Compare commits

..

107 Commits
3.4.0 ... 3.5.2

Author SHA1 Message Date
rocky
3e3dd87c3b Get ready for release 3.6.0 2019-12-09 21:51:15 -05:00
rocky
edbbefb57d Start to remove crud in control-flow detection for 3.7+ 2019-12-09 18:28:57 -05:00
rocky
6546bbdaf9 Fix 2.x false tryelsestmtl detection...
With grammar reduction tests. Same as tryelsestmt. Lots of stdlib tests work
now. (More remain though.)
2019-12-09 16:19:10 -05:00
rocky
825ed3fef9 Reinstate some stdlib tests...
now that we distinguish try/else a little better
2019-12-09 14:13:30 -05:00
rocky
7d9c4ce8ca Better try/else detection 2019-12-09 14:04:57 -05:00
rocky
fdac1e3c46 Use 3.9-enabled xdis 2019-12-09 12:56:30 -05:00
rocky
daab1e8610 Start to tolerate 3.9 (in pydisassemble) 2019-12-09 12:20:00 -05:00
rocky
b8f4dca505 Update README.rsgt 2019-12-09 07:19:51 -05:00
rocky
99b8a99ffa Python 2.5 fixes..
* "with" handling.
* Go over 2.5 runtest.sh exclusions
2019-12-09 06:57:02 -05:00
rocky
8c879c02de Small logic correction in run-time test. 2019-12-09 04:09:44 -05:00
rocky
d11a9ea126 Remember rocky: use off2int() in offset testing! 2019-12-08 21:42:49 -05:00
rocky
4926474efc Add jump range check for 2.7 assert_expr_and 2019-12-08 21:37:45 -05:00
rocky
eba5226a04 Typos: decompyle3 -> uncompyle6 2019-12-08 18:05:37 -05:00
R. Bernstein
8d0ff367d8 Merge pull request #297 from rocky/decompile-merge
Merging in recent 3.7 and 3.8 improvements from decompyle6
2019-12-08 18:01:38 -05:00
rocky
c6ddefcef5 Merging in recent 3.7 and 3.8 improvements from decompyle6
This rebases 3.7, 3.8 ...decompilation off of 3.7ish rather than a 3.4
base.

Add more 3.7 and 3.8 tests
2019-12-08 17:54:59 -05:00
rocky
301464d646 Accomodate for optional docstring in function kw calculation 2019-12-02 12:58:26 -05:00
rocky
d5b52d44e0 Better bytecode detection for Python > 3.0...
Not perfect though. More work is needed on the xdis side.
2019-11-21 19:39:57 -05:00
rocky
322f491c83 Revise NEWS 2019-11-20 10:08:20 -05:00
rocky
2987d6a72b Go over some 3.0 and 3.1 tests 2019-11-18 22:46:27 -05:00
rocky
7609165967 Revise mixed expressions 2019-11-18 18:22:16 -05:00
rocky
655162a05e One more test 2019-11-18 18:15:30 -05:00
rocky
ca7f483dbb Better test coverage of operators (in 2.7 and 3.0) 2019-11-18 18:10:58 -05:00
rocky
e713169bdf Administrivia: go over tests...
Some tests were deferred and are not now
update Python 2.7 standard library tests
2019-11-18 12:30:48 -05:00
rocky
cc856e2b95 Refine 2.7 control flow reduction tests...
for "iflastsmtl" and "and"
2019-11-18 11:34:06 -05:00
rocky
d696443eb2 More 2.7 reduction checks for conditionals:
Specficially for "and" and "laststmtl"
2019-11-18 08:36:28 -05:00
rocky
a5e7eb19c6 Reinstate some tests 2019-11-18 06:59:27 -05:00
rocky
6659fffc0d Two Bugs ...
2.7: more stringent comparison and comp_if testing
2.6-2.7: fix botched dict constant translation
2019-11-18 06:49:36 -05:00
rocky
1868b566a1 RsT markup 2019-11-17 20:47:40 -05:00
rocky
791274c45d RsT markup 2019-11-17 20:47:13 -05:00
rocky
4327ee98e6 Update README for the current situation 2019-11-17 20:45:37 -05:00
rocky
2717a5e302 Administrivia 2019-11-17 20:26:35 -05:00
rocky
77dd3b8d50 Administrivia 2019-11-17 20:25:14 -05:00
rocky
2cfc60fbd7 Get ready for release 3.5.1 2019-11-17 19:59:26 -05:00
rocky
daa424cf0c Some grammar cleanup based on coverage info 2019-11-17 01:01:52 -05:00
rocky
7b68c9c838 Administriva - bump testing versions 2019-11-16 22:54:32 -05:00
rocky
df5df9364c Grammar debugging for 3.0, 3.7 and 3.8 2019-11-16 17:59:30 -05:00
rocky
f1496cad4d 3.0 return_if_stmt and...
* Some grammar cleanup
* add more grammar debugging
2019-11-16 17:32:48 -05:00
rocky
a3a15414d3 Add 3.0 whileTrue rule for recent CONTINUE change 2019-11-16 16:18:39 -05:00
rocky
9874553fb4 while1 rule adjustment for 3.0 2019-11-16 16:04:16 -05:00
rocky
d21d93fd84 Handle 3.0 call_stmt better 2019-11-16 15:21:59 -05:00
rocky
dbf2729f76 expand 3.0 "continue" detection 2019-11-16 12:23:09 -05:00
rocky
047e27c966 3.0 assert2...
Not like other 3.x due to the lack of POP_JUMP_IF
2019-11-16 09:10:14 -05:00
rocky
6a81a752a7 Adjust 3.0 iflastsmtl rule 2019-11-16 00:59:58 -05:00
rocky
44f0ba0efb Add 3.0 try/except rule 2019-11-15 23:39:36 -05:00
rocky
bc8907e752 Guard again improper assert transform...
we see this happen in getheader() from 3.0.1/lib/python3.0/http/client.pyc
2019-11-15 22:19:17 -05:00
rocky
4e9d8783d1 Add Python 3.0.1 list_comp rule 2019-11-15 21:32:31 -05:00
rocky
47c847644e Modify 3.0 _ifstmts_jump rule 2019-11-15 19:23:08 -05:00
rocky
af2ed31871 Add 3.0 whilestmt rule 2019-11-15 15:14:33 -05:00
rocky
49de5b5c9d add 3.0 iflaststmt rule 2019-11-15 14:07:37 -05:00
rocky
c8252ca9cb 3.0 import_from rule 2019-11-15 09:27:47 -05:00
rocky
0441fbc616 3.0.1 "ret_or", "ret_and", and "or" rules 2019-11-15 09:12:53 -05:00
rocky
1b4335edf1 Add 3.0.1 while loop rule 2019-11-15 07:48:23 -05:00
rocky
2e36551c02 Remove more 3.0 parse errors...
However this doesn't mean that some wrong rules still don't
kid in. We still have control-flow "if/and/else" vs "if/if/else" problems.
2019-11-14 18:32:52 -05:00
rocky
fff6f82dd7 expand 3.0 jump_except rule 2019-11-14 10:11:28 -05:00
rocky
7c8f3cc9ec Two 3.0 rules ...
- ifstmtlastl
- ifnotstmt30
2019-11-14 03:57:41 -05:00
rocky
78a595c8cf Bang on 3.0.1 control flow...
more word is needed though
2019-11-13 20:35:44 -05:00
rocky
cda0154594 Pypy 3.6.9 tolerance 2019-11-12 23:33:36 -05:00
rocky
d852f23962 3.3 "yield from" semantic action fix 2019-11-12 17:48:16 -05:00
rocky
065fd13b81 Small tweaks 2019-11-12 17:04:35 -05:00
rocky
659f37585b Bug in 3.0 rule in "jump_absolute_else" ...
and disallowing "else" to the wrong place.
2019-11-12 16:31:43 -05:00
rocky
bc18fcf7fa 3.0 tweak in iflastsmtl reduction validation 2019-11-12 06:37:43 -05:00
rocky
144f52da8e More 3.0 control flow pattern fixups 2019-11-12 06:08:30 -05:00
rocky
9f250b49ee Cope more JUMP/POP_IF not being in 3.0...
more is probably needed though.
2019-11-11 19:58:35 -05:00
rocky
4abdffecb9 More 3.0 control-flow rules...
Much more is needed though
2019-11-11 19:07:58 -05:00
rocky
1419acf019 More Python 3.0 for JUMP elimination ...
here, in except blocks.
2019-11-11 13:50:48 -05:00
rocky
bdc24d7f51 Add 3.0 gen_comp_body rule. 2019-11-11 05:10:54 -05:00
rocky
07ec8fa1fb More Python 3.0 custom "if" statment handling. 2019-11-10 18:44:43 -05:00
rocky
04c2240d63 Python 3.0 if/else handling 2019-11-10 17:23:33 -05:00
rocky
96dcdfd744 Last change but closer... 2019-11-10 16:09:17 -05:00
rocky
82ea77c592 Python 3.0 bytecode decoding 2019-11-10 15:56:04 -05:00
rocky
4f0e580438 Update testenv pypy 3.6 2019-11-10 13:44:52 -05:00
rocky
09cc0d775a Pypy 3.3 tolerance and ...
Remove some duplicate grammar rules
2019-11-10 13:34:51 -05:00
rocky
2da5a5649f Python 3.5 tolerance 2019-11-10 12:04:21 -05:00
rocky
373916f57c Pypy 3.5 tolerance 2019-11-09 21:56:36 -05:00
rocky
1c0c54991e Backend some buffers 2019-11-09 18:49:40 -05:00
rocky
5de5d2357f Update test_grammar for Python 3.8 2019-11-09 17:55:58 -05:00
rocky
6d296f11c9 Add another 3.8 test 2019-10-31 07:13:41 -04:00
rocky
0ae4acff9e Remove extraneous iter() in "for" of list comp...
Fixes #272
2019-10-30 21:58:14 -04:00
rocky
40c2f2962c Try expanding 3.8 testing 2019-10-30 19:36:42 -04:00
rocky
dae195e36e Expand 3.8 testing 2019-10-30 19:11:19 -04:00
rocky
2c503d5a14 Bump xdis ...
to handle pypy3.6 from Python 2
2019-10-30 11:58:39 -04:00
rocky
eed4c1025b Pypy 3.6 tolerance 2019-10-30 11:44:04 -04:00
rocky
86c1d12e69 Pypy 3.6 tolerance 2019-10-29 18:12:06 -04:00
rocky
61a367b0ae Don't test 3.8 except on 3.8 for now 2019-10-29 13:46:04 -04:00
rocky
dba6d24361 3.8 for block without a POP_BLOCK ...
and confusing JUMP_BACK for CONTINUE. Expect more like this.

Fixes #293
2019-10-29 13:32:43 -04:00
R. Bernstein
0b111f1568 Merge pull request #263 from rocky/pypy3.6
pypy3.6 handling
2019-10-29 12:55:30 -04:00
rocky
c666e2dc3d Remove pypy 3.6 testing for now 2019-10-29 12:08:00 -04:00
rocky
0a5fcc51d8 Pypy 3.6 fixes and tests 2019-10-29 11:43:09 -04:00
rocky
ade9f7a182 Add Pypy 3.6 file for showing unmarshal problem 2019-10-28 20:58:42 -04:00
rocky
d41ef3e5dc Pypy 3.6 tolerance 2019-10-28 14:46:45 -04:00
rocky
ebb0342b38 WIP pypy3.6 handling 2019-10-28 13:20:51 -04:00
rocky
f17ebf42a9 Administrative kinds of changes 2019-10-28 13:17:10 -04:00
rocky
85dcce4ff2 Add twine check in release process 2019-10-19 12:33:29 -04:00
rocky
bc9a16eaac Correct version number in NEWS.md 2019-10-12 20:10:29 -04:00
rocky
d08d183fc8 bytecode 1.6 test omission 2019-10-12 19:58:01 -04:00
rocky
0b3d6b8add Get ready for release 3.5.0 2019-10-12 19:53:17 -04:00
rocky
5cb46c2ed3 Better simpler fragment fix...
remove hide_internal test. We changed the default and that's what
whas causing RETURN_LAST to not get included.
2019-10-12 17:55:52 -04:00
rocky
163e47fb49 Fragment fixes (and workarounds)
fragments.py: add more parent offsets. blacken buffer
parser3.py: additional grammar rules for fragment parser

Misc small typos and corrections
2019-10-12 12:22:27 -04:00
rocky
0cf32f1b70 Better 1.5 parameter tuple handling...
Tidy README.rst
2019-10-10 17:20:00 -04:00
rocky
f0f9676f52 update news 2019-10-02 13:50:02 -04:00
rocky
be610aa6b3 Bump min xdis version...
And testing versions
2019-10-02 13:46:56 -04:00
rocky
1494bb2049 Bump test python versions 2019-10-02 10:59:59 -04:00
rocky
d62dc3daac Get ready for release 3.4.1 2019-10-02 10:45:01 -04:00
rocky
5ad51707e3 Wasn't handling 3-arg %p in fragments.py...
and also fielding errors in code_deparse()
2019-10-02 10:29:49 -04:00
rocky
f28c255804 Add downloads per month 2019-09-25 16:00:57 -04:00
rocky
315965300f Note assert{,2}not is transformation only 2019-09-23 08:32:46 -04:00
rocky
9bd85fe5a0 Correct assert{,2} transforms
Fixes #289
2019-09-23 08:26:16 -04:00
129 changed files with 6501 additions and 1248 deletions

View File

@@ -1,11 +1,3 @@
# This configuration was automatically generated from a CircleCI 1.0 config.
# It should include any build commands you had along with commands that CircleCI
# inferred from your project structure. We strongly recommend you read all the
# comments in this file to understand the structure of CircleCI 2.0, as the idiom
# for configuration has changed substantially in 2.0 to allow arbitrary jobs rather
# than the prescribed lifecycle of 1.0. In general, we recommend using this generated
# configuration as a reference rather than using it in production, though in most
# cases it should duplicate the execution of your original 1.0 config.
version: 2
jobs:
build:

1
.gitignore vendored
View File

@@ -6,6 +6,7 @@
/.eggs
/.hypothesis
/.idea
/.mypy_cache
/.pytest_cache
/.python-version
/.tox

View File

@@ -5,6 +5,7 @@ python:
- '2.7'
- '3.4'
- '3.6'
- '3.8'
matrix:
include:

View File

@@ -47,8 +47,12 @@ check-3.8:
# Skip for now
2.6 5.0 5.3 5.6 5.8:
#:PyPy pypy3-2.4.0 Python 3:
pypy-3.2 2.4:
#:PyPy pypy3-2.4.0 Python 3.6.1:
7.1 pypy-3.2 2.4:
$(MAKE) -C test $@
#:PyPy pypy3-2.4.0 Python 3.6.9:
7.2:
$(MAKE) -C test $@
#: Run py.test tests

51
NEWS.md
View File

@@ -1,3 +1,54 @@
3.6.0: 2019-12-10 gecko gecko
=============================
The main focus in this release was more accurate decompilation especially
for 3.7 and 3.8. However there are some improvments to Python 2.x as well,
including one of the long-standing problems of detecting the difference between
`try ... ` and `try else ...`.
With this release we now rebase Python 3.7 on off of a 3.7 base; This
is also as it is (now) in decompyle3. This facilitates removing some of the
cruft in control-flow detection in the 2.7 uncompyle2 base.
Alas, decompilation speed for 3.7 on is greatly increased. Hopefull
this is temporary (cough, cough) until we can do a static control flow
pass.
Finally, runing in 3.9-dev is tolerated. We can disassemble, but no parse tables yet.
3.5.1 2019-11-17 JNC
====================
- Pypy 3.3, 3.5, 3.6, and 3.6.9 support
- bump xdis version to handle newer Python releases, e.g. 2.7.17, 3.5.8, and 3.5.9
- Improve 3.0 decompilation
- no parse errors on stlib bytecode. However accurate translation in
control-flow and and/or detection needs work
- Remove extraneous iter() in "for" of list comprehension Fixes #272
- "for" block without a `POP_BLOCK `and confusing `JUMP_BACK` for `CONTINUE`. Fixes #293
- Fix unmarshal incompletness detected in Pypy 3.6
- Miscellaneous bugs fixed
3.5.0 2019-10-12 Stony Brook Ride
=================================
- Fix fragment bugs
* missing `RETURN_LAST` introduced when adding transformation layer
* more parent entries on tokens
- Preliminary support for decompiling Python 1.0, 1.1, 1.2, and 1.6
* Newer _xdis_ version needed
3.4.1 2019-10-02
================
- Correct assert{,2} transforms Fixes #289
- Fragment parsing fixes:
* Wasn't handling 3-arg `%p`
* fielding error in `code_deparse()`
- Use newer _xdis_ to better track Python 3.8.0
3.4.0 2019-08-24 Totoro
=======================

View File

@@ -1,4 +1,4 @@
|buildstatus| |Latest Version| |Supported Python Versions|
|buildstatus| |Pypi Installs| |Latest Version| |Supported Python Versions|
|packagestatus|
@@ -13,9 +13,9 @@ Introduction
------------
*uncompyle6* translates Python bytecode back into equivalent Python
source code. It accepts bytecodes from Python version 1.3 to version
source code. It accepts bytecodes from Python version 1.0 to version
3.8, spanning over 24 years of Python releases. We include Dropbox's
Python 2.5 bytecode and some PyPy bytecode.
Python 2.5 bytecode and some PyPy bytecodes.
Why this?
---------
@@ -46,14 +46,15 @@ not exist and there is just bytecode. Again, my debuggers make use of
this.
There were (and still are) a number of decompyle, uncompyle,
uncompyle2, uncompyle3 forks around. Almost all of them come basically
from the same code base, and (almost?) all of them are no longer
actively maintained. One was really good at decompiling Python 1.5-2.3
or so, another really good at Python 2.7, but that only. Another
handles Python 3.2 only; another patched that and handled only 3.3.
You get the idea. This code pulls all of these forks together and
*moves forward*. There is some serious refactoring and cleanup in this
code base over those old forks.
uncompyle2, uncompyle3 forks around. Many of them come basically from
the same code base, and (almost?) all of them are no longer actively
maintained. One was really good at decompiling Python 1.5-2.3, another
really good at Python 2.7, but that only. Another handles Python 3.2
only; another patched that and handled only 3.3. You get the
idea. This code pulls all of these forks together and *moves
forward*. There is some serious refactoring and cleanup in this code
base over those old forks. Even more experimental refactoring is going
on in decompile3_.
This demonstrably does the best in decompiling Python across all
Python versions. And even when there is another project that only
@@ -75,11 +76,11 @@ fixed in the other decompilers.
Requirements
------------
The code here can be run on Python versions 2.6 or later, PyPy 3-2.4,
or PyPy-5.0.1. Python versions 2.4-2.7 are supported in the
python-2.4 branch. The bytecode files it can read have been tested on
Python bytecodes from versions 1.4, 2.1-2.7, and 3.0-3.8 and the
above-mentioned PyPy versions.
The code here can be run on Python versions 2.6 or later, PyPy 3-2.4
and later. Python versions 2.4-2.7 are supported in the python-2.4
branch. The bytecode files it can read have been tested on Python
bytecodes from versions 1.4, 2.1-2.7, and 3.0-3.8 and later PyPy
versions.
Installation
------------
@@ -88,9 +89,9 @@ This uses setup.py, so it follows the standard Python routine:
::
pip install -e . # set up to run from source tree
# Or if you want to install instead
python setup.py install # may need sudo
$ pip install -e . # set up to run from source tree
# Or if you want to install instead
$ python setup.py install # may need sudo
A GNU makefile is also provided so :code:`make install` (possibly as root or
sudo) will do the steps above.
@@ -186,15 +187,21 @@ they had been rare. Perhaps to compensate for the additional
added. So in sum handling control flow by ad hoc means as is currently
done is worse.
Between Python 3.5, 3.6 and 3.7 there have been major changes to the
:code:`MAKE_FUNCTION` and :code:`CALL_FUNCTION` instructions.
Between Python 3.5, 3.6, 3.7 there have been major changes to the
:code:`MAKE_FUNCTION` and :code:`CALL_FUNCTION` instructions. Python
Python 3.8 removes :code:`SETUP_LOOP`, :code:`SETUP_EXCEPT`,
:code:`BREAK_LOOP`, and :code:`CONTINUE_LOOP`, instructions which may
make control-flow detection harder, lacking the more sophisticated
control-flow analysis that is planned. We'll see.
Currently not all Python magic numbers are supported. Specifically in
some versions of Python, notably Python 3.6, the magic number has
changes several times within a version.
**We support only released versions, not candidate versions.** Note however
that the magic of a released version is usually the same as the *last* candidate version prior to release.
**We support only released versions, not candidate versions.** Note
however that the magic of a released version is usually the same as
the *last* candidate version prior to release.
There are also customized Python interpreters, notably Dropbox,
which use their own magic and encrypt bytcode. With the exception of
@@ -216,7 +223,7 @@ There is lots to do, so please dig in and help.
See Also
--------
* https://github.com/zrax/pycdc : purports to support all versions of Python. It is written in C++ and is most accurate for Python versions around 2.7 and 3.3 when the code was more actively developed. Accuracy for more recent versions of Python 3 and early versions of Python are especially lacking. See its `issue tracker <https://github.com/zrax/pycdc/issues>`_ for details. Currently lightly maintained.
* https://github.com/rocky/python-decompile3 : Much smaller and more modern code, focusing on 3.7+. Changes in that will get migrated back ehre.
* https://code.google.com/archive/p/unpyc3/ : supports Python 3.2 only. The above projects use a different decompiling technique than what is used here. Currently unmaintained.
* https://github.com/figment/unpyc3/ : fork of above, but supports Python 3.3 only. Includes some fixes like supporting function annotations. Currently unmaintained.
* https://github.com/wibiti/uncompyle2 : supports Python 2.7 only, but does that fairly well. There are situations where :code:`uncompyle6` results are incorrect while :code:`uncompyle2` results are not, but more often uncompyle6 is correct when uncompyle2 is not. Because :code:`uncompyle6` adheres to accuracy over idiomatic Python, :code:`uncompyle2` can produce more natural-looking code when it is correct. Currently :code:`uncompyle2` is lightly maintained. See its issue `tracker <https://github.com/wibiti/uncompyle2/issues>`_ for more details
@@ -225,6 +232,7 @@ See Also
* https://github.com/rocky/python-xdis : Cross Python version disassembler
* https://github.com/rocky/python-xasm : Cross Python version assembler
* https://github.com/rocky/python-uncompyle6/wiki : Wiki Documents which describe the code and aspects of it in more detail
* https://github.com/zrax/pycdc : The README for this C++ code syas it aims to support all versions of Python. It is best for Python versions around 2.7 and 3.3 when the code was initially developed. Accuracy for current versions of Python3 and early versions of Python is lacking. Without major effort, it is unlikely it can be made to support current Python 3. See its `issue tracker <https://github.com/zrax/pycdc/issues>`_ for details. Currently lightly maintained.
.. _trepan: https://pypi.python.org/pypi/trepan2g
@@ -233,6 +241,7 @@ See Also
.. _debuggers: https://pypi.python.org/pypi/trepan3k
.. _remake: https://bashdb.sf.net/remake
.. _pycdc: https://github.com/zrax/pycdc
.. _decompile3: https://github.com/rocky/python-decompile3
.. _this: https://github.com/rocky/python-uncompyle6/wiki/Deparsing-technology-and-its-use-in-exact-location-reporting
.. |buildstatus| image:: https://travis-ci.org/rocky/python-uncompyle6.svg
:target: https://travis-ci.org/rocky/python-uncompyle6
@@ -244,3 +253,4 @@ See Also
.. |Supported Python Versions| image:: https://img.shields.io/pypi/pyversions/uncompyle6.svg
.. |Latest Version| image:: https://badge.fury.io/py/uncompyle6.svg
:target: https://badge.fury.io/py/uncompyle6
.. |Pypi Installs| image:: https://pepy.tech/badge/uncompyle6/month

View File

@@ -58,7 +58,7 @@ entry_points = {
]}
ftp_url = None
install_requires = ["spark-parser >= 1.8.9, < 1.9.0",
"xdis >= 4.0.3, < 4.1.0"]
"xdis >= 4.2.0, < 4.3.0"]
license = "GPL3"
mailing_list = "python-debugger@googlegroups.com"

View File

@@ -56,19 +56,21 @@
$ . ./admin-tools/make-dist-older.sh
$ git tag release-python-2.4-$VERSION
$ twine check dist/uncompyle6-$VERSION*
$ . ./admin-tools/make-dist-newer.sh
Goto https://github.com/rocky/python-uncompyle6/releases
$ twine check dist/uncompyle6-$VERSION*
# Upload single package and look at Rst Formating
$ twine check dist/uncompyle6-${VERSION}*
$ twine upload dist/uncompyle6-${VERSION}-py3.3.egg
# Upload rest of versions
$ twine upload dist/uncompyle6-${VERSION}*
Goto https://github.com/rocky/python-uncompyle6/releases
# Push tags:
$ git push --tags

View File

@@ -5,4 +5,4 @@ if [[ $0 == ${BASH_SOURCE[0]} ]] ; then
echo "This script should be *sourced* rather than run directly through bash"
exit 1
fi
export PYVERSIONS='3.6.8 3.7.3 2.6.9 3.3.7 2.7.16 3.2.6 3.1.5 3.4.8'
export PYVERSIONS='3.5.9 3.6.9 2.6.9 3.3.7 2.7.17 3.2.6 3.1.5 3.4.10 3.7.5'

View File

@@ -1,5 +1,5 @@
#!/bin/bash
PYTHON_VERSION=3.6.8
PYTHON_VERSION=3.7.5
# FIXME put some of the below in a common routine
function finish {

View File

@@ -1,69 +1,81 @@
import re
from uncompyle6 import PYTHON_VERSION, PYTHON3, IS_PYPY # , PYTHON_VERSION
from uncompyle6 import PYTHON_VERSION, PYTHON3, IS_PYPY # , PYTHON_VERSION
from uncompyle6.parser import get_python_parser, python_parser
from uncompyle6.scanner import get_scanner
def test_grammar():
def test_grammar():
def check_tokens(tokens, opcode_set):
remain_tokens = set(tokens) - opcode_set
remain_tokens = set([re.sub(r'_\d+$','', t) for t in remain_tokens])
remain_tokens = set([re.sub('_CONT$','', t) for t in remain_tokens])
remain_tokens = set([re.sub('LOAD_CODE$','', t) for t in remain_tokens])
remain_tokens = set([re.sub(r"_\d+$", "", t) for t in remain_tokens])
remain_tokens = set([re.sub("_CONT$", "", t) for t in remain_tokens])
remain_tokens = set([re.sub("LOAD_CODE$", "", 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.dump_grammar())
assert remain_tokens == set([]), "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, dup_rhs) = p.check_sets()
(lhs, rhs, tokens, right_recursive, dup_rhs) = p.check_sets()
# We have custom rules that create the below
expect_lhs = set(['pos_arg', 'attribute'])
expect_lhs = set(["pos_arg"])
if PYTHON_VERSION < 3.8:
expect_lhs.add('get_iter')
if PYTHON_VERSION < 3.7:
expect_lhs.add("attribute")
expect_lhs.add("get_iter")
else:
expect_lhs.add("async_with_as_stmt")
expect_lhs.add("async_with_stmt")
unused_rhs = set(['list', 'mkfunc',
'mklambda',
'unpack',])
unused_rhs = set(["list", "mkfunc", "mklambda", "unpack"])
expect_right_recursive = set([('designList',
('store', 'DUP_TOP', 'designList'))])
expect_right_recursive = set([("designList", ("store", "DUP_TOP", "designList"))])
if PYTHON_VERSION < 3.7:
unused_rhs.add('call')
if PYTHON_VERSION <= 3.7:
unused_rhs.add("call")
if PYTHON_VERSION > 2.6:
expect_lhs.add('kvlist')
expect_lhs.add('kv3')
unused_rhs.add('dict')
expect_lhs.add("kvlist")
expect_lhs.add("kv3")
unused_rhs.add("dict")
if PYTHON3:
expect_lhs.add('load_genexpr')
expect_lhs.add("load_genexpr")
unused_rhs = unused_rhs.union(set("""
unused_rhs = unused_rhs.union(
set(
"""
except_pop_except generator_exp
""".split()))
""".split()
)
)
if PYTHON_VERSION >= 3.0:
expect_lhs.add("annotate_arg")
expect_lhs.add("annotate_tuple")
unused_rhs.add("mkfunc_annotate")
if PYTHON_VERSION < 3.7:
expect_lhs.add("annotate_arg")
expect_lhs.add("annotate_tuple")
unused_rhs.add("mkfunc_annotate")
unused_rhs.add("dict_comp")
unused_rhs.add("classdefdeco1")
unused_rhs.add("tryelsestmtl")
if PYTHON_VERSION >= 3.5:
expect_right_recursive.add((('l_stmts',
('lastl_stmt', 'come_froms', 'l_stmts'))))
expect_right_recursive.add(
(("l_stmts", ("lastl_stmt", "come_froms", "l_stmts")))
)
pass
elif 3.0 < PYTHON_VERSION < 3.3:
expect_right_recursive.add((('l_stmts',
('lastl_stmt', 'COME_FROM', 'l_stmts'))))
expect_right_recursive.add(
(("l_stmts", ("lastl_stmt", "COME_FROM", "l_stmts")))
)
pass
pass
pass
else:
expect_lhs.add('kwarg')
expect_lhs.add("kwarg")
assert expect_lhs == set(lhs)
@@ -73,9 +85,16 @@ def test_grammar():
assert expect_right_recursive == right_recursive
expect_dup_rhs = frozenset([('COME_FROM',), ('CONTINUE',), ('JUMP_ABSOLUTE',),
('LOAD_CONST',),
('JUMP_BACK',), ('JUMP_FORWARD',)])
expect_dup_rhs = frozenset(
[
("COME_FROM",),
("CONTINUE",),
("JUMP_ABSOLUTE",),
("LOAD_CONST",),
("JUMP_BACK",),
("JUMP_FORWARD",),
]
)
reduced_dup_rhs = dict((k, dup_rhs[k]) for k in dup_rhs if k not in expect_dup_rhs)
for k in reduced_dup_rhs:
print(k, reduced_dup_rhs[k])
@@ -83,7 +102,7 @@ def test_grammar():
s = get_scanner(PYTHON_VERSION, IS_PYPY)
ignore_set = set(
"""
"""
JUMP_BACK CONTINUE
COME_FROM COME_FROM_EXCEPT
COME_FROM_EXCEPT_CLAUSE
@@ -92,22 +111,33 @@ def test_grammar():
LOAD_GENEXPR LOAD_ASSERT LOAD_SETCOMP LOAD_DICTCOMP LOAD_STR LOAD_CODE
LAMBDA_MARKER
RETURN_END_IF RETURN_END_IF_LAMBDA RETURN_VALUE_LAMBDA RETURN_LAST
""".split())
""".split()
)
if 2.6 <= PYTHON_VERSION <= 2.7:
opcode_set = set(s.opc.opname).union(ignore_set)
if PYTHON_VERSION == 2.6:
opcode_set.add("THEN")
check_tokens(tokens, opcode_set)
elif PYTHON_VERSION == 3.4:
ignore_set.add('LOAD_CLASSNAME')
ignore_set.add('STORE_LOCALS')
ignore_set.add("LOAD_CLASSNAME")
ignore_set.add("STORE_LOCALS")
opcode_set = set(s.opc.opname).union(ignore_set)
check_tokens(tokens, opcode_set)
def test_dup_rule():
import inspect
python_parser(PYTHON_VERSION, inspect.currentframe().f_code,
is_pypy=IS_PYPY,
parser_debug={
'dups': True, 'transition': False, 'reduce': False,
'rules': False, 'errorstack': None, 'context': True})
python_parser(
PYTHON_VERSION,
inspect.currentframe().f_code,
is_pypy=IS_PYPY,
parser_debug={
"dups": True,
"transition": False,
"reduce": False,
"rules": False,
"errorstack": None,
"context": True,
},
)

View File

@@ -4,8 +4,8 @@ import sys
"""Setup script for the 'uncompyle6' distribution."""
SYS_VERSION = sys.version_info[0:2]
if not ((2, 6) <= SYS_VERSION <= (3, 8)):
mess = "Python Release 2.6 .. 3.8 are supported in this code branch."
if not ((2, 6) <= SYS_VERSION <= (3, 9)):
mess = "Python Release 2.6 .. 3.9 are supported in this code branch."
if ((2, 4) <= SYS_VERSION <= (2, 7)):
mess += ("\nFor your Python, version %s, use the python-2.4 code/branch." %
sys.version[0:3])
@@ -32,6 +32,7 @@ setup(
install_requires = install_requires,
license = license,
long_description = long_description,
long_description_content_type = "text/x-rst",
name = modname,
packages = find_packages(),
py_modules = py_modules,

View File

@@ -1,5 +1,6 @@
PHONY=check clean dist distclean test test-unit test-functional rmChangeLog clean_pyc nosetests \
check-bytecode-1 check-bytecode-1.3 check-bytecode-1.4 check-bytecode-1.5 \
check-bytecode-1.0 check-bytecode-1.1 check-bytecode-1.2 check-bytecode-1.3 \
check-bytecode-1 check-bytecode-1.4 check-bytecode-1.5 check-bytecode-1.6 \
check-bytecode-2 check-bytecode-3 check-bytecode-3-short \
check-bytecode-2.2 check-byteocde-2.3 check-bytecode-2.4 \
check-short check-2.6 check-2.7 check-3.0 check-3.1 check-3.2 check-3.3 \
@@ -85,7 +86,7 @@ check-disasm:
$(PYTHON) dis-compare.py
#: Check deparsing bytecode 1.x only
check-bytecode-1: check-bytecode-1.4 check-bytecode-1.5
check-bytecode-1: check-bytecode-1.0 check-bytecode-1.1 check-bytecode-1.2 check-bytecode-1.3 check-bytecode-1.4 check-bytecode-1.5 check-bytecode-1.6
#: Check deparsing bytecode 2.x only
check-bytecode-2:
@@ -98,8 +99,8 @@ check-bytecode-3:
$(PYTHON) test_pythonlib.py --bytecode-3.0 \
--bytecode-3.1 --bytecode-3.2 --bytecode-3.3 \
--bytecode-3.4 --bytecode-3.5 --bytecode-3.6 \
--bytecode-3.7 --bytecode-3.8 \
--bytecode-pypy3.2
--bytecode-3.7 \
--bytecode-pypy3.2 --bytecode-pypy3.6 --bytecode-3.8
#: Check deparsing on selected bytecode 3.x
check-bytecode-3-short:
@@ -109,6 +110,7 @@ check-bytecode-3-short:
#: Check deparsing bytecode on all Python 2 and Python 3 versions
check-bytecode: check-bytecode-3
$(PYTHON) test_pythonlib.py \
--bytecode-1.0 --bytecode-1.1 --bytecode-1.2 \
--bytecode-1.3 --bytecode-1.4 --bytecode-1.5 \
--bytecode-2.2 --bytecode-2.3 --bytecode-2.4 \
--bytecode-2.1 --bytecode-2.2 --bytecode-2.3 --bytecode-2.4 \
@@ -122,6 +124,18 @@ check-bytecode-short: check-bytecode-3-short
--bytecode-2.6 --bytecode-2.7 --bytecode-pypy2.7
#: Check deparsing bytecode 1.0 only
check-bytecode-1.0:
$(PYTHON) test_pythonlib.py --bytecode-1.0
#: Check deparsing bytecode 1.1 only
check-bytecode-1.1:
$(PYTHON) test_pythonlib.py --bytecode-1.1
#: Check deparsing bytecode 1.2 only
check-bytecode-1.2:
$(PYTHON) test_pythonlib.py --bytecode-1.2
#: Check deparsing bytecode 1.3 only
check-bytecode-1.3:
$(PYTHON) test_pythonlib.py --bytecode-1.3
@@ -134,6 +148,10 @@ check-bytecode-1.4:
check-bytecode-1.5:
$(PYTHON) test_pythonlib.py --bytecode-1.5
#: Check deparsing bytecode 1.6 only
check-bytecode-1.6:
$(PYTHON) test_pythonlib.py --bytecode-1.6
#: Check deparsing Python 2.1
check-bytecode-2.1:
$(PYTHON) test_pythonlib.py --bytecode-2.1
@@ -314,8 +332,16 @@ pypy-2.7 5.0 5.3 6.0:
pypy-3.2 2.4:
$(PYTHON) test_pythonlib.py --bytecode-pypy3.2 --verify
#: PyPy 5.0.x with Python 3.6 ...
#: PyPy 5.0.x with Python 3.6.1 ...
check-bytecode-pypy3.6: 7.1
7.1:
$(PYTHON) test_pythonlib.py --bytecode-pypy3.6-run --verify-run
$(PYTHON) test_pythonlib.py --bytecode-pypy3.6 --verify
#: PyPy 5.0.x with Python 3.6.9
check-bytecode-pypy3.6: 7.2
7.2:
$(PYTHON) test_pythonlib.py --bytecode-pypy3.6-run --verify-run
$(PYTHON) test_pythonlib.py --bytecode-pypy3.6 --verify

View File

@@ -2,22 +2,23 @@
""" Trivial helper program to bytecompile and run an uncompile
"""
import os, sys, py_compile
assert len(sys.argv) >= 2
version = sys.version[0:3]
if sys.argv[1] == '--run':
suffix = '_run'
if sys.argv[1] in ("--run", "-r"):
suffix = "_run"
py_source = sys.argv[2:]
else:
suffix = ''
suffix = ""
py_source = sys.argv[1:]
for path in py_source:
short = os.path.basename(path)
if hasattr(sys, 'pypy_version_info'):
cfile = "bytecode_pypy%s%s/%s" % (version, suffix, short) + 'c'
if hasattr(sys, "pypy_version_info"):
cfile = "bytecode_pypy%s%s/%s" % (version, suffix, short) + "c"
else:
cfile = "bytecode_%s%s/%s" % (version, suffix, short) + 'c'
cfile = "bytecode_%s%s/%s" % (version, suffix, short) + "c"
print("byte-compiling %s to %s" % (path, cfile))
py_compile.compile(path, cfile)
if isinstance(version, str) or version >= (2, 6, 0):
os.system("../bin/uncompyle6 -a -t %s" % cfile)
os.system("../bin/uncompyle6 -a -T %s" % cfile)

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

View File

@@ -14,4 +14,4 @@ for y in (1, 2, 10):
expected = 3
result.append(expected)
assert result == [10, 2, 3]
assert result == [3, 2, 3]

View File

@@ -7,3 +7,13 @@ def start_new_thread(function, args, kwargs={}):
pass
except:
args()
# Adapted from 3.0.1 code.py
# Bug is again JUMP_FORWARD elimination compared
# to earlier and later Pythons.
def interact():
while 1:
try:
more = 1
except KeyboardInterrupt:
more = 0

View File

@@ -7,3 +7,8 @@ while 1:
raise RuntimeError
else:
raise RuntimeError
# Adapted from 3.0.1 cgi.py
def _parseparam(s, end):
while end > 0 and s.count(''):
end = s.find(';')

View File

@@ -0,0 +1,50 @@
# Adapted from 3.0 base64
# Problem was handling if/else which
# needs to be like Python 2.6 (and not like 2.7 or 3.1)
def main(args, f, func, sys):
"""Small main program"""
if args and args[0] != '-':
func(f, sys.stdout.buffer)
else:
func(sys.stdin.buffer, sys.stdout.buffer)
# From Python 3.0 _markupbase.py.
#
# The Problem was in the way "if"s are generated in 3.0 which is sort
# of like a more optimized Python 2.6, with reduced extraneous jumps,
# but still 2.6-ish and not 2.7- or 3.1-ish.
def parse_marked_section(fn, i, rawdata, report=1):
if report:
j = 1
fn(rawdata[i: j])
return 10
# From 3.0.1 _abcoll.py
# Bug was in genexpr_func which doesn't have a JUMP_BACK but
# in its gen_comp_body, we can use COME_FROM in its place.
# As above omission of JUMPs is a feature of 3.0 that doesn't
# seem to be in later versions (or earlier like 2.6).
def __and__(self, other, Iterable):
if not isinstance(other, Iterable):
return NotImplemented
return self._from_iterable(value for value in other if value in self)
# Adapted from 3.0.1 abc.py
# Bug was in handling multiple COME_FROMs in return_if_stmt
def __instancecheck__(subtype, subclass, cls):
if subtype:
if (cls and subclass):
return False
# Adapted from 3.0.1 abc.py
# Bug was rule in "jump_absolute_else" and disallowing
# "else" to the wrong place.
def _strptime(locale_time, found_zone, time):
for tz_values in locale_time:
if found_zone:
if (time and found_zone):
break
else:
break

View File

@@ -18,3 +18,13 @@ assert normpath(['.']) == []
assert normpath(['a', 'b', '..']) == ['a']
assert normpath(['a', 'b', '', 'c']) == ['a', 'b', 'c']
assert normpath(['a', 'b', '.', '', 'c', '..']) == ['a', 'b']
# Adapted from 3.0.1 cgi.py
# Bug was in detecting "or" and "and" due to lack of PUSH/POP_IF instructions.
def handle(format, html, text):
formatter = (format and html) or text
return formatter
assert handle(False, False, True)
assert not handle(True, False, False)
assert handle(True, True, False)

View File

@@ -0,0 +1,8 @@
# Self-checking test.
# Bug was in if transform not inverting expression
# This file is RUNNABLE!
def test_assert2(c):
if c < 2:
raise SyntaxError('Oops')
test_assert2(5)

View File

@@ -0,0 +1,24 @@
# From decompyle3/semantics/customize3.py
# The bug is handling "for" loop inside the
# chained compare ifelse
def n_classdef3(a, b, c, l):
r = 1
if 3.0 <= a <= 3.2:
for n in l:
if b:
break
elif c:
r = 2
pass
pass
else:
r = 3
pass
return r
assert n_classdef3(10, True, True, []) == 3
assert n_classdef3(0, False, True, []) == 3
assert n_classdef3(3.1, True, True, []) == 1
assert n_classdef3(3.1, True, False, [1]) == 1
assert n_classdef3(3.1, True, True, [2]) == 1
assert n_classdef3(3.1, False, True, [3]) == 2

View File

@@ -0,0 +1,7 @@
# Adapted from From 3.3 urllib/parse.py
qs = "https://travis-ci.org/rocky/python-uncompyle6/builds/605260823?utm_medium=notification&utm_source=email"
expect = ['https://travis-ci.org/rocky/python-uncompyle6/builds/605260823?utm_medium=notification', 'utm_source=email']
# Should visually see that we don't add an extra iter() which is not technically wrong, just
# unnecessary.
assert expect == [s2 for s1 in qs.split('&') for s2 in s1.split(';')]

View File

@@ -0,0 +1,5 @@
# Bug is turning a JUMP_BACK for a CONTINUE so for has no JUMP_BACK.
# Also there is no POP_BLOCK since there isn't anything in the loop.
# In the future when we have better control flow, we might redo all of this.
for i in range(2):
pass

View File

@@ -0,0 +1,5 @@
(x, y) = "foo", 0
if x := __name__:
y = 1
assert x == "__main__", "Walrus operator changes value"
assert y == 1, "Walrus operator branch taken"

View File

@@ -0,0 +1,17 @@
# from mult_by_const/instruction.py
# Bug in 3.8 was handling no JUMP_BACK in "for" loop. It is
# in the "if" instead
def instruction_sequence_value(instrs, a, b):
for instr in instrs:
if a:
a = 6
elif b:
return 0
pass
return a
assert instruction_sequence_value([], True, True) == 1
assert instruction_sequence_value([1], True, True) == 6
assert instruction_sequence_value([1], False, True) == 0
assert instruction_sequence_value([1], False, False) == False

View File

@@ -1,4 +1,4 @@
# Tests BINARY_TRUE_DIVIDE and INPLACE_TRUE_DIVIDE
from __future__ import division # needed on 2.6 and 2.7
from __future__ import division # needed on 2.2 .. 2.7
x = len(__file__) / 1
x /= 1

View File

@@ -0,0 +1,53 @@
# Covers a large number of operators
#
# This code is RUNNABLE!
import sys
PYTHON_VERSION = sys.version_info[0] + (sys.version_info[1] / 10.0)
assert PYTHON_VERSION >= 3.7
# some floats (from 01_float.py)
x = 1e300
assert 0.0 == x * 0
assert x * 1e300 == float("inf")
assert str(float("inf") * 0.0) == "nan"
assert str(float("-inf") * 0.0) == "nan"
assert -1e300 * 1e300 == float("-inf")
# Complex (adapted from 02_complex.py)
y = 5j
assert y ** 2 == -25
y **= 3
assert y == (-0-125j)
# Tests BINARY_TRUE_DIVIDE and INPLACE_TRUE_DIVIDE (from 02_try_divide.py)
x = 2
assert 4 / x == 2
x = 5
assert x / 2 == 2.5
x = 3
x /= 2
assert x == 1.5
x = 2
assert 4 // x == 2
x = 7
x //= 2
assert x == 3
x = 3
assert x % 2 == 1
x %= 2
assert x == 1
assert x << 2 == 4
x <<= 3
assert x == 8
assert x >> 1 == 4
x >>= 1
assert x == 4

View File

@@ -0,0 +1,55 @@
# Covers a large number of operators
#
# This code is RUNNABLE!
from __future__ import division # needed on 2.2 .. 2.7
import sys
PYTHON_VERSION = sys.version_info[0] + (sys.version_info[1] / 10.0)
# some floats (from 01_float.py)
x = 1e300
assert 0.0 == x * 0
assert x * 1e300 == float("inf")
if PYTHON_VERSION > 2.41:
assert str(float("inf") * 0.0) == "nan"
else:
assert str(float("inf") * 0.0) == "-nan"
assert -1e300 * 1e300 == float("-inf")
# Complex (adapted from 02_complex.py)
y = 5j
assert y ** 2 == -25
y **= 3
assert y == (-0-125j)
# Tests BINARY_TRUE_DIVIDE and INPLACE_TRUE_DIVIDE (from 02_try_divide.py)
x = 2
assert 4 / x == 2
if PYTHON_VERSION >= 2.19:
x = 5
assert x / 2 == 2.5
x = 3
x /= 2
assert x == 1.5
x = 2
assert 4 // x == 2
x = 7
x //= 2
assert x == 3
x = 3
assert x % 2 == 1
x %= 2
assert x == 1
assert x << 2 == 4
x <<= 3
assert x == 8
assert x >> 1 == 4
x >>= 1
assert x == 4

View File

@@ -34,10 +34,17 @@ case $PYVERSION in
SKIP_TESTS=(
[test_dis.py]=1 # We change line numbers - duh!
[test_grp.py]=1 # Long test - might work Control flow?
[test_pwd.py]=1 # Long test - might work? Control flow?
[test_pep247.py]=1 # Long test - might work? Control flow?
[test_pwd.py]=1 # Long test - might work? Control flow?
[test_pyclbr.py]=1 # Investigate
[test_pyexpat.py]=1 # Investigate
[test_queue.py]=1 # Control flow?
# [test_threading.py]=1 # Long test - works
[test_re.py]=1 # try confused with try-else again
[test_socketserver.py]=1 # -- test takes too long to run: 40 seconds
[test_threading.py]=1 # Line numbers are expected to be different
[test_thread.py]=1 # test takes too long to run: 36 seconds
[test_trace.py]=1 # Long test - works
[test_zipfile64.py]=1 # Runs ok but takes 204 seconds
)
;;
2.5)
@@ -47,53 +54,35 @@ case $PYVERSION in
[test_grammar.py]=1 # Too many stmts. Handle large stmts
[test_grp.py]=1 # Long test - might work Control flow?
[test_pdb.py]=1 # Line-number specific
[test_pep247.py]=1 # "assert xxx or .." not detected properly in check_hash_module()
[test_pep352.py]=1 # Investigate
[test_pwd.py]=1 # Long test - might work? Control flow?
[test_pyclbr.py]=1 # Investigate
[test_queue.py]=1 # Control flow?
[test_re.py]=1 # Probably Control flow?
[test_re.py]=1 # Possibly try confused with try-else again
[test_struct.py]=1 # "if and" confused for if .. assert and
[test_sys.py]=1 # try confused with try-else again; in test_current_frames()
[test_tarfile.py]=1 # try confused with try-else again; top-level import
[test_threading.py]=1 # Line numbers are expected to be different
[test_thread.py]=1 # test takes too long to run: 36 seconds
[test_trace.py]=1 # Line numbers are expected to be different
[test_zipfile64.py]=1 # Runs ok but takes 204 seconds
)
;;
2.6)
SKIP_TESTS=(
[test_aepack.py]=1
[test_aifc.py]=1
[test_array.py]=1
[test_audioop.py]=1
[test_base64.py]=1
[test_bigmem.py]=1
[test_binascii.py]=1
[test_builtin.py]=1
[test_bytes.py]=1
[test_class.py]=1
[test_codeccallbacks.py]=1
[test_codecencodings_cn.py]=1
[test_codecencodings_hk.py]=1
[test_codecencodings_jp.py]=1
[test_codecencodings_kr.py]=1
[test_codecencodings_tw.py]=1
[test_codecencodings_cn.py]=1
[test_codecmaps_hk.py]=1
[test_codecmaps_jp.py]=1
[test_codecmaps_kr.py]=1
[test_codecmaps_tw.py]=1
[test_codecs.py]=1
[test_aepack.py]=1 # Fails on its own
[test_codeccallbacks.py]=1 # Fails on its own
[test_compile.py]=1 # Intermittent - sometimes works and sometimes doesn't
[test_cookielib.py]=1
[test_copy.py]=1
[test_decimal.py]=1
[test_descr.py]=1 # Problem in pickle.py?
[test_exceptions.py]=1
[test_extcall.py]=1
[test_float.py]=1
[test_future4.py]=1
[test_generators.py]=1
[test_generators.py]=1 # Investigate
[test_grp.py]=1 # Long test - might work Control flow?
[test_opcodes.py]=1
[test_pep352.py]=1 # Investigate
[test_pprint.py]=1
[test_pyclbr.py]=1 # Investigate
[test_pwd.py]=1 # Long test - might work? Control flow?
[test_re.py]=1 # Probably Control flow?
[test_queue.py]=1 # Control flow?
[test_trace.py]=1 # Line numbers are expected to be different
[test_urllib2net.py]=1 # Fails on its own. May need interactive input
[test_zipfile64.py]=1 # Skip Long test
[test_zlib.py]=1 # Takes too long to run (more than 3 minutes 39 seconds)
# .pyenv/versions/2.6.9/lib/python2.6/lib2to3/refactor.pyc
@@ -105,8 +94,6 @@ case $PYVERSION in
# .pyenv/versions/2.6.9/lib/python2.6/tabnanny.pyc
# .pyenv/versions/2.6.9/lib/python2.6/tarfile.pyc
# Not getting set by bach below?
[test_pprint.py]=1
)
if (( batch )) ; then
@@ -133,41 +120,36 @@ case $PYVERSION in
[test_capi.py]=1
[test_curses.py]=1 # Possibly fails on its own but not detected
[test test_cmd_line.py]=1 # Takes too long, maybe hangs, or looking for interactive input?
[test_dis.py]=1 # We change line numbers - duh!
[test_doctest.py]=1 # Fails on its own
[test_exceptions.py]=1
[test_format.py]=1 # control flow. uncompyle2 does not have problems here
[test_generators.py]=1 # control flow. uncompyle2 has problem here too
[test_grammar.py]=1 # Too many stmts. Handle large stmts
[test_grp.py]=1 # test takes to long, works interactively though
[test_hashlib.py]=1 # Investigate
[test_io.py]=1 # Test takes too long to run
[test_ioctl.py]=1 # Test takes too long to run
[test_itertools.py]=1 # Fix erroneous reduction to "conditional_true".
# See test/simple_source/bug27+/05_not_unconditional.py
[test_long.py]=1
[test_long_future.py]=1
[test_math.py]=1
[test_memoryio.py]=1 # FIX
[test_multiprocessing.py]=1 # On uncompyle2, taks 24 secs
[test_pep352.py]=1 # ?
[test_posix.py]=1 # Bug in try-else detection inside test_initgroups()
# Deal with when we have better flow-control detection
[test_modulefinder.py]=1 # FIX
[test_multiprocessing.py]=1 # On uncompyle2, takes 24 secs
[test_pwd.py]=1 # Takes too long
[test_pty.py]=1
[test_queue.py]=1 # Control flow?
[test_re.py]=1 # Probably Control flow?
[test_runpy.py]=1 # Long and fails on its own
[test_select.py]=1 # Runs okay but takes 11 seconds
[test_socket.py]=1 # Runs ok but takes 22 seconds
[test_subprocess.py]=1 # Runs ok but takes 22 seconds
[test_sys_setprofile.py]=1
[test_sys_settrace.py]=1 # Line numbers are expected to be different
[test_strtod.py]=1 # FIX
[test_traceback.py]=1 # Line numbers change - duh.
[test_types.py]=1 # try/else confusions
[test_unicode.py]=1 # Too long to run 11 seconds
[test_xpickle.py]=1 # Runs ok but takes 72 seconds
[test_zipfile64.py]=1 # Runs ok but takes 204 seconds
[test_zipimport.py]=1 # We can't distinguish try from try/else yet
[test_zipimport.py]=1 # FIXME: improper try from try/else ?
)
if (( batch )) ; then
# Fails in crontab environment?

View File

@@ -43,6 +43,9 @@ TEST_VERSIONS = (
"pypy3.5-5.7.1-beta",
"pypy3.5-5.9.0",
"pypy3.5-6.0.0",
"pypy3.6-7.1.0",
"pypy3.6-7.1.1",
"pypy3.6-7.2.0",
"native",
) + tuple(python_versions)
@@ -77,6 +80,9 @@ for vers in TEST_VERSIONS:
else:
if vers == "native":
short_vers = os.path.basename(sys.path[-1])
from xdis import PYTHON_VERSION
if PYTHON_VERSION > 3.0:
PYC = "*.cpython-%d.pyc" % int(PYTHON_VERSION * 10)
test_options[vers] = (sys.path[-1], PYC, short_vers)
else:
short_vers = vers[:3]

View File

@@ -77,9 +77,13 @@ for vers in (2.7, 3.4, 3.5, 3.6):
pass
for vers in (
1.0,
1.1,
1.2,
1.3,
1.4,
1.5,
1.6,
2.1,
2.2,
2.3,

View File

@@ -34,12 +34,11 @@ from __future__ import print_function
import sys
from collections import deque
import uncompyle6
from xdis.code import iscode
from xdis.load import check_object_path, load_module
from uncompyle6.scanner import get_scanner
def disco(version, co, out=None, is_pypy=False):
"""
diassembles and deparses a given code block 'co'
@@ -49,10 +48,9 @@ def disco(version, co, out=None, is_pypy=False):
# store final output stream for case of error
real_out = out or sys.stdout
print('# Python %s' % version, file=real_out)
print("# Python %s" % version, file=real_out)
if co.co_filename:
print('# Embedded file name: %s' % co.co_filename,
file=real_out)
print("# Embedded file name: %s" % co.co_filename, file=real_out)
scanner = get_scanner(version, is_pypy=is_pypy)
@@ -63,10 +61,12 @@ def disco(version, co, out=None, is_pypy=False):
def disco_loop(disasm, queue, real_out):
while len(queue) > 0:
co = queue.popleft()
if co.co_name != '<module>':
print('\n# %s line %d of %s' %
(co.co_name, co.co_firstlineno, co.co_filename),
file=real_out)
if co.co_name != "<module>":
print(
"\n# %s line %d of %s"
% (co.co_name, co.co_firstlineno, co.co_filename),
file=real_out,
)
tokens, customize = disasm(co)
for t in tokens:
if iscode(t.pattr):
@@ -77,6 +77,7 @@ def disco_loop(disasm, queue, real_out):
pass
pass
# def disassemble_fp(fp, outstream=None):
# """
# disassemble Python byte-code from an open file
@@ -90,6 +91,7 @@ def disco_loop(disasm, queue, real_out):
# disco(version, co, outstream, is_pypy=is_pypy)
# co = None
def disassemble_file(filename, outstream=None):
"""
disassemble Python byte-code file (.pyc)
@@ -98,8 +100,7 @@ def disassemble_file(filename, outstream=None):
try to find the corresponding compiled object.
"""
filename = check_object_path(filename)
(version, timestamp, magic_int, co, is_pypy,
source_size) = load_module(filename)
(version, timestamp, magic_int, co, is_pypy, source_size) = load_module(filename)
if type(co) == list:
for con in co:
disco(version, con, outstream)
@@ -107,6 +108,7 @@ def disassemble_file(filename, outstream=None):
disco(version, co, outstream, is_pypy=is_pypy)
co = None
def _test():
"""Simple test program to disassemble a file."""
argc = len(sys.argv)

View File

@@ -628,12 +628,30 @@ def get_python_parser(
if version < 3.0:
if version < 2.2:
if version == 1.0:
import uncompyle6.parsers.parse10 as parse10
if compile_mode == 'exec':
p = parse10.Python10Parser(debug_parser)
else:
p = parse10.Python01ParserSingle(debug_parser)
elif version == 1.1:
import uncompyle6.parsers.parse11 as parse11
if compile_mode == 'exec':
p = parse11.Python11Parser(debug_parser)
else:
p = parse11.Python11ParserSingle(debug_parser)
if version == 1.2:
import uncompyle6.parsers.parse12 as parse12
if compile_mode == 'exec':
p = parse12.Python12Parser(debug_parser)
else:
p = parse12.Python12ParserSingle(debug_parser)
if version == 1.3:
import uncompyle6.parsers.parse13 as parse13
if compile_mode == 'exec':
p = parse13.Python14Parser(debug_parser)
p = parse13.Python13Parser(debug_parser)
else:
p = parse13.Python14ParserSingle(debug_parser)
p = parse13.Python13ParserSingle(debug_parser)
elif version == 1.4:
import uncompyle6.parsers.parse14 as parse14
if compile_mode == 'exec':
@@ -646,6 +664,12 @@ def get_python_parser(
p = parse15.Python15Parser(debug_parser)
else:
p = parse15.Python15ParserSingle(debug_parser)
elif version == 1.6:
import uncompyle6.parsers.parse16 as parse16
if compile_mode == 'exec':
p = parse16.Python16Parser(debug_parser)
else:
p = parse16.Python16ParserSingle(debug_parser)
elif version == 2.1:
import uncompyle6.parsers.parse21 as parse21
if compile_mode == 'exec':

View File

@@ -0,0 +1,25 @@
# Copyright (c) 2019 Rocky Bernstein
from spark_parser import DEFAULT_DEBUG as PARSER_DEFAULT_DEBUG
from uncompyle6.parser import PythonParserSingle
from uncompyle6.parsers.parse11 import Python11Parser
class Python10Parser(Python11Parser):
def __init__(self, debug_parser=PARSER_DEFAULT_DEBUG):
super(Python11Parser, self).__init__(debug_parser)
self.customized = {}
class Python10ParserSingle(Python10Parser, PythonParserSingle):
pass
if __name__ == "__main__":
# Check grammar
p = Python10Parser()
p.check_grammar()
p.dump_grammar()
# local variables:
# tab-width: 4

View File

@@ -0,0 +1,25 @@
# Copyright (c) 2019 Rocky Bernstein
from spark_parser import DEFAULT_DEBUG as PARSER_DEFAULT_DEBUG
from uncompyle6.parser import PythonParserSingle
from uncompyle6.parsers.parse12 import Python12Parser
class Python11Parser(Python12Parser):
def __init__(self, debug_parser=PARSER_DEFAULT_DEBUG):
super(Python12Parser, self).__init__(debug_parser)
self.customized = {}
class Python11ParserSingle(Python11Parser, PythonParserSingle):
pass
if __name__ == "__main__":
# Check grammar
p = Python12Parser()
p.check_grammar()
p.dump_grammar()
# local variables:
# tab-width: 4

View File

@@ -0,0 +1,25 @@
# Copyright (c) 2019 Rocky Bernstein
from spark_parser import DEFAULT_DEBUG as PARSER_DEFAULT_DEBUG
from uncompyle6.parser import PythonParserSingle
from uncompyle6.parsers.parse13 import Python13Parser
class Python12Parser(Python13Parser):
def __init__(self, debug_parser=PARSER_DEFAULT_DEBUG):
super(Python12Parser, self).__init__(debug_parser)
self.customized = {}
class Python12ParserSingle(Python12Parser, PythonParserSingle):
pass
if __name__ == "__main__":
# Check grammar
p = Python12Parser()
p.check_grammar()
p.dump_grammar()
# local variables:
# tab-width: 4

View File

@@ -0,0 +1,46 @@
# Copyright (c) 2019 Rocky Bernstein
from spark_parser import DEFAULT_DEBUG as PARSER_DEFAULT_DEBUG
from uncompyle6.parser import PythonParserSingle, nop_func
from uncompyle6.parsers.parse21 import Python21Parser
class Python16Parser(Python21Parser):
def __init__(self, debug_parser=PARSER_DEFAULT_DEBUG):
super(Python16Parser, self).__init__(debug_parser)
self.customized = {}
def p_import16(self, args):
"""
import ::= filler IMPORT_NAME STORE_FAST
import ::= filler IMPORT_NAME STORE_NAME
import_from ::= filler IMPORT_NAME importlist
import_from ::= filler filler IMPORT_NAME importlist POP_TOP
importlist ::= importlist IMPORT_FROM
importlist ::= IMPORT_FROM
"""
def customize_grammar_rules(self, tokens, customize):
super(Python16Parser, self).customize_grammar_rules(tokens, customize)
for i, token in enumerate(tokens):
opname = token.kind
opname_base = opname[:opname.rfind('_')]
if opname_base == 'UNPACK_LIST':
self.addRule("store ::= unpack_list", nop_func)
class Python16ParserSingle(Python16Parser, PythonParserSingle):
pass
if __name__ == '__main__':
# Check grammar
p = Python15Parser()
p.check_grammar()
p.dump_grammar()
# local variables:
# tab-width: 4

View File

@@ -1,4 +1,4 @@
# Copyright (c) 2015-2018 Rocky Bernstein
# Copyright (c) 2015-2019 Rocky Bernstein
# Copyright (c) 2000-2002 by hartmut Goebel <h.goebel@crazy-compilers.com>
#
# Copyright (c) 1999 John Aycock
@@ -31,10 +31,10 @@ from uncompyle6.parser import PythonParser, PythonParserSingle, nop_func
from uncompyle6.parsers.treenode import SyntaxTree
from spark_parser import DEFAULT_DEBUG as PARSER_DEFAULT_DEBUG
class Python2Parser(PythonParser):
class Python2Parser(PythonParser):
def __init__(self, debug_parser=PARSER_DEFAULT_DEBUG):
super(Python2Parser, self).__init__(SyntaxTree, 'stmts', debug=debug_parser)
super(Python2Parser, self).__init__(SyntaxTree, "stmts", debug=debug_parser)
self.new_rules = set()
def p_print2(self, args):
@@ -52,7 +52,7 @@ class Python2Parser(PythonParser):
"""
def p_print_to(self, args):
'''
"""
stmt ::= print_to
stmt ::= print_to_nl
stmt ::= print_nl_to
@@ -62,10 +62,10 @@ class Python2Parser(PythonParser):
print_to_items ::= print_to_items print_to_item
print_to_items ::= print_to_item
print_to_item ::= DUP_TOP expr ROT_TWO PRINT_ITEM_TO
'''
"""
def p_grammar(self, args):
'''
"""
sstmt ::= stmt
sstmt ::= return RETURN_LAST
@@ -176,12 +176,12 @@ class Python2Parser(PythonParser):
jmp_abs ::= JUMP_ABSOLUTE
jmp_abs ::= JUMP_BACK
jmp_abs ::= CONTINUE
'''
"""
def p_generator_exp2(self, args):
'''
"""
generator_exp ::= LOAD_GENEXPR MAKE_FUNCTION_0 expr GET_ITER CALL_FUNCTION_1
'''
"""
def p_expr2(self, args):
"""
@@ -252,25 +252,41 @@ class Python2Parser(PythonParser):
this.
"""
if 'PyPy' in customize:
if "PyPy" in customize:
# PyPy-specific customizations
self.addRule("""
self.addRule(
"""
stmt ::= assign3_pypy
stmt ::= assign2_pypy
assign3_pypy ::= expr expr expr store store store
assign2_pypy ::= expr expr store store
list_comp ::= expr BUILD_LIST_FROM_ARG for_iter store list_iter
JUMP_BACK
""", nop_func)
""",
nop_func,
)
# For a rough break out on the first word. This may
# include instructions that don't need customization,
# but we'll do a finer check after the rough breakout.
customize_instruction_basenames = frozenset(
('BUILD', 'CALL', 'CONTINUE', 'DELETE',
'DUP', 'EXEC', 'GET', 'JUMP',
'LOAD', 'LOOKUP', 'MAKE', 'SETUP',
'RAISE', 'UNPACK'))
(
"BUILD",
"CALL",
"CONTINUE",
"DELETE",
"DUP",
"EXEC",
"GET",
"JUMP",
"LOAD",
"LOOKUP",
"MAKE",
"SETUP",
"RAISE",
"UNPACK",
)
)
# Opcode names in the custom_seen_ops set have rules that get added
# unconditionally and the rules are constant. So they need to be done
@@ -284,139 +300,191 @@ class Python2Parser(PythonParser):
# Do a quick breakout before testing potentially
# each of the dozen or so instruction in if elif.
if (opname[:opname.find('_')] not in customize_instruction_basenames
or opname in custom_seen_ops):
if (
opname[: opname.find("_")] not in customize_instruction_basenames
or opname in custom_seen_ops
):
continue
opname_base = opname[:opname.rfind('_')]
opname_base = opname[: opname.rfind("_")]
# The order of opname listed is roughly sorted below
if opname_base in ('BUILD_LIST', 'BUILD_SET', 'BUILD_TUPLE'):
if opname_base in ("BUILD_LIST", "BUILD_SET", "BUILD_TUPLE"):
# We do this complicated test to speed up parsing of
# pathelogically long literals, especially those over 1024.
build_count = token.attr
thousands = (build_count//1024)
thirty32s = ((build_count//32) % 32)
thousands = build_count // 1024
thirty32s = (build_count // 32) % 32
if thirty32s > 0:
rule = "expr32 ::=%s" % (' expr' * 32)
rule = "expr32 ::=%s" % (" expr" * 32)
self.add_unique_rule(rule, opname_base, build_count, customize)
if thousands > 0:
self.add_unique_rule("expr1024 ::=%s" % (' expr32' * 32),
opname_base, build_count, customize)
collection = opname_base[opname_base.find('_')+1:].lower()
rule = (('%s ::= ' % collection) + 'expr1024 '*thousands +
'expr32 '*thirty32s + 'expr '*(build_count % 32) + opname)
self.add_unique_rules([
"expr ::= %s" % collection,
rule], customize)
self.add_unique_rule(
"expr1024 ::=%s" % (" expr32" * 32),
opname_base,
build_count,
customize,
)
collection = opname_base[opname_base.find("_") + 1 :].lower()
rule = (
("%s ::= " % collection)
+ "expr1024 " * thousands
+ "expr32 " * thirty32s
+ "expr " * (build_count % 32)
+ opname
)
self.add_unique_rules(["expr ::= %s" % collection, rule], customize)
continue
elif opname_base == 'BUILD_MAP':
if opname == 'BUILD_MAP_n':
elif opname_base == "BUILD_MAP":
if opname == "BUILD_MAP_n":
# PyPy sometimes has no count. Sigh.
self.add_unique_rules([
'kvlist_n ::= kvlist_n kv3',
'kvlist_n ::=',
'dict ::= BUILD_MAP_n kvlist_n',
], customize)
self.add_unique_rules(
[
"kvlist_n ::= kvlist_n kv3",
"kvlist_n ::=",
"dict ::= BUILD_MAP_n kvlist_n",
],
customize,
)
if self.version >= 2.7:
self.add_unique_rule(
'dict_comp_func ::= BUILD_MAP_n LOAD_FAST FOR_ITER store '
'comp_iter JUMP_BACK RETURN_VALUE RETURN_LAST',
'dict_comp_func', 0, customize)
"dict_comp_func ::= BUILD_MAP_n LOAD_FAST FOR_ITER store "
"comp_iter JUMP_BACK RETURN_VALUE RETURN_LAST",
"dict_comp_func",
0,
customize,
)
else:
kvlist_n = ' kv3' * token.attr
kvlist_n = " kv3" * token.attr
rule = "dict ::= %s%s" % (opname, kvlist_n)
self.addRule(rule, nop_func)
continue
elif opname_base == 'BUILD_SLICE':
slice_num = token.attr
elif opname_base == "BUILD_SLICE":
slice_num = token.attr
if slice_num == 2:
self.add_unique_rules([
'expr ::= build_slice2',
'build_slice2 ::= expr expr BUILD_SLICE_2'
], customize)
self.add_unique_rules(
[
"expr ::= build_slice2",
"build_slice2 ::= expr expr BUILD_SLICE_2",
],
customize,
)
else:
assert slice_num == 3, ("BUILD_SLICE value must be 2 or 3; is %s" %
slice_num)
self.add_unique_rules([
'expr ::= build_slice3',
'build_slice3 ::= expr expr expr BUILD_SLICE_3',
], customize)
assert slice_num == 3, (
"BUILD_SLICE value must be 2 or 3; is %s" % slice_num
)
self.add_unique_rules(
[
"expr ::= build_slice3",
"build_slice3 ::= expr expr expr BUILD_SLICE_3",
],
customize,
)
continue
elif opname_base in ('CALL_FUNCTION', 'CALL_FUNCTION_VAR',
'CALL_FUNCTION_VAR_KW', 'CALL_FUNCTION_KW'):
elif opname_base in (
"CALL_FUNCTION",
"CALL_FUNCTION_VAR",
"CALL_FUNCTION_VAR_KW",
"CALL_FUNCTION_KW",
):
args_pos, args_kw = self.get_pos_kw(token)
# number of apply equiv arguments:
nak = ( len(opname_base)-len('CALL_FUNCTION') ) // 3
rule = 'call ::= expr ' + 'expr '*args_pos + 'kwarg '*args_kw \
+ 'expr ' * nak + opname
elif opname_base == 'CALL_METHOD':
nak = (len(opname_base) - len("CALL_FUNCTION")) // 3
rule = (
"call ::= expr "
+ "expr " * args_pos
+ "kwarg " * args_kw
+ "expr " * nak
+ opname
)
elif opname_base == "CALL_METHOD":
# PyPy only - DRY with parse3
args_pos, args_kw = self.get_pos_kw(token)
# number of apply equiv arguments:
nak = ( len(opname_base)-len('CALL_METHOD') ) // 3
rule = 'call ::= expr ' + 'expr '*args_pos + 'kwarg '*args_kw \
+ 'expr ' * nak + opname
elif opname == 'CONTINUE_LOOP':
self.addRule('continue ::= CONTINUE_LOOP', nop_func)
nak = (len(opname_base) - len("CALL_METHOD")) // 3
rule = (
"call ::= expr "
+ "expr " * args_pos
+ "kwarg " * args_kw
+ "expr " * nak
+ opname
)
elif opname == "CONTINUE_LOOP":
self.addRule("continue ::= CONTINUE_LOOP", nop_func)
custom_seen_ops.add(opname)
continue
elif opname == 'DELETE_ATTR':
self.addRule('del_stmt ::= expr DELETE_ATTR', nop_func)
elif opname == "DELETE_ATTR":
self.addRule("del_stmt ::= expr DELETE_ATTR", nop_func)
custom_seen_ops.add(opname)
continue
elif opname.startswith('DELETE_SLICE'):
self.addRule("""
elif opname.startswith("DELETE_SLICE"):
self.addRule(
"""
del_expr ::= expr
del_stmt ::= del_expr DELETE_SLICE+0
del_stmt ::= del_expr del_expr DELETE_SLICE+1
del_stmt ::= del_expr del_expr DELETE_SLICE+2
del_stmt ::= del_expr del_expr del_expr DELETE_SLICE+3
""", nop_func)
""",
nop_func,
)
custom_seen_ops.add(opname)
self.check_reduce['del_expr'] = 'AST'
self.check_reduce["del_expr"] = "AST"
continue
elif opname == 'DELETE_DEREF':
self.addRule("""
elif opname == "DELETE_DEREF":
self.addRule(
"""
stmt ::= del_deref_stmt
del_deref_stmt ::= DELETE_DEREF
""", nop_func)
""",
nop_func,
)
custom_seen_ops.add(opname)
continue
elif opname == 'DELETE_SUBSCR':
self.addRule("""
elif opname == "DELETE_SUBSCR":
self.addRule(
"""
del_stmt ::= delete_subscript
delete_subscript ::= expr expr DELETE_SUBSCR
""", nop_func)
self.check_reduce['delete_subscript'] = 'AST'
""",
nop_func,
)
self.check_reduce["delete_subscript"] = "AST"
custom_seen_ops.add(opname)
continue
elif opname == 'GET_ITER':
self.addRule("""
elif opname == "GET_ITER":
self.addRule(
"""
expr ::= get_iter
attribute ::= expr GET_ITER
""", nop_func)
""",
nop_func,
)
custom_seen_ops.add(opname)
continue
elif opname_base in ('DUP_TOPX', 'RAISE_VARARGS'):
elif opname_base in ("DUP_TOPX", "RAISE_VARARGS"):
# FIXME: remove these conditions if they are not needed.
# no longer need to add a rule
continue
elif opname == 'EXEC_STMT':
self.addRule("""
elif opname == "EXEC_STMT":
self.addRule(
"""
stmt ::= exec_stmt
exec_stmt ::= expr exprlist DUP_TOP EXEC_STMT
exec_stmt ::= expr exprlist EXEC_STMT
exprlist ::= expr+
""", nop_func)
""",
nop_func,
)
continue
elif opname == 'JUMP_IF_NOT_DEBUG':
self.addRule("""
elif opname == "JUMP_IF_NOT_DEBUG":
self.addRule(
"""
jmp_true_false ::= POP_JUMP_IF_TRUE
jmp_true_false ::= POP_JUMP_IF_FALSE
stmt ::= assert_pypy
@@ -426,107 +494,155 @@ class Python2Parser(PythonParser):
assert2_pypy ::= JUMP_IF_NOT_DEBUG assert_expr jmp_true_false
LOAD_ASSERT expr CALL_FUNCTION_1
RAISE_VARARGS_1 COME_FROM
""", nop_func)
""",
nop_func,
)
continue
elif opname == 'LOAD_ATTR':
self.addRule("""
elif opname == "LOAD_ATTR":
self.addRule(
"""
expr ::= attribute
attribute ::= expr LOAD_ATTR
""", nop_func)
""",
nop_func,
)
custom_seen_ops.add(opname)
continue
elif opname == 'LOAD_LISTCOMP':
elif opname == "LOAD_LISTCOMP":
self.addRule("expr ::= listcomp", nop_func)
custom_seen_ops.add(opname)
continue
elif opname == 'LOAD_SETCOMP':
self.add_unique_rules([
"expr ::= set_comp",
"set_comp ::= LOAD_SETCOMP MAKE_FUNCTION_0 expr GET_ITER CALL_FUNCTION_1"
], customize)
elif opname == "LOAD_SETCOMP":
self.add_unique_rules(
[
"expr ::= set_comp",
"set_comp ::= LOAD_SETCOMP MAKE_FUNCTION_0 expr GET_ITER CALL_FUNCTION_1",
],
customize,
)
custom_seen_ops.add(opname)
continue
elif opname == 'LOOKUP_METHOD':
elif opname == "LOOKUP_METHOD":
# A PyPy speciality - DRY with parse3
self.addRule("""
self.addRule(
"""
expr ::= attribute
attribute ::= expr LOOKUP_METHOD
""",
nop_func)
nop_func,
)
custom_seen_ops.add(opname)
continue
elif opname_base == 'MAKE_FUNCTION':
if i > 0 and tokens[i-1] == 'LOAD_LAMBDA':
self.addRule('mklambda ::= %s LOAD_LAMBDA %s' %
('pos_arg ' * token.attr, opname), nop_func)
rule = 'mkfunc ::= %s LOAD_CODE %s' % ('expr ' * token.attr, opname)
elif opname_base == 'MAKE_CLOSURE':
elif opname_base == "MAKE_FUNCTION":
if i > 0 and tokens[i - 1] == "LOAD_LAMBDA":
self.addRule(
"mklambda ::= %s LOAD_LAMBDA %s"
% ("pos_arg " * token.attr, opname),
nop_func,
)
rule = "mkfunc ::= %s LOAD_CODE %s" % ("expr " * token.attr, opname)
elif opname_base == "MAKE_CLOSURE":
# FIXME: use add_unique_rules to tidy this up.
if i > 0 and tokens[i-1] == 'LOAD_LAMBDA':
self.addRule('mklambda ::= %s load_closure LOAD_LAMBDA %s' %
('expr ' * token.attr, opname), nop_func)
if i > 0 and tokens[i - 1] == "LOAD_LAMBDA":
self.addRule(
"mklambda ::= %s load_closure LOAD_LAMBDA %s"
% ("expr " * token.attr, opname),
nop_func,
)
if i > 0:
prev_tok = tokens[i-1]
if prev_tok == 'LOAD_GENEXPR':
self.add_unique_rules([
('generator_exp ::= %s load_closure LOAD_GENEXPR %s expr'
' GET_ITER CALL_FUNCTION_1' %
('expr ' * token.attr, opname))], customize)
prev_tok = tokens[i - 1]
if prev_tok == "LOAD_GENEXPR":
self.add_unique_rules(
[
(
"generator_exp ::= %s load_closure LOAD_GENEXPR %s expr"
" GET_ITER CALL_FUNCTION_1"
% ("expr " * token.attr, opname)
)
],
customize,
)
pass
self.add_unique_rules([
('mkfunc ::= %s load_closure LOAD_CODE %s' %
('expr ' * token.attr, opname))], customize)
self.add_unique_rules(
[
(
"mkfunc ::= %s load_closure LOAD_CODE %s"
% ("expr " * token.attr, opname)
)
],
customize,
)
if self.version >= 2.7:
if i > 0:
prev_tok = tokens[i-1]
if prev_tok == 'LOAD_DICTCOMP':
self.add_unique_rules([
('dict_comp ::= %s load_closure LOAD_DICTCOMP %s expr'
' GET_ITER CALL_FUNCTION_1' %
('expr ' * token.attr, opname))], customize)
elif prev_tok == 'LOAD_SETCOMP':
self.add_unique_rules([
"expr ::= set_comp",
('set_comp ::= %s load_closure LOAD_SETCOMP %s expr'
' GET_ITER CALL_FUNCTION_1' %
('expr ' * token.attr, opname))
], customize)
prev_tok = tokens[i - 1]
if prev_tok == "LOAD_DICTCOMP":
self.add_unique_rules(
[
(
"dict_comp ::= %s load_closure LOAD_DICTCOMP %s expr"
" GET_ITER CALL_FUNCTION_1"
% ("expr " * token.attr, opname)
)
],
customize,
)
elif prev_tok == "LOAD_SETCOMP":
self.add_unique_rules(
[
"expr ::= set_comp",
(
"set_comp ::= %s load_closure LOAD_SETCOMP %s expr"
" GET_ITER CALL_FUNCTION_1"
% ("expr " * token.attr, opname)
),
],
customize,
)
pass
pass
continue
elif opname == 'SETUP_EXCEPT':
if 'PyPy' in customize:
self.add_unique_rules([
"stmt ::= try_except_pypy",
"try_except_pypy ::= SETUP_EXCEPT suite_stmts_opt except_handler_pypy",
"except_handler_pypy ::= COME_FROM except_stmts END_FINALLY COME_FROM"
], customize)
elif opname == "SETUP_EXCEPT":
if "PyPy" in customize:
self.add_unique_rules(
[
"stmt ::= try_except_pypy",
"try_except_pypy ::= SETUP_EXCEPT suite_stmts_opt except_handler_pypy",
"except_handler_pypy ::= COME_FROM except_stmts END_FINALLY COME_FROM",
],
customize,
)
custom_seen_ops.add(opname)
continue
elif opname == 'SETUP_FINALLY':
if 'PyPy' in customize:
self.addRule("""
elif opname == "SETUP_FINALLY":
if "PyPy" in customize:
self.addRule(
"""
stmt ::= tryfinallystmt_pypy
tryfinallystmt_pypy ::= SETUP_FINALLY suite_stmts_opt COME_FROM_FINALLY
suite_stmts_opt END_FINALLY""", nop_func)
suite_stmts_opt END_FINALLY""",
nop_func,
)
custom_seen_ops.add(opname)
continue
elif opname_base in ('UNPACK_TUPLE', 'UNPACK_SEQUENCE'):
elif opname_base in ("UNPACK_TUPLE", "UNPACK_SEQUENCE"):
custom_seen_ops.add(opname)
rule = 'unpack ::= ' + opname + ' store' * token.attr
elif opname_base == 'UNPACK_LIST':
rule = "unpack ::= " + opname + " store" * token.attr
elif opname_base == "UNPACK_LIST":
custom_seen_ops.add(opname)
rule = 'unpack_list ::= ' + opname + ' store' * token.attr
rule = "unpack_list ::= " + opname + " store" * token.attr
else:
continue
self.addRule(rule, nop_func)
pass
self.check_reduce['raise_stmt1'] = 'tokens'
self.check_reduce['aug_assign2'] = 'AST'
self.check_reduce['or'] = 'AST'
self.check_reduce["raise_stmt1"] = "tokens"
self.check_reduce["assert_expr_and"] = "AST"
self.check_reduce["tryelsestmt"] = "AST"
self.check_reduce["tryelsestmtl"] = "AST"
self.check_reduce["aug_assign2"] = "AST"
self.check_reduce["or"] = "AST"
# self.check_reduce['_stmts'] = 'AST'
# Dead code testing...
@@ -541,24 +657,61 @@ class Python2Parser(PythonParser):
# Dead code testing...
# if lhs == 'while1elsestmt':
# from trepan.api import debug; debug()
if lhs in ('aug_assign1', 'aug_assign2') and ast[0] and ast[0][0] in ('and', 'or'):
if (
lhs in ("aug_assign1", "aug_assign2")
and ast[0]
and ast[0][0] in ("and", "or")
):
return True
elif lhs in ('raise_stmt1',):
elif lhs == "assert_expr_and":
jmp_false = ast[1]
jump_target = jmp_false[0].attr
return jump_target > tokens[last].off2int()
elif lhs in ("raise_stmt1",):
# We will assume 'LOAD_ASSERT' will be handled by an assert grammar rule
return (tokens[first] == 'LOAD_ASSERT' and (last >= len(tokens)))
elif rule == ('or', ('expr', 'jmp_true', 'expr', '\\e_come_from_opt')):
return tokens[first] == "LOAD_ASSERT" and (last >= len(tokens))
elif rule == ("or", ("expr", "jmp_true", "expr", "\\e_come_from_opt")):
expr2 = ast[2]
return expr2 == 'expr' and expr2[0] == 'LOAD_ASSERT'
elif lhs in ('delete_subscript', 'del_expr'):
return expr2 == "expr" and expr2[0] == "LOAD_ASSERT"
elif lhs in ("delete_subscript", "del_expr"):
op = ast[0][0]
return op.kind in ('and', 'or')
return op.kind in ("and", "or")
elif lhs in ("tryelsestmt", "tryelsestmtl"):
# Check the end of the except handler that there isn't a jump from
# inside the except handler to the end. If that happens
# then this is a "try" with no "else".
except_handler = ast[3]
if except_handler == "except_handler":
come_from = except_handler[-1]
# We only care about the *first* come_from because that is the
# the innermost one. So if the "tryelse" is invalid (should be a "try")
# ti will be invalid here.
if come_from == "COME_FROM":
first_come_from = except_handler[-1]
else:
assert come_from == "come_froms"
first_come_from = come_from[0]
leading_jump = except_handler[0]
# We really don't care that this is a jump per-se. But
# we could also check that this jumps to the end of the except if
# desired.
if isinstance(leading_jump, SyntaxTree):
except_handler_first_offset = leading_jump.first_child().off2int()
else:
except_handler_first_offset = leading_jump.off2int()
return first_come_from.attr > except_handler_first_offset
return False
class Python2ParserSingle(Python2Parser, PythonParserSingle):
pass
if __name__ == '__main__':
if __name__ == "__main__":
# Check grammar
p = Python2Parser()
p.check_grammar()

View File

@@ -25,11 +25,17 @@ class Python25Parser(Python26Parser):
setupwithas ::= DUP_TOP LOAD_ATTR store LOAD_ATTR CALL_FUNCTION_0
setup_finally
# opcode SETUP_WITH
setupwith ::= DUP_TOP LOAD_ATTR STORE_NAME LOAD_ATTR CALL_FUNCTION_0 POP_TOP
withstmt ::= expr setupwith SETUP_FINALLY suite_stmts_opt
POP_BLOCK LOAD_CONST COME_FROM with_cleanup
setupwith ::= DUP_TOP LOAD_ATTR store LOAD_ATTR CALL_FUNCTION_0 POP_TOP
withstmt ::= expr setupwith SETUP_FINALLY suite_stmts_opt
POP_BLOCK LOAD_CONST COME_FROM with_cleanup
# Semantic actions want store to be at index 2
withasstmt ::= expr setupwithas store suite_stmts_opt
POP_BLOCK LOAD_CONST COME_FROM with_cleanup
store ::= STORE_NAME
store ::= STORE_FAST
# tryelsetmtl doesn't need COME_FROM since the jump might not
# be the the join point at the end of the "try" but instead back to the

View File

@@ -254,7 +254,7 @@ class Python26Parser(Python2Parser):
POP_TOP jb_pb_come_from
generator_exp ::= LOAD_GENEXPR MAKE_FUNCTION_0 expr GET_ITER CALL_FUNCTION_1 COME_FROM
list_if ::= list_if ::= expr jmp_false_then list_iter
list_if ::= expr jmp_false_then list_iter
'''
def p_ret26(self, args):
@@ -467,7 +467,7 @@ if __name__ == '__main__':
p.check_grammar()
from uncompyle6 import PYTHON_VERSION, IS_PYPY
if PYTHON_VERSION == 2.6:
lhs, rhs, tokens, right_recursive = p.check_sets()
lhs, rhs, tokens, right_recursive, dup_rhs = 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

@@ -41,8 +41,6 @@ class Python27Parser(Python2Parser):
comp_body ::= set_comp_body
comp_for ::= expr for_iter store comp_iter JUMP_BACK
comp_iter ::= comp_body
dict_comp_body ::= expr expr MAP_ADD
set_comp_body ::= expr SET_ADD
@@ -216,13 +214,17 @@ class Python27Parser(Python2Parser):
super(Python27Parser, self).customize_grammar_rules(tokens, customize)
self.check_reduce['and'] = 'AST'
# self.check_reduce['or'] = 'AST'
self.check_reduce['raise_stmt1'] = 'AST'
self.check_reduce['list_if_not'] = 'AST'
self.check_reduce['list_if'] = 'AST'
self.check_reduce['if_expr_true'] = 'tokens'
self.check_reduce['whilestmt'] = 'tokens'
self.check_reduce["and"] = "AST"
self.check_reduce["conditional"] = "AST"
# self.check_reduce["or"] = "AST"
self.check_reduce["raise_stmt1"] = "AST"
self.check_reduce["iflaststmtl"] = "AST"
self.check_reduce["list_if_not"] = "AST"
self.check_reduce["list_if"] = "AST"
self.check_reduce["comp_if"] = "AST"
self.check_reduce["if_expr_true"] = "tokens"
self.check_reduce["whilestmt"] = "tokens"
return
def reduce_is_invalid(self, rule, ast, tokens, first, last):
@@ -233,54 +235,99 @@ class Python27Parser(Python2Parser):
if invalid:
return invalid
if rule == ('and', ('expr', 'jmp_false', 'expr', '\\e_come_from_opt')):
# If the instruction after the instructions formin "and" is an "YIELD_VALUE"
if rule == ("and", ("expr", "jmp_false", "expr", "\\e_come_from_opt")):
# If the instruction after the instructions forming the "and" is an "YIELD_VALUE"
# then this is probably an "if" inside a comprehension.
if tokens[last] == 'YIELD_VALUE':
if tokens[last] == "YIELD_VALUE":
# Note: We might also consider testing last+1 being "POP_TOP"
return True
# Test that jump_false jump somewhere beyond the end of the "and"
# it might not be exactly the end of the "and" because this and can
# be a part of a larger condition. Oddly in 2.7 there doesn't seem to be
# an optimization where the "and" jump_false is back to a loop.
jmp_false = ast[1]
if jmp_false[0] == "POP_JUMP_IF_FALSE":
while (first < last and isinstance(tokens[last].offset, str)):
last -= 1
if jmp_false[0].attr < tokens[last].offset:
return True
# Test that jmp_false jumps to the end of "and"
# or that it jumps to the same place as the end of "and"
jmp_false = ast[1][0]
jmp_target = jmp_false.offset + jmp_false.attr + 3
return not (jmp_target == tokens[last].offset or
tokens[last].pattr == jmp_false.pattr)
elif rule[0] == ('raise_stmt1'):
return ast[0] == 'expr' and ast[0][0] == 'or'
elif rule[0] in ('assert', 'assert2'):
elif rule == ("comp_if", ("expr", "jmp_false", "comp_iter")):
jmp_false = ast[1]
if jmp_false[0] == "POP_JUMP_IF_FALSE":
return tokens[first].offset < jmp_false[0].attr < tokens[last].offset
pass
elif (rule[0], rule[1][0:5]) == (
"conditional",
("expr", "jmp_false", "expr", "JUMP_ABSOLUTE", "expr")):
jmp_false = ast[1]
if jmp_false[0] == "POP_JUMP_IF_FALSE":
else_instr = ast[4].first_child()
if jmp_false[0].attr != else_instr.offset:
return True
end_offset = ast[3].attr
return end_offset < tokens[last].offset
pass
elif rule[0] == ("raise_stmt1"):
return ast[0] == "expr" and ast[0][0] == "or"
elif rule[0] in ("assert", "assert2"):
jump_inst = ast[1][0]
jump_target = jump_inst.attr
return not (last >= len(tokens)
or jump_target == tokens[last].offset
or jump_target == next_offset(ast[-1].op, ast[-1].opc, ast[-1].offset))
elif rule == ('list_if_not', ('expr', 'jmp_true', 'list_iter')):
elif rule == ("iflaststmtl", ("testexpr", "c_stmts")):
testexpr = ast[0]
if testexpr[0] == "testfalse":
testfalse = testexpr[0]
if testfalse[1] == "jmp_false":
jmp_false = testfalse[1]
if last == len(tokens):
last -= 1
while (isinstance(tokens[first].offset, str) and first < last):
first += 1
if first == last:
return True
while (first < last and isinstance(tokens[last].offset, str)):
last -= 1
return tokens[first].offset < jmp_false[0].attr < tokens[last].offset
pass
pass
pass
elif rule == ("list_if_not", ("expr", "jmp_true", "list_iter")):
jump_inst = ast[1][0]
jump_offset = jump_inst.attr
return jump_offset > jump_inst.offset and jump_offset < tokens[last].offset
elif rule == ('list_if', ('expr', 'jmp_false', 'list_iter')):
elif rule == ("list_if", ("expr", "jmp_false", "list_iter")):
jump_inst = ast[1][0]
jump_offset = jump_inst.attr
return jump_offset > jump_inst.offset and jump_offset < tokens[last].offset
elif rule == ('or', ('expr', 'jmp_true', 'expr', '\\e_come_from_opt')):
# Test that jmp_true doesn't jump inside the middle the "or"
elif rule == ("or", ("expr", "jmp_true", "expr", "\\e_come_from_opt")):
# Test that jmp_true doesn"t jump inside the middle the "or"
# or that it jumps to the same place as the end of "and"
jmp_true = ast[1][0]
jmp_target = jmp_true.offset + jmp_true.attr + 3
return not (jmp_target == tokens[last].offset or
tokens[last].pattr == jmp_true.pattr)
elif (rule[0] == 'whilestmt' and
elif (rule[0] == "whilestmt" and
rule[1][0:-2] ==
('SETUP_LOOP', 'testexpr', 'l_stmts_opt',
'JUMP_BACK', 'JUMP_BACK')):
("SETUP_LOOP", "testexpr", "l_stmts_opt",
"JUMP_BACK", "JUMP_BACK")):
# Make sure that the jump backs all go to the same place
i = last-1
while (tokens[i] != 'JUMP_BACK'):
while (tokens[i] != "JUMP_BACK"):
i -= 1
return tokens[i].attr != tokens[i-1].attr
elif rule[0] == 'if_expr_true':
return (first) > 0 and tokens[first-1] == 'POP_JUMP_IF_FALSE'
elif rule[0] == "if_expr_true":
return (first) > 0 and tokens[first-1] == "POP_JUMP_IF_FALSE"
return False
@@ -288,13 +335,13 @@ class Python27Parser(Python2Parser):
class Python27ParserSingle(Python27Parser, PythonParserSingle):
pass
if __name__ == '__main__':
if __name__ == "__main__":
# Check grammar
p = Python27Parser()
p.check_grammar()
from uncompyle6 import PYTHON_VERSION, IS_PYPY
if PYTHON_VERSION == 2.7:
lhs, rhs, tokens, right_recursive = p.check_sets()
lhs, rhs, tokens, right_recursive, dup_rhs = p.check_sets()
from uncompyle6.scanner import get_scanner
s = get_scanner(PYTHON_VERSION, IS_PYPY)
opcode_set = set(s.opc.opname).union(set(
@@ -304,9 +351,9 @@ if __name__ == '__main__':
""".split()))
remain_tokens = set(tokens) - opcode_set
import re
remain_tokens = set([re.sub(r'_\d+$', '', t)
remain_tokens = set([re.sub(r"_\d+$", "", t)
for t in remain_tokens])
remain_tokens = set([re.sub('_CONT$', '', t)
remain_tokens = set([re.sub("_CONT$", "", t)
for t in remain_tokens])
remain_tokens = set(remain_tokens) - opcode_set
print(remain_tokens)

View File

@@ -86,10 +86,8 @@ class Python3Parser(PythonParser):
dict_comp_func ::= BUILD_MAP_0 LOAD_FAST FOR_ITER store
comp_iter JUMP_BACK RETURN_VALUE RETURN_LAST
comp_iter ::= comp_if
comp_iter ::= comp_if_not
comp_if_not ::= expr jmp_true comp_iter
comp_iter ::= comp_body
"""
def p_grammar(self, args):
@@ -432,7 +430,7 @@ class Python3Parser(PythonParser):
else:
return "%s_0" % (token.kind)
def custom_build_class_rule(self, opname, i, token, tokens, customize):
def custom_build_class_rule(self, opname, i, token, tokens, customize, is_pypy):
"""
# Should the first rule be somehow folded into the 2nd one?
build_class ::= LOAD_BUILD_CLASS mkfunc
@@ -483,10 +481,18 @@ class Python3Parser(PythonParser):
call_function = call_fn_tok.kind
if call_function.startswith("CALL_FUNCTION_KW"):
self.addRule("classdef ::= build_class_kw store", nop_func)
rule = "build_class_kw ::= LOAD_BUILD_CLASS mkfunc %sLOAD_CONST %s" % (
"expr " * (call_fn_tok.attr - 1),
call_function,
)
if is_pypy:
args_pos, args_kw = self.get_pos_kw(call_fn_tok)
rule = "build_class_kw ::= LOAD_BUILD_CLASS mkfunc %s%s%s" % (
"expr " * (args_pos - 1),
"kwarg " * (args_kw),
call_function,
)
else:
rule = (
"build_class_kw ::= LOAD_BUILD_CLASS mkfunc %sLOAD_CONST %s"
% ("expr " * (call_fn_tok.attr - 1), call_function)
)
else:
call_function = self.call_fn_name(call_fn_tok)
rule = "build_class ::= LOAD_BUILD_CLASS mkfunc %s%s" % (
@@ -496,7 +502,7 @@ class Python3Parser(PythonParser):
self.addRule(rule, nop_func)
return
def custom_classfunc_rule(self, opname, token, customize, next_token):
def custom_classfunc_rule(self, opname, token, customize, next_token, is_pypy):
"""
call ::= expr {expr}^n CALL_FUNCTION_n
call ::= expr {expr}^n CALL_FUNCTION_VAR_n
@@ -514,18 +520,28 @@ class Python3Parser(PythonParser):
# Yes, this computation based on instruction name is a little bit hoaky.
nak = (len(opname) - len("CALL_FUNCTION")) // 3
token.kind = self.call_fn_name(token)
uniq_param = args_kw + args_pos
# Note: 3.5+ have subclassed this method; so we don't handle
# 'CALL_FUNCTION_VAR' or 'CALL_FUNCTION_EX' here.
rule = (
"call ::= expr "
+ ("pos_arg " * args_pos)
+ ("kwarg " * args_kw)
+ "expr " * nak
+ token.kind
)
if is_pypy and self.version >= 3.6:
if token == "CALL_FUNCTION":
token.kind = self.call_fn_name(token)
rule = (
"call ::= expr "
+ ("pos_arg " * args_pos)
+ ("kwarg " * args_kw)
+ token.kind
)
else:
token.kind = self.call_fn_name(token)
rule = (
"call ::= expr "
+ ("pos_arg " * args_pos)
+ ("kwarg " * args_kw)
+ "expr " * nak
+ token.kind
)
self.add_unique_rule(rule, token.kind, uniq_param, customize)
@@ -543,7 +559,12 @@ class Python3Parser(PythonParser):
this has an effect on many rules.
"""
if self.version >= 3.3:
new_rule = rule % (("LOAD_STR ") * 1)
if PYTHON3 or not self.is_pypy:
load_op = "LOAD_STR "
else:
load_op = "LOAD_CONST "
new_rule = rule % ((load_op) * 1)
else:
new_rule = rule % (("LOAD_STR ") * 0)
self.add_unique_rule(new_rule, opname, attr, customize)
@@ -571,7 +592,7 @@ class Python3Parser(PythonParser):
"""
is_pypy = False
self.is_pypy = False
# For a rough break out on the first word. This may
# include instructions that don't need customization,
@@ -616,7 +637,7 @@ class Python3Parser(PythonParser):
# a specific instruction seen.
if "PyPy" in customize:
is_pypy = True
self.is_pypy = True
self.addRule(
"""
stmt ::= assign3_pypy
@@ -821,7 +842,9 @@ class Python3Parser(PythonParser):
"""
self.addRule(rule, nop_func)
self.custom_classfunc_rule(opname, token, customize, tokens[i + 1])
self.custom_classfunc_rule(
opname, token, customize, tokens[i + 1], self.is_pypy
)
# Note: don't add to custom_ops_processed.
elif opname_base == "CALL_METHOD":
@@ -880,21 +903,30 @@ class Python3Parser(PythonParser):
self.addRule(
"""
stmt ::= assert_pypy
stmt ::= assert2_pypy", nop_func)
stmt ::= assert_not_pypy
stmt ::= assert2_pypy
stmt ::= assert2_not_pypy
assert_pypy ::= JUMP_IF_NOT_DEBUG assert_expr jmp_true
LOAD_ASSERT RAISE_VARARGS_1 COME_FROM
assert_not_pypy ::= JUMP_IF_NOT_DEBUG assert_expr jmp_false
LOAD_ASSERT RAISE_VARARGS_1 COME_FROM
assert2_pypy ::= JUMP_IF_NOT_DEBUG assert_expr jmp_true
LOAD_ASSERT expr CALL_FUNCTION_1
RAISE_VARARGS_1 COME_FROM
assert2_pypy ::= JUMP_IF_NOT_DEBUG assert_expr jmp_true
LOAD_ASSERT expr CALL_FUNCTION_1
RAISE_VARARGS_1 COME_FROM,
RAISE_VARARGS_1 COME_FROM
assert2_not_pypy ::= JUMP_IF_NOT_DEBUG assert_expr jmp_false
LOAD_ASSERT expr CALL_FUNCTION_1
RAISE_VARARGS_1 COME_FROM
""",
nop_func,
)
custom_ops_processed.add(opname)
elif opname == "LOAD_BUILD_CLASS":
self.custom_build_class_rule(opname, i, token, tokens, customize)
self.custom_build_class_rule(
opname, i, token, tokens, customize, self.is_pypy
)
# Note: don't add to custom_ops_processed.
elif opname == "LOAD_CLASSDEREF":
# Python 3.4+
@@ -967,7 +999,7 @@ class Python3Parser(PythonParser):
j = 1
else:
j = 2
if is_pypy or (i >= j and tokens[i - j] == "LOAD_LAMBDA"):
if self.is_pypy or (i >= j and tokens[i - j] == "LOAD_LAMBDA"):
rule_pat = "mklambda ::= %sload_closure LOAD_LAMBDA %%s%s" % (
"pos_arg " * args_pos,
opname,
@@ -982,7 +1014,7 @@ class Python3Parser(PythonParser):
self.add_make_function_rule(rule_pat, opname, token.attr, customize)
if has_get_iter_call_function1:
if is_pypy or (i >= j and tokens[i - j] == "LOAD_LISTCOMP"):
if self.is_pypy or (i >= j and tokens[i - j] == "LOAD_LISTCOMP"):
# In the tokens we saw:
# LOAD_LISTCOMP LOAD_CONST MAKE_FUNCTION (>= 3.3) or
# LOAD_LISTCOMP MAKE_FUNCTION (< 3.3) or
@@ -996,7 +1028,7 @@ class Python3Parser(PythonParser):
self.add_make_function_rule(
rule_pat, opname, token.attr, customize
)
if is_pypy or (i >= j and tokens[i - j] == "LOAD_SETCOMP"):
if self.is_pypy or (i >= j and tokens[i - j] == "LOAD_SETCOMP"):
rule_pat = (
"set_comp ::= %sload_closure LOAD_SETCOMP %%s%s expr "
"GET_ITER CALL_FUNCTION_1"
@@ -1005,7 +1037,7 @@ class Python3Parser(PythonParser):
self.add_make_function_rule(
rule_pat, opname, token.attr, customize
)
if is_pypy or (i >= j and tokens[i - j] == "LOAD_DICTCOMP"):
if self.is_pypy or (i >= j and tokens[i - j] == "LOAD_DICTCOMP"):
self.add_unique_rule(
"dict_comp ::= %sload_closure LOAD_DICTCOMP %s "
"expr GET_ITER CALL_FUNCTION_1"
@@ -1051,17 +1083,24 @@ class Python3Parser(PythonParser):
)
elif self.version >= 3.4:
if PYTHON3 or not self.is_pypy:
load_op = "LOAD_STR"
else:
load_op = "LOAD_CONST"
if annotate_args > 0:
rule = "mkfunc_annotate ::= %s%s%sannotate_tuple load_closure LOAD_CODE LOAD_STR %s" % (
rule = "mkfunc_annotate ::= %s%s%sannotate_tuple load_closure %s %s %s" % (
"pos_arg " * args_pos,
kwargs_str,
"annotate_arg " * (annotate_args - 1),
load_op,
opname,
)
else:
rule = "mkfunc ::= %s%s load_closure LOAD_CODE LOAD_STR %s" % (
rule = "mkfunc ::= %s%s load_closure LOAD_CODE %s %s" % (
"pos_arg " * args_pos,
kwargs_str,
load_op,
opname,
)
@@ -1119,6 +1158,14 @@ class Python3Parser(PythonParser):
opname,
)
self.add_unique_rule(rule, opname, token.attr, customize)
if not PYTHON3 and self.is_pypy:
rule = "mkfunc ::= %s%s%s%s" % (
"expr " * stack_count,
"load_closure " * closure,
"LOAD_CODE LOAD_CONST ",
opname,
)
self.add_unique_rule(rule, opname, token.attr, customize)
if has_get_iter_call_function1:
rule_pat = (
@@ -1135,7 +1182,7 @@ class Python3Parser(PythonParser):
self.add_make_function_rule(
rule_pat, opname, token.attr, customize
)
if is_pypy or (i >= 2 and tokens[i - 2] == "LOAD_LISTCOMP"):
if self.is_pypy or (i >= 2 and tokens[i - 2] == "LOAD_LISTCOMP"):
if self.version >= 3.6:
# 3.6+ sometimes bundles all of the
# 'exprs' in the rule above into a
@@ -1156,7 +1203,7 @@ class Python3Parser(PythonParser):
rule_pat, opname, token.attr, customize
)
if is_pypy or (i >= 2 and tokens[i - 2] == "LOAD_LAMBDA"):
if self.is_pypy or (i >= 2 and tokens[i - 2] == "LOAD_LAMBDA"):
rule_pat = "mklambda ::= %s%sLOAD_LAMBDA %%s%s" % (
("pos_arg " * args_pos),
("kwarg " * args_kw),
@@ -1184,7 +1231,7 @@ class Python3Parser(PythonParser):
)
self.add_make_function_rule(rule_pat, opname, token.attr, customize)
if is_pypy or (i >= j and tokens[i - j] == "LOAD_LISTCOMP"):
if self.is_pypy or (i >= j and tokens[i - j] == "LOAD_LISTCOMP"):
# In the tokens we saw:
# LOAD_LISTCOMP LOAD_CONST MAKE_FUNCTION (>= 3.3) or
# LOAD_LISTCOMP MAKE_FUNCTION (< 3.3) or
@@ -1199,7 +1246,7 @@ class Python3Parser(PythonParser):
)
# FIXME: Fold test into add_make_function_rule
if is_pypy or (i >= j and tokens[i - j] == "LOAD_LAMBDA"):
if self.is_pypy or (i >= j and tokens[i - j] == "LOAD_LAMBDA"):
rule_pat = "mklambda ::= %s%sLOAD_LAMBDA %%s%s" % (
("pos_arg " * args_pos),
("kwarg " * args_kw),
@@ -1390,8 +1437,9 @@ class Python3Parser(PythonParser):
except_handler COME_FROM else_suitel
opt_come_from_except
""",
nop_func,
nop_func
)
custom_ops_processed.add(opname)
elif opname_base in ("UNPACK_EX",):
before_count, after_count = token.attr
@@ -1494,12 +1542,24 @@ class Python3Parser(PythonParser):
for i in range(cfl - 1, first, -1):
if tokens[i] != "POP_BLOCK":
break
if tokens[i].kind not in ("JUMP_BACK", "RETURN_VALUE"):
if tokens[i].kind not in ("JUMP_BACK", "RETURN_VALUE", "BREAK_LOOP"):
if not tokens[i].kind.startswith("COME_FROM"):
return True
# Check that the SETUP_LOOP jumps to the offset after the
# COME_FROM_LOOP
# Python 3.0 has additional:
# JUMP_FORWARD here
# COME_FROM
# POP_TOP
# COME_FROM
# here:
# (target of SETUP_LOOP)
# We won't check this.
if self.version == 3.0:
return False
if 0 <= last < len(tokens) and tokens[last] in (
"COME_FROM_LOOP",
"JUMP_BACK",

View File

@@ -12,13 +12,19 @@ class Python30Parser(Python31Parser):
def p_30(self, args):
"""
pt_bp ::= POP_TOP POP_BLOCK
assert ::= assert_expr jmp_true LOAD_ASSERT RAISE_VARARGS_1 COME_FROM POP_TOP
assert2 ::= assert_expr jmp_true LOAD_ASSERT expr CALL_FUNCTION_1 RAISE_VARARGS_1
come_froms
call_stmt ::= expr _come_froms POP_TOP
return_if_lambda ::= RETURN_END_IF_LAMBDA COME_FROM POP_TOP
compare_chained2 ::= expr COMPARE_OP RETURN_END_IF_LAMBDA
# FIXME: combine with parse3.2
whileTruestmt ::= SETUP_LOOP l_stmts_opt JUMP_BACK
COME_FROM_LOOP
whileTruestmt ::= SETUP_LOOP l_stmts_opt
jb_or_c COME_FROM_LOOP
whileTruestmt ::= SETUP_LOOP returns
COME_FROM_LOOP
@@ -43,10 +49,22 @@ class Python30Parser(Python31Parser):
else_suitel ::= l_stmts COME_FROM_LOOP JUMP_BACK
ifelsestmtl ::= testexpr c_stmts_opt jb_pop_top else_suitel
jump_absolute_else ::= COME_FROM JUMP_ABSOLUTE COME_FROM POP_TOP
jump_cf_pop ::= _come_froms _jump _come_froms POP_TOP
ifelsestmt ::= testexpr c_stmts_opt jump_cf_pop else_suite COME_FROM
ifelsestmtl ::= testexpr c_stmts_opt jump_cf_pop else_suitel
ifelsestmtc ::= testexpr c_stmts_opt jump_absolute_else else_suitec
ifelsestmtc ::= testexpr c_stmts_opt jump_cf_pop else_suitec
iflaststmt ::= testexpr c_stmts_opt JUMP_ABSOLUTE COME_FROM
iflaststmtl ::= testexpr c_stmts_opt jb_pop_top
iflaststmtl ::= testexpr c_stmts_opt come_froms JUMP_BACK COME_FROM POP_TOP
iflaststmt ::= testexpr c_stmts_opt JUMP_ABSOLUTE COME_FROM POP_TOP
withasstmt ::= expr setupwithas store suite_stmts_opt
POP_BLOCK LOAD_CONST COME_FROM_FINALLY
LOAD_FAST DELETE_FAST WITH_CLEANUP END_FINALLY
@@ -54,8 +72,8 @@ class Python30Parser(Python31Parser):
setup_finally ::= STORE_FAST SETUP_FINALLY LOAD_FAST DELETE_FAST
# Need to keep LOAD_FAST as index 1
set_comp_func_header ::= BUILD_SET_0 DUP_TOP STORE_FAST
set_comp_func ::= set_comp_func_header
set_comp_header ::= BUILD_SET_0 DUP_TOP STORE_FAST
set_comp_func ::= set_comp_header
LOAD_FAST FOR_ITER store comp_iter
JUMP_BACK POP_TOP JUMP_BACK RETURN_VALUE RETURN_LAST
@@ -63,8 +81,10 @@ class Python30Parser(Python31Parser):
list_comp ::= list_comp_header
LOAD_FAST FOR_ITER store comp_iter
JUMP_BACK
list_comp ::= list_comp_header
LOAD_FAST FOR_ITER store comp_iter
JUMP_BACK _come_froms POP_TOP JUMP_BACK
set_comp_header ::= BUILD_SET_0 DUP_TOP STORE_FAST
set_comp ::= set_comp_header
LOAD_FAST FOR_ITER store comp_iter
JUMP_BACK
@@ -73,6 +93,24 @@ class Python30Parser(Python31Parser):
dict_comp ::= dict_comp_header
LOAD_FAST FOR_ITER store dict_comp_iter
JUMP_BACK
dict_comp ::= dict_comp_header
LOAD_FAST FOR_ITER store dict_comp_iter
JUMP_BACK _come_froms POP_TOP JUMP_BACK
stmt ::= try_except30
try_except30 ::= SETUP_EXCEPT suite_stmts_opt
_come_froms pt_bp
except_handler opt_come_from_except
# From Python 2.6
list_iter ::= list_if JUMP_BACK
list_iter ::= list_if JUMP_BACK _come_froms POP_TOP
lc_body ::= LOAD_NAME expr LIST_APPEND
lc_body ::= LOAD_FAST expr LIST_APPEND
list_if ::= expr jmp_false_then list_iter
#############
dict_comp_iter ::= expr expr ROT_TWO expr STORE_SUBSCR
@@ -88,19 +126,52 @@ class Python30Parser(Python31Parser):
except_suite ::= c_stmts POP_EXCEPT jump_except POP_TOP
except_suite_finalize ::= SETUP_FINALLY c_stmts_opt except_var_finalize END_FINALLY
_jump COME_FROM POP_TOP
jump_except ::= JUMP_FORWARD COME_FROM POP_TOP
jump_except ::= JUMP_ABSOLUTE COME_FROM POP_TOP
except_handler ::= jmp_abs COME_FROM_EXCEPT except_stmts END_FINALLY
_ifstmts_jump ::= c_stmts_opt JUMP_FORWARD COME_FROM POP_TOP
_ifstmts_jump ::= c_stmts_opt come_froms POP_TOP JUMP_FORWARD _come_froms
jump_except ::= _jump COME_FROM POP_TOP
or ::= expr jmp_false expr jmp_true expr
or ::= expr jmp_true expr
import_from ::= LOAD_CONST LOAD_CONST IMPORT_NAME importlist _come_froms POP_TOP
################################################################################
# In many ways 3.0 is like 2.6. One similarity is there is no JUMP_IF_TRUE and
# JUMP_IF_FALSE
# The below rules in fact are the same or similar.
jmp_true ::= JUMP_IF_TRUE POP_TOP
jmp_false ::= JUMP_IF_FALSE _come_froms POP_TOP
jmp_true ::= JUMP_IF_TRUE POP_TOP
jmp_true_then ::= JUMP_IF_TRUE _come_froms POP_TOP
jmp_false ::= JUMP_IF_FALSE _come_froms POP_TOP
jmp_false_then ::= JUMP_IF_FALSE POP_TOP
# We don't have hacky THEN detection, so we do it
# in the grammar below which is also somewhat hacky.
stmt ::= ifstmt30
stmt ::= ifnotstmt30
ifstmt30 ::= testfalse_then _ifstmts_jump30
ifnotstmt30 ::= testtrue_then _ifstmts_jump30
testfalse_then ::= expr jmp_false_then
testtrue_then ::= expr jmp_true_then
call_stmt ::= expr COME_FROM
_ifstmts_jump30 ::= c_stmts POP_TOP
gen_comp_body ::= expr YIELD_VALUE COME_FROM POP_TOP
except_handler ::= jmp_abs COME_FROM_EXCEPT except_stmts
COME_FROM POP_TOP END_FINALLY
or ::= expr jmp_true_then expr come_from_opt
ret_or ::= expr jmp_true_then expr come_from_opt
ret_and ::= expr jump_false expr come_from_opt
################################################################################
for_block ::= l_stmts_opt _come_froms POP_TOP JUMP_BACK
except_handler ::= JUMP_FORWARD COME_FROM_EXCEPT except_stmts
@@ -108,12 +179,17 @@ class Python30Parser(Python31Parser):
except_handler ::= jmp_abs COME_FROM_EXCEPT except_stmts
POP_TOP END_FINALLY
return_if_stmt ::= ret_expr RETURN_END_IF COME_FROM POP_TOP
and ::= expr jmp_false expr come_from_opt
return_if_stmt ::= ret_expr RETURN_END_IF come_froms POP_TOP
return_if_stmt ::= ret_expr RETURN_VALUE come_froms POP_TOP
and ::= expr jmp_false_then expr come_from_opt
whilestmt ::= SETUP_LOOP testexpr l_stmts_opt come_from_opt
JUMP_BACK COME_FROM POP_TOP POP_BLOCK COME_FROM_LOOP
JUMP_BACK _come_froms POP_TOP POP_BLOCK COME_FROM_LOOP
whilestmt ::= SETUP_LOOP testexpr returns
POP_TOP POP_BLOCK COME_FROM_LOOP
whilestmt ::= SETUP_LOOP testexpr l_stmts_opt come_from_opt
come_froms POP_TOP POP_BLOCK COME_FROM_LOOP
# compare_chained is like x <= y <= z
@@ -124,34 +200,177 @@ class Python30Parser(Python31Parser):
compare_chained2 ::= expr COMPARE_OP RETURN_END_IF
"""
def customize_grammar_rules(self, tokens, customize):
super(Python30Parser, self).customize_grammar_rules(tokens, customize)
def remove_rules_30(self):
self.remove_rules("""
# The were found using grammar coverage
while1stmt ::= SETUP_LOOP l_stmts COME_FROM JUMP_BACK COME_FROM_LOOP
whileTruestmt ::= SETUP_LOOP l_stmts_opt JUMP_BACK POP_BLOCK COME_FROM_LOOP
whileelsestmt ::= SETUP_LOOP testexpr l_stmts_opt JUMP_BACK POP_BLOCK else_suitel COME_FROM_LOOP
whilestmt ::= SETUP_LOOP testexpr l_stmts_opt JUMP_BACK POP_BLOCK COME_FROM_LOOP
whilestmt ::= SETUP_LOOP testexpr l_stmts_opt JUMP_BACK POP_BLOCK JUMP_BACK COME_FROM_LOOP
whilestmt ::= SETUP_LOOP testexpr returns POP_TOP POP_BLOCK COME_FROM_LOOP
withasstmt ::= expr SETUP_WITH store suite_stmts_opt POP_BLOCK LOAD_CONST COME_FROM_WITH WITH_CLEANUP END_FINALLY
withstmt ::= expr SETUP_WITH POP_TOP suite_stmts_opt POP_BLOCK LOAD_CONST COME_FROM_WITH WITH_CLEANUP END_FINALLY
# lc_body ::= LOAD_FAST expr LIST_APPEND
# lc_body ::= LOAD_NAME expr LIST_APPEND
# lc_body ::= expr LIST_APPEND
# list_comp ::= BUILD_LIST_0 list_iter
# list_for ::= expr FOR_ITER store list_iter jb_or_c
# list_if ::= expr jmp_false list_iter
# list_if ::= expr jmp_false_then list_iter
# list_if_not ::= expr jmp_true list_iter
# list_iter ::= list_if JUMP_BACK
# list_iter ::= list_if JUMP_BACK _come_froms POP_TOP
# list_iter ::= list_if_not
# load_closure ::= BUILD_TUPLE_0
# load_genexpr ::= BUILD_TUPLE_1 LOAD_GENEXPR LOAD_STR
##########################################################################################
iflaststmtl ::= testexpr c_stmts_opt JUMP_BACK COME_FROM_LOOP
ifelsestmtl ::= testexpr c_stmts_opt JUMP_BACK else_suitel
iflaststmt ::= testexpr c_stmts_opt JUMP_ABSOLUTE
_ifstmts_jump ::= c_stmts_opt JUMP_FORWARD _come_froms
jump_forward_else ::= JUMP_FORWARD ELSE
jump_absolute_else ::= JUMP_ABSOLUTE ELSE
whilestmt ::= SETUP_LOOP testexpr l_stmts_opt COME_FROM JUMP_BACK POP_BLOCK
COME_FROM_LOOP
whilestmt ::= SETUP_LOOP testexpr returns
POP_BLOCK COME_FROM_LOOP
assert ::= assert_expr jmp_true LOAD_ASSERT RAISE_VARARGS_1
return_if_lambda ::= RETURN_END_IF_LAMBDA
except_suite ::= c_stmts POP_EXCEPT jump_except
whileelsestmt ::= SETUP_LOOP testexpr l_stmts JUMP_BACK POP_BLOCK
else_suitel COME_FROM_LOOP
# No JUMP_IF_FALSE_OR_POP
################################################################
# No JUMP_IF_FALSE_OR_POP, JUMP_IF_TRUE_OR_POP,
# POP_JUMP_IF_FALSE, or POP_JUMP_IF_TRUE
jmp_false ::= POP_JUMP_IF_FALSE
jmp_true ::= JUMP_IF_TRUE_OR_POP POP_TOP
jmp_true ::= POP_JUMP_IF_TRUE
compare_chained1 ::= expr DUP_TOP ROT_THREE COMPARE_OP JUMP_IF_FALSE_OR_POP
compare_chained1 COME_FROM
compare_chained1 ::= expr DUP_TOP ROT_THREE COMPARE_OP JUMP_IF_FALSE_OR_POP
compare_chained2 COME_FROM
ret_or ::= expr JUMP_IF_TRUE_OR_POP ret_expr_or_cond COME_FROM
ret_and ::= expr JUMP_IF_FALSE_OR_POP ret_expr_or_cond COME_FROM
ret_cond ::= expr POP_JUMP_IF_FALSE expr RETURN_END_IF
COME_FROM ret_expr_or_cond
ret_expr_or_cond ::= ret_cond
or ::= expr JUMP_IF_TRUE_OR_POP expr COME_FROM
and ::= expr JUMP_IF_TRUE_OR_POP expr COME_FROM
and ::= expr JUMP_IF_FALSE_OR_POP expr COME_FROM
""")
def customize_grammar_rules(self, tokens, customize):
super(Python30Parser, self).customize_grammar_rules(tokens, customize)
self.remove_rules_30()
self.check_reduce["iflaststmtl"] = "AST"
self.check_reduce['ifstmt'] = "AST"
self.check_reduce["ifelsestmtc"] = "AST"
self.check_reduce["ifelsestmt"] = "AST"
# self.check_reduce["and"] = "stmt"
return
def reduce_is_invalid(self, rule, ast, tokens, first, last):
invalid = super(Python30Parser,
self).reduce_is_invalid(rule, ast,
tokens, first, last)
if invalid:
return invalid
lhs = rule[0]
if (
lhs in ("iflaststmtl", "ifstmt",
"ifelsestmt", "ifelsestmtc") and ast[0] == "testexpr"
):
testexpr = ast[0]
if testexpr[0] == "testfalse":
testfalse = testexpr[0]
if lhs == "ifelsestmtc" and ast[2] == "jump_absolute_else":
jump_absolute_else = ast[2]
come_from = jump_absolute_else[2]
return come_from == "COME_FROM" and come_from.attr < tokens[first].offset
pass
elif lhs in ("ifelsestmt", "ifelsestmtc") and ast[2] == "jump_cf_pop":
jump_cf_pop = ast[2]
come_froms = jump_cf_pop[0]
for come_from in come_froms:
if come_from.attr < tokens[first].offset:
return True
come_froms = jump_cf_pop[2]
if come_froms == "COME_FROM":
if come_froms.attr < tokens[first].offset:
return True
pass
elif come_froms == "_come_froms":
for come_from in come_froms:
if come_from.attr < tokens[first].offset:
return True
return False
elif testfalse[1] == "jmp_false":
jmp_false = testfalse[1]
if last == len(tokens):
last -= 1
while (isinstance(tokens[first].offset, str) and first < last):
first += 1
if first == last:
return True
while (first < last and isinstance(tokens[last].offset, str)):
last -= 1
if rule[0] == "iflaststmtl":
return not (jmp_false[0].attr <= tokens[last].offset)
else:
jmp_false_target = jmp_false[0].attr
if tokens[first].offset > jmp_false_target:
return True
return (
(jmp_false_target > tokens[last].offset) and tokens[last] != "JUMP_FORWARD")
pass
pass
pass
# elif lhs == "and":
# return tokens[last+1] == "JUMP_FORWARD"
pass
class Python30ParserSingle(Python30Parser, PythonParserSingle):
pass
if __name__ == '__main__':
# Check grammar
p = Python30Parser()
p.remove_rules_30()
p.check_grammar()
from uncompyle6 import PYTHON_VERSION, IS_PYPY
if PYTHON_VERSION == 3.0:
lhs, rhs, tokens, right_recursive, dup_rhs = p.check_sets()
from uncompyle6.scanner import get_scanner
s = get_scanner(PYTHON_VERSION, IS_PYPY)
opcode_set = set(s.opc.opname).union(set(
"""JUMP_BACK CONTINUE RETURN_END_IF COME_FROM
LOAD_GENEXPR LOAD_ASSERT LOAD_SETCOMP LOAD_DICTCOMP LOAD_CLASSNAME
LAMBDA_MARKER RETURN_LAST
""".split()))
## FIXME: try this
remain_tokens = set(tokens) - opcode_set
import re
remain_tokens = set([re.sub(r'_\d+$', '', t) for t in remain_tokens])
remain_tokens = set([re.sub('_CONT$', '', t) for t in remain_tokens])
remain_tokens = set(remain_tokens) - opcode_set
print(remain_tokens)
import sys
if len(sys.argv) > 1:
from spark_parser.spark import rule2str
for rule in sorted(p.rule2name.items()):
print(rule2str(rule[0]))

View File

@@ -32,11 +32,49 @@ class Python31Parser(Python32Parser):
load ::= LOAD_FAST
load ::= LOAD_NAME
"""
def remove_rules_31(self):
self.remove_rules("""
# DUP_TOP_TWO is DUP_TOPX in 3.1 and earlier
subscript2 ::= expr expr DUP_TOP_TWO BINARY_SUBSCR
# The were found using grammar coverage
list_if ::= expr jmp_false list_iter COME_FROM
list_if_not ::= expr jmp_true list_iter COME_FROM
""")
def customize_grammar_rules(self, tokens, customize):
super(Python31Parser, self).customize_grammar_rules(tokens, customize)
self.remove_rules_31()
return
pass
class Python31ParserSingle(Python31Parser, PythonParserSingle):
pass
if __name__ == '__main__':
# Check grammar
p = Python31Parser()
p.remove_rules_31()
p.check_grammar()
from uncompyle6 import PYTHON_VERSION, IS_PYPY
if PYTHON_VERSION == 3.1:
lhs, rhs, tokens, right_recursive, dup_rhs = p.check_sets()
from uncompyle6.scanner import get_scanner
s = get_scanner(PYTHON_VERSION, IS_PYPY)
opcode_set = set(s.opc.opname).union(set(
"""JUMP_BACK CONTINUE RETURN_END_IF COME_FROM
LOAD_GENEXPR LOAD_ASSERT LOAD_SETCOMP LOAD_DICTCOMP LOAD_CLASSNAME
LAMBDA_MARKER RETURN_LAST
""".split()))
## FIXME: try this
remain_tokens = set(tokens) - opcode_set
import re
remain_tokens = set([re.sub(r'_\d+$', '', t) for t in remain_tokens])
remain_tokens = set([re.sub('_CONT$', '', t) for t in remain_tokens])
remain_tokens = set(remain_tokens) - opcode_set
print(remain_tokens)
import sys
if len(sys.argv) > 1:
from spark_parser.spark import rule2str
for rule in sorted(p.rule2name.items()):
print(rule2str(rule[0]))

View File

@@ -8,9 +8,15 @@ from uncompyle6.parser import PythonParserSingle
from uncompyle6.parsers.parse3 import Python3Parser
class Python32Parser(Python3Parser):
def p_30to33(self, args):
"""
# Store locals is only in Python 3.0 to 3.3
stmt ::= store_locals
store_locals ::= LOAD_FAST STORE_LOCALS
"""
def p_32to35(self, args):
"""
expr ::= conditional
conditional ::= expr jmp_false expr jump_forward_else expr COME_FROM
# compare_chained2 is used in a "chained_compare": x <= y <= z
@@ -18,10 +24,6 @@ class Python32Parser(Python3Parser):
compare_chained2 ::= expr COMPARE_OP RETURN_VALUE
compare_chained2 ::= expr COMPARE_OP RETURN_VALUE_LAMBDA
# Store locals is only in Python 3.0 to 3.3
stmt ::= store_locals
store_locals ::= LOAD_FAST STORE_LOCALS
# Python < 3.5 no POP BLOCK
whileTruestmt ::= SETUP_LOOP l_stmts_opt JUMP_BACK COME_FROM_LOOP

View File

@@ -14,23 +14,6 @@ class Python33Parser(Python32Parser):
# Python 3.3+ adds yield from.
expr ::= yield_from
yield_from ::= expr expr YIELD_FROM
# We do the grammar hackery below for semantics
# actions that want c_stmts_opt at index 1
# Python 3.5+ has jump optimization to remove the redundant
# jump_excepts. But in 3.3 we need them added
try_except ::= SETUP_EXCEPT suite_stmts_opt POP_BLOCK
except_handler
jump_excepts come_from_except_clauses
"""
def p_30to33(self, args):
"""
# Store locals is only in Python 3.0 to 3.3
stmt ::= store_locals
store_locals ::= LOAD_FAST STORE_LOCALS
"""
def customize_grammar_rules(self, tokens, customize):

View File

@@ -72,7 +72,7 @@ if __name__ == '__main__':
p.check_grammar()
from uncompyle6 import PYTHON_VERSION, IS_PYPY
if PYTHON_VERSION == 3.4:
lhs, rhs, tokens, right_recursive = p.check_sets()
lhs, rhs, tokens, right_recursive, dup_rhs = 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

@@ -144,9 +144,15 @@ class Python35Parser(Python34Parser):
super(Python35Parser, self).customize_grammar_rules(tokens, customize)
for i, token in enumerate(tokens):
opname = token.kind
if opname == 'LOAD_ASSERT':
if 'PyPy' in customize:
rules_str = """
stmt ::= JUMP_IF_NOT_DEBUG stmts COME_FROM
"""
self.add_unique_doc_rules(rules_str, customize)
# FIXME: I suspect this is wrong for 3.6 and 3.5, but
# I haven't verified what the 3.7ish fix is
if opname == 'BUILD_MAP_UNPACK_WITH_CALL':
elif opname == 'BUILD_MAP_UNPACK_WITH_CALL':
if self.version < 3.7:
self.addRule("expr ::= unmapexpr", nop_func)
nargs = token.attr % 256
@@ -257,7 +263,7 @@ if __name__ == '__main__':
p.check_grammar()
from uncompyle6 import PYTHON_VERSION, IS_PYPY
if PYTHON_VERSION == 3.5:
lhs, rhs, tokens, right_recursive = p.check_sets()
lhs, rhs, tokens, right_recursive, dup_rhs = 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

@@ -188,13 +188,7 @@ class Python36Parser(Python35Parser):
for i, token in enumerate(tokens):
opname = token.kind
if opname == 'LOAD_ASSERT':
if 'PyPy' in customize:
rules_str = """
stmt ::= JUMP_IF_NOT_DEBUG stmts COME_FROM
"""
self.add_unique_doc_rules(rules_str, customize)
elif opname == 'FORMAT_VALUE':
if opname == 'FORMAT_VALUE':
rules_str = """
expr ::= formatted_value1
formatted_value1 ::= expr FORMAT_VALUE
@@ -316,7 +310,7 @@ class Python36Parser(Python35Parser):
pass
return
def custom_classfunc_rule(self, opname, token, customize, next_token):
def custom_classfunc_rule(self, opname, token, customize, next_token, is_pypy):
args_pos, args_kw = self.get_pos_kw(token)
@@ -338,10 +332,14 @@ class Python36Parser(Python35Parser):
self.add_unique_rule('expr ::= async_call', token.kind, uniq_param, customize)
if opname.startswith('CALL_FUNCTION_KW'):
self.addRule("expr ::= call_kw36", nop_func)
values = 'expr ' * token.attr
rule = "call_kw36 ::= expr {values} LOAD_CONST {opname}".format(**locals())
self.add_unique_rule(rule, token.kind, token.attr, customize)
if is_pypy:
# PYPY doesn't follow CPython 3.6 CALL_FUNCTION_KW conventions
super(Python36Parser, self).custom_classfunc_rule(opname, token, customize, next_token, is_pypy)
else:
self.addRule("expr ::= call_kw36", nop_func)
values = 'expr ' * token.attr
rule = "call_kw36 ::= expr {values} LOAD_CONST {opname}".format(**locals())
self.add_unique_rule(rule, token.kind, token.attr, customize)
elif opname == 'CALL_FUNCTION_EX_KW':
# Note: this doesn't exist in 3.7 and later
self.addRule("""expr ::= call_ex_kw4
@@ -406,7 +404,7 @@ class Python36Parser(Python35Parser):
""", nop_func)
pass
else:
super(Python36Parser, self).custom_classfunc_rule(opname, token, customize, next_token)
super(Python36Parser, self).custom_classfunc_rule(opname, token, customize, next_token, is_pypy)
def reduce_is_invalid(self, rule, ast, tokens, first, last):
invalid = super(Python36Parser,
@@ -443,7 +441,7 @@ if __name__ == '__main__':
p.check_grammar()
from uncompyle6 import PYTHON_VERSION, IS_PYPY
if PYTHON_VERSION == 3.6:
lhs, rhs, tokens, right_recursive = p.check_sets()
lhs, rhs, tokens, right_recursive, dup_rhs = p.check_sets()
from uncompyle6.scanner import get_scanner
s = get_scanner(PYTHON_VERSION, IS_PYPY)
opcode_set = set(s.opc.opname).union(set(

File diff suppressed because it is too large Load Diff

Some files were not shown because too many files have changed in this diff Show More