts return_stmt
"""
pass
@@ -530,7 +536,9 @@ class PythonParser(GenericASTBuilder):
stmt ::= return_lambda
stmt ::= conditional_lambda
return_lambda ::= ret_expr RETURN_VALUE LAMBDA_MARKER
return_lambda ::= ret_expr RETURN_VALUE_LAMBDA LAMBDA_MARKER
return_lambda ::= ret_expr RETURN_VALUE_LAMBDA
conditional_lambda ::= expr jmp_false return_if_stmt return_stmt LAMBDA_MARKER
cmp ::= cmp_list
@@ -726,7 +734,7 @@ def get_python_parser(
else:
p = parse3.Python3ParserSingle(debug_parser)
p.version = version
# p.dumpGrammar() # debug
# p.dump_grammar() # debug
return p
class PythonParserSingle(PythonParser):

View File

@@ -29,8 +29,8 @@ class Python15ParserSingle(Python21Parser, PythonParserSingle):
if __name__ == '__main__':
# Check grammar
p = Python15Parser()
p.checkGrammar()
p.dumpGrammar()
p.check_grammar()
p.dump_grammar()
# local variables:
# tab-width: 4

View File

@@ -395,6 +395,8 @@ class Python2Parser(PythonParser):
return
def reduce_is_invalid(self, rule, ast, tokens, first, last):
if tokens is None:
return False
lhs = rule[0]
if lhs in ('augassign1', 'augassign2') and ast[0][0] == 'and':
return True
@@ -415,4 +417,4 @@ class Python2ParserSingle(Python2Parser, PythonParserSingle):
if __name__ == '__main__':
# Check grammar
p = Python2Parser()
p.checkGrammar()
p.check_grammar()

View File

@@ -33,8 +33,8 @@ class Python21ParserSingle(Python22Parser, PythonParserSingle):
if __name__ == '__main__':
# Check grammar
p = Python21Parser()
p.checkGrammar()
p.dumpGrammar()
p.check_grammar()
p.dump_grammar()
# local variables:
# tab-width: 4

View File

@@ -26,8 +26,8 @@ class Python22ParserSingle(Python23Parser, PythonParserSingle):
if __name__ == '__main__':
# Check grammar
p = Python22Parser()
p.checkGrammar()
p.dumpGrammar()
p.check_grammar()
p.dump_grammar()
# local variables:
# tab-width: 4

View File

@@ -67,8 +67,8 @@ class Python23ParserSingle(Python23Parser, PythonParserSingle):
if __name__ == '__main__':
# Check grammar
p = Python23Parser()
p.checkGrammar()
p.dumpGrammar()
p.check_grammar()
p.dump_grammar()
# local variables:
# tab-width: 4

View File

@@ -55,13 +55,14 @@ class Python24Parser(Python25Parser):
invalid = super(Python24Parser,
self).reduce_is_invalid(rule, ast,
tokens, first, last)
if invalid:
if invalid or tokens is None:
return invalid
# FiXME: this code never gets called...
lhs = rule[0]
if lhs == 'nop_stmt':
return not int(tokens[first].pattr) == tokens[last].offset
l = len(tokens)
if 0 <= l < len(tokens):
return not int(tokens[first].pattr) == tokens[last].offset
return False
@@ -71,4 +72,4 @@ class Python24ParserSingle(Python24Parser, PythonParserSingle):
if __name__ == '__main__':
# Check grammar
p = Python24Parser()
p.checkGrammar()
p.check_grammar()

View File

@@ -60,4 +60,4 @@ class Python25ParserSingle(Python26Parser, PythonParserSingle):
if __name__ == '__main__':
# Check grammar
p = Python25Parser()
p.checkGrammar()
p.check_grammar()

View File

@@ -247,7 +247,9 @@ class Python26Parser(Python2Parser):
and ::= expr JUMP_IF_FALSE POP_TOP expr JUMP_IF_FALSE POP_TOP
cmp_list ::= expr cmp_list1 ROT_TWO COME_FROM POP_TOP _come_from
conditional_lambda ::= expr jmp_false_then return_if_stmt return_stmt LAMBDA_MARKER
return_if_lambda ::= RETURN_END_IF_LAMBDA POP_TOP
conditional_lambda ::= expr jmp_false_then expr return_if_lambda
return_stmt_lambda LAMBDA_MARKER
"""
def add_custom_rules(self, tokens, customize):
@@ -258,7 +260,7 @@ class Python26Parser(Python2Parser):
invalid = super(Python26Parser,
self).reduce_is_invalid(rule, ast,
tokens, first, last)
if invalid:
if invalid or tokens is None:
return invalid
if rule == ('and', ('expr', 'jmp_false', 'expr', '\\e_come_from_opt')):
# Test that jmp_false jumps to the end of "and"
@@ -274,10 +276,10 @@ class Python26ParserSingle(Python2Parser, PythonParserSingle):
if __name__ == '__main__':
# Check grammar
p = Python26Parser()
p.checkGrammar()
p.check_grammar()
from uncompyle6 import PYTHON_VERSION, IS_PYPY
if PYTHON_VERSION == 2.6:
lhs, rhs, tokens, right_recursive = p.checkSets()
lhs, rhs, tokens, right_recursive = p.check_sets()
from uncompyle6.scanner import get_scanner
s = get_scanner(PYTHON_VERSION, IS_PYPY)
opcode_set = set(s.opc.opname).union(set(

View File

@@ -94,6 +94,10 @@ class Python27Parser(Python2Parser):
WITH_CLEANUP END_FINALLY
# Common with 2.6
return_if_lambda ::= RETURN_END_IF_LAMBDA COME_FROM
conditional_lambda ::= expr jmp_false expr return_if_lambda
return_stmt_lambda LAMBDA_MARKER
while1stmt ::= SETUP_LOOP return_stmts bp_come_from
while1stmt ::= SETUP_LOOP return_stmts COME_FROM
"""
@@ -125,10 +129,10 @@ class Python27ParserSingle(Python27Parser, PythonParserSingle):
if __name__ == '__main__':
# Check grammar
p = Python27Parser()
p.checkGrammar()
p.check_grammar()
from uncompyle6 import PYTHON_VERSION, IS_PYPY
if PYTHON_VERSION == 2.7:
lhs, rhs, tokens, right_recursive = p.checkSets()
lhs, rhs, tokens, right_recursive = p.check_sets()
from uncompyle6.scanner import get_scanner
s = get_scanner(PYTHON_VERSION, IS_PYPY)
opcode_set = set(s.opc.opname).union(set(
@@ -144,4 +148,5 @@ if __name__ == '__main__':
for t in remain_tokens])
remain_tokens = set(remain_tokens) - opcode_set
print(remain_tokens)
# p.dumpGrammar()
p.check_grammar()
p.dump_grammar()

View File

@@ -18,6 +18,7 @@ that a later phase can turn into a sequence of ASCII text.
from uncompyle6.parser import PythonParser, PythonParserSingle, nop_func
from uncompyle6.parsers.astnode import AST
from spark_parser import DEFAULT_DEBUG as PARSER_DEFAULT_DEBUG
from xdis import PYTHON3
class Python3Parser(PythonParser):
@@ -415,6 +416,13 @@ class Python3Parser(PythonParser):
# a JUMP_ABSOLUTE with no COME_FROM
conditional ::= expr jmp_false expr jump_absolute_else expr
return_if_lambda ::= RETURN_END_IF_LAMBDA
conditional_lambda ::= expr jmp_false return_stmt_lambda
return_stmt_lambda LAMBDA_MARKER
conditional_lambda ::= expr jmp_false expr return_if_lambda
return_stmt_lambda LAMBDA_MARKER
expr ::= LOAD_CLASSNAME
# Python 3.4+
@@ -425,7 +433,7 @@ class Python3Parser(PythonParser):
@staticmethod
def call_fn_name(token):
"""Customize CALL_FUNCTION to add the number of positional arguments"""
return '%s_%i' % (token.type, token.attr)
return '%s_%i' % (token.kind, token.attr)
def custom_build_class_rule(self, opname, i, token, tokens, customize):
'''
@@ -441,16 +449,16 @@ class Python3Parser(PythonParser):
# FIXME: I bet this can be simplified
# look for next MAKE_FUNCTION
for i in range(i+1, len(tokens)):
if tokens[i].type.startswith('MAKE_FUNCTION'):
if tokens[i].kind.startswith('MAKE_FUNCTION'):
break
elif tokens[i].type.startswith('MAKE_CLOSURE'):
elif tokens[i].kind.startswith('MAKE_CLOSURE'):
break
pass
assert i < len(tokens), "build_class needs to find MAKE_FUNCTION or MAKE_CLOSURE"
assert tokens[i+1].type == 'LOAD_CONST', \
assert tokens[i+1].kind == 'LOAD_CONST', \
"build_class expecting CONST after MAKE_FUNCTION/MAKE_CLOSURE"
for i in range(i, len(tokens)):
if tokens[i].type == 'CALL_FUNCTION':
if tokens[i].kind == 'CALL_FUNCTION':
call_fn_tok = tokens[i]
break
assert call_fn_tok, "build_class custom rule needs to find CALL_FUNCTION"
@@ -491,7 +499,7 @@ class Python3Parser(PythonParser):
# Yes, this computation based on instruction name is a little bit hoaky.
nak = ( len(opname)-len('CALL_FUNCTION') ) // 3
token.type = self.call_fn_name(token)
token.kind = self.call_fn_name(token)
uniq_param = args_kw + args_pos
if self.version == 3.5 and opname.startswith('CALL_FUNCTION_VAR'):
# Python 3.5 changes the stack position of *args. KW args come
@@ -503,33 +511,33 @@ class Python3Parser(PythonParser):
kw = ''
rule = ('call_function ::= expr expr ' +
('pos_arg ' * args_pos) +
('kwarg ' * args_kw) + kw + token.type)
self.add_unique_rule(rule, token.type, uniq_param, customize)
('kwarg ' * args_kw) + kw + token.kind)
self.add_unique_rule(rule, token.kind, uniq_param, customize)
if self.version >= 3.6 and opname == 'CALL_FUNCTION_EX_KW':
rule = ('call_function36 ::= '
'expr build_tuple_unpack_with_call build_map_unpack_with_call '
'CALL_FUNCTION_EX_KW_1')
self.add_unique_rule(rule, token.type, uniq_param, customize)
self.add_unique_rule(rule, token.kind, uniq_param, customize)
rule = 'call_function ::= call_function36'
else:
rule = ('call_function ::= expr ' +
('pos_arg ' * args_pos) +
('kwarg ' * args_kw) +
'expr ' * nak + token.type)
'expr ' * nak + token.kind)
self.add_unique_rule(rule, token.type, uniq_param, customize)
self.add_unique_rule(rule, token.kind, uniq_param, customize)
if self.version >= 3.5:
rule = ('async_call_function ::= expr ' +
('pos_arg ' * args_pos) +
('kwarg ' * args_kw) +
'expr ' * nak + token.type +
'expr ' * nak + token.kind +
' GET_AWAITABLE LOAD_CONST YIELD_FROM')
self.add_unique_rule(rule, token.type, uniq_param, customize)
self.add_unique_rule('expr ::= async_call_function', token.type, uniq_param, customize)
self.add_unique_rule(rule, token.kind, uniq_param, customize)
self.add_unique_rule('expr ::= async_call_function', token.kind, uniq_param, customize)
rule = ('classdefdeco2 ::= LOAD_BUILD_CLASS mkfunc %s%s_%d'
% (('expr ' * (args_pos-1)), opname, args_pos))
self.add_unique_rule(rule, token.type, uniq_param, customize)
self.add_unique_rule(rule, token.kind, uniq_param, customize)
def add_make_function_rule(self, rule, opname, attr, customize):
"""Python 3.3 added a an addtional LOAD_CONST before MAKE_FUNCTION and
@@ -606,7 +614,7 @@ class Python3Parser(PythonParser):
call_function ::= expr CALL_METHOD
"""
for i, token in enumerate(tokens):
opname = token.type
opname = token.kind
opname_base = opname[:opname.rfind('_')]
if opname == 'PyPy':
@@ -890,8 +898,11 @@ class Python3Parser(PythonParser):
elif lhs == 'annotate_tuple':
return not isinstance(tokens[first].attr, tuple)
elif lhs == 'kwarg':
return not (isinstance(tokens[first].attr, unicode) or
isinstance(tokens[first].attr, str))
arg = tokens[first].attr
if PYTHON3:
return not isinstance(arg, str)
else:
return not (isinstance(arg, str) or isinstance(arg, unicode))
elif lhs == 'while1elsestmt':
# if SETUP_LOOP target spans the else part, then this is
# not while1else. Also do for whileTrue?
@@ -900,7 +911,8 @@ class Python3Parser(PythonParser):
last += 1
return tokens[first].attr == tokens[last].offset
elif lhs == 'while1stmt':
if tokens[last] in ('COME_FROM_LOOP', 'JUMP_BACK'):
if (0 <= last < len(tokens)
and tokens[last] in ('COME_FROM_LOOP', 'JUMP_BACK')):
# jump_back should be right afer SETUP_LOOP. Test?
last += 1
while last < len(tokens) and isinstance(tokens[last].offset, str):
@@ -944,10 +956,10 @@ def info(args):
p = Python32Parser()
elif arg == '3.0':
p = Python30Parser()
p.checkGrammar()
p.check_grammar()
if len(sys.argv) > 1 and sys.argv[1] == 'dump':
print('-' * 50)
p.dumpGrammar()
p.dump_grammar()
if __name__ == '__main__':
import sys

View File

@@ -42,7 +42,7 @@ class Python32Parser(Python3Parser):
def add_custom_rules(self, tokens, customize):
super(Python32Parser, self).add_custom_rules(tokens, customize)
for i, token in enumerate(tokens):
opname = token.type
opname = token.kind
if opname.startswith('MAKE_FUNCTION_A'):
args_pos, args_kw, annotate_args = token.attr
# Check that there are 2 annotated params?

View File

@@ -29,10 +29,10 @@ class Python34ParserSingle(Python34Parser, PythonParserSingle):
if __name__ == '__main__':
# Check grammar
p = Python34Parser()
p.checkGrammar()
p.check_grammar()
from uncompyle6 import PYTHON_VERSION, IS_PYPY
if PYTHON_VERSION == 3.4:
lhs, rhs, tokens, right_recursive = p.checkSets()
lhs, rhs, tokens, right_recursive = p.check_sets()
from uncompyle6.scanner import get_scanner
s = get_scanner(PYTHON_VERSION, IS_PYPY)
opcode_set = set(s.opc.opname).union(set(

View File

@@ -142,7 +142,7 @@ class Python35Parser(Python34Parser):
def add_custom_rules(self, tokens, customize):
super(Python35Parser, self).add_custom_rules(tokens, customize)
for i, token in enumerate(tokens):
opname = token.type
opname = token.kind
if opname == 'BUILD_MAP_UNPACK_WITH_CALL':
nargs = token.attr % 256
map_unpack_n = "map_unpack_%s" % nargs
@@ -152,7 +152,7 @@ class Python35Parser(Python34Parser):
self.add_unique_rule(rule, opname, token.attr, customize)
call_token = tokens[i+1]
if self.version == 3.5:
rule = 'call_function ::= expr unmapexpr ' + call_token.type
rule = 'call_function ::= expr unmapexpr ' + call_token.kind
self.add_unique_rule(rule, opname, token.attr, customize)
pass
pass
@@ -164,10 +164,10 @@ class Python35ParserSingle(Python35Parser, PythonParserSingle):
if __name__ == '__main__':
# Check grammar
p = Python35Parser()
p.checkGrammar()
p.check_grammar()
from uncompyle6 import PYTHON_VERSION, IS_PYPY
if PYTHON_VERSION == 3.5:
lhs, rhs, tokens, right_recursive = p.checkSets()
lhs, rhs, tokens, right_recursive = p.check_sets()
from uncompyle6.scanner import get_scanner
s = get_scanner(PYTHON_VERSION, IS_PYPY)
opcode_set = set(s.opc.opname).union(set(

View File

@@ -36,7 +36,7 @@ class Python36Parser(Python35Parser):
def add_custom_rules(self, tokens, customize):
super(Python36Parser, self).add_custom_rules(tokens, customize)
for i, token in enumerate(tokens):
opname = token.type
opname = token.kind
if opname == 'FORMAT_VALUE':
rules_str = """
@@ -64,10 +64,10 @@ class Python36Parser(Python35Parser):
if opname.startswith('CALL_FUNCTION_KW'):
values = 'expr ' * token.attr
rule = 'call_function ::= expr kwargs_only_36 {token.type}'.format(**locals())
self.add_unique_rule(rule, token.type, token.attr, customize)
rule = 'call_function ::= expr kwargs_only_36 {token.kind}'.format(**locals())
self.add_unique_rule(rule, token.kind, token.attr, customize)
rule = 'kwargs_only_36 ::= {values} LOAD_CONST'.format(**locals())
self.add_unique_rule(rule, token.type, token.attr, customize)
self.add_unique_rule(rule, token.kind, token.attr, customize)
else:
super(Python36Parser, self).custom_classfunc_rule(opname, token, customize)
@@ -78,10 +78,10 @@ class Python36ParserSingle(Python36Parser, PythonParserSingle):
if __name__ == '__main__':
# Check grammar
p = Python36Parser()
p.checkGrammar()
p.check_grammar()
from uncompyle6 import PYTHON_VERSION, IS_PYPY
if PYTHON_VERSION == 3.6:
lhs, rhs, tokens, right_recursive = p.checkSets()
lhs, rhs, tokens, right_recursive = p.check_sets()
from uncompyle6.scanner import get_scanner
s = get_scanner(PYTHON_VERSION, IS_PYPY)
opcode_set = set(s.opc.opname).union(set(

View File

@@ -21,10 +21,10 @@ class Python37ParserSingle(Python37Parser, PythonParserSingle):
if __name__ == '__main__':
# Check grammar
p = Python37Parser()
p.checkGrammar()
p.check_grammar()
from uncompyle6 import PYTHON_VERSION, IS_PYPY
if PYTHON_VERSION == 3.7:
lhs, rhs, tokens, right_recursive = p.checkSets()
lhs, rhs, tokens, right_recursive = p.check_sets()
from uncompyle6.scanner import get_scanner
s = get_scanner(PYTHON_VERSION, IS_PYPY)
opcode_set = set(s.opc.opname).union(set(

View File

@@ -20,7 +20,7 @@ from xdis.magics import py_str2float
# The byte code versions we support
PYTHON_VERSIONS = (1.5,
2.1, 2.2, 2.3, 2.4, 2.5, 2.6, 2.7,
3.0, 3.1, 3.2, 3.3, 3.4, 3.5, 3.6)
3.0, 3.1, 3.2, 3.3, 3.4, 3.5, 3.6, 3.7)
# FIXME: DRY
if PYTHON3:
@@ -54,7 +54,7 @@ class Scanner(object):
if version in PYTHON_VERSIONS:
if is_pypy:
v_str = "opcode_pypy%s" % (int(version * 10))
v_str = "opcode_%spypy" % (int(version * 10))
else:
v_str = "opcode_%s" % (int(version * 10))
exec("from xdis.opcodes import %s" % v_str)
@@ -63,6 +63,7 @@ class Scanner(object):
raise TypeError("%s is not a Python version I know about" % version)
self.opname = self.opc.opname
# FIXME: This weird Python2 behavior is not Python3
self.resetTokenClass()
@@ -99,7 +100,7 @@ class Scanner(object):
def print_bytecode(self):
for i in self.op_range(0, len(self.code)):
op = self.code[i]
if op in self.JUMP_OPs:
if op in self.JUMP_OPS:
dest = self.get_target(i, op)
print('%i\t%s\t%i' % (i, self.opname[op], dest))
else:

View File

@@ -1,4 +1,4 @@
# Copyright (c) 2016 by Rocky Bernstein
# Copyright (c) 2016-2017 by Rocky Bernstein
"""
Python PyPy 2.7 bytecode scanner/deparser
@@ -10,8 +10,8 @@ information for later use in deparsing.
import uncompyle6.scanners.scanner27 as scan
# bytecode verification, verify(), uses JUMP_OPs from here
from xdis.opcodes import opcode_pypy27
JUMP_OPs = opcode_pypy27.JUMP_OPs
from xdis.opcodes import opcode_27pypy
JUMP_OPS = opcode_27pypy.JUMP_OPS
# We base this off of 2.6 instead of the other way around
# because we cleaned things up this way.

View File

@@ -8,9 +8,9 @@ make things easier for decompilation.
import uncompyle6.scanners.scanner35 as scan
# bytecode verification, verify(), uses JUMP_OPs from here
# bytecode verification, verify(), uses JUMP_OPS from here
from xdis.opcodes import opcode_35 as opc # is this right?
JUMP_OPs = map(lambda op: opc.opname[op], opc.hasjrel + opc.hasjabs)
JUMP_OPs = opc.JUMP_OPS
# We base this off of 3.5
class ScannerPyPy35(scan.Scanner35):

View File

@@ -11,7 +11,7 @@ import uncompyle6.scanners.scanner21 as scan
# bytecode verification, verify(), uses JUMP_OPs from here
from xdis.opcodes import opcode_15
JUMP_OPs = opcode_15.JUMP_OPs
JUMP_OPS = opcode_15.JUMP_OPS
# We base this off of 2.1 instead of the other way around
# because we cleaned things up this way.

View File

@@ -99,12 +99,18 @@ class Scanner2(Scanner):
for instr in bytecode.get_instructions(co):
print(instr._disassemble())
# Container for tokens
# list of tokens/instructions
tokens = []
# "customize" is a dict whose keys are nonterminals
# and the value is the argument stack entries for that
# nonterminal. The count is a little hoaky. It is mostly
# not used, but sometimes it is.
# "customize" is a dict whose keys are nonterminals
customize = {}
if self.is_pypy:
customize['PyPy'] = 1
customize['PyPy'] = 0
Token = self.Token # shortcut

View File

@@ -1,4 +1,4 @@
# Copyright (c) 2016 by Rocky Bernstein
# Copyright (c) 2016-2017 by Rocky Bernstein
"""
Python 2.1 bytecode scanner/deparser
@@ -11,7 +11,7 @@ import uncompyle6.scanners.scanner22 as scan
# bytecode verification, verify(), uses JUMP_OPs from here
from xdis.opcodes import opcode_21
JUMP_OPs = opcode_21.JUMP_OPs
JUMP_OPS = opcode_21.JUMP_OPS
# We base this off of 2.2 instead of the other way around
# because we cleaned things up this way.

View File

@@ -1,4 +1,4 @@
# Copyright (c) 2016 by Rocky Bernstein
# Copyright (c) 2016-2017 by Rocky Bernstein
"""
Python 2.2 bytecode ingester.
@@ -11,7 +11,7 @@ import uncompyle6.scanners.scanner23 as scan
# bytecode verification, verify(), uses JUMP_OPs from here
from xdis.opcodes import opcode_22
JUMP_OPs = opcode_22.JUMP_OPs
JUMP_OPS = opcode_22.JUMP_OPS
# We base this off of 2.3 instead of the other way around
# because we cleaned things up this way.
@@ -30,5 +30,5 @@ class Scanner22(scan.Scanner23):
def ingest22(self, co, classname=None, code_objects={}, show_asm=None):
tokens, customize = self.parent_ingest(co, classname, code_objects, show_asm)
tokens = [t for t in tokens if t.type != 'SET_LINENO']
tokens = [t for t in tokens if t.kind != 'SET_LINENO']
return tokens, customize

View File

@@ -1,4 +1,4 @@
# Copyright (c) 2016 by Rocky Bernstein
# Copyright (c) 2016-2017 by Rocky Bernstein
"""
Python 2.3 bytecode scanner/deparser
@@ -10,7 +10,7 @@ import uncompyle6.scanners.scanner24 as scan
# bytecode verification, verify(), uses JUMP_OPs from here
from xdis.opcodes import opcode_23
JUMP_OPs = opcode_23.JUMP_OPs
JUMP_OPS = opcode_23.JUMP_OPS
# We base this off of 2.4 instead of the other way around
# because we cleaned things up this way.

View File

@@ -1,4 +1,4 @@
# Copyright (c) 2016 by Rocky Bernstein
# Copyright (c) 2016-2017 by Rocky Bernstein
"""
Python 2.4 bytecode scanner/deparser
@@ -10,7 +10,7 @@ import uncompyle6.scanners.scanner25 as scan
# bytecode verification, verify(), uses JUMP_OPs from here
from xdis.opcodes import opcode_24
JUMP_OPs = opcode_24.JUMP_OPs
JUMP_OPS = opcode_24.JUMP_OPS
# We base this off of 2.5 instead of the other way around
# because we cleaned things up this way.

View File

@@ -1,4 +1,4 @@
# Copyright (c) 2015-2016 by Rocky Bernstein
# Copyright (c) 2015-2017 by Rocky Bernstein
"""
Python 2.5 bytecode scanner/deparser
@@ -11,7 +11,7 @@ import uncompyle6.scanners.scanner26 as scan
# bytecode verification, verify(), uses JUMP_OPs from here
from xdis.opcodes import opcode_25
JUMP_OPs = opcode_25.JUMP_OPs
JUMP_OPS = opcode_25.JUMP_OPS
# We base this off of 2.6 instead of the other way around
# because we cleaned things up this way.

View File

@@ -19,7 +19,7 @@ from uncompyle6.scanner import L65536
# bytecode verification, verify(), uses JUMP_OPs from here
from xdis.opcodes import opcode_26
JUMP_OPs = opcode_26.JUMP_OPs
JUMP_OPS = opcode_26.JUMP_OPS
class Scanner26(scan.Scanner2):
def __init__(self, show_asm=False):
@@ -217,8 +217,8 @@ class Scanner26(scan.Scanner2):
# FIXME: this is a hack to catch stuff like:
# if x: continue
# the "continue" is not on a new line.
if len(tokens) and tokens[-1].type == 'JUMP_BACK':
tokens[-1].type = intern('CONTINUE')
if len(tokens) and tokens[-1].kind == 'JUMP_BACK':
tokens[-1].kind = intern('CONTINUE')
elif op in self.opc.JABS_OPS:
pattr = repr(oparg)
@@ -258,18 +258,18 @@ class Scanner26(scan.Scanner2):
and self.code[offset+3] not in (self.opc.END_FINALLY,
self.opc.POP_BLOCK)):
if ((offset in self.linestartoffsets and
tokens[-1].type == 'JUMP_BACK')
tokens[-1].kind == 'JUMP_BACK')
or offset not in self.not_continue):
op_name = 'CONTINUE'
else:
# FIXME: this is a hack to catch stuff like:
# if x: continue
# the "continue" is not on a new line.
if tokens[-1].type == 'JUMP_BACK':
if tokens[-1].kind == 'JUMP_BACK':
# We need 'intern' since we have
# already have processed the previous
# token.
tokens[-1].type = intern('CONTINUE')
tokens[-1].kind = intern('CONTINUE')
elif op == self.opc.LOAD_GLOBAL:
if offset in self.load_asserts:

View File

@@ -16,7 +16,7 @@ if PYTHON3:
# bytecode verification, verify(), uses JUMP_OPs from here
from xdis.opcodes import opcode_27
JUMP_OPs = opcode_27.JUMP_OPs
JUMP_OPS = opcode_27.JUMP_OPs
class Scanner27(Scanner2):
def __init__(self, show_asm=False, is_pypy=False):
@@ -92,9 +92,9 @@ class Scanner27(Scanner2):
# the "continue" is not on a new line.
n = len(tokens)
if (n > 2 and
tokens[-1].type == 'JUMP_BACK' and
tokens[-1].kind == 'JUMP_BACK' and
self.code[offset+3] == self.opc.END_FINALLY):
tokens[-1].type = intern('CONTINUE')
tokens[-1].kind = intern('CONTINUE')
pass

View File

@@ -175,12 +175,16 @@ class Scanner3(Scanner):
for instr in bytecode.get_instructions(co):
print(instr._disassemble())
# Container for tokens
# list of tokens/instructions
tokens = []
# "customize" is a dict whose keys are nonterminals
# and the value is the argument stack entries for that
# nonterminal. The count is a little hoaky. It is mostly
# not used, but sometimes it is.
customize = {}
if self.is_pypy:
customize['PyPy'] = 1
customize['PyPy'] = 0
self.code = array('B', co.co_code)
self.build_lines_data(co)
@@ -336,7 +340,7 @@ class Scanner3(Scanner):
attr = (pos_args, name_pair_args, annotate_args)
tokens.append(
Token(
type_ = opname,
opname = opname,
attr = attr,
pattr = pattr,
offset = inst.offset,
@@ -396,12 +400,12 @@ class Scanner3(Scanner):
# the "continue" is not on a new line.
# There are other situations where we don't catch
# CONTINUE as well.
if tokens[-1].type == 'JUMP_BACK' and tokens[-1].attr <= argval:
if tokens[-2].type == 'BREAK_LOOP':
if tokens[-1].kind == 'JUMP_BACK' and tokens[-1].attr <= argval:
if tokens[-2].kind == 'BREAK_LOOP':
del tokens[-1]
else:
# intern is used because we are changing the *previous* token
tokens[-1].type = intern('CONTINUE')
tokens[-1].kind = intern('CONTINUE')
if last_op_was_break and opname == 'CONTINUE':
last_op_was_break = False
continue
@@ -414,7 +418,7 @@ class Scanner3(Scanner):
last_op_was_break = opname == 'BREAK_LOOP'
tokens.append(
Token(
type_ = opname,
opname = opname,
attr = argval,
pattr = pattr,
offset = inst.offset,
@@ -949,7 +953,7 @@ class Scanner3(Scanner):
return
pass
pass
if code[pre_rtarget] == self.opc.RETURN_VALUE and self.version < 3.5:
if code[pre_rtarget] == self.opc.RETURN_VALUE:
self.return_end_ifs.add(pre_rtarget)
else:
self.fixed_jumps[offset] = rtarget
@@ -969,7 +973,7 @@ class Scanner3(Scanner):
if target > next_offset:
next_op = code[next_offset]
if (self.opc.JUMP_ABSOLUTE == next_op and
END_FINALLY != code[xdis.next_offset(next_op, self.opc, next_offset)]):
self.opc.END_FINALLY != code[xdis.next_offset(next_op, self.opc, next_offset)]):
self.fixed_jumps[next_offset] = target
self.except_targets[target] = next_offset
@@ -992,7 +996,8 @@ class Scanner3(Scanner):
# misclassified as RETURN_END_IF. Handle that here.
# In RETURN_VALUE, JUMP_ABSOLUTE, RETURN_VALUE is never RETURN_END_IF
if op == self.opc.RETURN_VALUE:
if (offset+1 < len(code) and code[offset+1] == self.opc.JUMP_ABSOLUTE and
next_offset = xdis.next_offset(op, self.opc, offset)
if (next_offset < len(code) and code[next_offset] == self.opc.JUMP_ABSOLUTE and
offset in self.return_end_ifs):
self.return_end_ifs.remove(offset)
pass

View File

@@ -10,7 +10,7 @@ scanner routine for Python 3.
from xdis.opcodes import opcode_30 as opc
from xdis.bytecode import op_size
JUMP_OPs = map(lambda op: opc.opname[op], opc.hasjrel + opc.hasjabs)
JUMP_OPS = opc.JUMP_OPS
JUMP_TF = frozenset([opc.JUMP_IF_FALSE, opc.JUMP_IF_TRUE])

View File

@@ -1,4 +1,4 @@
# Copyright (c) 2016 by Rocky Bernstein
# Copyright (c) 2016-2017 by Rocky Bernstein
"""
Python 3.1 bytecode scanner/deparser
@@ -8,7 +8,7 @@ scanner routine for Python 3.
# bytecode verification, verify(), uses JUMP_OPs from here
from xdis.opcodes import opcode_31 as opc
JUMP_OPs = map(lambda op: opc.opname[op], opc.hasjrel + opc.hasjabs)
JUMP_OPS = opc.JUMP_OPS
from uncompyle6.scanners.scanner3 import Scanner3
class Scanner31(Scanner3):

View File

@@ -11,7 +11,7 @@ scanner routine for Python 3.
# bytecode verification, verify(), uses JUMP_OPs from here
from xdis.opcodes import opcode_32 as opc
JUMP_OPs = map(lambda op: opc.opname[op], opc.hasjrel + opc.hasjabs)
JUMP_OPS = opc.JUMP_OPS
from uncompyle6.scanners.scanner3 import Scanner3
class Scanner32(Scanner3):

View File

@@ -1,4 +1,4 @@
# Copyright (c) 2015-2016 by Rocky Bernstein
# Copyright (c) 2015-2017 by Rocky Bernstein
"""
Python 3.3 bytecode scanner/deparser
@@ -8,7 +8,7 @@ scanner routine for Python 3.
# bytecode verification, verify(), uses JUMP_OPs from here
from xdis.opcodes import opcode_33 as opc
JUMP_OPs = map(lambda op: opc.opname[op], opc.hasjrel + opc.hasjabs)
JUMP_OPS = opc.JUMP_OPS
from uncompyle6.scanners.scanner3 import Scanner3
class Scanner33(Scanner3):

View File

@@ -12,7 +12,7 @@ scanner routine for Python 3.
from xdis.opcodes import opcode_34 as opc
# bytecode verification, verify(), uses JUMP_OPs from here
JUMP_OPs = map(lambda op: opc.opname[op], opc.hasjrel + opc.hasjabs)
JUMP_OPS = opc.JUMP_OPS
from uncompyle6.scanners.scanner3 import Scanner3

View File

@@ -13,7 +13,7 @@ from uncompyle6.scanners.scanner3 import Scanner3
# bytecode verification, verify(), uses JUMP_OPs from here
from xdis.opcodes import opcode_35 as opc
JUMP_OPs = map(lambda op: opc.opname[op], opc.hasjrel + opc.hasjabs)
JUMP_OPS = opc.JUMP_OPS
class Scanner35(Scanner3):

View File

@@ -11,9 +11,9 @@ scanner routine for Python 3.
from uncompyle6.scanners.scanner3 import Scanner3
# bytecode verification, verify(), uses JUMP_OPs from here
# bytecode verification, verify(), uses JUMP_OPS from here
from xdis.opcodes import opcode_36 as opc
JUMP_OPs = map(lambda op: opc.opname[op], opc.hasjrel + opc.hasjabs)
JUMP_OPS = opc.JUMP_OPS
class Scanner36(Scanner3):
@@ -27,14 +27,14 @@ class Scanner36(Scanner3):
# The lowest bit of flags indicates whether the
# var-keyword argument is placed at the top of the stack
if t.op == self.opc.CALL_FUNCTION_EX and t.attr & 1:
t.type = 'CALL_FUNCTION_EX_KW'
t.kind = 'CALL_FUNCTION_EX_KW'
pass
elif t.op == self.opc.CALL_FUNCTION_KW:
t.type = 'CALL_FUNCTION_KW_{t.attr}'.format(**locals())
t.kind = 'CALL_FUNCTION_KW_{t.attr}'.format(**locals())
elif t.op == self.opc.BUILD_TUPLE_UNPACK_WITH_CALL:
t.type = 'BUILD_TUPLE_UNPACK_WITH_CALL_%d' % t.attr
t.kind = 'BUILD_TUPLE_UNPACK_WITH_CALL_%d' % t.attr
elif t.op == self.opc.BUILD_MAP_UNPACK_WITH_CALL:
t.type = 'BUILD_MAP_UNPACK_WITH_CALL_%d' % t.attr
t.kind = 'BUILD_MAP_UNPACK_WITH_CALL_%d' % t.attr
pass
return tokens, customize

View File

@@ -0,0 +1,38 @@
# Copyright (c) 2016-2017 by Rocky Bernstein
"""
Python 3.7 bytecode decompiler scanner
Does some additional massaging of xdis-disassembled instructions to
make things easier for decompilation.
This sets up opcodes Python's 3.6 and calls a generalized
scanner routine for Python 3.
"""
from __future__ import print_function
from uncompyle6.scanners.scanner3 import Scanner3
# bytecode verification, verify(), uses JUMP_OPs from here
from xdis.opcodes import opcode_36 as opc
JUMP_OPs = opc.JUMP_OPS
class Scanner37(Scanner3):
def __init__(self, show_asm=None):
Scanner3.__init__(self, 3.7, show_asm)
return
pass
if __name__ == "__main__":
from uncompyle6 import PYTHON_VERSION
if PYTHON_VERSION == 3.7:
import inspect
co = inspect.currentframe().f_code
tokens, customize = Scanner37().ingest(co)
for t in tokens:
print(t.format())
pass
else:
print("Need to be Python 3.7 to demo; I am %s." %
PYTHON_VERSION)

View File

@@ -1,4 +1,4 @@
# Copyright (c) 2016 by Rocky Bernstein
# Copyright (c) 2016-2017 by Rocky Bernstein
# Copyright (c) 2000-2002 by hartmut Goebel <h.goebel@crazy-compilers.com>
# Copyright (c) 1999 John Aycock
@@ -16,13 +16,12 @@ class Token:
the contents of one line as output by dis.dis().
"""
# FIXME: match Python 3.4's terms:
# type_ should be opname
# linestart = starts_line
# attr = argval
# pattr = argrepr
def __init__(self, type_, attr=None, pattr=None, offset=-1,
def __init__(self, opname, attr=None, pattr=None, offset=-1,
linestart=None, op=None, has_arg=None, opc=None):
self.type = intern(type_)
self.kind = intern(opname)
self.op = op
self.has_arg = has_arg
self.attr = attr
@@ -37,20 +36,20 @@ class Token:
def __eq__(self, o):
""" '==', but it's okay if offsets and linestarts are different"""
if isinstance(o, Token):
# Both are tokens: compare type and attr
# Both are tokens: compare kind and attr
# It's okay if offsets are different
return (self.type == o.type) and (self.pattr == o.pattr)
return (self.kind == o.kind) and (self.pattr == o.pattr)
else:
return self.type == o
return self.kind == o
def __repr__(self):
return str(self.type)
return str(self.kind)
# def __str__(self):
# pattr = self.pattr if self.pattr is not None else ''
# prefix = '\n%3d ' % self.linestart if self.linestart else (' ' * 6)
# return (prefix +
# ('%9s %-18s %r' % (self.offset, self.type, pattr)))
# ('%9s %-18s %r' % (self.offset, self.kind, pattr)))
def __str__(self):
return self.format(line_prefix='')
@@ -60,7 +59,7 @@ class Token:
prefix = '\n%s%4d ' % (line_prefix, self.linestart)
else:
prefix = ' ' * (6 + len(line_prefix))
offset_opname = '%6s %-17s' % (self.offset, self.type)
offset_opname = '%6s %-17s' % (self.offset, self.kind)
if not self.has_arg:
return "%s%s" % (prefix, offset_opname)
@@ -84,14 +83,14 @@ class Token:
pattr = self.opc.cmp_op[self.attr]
# And so on. See xdis/bytecode.py get_instructions_bytes
pass
elif re.search('_\d+$', self.type):
elif re.search('_\d+$', self.kind):
return "%s%s%s" % (prefix, offset_opname, argstr)
else:
pattr = ''
return "%s%s%s %r" % (prefix, offset_opname, argstr, pattr)
def __hash__(self):
return hash(self.type)
return hash(self.kind)
def __getitem__(self, i):
raise IndexError

View File

@@ -9,16 +9,16 @@ before reduction and don't reduce when there is a problem.
"""
def checker(ast, in_loop, errors):
in_loop = in_loop or ast.type in ('while1stmt', 'whileTruestmt',
in_loop = in_loop or ast.kind in ('while1stmt', 'whileTruestmt',
'whilestmt', 'whileelsestmt', 'while1elsestmt',
'for_block')
if ast.type in ('augassign1', 'augassign2') and ast[0][0] == 'and':
if ast.kind in ('augassign1', 'augassign2') and ast[0][0] == 'and':
text = str(ast)
error_text = '\n# improper augmented assigment (e.g. +=, *=, ...):\n#\t' + '\n# '.join(text.split("\n")) + '\n'
errors.append(error_text)
for node in ast:
if not in_loop and node.type in ('continue_stmt', 'break_stmt'):
if not in_loop and node.kind in ('continue_stmt', 'break_stmt'):
text = str(node)
error_text = '\n# not in loop:\n#\t' + '\n# '.join(text.split("\n"))
errors.append(error_text)

View File

@@ -1,5 +1,5 @@
# Copyright (c) 2017 by Rocky Bernstein
"""Constants used in pysource.py"""
"""Constants and initial table values used in pysource.py and fragments.py"""
import re, sys
from uncompyle6.parsers.astnode import AST
@@ -57,9 +57,7 @@ INDENT_PER_LEVEL = ' ' # additional intent per pretty-print level
TABLE_R = {
'STORE_ATTR': ( '%c.%[1]{pattr}', 0),
# 'STORE_SUBSCR': ( '%c[%c]', 0, 1 ),
'DELETE_ATTR': ( '%|del %c.%[-1]{pattr}\n', 0 ),
# 'EXEC_STMT': ( '%|exec %c in %[1]C\n', 0, (0,maxint,', ') ),
}
TABLE_R0 = {
@@ -67,8 +65,9 @@ TABLE_R0 = {
# 'BUILD_TUPLE': ( '(%C)', (0,-1,', ') ),
# 'CALL_FUNCTION': ( '%c(%P)', 0, (1,-1,', ') ),
}
TABLE_DIRECT = {
'BINARY_ADD': ( '+' ,),
'BINARY_ADD': ( '+' ,),
'BINARY_SUBTRACT': ( '-' ,),
'BINARY_MULTIPLY': ( '*' ,),
'BINARY_DIVIDE': ( '/' ,),
@@ -76,13 +75,13 @@ TABLE_DIRECT = {
'BINARY_TRUE_DIVIDE': ( '/' ,), # Not in <= 2.1
'BINARY_FLOOR_DIVIDE': ( '//' ,),
'BINARY_MODULO': ( '%%',),
'BINARY_POWER': ( '**',),
'BINARY_POWER': ( '**',),
'BINARY_LSHIFT': ( '<<',),
'BINARY_RSHIFT': ( '>>',),
'BINARY_AND': ( '&' ,),
'BINARY_OR': ( '|' ,),
'BINARY_XOR': ( '^' ,),
'INPLACE_ADD': ( '+=' ,),
'BINARY_AND': ( '&' ,),
'BINARY_OR': ( '|' ,),
'BINARY_XOR': ( '^' ,),
'INPLACE_ADD': ( '+=' ,),
'INPLACE_SUBTRACT': ( '-=' ,),
'INPLACE_MULTIPLY': ( '*=' ,),
'INPLACE_MATRIX_MULTIPLY': ( '@=' ,),
@@ -93,125 +92,126 @@ TABLE_DIRECT = {
'INPLACE_POWER': ( '**=',),
'INPLACE_LSHIFT': ( '<<=',),
'INPLACE_RSHIFT': ( '>>=',),
'INPLACE_AND': ( '&=' ,),
'INPLACE_OR': ( '|=' ,),
'INPLACE_XOR': ( '^=' ,),
'binary_expr': ( '%c %c %c', 0, -1, 1 ),
'INPLACE_AND': ( '&=' ,),
'INPLACE_OR': ( '|=' ,),
'INPLACE_XOR': ( '^=' ,),
'binary_expr': ( '%c %c %c', 0, -1, 1 ),
'UNARY_POSITIVE': ( '+',),
'UNARY_NEGATIVE': ( '-',),
'UNARY_INVERT': ( '~%c'),
'unary_expr': ( '%c%c', 1, 0),
'UNARY_INVERT': ( '~'),
'unary_expr': ( '%c%c', 1, 0),
'unary_not': ( 'not %c', 0 ),
'unary_not': ( 'not %c', 0 ),
'unary_convert': ( '`%c`', 0 ),
'get_iter': ( 'iter(%c)', 0 ),
'slice0': ( '%c[:]', 0 ),
'slice1': ( '%c[%p:]', 0, (1, 100) ),
'slice2': ( '%c[:%p]', 0, (1, 100) ),
'slice3': ( '%c[%p:%p]', 0, (1, 100), (2, 100) ),
'get_iter': ( 'iter(%c)', 0 ),
'slice0': ( '%c[:]', 0 ),
'slice1': ( '%c[%p:]', 0, (1, 100) ),
'slice2': ( '%c[:%p]', 0, (1, 100) ),
'slice3': ( '%c[%p:%p]', 0, (1, 100), (2, 100) ),
'IMPORT_FROM': ( '%{pattr}', ),
'load_attr': ( '%c.%[1]{pattr}', 0),
'LOAD_FAST': ( '%{pattr}', ),
'LOAD_NAME': ( '%{pattr}', ),
'IMPORT_FROM': ( '%{pattr}', ),
'load_attr': ( '%c.%[1]{pattr}', 0),
'LOAD_FAST': ( '%{pattr}', ),
'LOAD_NAME': ( '%{pattr}', ),
'LOAD_CLASSNAME': ( '%{pattr}', ),
'LOAD_GLOBAL': ( '%{pattr}', ),
'LOAD_DEREF': ( '%{pattr}', ),
'LOAD_LOCALS': ( 'locals()', ),
'LOAD_ASSERT': ( '%{pattr}', ),
'LOAD_GLOBAL': ( '%{pattr}', ),
'LOAD_DEREF': ( '%{pattr}', ),
'LOAD_LOCALS': ( 'locals()', ),
'LOAD_ASSERT': ( '%{pattr}', ),
# 'LOAD_CONST': ( '%{pattr}', ), # handled by n_LOAD_CONST
'DELETE_FAST': ( '%|del %{pattr}\n', ),
'DELETE_NAME': ( '%|del %{pattr}\n', ),
'DELETE_FAST': ( '%|del %{pattr}\n', ),
'DELETE_NAME': ( '%|del %{pattr}\n', ),
'DELETE_GLOBAL': ( '%|del %{pattr}\n', ),
'delete_subscr': ( '%|del %c[%c]\n', 0, 1,),
'binary_subscr': ( '%c[%p]', 0, (1, 100)),
'binary_subscr2': ( '%c[%p]', 0, (1, 100)),
'store_subscr': ( '%c[%c]', 0, 1),
'STORE_FAST': ( '%{pattr}', ),
'STORE_NAME': ( '%{pattr}', ),
'STORE_GLOBAL': ( '%{pattr}', ),
'STORE_DEREF': ( '%{pattr}', ),
'unpack': ( '%C%,', (1, maxint, ', ') ),
'store_subscr': ( '%c[%c]', 0, 1),
'STORE_FAST': ( '%{pattr}', ),
'STORE_NAME': ( '%{pattr}', ),
'STORE_GLOBAL': ( '%{pattr}', ),
'STORE_DEREF': ( '%{pattr}', ),
'unpack': ( '%C%,', (1, maxint, ', ') ),
# This nonterminal we create on the fly in semantic routines
'unpack_w_parens': ( '(%C%,)', (1, maxint, ', ') ),
'unpack_list': ( '[%C]', (1, maxint, ', ') ),
'build_tuple2': ( '%P', (0, -1, ', ', 100) ),
'unpack_list': ( '[%C]', (1, maxint, ', ') ),
'build_tuple2': ( '%P', (0, -1, ', ', 100) ),
# 'list_compr': ( '[ %c ]', -2), # handled by n_list_compr
'list_iter': ( '%c', 0),
'list_for': ( ' for %c in %c%c', 2, 0, 3 ),
'list_if': ( ' if %c%c', 0, 2 ),
'list_iter': ( '%c', 0 ),
'list_for': ( ' for %c in %c%c', 2, 0, 3 ),
'list_if': ( ' if %c%c', 0, 2 ),
'list_if_not': ( ' if not %p%c', (0, 22), 2 ),
'lc_body': ( '', ), # ignore when recusing
'lc_body': ( '', ), # ignore when recusing
'comp_iter': ( '%c', 0),
'comp_if': ( ' if %c%c', 0, 2 ),
'comp_ifnot': ( ' if not %p%c', (0, 22), 2 ),
'comp_body': ( '', ), # ignore when recusing
'comp_iter': ( '%c', 0 ),
'comp_if': ( ' if %c%c', 0, 2 ),
'comp_ifnot': ( ' if not %p%c', (0, 22), 2 ),
'comp_body': ( '', ), # ignore when recusing
'set_comp_body': ( '%c', 0 ),
'gen_comp_body': ( '%c', 0 ),
'dict_comp_body': ( '%c:%c', 1, 0 ),
'assign': ( '%|%c = %p\n', -1, (0, 200) ),
'assign': ( '%|%c = %p\n', -1, (0, 200) ),
# The 2nd parameter should have a = suffix.
# There is a rule with a 4th parameter "designator"
# which we don't use here.
'augassign1': ( '%|%c %c %c\n', 0, 2, 1),
'augassign1': ( '%|%c %c %c\n', 0, 2, 1),
'augassign2': ( '%|%c.%[2]{pattr} %c %c\n', 0, -3, -4),
'designList': ( '%c = %c', 0, -1 ),
'augassign2': ( '%|%c.%[2]{pattr} %c %c\n', 0, -3, -4 ),
'designList': ( '%c = %c', 0, -1 ),
'and': ( '%c and %c', 0, 2 ),
'ret_and': ( '%c and %c', 0, 2 ),
'and2': ( '%c', 3 ),
'or': ( '%c or %c', 0, 2 ),
'ret_or': ( '%c or %c', 0, 2 ),
'conditional': ( '%p if %p else %p', (2, 27), (0, 27), (4, 27)),
'conditionalTrue': ( '%p if 1 else %p', (0, 27), (2, 27)),
'ret_cond': ( '%p if %p else %p', (2, 27), (0, 27), (-1, 27)),
'conditionalnot': ( '%p if not %p else %p', (2, 27), (0, 22), (4, 27)),
'ret_cond_not': ( '%p if not %p else %p', (2, 27), (0, 22), (-1, 27)),
'ret_or': ( '%c or %c', 0, 2 ),
'conditional': ( '%p if %p else %p', (2, 27), (0, 27), (4, 27) ),
'conditionalTrue': ( '%p if 1 else %p', (0, 27), (2, 27) ),
'ret_cond': ( '%p if %p else %p', (2, 27), (0, 27), (-1, 27) ),
'conditionalnot': ( '%p if not %p else %p', (2, 27), (0, 22), (4, 27) ),
'ret_cond_not': ( '%p if not %p else %p', (2, 27), (0, 22), (-1, 27) ),
'conditional_lambda': ( '(%c if %c else %c)', 2, 0, 3),
'return_lambda': ('%c', 0),
'compare': ( '%p %[-1]{pattr.replace("-", " ")} %p', (0, 19), (1, 19) ),
'cmp_list': ( '%p %p', (0, 29), (1, 30)),
'cmp_list1': ( '%[3]{pattr} %p %p', (0, 19), (-2, 19)),
'cmp_list2': ( '%[1]{pattr} %p', (0, 19)),
'compare': ( '%p %[-1]{pattr.replace("-", " ")} %p', (0, 19), (1, 19) ),
'cmp_list': ( '%p %p', (0, 29), (1, 30)),
'cmp_list1': ( '%[3]{pattr} %p %p', (0, 19), (-2, 19)),
'cmp_list2': ( '%[1]{pattr} %p', (0, 19)),
# 'classdef': (), # handled by n_classdef()
'funcdef': ( '\n\n%|def %c\n', -2), # -2 to handle closures
'funcdef': ( '\n\n%|def %c\n', -2), # -2 to handle closures
'funcdefdeco': ( '\n\n%c', 0),
'mkfuncdeco': ( '%|@%c\n%c', 0, 1),
'mkfuncdeco': ( '%|@%c\n%c', 0, 1),
'mkfuncdeco0': ( '%|def %c\n', 0),
'classdefdeco': ( '\n\n%c', 0),
'classdefdeco1': ( '%|@%c\n%c', 0, 1),
'kwarg': ( '%[0]{pattr}=%c', 1),
'kwargs': ( '%D', (0, maxint, ', ') ),
'kwarg': ( '%[0]{pattr}=%c', 1),
'kwargs': ( '%D', (0, maxint, ', ') ),
'assert_expr_or': ( '%c or %c', 0, 2 ),
'assert_expr_and': ( '%c and %c', 0, 2 ),
'print_items_stmt': ( '%|print %c%c,\n', 0, 2), # Python 2 only
'print_items_nl_stmt': ( '%|print %c%c\n', 0, 2),
'print_item': ( ', %c', 0),
'print_nl': ( '%|print\n', ),
'print_to': ( '%|print >> %c, %c,\n', 0, 1 ),
'print_to_nl': ( '%|print >> %c, %c\n', 0, 1 ),
'print_nl_to': ( '%|print >> %c\n', 0 ),
'assert_expr_or': ( '%c or %c', 0, 2 ),
'assert_expr_and': ( '%c and %c', 0, 2 ),
'print_items_stmt': ( '%|print %c%c,\n', 0, 2 ), # Python 2 only
'print_items_nl_stmt': ( '%|print %c%c\n', 0, 2 ),
'print_item': ( ', %c', 0),
'print_nl': ( '%|print\n', ),
'print_to': ( '%|print >> %c, %c,\n', 0, 1 ),
'print_to_nl': ( '%|print >> %c, %c\n', 0, 1 ),
'print_nl_to': ( '%|print >> %c\n', 0 ),
'print_to_items': ( '%C', (0, 2, ', ') ),
'call_stmt': ( '%|%p\n', (0, 200)),
'break_stmt': ( '%|break\n', ),
'call_stmt': ( '%|%p\n', (0, 200)),
'break_stmt': ( '%|break\n', ),
'continue_stmt': ( '%|continue\n', ),
'raise_stmt0': ( '%|raise\n', ),
'raise_stmt1': ( '%|raise %c\n', 0),
'raise_stmt3': ( '%|raise %c, %c, %c\n', 0, 1, 2),
'raise_stmt0': ( '%|raise\n', ),
'raise_stmt1': ( '%|raise %c\n', 0),
'raise_stmt3': ( '%|raise %c, %c, %c\n', 0, 1, 2),
# 'yield': ( 'yield %c', 0),
# 'return_stmt': ( '%|return %c\n', 0),
'return_if_stmt': ( 'return %c\n', 0),
'ifstmt': ( '%|if %c:\n%+%c%-', 0, 1 ),
'ifstmt': ( '%|if %c:\n%+%c%-', 0, 1 ),
'iflaststmt': ( '%|if %c:\n%+%c%-', 0, 1 ),
'iflaststmtl': ( '%|if %c:\n%+%c%-', 0, 1 ),
'testtrue': ( 'not %p', (0, 22) ),
@@ -229,37 +229,37 @@ TABLE_DIRECT = {
'elifelsestmtr2': ( '%|elif %c:\n%+%c%-%|else:\n%+%c%-\n\n', 0, 1, 3 ), # has COME_FROM
'whileTruestmt': ( '%|while True:\n%+%c%-\n\n', 1 ),
'whilestmt': ( '%|while %c:\n%+%c%-\n\n', 1, 2 ),
'while1stmt': ( '%|while 1:\n%+%c%-\n\n', 1 ),
'while1elsestmt': ( '%|while 1:\n%+%c%-%|else:\n%+%c%-\n\n', 1, -2 ),
'whilestmt': ( '%|while %c:\n%+%c%-\n\n', 1, 2 ),
'while1stmt': ( '%|while 1:\n%+%c%-\n\n', 1 ),
'while1elsestmt': ( '%|while 1:\n%+%c%-%|else:\n%+%c%-\n\n', 1, -2 ),
'whileelsestmt': ( '%|while %c:\n%+%c%-%|else:\n%+%c%-\n\n', 1, 2, -2 ),
'whileelselaststmt': ( '%|while %c:\n%+%c%-%|else:\n%+%c%-', 1, 2, -2 ),
'forstmt': ( '%|for %c in %c:\n%+%c%-\n\n', 3, 1, 4 ),
'forelsestmt': (
'%|for %c in %c:\n%+%c%-%|else:\n%+%c%-\n\n', 3, 1, 4, -2),
'forstmt': ( '%|for %c in %c:\n%+%c%-\n\n', 3, 1, 4 ),
'forelsestmt': (
'%|for %c in %c:\n%+%c%-%|else:\n%+%c%-\n\n', 3, 1, 4, -2 ),
'forelselaststmt': (
'%|for %c in %c:\n%+%c%-%|else:\n%+%c%-', 3, 1, 4, -2),
'%|for %c in %c:\n%+%c%-%|else:\n%+%c%-', 3, 1, 4, -2 ),
'forelselaststmtl': (
'%|for %c in %c:\n%+%c%-%|else:\n%+%c%-\n\n', 3, 1, 4, -2),
'trystmt': ( '%|try:\n%+%c%-%c\n\n', 1, 3 ),
'tryelsestmt': ( '%|try:\n%+%c%-%c%|else:\n%+%c%-\n\n', 1, 3, 4 ),
'tryelsestmtc': ( '%|try:\n%+%c%-%c%|else:\n%+%c%-', 1, 3, 4 ),
'tryelsestmtl': ( '%|try:\n%+%c%-%c%|else:\n%+%c%-', 1, 3, 4 ),
'tf_trystmt': ( '%c%-%c%+', 1, 3 ),
'%|for %c in %c:\n%+%c%-%|else:\n%+%c%-\n\n', 3, 1, 4, -2 ),
'trystmt': ( '%|try:\n%+%c%-%c\n\n', 1, 3 ),
'tryelsestmt': ( '%|try:\n%+%c%-%c%|else:\n%+%c%-\n\n', 1, 3, 4 ),
'tryelsestmtc': ( '%|try:\n%+%c%-%c%|else:\n%+%c%-', 1, 3, 4 ),
'tryelsestmtl': ( '%|try:\n%+%c%-%c%|else:\n%+%c%-', 1, 3, 4 ),
'tf_trystmt': ( '%c%-%c%+', 1, 3 ),
'tf_tryelsestmt': ( '%c%-%c%|else:\n%+%c', 1, 3, 4 ),
'tryfinallystmt': ( '%|try:\n%+%c%-%|finally:\n%+%c%-\n\n', 1, 5 ),
'except': ( '%|except:\n%+%c%-', 3 ),
'except_cond1': ( '%|except %c:\n', 1 ),
'except_cond1': ( '%|except %c:\n', 1 ),
'except_suite': ( '%+%c%-%C', 0, (1, maxint, '') ),
'except_suite_finalize': ( '%+%c%-%C', 1, (3, maxint, '') ),
'passstmt': ( '%|pass\n', ),
'STORE_FAST': ( '%{pattr}', ),
'kv': ( '%c: %c', 3, 1 ),
'kv2': ( '%c: %c', 1, 2 ),
'mapexpr': ( '{%[1]C}', (0, maxint, ', ') ),
'importstmt': ( '%|import %c\n', 2),
'importfrom': ( '%|from %[2]{pattr} import %c\n', 3 ),
'importstar': ( '%|from %[2]{pattr} import *\n', ),
'passstmt': ( '%|pass\n', ),
'STORE_FAST': ( '%{pattr}', ),
'kv': ( '%c: %c', 3, 1 ),
'kv2': ( '%c: %c', 1, 2 ),
'mapexpr': ( '{%[1]C}', (0, maxint, ', ') ),
'importstmt': ( '%|import %c\n', 2),
'importfrom': ( '%|from %[2]{pattr} import %c\n', 3 ),
'importstar': ( '%|from %[2]{pattr} import *\n', ),
}
@@ -276,7 +276,7 @@ MAP = {
}
# Operator precidence
# See https://docs.python.org/3/reference/expressions.html
# See https://docs.python.org/2/reference/expressions.html
# or https://docs.python.org/3/reference/expressions.html
# for a list.
PRECEDENCE = {
@@ -332,6 +332,7 @@ PRECEDENCE = {
'ret_or': 26,
'conditional': 28,
'conditional_lamdba': 28,
'conditionalnot': 28,
'ret_cond': 28,
'ret_cond_not': 28,

View File

@@ -1,6 +1,4 @@
# Copyright (c) 2015, 2016 by Rocky Bernstein
# Copyright (c) 2005 by Dan Pascu <dan@windowmaker.org>
# Copyright (c) 2000-2002 by hartmut Goebel <h.goebel@crazy-compilers.com>
# Copyright (c) 2015-2017 by Rocky Bernstein
# Copyright (c) 1999 John Aycock
"""
@@ -8,8 +6,8 @@ Creates Python source code from an uncompyle6 abstract syntax tree,
and indexes fragments which can be accessed by instruction offset
address.
See the comments in pysource for information on the abstract sytax tree
and how semantic actions are written.
See https://github.com/rocky/python-uncompyle6/wiki/Table-driven-semantic-actions.
for a more complete explanation, nicely marked up and with examples.
We add some format specifiers here not used in pysource
@@ -40,7 +38,8 @@ do it recursively which is where offsets are probably located.
2. %b
-----
%b associates the text from the previous start node up to what we have now
%b associates the text from the specified index to what we have now.
it takes an integer argument.
For example in:
'importmultiple': ( '%|import%b %c%c\n', 0, 2, 3 ),
@@ -96,9 +95,8 @@ TABLE_DIRECT_FRAGMENT = {
'importfrom': ( '%|from %[2]{pattr}%x import %c\n', (2, (0, 1)), 3),
'importmultiple': ( '%|import%b %c%c\n', 0, 2, 3 ),
'list_for': (' for %c%x in %c%c', 2, (2, (1, )), 0, 3 ),
'forstmt': ( '%|for%b %c%x in %c:\n%+%c%-\n\n', 0, 3, (3, (2, )), 1, 4 ),
'forelsestmt': (
'%|for %c in %c%x:\n%+%c%-%|else:\n%+%c%-\n\n', 3, (3, (2,)), 1, 4, -2),
'%|for %c%x in %c:\n%+%c%-%|else:\n%+%c%-\n\n', 3, (3, (2,)), 1, 4, -2),
'forelselaststmt': (
'%|for %c%x in %c:\n%+%c%-%|else:\n%+%c%-', 3, (3, (2,)), 1, 4, -2),
'forelselaststmtl': (
@@ -310,11 +308,11 @@ class FragmentsWalker(pysource.SourceWalker, object):
def n_expr(self, node):
start = len(self.f.getvalue())
p = self.prec
if node[0].type.startswith('binary_expr'):
if node[0].kind.startswith('binary_expr'):
n = node[0][-1][0]
else:
n = node[0]
self.prec = PRECEDENCE.get(n.type, -2)
self.prec = PRECEDENCE.get(n.kind, -2)
if n == 'LOAD_CONST' and repr(n.pattr)[0] == '-':
n.parent = node
self.set_pos_info(n, start, len(self.f.getvalue()))
@@ -407,7 +405,7 @@ class FragmentsWalker(pysource.SourceWalker, object):
def n_ifelsestmtr(self, node):
if node[2] == 'COME_FROM':
return_stmts_node = node[3]
node.type = 'ifelsestmtr2'
node.kind = 'ifelsestmtr2'
else:
return_stmts_node = node[2]
if len(return_stmts_node) != 2:
@@ -424,10 +422,10 @@ class FragmentsWalker(pysource.SourceWalker, object):
self.write(self.indent, 'if ')
self.preorder(node[0])
self.println(':')
self.indentMore()
self.indent_more()
node[1].parent = node
self.preorder(node[1])
self.indentLess()
self.indent_less()
if_ret_at_end = False
if len(node[2][0]) >= 3:
@@ -440,23 +438,23 @@ class FragmentsWalker(pysource.SourceWalker, object):
for n in return_stmts_node[0]:
if (n[0] == 'ifstmt' and n[0][1][0] == 'return_if_stmts'):
if prev_stmt_is_if_ret:
n[0].type = 'elifstmt'
n[0].kind = 'elifstmt'
prev_stmt_is_if_ret = True
else:
prev_stmt_is_if_ret = False
if not past_else and not if_ret_at_end:
self.println(self.indent, 'else:')
self.indentMore()
self.indent_more()
past_else = True
n.parent = node
self.preorder(n)
if not past_else or if_ret_at_end:
self.println(self.indent, 'else:')
self.indentMore()
self.indent_more()
node[2][1].parent = node
self.preorder(node[2][1])
self.set_pos_info(node, start, len(self.f.getvalue()))
self.indentLess()
self.indent_less()
self.prune()
def n_elifelsestmtr(self, node):
@@ -473,20 +471,20 @@ class FragmentsWalker(pysource.SourceWalker, object):
node[0].parent = node
self.preorder(node[0])
self.println(':')
self.indentMore()
self.indent_more()
node[1].parent = node
self.preorder(node[1])
self.indentLess()
self.indent_less()
for n in node[2][0]:
n[0].type = 'elifstmt'
n[0].kind = 'elifstmt'
n.parent = node
self.preorder(n)
self.println(self.indent, 'else:')
self.indentMore()
self.indent_more()
node[2][1].parent = node
self.preorder(node[2][1])
self.indentLess()
self.indent_less()
self.set_pos_info(node, start, len(self.f.getvalue()))
self.prune()
@@ -495,7 +493,7 @@ class FragmentsWalker(pysource.SourceWalker, object):
iname = node[0].pattr
store_import_node = node[-1][-1]
assert store_import_node.type.startswith('STORE_')
assert store_import_node.kind.startswith('STORE_')
sname = store_import_node.pattr
self.write(iname)
@@ -530,7 +528,7 @@ class FragmentsWalker(pysource.SourceWalker, object):
self.write(func_name)
self.set_pos_info(code_node, start, len(self.f.getvalue()))
self.indentMore()
self.indent_more()
start = len(self.f.getvalue())
self.make_function(node, isLambda=False, codeNode=code_node)
@@ -540,7 +538,7 @@ class FragmentsWalker(pysource.SourceWalker, object):
self.write('\n\n')
else:
self.write('\n\n\n')
self.indentLess()
self.indent_less()
self.prune() # stop recursing
def n_list_compr(self, node):
@@ -556,7 +554,7 @@ class FragmentsWalker(pysource.SourceWalker, object):
elif n == 'list_if': n = n[2]
elif n == 'list_if_not': n= n[2]
assert n == 'lc_body'
if node[0].type.startswith('BUILD_LIST'):
if node[0].kind.startswith('BUILD_LIST'):
start = len(self.f.getvalue())
self.set_pos_info(node[0], start, start+1)
self.write( '[ ')
@@ -689,7 +687,7 @@ class FragmentsWalker(pysource.SourceWalker, object):
# Python 2.7+ starts including set_comp_body
# Python 3.5+ starts including setcomp_func
assert n.type in ('lc_body', 'comp_body', 'setcomp_func', 'set_comp_body'), ast
assert n.kind in ('lc_body', 'comp_body', 'setcomp_func', 'set_comp_body'), ast
assert designator, "Couldn't find designator in list/set comprehension"
old_name = self.name
@@ -716,7 +714,7 @@ class FragmentsWalker(pysource.SourceWalker, object):
self.preorder(if_node)
self.prec = p
self.name = old_name
if node[-1].type.startswith('CALL_FUNCTION'):
if node[-1].kind.startswith('CALL_FUNCTION'):
self.set_pos_info(node[-1], gen_start, len(self.f.getvalue()))
def listcomprehension_walk2(self, node):
@@ -745,7 +743,7 @@ class FragmentsWalker(pysource.SourceWalker, object):
n = n[3]
elif n in ('list_if', 'list_if_not'):
# FIXME: just a guess
if n[0].type == 'expr':
if n[0].kind == 'expr':
list_if = n
else:
list_if = n[1]
@@ -791,7 +789,7 @@ class FragmentsWalker(pysource.SourceWalker, object):
start = len(self.f.getvalue())
self.set_pos_info(node[0], start-1, start)
self.comprehension_walk3(node, 1, 0)
elif node[0].type == 'load_closure':
elif node[0].kind == 'load_closure':
self.setcomprehension_walk3(node, collection_index=4)
else:
self.comprehension_walk(node, iter_index=4)
@@ -810,7 +808,7 @@ class FragmentsWalker(pysource.SourceWalker, object):
self.set_pos_info(node[0], start, len(self.f.getvalue()))
self.write(': {')
start = len(self.f.getvalue())
assert node[0].type.startswith('BUILD_SET')
assert node[0].kind.startswith('BUILD_SET')
self.set_pos_info(node[0], start-1, start)
designator = node[3]
assert designator == 'designator'
@@ -819,7 +817,7 @@ class FragmentsWalker(pysource.SourceWalker, object):
fin = len(self.f.getvalue())
self.set_pos_info(designator, start, fin)
for_iter_node = node[2]
assert for_iter_node.type == 'FOR_ITER'
assert for_iter_node.kind == 'FOR_ITER'
self.set_pos_info(for_iter_node, start, fin)
self.write(" for ")
self.preorder(designator)
@@ -838,7 +836,7 @@ class FragmentsWalker(pysource.SourceWalker, object):
def n_listcomp(self, node):
self.write('[')
if node[0].type == 'load_closure':
if node[0].kind == 'load_closure':
self.listcomprehension_walk2(node)
else:
if node[0] == 'LOAD_LISTCOMP':
@@ -852,7 +850,7 @@ class FragmentsWalker(pysource.SourceWalker, object):
if len(node) > 1:
if (node[0] == 'c_stmts_opt' and
node[0][0] == 'passstmt' and
node[1].type.startswith('JUMP_FORWARD')):
node[1].kind.startswith('JUMP_FORWARD')):
self.set_pos_info(node[1], node[0][0].start, node[0][0].finish)
def setcomprehension_walk3(self, node, collection_index):
@@ -883,7 +881,7 @@ class FragmentsWalker(pysource.SourceWalker, object):
n = n[3]
elif n in ('list_if', 'list_if_not', 'comp_if', 'comp_if_not'):
# FIXME: just a guess
if n[0].type == 'expr':
if n[0].kind == 'expr':
list_if = n
else:
list_if = n[1]
@@ -989,9 +987,9 @@ class FragmentsWalker(pysource.SourceWalker, object):
self.println(':')
# class body
self.indentMore()
self.indent_more()
self.build_class(subclass)
self.indentLess()
self.indent_less()
self.currentclass = cclass
self.set_pos_info(node, start, len(self.f.getvalue()))
@@ -1046,8 +1044,8 @@ class FragmentsWalker(pysource.SourceWalker, object):
# NOTE: this differs from behavior in pysource.py
if len(tokens) >= 2 and not noneInNames:
if tokens[-1].type == 'RETURN_VALUE':
if tokens[-2].type != 'LOAD_CONST':
if tokens[-1].kind == 'RETURN_VALUE':
if tokens[-2].kind != 'LOAD_CONST':
tokens.append(Token('RETURN_LAST'))
if len(tokens) == 0:
return
@@ -1301,10 +1299,10 @@ class FragmentsWalker(pysource.SourceWalker, object):
# as a custom rule
start = len(self.f.getvalue())
n = len(node)-1
assert node[n].type.startswith('CALL_FUNCTION')
assert node[n].kind.startswith('CALL_FUNCTION')
for i in range(n-2, 0, -1):
if not node[i].type in ['expr', 'LOAD_CLASSNAME']:
if not node[i].kind in ['expr', 'LOAD_CLASSNAME']:
break
pass
@@ -1332,14 +1330,14 @@ class FragmentsWalker(pysource.SourceWalker, object):
p = self.prec
self.prec = 100
self.indentMore(INDENT_PER_LEVEL)
self.indent_more(INDENT_PER_LEVEL)
line_seperator = ',\n' + self.indent
sep = INDENT_PER_LEVEL[:-1]
start = len(self.f.getvalue())
self.write('{')
if self.version > 3.0:
if node[0].type.startswith('kvlist'):
if node[0].kind.startswith('kvlist'):
# Python 3.5+ style key/value list in mapexpr
kv_node = node[0]
l = list(kv_node)
@@ -1354,11 +1352,11 @@ class FragmentsWalker(pysource.SourceWalker, object):
i += 2
pass
pass
elif node[1].type.startswith('kvlist'):
elif node[1].kind.startswith('kvlist'):
# Python 3.0..3.4 style key/value list in mapexpr
kv_node = node[1]
l = list(kv_node)
if len(l) > 0 and l[0].type == 'kv3':
if len(l) > 0 and l[0].kind == 'kv3':
# Python 3.2 does this
kv_node = node[1][0]
l = list(kv_node)
@@ -1381,7 +1379,7 @@ class FragmentsWalker(pysource.SourceWalker, object):
pass
else:
# Python 2 style kvlist
assert node[-1].type.startswith('kvlist')
assert node[-1].kind.startswith('kvlist')
kv_node = node[-1] # goto kvlist
for kv in kv_node:
@@ -1409,7 +1407,7 @@ class FragmentsWalker(pysource.SourceWalker, object):
n.parent = node
self.set_pos_info(n, start, finish)
self.set_pos_info(node, start, finish)
self.indentLess(INDENT_PER_LEVEL)
self.indent_less(INDENT_PER_LEVEL)
self.prec = p
self.prune()
@@ -1420,7 +1418,7 @@ class FragmentsWalker(pysource.SourceWalker, object):
p = self.prec
self.prec = 100
n = node.pop()
lastnode = n.type
lastnode = n.kind
start = len(self.f.getvalue())
if lastnode.startswith('BUILD_LIST'):
self.write('['); endchar = ']'
@@ -1445,7 +1443,7 @@ class FragmentsWalker(pysource.SourceWalker, object):
else:
flat_elems.append(elem)
self.indentMore(INDENT_PER_LEVEL)
self.indent_more(INDENT_PER_LEVEL)
if len(node) > 3:
line_separator = ',\n' + self.indent
else:
@@ -1470,14 +1468,14 @@ class FragmentsWalker(pysource.SourceWalker, object):
n.parent = node.parent
self.set_pos_info(n, start, finish)
self.set_pos_info(node, start, finish)
self.indentLess(INDENT_PER_LEVEL)
self.indent_less(INDENT_PER_LEVEL)
self.prec = p
self.prune()
def engine(self, entry, startnode):
def template_engine(self, entry, startnode):
"""The format template interpetation engine. See the comment at the
beginning of this module for the how we interpret format specifications such as
%c, %C, and so on.
beginning of this module for the how we interpret format
specifications such as %c, %C, and so on.
"""
# print("-----")
@@ -1514,8 +1512,8 @@ class FragmentsWalker(pysource.SourceWalker, object):
self.write('%')
self.set_pos_info(node, start, len(self.f.getvalue()))
elif typ == '+': self.indentMore()
elif typ == '-': self.indentLess()
elif typ == '+': self.indent_more()
elif typ == '-': self.indent_less()
elif typ == '|': self.write(self.indent)
# no longer used, since BUILD_TUPLE_n is pretty printed:
elif typ == 'r': recurse_node = True
@@ -1535,7 +1533,7 @@ class FragmentsWalker(pysource.SourceWalker, object):
# for loops have two positions that correspond to a single text
# location. In "for i in ..." there is the initialization "i" code as well
# as the iteration code with "i"
match = re.search(r'^for', startnode.type)
match = re.search(r'^for', startnode.kind)
if match and entry[arg] == 3:
self.set_pos_info(node[0], start, finish)
for n in node[2]:
@@ -1629,7 +1627,7 @@ class FragmentsWalker(pysource.SourceWalker, object):
# 2. subroutine calls. It the last op is the call and for purposes of printing
# we don't need to print anything special there. However it encompases the
# entire string of the node fn(...)
match = re.search(r'^call_function', startnode.type)
match = re.search(r'^call_function', startnode.kind)
if match:
last_node = startnode[-1]
# import traceback; traceback.print_stack()
@@ -1770,7 +1768,7 @@ if __name__ == '__main__':
nodeInfo = walk.offsets[name, offset]
node = nodeInfo.node
extractInfo = walk.extract_node_info(node)
print("code: %s" % node.type)
print("code: %s" % node.kind)
# print extractInfo
print(extractInfo.selectedText)
print(extractInfo.selectedLine)
@@ -1780,7 +1778,7 @@ if __name__ == '__main__':
print("Contained in...")
print(extractInfo.selectedLine)
print(extractInfo.markerLine)
print("code: %s" % p.type)
print("code: %s" % p.kind)
print('=' * 40)
pass
pass
@@ -1799,7 +1797,7 @@ if __name__ == '__main__':
nodeInfo = walk.offsets[name, offset]
node = nodeInfo.node
extractInfo = walk.extract_node_info(node)
print("code: %s" % node.type)
print("code: %s" % node.kind)
# print extractInfo
print(extractInfo.selectedText)
print(extractInfo.selectedLine)
@@ -1809,7 +1807,7 @@ if __name__ == '__main__':
print("Contained in...")
print(extractInfo.selectedLine)
print(extractInfo.markerLine)
print("code: %s" % p.type)
print("code: %s" % p.kind)
print('=' * 40)
pass
pass

View File

@@ -17,7 +17,7 @@ def find_all_globals(node, globs):
for n in node:
if isinstance(n, AST):
globs = find_all_globals(n, globs)
elif n.type in ('STORE_GLOBAL', 'DELETE_GLOBAL', 'LOAD_GLOBAL'):
elif n.kind in ('STORE_GLOBAL', 'DELETE_GLOBAL', 'LOAD_GLOBAL'):
globs.add(n.pattr)
return globs
@@ -26,7 +26,7 @@ def find_globals(node, globs):
for n in node:
if isinstance(n, AST):
globs = find_globals(n, globs)
elif n.type in ('STORE_GLOBAL', 'DELETE_GLOBAL'):
elif n.kind in ('STORE_GLOBAL', 'DELETE_GLOBAL'):
globs.add(n.pattr)
return globs
@@ -36,7 +36,7 @@ def find_none(node):
if n not in ('return_stmt', 'return_if_stmt'):
if find_none(n):
return True
elif n.type == 'LOAD_CONST' and n.pattr is None:
elif n.kind == 'LOAD_CONST' and n.pattr is None:
return True
return False
@@ -64,7 +64,7 @@ def make_function3_annotate(self, node, isLambda, nested=1,
return name
# MAKE_FUNCTION_... or MAKE_CLOSURE_...
assert node[-1].type.startswith('MAKE_')
assert node[-1].kind.startswith('MAKE_')
annotate_tuple = None
for annotate_last in range(len(node)-1, -1, -1):
@@ -80,7 +80,7 @@ def make_function3_annotate(self, node, isLambda, nested=1,
i = -1
j = annotate_last-1
l = -len(node)
while j >= l and node[j].type in ('annotate_arg' 'annotate_tuple'):
while j >= l and node[j].kind in ('annotate_arg' 'annotate_tuple'):
annotate_args[annotate_tup[i]] = node[j][0]
i -= 1
j -= 1
@@ -106,7 +106,7 @@ def make_function3_annotate(self, node, isLambda, nested=1,
lambda_index = None
if lambda_index and isLambda and iscode(node[lambda_index].attr):
assert node[lambda_index].type == 'LOAD_LAMBDA'
assert node[lambda_index].kind == 'LOAD_LAMBDA'
code = node[lambda_index].attr
else:
code = codeNode.attr
@@ -318,7 +318,7 @@ def make_function2(self, node, isLambda, nested=1, codeNode=None):
return name
# MAKE_FUNCTION_... or MAKE_CLOSURE_...
assert node[-1].type.startswith('MAKE_')
assert node[-1].kind.startswith('MAKE_')
args_node = node[-1]
if isinstance(args_node.attr, tuple):
@@ -334,7 +334,7 @@ def make_function2(self, node, isLambda, nested=1, codeNode=None):
lambda_index = None
if lambda_index and isLambda and iscode(node[lambda_index].attr):
assert node[lambda_index].type == 'LOAD_LAMBDA'
assert node[lambda_index].kind == 'LOAD_LAMBDA'
code = node[lambda_index].attr
else:
code = codeNode.attr
@@ -450,7 +450,7 @@ def make_function3(self, node, isLambda, nested=1, codeNode=None):
return name
# MAKE_FUNCTION_... or MAKE_CLOSURE_...
assert node[-1].type.startswith('MAKE_')
assert node[-1].kind.startswith('MAKE_')
args_node = node[-1]
if isinstance(args_node.attr, tuple):
@@ -484,7 +484,7 @@ def make_function3(self, node, isLambda, nested=1, codeNode=None):
lambda_index = None
if lambda_index and isLambda and iscode(node[lambda_index].attr):
assert node[lambda_index].type == 'LOAD_LAMBDA'
assert node[lambda_index].kind == 'LOAD_LAMBDA'
code = node[lambda_index].attr
else:
code = codeNode.attr
@@ -585,7 +585,7 @@ def make_function3(self, node, isLambda, nested=1, codeNode=None):
for n in node:
if n == 'pos_arg':
continue
elif self.version >= 3.4 and not (n.type in ('kwargs', 'kwarg')):
elif self.version >= 3.4 and not (n.kind in ('kwargs', 'kwarg')):
continue
else:
self.preorder(n)

View File

@@ -11,62 +11,102 @@ and what they mean).
Upper levels of the grammar is a more-or-less conventional grammar for
Python.
Semantic action rules for nonterminal symbols can be specified here by
creating a method prefaced with "n_" for that nonterminal. For
example, "n_exec_stmt" handles the semantic actions for the
"exec_smnt" nonterminal symbol. Similarly if a method with the name
of the nonterminal is suffixed with "_exit" it will be called after
all of its children are called.
Another other way to specify a semantic rule for a nonterminal is via
rule given in one of the tables MAP_R0, MAP_R, or MAP_DIRECT.
These uses a printf-like syntax to direct substitution from attributes
of the nonterminal and its children..
The rest of the below describes how table-driven semantic actions work
and gives a list of the format specifiers. The default() and engine()
methods implement most of the below.
Step 1 determines a table (T) and a path to a
table key (K) from the node type (N) (other nodes are shown as O):
N N N&K
/ | ... \ / | ... \ / | ... \
O O O O O K O O O
|
K
MAP_R0 (TABLE_R0) MAP_R (TABLE_R) MAP_DIRECT (TABLE_DIRECT)
The default is a direct mapping. The key K is then extracted from the
subtree and used to find a table entry T[K], if any. The result is a
format string and arguments (a la printf()) for the formatting engine.
Escapes in the format string are:
%c evaluate children N[A] recursively*
%C evaluate children N[A[0]]..N[A[1]-1] recursively, separate by A[2]*
%P same as %C but sets operator precedence
%D same as %C but is for left-recursive lists like kwargs which
goes to epsilon at the beginning. Using %C an extra separator
with an epsilon appears at the beginning
%, print ',' if last %C only printed one item. This is mostly for tuples
on the LHS of an assignment statement since BUILD_TUPLE_n pretty-prints
other tuples.
%| tab to current indentation level
%+ increase current indentation level
%- decrease current indentation level
%{...} evaluate ... in context of N
%% literal '%'
%p evaluate N setting precedence
* indicates an argument (A) required.
The '%' may optionally be followed by a number (C) in square brackets, which
makes the engine walk down to N[C] before evaluating the escape code.
"""
# The below is a bit long, but still it is somehwat abbreviated.
# See https://github.com/rocky/python-uncompyle6/wiki/Table-driven-semantic-actions.
# for a more complete explanation, nicely marked up and with examples.
#
#
# Semantic action rules for nonterminal symbols can be specified here by
# creating a method prefaced with "n_" for that nonterminal. For
# example, "n_exec_stmt" handles the semantic actions for the
# "exec_stmt" nonterminal symbol. Similarly if a method with the name
# of the nonterminal is suffixed with "_exit" it will be called after
# all of its children are called.
#
# After a while writing methods this way, you'll find many routines which do similar
# sorts of things, and soon you'll find you want a short notation to
# describe rules and not have to create methods at all.
#
# So another other way to specify a semantic rule for a nonterminal is via
# one of the tables MAP_R0, MAP_R, or MAP_DIRECT where the key is the
# nonterminal name.
#
# These dictionaries use a printf-like syntax to direct substitution
# from attributes of the nonterminal and its children..
#
# The rest of the below describes how table-driven semantic actions work
# and gives a list of the format specifiers. The default() and
# template_engine() methods implement most of the below.
#
# We allow for a couple of ways to interact with a node in a tree. So
# step 1 after not seeing a custom method for a nonterminal is to
# determine from what point of view tree-wise the rule is applied.
# In the diagram below, N is a nonterminal name, and K also a nonterminal
# name but the one used as a key in the table.
# we show where those are with respect to each other in the
# AST tree for N.
#
#
# N&K N N
# / | ... \ / | ... \ / | ... \
# O O O O O K O O O
# |
# K
# TABLE_DIRECT TABLE_R TABLE_R0
#
# The default table is TABLE_DIRECT mapping By far, most rules used work this way.
# TABLE_R0 is rarely used.
#
# The key K is then extracted from the subtree and used to find one
# of the tables, T listed above. The result after applying T[K] is
# a format string and arguments (a la printf()) for the formatting
# engine.
#
# Escapes in the format string are:
#
# %c evaluate the node recursively. Its argument is a single
# integer representing a node index.
#
# %p like %c but sets the operator precedence.
# Its argument then is a tuple indicating the node
# index and the precidence value, an integer.
#
# %C evaluate children recursively, with sibling children separated by the
# given string. It needs a 3-tuple: a starting node, the maximimum
# value of an end node, and a string to be inserted between sibling children
#
# %, Append ',' if last %C only printed one item. This is mostly for tuples
# on the LHS of an assignment statement since BUILD_TUPLE_n pretty-prints
# other tuples. The specifier takes no arguments
#
# %P same as %C but sets operator precedence. Its argument is a 4-tuple:
# the node low and high indices, the separator, a string the precidence
# value, an integer.
#
# %D Same as `%C` this is for left-recursive lists like kwargs where goes
# to epsilon at the beginning. It needs a 3-tuple: a starting node, the
# maximimum value of an end node, and a string to be inserted between
# sibling children. If we were to use `%C` an extra separator with an
# epsilon would appear at the beginning.
#
# %| Insert spaces to the current indentation level. Takes no arguments.
#
# %+ increase current indentation level. Takes no arguments.
#
# %- decrease current indentation level. Takes no arguments.
#
# %{...} evaluate ... in context of N
#
# %% literal '%'. Takes no arguments.
#
#
# The '%' may optionally be followed by a number (C) in square
# brackets, which makes the template_engine walk down to N[C] before
# evaluating the escape code.
import sys
from uncompyle6 import PYTHON3
@@ -122,6 +162,29 @@ class SourceWalker(GenericASTTraversal, object):
debug_parser=PARSER_DEFAULT_DEBUG,
compile_mode='exec', is_pypy=False,
linestarts={}):
"""version is the Python version (a float) of the Python dialect
of both the AST and language we should produce.
out is IO-like file pointer to where the output should go. It
whould have a getvalue() method.
scanner is a method to call when we need to scan tokens. Sometimes
in producing output we will run across further tokens that need
to be scaned.
If showast is True, we print the AST tree.
compile_mode is is either 'exec' or 'single'. It isthe compile
mode that was used to create the AST and specifies a gramar variant within
a Python version to use.
is_pypy should be True if the AST was generated for PyPy.
linestarts is a dictionary of line number to bytecode offset. This
can sometimes assist in determinte which kind of source-code construct
to use when there is ambiguity.
"""
GenericASTTraversal.__init__(self, ast=None)
self.scanner = scanner
params = {
@@ -304,7 +367,7 @@ class SourceWalker(GenericASTTraversal, object):
# MAKE_FUNCTION ..
code = node[-3]
self.indentMore()
self.indent_more()
for annotate_last in range(len(node)-1, -1, -1):
if node[annotate_last] == 'annotate_tuple':
break
@@ -324,7 +387,7 @@ class SourceWalker(GenericASTTraversal, object):
self.write('\n\n')
else:
self.write('\n\n\n')
self.indentLess()
self.indent_less()
self.prune() # stop recursing
self.n_mkfunc_annotate = n_mkfunc_annotate
@@ -359,8 +422,10 @@ class SourceWalker(GenericASTTraversal, object):
node.type == 'call_function'
p = self.prec
self.prec = 80
self.engine(('%c(%P)', 0, (1, -4, ', ', 100)), node)
self.template_engine(('%c(%P)', 0,
(1, -4, ', ', 100)), node)
self.prec = p
node.type == 'async_call_function'
self.prune()
self.n_async_call_function = n_async_call_function
self.n_build_list_unpack = self.n_build_list
@@ -373,13 +438,13 @@ class SourceWalker(GenericASTTraversal, object):
for i in mapping[1:]:
key = key[i]
pass
if key.type.startswith('CALL_FUNCTION_VAR_KW'):
if key.kind.startswith('CALL_FUNCTION_VAR_KW'):
# Python 3.5 changes the stack position of *args. kwargs come
# after *args whereas in earlier Pythons, *args is at the end
# which simpilfiies things from our perspective.
# Python 3.6+ replaces CALL_FUNCTION_VAR_KW with CALL_FUNCTION_EX
# We will just swap the order to make it look like earlier Python 3.
entry = table[key.type]
entry = table[key.kind]
kwarg_pos = entry[2][1]
args_pos = kwarg_pos - 1
# Put last node[args_pos] after subsequent kwargs
@@ -400,9 +465,11 @@ class SourceWalker(GenericASTTraversal, object):
is_code = hasattr(code_node, 'attr') and iscode(code_node.attr)
if (is_code and
(code_node.attr.co_flags & COMPILER_FLAG_BIT['COROUTINE'])):
self.engine(('\n\n%|async def %c\n', -2), node)
self.template_engine(('\n\n%|async def %c\n',
-2), node)
else:
self.engine(('\n\n%|def %c\n', -2), node)
self.template_engine(('\n\n%|def %c\n', -2),
node)
self.prune()
self.n_funcdef = n_funcdef
@@ -500,10 +567,10 @@ class SourceWalker(GenericASTTraversal, object):
super(SourceWalker, self).preorder(node)
self.set_pos_info(node)
def indentMore(self, indent=TAB):
def indent_more(self, indent=TAB):
self.indent += indent
def indentLess(self, indent=TAB):
def indent_less(self, indent=TAB):
self.indent = self.indent[:-len(indent)]
def traverse(self, node, indent=None, isLambda=False):
@@ -578,6 +645,20 @@ class SourceWalker(GenericASTTraversal, object):
node == AST('return_stmt',
[AST('ret_expr', [NONE]), Token('RETURN_VALUE')]))
# Python 3.x can have be dead code as a result of its optimization?
# So we'll add a # at the end of the return lambda so the rest is ignored
def n_return_lambda(self, node):
if 1 <= len(node) <= 2:
self.preorder(node[0])
self.write(' # Avoid dead code: ')
self.prune()
else:
# We can't comment out like above because there may be a trailing ')'
# that needs to be written
assert len(node) == 3 and node[2] == 'LAMBDA_MARKER'
self.preorder(node[0])
self.prune()
def n_return_stmt(self, node):
if self.params['isLambda']:
self.preorder(node[0])
@@ -595,6 +676,7 @@ class SourceWalker(GenericASTTraversal, object):
def n_return_if_stmt(self, node):
if self.params['isLambda']:
self.write(' return ')
self.preorder(node[0])
self.prune()
else:
@@ -651,12 +733,12 @@ class SourceWalker(GenericASTTraversal, object):
def n_expr(self, node):
p = self.prec
if node[0].type.startswith('binary_expr'):
if node[0].kind.startswith('binary_expr'):
n = node[0][-1][0]
else:
n = node[0]
self.prec = PRECEDENCE.get(n.type, -2)
self.prec = PRECEDENCE.get(n.kind, -2)
if n == 'LOAD_CONST' and repr(n.pattr)[0] == '-':
self.prec = 6
@@ -739,9 +821,9 @@ class SourceWalker(GenericASTTraversal, object):
self.prune()
def n_delete_subscr(self, node):
if node[-2][0] == 'build_list' and node[-2][0][-1].type.startswith('BUILD_TUPLE'):
if node[-2][0] == 'build_list' and node[-2][0][-1].kind.startswith('BUILD_TUPLE'):
if node[-2][0][-1] != 'BUILD_TUPLE_0':
node[-2][0].type = 'build_tuple2'
node[-2][0].kind = 'build_tuple2'
self.default(node)
n_store_subscr = n_binary_subscr = n_delete_subscr
@@ -750,9 +832,9 @@ class SourceWalker(GenericASTTraversal, object):
def n_tryfinallystmt(self, node):
if len(node[1][0]) == 1 and node[1][0][0] == 'stmt':
if node[1][0][0][0] == 'trystmt':
node[1][0][0][0].type = 'tf_trystmt'
node[1][0][0][0].kind = 'tf_trystmt'
if node[1][0][0][0] == 'tryelsestmt':
node[1][0][0][0].type = 'tf_tryelsestmt'
node[1][0][0][0].kind = 'tf_tryelsestmt'
self.default(node)
def n_exec_stmt(self, node):
@@ -777,26 +859,26 @@ class SourceWalker(GenericASTTraversal, object):
if len(n) == 1 == len(n[0]) and n[0] == '_stmts':
n = n[0][0][0]
elif n[0].type in ('lastc_stmt', 'lastl_stmt'):
elif n[0].kind in ('lastc_stmt', 'lastl_stmt'):
n = n[0][0]
else:
if not preprocess:
self.default(node)
return
if n.type in ('ifstmt', 'iflaststmt', 'iflaststmtl'):
node.type = 'ifelifstmt'
n.type = 'elifstmt'
elif n.type in ('ifelsestmtr',):
node.type = 'ifelifstmt'
n.type = 'elifelsestmtr'
elif n.type in ('ifelsestmt', 'ifelsestmtc', 'ifelsestmtl'):
node.type = 'ifelifstmt'
if n.kind in ('ifstmt', 'iflaststmt', 'iflaststmtl'):
node.kind = 'ifelifstmt'
n.kind = 'elifstmt'
elif n.kind in ('ifelsestmtr',):
node.kind = 'ifelifstmt'
n.kind = 'elifelsestmtr'
elif n.kind in ('ifelsestmt', 'ifelsestmtc', 'ifelsestmtl'):
node.kind = 'ifelifstmt'
self.n_ifelsestmt(n, preprocess=True)
if n == 'ifelifstmt':
n.type = 'elifelifstmt'
elif n.type in ('ifelsestmt', 'ifelsestmtc', 'ifelsestmtl'):
n.type = 'elifelsestmt'
n.kind = 'elifelifstmt'
elif n.kind in ('ifelsestmt', 'ifelsestmtc', 'ifelsestmtl'):
n.kind = 'elifelsestmt'
if not preprocess:
self.default(node)
@@ -805,7 +887,7 @@ class SourceWalker(GenericASTTraversal, object):
def n_ifelsestmtr(self, node):
if node[2] == 'COME_FROM':
return_stmts_node = node[3]
node.type = 'ifelsestmtr2'
node.kind = 'ifelsestmtr2'
else:
return_stmts_node = node[2]
if len(return_stmts_node) != 2:
@@ -821,9 +903,9 @@ class SourceWalker(GenericASTTraversal, object):
self.write(self.indent, 'if ')
self.preorder(node[0])
self.println(':')
self.indentMore()
self.indent_more()
self.preorder(node[1])
self.indentLess()
self.indent_less()
if_ret_at_end = False
if len(return_stmts_node[0]) >= 3:
@@ -836,27 +918,27 @@ class SourceWalker(GenericASTTraversal, object):
for n in return_stmts_node[0]:
if (n[0] == 'ifstmt' and n[0][1][0] == 'return_if_stmts'):
if prev_stmt_is_if_ret:
n[0].type = 'elifstmt'
n[0].kind = 'elifstmt'
prev_stmt_is_if_ret = True
else:
prev_stmt_is_if_ret = False
if not past_else and not if_ret_at_end:
self.println(self.indent, 'else:')
self.indentMore()
self.indent_more()
past_else = True
self.preorder(n)
if not past_else or if_ret_at_end:
self.println(self.indent, 'else:')
self.indentMore()
self.indent_more()
self.preorder(return_stmts_node[1])
self.indentLess()
self.indent_less()
self.prune()
n_ifelsestmtr2 = n_ifelsestmtr
def n_elifelsestmtr(self, node):
if node[2] == 'COME_FROM':
return_stmts_node = node[3]
node.type = 'elifelsestmtr2'
node.kind = 'elifelsestmtr2'
else:
return_stmts_node = node[2]
@@ -871,22 +953,22 @@ class SourceWalker(GenericASTTraversal, object):
self.write(self.indent, 'elif ')
self.preorder(node[0])
self.println(':')
self.indentMore()
self.indent_more()
self.preorder(node[1])
self.indentLess()
self.indent_less()
for n in return_stmts_node[0]:
n[0].type = 'elifstmt'
n[0].kind = 'elifstmt'
self.preorder(n)
self.println(self.indent, 'else:')
self.indentMore()
self.indent_more()
self.preorder(return_stmts_node[1])
self.indentLess()
self.indent_less()
self.prune()
def n_import_as(self, node):
store_node = node[-1][-1]
assert store_node.type.startswith('STORE_')
assert store_node.kind.startswith('STORE_')
iname = node[0].pattr # import name
sname = store_node.pattr # store_name
if iname and iname == sname or iname.startswith(sname + '.'):
@@ -922,14 +1004,14 @@ class SourceWalker(GenericASTTraversal, object):
func_name = code_node.attr.co_name
self.write(func_name)
self.indentMore()
self.indent_more()
self.make_function(node, isLambda=False, codeNode=code_node)
if len(self.param_stack) > 1:
self.write('\n\n')
else:
self.write('\n\n\n')
self.indentLess()
self.indent_less()
self.prune() # stop recursing
def make_function(self, node, isLambda, nested=1,
@@ -1006,7 +1088,7 @@ class SourceWalker(GenericASTTraversal, object):
"""
p = self.prec
self.prec = 27
if node[-1].type == 'list_iter':
if node[-1].kind == 'list_iter':
n = node[-1]
elif self.is_pypy and node[-1] == 'JUMP_BACK':
n = node[-2]
@@ -1130,7 +1212,7 @@ class SourceWalker(GenericASTTraversal, object):
self.write('{')
if node[0] in ['LOAD_SETCOMP', 'LOAD_DICTCOMP']:
self.comprehension_walk3(node, 1, 0)
elif node[0].type == 'load_closure' and self.version >= 3.0:
elif node[0].kind == 'load_closure' and self.version >= 3.0:
self.setcomprehension_walk3(node, collection_index=4)
else:
self.comprehension_walk(node, iter_index=4)
@@ -1197,7 +1279,7 @@ class SourceWalker(GenericASTTraversal, object):
# Python 2.7+ starts including set_comp_body
# Python 3.5+ starts including setcomp_func
assert n.type in ('lc_body', 'comp_body', 'setcomp_func', 'set_comp_body'), ast
assert n.kind in ('lc_body', 'comp_body', 'setcomp_func', 'set_comp_body'), ast
assert designator, "Couldn't find designator in list/set comprehension"
self.preorder(n[0])
@@ -1247,7 +1329,7 @@ class SourceWalker(GenericASTTraversal, object):
n = n[3]
elif n in ('list_if', 'list_if_not'):
# FIXME: just a guess
if n[0].type == 'expr':
if n[0].kind == 'expr':
list_if = n
else:
list_if = n[1]
@@ -1268,7 +1350,7 @@ class SourceWalker(GenericASTTraversal, object):
def n_listcomp(self, node):
self.write('[')
if node[0].type == 'load_closure':
if node[0].kind == 'load_closure':
self.listcomprehension_walk2(node)
else:
self.comprehension_walk3(node, 1, 0)
@@ -1305,7 +1387,7 @@ class SourceWalker(GenericASTTraversal, object):
n = n[3]
elif n in ('list_if', 'list_if_not', 'comp_if', 'comp_if_not'):
# FIXME: just a guess
if n[0].type == 'expr':
if n[0].kind == 'expr':
list_if = n
else:
list_if = n[1]
@@ -1421,9 +1503,9 @@ class SourceWalker(GenericASTTraversal, object):
self.println(':')
# class body
self.indentMore()
self.indent_more()
self.build_class(subclass_code)
self.indentLess()
self.indent_less()
self.currentclass = cclass
if len(self.param_stack) > 1:
@@ -1457,10 +1539,10 @@ class SourceWalker(GenericASTTraversal, object):
def print_super_classes3(self, node):
n = len(node)-1
if node.type != 'expr':
assert node[n].type.startswith('CALL_FUNCTION')
if node.kind != 'expr':
assert node[n].kind.startswith('CALL_FUNCTION')
for i in range(n-2, 0, -1):
if not node[i].type in ['expr', 'LOAD_CLASSNAME']:
if not node[i].kind in ['expr', 'LOAD_CLASSNAME']:
break
pass
@@ -1494,13 +1576,13 @@ class SourceWalker(GenericASTTraversal, object):
p = self.prec
self.prec = 100
self.indentMore(INDENT_PER_LEVEL)
self.indent_more(INDENT_PER_LEVEL)
sep = INDENT_PER_LEVEL[:-1]
self.write('{')
line_number = self.line_number
if self.version >= 3.0 and not self.is_pypy:
if node[0].type.startswith('kvlist'):
if node[0].kind.startswith('kvlist'):
# Python 3.5+ style key/value list in mapexpr
kv_node = node[0]
l = list(kv_node)
@@ -1523,11 +1605,11 @@ class SourceWalker(GenericASTTraversal, object):
i += 2
pass
pass
elif len(node) > 1 and node[1].type.startswith('kvlist'):
elif len(node) > 1 and node[1].kind.startswith('kvlist'):
# Python 3.0..3.4 style key/value list in mapexpr
kv_node = node[1]
l = list(kv_node)
if len(l) > 0 and l[0].type == 'kv3':
if len(l) > 0 and l[0].kind == 'kv3':
# Python 3.2 does this
kv_node = node[1][0]
l = list(kv_node)
@@ -1552,7 +1634,7 @@ class SourceWalker(GenericASTTraversal, object):
i += 3
pass
pass
elif node[-1].type.startswith('BUILD_CONST_KEY_MAP'):
elif node[-1].kind.startswith('BUILD_CONST_KEY_MAP'):
# Python 3.6+ style const map
keys = node[-2].pattr
values = node[:-2]
@@ -1577,7 +1659,7 @@ class SourceWalker(GenericASTTraversal, object):
pass
else:
# Python 2 style kvlist
assert node[-1].type.startswith('kvlist')
assert node[-1].kind.startswith('kvlist')
kv_node = node[-1] # goto kvlist
first_time = True
@@ -1632,7 +1714,7 @@ class SourceWalker(GenericASTTraversal, object):
if sep.startswith(",\n"):
self.write(sep[1:])
self.write('}')
self.indentLess(INDENT_PER_LEVEL)
self.indent_less(INDENT_PER_LEVEL)
self.prec = p
self.prune()
@@ -1643,7 +1725,7 @@ class SourceWalker(GenericASTTraversal, object):
p = self.prec
self.prec = 100
lastnode = node.pop()
lastnodetype = lastnode.type
lastnodetype = lastnode.kind
# If this build list is inside a CALL_FUNCTION_VAR,
# then the first * has already been printed.
@@ -1683,7 +1765,7 @@ class SourceWalker(GenericASTTraversal, object):
else:
flat_elems.append(elem)
self.indentMore(INDENT_PER_LEVEL)
self.indent_more(INDENT_PER_LEVEL)
sep = ''
for elem in flat_elems:
@@ -1708,12 +1790,12 @@ class SourceWalker(GenericASTTraversal, object):
if lastnode.attr == 1 and lastnodetype.startswith('BUILD_TUPLE'):
self.write(',')
self.write(endchar)
self.indentLess(INDENT_PER_LEVEL)
self.indent_less(INDENT_PER_LEVEL)
self.prec = p
self.prune()
def n_unpack(self, node):
if node[0].type.startswith('UNPACK_EX'):
if node[0].kind.startswith('UNPACK_EX'):
# Python 3+
before_count, after_count = node[0].attr
for i in range(before_count+1):
@@ -1728,8 +1810,8 @@ class SourceWalker(GenericASTTraversal, object):
self.prune()
return
for n in node[1:]:
if n[0].type == 'unpack':
n[0].type = 'unpack_w_parens'
if n[0].kind == 'unpack':
n[0].kind = 'unpack_w_parens'
self.default(node)
n_unpack_w_parens = n_unpack
@@ -1738,33 +1820,34 @@ class SourceWalker(GenericASTTraversal, object):
# A horrible hack for Python 3.0 .. 3.2
if 3.0 <= self.version <= 3.2 and len(node) == 2:
if (node[0][0] == 'LOAD_FAST' and node[0][0].pattr == '__locals__' and
node[1][0].type == 'STORE_LOCALS'):
node[1][0].kind == 'STORE_LOCALS'):
self.prune()
self.default(node)
def n_assign2(self, node):
for n in node[-2:]:
if n[0] == 'unpack':
n[0].type = 'unpack_w_parens'
n[0].kind = 'unpack_w_parens'
self.default(node)
def n_assign3(self, node):
for n in node[-3:]:
if n[0] == 'unpack':
n[0].type = 'unpack_w_parens'
n[0].kind = 'unpack_w_parens'
self.default(node)
def n_except_cond2(self, node):
if node[-2][0] == 'unpack':
node[-2][0].type = 'unpack_w_parens'
node[-2][0].kind = 'unpack_w_parens'
self.default(node)
def engine(self, entry, startnode):
def template_engine(self, entry, startnode):
"""The format template interpetation engine. See the comment at the
beginning of this module for the how we interpret format specifications such as
%c, %C, and so on.
beginning of this module for the how we interpret format
specifications such as %c, %C, and so on.
"""
# self.println("----> ", startnode.type, ', ', entry[0])
# self.println("----> ", startnode.kind, ', ', entry[0])
fmt = entry[0]
arg = 1
i = 0
@@ -1782,24 +1865,23 @@ class SourceWalker(GenericASTTraversal, object):
if typ == '%': self.write('%')
elif typ == '+':
self.line_number += 1
self.indentMore()
self.indent_more()
elif typ == '-':
self.line_number += 1
self.indentLess()
self.indent_less()
elif typ == '|':
self.line_number += 1
self.write(self.indent)
# Used mostly on the LHS of an assignment
# BUILD_TUPLE_n is pretty printed and may take care of other uses.
elif typ == ',':
if (node.type in ('unpack', 'unpack_w_parens') and
if (node.kind in ('unpack', 'unpack_w_parens') and
node[0].attr == 1):
self.write(',')
elif typ == 'c':
if isinstance(entry[arg], int):
entry_node = node[entry[arg]]
self.preorder(entry_node)
arg += 1
entry_node = node[entry[arg]]
self.preorder(entry_node)
arg += 1
elif typ == 'p':
p = self.prec
(index, self.prec) = entry[arg]
@@ -1865,8 +1947,8 @@ class SourceWalker(GenericASTTraversal, object):
key = key[i]
pass
if key.type in table:
self.engine(table[key.type], node)
if key.kind in table:
self.template_engine(table[key.kind], node)
self.prune()
def customize(self, customize):
@@ -1890,7 +1972,7 @@ class SourceWalker(GenericASTTraversal, object):
'CALL_FUNCTION_VAR_KW', 'CALL_FUNCTION_KW'):
if v == 0:
str = '%c(%C' # '%C' is a dummy here ...
p2 = (0, 0, None) # .. because of this
p2 = (0, 0, None) # .. because of the None in this
else:
str = '%c(%C, '
p2 = (1, -2, ', ')
@@ -2085,6 +2167,11 @@ class SourceWalker(GenericASTTraversal, object):
# assert isinstance(tokens[0], Token)
if isLambda:
for t in tokens:
if t.kind == 'RETURN_END_IF':
t.kind = 'RETURN_END_IF_LAMBDA'
elif t.kind == 'RETURN_VALUE':
t.kind = 'RETURN_VALUE_LAMBDA'
tokens.append(Token('LAMBDA_MARKER'))
try:
ast = python_parser.parse(self.p, tokens, customize)
@@ -2101,10 +2188,10 @@ class SourceWalker(GenericASTTraversal, object):
# than fight (with the grammar to not emit "return None").
if self.hide_internal:
if len(tokens) >= 2 and not noneInNames:
if tokens[-1].type == 'RETURN_VALUE':
if tokens[-1].kind in ('RETURN_VALUE', 'RETURN_VALUE_LAMBDA'):
# Python 3.4's classes can add a "return None" which is
# invalid syntax.
if tokens[-2].type == 'LOAD_CONST':
if tokens[-2].kind == 'LOAD_CONST':
if isTopLevel or tokens[-2].pattr is None:
del tokens[-2:]
else:

View File

@@ -43,7 +43,7 @@ BIN_OP_FUNCS = {
'BINARY_OR': operator.or_,
}
JUMP_OPs = None
JUMP_OPS = None
# --- exceptions ---
@@ -225,8 +225,8 @@ def cmp_code_objects(version, is_pypy, code_obj1, code_obj2,
import uncompyle6.scanners.scanner36 as scan
scanner = scan.Scanner36()
global JUMP_OPs
JUMP_OPs = list(scan.JUMP_OPs) + ['JUMP_BACK']
global JUMP_OPS
JUMP_OPS = list(scan.JUMP_OPS) + ['JUMP_BACK']
# use changed Token class
# We (re)set this here to save exception handling,
@@ -242,18 +242,18 @@ def cmp_code_objects(version, is_pypy, code_obj1, code_obj2,
scanner.resetTokenClass() # restore Token class
targets1 = dis.findlabels(code_obj1.co_code)
tokens1 = [t for t in tokens1 if t.type != 'COME_FROM']
tokens2 = [t for t in tokens2 if t.type != 'COME_FROM']
tokens1 = [t for t in tokens1 if t.kind != 'COME_FROM']
tokens2 = [t for t in tokens2 if t.kind != 'COME_FROM']
i1 = 0; i2 = 0
offset_map = {}; check_jumps = {}
while i1 < len(tokens1):
if i2 >= len(tokens2):
if len(tokens1) == len(tokens2) + 2 \
and tokens1[-1].type == 'RETURN_VALUE' \
and tokens1[-2].type == 'LOAD_CONST' \
and tokens1[-1].kind == 'RETURN_VALUE' \
and tokens1[-2].kind == 'LOAD_CONST' \
and tokens1[-2].pattr is None \
and tokens1[-3].type == 'RETURN_VALUE':
and tokens1[-3].kind == 'RETURN_VALUE':
break
else:
raise CmpErrorCodeLen(name, tokens1, tokens2)
@@ -265,13 +265,13 @@ def cmp_code_objects(version, is_pypy, code_obj1, code_obj2,
raise CmpErrorCode(name, tokens1[idx1].offset, tokens1[idx1],
tokens2[idx2], tokens1, tokens2)
if tokens1[i1].type != tokens2[i2].type:
if tokens1[i1].type == 'LOAD_CONST' == tokens2[i2].type:
if tokens1[i1].kind != tokens2[i2].kind:
if tokens1[i1].kind == 'LOAD_CONST' == tokens2[i2].kind:
i = 1
while tokens1[i1+i].type == 'LOAD_CONST':
while tokens1[i1+i].kind == 'LOAD_CONST':
i += 1
if tokens1[i1+i].type.startswith(('BUILD_TUPLE', 'BUILD_LIST')) \
and i == int(tokens1[i1+i].type.split('_')[-1]):
if tokens1[i1+i].kind.startswith(('BUILD_TUPLE', 'BUILD_LIST')) \
and i == int(tokens1[i1+i].kind.split('_')[-1]):
t = tuple([ elem.pattr for elem in tokens1[i1:i1+i] ])
if t != tokens2[i2].pattr:
raise CmpErrorCode(name, tokens1[i1].offset, tokens1[i1],
@@ -279,60 +279,60 @@ def cmp_code_objects(version, is_pypy, code_obj1, code_obj2,
i1 += i + 1
i2 += 1
continue
elif i == 2 and tokens1[i1+i].type == 'ROT_TWO' and tokens2[i2+1].type == 'UNPACK_SEQUENCE_2':
elif i == 2 and tokens1[i1+i].kind == 'ROT_TWO' and tokens2[i2+1].kind == 'UNPACK_SEQUENCE_2':
i1 += 3
i2 += 2
continue
elif i == 2 and tokens1[i1+i].type in BIN_OP_FUNCS:
f = BIN_OP_FUNCS[tokens1[i1+i].type]
elif i == 2 and tokens1[i1+i].kind in BIN_OP_FUNCS:
f = BIN_OP_FUNCS[tokens1[i1+i].kind]
if f(tokens1[i1].pattr, tokens1[i1+1].pattr) == tokens2[i2].pattr:
i1 += 3
i2 += 1
continue
elif tokens1[i1].type == 'UNARY_NOT':
if tokens2[i2].type == 'POP_JUMP_IF_TRUE':
if tokens1[i1+1].type == 'POP_JUMP_IF_FALSE':
elif tokens1[i1].kind == 'UNARY_NOT':
if tokens2[i2].kind == 'POP_JUMP_IF_TRUE':
if tokens1[i1+1].kind == 'POP_JUMP_IF_FALSE':
i1 += 2
i2 += 1
continue
elif tokens2[i2].type == 'POP_JUMP_IF_FALSE':
if tokens1[i1+1].type == 'POP_JUMP_IF_TRUE':
elif tokens2[i2].kind == 'POP_JUMP_IF_FALSE':
if tokens1[i1+1].kind == 'POP_JUMP_IF_TRUE':
i1 += 2
i2 += 1
continue
elif tokens1[i1].type in ('JUMP_FORWARD', 'JUMP_BACK') \
and tokens1[i1-1].type == 'RETURN_VALUE' \
and tokens2[i2-1].type in ('RETURN_VALUE', 'RETURN_END_IF') \
elif tokens1[i1].kind in ('JUMP_FORWARD', 'JUMP_BACK') \
and tokens1[i1-1].kind == 'RETURN_VALUE' \
and tokens2[i2-1].kind in ('RETURN_VALUE', 'RETURN_END_IF') \
and int(tokens1[i1].offset) not in targets1:
i1 += 1
continue
elif tokens1[i1].type == 'JUMP_FORWARD' and tokens2[i2].type == 'JUMP_BACK' \
and tokens1[i1+1].type == 'JUMP_BACK' and tokens2[i2+1].type == 'JUMP_BACK' \
elif tokens1[i1].kind == 'JUMP_FORWARD' and tokens2[i2].kind == 'JUMP_BACK' \
and tokens1[i1+1].kind == 'JUMP_BACK' and tokens2[i2+1].kind == 'JUMP_BACK' \
and int(tokens1[i1].pattr) == int(tokens1[i1].offset) + 3:
if int(tokens1[i1].pattr) == int(tokens1[i1+1].offset):
i1 += 2
i2 += 2
continue
elif tokens1[i1].type == 'LOAD_NAME' and tokens2[i2].type == 'LOAD_CONST' \
elif tokens1[i1].kind == 'LOAD_NAME' and tokens2[i2].kind == 'LOAD_CONST' \
and tokens1[i1].pattr == 'None' and tokens2[i2].pattr is None:
pass
elif tokens1[i1].type == 'LOAD_GLOBAL' and tokens2[i2].type == 'LOAD_NAME' \
elif tokens1[i1].kind == 'LOAD_GLOBAL' and tokens2[i2].kind == 'LOAD_NAME' \
and tokens1[i1].pattr == tokens2[i2].pattr:
pass
elif tokens1[i1].type == 'LOAD_ASSERT' and tokens2[i2].type == 'LOAD_NAME' \
elif tokens1[i1].kind == 'LOAD_ASSERT' and tokens2[i2].kind == 'LOAD_NAME' \
and tokens1[i1].pattr == tokens2[i2].pattr:
pass
elif (tokens1[i1].type == 'RETURN_VALUE' and
tokens2[i2].type == 'RETURN_END_IF'):
elif (tokens1[i1].kind == 'RETURN_VALUE' and
tokens2[i2].kind == 'RETURN_END_IF'):
pass
elif (tokens1[i1].type == 'BUILD_TUPLE_0' and
elif (tokens1[i1].kind == 'BUILD_TUPLE_0' and
tokens2[i2].pattr == ()):
pass
else:
raise CmpErrorCode(name, tokens1[i1].offset, tokens1[i1],
tokens2[i2], tokens1, tokens2)
elif tokens1[i1].type in JUMP_OPs and tokens1[i1].pattr != tokens2[i2].pattr:
if tokens1[i1].type == 'JUMP_BACK':
elif tokens1[i1].kind in JUMP_OPS and tokens1[i1].pattr != tokens2[i2].pattr:
if tokens1[i1].kind == 'JUMP_BACK':
dest1 = int(tokens1[i1].pattr)
dest2 = int(tokens2[i2].pattr)
if offset_map[dest1] != dest2:
@@ -387,28 +387,28 @@ def cmp_code_objects(version, is_pypy, code_obj1, code_obj2,
class Token(scanner.Token):
"""Token class with changed semantics for 'cmp()'."""
def __cmp__(self, o):
t = self.type # shortcut
if t == 'BUILD_TUPLE_0' and o.type == 'LOAD_CONST' and o.pattr == ():
t = self.kind # shortcut
if t == 'BUILD_TUPLE_0' and o.kind == 'LOAD_CONST' and o.pattr == ():
return 0
if t == 'COME_FROM' == o.type:
if t == 'COME_FROM' == o.kind:
return 0
if t == 'PRINT_ITEM_CONT' and o.type == 'PRINT_ITEM':
if t == 'PRINT_ITEM_CONT' and o.kind == 'PRINT_ITEM':
return 0
if t == 'RETURN_VALUE' and o.type == 'RETURN_END_IF':
if t == 'RETURN_VALUE' and o.kind == 'RETURN_END_IF':
return 0
if t == 'JUMP_IF_FALSE_OR_POP' and o.type == 'POP_JUMP_IF_FALSE':
if t == 'JUMP_IF_FALSE_OR_POP' and o.kind == 'POP_JUMP_IF_FALSE':
return 0
if JUMP_OPs and t in JUMP_OPs:
if JUMP_OPS and t in JUMP_OPS:
# ignore offset
return t == o.type
return (t == o.type) or self.pattr == o.pattr
return t == o.kind
return (t == o.kind) or self.pattr == o.pattr
def __repr__(self):
return '%s %s (%s)' % (str(self.type), str(self.attr),
return '%s %s (%s)' % (str(self.kind), str(self.attr),
repr(self.pattr))
def __str__(self):
return '%s\t%-17s %r' % (self.offset, self.type, self.pattr)
return '%s\t%-17s %r' % (self.offset, self.kind, self.pattr)
def compare_code_with_srcfile(pyc_filename, src_filename, weak_verify=False):
"""Compare a .pyc with a source code file."""
@@ -442,4 +442,4 @@ if __name__ == '__main__':
t2 = Token('LOAD_CONST', -421, 'code_object _expandLang', 55)
print(repr(t1))
print(repr(t2))
print(t1.type == t2.type, t1.attr == t2.attr)
print(t1.kind == t2.kind, t1.attr == t2.attr)

View File

@@ -1,3 +1,3 @@
# This file is suitable for sourcing inside bash as
# well as importing into Python
VERSION='2.11.5'
VERSION='2.13.0'