Compare commits

...

73 Commits

Author SHA1 Message Date
rocky
114fe11e66 Merge branch 'master' of github.com:rocky/python-uncompyle6 2017-01-11 21:44:12 -05:00
rocky
b131c20e99 Get ready for release 2.9.9 2017-01-11 21:42:25 -05:00
rocky
5db1178b3e Get ready for release 2.10.9 2017-01-11 21:38:30 -05:00
R. Bernstein
7ece296f76 Merge pull request #79 from rocky/revert-78-patch-1
Revert "fix bug : not generate all files when use "-ro""
2017-01-11 07:10:23 -05:00
R. Bernstein
5035d5433b Revert "fix bug : not generate all files when use "-ro"" 2017-01-11 07:09:18 -05:00
R. Bernstein
78a5b620a7 Merge pull request #78 from jlugjb/patch-1
fix bug : not generate all files when use "-ro"
2017-01-11 07:06:10 -05:00
jlugjb
e851c0d46a fix bug : not generate all files when use "-ro"
when use the args of "-ro  outdir inputdir", only the first file is generated, other files is covered.
2017-01-11 17:02:36 +08:00
rocky
a760188724 Improve BUILD_xxx_UNPACK slightly 2017-01-10 04:36:28 -05:00
rocky
ad345ef94a Add async_call_function for 3.5+ 2017-01-09 07:03:51 -05:00
rocky
d050dd3adb Reinstate test 2017-01-09 06:01:06 -05:00
rocky
9392103998 Works now 2017-01-08 22:28:33 -05:00
rocky
707770049f Python 3.0 decompile bugs 2017-01-08 22:19:15 -05:00
rocky
ec0669367f Towards better 3.0 decompilation
Sync scanner2 and scanner3 better
2017-01-08 17:40:57 -05:00
rocky
3f40c16587 Fix 3.5, 3.6 while true if/break bug 2017-01-08 15:54:49 -05:00
rocky
66518baed0 Misc cleanups
Favor "decompile" over "uncompyle" since "decompile" is in common use
Reduce size of pysource.py by splitting out constants
2017-01-08 09:26:19 -05:00
rocky
21023fea74 Add 3.5+ async with/for ..
scanner3.py: 3.6 bytecode vs wordcode fix
2017-01-08 08:54:03 -05:00
rocky
66741d16ba Start to add 3.5+ await and async 2017-01-07 21:36:37 -05:00
rocky
e02ebef45d More Python 3 annotation bugs 2017-01-07 10:27:42 -05:00
rocky
99fce6dfd7 Fix some errors in deparsing Python 3 annotations 2017-01-07 03:03:53 -05:00
rocky
7b8c5e091c Small Pyhton 3.x annotate bug 2017-01-07 00:21:59 -05:00
rocky
77caf515ea Note what's up with Python 3 decompile quality 2017-01-03 07:38:01 -05:00
rocky
e4c0d56947 3.5 continue check is needed on 3.6 2017-01-03 07:22:25 -05:00
rocky
4827b1e994 Towards better 3.6 support 2017-01-03 00:44:07 -05:00
rocky
2b46e71264 Python 3.5 continue detection bug 2017-01-02 10:06:52 -05:00
rocky
84c2932bc5 add come_from for setup_finally and setup_except 2017-01-01 21:11:35 -05:00
rocky
874b3c9d31 Towards fixing Python 3.5 return bugs 2017-01-01 04:56:15 -05:00
rocky
f6a997befc Note how to verify correctness ...
with --verify, --weak-verify and cross checking with pycdc
2017-01-01 02:13:13 -05:00
rocky
136f42a610 Get ready for release 2.9.9 2016-12-31 05:38:16 -05:00
rocky
c43e734f37 2.x list_if may have a THEN in it 2016-12-31 05:28:37 -05:00
rocky
2327f0fdfa Towards fixing a Python 3.3 return/continue bug 2016-12-31 03:56:41 -05:00
rocky
0afcd31bd5 On --verify if we can't unbuffer output, don't 2016-12-30 05:07:41 -05:00
rocky
6f097ff1ca dectect_structure() -> detect_control_flow() 2016-12-29 07:32:36 -05:00
rocky
8eb1a16f5b DRY code and emitted Python 3 source
* Python 3: break; continue -> break
* Use variable in detect_structure for pre[rtarget]
* Make Python 2 and Python 3 detect_structure more alie
2016-12-29 07:28:37 -05:00
rocky
ed9fb64e72 More if/then detection in Python 3.x 2016-12-29 03:56:39 -05:00
R. Bernstein
d002c667ae Merge pull request #73 from rocky/then-crap
Add THEN token to improve Python 2.2-2.6 control flow detection
2016-12-29 02:52:41 -05:00
R. Bernstein
e56743cc14 Merge pull request #72 from rocky/master
THEN psuedo-ops for Python 2.x
2016-12-29 01:49:59 -05:00
rocky
39814fab8b Misc bugs 2016-12-28 20:16:13 -05:00
rocky
970774ab95 Merge branch 'master' of github.com:rocky/python-uncompyle6 2016-12-28 20:15:36 -05:00
rocky
723fa5dfed Towards fixing a 3.2 while true: ... break bug 2016-12-28 19:13:11 -05:00
rocky
4d4e59c40b Towards fixing a 3.2 while true: ... break bug 2016-12-28 18:58:02 -05:00
rocky
a92e6c9688 Bugs in Python 2.6- "and" and "lambda" handling ..
and clean up verify output
2016-12-28 04:54:11 -05:00
rocky
6c546fe6e1 WIP : Add THEN to disambigute from "and" 2016-12-27 22:45:08 -05:00
rocky
9b1dd0f26c Make 2.6 and 2.7 ingest more alike 2016-12-27 10:29:29 -05:00
rocky
0ff0c97a95 Update 2.7 bytecode file for last fix 2016-12-26 09:37:20 -05:00
R. Bernstein
3e988be075 Merge pull request #71 from jiangpengcheng/tupple_bug
tupples which contain only 1 element need a comma
2016-12-26 09:31:15 -05:00
jiangpch
eb64a03dfa add testcases for tuple assignment 2016-12-26 19:22:57 +08:00
jiangpch
9aa4e2b9ae tupples which contain only 1 element need a comma 2016-12-26 15:23:50 +08:00
rocky
c147514e9e fix bug in using python2 AST rules in python 2.5 2016-12-26 02:03:43 -05:00
rocky
813229ac45 Merge branch 'master' of github.com:rocky/python-uncompyle6 2016-12-26 00:43:12 -05:00
rocky
f1a947f106 lint . 2016-12-26 00:43:02 -05:00
rocky
2f51067a9d Scanner call fixes. NAME_MODULE removal for <=2.4 2016-12-25 09:20:57 -05:00
rocky
e3f4beeb74 Lint 2016-12-24 07:45:02 -05:00
rocky
7d58dcf6dd Remove stray debug hook 2016-12-24 04:10:31 -05:00
rocky
bfff1b4e9f Bang on 3.6 build_map_unpack_with_call
Probably will fix better in the future.
2016-12-20 19:42:23 -05:00
rocky
e6761e13bb Python flake8 crap
Was testing realgud's C-x!8 (goto flake8 warning/error)
2016-12-18 20:18:19 -05:00
rocky
c7c0a98982 Python 2.5 mistaken try/else 2016-12-18 00:56:07 -05:00
rocky
eebec48308 show-asm on python2.5 is optional
make scanner2 look a little more like scanner3
2016-12-17 08:01:25 -05:00
rocky
da50394841 Release 2.9.8 news 2016-12-16 22:56:48 -05:00
rocky
13d5cd1a58 Get ready for release 2.9.8 2016-12-16 22:42:46 -05:00
rocky
08dcc7d820 Start to handle 3.5 build_map_unpack_with_call
3.6 also started but needs even more work
2016-12-16 20:39:24 -05:00
rocky
7755563b65 Some Python 3.6 bytecode->wordcode fixes 2016-12-15 02:54:25 -05:00
rocky
b43cbc050d Was passing wrong type 2016-12-13 20:05:08 -05:00
rocky
db7a26d47d option -g: show start-end range when possible 2016-12-11 09:02:28 -05:00
rocky
92166452c1 two misc changes
- track print_docstring move to help (used in python 3.1)
- verify: allow RETURN_VALUE to match RETURN_END_IF
2016-12-11 08:22:26 -05:00
rocky
96fa3ef381 3.2 needs --weak-verify 2016-12-10 07:35:31 -05:00
rocky
755415c7d8 Try testing on 3.2 2016-12-10 07:32:56 -05:00
rocky
b168e1de55 Can run in Python 3.1 and Python 3.2 2016-12-10 07:30:27 -05:00
rocky
38eed14b41 Another python 3 ELSE fixes and ...
Makefile:
  - test python 3.0 bytecode
  - turn full --verify back on Python 3.x
2016-12-10 06:36:22 -05:00
rocky
2c993f8c32 Another faulty Python3 ELSE tag remove 2016-12-10 00:43:55 -05:00
rocky
65858a4c74 Grammar check: ELSE on RHS is ok. 2016-12-09 22:22:01 -05:00
rocky
263c63e009 Back of some of the verification changes 2016-12-09 21:43:22 -05:00
rocky
813bce4697 Merge branch 'master' of github.com:rocky/python-uncompyle6 2016-12-09 21:13:31 -05:00
rocky
a5d2237435 Python 3.x else clause detection and..
- Strengthen verify check.
- weak verification on Python 3.5 for now
2016-12-09 21:10:10 -05:00
79 changed files with 2025 additions and 658 deletions

View File

@@ -8,6 +8,7 @@ python:
- '2.6'
- '3.3'
- '3.4'
- '3.2'
install:
- pip install -r requirements.txt

339
ChangeLog
View File

@@ -1,6 +1,343 @@
2017-01-11 rocky <rb@dustyfeet.com>
* uncompyle6/version.py: Get ready for release 2.10.9
2017-01-11 R. Bernstein <rocky@users.noreply.github.com>
* : Merge pull request #79 from rocky/revert-78-patch-1 Revert "fix bug : not generate all files when use "-ro""
2017-01-11 R. Bernstein <rocky@users.noreply.github.com>
* : Merge pull request #78 from jlugjb/patch-1 fix bug : not generate all files when use "-ro"
2017-01-10 rocky <rb@dustyfeet.com>
* test/simple_source/bug35/03_double_star_unpack.py,
uncompyle6/parsers/parse3.py, uncompyle6/semantics/pysource.py:
Improve BUILD_xxx_UNPACK slightly
2017-01-09 rocky <rb@dustyfeet.com>
* test/simple_source/bug35/03_async_await.py,
uncompyle6/parsers/parse3.py, uncompyle6/semantics/pysource.py: Add
async_call_function for 3.5+
2017-01-09 rocky <rb@dustyfeet.com>
* : Reinstate test
2017-01-08 rocky <rb@dustyfeet.com>
* : Works now
2017-01-08 rocky <rb@dustyfeet.com>
* uncompyle6/parsers/parse30.py, uncompyle6/scanners/scanner3.py:
Python 3.0 decompile bugs
2017-01-08 rocky <rb@dustyfeet.com>
* uncompyle6/scanners/scanner2.py, uncompyle6/scanners/scanner3.py,
uncompyle6/scanners/scanner30.py: Towards better 3.0 decompilation Sync scanner2 and scanner3 better
2017-01-08 rocky <rb@dustyfeet.com>
* test/simple_source/bug35/03_while-if-break.py,
uncompyle6/parsers/parse35.py, uncompyle6/scanner.py,
uncompyle6/scanners/scanner3.py: Fix 3.5, 3.6 while true if/break
bug
2017-01-08 rocky <rb@dustyfeet.com>
* uncompyle6/__init__.py, uncompyle6/main.py,
uncompyle6/semantics/consts.py, uncompyle6/semantics/fragments.py,
uncompyle6/semantics/pysource.py: Misc cleanups Favor "decompile" over "uncompyle" since "decompile" is in common
use Reduce size of pysource.py by splitting out constants
2017-01-08 rocky <rb@dustyfeet.com>
* test/simple_source/bug35/03_async_await.py,
uncompyle6/parsers/parse35.py, uncompyle6/scanners/scanner3.py,
uncompyle6/semantics/pysource.py: Add 3.5+ async with/for .. scanner3.py: 3.6 bytecode vs wordcode fix
2017-01-07 rocky <rb@dustyfeet.com>
* test/simple_source/bug35/03_async_await.py,
uncompyle6/parsers/parse35.py, uncompyle6/semantics/pysource.py:
Start to add 3.5+ await and async
2017-01-07 rocky <rb@dustyfeet.com>
* test/simple_source/bug31/04_def_annotate.py,
uncompyle6/semantics/make_function.py: More Python 3 annotation bugs
2017-01-07 rocky <rb@dustyfeet.com>
* uncompyle6/parsers/parse3.py, uncompyle6/parsers/parse31.py,
uncompyle6/parsers/parse32.py,
uncompyle6/semantics/make_function.py,
uncompyle6/semantics/pysource.py: Fix some errors in deparsing
Python 3 annotations
2017-01-07 rocky <rb@dustyfeet.com>
* uncompyle6/semantics/make_function.py: Small Pyhton 3.x annotate
bug
2017-01-03 rocky <rb@dustyfeet.com>
* README.rst: Note what's up with Python 3 decompile quality
2017-01-03 rocky <rb@dustyfeet.com>
* uncompyle6/scanners/scanner3.py: 3.5 continue check is needed on
3.6
2017-01-03 rocky <rb@dustyfeet.com>
* test/test_pyenvlib.py, uncompyle6/parsers/parse36.py,
uncompyle6/scanners/scanner3.py: Towards better 3.6 support
2017-01-02 rocky <rb@dustyfeet.com>
* uncompyle6/parsers/parse35.py, uncompyle6/scanners/scanner3.py:
Python 3.5 continue detection bug
2017-01-01 rocky <rb@dustyfeet.com>
* uncompyle6/scanners/scanner3.py: add come_from for setup_finally
and setup_except
2017-01-01 rocky <rb@dustyfeet.com>
* uncompyle6/parsers/parse35.py, uncompyle6/scanners/scanner3.py:
Towards fixing Python 3.5 return bugs
2017-01-01 rocky <rb@dustyfeet.com>
* README.rst: Note how to verify correctness ... with --verify, --weak-verify and cross checking with pycdc
2016-12-31 rocky <rb@dustyfeet.com>
* ChangeLog, NEWS, uncompyle6/version.py: Get ready for release
2.9.9
2016-12-31 rocky <rb@dustyfeet.com>
* uncompyle6/parsers/parse26.py: 2.x list_if may have a THEN in it
2016-12-31 rocky <rb@dustyfeet.com>
* uncompyle6/scanners/scanner3.py: Towards fixing a Python 3.3
return/continue bug
2016-12-30 rocky <rb@dustyfeet.com>
* uncompyle6/main.py: On --verify if we can't unbuffer output, don't
2016-12-29 rocky <rb@dustyfeet.com>
* uncompyle6/scanners/scanner2.py, uncompyle6/scanners/scanner3.py:
dectect_structure() -> detect_control_flow()
2016-12-29 rocky <rb@dustyfeet.com>
* uncompyle6/scanners/scanner2.py, uncompyle6/scanners/scanner3.py:
DRY code and emitted Python 3 source * Python 3: break; continue -> break * Use variable in detect_structure for pre[rtarget] * Make Python 2 and Python 3 detect_structure more alie
2016-12-29 rocky <rb@dustyfeet.com>
* uncompyle6/scanners/scanner3.py: More if/then detection in Python
3.x
2016-12-29 R. Bernstein <rocky@users.noreply.github.com>
* : Merge pull request #73 from rocky/then-crap Add THEN token to improve Python 2.2-2.6 control flow detection
2016-12-28 rocky <rb@dustyfeet.com>
* uncompyle6/parsers/parse3.py, uncompyle6/scanners/tok.py: Misc
bugs
2016-12-28 rocky <rb@dustyfeet.com>
* : commit 723fa5dfed5bb198c66741c594e2c277ded88970 Author: rocky
<rb@dustyfeet.com> Date: Wed Dec 28 18:57:09 2016 -0500
2016-12-28 rocky <rb@dustyfeet.com>
* uncompyle6/parsers/parse3.py, uncompyle6/parsers/parse32.py,
uncompyle6/parsers/parse33.py: Towards fixing a 3.2 while true: ...
break bug
2016-12-28 rocky <rb@dustyfeet.com>
* test/Makefile, uncompyle6/main.py, uncompyle6/parsers/parse26.py,
uncompyle6/verify.py: Bugs in Python 2.6- "and" and "lambda"
handling .. and clean up verify output
2016-12-27 rocky <rb@dustyfeet.com>
* uncompyle6/parsers/parse26.py, uncompyle6/scanners/scanner2.py,
uncompyle6/scanners/scanner26.py, uncompyle6/semantics/pysource.py:
WIP : Add THEN to disambigute from "and"
2016-12-27 rocky <rb@dustyfeet.com>
* uncompyle6/scanners/scanner2.py: Make 2.6 and 2.7 ingest more
alike
2016-12-26 rocky <rb@dustyfeet.com>
* : Update 2.7 bytecode file for last fix
2016-12-26 R. Bernstein <rocky@users.noreply.github.com>
* : Merge pull request #71 from jiangpengcheng/tupple_bug tupples which contain only 1 element need a comma
2016-12-26 jiangpch <jiangpch@gohighsec.com>
* uncompyle6/semantics/pysource.py: tupples which contain only 1
element need a comma
2016-12-26 rocky <rb@dustyfeet.com>
* uncompyle6/parsers/parse25.py: fix bug in using python2 AST rules
in python 2.5
2016-12-26 rocky <rb@dustyfeet.com>
* : commit f1a947f106b231fb1480ba301b15e3ceaf78c94f Author: rocky
<rb@dustyfeet.com> Date: Mon Dec 26 00:43:02 2016 -0500
2016-12-25 rocky <rb@dustyfeet.com>
* uncompyle6/scanners/scanner23.py,
uncompyle6/scanners/scanner24.py, uncompyle6/semantics/pysource.py,
uncompyle6/verify.py: Scanner call fixes. NAME_MODULE removal for
<=2.4
2016-12-24 rocky <rb@dustyfeet.com>
* uncompyle6/parsers/astnode.py, uncompyle6/parsers/parse2.py,
uncompyle6/parsers/parse26.py, uncompyle6/parsers/parse3.py,
uncompyle6/parsers/parse36.py, uncompyle6/scanners/scanner15.py,
uncompyle6/scanners/scanner2.py, uncompyle6/scanners/scanner21.py,
uncompyle6/scanners/scanner22.py,
uncompyle6/semantics/fragments.py, uncompyle6/semantics/pysource.py:
Lint
2016-12-24 rocky <rb@dustyfeet.com>
* uncompyle6/semantics/pysource.py: Remove stray debug hook
2016-12-20 rocky <rb@dustyfeet.com>
* uncompyle6/semantics/pysource.py: Bang on 3.6
build_map_unpack_with_call Probably will fix better in the future.
2016-12-18 rocky <rb@dustyfeet.com>
* uncompyle6/bin/pydisassemble.py, uncompyle6/bin/uncompile.py,
uncompyle6/parsers/parse2.py, uncompyle6/parsers/parse25.py,
uncompyle6/parsers/parse27.py, uncompyle6/parsers/parse3.py,
uncompyle6/scanners/scanner2.py, uncompyle6/scanners/scanner3.py:
Python flake8 crap Was testing realgud's C-x!8 (goto flake8 warning/error)
2016-12-18 rocky <rb@dustyfeet.com>
* pytest/.gitignore, test/simple_source/bug25/02_try_else.py,
uncompyle6/parsers/parse25.py, uncompyle6/parsers/parse26.py: Python
2.5 mistaken try/else
2016-12-17 rocky <rb@dustyfeet.com>
* uncompyle6/scanners/scanner2.py, uncompyle6/scanners/scanner25.py:
show-asm on python2.5 is optional make scanner2 look a little more like scanner3
2016-12-16 rocky <rb@dustyfeet.com>
* NEWS: Release 2.9.8 news
2016-12-16 rocky <rb@dustyfeet.com>
* __pkginfo__.py, uncompyle6/version.py: Get ready for release 2.9.8
2016-12-16 rocky <rb@dustyfeet.com>
* test/simple_source/bug35/02_build_map_unpack_with_call.py,
uncompyle6/parsers/parse3.py, uncompyle6/parsers/parse35.py,
uncompyle6/parsers/parse36.py, uncompyle6/scanners/scanner3.py,
uncompyle6/semantics/pysource.py: Start to handle 3.5
build_map_unpack_with_call 3.6 also started but needs even more work
2016-12-15 rocky <rb@dustyfeet.com>
* uncompyle6/scanner.py, uncompyle6/scanners/scanner3.py: Some
Python 3.6 bytecode->wordcode fixes
2016-12-13 rocky <rb@dustyfeet.com>
* uncompyle6/semantics/fragments.py: Was passing wrong type
2016-12-11 rocky <rb@dustyfeet.com>
* uncompyle6/parser.py: option -g: show start-end range when
possible
2016-12-11 rocky <rb@dustyfeet.com>
* uncompyle6/semantics/make_function.py, uncompyle6/verify.py: two
misc changes - track print_docstring move to help (used in python 3.1) - verify: allow RETURN_VALUE to match RETURN_END_IF
2016-12-10 rocky <rb@dustyfeet.com>
* .travis.yml, test/Makefile: 3.2 needs --weak-verify
2016-12-10 rocky <rb@dustyfeet.com>
* .travis.yml: Try testing on 3.2
2016-12-10 rocky <rb@dustyfeet.com>
* __pkginfo__.py, uncompyle6/bin/uncompile.py: Can run in Python 3.1
and Python 3.2
2016-12-10 rocky <rb@dustyfeet.com>
* test/Makefile, uncompyle6/parsers/parse3.py,
uncompyle6/scanners/scanner3.py: Another python 3 ELSE fixes and ... Makefile: - test python 3.0 bytecode - turn full --verify back on Python 3.x
2016-12-10 rocky <rb@dustyfeet.com>
* uncompyle6/scanners/scanner3.py: Another faulty Python3 ELSE tag
remove
2016-12-09 rocky <rb@dustyfeet.com>
* pytest/test_grammar.py: Grammar check: ELSE on RHS is ok.
2016-12-09 rocky <rb@dustyfeet.com>
* uncompyle6/scanners/tok.py, uncompyle6/verify.py: Back of some of
the verification changes
2016-12-09 rocky <rb@dustyfeet.com>
* : commit a5d2237435ee51e681c73db9e7ea379d56456205 Author: rocky
<rb@dustyfeet.com> Date: Fri Dec 9 21:10:10 2016 -0500
2016-12-04 rocky <rb@dustyfeet.com>
* uncompyle6/version.py: Get ready for release 2.9.7
* ChangeLog, NEWS, uncompyle6/main.py, uncompyle6/parser.py,
uncompyle6/parsers/parse26.py, uncompyle6/parsers/parse3.py,
uncompyle6/parsers/parse34.py, uncompyle6/parsers/parse35.py,
uncompyle6/scanner.py, uncompyle6/scanners/scanner2.py,
uncompyle6/scanners/scanner23.py, uncompyle6/scanners/scanner24.py,
uncompyle6/scanners/scanner3.py, uncompyle6/scanners/tok.py,
uncompyle6/semantics/make_function.py,
uncompyle6/semantics/pysource.py, uncompyle6/verify.py,
uncompyle6/version.py: Get ready for release 2.9.7 Some of the many lint things. Linting is kind of stupid though.
2016-11-28 rocky <rb@dustyfeet.com>

33
NEWS
View File

@@ -1,3 +1,36 @@
uncompyle6 2.9.9 2016-12-16
- Remaining Python 3.5 ops handled
(this also means more Python 3.6 ops are handled)
- Python 3.5 and 3.6 async and await handled
- Python 3.0 decompilation improved
- Python 3 annotations fixed
- Better control-flow detection
- Code cleanups and misc bug fixes
uncompyle6 2.9.8 2016-12-16
- Better control-flow detection
- pseudo instruction THEN in 2.x
to disambiguate if from and
- fix bug in --verify option
- DRY (a little) control-flow detection
- fix syntax in tuples with one element
- if AST rule inheritence in Python 2.5
- NAME_MODULE removal for Python <= 2.4
- verifycall fixes for Python <= 2.4
- more Python lint
uncompyle6 2.9.7 2016-12-16
- Start to handle 3.5/3.6 build_map_unpack_with_call
- Some Python 3.6 bytecode to wordcode conversion fixes
- option -g: show start-end range when possible
- track print_docstring move to help (used in python 3.1)
- verify: allow RETURN_VALUE to match RETURN_END_IF
- some 3.2 compatibility
- Better Python 3 control flow detection by adding Pseudo ELSE opcodes
uncompyle6 2.9.6 2016-12-04
- Shorten Python3 grammars with + and *

View File

@@ -43,10 +43,10 @@ information.
Requirements
------------
This project requires Python 2.6 or later, PyPy 3-2.4, or PyPy-5.0.1.
Python versions 2.3-2.7 are supported in the python-2.4 branch.
This project requires Python 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 has been tested on Python bytecodes from
versions 2.1-2.7, and 3.2-3.6 and the above-mentioned PyPy versions.
versions 1.5, 2.1-2.7, and 3.2-3.6 and the above-mentioned PyPy versions.
Installation
------------
@@ -93,6 +93,16 @@ For usage help:
$ uncompyle6 -h
If you want strong verification of the correctness of the
decompilation process, add the `--verify` option. But there are
situations where this will indicate a failure, although the generated
program is semantically equivalent. Using option `--weak-verify` will
tell you if there is something definitely wrong. Generally, large
swaths of code are decompiled correctly, if not the entire program.
You can also cross compare the results with pycdc_ . Since they work
differently, bugs here often aren't in that, and vice versa.
Known Bugs/Restrictions
-----------------------
@@ -128,10 +138,13 @@ on the lower end Python versions which is more difficult for us to
handle since we don't have a Python interpreter for versions 1.5, 1.6,
and 2.0.
Python 3.0 support is weak; Python 3.5 largely works, but still has
some bugs in it. Python 3.6 changes things drastically by using word
codes rather than byte codes. That has been addressed, but then it also
changes function call opcodes and its semantics.
In the Python 3 series, Python support is is strongest around 3.4 or
3.3 and drops off as you move further away from those versions. Python
3.5 largely works, but still has some bugs in it and is missing some
opcodes. Python 3.6 changes things drastically by using word codes
rather than byte codes. That has been addressed, but then it also
changes function call opcodes and its semantics and has more problems
with control flow than 3.5 has.
Currently not all Python magic numbers are supported. Specifically in
some versions of Python, notably Python 3.6, the magic number has

View File

@@ -20,6 +20,8 @@ classifiers = ['Development Status :: 5 - Production/Stable',
'Programming Language :: Python :: 2.5',
'Programming Language :: Python :: 2.6',
'Programming Language :: Python :: 2.7',
'Programming Language :: Python :: 3.1',
'Programming Language :: Python :: 3.2',
'Programming Language :: Python :: 3.3',
'Programming Language :: Python :: 3.4',
'Programming Language :: Python :: 3.5',
@@ -38,7 +40,7 @@ entry_points={
]}
ftp_url = None
install_requires = ['spark-parser >= 1.5.1, < 1.6.0',
'xdis >= 3.2.3, < 3.3.0']
'xdis >= 3.2.4, < 3.3.0']
license = 'MIT'
mailing_list = 'python-debugger@googlegroups.com'
modname = 'uncompyle6'

1
pytest/.gitignore vendored
View File

@@ -1 +1,2 @@
/.hypothesis
/__pycache__

View File

@@ -41,7 +41,7 @@ def test_grammar():
"""
JUMP_BACK CONTINUE RETURN_END_IF
COME_FROM COME_FROM_EXCEPT COME_FROM_LOOP COME_FROM_WITH
COME_FROM_FINALLY
COME_FROM_FINALLY ELSE
LOAD_GENEXPR LOAD_ASSERT LOAD_SETCOMP LOAD_DICTCOMP
LAMBDA_MARKER RETURN_LAST
""".split())

View File

@@ -22,9 +22,9 @@ check:
#: Run working tests from Python 2.6 or 2.7
check-2.6 check-2.7: check-bytecode-2 check-bytecode-3 check-bytecode-1 check-2.7-ok
#: Run working tests from Python 3.1
#: Run working tests from Python 3.0
check-3.0: check-bytecode
@echo Python 3.0 testing not done yet
$(PYTHON) test_pythonlib.py --bytecode-3.0 --weak-verify $(COMPILE)
#: Run working tests from Python 3.1
check-3.1: check-bytecode
@@ -36,11 +36,11 @@ check-3.2: check-bytecode
#: Run working tests from Python 3.3
check-3.3: check-bytecode
$(PYTHON) test_pythonlib.py --bytecode-3.3 --weak-verify $(COMPILE)
$(PYTHON) test_pythonlib.py --bytecode-3.3 --verify $(COMPILE)
#: Run working tests from Python 3.4
check-3.4: check-bytecode check-3.4-ok check-2.7-ok
$(PYTHON) test_pythonlib.py --bytecode-3.4 --weak-verify $(COMPILE)
$(PYTHON) test_pythonlib.py --bytecode-3.4 --verify $(COMPILE)
#: Run working tests from Python 3.5
check-3.5: check-bytecode
@@ -100,7 +100,7 @@ check-bytecode-2.5:
#: Check deparsing Python 2.6
check-bytecode-2.6:
$(PYTHON) test_pythonlib.py --bytecode-2.6
$(PYTHON) test_pythonlib.py --bytecode-2.6 --weak-verify
#: Check deparsing Python 2.7
check-bytecode-2.7:

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

@@ -0,0 +1,12 @@
# Python 2.5 bug
# Was turning into tryelse when there in fact is no else.
def options(self, section):
"""Return a list of option names for the given section name."""
try:
opts = self._sections[section].copy()
except KeyError:
raise NoSectionError(section)
opts.update(self._defaults)
if '__name__' in opts:
del opts['__name__']
return opts.keys()

View File

@@ -8,3 +8,12 @@ def open(file, mode = "r", buffering = None,
encoding = None, errors = None,
newline = None, closefd = True) -> "IOBase":
return text
def foo(x: 'an argument that defaults to 5' = 5):
print(x)
def div(a: dict(type=float, help='the dividend'),
b: dict(type=float, help='the divisor (must be different than 0)')
) -> dict(type=float, help='the result of dividing a by b'):
"""Divide a by b"""
return a / b

View File

@@ -0,0 +1 @@
f(**a, **b)

View File

@@ -0,0 +1,26 @@
# Python 3.5+ async and await
async def await_test(asyncio):
reader, writer = await asyncio.open_connection(80)
await bar()
async def afor_test():
async for i in [1,2,3]:
x = i
async def afor_else_test():
async for i in [1,2,3]:
x = i
else:
z = 4
async def awith_test():
async with i:
print(i)
async def awith_as_test():
async with 1 as i:
print(i)

View File

@@ -0,0 +1,9 @@
# Bug in Python 3.5 is getting the two star'd arguments right.
def sum(a,b,c,d):
return a + b + c + d
args=(1,2)
sum(*args, *args)
# FIXME: this is handled incorrectly
# (*c,) = (3,4)

View File

@@ -0,0 +1,7 @@
# Python 3.5 and 3.6 break inside a
# while True and if / break
def display_date(loop):
while True:
if loop.time():
break
x = 5

View File

@@ -5,3 +5,8 @@ def some_function():
def some_other_function():
some_variable, = some_function()
print(some_variable)
empty_tup = ()
one_item_tup = ("item1", )
one_item_tup_without_parentheses = "item",
many_items_tup = ("item1", "item2", "item3")

View File

@@ -33,7 +33,7 @@ TEST_VERSIONS=('2.3.7', '2.4.6', '2.5.6', '2.6.9',
'2.7.10', '2.7.11', '2.7.12',
'3.0.1', '3.1.5', '3.2.6',
'3.3.5', '3.3.6',
'3.4.2', '3.5.1')
'3.4.2', '3.5.1', '3.6.0')
target_base = '/tmp/py-dis/'
lib_prefix = os.path.join(os.environ['HOME'], '.pyenv/versions')

View File

@@ -47,7 +47,10 @@ import uncompyle6.semantics.pysource
import uncompyle6.semantics.fragments
# Export some functions
from uncompyle6.main import uncompyle_file
from uncompyle6.main import decompile_file
# For compaitility
uncompyle_file = decompile_file
# Conventience functions so you can say:
# from uncompyle6 import deparse_code

View File

@@ -62,7 +62,6 @@ Type -h for for full help.""" % program
print(Usage_short, file=sys.stderr)
sys.exit(1)
for file in files:
if os.path.exists(files[0]):
disassemble_file(file, sys.stdout, native)

View File

@@ -66,9 +66,9 @@ def usage():
def main_bin():
if not (sys.version_info[0:2] in ((2, 6), (2, 7),
(3, 2), (3, 3),
(3, 1), (3, 2), (3, 3),
(3, 4), (3, 5), (3, 6))):
print('Error: %s requires Python 2.6, 2.7, 3.2, 3.3, 3.4, 3.5, or 3.6' % program,
print('Error: %s requires Python 2.6-2.7, or 3.1-3.6' % program,
file=sys.stderr)
sys.exit(-1)
@@ -142,7 +142,6 @@ def main_bin():
if src_base:
sb_len = len( os.path.join(src_base, '') )
files = [f[sb_len:] for f in files]
del sb_len
if not files:
print("No files given", file=sys.stderr)
@@ -225,7 +224,6 @@ def main_bin():
except (KeyboardInterrupt, OSError):
pass
if timestamp:
print(time.strftime(timestampfmt))

View File

@@ -11,7 +11,7 @@ from uncompyle6.linenumbers import line_number_mapping
from xdis.load import load_module
def uncompyle(
def decompile(
bytecode_version, co, out=None, showasm=None, showast=False,
timestamp=None, showgrammar=False, code_objects={},
source_size=None, is_pypy=False, magic_int=None):
@@ -48,8 +48,10 @@ def uncompyle(
# deparsing failed
raise pysource.SourceWalkerError(str(e))
# For compatiblity
uncompyle = decompile
def uncompyle_file(filename, outstream=None, showasm=None, showast=False,
def decompile_file(filename, outstream=None, showasm=None, showast=False,
showgrammar=False):
"""
decompile Python byte-code file (.pyc)
@@ -62,16 +64,20 @@ def uncompyle_file(filename, outstream=None, showasm=None, showast=False,
if type(co) == list:
for con in co:
uncompyle(version, con, outstream, showasm, showast,
decompile(version, con, outstream, showasm, showast,
timestamp, showgrammar, code_objects=code_objects,
is_pypy=is_pypy, magic_int=magic_int)
else:
uncompyle(version, co, outstream, showasm, showast,
decompile(version, co, outstream, showasm, showast,
timestamp, showgrammar,
code_objects=code_objects, source_size=source_size,
is_pypy=is_pypy, magic_int=magic_int)
co = None
# For compatiblity
uncompyle_file = decompile_file
# FIXME: combine into an options parameter
def main(in_base, out_base, files, codes, outfile=None,
showasm=None, showast=False, do_verify=False,
@@ -101,12 +107,6 @@ def main(in_base, out_base, files, codes, outfile=None,
tot_files = okay_files = failed_files = verify_failed_files = 0
# for code in codes:
# version = sys.version[:3] # "2.5"
# with open(code, "r") as f:
# co = compile(f.read(), "", "exec")
# uncompyle(sys.version[:3], co, sys.stdout, showasm=showasm, showast=showast)
for filename in files:
infile = os.path.join(in_base, filename)
if not os.path.exists(infile):
@@ -126,8 +126,9 @@ def main(in_base, out_base, files, codes, outfile=None,
prefix = prefix[:-len('.py')]
junk, outfile = tempfile.mkstemp(suffix=".py",
prefix=prefix)
# Unbuffer output
sys.stdout = os.fdopen(sys.stdout.fileno(), 'w', 0)
# Unbuffer output if possible
buffering = -1 if sys.stdout.isatty() else 0
sys.stdout = os.fdopen(sys.stdout.fileno(), 'w', buffering)
tee = subprocess.Popen(["tee", outfile], stdin=subprocess.PIPE)
os.dup2(tee.stdin.fileno(), sys.stdout.fileno())
os.dup2(tee.stdin.fileno(), sys.stderr.fileno())
@@ -141,7 +142,7 @@ def main(in_base, out_base, files, codes, outfile=None,
# Try to uncompile the input file
try:
uncompyle_file(infile, outstream, showasm, showast, showgrammar)
decompile_file(infile, outstream, showasm, showast, showgrammar)
tot_files += 1
except (ValueError, SyntaxError, ParserError, pysource.SourceWalkerError) as e:
sys.stdout.write("\n")
@@ -230,11 +231,11 @@ def status_msg(do_verify, tot_files, okay_files, failed_files,
verify_failed_files):
if tot_files == 1:
if failed_files:
return "decompile failed"
return "\n# decompile failed"
elif verify_failed_files:
return "decompile verify failed"
return "\n# decompile verify failed"
else:
return "Successfully decompiled file"
return "\n# Successfully decompiled file"
pass
pass
mess = "decompiled %i files: %i okay, %i failed" % (tot_files, okay_files, failed_files)

View File

@@ -73,6 +73,11 @@ class PythonParser(GenericASTBuilder):
"""Customized format and print for our kind of tokens
which gets called in debugging grammar reduce rules
"""
def fix(c):
s = str(c)
i = s.find('_')
return s if i == -1 else s[:i]
prefix = ''
if parent and tokens:
p_token = tokens[parent]
@@ -81,8 +86,11 @@ class PythonParser(GenericASTBuilder):
else:
prefix = ' '
if hasattr(p_token, 'offset'):
prefix += "%3s " % str(p_token.offset)
prefix += " "
prefix += "%3s" % fix(p_token.offset)
if len(rule[1]) > 1:
prefix += '-%-3s ' % fix(tokens[i-1].offset)
else:
prefix += ' '
else:
prefix = ' '
@@ -264,8 +272,7 @@ class PythonParser(GenericASTBuilder):
# Zero or more COME_FROMs
# loops can have this
_come_from ::= _come_from COME_FROM
_come_from ::=
_come_from ::= COME_FROM*
# Zero or one COME_FROM
# And/or expressions have this

View File

@@ -28,9 +28,9 @@ class AST(spark_AST):
i = 0
for node in self:
if hasattr(node, '__repr1__'):
if enumerate_children:
if enumerate_children:
child = node.__repr1__(indent, i)
else:
else:
child = node.__repr1__(indent, None)
else:
inst = node.format(line_prefix='L.')

View File

@@ -272,7 +272,7 @@ class Python2Parser(PythonParser):
continue
elif opname_base in ('BUILD_LIST', 'BUILD_TUPLE', 'BUILD_SET'):
thousands = (v//1024)
thirty32s = ((v//32)%32)
thirty32s = ((v//32) % 32)
if thirty32s > 0:
rule = "expr32 ::=%s" % (' expr' * 32)
self.add_unique_rule(rule, opname_base, v, customize)
@@ -282,7 +282,7 @@ class Python2Parser(PythonParser):
opname_base, v, customize)
self.seen1024 = True
rule = ('build_list ::= ' + 'expr1024 '*thousands +
'expr32 '*thirty32s + 'expr '*(v%32) + opname)
'expr32 '*thirty32s + 'expr '*(v % 32) + opname)
elif opname == 'LOOKUP_METHOD':
# A PyPy speciality - DRY with parse3
self.add_unique_rule("load_attr ::= expr LOOKUP_METHOD",

View File

@@ -13,7 +13,7 @@ class Python25Parser(Python26Parser):
self.customized = {}
def p_misc25(self, args):
'''
"""
# If "return_if_stmt" is in a loop, a JUMP_BACK can be emitted. In 2.6 the
# JUMP_BACK doesn't appear
@@ -33,7 +33,33 @@ class Python25Parser(Python26Parser):
with_cleanup ::= LOAD_FAST DELETE_FAST WITH_CLEANUP END_FINALLY
with_cleanup ::= LOAD_NAME DELETE_NAME WITH_CLEANUP END_FINALLY
'''
"""
def add_custom_rules(self, tokens, customize):
super(Python25Parser, self).add_custom_rules(tokens, customize)
if self.version == 2.5:
self.check_reduce['tryelsestmt'] = 'tokens'
def reduce_is_invalid(self, rule, ast, tokens, first, last):
invalid = super(Python25Parser,
self).reduce_is_invalid(rule, ast,
tokens, first, last)
if invalid:
return invalid
lhs = rule[0]
if lhs in ('tryelsestmt', ):
# The end of the else part of try/else come_from has to come
# from an END_FINALLY statement
if tokens[last-1].type.startswith('COME_FROM'):
end_finally_offset = int(tokens[last-1].pattr)
current = first
while current < last:
offset = tokens[current].offset
if offset == end_finally_offset:
return tokens[current].type != 'END_FINALLY'
current += 1
return False
class Python25ParserSingle(Python26Parser, PythonParserSingle):
pass

View File

@@ -42,7 +42,7 @@ class Python26Parser(Python2Parser):
try_middle come_froms
tryelsestmt ::= SETUP_EXCEPT suite_stmts_opt POP_BLOCK
try_middle else_suite come_froms
try_middle else_suite COME_FROM
_ifstmts_jump ::= c_stmts_opt JUMP_FORWARD COME_FROM POP_TOP
@@ -113,16 +113,10 @@ class Python26Parser(Python2Parser):
break_stmt ::= BREAK_LOOP JUMP_BACK
# Semantic actions want the else to be at position 3
ifelsestmt ::= testexpr c_stmts_opt jf_cf_pop else_suite come_froms
ifelsestmt ::= testexpr c_stmts_opt filler else_suitel come_froms POP_TOP
# Semantic actions want else_suitel to be at index 3
ifelsestmtl ::= testexpr c_stmts_opt jb_cf_pop else_suitel
ifelsestmtc ::= testexpr c_stmts_opt ja_cf_pop else_suitec
iflaststmt ::= testexpr c_stmts_opt JUMP_ABSOLUTE come_froms POP_TOP
# Semantic actions want suite_stmts_opt to be at index 3
withstmt ::= expr setupwith SETUP_FINALLY suite_stmts_opt
POP_BLOCK LOAD_CONST COME_FROM WITH_CLEANUP END_FINALLY
@@ -159,6 +153,29 @@ class Python26Parser(Python2Parser):
while1stmt ::= SETUP_LOOP l_stmts_opt JUMP_BACK COME_FROM
ifstmt ::= testexpr_then _ifstmts_jump
# Semantic actions want the else to be at position 3
ifelsestmt ::= testexpr c_stmts_opt jf_cf_pop else_suite come_froms
ifelsestmt ::= testexpr_then c_stmts_opt jf_cf_pop else_suite come_froms
ifelsestmt ::= testexpr c_stmts_opt filler else_suitel come_froms POP_TOP
ifelsestmt ::= testexpr_then c_stmts_opt filler else_suitel come_froms POP_TOP
# Semantic actions want else_suitel to be at index 3
ifelsestmtl ::= testexpr_then c_stmts_opt jb_cf_pop else_suitel
ifelsestmtc ::= testexpr_then c_stmts_opt ja_cf_pop else_suitec
iflaststmt ::= testexpr_then c_stmts_opt JUMP_ABSOLUTE come_froms POP_TOP
iflaststmt ::= testexpr c_stmts_opt JUMP_ABSOLUTE come_froms POP_TOP
testexpr_then ::= testtrue_then
testexpr_then ::= testfalse_then
testtrue_then ::= expr jmp_true_then
testfalse_then ::= expr jmp_false_then
jmp_false_then ::= JUMP_IF_FALSE THEN POP_TOP
jmp_true_then ::= JUMP_IF_TRUE THEN POP_TOP
# Common with 2.7
while1stmt ::= SETUP_LOOP return_stmts bp_come_from
while1stmt ::= SETUP_LOOP return_stmts COME_FROM
@@ -177,11 +194,11 @@ class Python26Parser(Python2Parser):
list_iter ::= list_if JUMP_BACK
list_iter ::= list_if JUMP_BACK COME_FROM POP_TOP
list_compr ::= BUILD_LIST_0 DUP_TOP
designator list_iter del_stmt
list_compr ::= BUILD_LIST_0 DUP_TOP
designator list_iter JUMP_BACK del_stmt
lc_body ::= LOAD_NAME expr LIST_APPEND
list_compr ::= BUILD_LIST_0 DUP_TOP
designator list_iter del_stmt
list_compr ::= BUILD_LIST_0 DUP_TOP
designator list_iter JUMP_BACK del_stmt
lc_body ::= LOAD_NAME expr LIST_APPEND
lc_body ::= LOAD_FAST expr LIST_APPEND
comp_for ::= SETUP_LOOP expr _for designator comp_iter jb_bp_come_from
@@ -196,16 +213,16 @@ class Python26Parser(Python2Parser):
genexpr_func ::= setup_loop_lf FOR_ITER designator comp_iter JUMP_BACK come_from_pop
jb_bp_come_from
genexpr ::= LOAD_GENEXPR MAKE_FUNCTION_0 expr GET_ITER CALL_FUNCTION_1 COME_FROM
list_if ::= list_if ::= expr jmp_false_then list_iter
'''
def p_ret26(self, args):
'''
ret_and ::= expr jmp_false ret_expr_or_cond COME_FROM
ret_or ::= expr jmp_true ret_expr_or_cond COME_FROM
ret_cond ::= expr jmp_false expr RETURN_END_IF POP_TOP ret_expr_or_cond
ret_cond ::= expr jmp_false expr ret_expr_or_cond
ret_cond_not ::= expr jmp_true expr RETURN_END_IF POP_TOP ret_expr_or_cond
ret_and ::= expr jmp_false ret_expr_or_cond COME_FROM
ret_or ::= expr jmp_true ret_expr_or_cond COME_FROM
ret_cond ::= expr jmp_false_then expr RETURN_END_IF POP_TOP ret_expr_or_cond
ret_cond ::= expr jmp_false_then expr ret_expr_or_cond
ret_cond_not ::= expr jmp_true_then expr RETURN_END_IF POP_TOP ret_expr_or_cond
return_if_stmt ::= ret_expr RETURN_END_IF POP_TOP
return_stmt ::= ret_expr RETURN_VALUE POP_TOP
@@ -215,17 +232,37 @@ class Python26Parser(Python2Parser):
'''
def p_except26(self, args):
'''
"""
except_suite ::= c_stmts_opt jmp_abs POP_TOP
'''
"""
def p_misc26(self, args):
'''
"""
conditional ::= expr jmp_false expr jf_cf_pop expr come_from_opt
and ::= expr JUMP_IF_FALSE POP_TOP expr JUMP_IF_FALSE POP_TOP
cmp_list ::= expr cmp_list1 ROT_TWO COME_FROM POP_TOP _come_from
'''
conditional_lambda ::= expr jmp_false_then return_if_stmt return_stmt LAMBDA_MARKER
"""
def add_custom_rules(self, tokens, customize):
super(Python26Parser, self).add_custom_rules(tokens, customize)
self.check_reduce['and'] = 'AST'
def reduce_is_invalid(self, rule, ast, tokens, first, last):
invalid = super(Python26Parser,
self).reduce_is_invalid(rule, ast,
tokens, first, last)
if invalid:
return invalid
if rule == ('and', ('expr', 'jmp_false', 'expr', '\\e_come_from_opt')):
# 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)
return False
class Python26ParserSingle(Python2Parser, PythonParserSingle):
pass

View File

@@ -115,8 +115,10 @@ if __name__ == '__main__':
""".split()))
remain_tokens = set(tokens) - opcode_set
import re
remain_tokens = set([re.sub('_\d+$','', t) for t in remain_tokens])
remain_tokens = set([re.sub('_CONT$','', t) for t in remain_tokens])
remain_tokens = set([re.sub('_\d+$', '', t)
for t in remain_tokens])
remain_tokens = set([re.sub('_CONT$', '', t)
for t in remain_tokens])
remain_tokens = set(remain_tokens) - opcode_set
print(remain_tokens)
# p.dumpGrammar()

View File

@@ -138,15 +138,24 @@ class Python3Parser(PythonParser):
iflaststmtl ::= testexpr c_stmts_opt JUMP_BACK
iflaststmtl ::= testexpr c_stmts_opt JUMP_BACK COME_FROM_LOOP
# These are used to keep AST indices the same
jf_else ::= JUMP_FORWARD ELSE
ja_else ::= JUMP_ABSOLUTE ELSE
# Note: in if/else kinds of statements, we err on the side
# of missing "else" clauses. Therefore we include grammar
# rules with and without ELSE.
ifelsestmt ::= testexpr c_stmts_opt JUMP_FORWARD else_suite COME_FROM
ifelsestmt ::= testexpr c_stmts_opt jf_else else_suite _come_from
ifelsestmtc ::= testexpr c_stmts_opt JUMP_ABSOLUTE else_suitec
ifelsestmtc ::= testexpr c_stmts_opt ja_else else_suitec
ifelsestmtr ::= testexpr return_if_stmts return_stmts
ifelsestmtl ::= testexpr c_stmts_opt JUMP_BACK else_suitel
# FIXME: this feels like a hack. Is it just 1 or two
# COME_FROMs? the parsed tree for this and even with just the
# one COME_FROM for Python 2.7 seems to associate the
@@ -366,14 +375,17 @@ class Python3Parser(PythonParser):
'''
def p_expr3(self, args):
'''
"""
conditional ::= expr jmp_false expr jf_else expr COME_FROM
conditionalnot ::= expr jmp_true expr jf_else expr COME_FROM
expr ::= LOAD_CLASSNAME
# Python 3.4+
expr ::= LOAD_CLASSDEREF
# Python3 drops slice0..slice3
'''
"""
@staticmethod
def call_fn_name(token):
@@ -441,6 +453,15 @@ class Python3Parser(PythonParser):
('kwarg ' * args_kw) +
'expr ' * nak + token.type)
self.add_unique_rule(rule, token.type, args_pos, customize)
if self.version >= 3.5:
rule = ('async_call_function ::= expr ' +
('pos_arg ' * args_pos) +
('kwarg ' * args_kw) +
'expr ' * nak + token.type +
' GET_AWAITABLE LOAD_CONST YIELD_FROM')
self.add_unique_rule(rule, token.type, args_pos, customize)
self.add_unique_rule('expr ::= async_call_function', token.type, args_pos, customize)
rule = ('classdefdeco2 ::= LOAD_BUILD_CLASS mkfunc %s%s_%d'
% (('expr ' * (args_pos-1)), opname, args_pos))
self.add_unique_rule(rule, token.type, args_pos, customize)
@@ -464,8 +485,15 @@ class Python3Parser(PythonParser):
# build_class (see load_build_class)
build_list ::= {expr}^n BUILD_LIST_n
build_list ::= {expr}^n BUILD_TUPLE_n
# Even the below say _list, in the semantic rules we
# disambiguate tuples, and sets from lists
build_list ::= {expr}^n BUILD_LIST_n
build_list ::= {expr}^n BUILD_TUPLE_n
build_list ::= {expr}^n BUILD_SET_n
build_list ::= {expr}^n BUILD_LIST_UNPACK_n
build_list ::= {expr}^n BUILD_SET_UNPACK_n
build_list ::= {expr}^n BUILD_TUPLE_UNPACK_n
load_closure ::= {LOAD_CLOSURE}^n BUILD_TUPLE_n
# call_function (see custom_classfunc_rule)
@@ -538,7 +566,8 @@ class Python3Parser(PythonParser):
elif opname_base in ('BUILD_LIST', 'BUILD_TUPLE', 'BUILD_SET'):
v = token.attr
rule = ('build_list ::= ' + 'expr1024 ' * int(v//1024) +
'expr32 ' * int((v//32)%32) + 'expr '*(v%32) + opname)
'expr32 ' * int((v//32) % 32) +
'expr ' * (v % 32) + opname)
self.add_unique_rule(rule, opname, token.attr, customize)
if opname_base == 'BUILD_TUPLE':
rule = ('load_closure ::= %s%s' % (('LOAD_CLOSURE ' * v), opname))
@@ -578,9 +607,10 @@ class Python3Parser(PythonParser):
self.add_unique_rule(rule, 'kvlist_n', 1, customize)
rule = "mapexpr ::= BUILD_MAP_n kvlist_n"
elif self.version >= 3.5:
rule = kvlist_n + ' ::= ' + 'expr ' * (token.attr*2)
self.add_unique_rule(rule, opname, token.attr, customize)
rule = "mapexpr ::= %s %s" % (kvlist_n, opname)
if opname != 'BUILD_MAP_WITH_CALL':
rule = kvlist_n + ' ::= ' + 'expr ' * (token.attr*2)
self.add_unique_rule(rule, opname, token.attr, customize)
rule = "mapexpr ::= %s %s" % (kvlist_n, opname)
else:
rule = kvlist_n + ' ::= ' + 'expr expr STORE_MAP ' * token.attr
self.add_unique_rule(rule, opname, token.attr, customize)
@@ -622,6 +652,27 @@ class Python3Parser(PythonParser):
rule = ('mkfunc ::= kwargs %sexpr %s' %
('pos_arg ' * args_pos, opname))
self.add_unique_rule(rule, opname, token.attr, customize)
if opname.startswith('MAKE_FUNCTION_A'):
# rule = ('mkfunc2 ::= %s%sEXTENDED_ARG %s' %
# ('pos_arg ' * (args_pos), 'kwargs ' * (annotate_args-1), opname))
self.add_unique_rule(rule, opname, token.attr, customize)
if self.version >= 3.3:
rule = ('mkfunc_annotate ::= %s%sannotate_tuple LOAD_CONST LOAD_CONST EXTENDED_ARG %s' %
(('pos_arg ' * (args_pos)),
('call_function ' * (annotate_args-1)), opname))
self.add_unique_rule(rule, opname, token.attr, customize)
rule = ('mkfunc_annotate ::= %s%sannotate_tuple LOAD_CONST LOAD_CONST EXTENDED_ARG %s' %
(('pos_arg ' * (args_pos)),
('annotate_arg ' * (annotate_args-1)), opname))
else:
rule = ('mkfunc_annotate ::= %s%sannotate_tuple LOAD_CONST EXTENDED_ARG %s' %
(('pos_arg ' * (args_pos)),
('annotate_arg ' * (annotate_args-1)), opname))
self.add_unique_rule(rule, opname, token.attr, customize)
rule = ('mkfunc_annotate ::= %s%sannotate_tuple LOAD_CONST EXTENDED_ARG %s' %
(('pos_arg ' * (args_pos)),
('call_function ' * (annotate_args-1)), opname))
self.add_unique_rule(rule, opname, token.attr, customize)
elif opname_base == 'CALL_METHOD':
# PyPy only - DRY with parse2
@@ -682,12 +733,27 @@ class Python3Parser(PythonParser):
self.check_reduce['augassign1'] = 'AST'
self.check_reduce['augassign2'] = 'AST'
self.check_reduce['while1stmt'] = 'noAST'
self.check_reduce['annotate_tuple'] = 'noAST'
self.check_reduce['kwarg'] = 'noAST'
# FIXME: remove parser errors caused by the below
# self.check_reduce['while1elsestmt'] = 'noAST'
return
def reduce_is_invalid(self, rule, ast, tokens, first, last):
lhs = rule[0]
if lhs in ('augassign1', 'augassign2') and ast[0][0] == 'and':
return True
elif lhs == 'annotate_tuple':
return not isinstance(tokens[first].attr, tuple)
elif lhs == 'kwarg':
return not isinstance(tokens[first].attr, str)
elif lhs == 'while1elsestmt':
# if SETUP_LOOP target spans the else part, then this is
# not while1else. Also do for whileTrue?
last += 1
while isinstance(tokens[last].offset, str):
last += 1
return tokens[first].attr == tokens[last].offset
elif lhs == 'while1stmt':
if tokens[last] in ('COME_FROM_LOOP', 'JUMP_BACK'):
# jump_back should be right afer SETUP_LOOP. Test?

View File

@@ -15,6 +15,11 @@ class Python30Parser(Python3Parser):
stmt ::= store_locals
store_locals ::= LOAD_FAST STORE_LOCALS
# FIXME: combine with parse3.2
whileTruestmt ::= SETUP_LOOP l_stmts_opt JUMP_BACK
COME_FROM_LOOP
whileTruestmt ::= SETUP_LOOP return_stmts
COME_FROM_LOOP
# In many ways Python 3.0 code generation is more like Python 2.6 than
# it is 2.7 or 3.1. So we have a number of 2.6ish (and before) rules below

View File

@@ -36,16 +36,8 @@ class Python31Parser(Python32Parser):
def add_custom_rules(self, tokens, customize):
super(Python31Parser, self).add_custom_rules(tokens, customize)
for i, token in enumerate(tokens):
opname = token.type
if opname.startswith('MAKE_FUNCTION_A'):
args_pos, args_kw, annotate_args = token.attr
# Check that there are 2 annotated params?
# rule = ('mkfunc2 ::= %s%sEXTENDED_ARG %s' %
# ('pos_arg ' * (args_pos), 'kwargs ' * (annotate_args-1), opname))
rule = ('mkfunc_annotate ::= %s%sannotate_tuple LOAD_CONST EXTENDED_ARG %s' %
(('pos_arg ' * (args_pos)),
('annotate_arg ' * (annotate_args-1)), opname))
self.add_unique_rule(rule, opname, token.attr, customize)
return
pass
class Python31ParserSingle(Python31Parser, PythonParserSingle):
pass

View File

@@ -19,6 +19,11 @@ class Python32Parser(Python3Parser):
COME_FROM_LOOP
whileTruestmt ::= SETUP_LOOP return_stmts
COME_FROM_LOOP
# Python 3.2+ has more loop optimization that removes
# JUMP_FORWARD in some cases, and hence we also don't
# see COME_FROM
_ifstmts_jump ::= c_stmts_opt
"""
pass
@@ -41,6 +46,9 @@ class Python32Parser(Python3Parser):
(('pos_arg ' * (args_pos)),
('annotate_arg ' * (annotate_args-1)), opname))
self.add_unique_rule(rule, opname, token.attr, customize)
pass
return
pass
class Python32ParserSingle(Python32Parser, PythonParserSingle):

View File

@@ -21,11 +21,6 @@ class Python33Parser(Python32Parser):
iflaststmt ::= testexpr c_stmts_opt33
c_stmts_opt33 ::= JUMP_BACK JUMP_ABSOLUTE c_stmts_opt
_ifstmts_jump ::= c_stmts_opt JUMP_FORWARD _come_from
# Python 3.3+ has more loop optimization that removes
# JUMP_FORWARD in some cases, and hence we also don't
# see COME_FROM
_ifstmts_jump ::= c_stmts_opt
"""
class Python33ParserSingle(Python33Parser, PythonParserSingle):

View File

@@ -16,37 +16,122 @@ class Python35Parser(Python34Parser):
def p_35on(self, args):
"""
# The number of canned instructions in new statements is mind boggling.
# I'm sure by the time Python 4 comes around these will be turned
# into special opcodes
# Python 3.5+ Await statement
stmt ::= await_stmt
await_stmt ::= call_function GET_AWAITABLE LOAD_CONST YIELD_FROM POP_TOP
# Python 3.5+ has WITH_CLEANUP_START/FINISH
withstmt ::= expr SETUP_WITH exprlist suite_stmts_opt
POP_BLOCK LOAD_CONST COME_FROM_WITH
WITH_CLEANUP_START WITH_CLEANUP_FINISH END_FINALLY
withstmt ::= expr
SETUP_WITH exprlist suite_stmts_opt
POP_BLOCK LOAD_CONST COME_FROM_WITH
WITH_CLEANUP_START WITH_CLEANUP_FINISH END_FINALLY
withstmt ::= expr SETUP_WITH POP_TOP suite_stmts_opt
POP_BLOCK LOAD_CONST COME_FROM_WITH
WITH_CLEANUP_START WITH_CLEANUP_FINISH END_FINALLY
withstmt ::= expr
SETUP_WITH POP_TOP suite_stmts_opt
POP_BLOCK LOAD_CONST COME_FROM_WITH
WITH_CLEANUP_START WITH_CLEANUP_FINISH END_FINALLY
withasstmt ::= expr
SETUP_WITH designator suite_stmts_opt
POP_BLOCK LOAD_CONST COME_FROM_WITH
WITH_CLEANUP_START WITH_CLEANUP_FINISH END_FINALLY
# Python 3.5+ async additions
stmt ::= async_with_stmt
async_with_stmt ::= expr
BEFORE_ASYNC_WITH GET_AWAITABLE LOAD_CONST YIELD_FROM
SETUP_ASYNC_WITH POP_TOP suite_stmts_opt
POP_BLOCK LOAD_CONST
WITH_CLEANUP_START
GET_AWAITABLE LOAD_CONST YIELD_FROM
WITH_CLEANUP_FINISH END_FINALLY
stmt ::= async_with_as_stmt
async_with_as_stmt ::= expr
BEFORE_ASYNC_WITH GET_AWAITABLE LOAD_CONST YIELD_FROM
SETUP_ASYNC_WITH designator suite_stmts_opt
POP_BLOCK LOAD_CONST
WITH_CLEANUP_START
GET_AWAITABLE LOAD_CONST YIELD_FROM
WITH_CLEANUP_FINISH END_FINALLY
stmt ::= async_for_stmt
async_for_stmt ::= SETUP_LOOP expr
GET_AITER
LOAD_CONST YIELD_FROM SETUP_EXCEPT GET_ANEXT LOAD_CONST
YIELD_FROM
designator
POP_BLOCK JUMP_FORWARD COME_FROM_EXCEPT DUP_TOP
LOAD_GLOBAL COMPARE_OP POP_JUMP_IF_FALSE
POP_TOP POP_TOP POP_TOP POP_EXCEPT POP_BLOCK
JUMP_ABSOLUTE END_FINALLY COME_FROM
for_block POP_BLOCK JUMP_ABSOLUTE
opt_come_from_loop
stmt ::= async_forelse_stmt
async_forelse_stmt ::= SETUP_LOOP expr
GET_AITER
LOAD_CONST YIELD_FROM SETUP_EXCEPT GET_ANEXT LOAD_CONST
YIELD_FROM
designator
POP_BLOCK JUMP_FORWARD COME_FROM_EXCEPT DUP_TOP
LOAD_GLOBAL COMPARE_OP POP_JUMP_IF_FALSE
POP_TOP POP_TOP POP_TOP POP_EXCEPT POP_BLOCK
JUMP_ABSOLUTE END_FINALLY COME_FROM
for_block POP_BLOCK JUMP_ABSOLUTE
else_suite COME_FROM_LOOP
withasstmt ::= expr SETUP_WITH designator suite_stmts_opt
POP_BLOCK LOAD_CONST COME_FROM_WITH
WITH_CLEANUP_START WITH_CLEANUP_FINISH END_FINALLY
inplace_op ::= INPLACE_MATRIX_MULTIPLY
binary_op ::= BINARY_MATRIX_MULTIPLY
# Python 3.5+ does jump optimization
# In <.3.5 the below is a JUMP_FORWARD to a JUMP_ABSOLUTE.
# in return_stmt, we will need the semantic actions in pysource.py
# to work out whether to dedent or not based on the presence of
# RETURN_END_IF vs RETURN_VALUE
return_if_stmt ::= ret_expr RETURN_END_IF POP_BLOCK
ifelsestmtc ::= testexpr c_stmts_opt JUMP_FORWARD else_suitec
ifelsestmtc ::= testexpr c_stmts_opt jf_else else_suitec
# ifstmt ::= testexpr c_stmts_opt
iflaststmt ::= testexpr c_stmts_opt JUMP_FORWARD
# Python 3.3+ also has yield from. 3.5 does it
# differently than 3.3, 3.4
yield_from ::= expr GET_YIELD_FROM_ITER LOAD_CONST YIELD_FROM
_ifstmts_jump ::= c_stmts_opt COME_FROM
"""
def add_custom_rules(self, tokens, customize):
super(Python35Parser, self).add_custom_rules(tokens, customize)
for i, token in enumerate(tokens):
opname = token.type
if opname == 'BUILD_MAP_UNPACK_WITH_CALL':
nargs = token.attr % 256
map_unpack_n = "map_unpack_%s" % nargs
rule = map_unpack_n + ' ::= ' + 'expr ' * (nargs)
self.add_unique_rule(rule, opname, token.attr, customize)
rule = "unmapexpr ::= %s %s" % (map_unpack_n, opname)
self.add_unique_rule(rule, opname, token.attr, customize)
call_token = tokens[i+1]
if self.version == 3.5:
rule = 'call_function ::= expr unmapexpr ' + call_token.type
self.add_unique_rule(rule, opname, token.attr, customize)
pass
pass
return
class Python35ParserSingle(Python35Parser, PythonParserSingle):
pass

View File

@@ -18,6 +18,12 @@ class Python36Parser(Python35Parser):
"""
fstring_multi ::= fstring_expr_or_strs BUILD_STRING
fstring_expr_or_strs ::= fstring_expr_or_str+
func_args36 ::= expr BUILD_TUPLE_0
call_function ::= func_args36 unmapexpr CALL_FUNCTION_EX
withstmt ::= expr SETUP_WITH POP_TOP suite_stmts_opt POP_BLOCK LOAD_CONST
WITH_CLEANUP_START WITH_CLEANUP_FINISH END_FINALLY
"""
def add_custom_rules(self, tokens, customize):
@@ -46,6 +52,7 @@ class Python36Parser(Python35Parser):
""" % (fstring_expr_or_str_n, fstring_expr_or_str_n, "fstring_expr_or_str " * v)
self.add_unique_doc_rules(rules_str, customize)
class Python36ParserSingle(Python36Parser, PythonParserSingle):
pass
@@ -65,8 +72,8 @@ if __name__ == '__main__':
""".split()))
remain_tokens = set(tokens) - opcode_set
import re
remain_tokens = set([re.sub('_\d+$','', t) for t in remain_tokens])
remain_tokens = set([re.sub('_CONT$','', t) for t in remain_tokens])
remain_tokens = set([re.sub('_\d+$', '', t) for t in remain_tokens])
remain_tokens = set([re.sub('_CONT$', '', t) for t in remain_tokens])
remain_tokens = set(remain_tokens) - opcode_set
print(remain_tokens)
# print(sorted(p.rule2name.items()))

View File

@@ -226,9 +226,9 @@ class Scanner(object):
for given opcode <op>.
"""
if op < self.opc.HAVE_ARGUMENT:
return 1
return 2 if self.version >= 3.6 else 1
else:
return 3
return 2 if self.version >= 3.6 else 3
def remove_mid_line_ifs(self, ifs):
"""

View File

@@ -23,5 +23,5 @@ class Scanner15(scan.Scanner21):
self.opc = opcode_15
self.opname = opcode_15.opname
self.version = 1.5
self.genexpr_name = '<generator expression>';
self.genexpr_name = '<generator expression>'
return

View File

@@ -37,7 +37,7 @@ class Scanner2(scan.Scanner):
self.jump_forward = frozenset([self.opc.JUMP_ABSOLUTE, self.opc.JUMP_FORWARD])
# This is the 2.5+ default
# For <2.5 it is <generator expression>
self.genexpr_name = '<genexpr>';
self.genexpr_name = '<genexpr>'
@staticmethod
def unmangle_name(name, classname):
@@ -68,7 +68,6 @@ class Scanner2(scan.Scanner):
varnames = co.co_varnames
return free, names, varnames
def ingest(self, co, classname=None, code_objects={}, show_asm=None):
"""
Pick out tokens from an uncompyle6 code object, and transform them,
@@ -98,14 +97,14 @@ class Scanner2(scan.Scanner):
customize = {}
if self.is_pypy:
customize['PyPy'] = 1;
customize['PyPy'] = 1
Token = self.Token # shortcut
n = self.setup_code(co)
codelen = self.setup_code(co)
self.build_lines_data(co, n)
self.build_prev_op(n)
self.build_lines_data(co, codelen)
self.build_prev_op(codelen)
free, names, varnames = self.unmangle_code_names(co, classname)
self.names = names
@@ -114,7 +113,7 @@ class Scanner2(scan.Scanner):
# turn 'LOAD_GLOBAL' to 'LOAD_ASSERT'.
# 'LOAD_ASSERT' is used in assert statements.
self.load_asserts = set()
for i in self.op_range(0, n):
for i in self.op_range(0, codelen):
# We need to detect the difference between:
# raise AssertionError
# and
@@ -139,7 +138,7 @@ class Scanner2(scan.Scanner):
last_stmt = self.next_stmt[0]
i = self.next_stmt[last_stmt]
replace = {}
while i < n-1:
while i < codelen - 1:
if self.lines[last_stmt].next > i:
# Distinguish "print ..." from "print ...,"
if self.code[last_stmt] == self.opc.PRINT_ITEM:
@@ -151,7 +150,7 @@ class Scanner2(scan.Scanner):
i = self.next_stmt[i]
extended_arg = 0
for offset in self.op_range(0, n):
for offset in self.op_range(0, codelen):
if offset in jump_targets:
jump_idx = 0
# We want to process COME_FROMs to the same offset to be in *descending*
@@ -177,6 +176,7 @@ class Scanner2(scan.Scanner):
offset="%s_%d" % (offset, jump_idx),
has_arg = True))
jump_idx += 1
pass
op = self.code[offset]
op_name = self.opc.opname[op]
@@ -459,7 +459,6 @@ class Scanner2(scan.Scanner):
self.ignore_if.add(except_match)
return None
self.ignore_if.add(except_match)
self.not_continue.add(jmp)
return jmp
@@ -479,26 +478,27 @@ class Scanner2(scan.Scanner):
elif op in self.setup_ops:
count_SETUP_ += 1
def detect_structure(self, offset, op):
def detect_control_flow(self, offset, op):
"""
Detect type of block structures and their boundaries to fix optimized jumps
in python2.3+
"""
# TODO: check the struct boundaries more precisely -Dan
code = self.code
# Detect parent structure
parent = self.structs[0]
start = parent['start']
end = parent['end']
# Pick inner-most parent for our offset
for struct in self.structs:
_start = struct['start']
_end = struct['end']
if (_start <= offset < _end) and (_start >= start and _end <= end):
start = _start
end = _end
current_start = struct['start']
current_end = struct['end']
if ((current_start <= offset < current_end)
and (current_start >= start and current_end <= end)):
start = current_start
end = current_end
parent = struct
if op == self.opc.SETUP_LOOP:
@@ -677,6 +677,8 @@ class Scanner2(scan.Scanner):
self.fixed_jumps[offset] = rtarget
return
jump_if_offset = offset
start = offset+3
pre = self.prev
@@ -699,6 +701,10 @@ class Scanner2(scan.Scanner):
'end': pre[target]})
return
# The op offset just before the target jump offset is important
# in making a determination of what we have. Save that.
pre_rtarget = pre[rtarget]
# Is it an "and" inside an "if" or "while" block
if op == self.opc.PJIF:
@@ -709,22 +715,22 @@ class Scanner2(scan.Scanner):
# If we still have any offsets in set, start working on it
if match:
if code[pre[rtarget]] in self.jump_forward \
and pre[rtarget] not in self.stmts \
and self.restrict_to_parent(self.get_target(pre[rtarget]), parent) == rtarget:
if code[pre[pre[rtarget]]] == self.opc.JUMP_ABSOLUTE \
if code[pre_rtarget] in self.jump_forward \
and pre_rtarget not in self.stmts \
and self.restrict_to_parent(self.get_target(pre_rtarget), parent) == rtarget:
if code[pre[pre_rtarget]] == self.opc.JUMP_ABSOLUTE \
and self.remove_mid_line_ifs([offset]) \
and target == self.get_target(pre[pre[rtarget]]) \
and (pre[pre[rtarget]] not in self.stmts or self.get_target(pre[pre[rtarget]]) > pre[pre[rtarget]])\
and 1 == len(self.remove_mid_line_ifs(self.rem_or(start, pre[pre[rtarget]], self.pop_jump_if, target))):
and target == self.get_target(pre[pre_rtarget]) \
and (pre[pre_rtarget] not in self.stmts or self.get_target(pre[pre_rtarget]) > pre[pre_rtarget])\
and 1 == len(self.remove_mid_line_ifs(self.rem_or(start, pre[pre_rtarget], self.pop_jump_if, target))):
pass
elif code[pre[pre[rtarget]]] == self.opc.RETURN_VALUE \
elif code[pre[pre_rtarget]] == self.opc.RETURN_VALUE \
and self.remove_mid_line_ifs([offset]) \
and 1 == (len(set(self.remove_mid_line_ifs(self.rem_or(start,
pre[pre[rtarget]],
pre[pre_rtarget],
self.pop_jump_if, target)))
| set(self.remove_mid_line_ifs(self.rem_or(start, pre[pre[rtarget]],
(self.opc.PJIF, self.opc.PJIT, self.opc.JUMP_ABSOLUTE), pre[rtarget], True))))):
| set(self.remove_mid_line_ifs(self.rem_or(start, pre[pre_rtarget],
(self.opc.PJIF, self.opc.PJIT, self.opc.JUMP_ABSOLUTE), pre_rtarget, True))))):
pass
else:
fix = None
@@ -742,7 +748,7 @@ class Scanner2(scan.Scanner):
else:
if (self.version < 2.7
and parent['type'] in ('root', 'for-loop', 'if-then',
'if-else', 'try')):
'else', 'try')):
self.fixed_jumps[offset] = rtarget
else:
# note test for < 2.7 might be superflous although informative
@@ -757,7 +763,7 @@ class Scanner2(scan.Scanner):
else:
assert_offset = offset + 3
if (assert_offset) in self.load_asserts:
if code[pre[rtarget]] == self.opc.RAISE_VARARGS:
if code[pre_rtarget] == self.opc.RAISE_VARARGS:
return
self.load_asserts.remove(assert_offset)
@@ -766,7 +772,7 @@ class Scanner2(scan.Scanner):
pass
elif code[next] in self.jump_forward and target == self.get_target(next):
if code[pre[next]] == self.opc.PJIF:
if code[next] == self.opc.JUMP_FORWARD or target != rtarget or code[pre[pre[rtarget]]] not in (self.opc.JUMP_ABSOLUTE, self.opc.RETURN_VALUE):
if code[next] == self.opc.JUMP_FORWARD or target != rtarget or code[pre[pre_rtarget]] not in (self.opc.JUMP_ABSOLUTE, self.opc.RETURN_VALUE):
self.fixed_jumps[offset] = pre[next]
return
elif code[next] == self.opc.JUMP_ABSOLUTE and code[target] in self.jump_forward:
@@ -783,20 +789,32 @@ class Scanner2(scan.Scanner):
return
if self.version == 2.7:
if code[pre[rtarget]] == self.opc.JUMP_ABSOLUTE and pre[rtarget] in self.stmts \
and pre[rtarget] != offset and pre[pre[rtarget]] != offset:
if code[pre_rtarget] == self.opc.JUMP_ABSOLUTE and pre_rtarget in self.stmts \
and pre_rtarget != offset and pre[pre_rtarget] != offset:
if code[rtarget] == self.opc.JUMP_ABSOLUTE and code[rtarget+3] == self.opc.POP_BLOCK:
if code[pre[pre[rtarget]]] != self.opc.JUMP_ABSOLUTE:
if code[pre[pre_rtarget]] != self.opc.JUMP_ABSOLUTE:
pass
elif self.get_target(pre[pre[rtarget]]) != target:
elif self.get_target(pre[pre_rtarget]) != target:
pass
else:
rtarget = pre[rtarget]
rtarget = pre_rtarget
else:
rtarget = pre[rtarget]
rtarget = pre_rtarget
# Does the "if" jump just beyond a jump op, then this is probably an if statement
pre_rtarget = pre[rtarget]
# Does the "jump if" jump beyond a jump op?
# That is, we have something like:
# POP_JUMP_IF_FALSE HERE
# ...
# JUMP_FORWARD
# HERE:
#
# If so, this can be block inside an "if" statement
# or a conditional assignment like:
# x = 1 if x else 2
#
# There are other contexts we may need to consider
# like whether the target is "END_FINALLY"
# or if the condition jump is to a forward location
code_pre_rtarget = code[pre_rtarget]
if code_pre_rtarget in self.jump_forward:
@@ -816,21 +834,87 @@ class Scanner2(scan.Scanner):
jump_target = self.get_target(next_offset, next_op)
if jump_target in self.setup_loops:
self.structs.append({'type': 'while-loop',
'start': start - 3,
'start': jump_if_offset,
'end': jump_target})
self.fixed_jumps[start-3] = jump_target
self.fixed_jumps[jump_if_offset] = jump_target
return
end = self.restrict_to_parent(if_end, parent)
self.structs.append({'type': 'if-then',
'start': start-3,
'end': pre_rtarget})
if_then_maybe = None
if 2.2 <= self.version <= 2.6:
# Take the JUMP_IF target. In an "if/then", it will be
# a POP_TOP instruction and the instruction before it
# will be a JUMP_FORWARD to just after the POP_TOP.
# For example:
# Good:
# 3 JUMP_IF_FALSE 33 'to 39'
# ..
# 36 JUMP_FORWARD 1 'to 40'
# 39 POP_TOP
# 40 ...
# example:
# BAD (is an "and"):
# 28 JUMP_IF_FALSE 4 'to 35'
# ...
# 32 JUMP_ABSOLUTE 40 'to 40' # should be 36 or there should
# # be a COME_FROM at the pop top
# # before 40 to 35
# 35 POP_TOP
# 36 ...
# 39 POP_TOP
# 39_0 COME_FROM 3
# 40 ...
if self.opc.opname[code[jump_if_offset]].startswith('JUMP_IF'):
jump_if_target = code[jump_if_offset+1]
if self.opc.opname[code[jump_if_target + jump_if_offset + 3]] == 'POP_TOP':
jump_inst = jump_if_target + jump_if_offset
jump_offset = code[jump_inst+1]
jump_op = self.opc.opname[code[jump_inst]]
if (jump_op == 'JUMP_FORWARD' and jump_offset == 1):
self.structs.append({'type': 'if-then',
'start': start-3,
'end': pre_rtarget})
self.thens[start] = end
elif jump_op == 'JUMP_ABSOLUTE':
if_then_maybe = {'type': 'if-then',
'start': start-3,
'end': pre_rtarget}
elif self.version == 2.7:
self.structs.append({'type': 'if-then',
'start': start-3,
'end': pre_rtarget})
self.not_continue.add(pre_rtarget)
if rtarget < end:
self.structs.append({'type': 'if-else',
# We have an "else" block of some kind.
# Is it associated with "if_then_maybe" seen above?
# These will be linked in this funny way:
# 198 JUMP_IF_FALSE 18 'to 219'
# 201 POP_TOP
# ...
# 216 JUMP_ABSOLUTE 256 'to 256'
# 219 POP_TOP
# ...
# 252 JUMP_FORWARD 1 'to 256'
# 255 POP_TOP
# 256
if if_then_maybe and jump_op == 'JUMP_ABSOLUTE':
jump_target = self.get_target(jump_inst, code[jump_inst])
if self.opc.opname[code[end]] == 'JUMP_FORWARD':
end_target = self.get_target(end, code[end])
if jump_target == end_target:
self.structs.append(if_then_maybe)
self.thens[start] = end
self.structs.append({'type': 'else',
'start': rtarget,
'end': end})
elif code_pre_rtarget == self.opc.RETURN_VALUE:
@@ -838,6 +922,7 @@ class Scanner2(scan.Scanner):
self.structs.append({'type': 'if-then',
'start': start,
'end': rtarget})
self.thens[start] = rtarget
if self.version == 2.7 or code[pre_rtarget+1] != self.opc.JUMP_FORWARD:
self.return_end_ifs.add(pre_rtarget)
@@ -871,11 +956,12 @@ class Scanner2(scan.Scanner):
self.ignore_if = set()
self.build_statement_indices()
# Containers filled by detect_structure()
# Containers filled by detect_control_flow()
self.not_continue = set()
self.return_end_ifs = set()
self.setup_loop_targets = {} # target given setup_loop offset
self.setup_loops = {} # setup_loop offset given target
self.thens = {} # JUMP_IF's that separate the 'then' part of an 'if'
targets = {}
for offset in self.op_range(0, n):
@@ -883,7 +969,7 @@ class Scanner2(scan.Scanner):
# Determine structures and fix jumps in Python versions
# since 2.3
self.detect_structure(offset, op)
self.detect_control_flow(offset, op)
if op_has_argument(op, self.opc):
label = self.fixed_jumps.get(offset)
@@ -891,8 +977,8 @@ class Scanner2(scan.Scanner):
if label is None:
if op in self.opc.hasjrel and self.opc.opname[op] != 'FOR_ITER':
# if (op in self.opc.hasjrel and
# (self.version < 2.0 or op != self.opc.FOR_ITER)):
# if (op in self.opc.hasjrel and
# (self.version < 2.0 or op != self.opc.FOR_ITER)):
label = offset + 3 + oparg
elif self.version == 2.7 and op in self.opc.hasjabs:
if op in (self.opc.JUMP_IF_FALSE_OR_POP,

View File

@@ -23,5 +23,5 @@ class Scanner21(scan.Scanner22):
self.opc = opcode_21
self.opname = opcode_21.opname
self.version = 2.1
self.genexpr_name = '<generator expression>';
self.genexpr_name = '<generator expression>'
return

View File

@@ -23,7 +23,7 @@ class Scanner22(scan.Scanner23):
self.opc = opcode_22
self.opname = opcode_22.opname
self.version = 2.2
self.genexpr_name = '<generator expression>';
self.genexpr_name = '<generator expression>'
self.parent_ingest = self.ingest
self.ingest = self.ingest22
return

View File

@@ -2,9 +2,8 @@
"""
Python 2.3 bytecode scanner/deparser
This overlaps Python's 2.3's dis module, but it can be run from
Python 3 and other versions of Python. Also, we save token
information for later use in deparsing.
This massages tokenized 2.3 bytecode to make it more amenable for
grammar parsing.
"""
import uncompyle6.scanners.scanner24 as scan
@@ -13,12 +12,12 @@ import uncompyle6.scanners.scanner24 as scan
from xdis.opcodes import opcode_23
JUMP_OPs = opcode_23.JUMP_OPs
# We base this off of 2.5 instead of the other way around
# We base this off of 2.4 instead of the other way around
# because we cleaned things up this way.
# The history is that 2.7 support is the cleanest,
# then from that we got 2.6 and so on.
class Scanner23(scan.Scanner24):
def __init__(self, show_asm):
def __init__(self, show_asm=False):
scan.Scanner24.__init__(self, show_asm)
self.opc = opcode_23
self.opname = opcode_23.opname

View File

@@ -2,9 +2,8 @@
"""
Python 2.4 bytecode scanner/deparser
This overlaps Python's 2.4's dis module, but it can be run from
Python 3 and other versions of Python. Also, we save token
information for later use in deparsing.
This massages tokenized 2.7 bytecode to make it more amenable for
grammar parsing.
"""
import uncompyle6.scanners.scanner25 as scan
@@ -18,7 +17,7 @@ JUMP_OPs = opcode_24.JUMP_OPs
# The history is that 2.7 support is the cleanest,
# then from that we got 2.6 and so on.
class Scanner24(scan.Scanner25):
def __init__(self, show_asm):
def __init__(self, show_asm=False):
scan.Scanner25.__init__(self, show_asm)
# These are the only differences in initialization between
# 2.4, 2.5 and 2.6

View File

@@ -18,7 +18,7 @@ JUMP_OPs = opcode_25.JUMP_OPs
# The history is that 2.7 support is the cleanest,
# then from that we got 2.6 and so on.
class Scanner25(scan.Scanner26):
def __init__(self, show_asm):
def __init__(self, show_asm=False):
# There are no differences in initialization between
# 2.5 and 2.6
self.opc = opcode_25

View File

@@ -94,35 +94,32 @@ class Scanner26(scan.Scanner2):
for instr in bytecode.get_instructions(co):
print(instr._disassemble())
# from xdis.bytecode import Bytecode
# bytecode = Bytecode(co, self.opc)
# for instr in bytecode.get_instructions(co):
# print(instr._disassemble())
# Container for tokens
tokens = []
customize = {}
if self.is_pypy:
customize['PyPy'] = 1
Token = self.Token # shortcut
n = self.setup_code(co)
codelen = self.setup_code(co)
self.build_lines_data(co, n)
self.build_prev_op(n)
self.build_lines_data(co, codelen)
self.build_prev_op(codelen)
free, names, varnames = self.unmangle_code_names(co, classname)
self.names = names
codelen = len(self.code)
# Scan for assertions. Later we will
# turn 'LOAD_GLOBAL' to 'LOAD_ASSERT'.
# 'LOAD_ASSERT' is used in assert statements.
self.load_asserts = set()
for i in self.op_range(0, n):
# We need to detect the difference between
# "raise AssertionError" and
# "assert"
for i in self.op_range(0, codelen):
# We need to detect the difference between:
# raise AssertionError
# and
# assert ...
if (self.code[i] == self.opc.JUMP_IF_TRUE and
i + 4 < codelen and
self.code[i+3] == self.opc.POP_TOP and
@@ -167,6 +164,11 @@ class Scanner26(scan.Scanner2):
offset="%s_%d" % (offset, jump_idx),
has_arg = True))
jump_idx += 1
elif offset in self.thens:
tokens.append(Token(
'THEN', None, self.thens[offset],
offset="%s_0" % offset,
has_arg = True))
has_arg = (op >= self.opc.HAVE_ARGUMENT)
if has_arg:

View File

@@ -148,7 +148,7 @@ class Scanner3(Scanner):
"""
show_asm = self.show_asm if not show_asm else show_asm
# show_asm = 'after'
# show_asm = 'both'
if show_asm in ('both', 'before'):
bytecode = Bytecode(co, self.opc)
for instr in bytecode.get_instructions(co):
@@ -159,7 +159,7 @@ class Scanner3(Scanner):
customize = {}
if self.is_pypy:
customize['PyPy'] = 1;
customize['PyPy'] = 1
self.code = array('B', co.co_code)
self.build_lines_data(co)
@@ -199,6 +199,7 @@ class Scanner3(Scanner):
# Get jump targets
# Format: {target offset: [jump offsets]}
jump_targets = self.find_jump_targets(show_asm)
last_op_was_break = False
for inst in bytecode:
@@ -225,6 +226,14 @@ class Scanner3(Scanner):
jump_idx += 1
pass
pass
elif inst.offset in self.else_start:
end_offset = self.else_start[inst.offset]
tokens.append(Token('ELSE',
None, repr(end_offset),
offset='%s' % (inst.offset),
has_arg = True, opc=self.opc))
pass
pattr = inst.argrepr
opname = inst.opname
@@ -313,11 +322,15 @@ class Scanner3(Scanner):
if target <= inst.offset:
next_opname = self.opname[self.code[inst.offset+3]]
if (inst.offset in self.stmts and
next_opname not in ('END_FINALLY', 'POP_BLOCK',
(self.version != 3.0 or (hasattr(inst, 'linestart'))) and
(next_opname not in ('END_FINALLY', 'POP_BLOCK',
# Python 3.0 only uses POP_TOP
'POP_TOP')
and inst.offset not in self.not_continue):
opname = 'CONTINUE'
'POP_TOP'))):
if (self.version >= 3.5 or
(inst.offset not in self.not_continue) or
(tokens[-1].type == 'RETURN_VALUE')):
opname = 'CONTINUE'
pass
else:
opname = 'JUMP_BACK'
# FIXME: this is a hack to catch stuff like:
@@ -326,15 +339,21 @@ class Scanner3(Scanner):
# There are other situations where we don't catch
# CONTINUE as well.
if tokens[-1].type == 'JUMP_BACK' and tokens[-1].attr <= argval:
# intern is used because we are changing the *previous* token
tokens[-1].type = intern('CONTINUE')
if tokens[-2].type == 'BREAK_LOOP':
del tokens[-1]
else:
# intern is used because we are changing the *previous* token
tokens[-1].type = intern('CONTINUE')
if last_op_was_break and opname == 'CONTINUE':
last_op_was_break = False
continue
elif op == self.opc.RETURN_VALUE:
if inst.offset in self.return_end_ifs:
opname = 'RETURN_END_IF'
elif inst.offset in self.load_asserts:
opname = 'LOAD_ASSERT'
last_op_was_break = opname == 'BREAK_LOOP'
tokens.append(
Token(
type_ = opname,
@@ -424,8 +443,9 @@ class Scanner3(Scanner):
self.fixed_jumps = {}
self.ignore_if = set()
self.build_statement_indices()
self.else_start = {}
# Containers filled by detect_structure()
# Containers filled by detect_control_flow()
self.not_continue = set()
self.return_end_ifs = set()
self.setup_loop_targets = {} # target given setup_loop offset
@@ -437,16 +457,20 @@ class Scanner3(Scanner):
# Determine structures and fix jumps in Python versions
# since 2.3
self.detect_structure(offset, targets)
self.detect_control_flow(offset, targets)
has_arg = (op >= op3.HAVE_ARGUMENT)
if has_arg:
label = self.fixed_jumps.get(offset)
oparg = code[offset+1] + code[offset+2] * 256
if self.version >= 3.6:
oparg = code[offset+1]
else:
oparg = code[offset+1] + code[offset+2] * 256
next_offset = offset + self.op_size(op)
if label is None:
if op in op3.hasjrel and op != self.opc.FOR_ITER:
label = offset + 3 + oparg
label = next_offset + oparg
elif op in op3.hasjabs:
if op in self.jump_if_pop:
if oparg > offset:
@@ -476,7 +500,7 @@ class Scanner3(Scanner):
prelim = self.all_instr(start, end, self.statement_opcodes)
# Initialize final container with statements with
# preliminnary data
# preliminary data
stmts = self.stmts = set(prelim)
# Same for opcode sequences
@@ -553,12 +577,18 @@ class Scanner3(Scanner):
Get target offset for op located at given <offset>.
"""
op = self.code[offset]
target = self.code[offset+1] + self.code[offset+2] * 256
if op in op3.hasjrel:
target += offset + 3
if self.version >= 3.6:
target = self.code[offset+1]
if op in self.opc.hasjrel:
target += offset + 2
else:
target = self.code[offset+1] + self.code[offset+2] * 256
if op in self.opc.hasjrel:
target += offset + 3
return target
def detect_structure(self, offset, targets):
def detect_control_flow(self, offset, targets):
"""
Detect structures and their boundaries to fix optimized jumps
in python2.3+
@@ -585,13 +615,15 @@ class Scanner3(Scanner):
parent = struct
if op == self.opc.SETUP_LOOP:
# We categorize loop types: 'for', 'while', 'while 1' with
# possibly suffixes '-loop' and '-else'
# Try to find the jump_back instruction of the loop.
# It could be a return instruction.
start = offset+3
if self.version <= 3.5:
start = offset+3
else:
start = offset+2
target = self.get_target(offset)
end = self.restrict_to_parent(target, parent)
self.setup_loop_targets[offset] = target
@@ -601,22 +633,35 @@ class Scanner3(Scanner):
self.fixed_jumps[offset] = end
(line_no, next_line_byte) = self.lines[offset]
jump_back = self.last_instr(start, end, self.opc.JUMP_ABSOLUTE,
next_line_byte, False)
next_line_byte, False)
if jump_back and jump_back != self.prev_op[end] and self.is_jump_forward(jump_back+3):
if (code[self.prev_op[end]] == self.opc.RETURN_VALUE
or (code[self.prev_op[end]] == self.opc.POP_BLOCK
and code[self.prev_op[self.prev_op[end]]] == self.opc.RETURN_VALUE)):
if jump_back:
jump_forward_offset = jump_back+3
else:
jump_forward_offset = None
return_val_offset1 = self.prev[self.prev[end]]
if (jump_back and jump_back != self.prev_op[end]
and self.is_jump_forward(jump_forward_offset)):
if (code[self.prev_op[end]] == self.opc.RETURN_VALUE or
(code[self.prev_op[end]] == self.opc.POP_BLOCK
and code[return_val_offset1] == self.opc.RETURN_VALUE)):
jump_back = None
if not jump_back: # loop suite ends in return. wtf right?
jump_back = self.last_instr(start, end, self.opc.RETURN_VALUE) + 1
if not jump_back:
jump_back = self.last_instr(start, end, self.opc.RETURN_VALUE)
if not jump_back:
return
jump_back += 2
if_offset = None
if code[self.prev_op[next_line_byte]] not in POP_JUMP_TF:
loop_type = 'for'
else:
if_offset = self.prev[next_line_byte]
if if_offset:
loop_type = 'while'
self.ignore_if.add(self.prev_op[next_line_byte])
self.ignore_if.add(if_offset)
else:
loop_type = 'for'
target = next_line_byte
end = jump_back + 3
else:
@@ -630,6 +675,7 @@ class Scanner3(Scanner):
elif target < offset:
self.fixed_jumps[offset] = jump_back+4
end = jump_back+4
target = self.get_target(jump_back)
if code[target] in (self.opc.FOR_ITER, self.opc.GET_ITER):
@@ -637,6 +683,7 @@ class Scanner3(Scanner):
else:
loop_type = 'while'
test = self.prev_op[next_line_byte]
if test == offset:
loop_type = 'while 1'
elif self.code[test] in op3.hasjabs+op3.hasjrel:
@@ -677,38 +724,40 @@ class Scanner3(Scanner):
'end': prev_op[target]})
return
# Is it an "and" inside an "if" block
# The op offset just before the target jump offset is important
# in making a determination of what we have. Save that.
pre_rtarget = prev_op[rtarget]
# Is it an "and" inside an "if" or "while" block
if op == self.opc.POP_JUMP_IF_FALSE:
# Search for another POP_JUMP_IF_FALSE targetting the same op,
# in current statement, starting from current offset, and filter
# everything inside inner 'or' jumps and midline ifs
match = self.rem_or(start, self.next_stmt[offset],
self.opc.POP_JUMP_IF_FALSE, target)
## We can't remove mid-line ifs because line structures have changed
## from restructBytecode().
## match = self.remove_mid_line_ifs(match)
# If we still have any offsets in set, start working on it
if match:
is_jump_forward = self.is_jump_forward(prev_op[rtarget])
if (is_jump_forward and prev_op[rtarget] not in self.stmts and
self.restrict_to_parent(self.get_target(prev_op[rtarget]), parent) == rtarget):
if (code[prev_op[prev_op[rtarget]]] == self.opc.JUMP_ABSOLUTE
is_jump_forward = self.is_jump_forward(pre_rtarget)
if (is_jump_forward and pre_rtarget not in self.stmts and
self.restrict_to_parent(self.get_target(pre_rtarget), parent) == rtarget):
if (code[prev_op[pre_rtarget]] == self.opc.JUMP_ABSOLUTE
and self.remove_mid_line_ifs([offset]) and
target == self.get_target(prev_op[prev_op[rtarget]]) and
(prev_op[prev_op[rtarget]] not in self.stmts or
self.get_target(prev_op[prev_op[rtarget]]) > prev_op[prev_op[rtarget]]) and
1 == len(self.remove_mid_line_ifs(self.rem_or(start, prev_op[prev_op[rtarget]], POP_JUMP_TF, target)))):
target == self.get_target(prev_op[pre_rtarget]) and
(prev_op[pre_rtarget] not in self.stmts or
self.get_target(prev_op[pre_rtarget]) > prev_op[pre_rtarget]) and
1 == len(self.remove_mid_line_ifs(self.rem_or(start, prev_op[pre_rtarget], POP_JUMP_TF, target)))):
pass
elif (code[prev_op[prev_op[rtarget]]] == self.opc.RETURN_VALUE
elif (code[prev_op[pre_rtarget]] == self.opc.RETURN_VALUE
and self.remove_mid_line_ifs([offset]) and
1 == (len(set(self.remove_mid_line_ifs(self.rem_or(start, prev_op[prev_op[rtarget]],
1 == (len(set(self.remove_mid_line_ifs(self.rem_or(start, prev_op[pre_rtarget],
POP_JUMP_TF, target))) |
set(self.remove_mid_line_ifs(self.rem_or(start, prev_op[prev_op[rtarget]],
set(self.remove_mid_line_ifs(self.rem_or(start, prev_op[pre_rtarget],
(self.opc.POP_JUMP_IF_FALSE,
self.opc.POP_JUMP_IF_TRUE,
self.opc.JUMP_ABSOLUTE),
prev_op[rtarget], True)))))):
pre_rtarget, True)))))):
pass
else:
fix = None
@@ -736,7 +785,7 @@ class Scanner3(Scanner):
if code[prev_op[next]] == self.opc.POP_JUMP_IF_FALSE:
if (code[next] == self.opc.JUMP_FORWARD
or target != rtarget
or code[prev_op[prev_op[rtarget]]] not in
or code[prev_op[pre_rtarget]] not in
(self.opc.JUMP_ABSOLUTE, self.opc.RETURN_VALUE)):
self.fixed_jumps[offset] = prev_op[next]
return
@@ -749,38 +798,62 @@ class Scanner3(Scanner):
if offset in self.ignore_if:
return
if (code[prev_op[rtarget]] == self.opc.JUMP_ABSOLUTE and
prev_op[rtarget] in self.stmts and
prev_op[rtarget] != offset and
prev_op[prev_op[rtarget]] != offset and
if (code[pre_rtarget] == self.opc.JUMP_ABSOLUTE and
pre_rtarget in self.stmts and
pre_rtarget != offset and
prev_op[pre_rtarget] != offset and
not (code[rtarget] == self.opc.JUMP_ABSOLUTE and
code[rtarget+3] == self.opc.POP_BLOCK and
code[prev_op[prev_op[rtarget]]] != self.opc.JUMP_ABSOLUTE)):
rtarget = prev_op[rtarget]
code[prev_op[pre_rtarget]] != self.opc.JUMP_ABSOLUTE)):
rtarget = pre_rtarget
# Does the "if" jump just beyond a jump op, then this can be
# a block inside an "if" statement
if self.is_jump_forward(prev_op[rtarget]):
if_end = self.get_target(prev_op[rtarget])
# Does the "jump if" jump beyond a jump op?
# That is, we have something like:
# POP_JUMP_IF_FALSE HERE
# ...
# JUMP_FORWARD
# HERE:
#
# If so, this can be block inside an "if" statement
# or a conditional assignment like:
# x = 1 if x else 2
#
# There are other contexts we may need to consider
# like whether the target is "END_FINALLY"
# or if the condition jump is to a forward location
if self.is_jump_forward(pre_rtarget):
if_end = self.get_target(pre_rtarget)
# Is this a loop and not an "if" statement?
if ((if_end < prev_op[rtarget]) and
# If the jump target is back, we are looping
if (if_end < pre_rtarget and
(code[prev_op[if_end]] == self.opc.SETUP_LOOP)):
if(if_end > start):
if (if_end > start):
return
end = self.restrict_to_parent(if_end, parent)
self.structs.append({'type': 'if-then',
'start': start,
'end': prev_op[rtarget]})
self.not_continue.add(prev_op[rtarget])
'end': pre_rtarget})
self.not_continue.add(pre_rtarget)
if rtarget < end:
self.structs.append({'type': 'if-else',
if rtarget < end and (
code[rtarget] not in (self.opc.END_FINALLY,
self.opc.JUMP_ABSOLUTE) and
code[prev_op[pre_rtarget]] not in (self.opc.POP_EXCEPT,
self.opc.END_FINALLY)):
self.structs.append({'type': 'else',
'start': rtarget,
'end': end})
elif code[prev_op[rtarget]] == self.opc.RETURN_VALUE:
self.else_start[rtarget] = end
elif self.is_jump_back(pre_rtarget):
if_end = rtarget
self.structs.append({'type': 'if-then',
'start': start,
'end': pre_rtarget})
self.not_continue.add(pre_rtarget)
elif code[pre_rtarget] in (self.opc.RETURN_VALUE,
self.opc.BREAK_LOOP):
self.structs.append({'type': 'if-then',
'start': start,
'end': rtarget})
@@ -810,8 +883,21 @@ class Scanner3(Scanner):
return
pass
pass
self.return_end_ifs.add(prev_op[rtarget])
if code[pre_rtarget] == self.opc.RETURN_VALUE:
self.return_end_ifs.add(pre_rtarget)
else:
self.fixed_jumps[offset] = rtarget
self.not_continue.add(pre_rtarget)
elif op == self.opc.SETUP_EXCEPT:
target = self.get_target(offset)
end = self.restrict_to_parent(target, parent)
self.fixed_jumps[offset] = end
elif op == self.opc.SETUP_FINALLY:
target = self.get_target(offset)
end = self.restrict_to_parent(target, parent)
self.fixed_jumps[offset] = end
elif op in self.jump_if_pop:
target = self.get_target(offset)
if target > offset:
@@ -849,6 +935,16 @@ class Scanner3(Scanner):
pass
return
def is_jump_back(self, offset):
"""
Return True if the code at offset is some sort of jump back.
That is, it is ether "JUMP_FORWARD" or an absolute jump that
goes forward.
"""
if self.code[offset] != self.opc.JUMP_ABSOLUTE:
return False
return offset > self.get_target(offset)
def next_except_jump(self, start):
"""
Return the next jump that was generated by an except SomeException:
@@ -869,7 +965,9 @@ class Scanner3(Scanner):
op = self.code[i]
if op == self.opc.END_FINALLY:
if count_END_FINALLY == count_SETUP_:
assert self.code[self.prev_op[i]] in (JUMP_ABSOLUTE, JUMP_FORWARD, RETURN_VALUE)
assert self.code[self.prev_op[i]] in (JUMP_ABSOLUTE,
JUMP_FORWARD,
RETURN_VALUE)
self.not_continue.add(self.prev_op[i])
return self.prev_op[i]
count_END_FINALLY += 1

View File

@@ -1,4 +1,4 @@
# Copyright (c) 2016 by Rocky Bernstein
# Copyright (c) 2016, 2017 by Rocky Bernstein
"""
Python 3.0 bytecode scanner/deparser
@@ -12,6 +12,8 @@ from __future__ import print_function
from xdis.opcodes import opcode_30 as opc
JUMP_OPs = map(lambda op: opc.opname[op], opc.hasjrel + opc.hasjabs)
JUMP_TF = frozenset([opc.JUMP_IF_FALSE, opc.JUMP_IF_TRUE])
from uncompyle6.scanners.scanner3 import Scanner3
class Scanner30(Scanner3):
@@ -20,6 +22,373 @@ class Scanner30(Scanner3):
return
pass
def detect_control_flow(self, offset, targets):
"""
Detect structures and their boundaries to fix optimized jumps
Python 3.0 is more like Python 2.6 than it is Python 3.x.
So we have a special routine here.
"""
code = self.code
op = code[offset]
# Detect parent structure
parent = self.structs[0]
start = parent['start']
end = parent['end']
# Pick inner-most parent for our offset
for struct in self.structs:
current_start = struct['start']
current_end = struct['end']
if ((current_start <= offset < current_end)
and (current_start >= start and current_end <= end)):
start = current_start
end = current_end
parent = struct
if op == self.opc.SETUP_LOOP:
# We categorize loop types: 'for', 'while', 'while 1' with
# possibly suffixes '-loop' and '-else'
# Try to find the jump_back instruction of the loop.
# It could be a return instruction.
start = offset+3
target = self.get_target(offset)
end = self.restrict_to_parent(target, parent)
self.setup_loop_targets[offset] = target
self.setup_loops[target] = offset
if target != end:
self.fixed_jumps[offset] = end
(line_no, next_line_byte) = self.lines[offset]
jump_back = self.last_instr(start, end, self.opc.JUMP_ABSOLUTE,
next_line_byte, False)
if jump_back:
jump_forward_offset = jump_back+3
else:
jump_forward_offset = None
return_val_offset1 = self.prev[self.prev[end]]
if (jump_back and jump_back != self.prev_op[end]
and self.is_jump_forward(jump_forward_offset)):
if (code[self.prev_op[end]] == self.opc.RETURN_VALUE or
(code[self.prev_op[end]] == self.opc.POP_BLOCK
and code[return_val_offset1] == self.opc.RETURN_VALUE)):
jump_back = None
if not jump_back:
# loop suite ends in return
jump_back = self.last_instr(start, end, self.opc.RETURN_VALUE)
if not jump_back:
return
jump_back += 2
if_offset = None
if code[self.prev_op[next_line_byte]] not in JUMP_TF:
if_offset = self.prev[next_line_byte]
if if_offset:
loop_type = 'while'
self.ignore_if.add(if_offset)
else:
loop_type = 'for'
target = next_line_byte
end = jump_back + 3
else:
if self.get_target(jump_back) >= next_line_byte:
jump_back = self.last_instr(start, end, self.opc.JUMP_ABSOLUTE, start, False)
if end > jump_back+4 and self.is_jump_forward(end):
if self.is_jump_forward(jump_back+4):
if self.get_target(jump_back+4) == self.get_target(end):
self.fixed_jumps[offset] = jump_back+4
end = jump_back+4
elif target < offset:
self.fixed_jumps[offset] = jump_back+4
end = jump_back+4
target = self.get_target(jump_back)
if code[target] in (self.opc.FOR_ITER, self.opc.GET_ITER):
loop_type = 'for'
else:
loop_type = 'while'
test = self.prev_op[next_line_byte]
if test == offset:
loop_type = 'while 1'
elif self.code[test] in opc.hasjabs+opc.hasjrel:
self.ignore_if.add(test)
test_target = self.get_target(test)
if test_target > (jump_back+3):
jump_back = test_target
self.not_continue.add(jump_back)
self.loops.append(target)
self.structs.append({'type': loop_type + '-loop',
'start': target,
'end': jump_back})
if jump_back+3 != end:
self.structs.append({'type': loop_type + '-else',
'start': jump_back+3,
'end': end})
elif op in JUMP_TF:
start = offset + self.op_size(op)
target = self.get_target(offset)
rtarget = self.restrict_to_parent(target, parent)
prev_op = self.prev_op
# Do not let jump to go out of parent struct bounds
if target != rtarget and parent['type'] == 'and/or':
self.fixed_jumps[offset] = rtarget
return
# Does this jump to right after another conditional jump that is
# not myself? If so, it's part of a larger conditional.
# rocky: if we have a conditional jump to the next instruction, then
# possibly I am "skipping over" a "pass" or null statement.
if ((code[prev_op[target]] in self.pop_jump_if_pop) and
(target > offset) and prev_op[target] != offset):
self.fixed_jumps[offset] = prev_op[target]
self.structs.append({'type': 'and/or',
'start': start,
'end': prev_op[target]})
return
# The op offset just before the target jump offset is important
# in making a determination of what we have. Save that.
pre_rtarget = prev_op[rtarget]
# Is it an "and" inside an "if" or "while" block
if op == opc.JUMP_IF_FALSE:
# Search for another JUMP_IF_FALSE targetting the same op,
# in current statement, starting from current offset, and filter
# everything inside inner 'or' jumps and midline ifs
match = self.rem_or(start, self.next_stmt[offset],
opc.JUMP_IF_FALSE, target)
# If we still have any offsets in set, start working on it
if match:
is_jump_forward = self.is_jump_forward(pre_rtarget)
if (is_jump_forward and pre_rtarget not in self.stmts and
self.restrict_to_parent(self.get_target(pre_rtarget), parent) == rtarget):
if (code[prev_op[pre_rtarget]] == self.opc.JUMP_ABSOLUTE
and self.remove_mid_line_ifs([offset]) and
target == self.get_target(prev_op[pre_rtarget]) and
(prev_op[pre_rtarget] not in self.stmts or
self.get_target(prev_op[pre_rtarget]) > prev_op[pre_rtarget]) and
1 == len(self.remove_mid_line_ifs(self.rem_or(start, prev_op[pre_rtarget], JUMP_TF, target)))):
pass
elif (code[prev_op[pre_rtarget]] == self.opc.RETURN_VALUE
and self.remove_mid_line_ifs([offset]) and
1 == (len(set(self.remove_mid_line_ifs(self.rem_or(start, prev_op[pre_rtarget],
JUMP_TF, target))) |
set(self.remove_mid_line_ifs(self.rem_or(start, prev_op[pre_rtarget],
(opc.JUMP_IF_FALSE,
opc.JUMP_IF_TRUE,
opc.JUMP_ABSOLUTE),
pre_rtarget, True)))))):
pass
else:
fix = None
jump_ifs = self.all_instr(start, self.next_stmt[offset],
opc.JUMP_IF_FALSE)
last_jump_good = True
for j in jump_ifs:
if target == self.get_target(j):
if self.lines[j].next == j + 3 and last_jump_good:
fix = j
break
else:
last_jump_good = False
self.fixed_jumps[offset] = fix or match[-1]
return
else:
self.fixed_jumps[offset] = match[-1]
return
# op == JUMP_IF_TRUE
else:
next = self.next_stmt[offset]
if prev_op[next] == offset:
pass
elif self.is_jump_forward(next) and target == self.get_target(next):
if code[prev_op[next]] == opc.JUMP_IF_FALSE:
if (code[next] == self.opc.JUMP_FORWARD
or target != rtarget
or code[prev_op[pre_rtarget]] not in
(self.opc.JUMP_ABSOLUTE, self.opc.RETURN_VALUE)):
self.fixed_jumps[offset] = prev_op[next]
return
elif (code[next] == self.opc.JUMP_ABSOLUTE and self.is_jump_forward(target) and
self.get_target(target) == self.get_target(next)):
self.fixed_jumps[offset] = prev_op[next]
return
# Don't add a struct for a while test, it's already taken care of
if offset in self.ignore_if:
return
if (code[pre_rtarget] == self.opc.JUMP_ABSOLUTE and
pre_rtarget in self.stmts and
pre_rtarget != offset and
prev_op[pre_rtarget] != offset and
not (code[rtarget] == self.opc.JUMP_ABSOLUTE and
code[rtarget+3] == self.opc.POP_BLOCK and
code[prev_op[pre_rtarget]] != self.opc.JUMP_ABSOLUTE)):
rtarget = pre_rtarget
# Does the "jump if" jump beyond a jump op?
# That is, we have something like:
# JUMP_IF_FALSE HERE
# ...
# JUMP_FORWARD
# HERE:
#
# If so, this can be block inside an "if" statement
# or a conditional assignment like:
# x = 1 if x else 2
#
# There are other contexts we may need to consider
# like whether the target is "END_FINALLY"
# or if the condition jump is to a forward location
if self.is_jump_forward(pre_rtarget):
if_end = self.get_target(pre_rtarget)
# If the jump target is back, we are looping
if (if_end < pre_rtarget and
(code[prev_op[if_end]] == self.opc.SETUP_LOOP)):
if (if_end > start):
return
end = self.restrict_to_parent(if_end, parent)
self.structs.append({'type': 'if-then',
'start': start,
'end': pre_rtarget})
self.not_continue.add(pre_rtarget)
# if rtarget < end and (
# code[rtarget] not in (self.opc.END_FINALLY,
# self.opc.JUMP_ABSOLUTE) and
# code[prev_op[pre_rtarget]] not in (self.opc.POP_EXCEPT,
# self.opc.END_FINALLY)):
# self.structs.append({'type': 'else',
# 'start': rtarget,
# 'end': end})
# self.else_start[rtarget] = end
elif self.is_jump_back(pre_rtarget):
if_end = rtarget
self.structs.append({'type': 'if-then',
'start': start,
'end': pre_rtarget})
self.not_continue.add(pre_rtarget)
elif code[pre_rtarget] in (self.opc.RETURN_VALUE,
self.opc.BREAK_LOOP):
self.structs.append({'type': 'if-then',
'start': start,
'end': rtarget})
# It is important to distingish if this return is inside some sort
# except block return
jump_prev = prev_op[offset]
if self.is_pypy and code[jump_prev] == self.opc.COMPARE_OP:
if self.opc.cmp_op[code[jump_prev+1]] == 'exception match':
return
if self.version >= 3.5:
# Python 3.5 may remove as dead code a JUMP
# instruction after a RETURN_VALUE. So we check
# based on seeing SETUP_EXCEPT various places.
if code[rtarget] == self.opc.SETUP_EXCEPT:
return
# Check that next instruction after pops and jump is
# not from SETUP_EXCEPT
next_op = rtarget
if code[next_op] == self.opc.POP_BLOCK:
next_op += self.op_size(self.code[next_op])
if code[next_op] == self.opc.JUMP_ABSOLUTE:
next_op += self.op_size(self.code[next_op])
if next_op in targets:
for try_op in targets[next_op]:
come_from_op = code[try_op]
if come_from_op == self.opc.SETUP_EXCEPT:
return
pass
pass
if code[pre_rtarget] == self.opc.RETURN_VALUE:
self.return_end_ifs.add(pre_rtarget)
else:
self.fixed_jumps[offset] = rtarget
self.not_continue.add(pre_rtarget)
elif op == self.opc.SETUP_EXCEPT:
target = self.get_target(offset)
end = self.restrict_to_parent(target, parent)
self.fixed_jumps[offset] = end
elif op == self.opc.SETUP_FINALLY:
target = self.get_target(offset)
end = self.restrict_to_parent(target, parent)
self.fixed_jumps[offset] = end
elif op in self.jump_if_pop:
target = self.get_target(offset)
if target > offset:
unop_target = self.last_instr(offset, target, self.opc.JUMP_FORWARD, target)
if unop_target and code[unop_target+3] != self.opc.ROT_TWO:
self.fixed_jumps[offset] = unop_target
else:
self.fixed_jumps[offset] = self.restrict_to_parent(target, parent)
pass
pass
elif self.version >= 3.5:
# 3.5+ has Jump optimization which too often causes RETURN_VALUE to get
# misclassified as RETURN_END_IF. Handle that here.
# In RETURN_VALUE, JUMP_ABSOLUTE, RETURN_VALUE is never RETURN_END_IF
if op == self.opc.RETURN_VALUE:
if (offset+1 < len(code) and code[offset+1] == self.opc.JUMP_ABSOLUTE and
offset in self.return_end_ifs):
self.return_end_ifs.remove(offset)
pass
pass
elif op == self.opc.JUMP_FORWARD:
# If we have:
# JUMP_FORWARD x, [non-jump, insns], RETURN_VALUE, x:
# then RETURN_VALUE is not RETURN_END_IF
rtarget = self.get_target(offset)
rtarget_prev = self.prev[rtarget]
if (code[rtarget_prev] == self.opc.RETURN_VALUE and
rtarget_prev in self.return_end_ifs):
i = rtarget_prev
while i != offset:
if code[i] in [opc.JUMP_FORWARD, opc.JUMP_ABSOLUTE]:
return
i = self.prev[i]
self.return_end_ifs.remove(rtarget_prev)
pass
return
def rem_or(self, start, end, instr, target=None, include_beyond_target=False):
"""
Find offsets of all requested <instr> between <start> and <end>,
optionally <target>ing specified offset, and return list found
<instr> offsets which are not within any POP_JUMP_IF_TRUE jumps.
"""
assert(start>=0 and end<=len(self.code) and start <= end)
# Find all offsets of requested instructions
instr_offsets = self.all_instr(start, end, instr, target, include_beyond_target)
# Get all JUMP_IF_TRUE (or) offsets
pjit_offsets = self.all_instr(start, end, opc.JUMP_IF_TRUE)
filtered = []
for pjit_offset in pjit_offsets:
pjit_tgt = self.get_target(pjit_offset) - 3
for instr_offset in instr_offsets:
if instr_offset <= pjit_offset or instr_offset >= pjit_tgt:
filtered.append(instr_offset)
instr_offsets = filtered
filtered = []
return instr_offsets
if __name__ == "__main__":
from uncompyle6 import PYTHON_VERSION
if PYTHON_VERSION == 3.0:

View File

@@ -66,7 +66,8 @@ class Token:
pattr = self.pattr
if self.opc:
if self.op in self.opc.hasjrel:
pattr = "to " + self.pattr
if not self.pattr.startswith('to '):
pattr = "to " + self.pattr
elif self.op in self.opc.hasjabs:
self.pattr= str(self.pattr)
if not self.pattr.startswith('to '):

View File

@@ -0,0 +1,347 @@
# Copyright (c) 2017 by Rocky Bernstein
"""Constants used in pysource.py"""
import re, sys
from uncompyle6.parsers.astnode import AST
from uncompyle6 import PYTHON3
from uncompyle6.scanners.tok import Token, NoneToken
if PYTHON3:
minint = -sys.maxsize-1
maxint = sys.maxsize
else:
minint = -sys.maxint-1
maxint = sys.maxint
LINE_LENGTH = 80
# Some ASTs used for comparing code fragments (like 'return None' at
# the end of functions).
RETURN_LOCALS = AST('return_stmt',
[ AST('ret_expr', [AST('expr', [ Token('LOAD_LOCALS') ])]),
Token('RETURN_VALUE')])
NONE = AST('expr', [ NoneToken ] )
RETURN_NONE = AST('stmt',
[ AST('return_stmt',
[ NONE, Token('RETURN_VALUE')]) ])
PASS = AST('stmts',
[ AST('sstmt',
[ AST('stmt',
[ AST('passstmt', [])])])])
ASSIGN_DOC_STRING = lambda doc_string: \
AST('stmt',
[ AST('assign',
[ AST('expr', [ Token('LOAD_CONST', pattr=doc_string) ]),
AST('designator', [ Token('STORE_NAME', pattr='__doc__')])
])])
NAME_MODULE = AST('stmt',
[ AST('assign',
[ AST('expr',
[Token('LOAD_NAME', pattr='__name__', offset=0, has_arg=True)]),
AST('designator',
[ Token('STORE_NAME', pattr='__module__', offset=3, has_arg=True)])
])])
# God intended \t, but Python has decided to use 4 spaces.
# If you want real tabs, use Go.
# TAB = '\t'
TAB = ' ' * 4
INDENT_PER_LEVEL = ' ' # additional intent per pretty-print level
TABLE_R = {
'STORE_ATTR': ( '%c.%[1]{pattr}', 0),
# 'STORE_SUBSCR': ( '%c[%c]', 0, 1 ),
'DELETE_ATTR': ( '%|del %c.%[-1]{pattr}\n', 0 ),
# 'EXEC_STMT': ( '%|exec %c in %[1]C\n', 0, (0,maxint,', ') ),
}
TABLE_R0 = {
# 'BUILD_LIST': ( '[%C]', (0,-1,', ') ),
# 'BUILD_TUPLE': ( '(%C)', (0,-1,', ') ),
# 'CALL_FUNCTION': ( '%c(%P)', 0, (1,-1,', ') ),
}
TABLE_DIRECT = {
'BINARY_ADD': ( '+' ,),
'BINARY_SUBTRACT': ( '-' ,),
'BINARY_MULTIPLY': ( '*' ,),
'BINARY_DIVIDE': ( '/' ,),
'BINARY_MATRIX_MULTIPLY': ( '@' ,),
'BINARY_TRUE_DIVIDE': ( '/' ,),
'BINARY_FLOOR_DIVIDE': ( '//' ,),
'BINARY_MODULO': ( '%%',),
'BINARY_POWER': ( '**',),
'BINARY_LSHIFT': ( '<<',),
'BINARY_RSHIFT': ( '>>',),
'BINARY_AND': ( '&' ,),
'BINARY_OR': ( '|' ,),
'BINARY_XOR': ( '^' ,),
'INPLACE_ADD': ( '+=' ,),
'INPLACE_SUBTRACT': ( '-=' ,),
'INPLACE_MULTIPLY': ( '*=' ,),
'INPLACE_MATRIX_MULTIPLY': ( '@=' ,),
'INPLACE_DIVIDE': ( '/=' ,),
'INPLACE_TRUE_DIVIDE': ( '/=' ,),
'INPLACE_FLOOR_DIVIDE': ( '//=' ,),
'INPLACE_MODULO': ( '%%=',),
'INPLACE_POWER': ( '**=',),
'INPLACE_LSHIFT': ( '<<=',),
'INPLACE_RSHIFT': ( '>>=',),
'INPLACE_AND': ( '&=' ,),
'INPLACE_OR': ( '|=' ,),
'INPLACE_XOR': ( '^=' ,),
'binary_expr': ( '%c %c %c', 0, -1, 1 ),
'UNARY_POSITIVE': ( '+',),
'UNARY_NEGATIVE': ( '-',),
'UNARY_INVERT': ( '~%c'),
'unary_expr': ( '%c%c', 1, 0),
'unary_not': ( 'not %c', 0 ),
'unary_convert': ( '`%c`', 0 ),
'get_iter': ( 'iter(%c)', 0 ),
'slice0': ( '%c[:]', 0 ),
'slice1': ( '%c[%p:]', 0, (1, 100) ),
'slice2': ( '%c[:%p]', 0, (1, 100) ),
'slice3': ( '%c[%p:%p]', 0, (1, 100), (2, 100) ),
'IMPORT_FROM': ( '%{pattr}', ),
'load_attr': ( '%c.%[1]{pattr}', 0),
'LOAD_FAST': ( '%{pattr}', ),
'LOAD_NAME': ( '%{pattr}', ),
'LOAD_CLASSNAME': ( '%{pattr}', ),
'LOAD_GLOBAL': ( '%{pattr}', ),
'LOAD_DEREF': ( '%{pattr}', ),
'LOAD_LOCALS': ( 'locals()', ),
'LOAD_ASSERT': ( '%{pattr}', ),
# 'LOAD_CONST': ( '%{pattr}', ), # handled by n_LOAD_CONST
'DELETE_FAST': ( '%|del %{pattr}\n', ),
'DELETE_NAME': ( '%|del %{pattr}\n', ),
'DELETE_GLOBAL': ( '%|del %{pattr}\n', ),
'delete_subscr': ( '%|del %c[%c]\n', 0, 1,),
'binary_subscr': ( '%c[%p]', 0, (1, 100)),
'binary_subscr2': ( '%c[%p]', 0, (1, 100)),
'store_subscr': ( '%c[%c]', 0, 1),
'STORE_FAST': ( '%{pattr}', ),
'STORE_NAME': ( '%{pattr}', ),
'STORE_GLOBAL': ( '%{pattr}', ),
'STORE_DEREF': ( '%{pattr}', ),
'unpack': ( '%C%,', (1, maxint, ', ') ),
# This nonterminal we create on the fly in semantic routines
'unpack_w_parens': ( '(%C%,)', (1, maxint, ', ') ),
'unpack_list': ( '[%C]', (1, maxint, ', ') ),
'build_tuple2': ( '%P', (0, -1, ', ', 100) ),
# 'list_compr': ( '[ %c ]', -2), # handled by n_list_compr
'list_iter': ( '%c', 0),
'list_for': ( ' for %c in %c%c', 2, 0, 3 ),
'list_if': ( ' if %c%c', 0, 2 ),
'list_if_not': ( ' if not %p%c', (0, 22), 2 ),
'lc_body': ( '', ), # ignore when recusing
'comp_iter': ( '%c', 0),
'comp_if': ( ' if %c%c', 0, 2 ),
'comp_ifnot': ( ' if not %p%c', (0, 22), 2 ),
'comp_body': ( '', ), # ignore when recusing
'set_comp_body': ( '%c', 0 ),
'gen_comp_body': ( '%c', 0 ),
'dict_comp_body': ( '%c:%c', 1, 0 ),
'assign': ( '%|%c = %p\n', -1, (0, 200) ),
# The 2nd parameter should have a = suffix.
# There is a rule with a 4th parameter "designator"
# which we don't use here.
'augassign1': ( '%|%c %c %c\n', 0, 2, 1),
'augassign2': ( '%|%c.%[2]{pattr} %c %c\n', 0, -3, -4),
'designList': ( '%c = %c', 0, -1 ),
'and': ( '%c and %c', 0, 2 ),
'ret_and': ( '%c and %c', 0, 2 ),
'and2': ( '%c', 3 ),
'or': ( '%c or %c', 0, 2 ),
'ret_or': ( '%c or %c', 0, 2 ),
'conditional': ( '%p if %p else %p', (2, 27), (0, 27), (4, 27)),
'ret_cond': ( '%p if %p else %p', (2, 27), (0, 27), (-1, 27)),
'conditionalnot': ( '%p if not %p else %p', (2, 27), (0, 22), (4, 27)),
'ret_cond_not': ( '%p if not %p else %p', (2, 27), (0, 22), (-1, 27)),
'conditional_lambda': ( '(%c if %c else %c)', 2, 0, 3),
'return_lambda': ('%c', 0),
'compare': ( '%p %[-1]{pattr} %p', (0, 19), (1, 19) ),
'cmp_list': ( '%p %p', (0, 20), (1, 19)),
'cmp_list1': ( '%[3]{pattr} %p %p', (0, 19), (-2, 19)),
'cmp_list2': ( '%[1]{pattr} %p', (0, 19)),
# 'classdef': (), # handled by n_classdef()
'funcdef': ( '\n\n%|def %c\n', -2), # -2 to handle closures
'funcdefdeco': ( '\n\n%c', 0),
'mkfuncdeco': ( '%|@%c\n%c', 0, 1),
'mkfuncdeco0': ( '%|def %c\n', 0),
'classdefdeco': ( '\n\n%c', 0),
'classdefdeco1': ( '%|@%c\n%c', 0, 1),
'kwarg': ( '%[0]{pattr}=%c', 1),
'kwargs': ( '%D', (0, maxint, ', ') ),
'assert_expr_or': ( '%c or %c', 0, 2 ),
'assert_expr_and': ( '%c and %c', 0, 2 ),
'print_items_stmt': ( '%|print %c%c,\n', 0, 2), # Python 2 only
'print_items_nl_stmt': ( '%|print %c%c\n', 0, 2),
'print_item': ( ', %c', 0),
'print_nl': ( '%|print\n', ),
'print_to': ( '%|print >> %c, %c,\n', 0, 1 ),
'print_to_nl': ( '%|print >> %c, %c\n', 0, 1 ),
'print_nl_to': ( '%|print >> %c\n', 0 ),
'print_to_items': ( '%C', (0, 2, ', ') ),
'call_stmt': ( '%|%p\n', (0, 200)),
'break_stmt': ( '%|break\n', ),
'continue_stmt': ( '%|continue\n', ),
'raise_stmt0': ( '%|raise\n', ),
'raise_stmt1': ( '%|raise %c\n', 0),
'raise_stmt3': ( '%|raise %c, %c, %c\n', 0, 1, 2),
# 'yield': ( 'yield %c', 0),
# 'return_stmt': ( '%|return %c\n', 0),
'ifstmt': ( '%|if %c:\n%+%c%-', 0, 1 ),
'iflaststmt': ( '%|if %c:\n%+%c%-', 0, 1 ),
'iflaststmtl': ( '%|if %c:\n%+%c%-', 0, 1 ),
'testtrue': ( 'not %p', (0, 22) ),
'ifelsestmt': ( '%|if %c:\n%+%c%-%|else:\n%+%c%-', 0, 1, 3 ),
'ifelsestmtc': ( '%|if %c:\n%+%c%-%|else:\n%+%c%-', 0, 1, 3 ),
'ifelsestmtl': ( '%|if %c:\n%+%c%-%|else:\n%+%c%-', 0, 1, 3 ),
'ifelifstmt': ( '%|if %c:\n%+%c%-%c', 0, 1, 3 ),
'elifelifstmt': ( '%|elif %c:\n%+%c%-%c', 0, 1, 3 ),
'elifstmt': ( '%|elif %c:\n%+%c%-', 0, 1 ),
'elifelsestmt': ( '%|elif %c:\n%+%c%-%|else:\n%+%c%-', 0, 1, 3 ),
'ifelsestmtr': ( '%|if %c:\n%+%c%-%|else:\n%+%c%-', 0, 1, 2 ),
'elifelsestmtr': ( '%|elif %c:\n%+%c%-%|else:\n%+%c%-\n\n', 0, 1, 2 ),
'whileTruestmt': ( '%|while True:\n%+%c%-\n\n', 1 ),
'whilestmt': ( '%|while %c:\n%+%c%-\n\n', 1, 2 ),
'while1stmt': ( '%|while 1:\n%+%c%-\n\n', 1 ),
'while1elsestmt': ( '%|while 1:\n%+%c%-%|else:\n%+%c%-\n\n', 1, -2 ),
'whileelsestmt': ( '%|while %c:\n%+%c%-%|else:\n%+%c%-\n\n', 1, 2, -2 ),
'whileelselaststmt': ( '%|while %c:\n%+%c%-%|else:\n%+%c%-', 1, 2, -2 ),
'forstmt': ( '%|for %c in %c:\n%+%c%-\n\n', 3, 1, 4 ),
'forelsestmt': (
'%|for %c in %c:\n%+%c%-%|else:\n%+%c%-\n\n', 3, 1, 4, -2),
'forelselaststmt': (
'%|for %c in %c:\n%+%c%-%|else:\n%+%c%-', 3, 1, 4, -2),
'forelselaststmtl': (
'%|for %c in %c:\n%+%c%-%|else:\n%+%c%-\n\n', 3, 1, 4, -2),
'trystmt': ( '%|try:\n%+%c%-%c\n\n', 1, 3 ),
'tryelsestmt': ( '%|try:\n%+%c%-%c%|else:\n%+%c%-\n\n', 1, 3, 4 ),
'tryelsestmtc': ( '%|try:\n%+%c%-%c%|else:\n%+%c%-', 1, 3, 4 ),
'tryelsestmtl': ( '%|try:\n%+%c%-%c%|else:\n%+%c%-', 1, 3, 4 ),
'tf_trystmt': ( '%c%-%c%+', 1, 3 ),
'tf_tryelsestmt': ( '%c%-%c%|else:\n%+%c', 1, 3, 4 ),
'tryfinallystmt': ( '%|try:\n%+%c%-%|finally:\n%+%c%-\n\n', 1, 5 ),
'except': ( '%|except:\n%+%c%-', 3 ),
'except_cond1': ( '%|except %c:\n', 1 ),
'except_suite': ( '%+%c%-%C', 0, (1, maxint, '') ),
'except_suite_finalize': ( '%+%c%-%C', 1, (3, maxint, '') ),
'withstmt': ( '%|with %c:\n%+%c%-', 0, 3),
'withasstmt': ( '%|with %c as %c:\n%+%c%-', 0, 2, 3),
'passstmt': ( '%|pass\n', ),
'STORE_FAST': ( '%{pattr}', ),
'kv': ( '%c: %c', 3, 1 ),
'kv2': ( '%c: %c', 1, 2 ),
'mapexpr': ( '{%[1]C}', (0, maxint, ', ') ),
'importstmt': ( '%|import %c\n', 2),
'importfrom': ( '%|from %[2]{pattr} import %c\n', 3 ),
'importstar': ( '%|from %[2]{pattr} import *\n', ),
}
MAP_DIRECT = (TABLE_DIRECT, )
MAP_R0 = (TABLE_R0, -1, 0)
MAP_R = (TABLE_R, -1)
MAP = {
'stmt': MAP_R,
'call_function': MAP_R,
'del_stmt': MAP_R,
'designator': MAP_R,
'exprlist': MAP_R0,
}
PRECEDENCE = {
'build_list': 0,
'mapexpr': 0,
'unary_convert': 0,
'dictcomp': 0,
'setcomp': 0,
'list_compr': 0,
'genexpr': 0,
'load_attr': 2,
'binary_subscr': 2,
'binary_subscr2': 2,
'slice0': 2,
'slice1': 2,
'slice2': 2,
'slice3': 2,
'buildslice2': 2,
'buildslice3': 2,
'call_function': 2,
'BINARY_POWER': 4,
'unary_expr': 6,
'BINARY_MULTIPLY': 8,
'BINARY_DIVIDE': 8,
'BINARY_TRUE_DIVIDE': 8,
'BINARY_FLOOR_DIVIDE': 8,
'BINARY_MODULO': 8,
'BINARY_ADD': 10,
'BINARY_SUBTRACT': 10,
'BINARY_LSHIFT': 12,
'BINARY_RSHIFT': 12,
'BINARY_AND': 14,
'BINARY_XOR': 16,
'BINARY_OR': 18,
'cmp': 20,
'unary_not': 22,
'and': 24,
'ret_and': 24,
'or': 26,
'ret_or': 26,
'conditional': 28,
'conditionalnot': 28,
'ret_cond': 28,
'ret_cond_not': 28,
'_mklambda': 30,
'yield': 101,
'yield_from': 101
}
ASSIGN_TUPLE_PARAM = lambda param_name: \
AST('expr', [ Token('LOAD_FAST', pattr=param_name) ])
escape = re.compile(r'''
(?P<prefix> [^%]* )
% ( \[ (?P<child> -? \d+ ) \] )?
((?P<type> [^{] ) |
( [{] (?P<expr> [^}]* ) [}] ))
''', re.VERBOSE)

View File

@@ -69,17 +69,22 @@ from uncompyle6.show import (
maybe_show_ast_param_default,
)
from uncompyle6.semantics.pysource import AST, INDENT_PER_LEVEL, NONE, PRECEDENCE, \
ParserError, TABLE_DIRECT, escape, find_globals, minint, MAP
from uncompyle6.parsers.astnode import AST
from uncompyle6.semantics.pysource import (
ParserError, find_globals, StringIO)
from uncompyle6.semantics.consts import (
INDENT_PER_LEVEL, NONE, PRECEDENCE,
TABLE_DIRECT, escape, minint, MAP
)
from uncompyle6.semantics.make_function import find_all_globals, find_none
if PYTHON3:
from itertools import zip_longest
from io import StringIO
else:
from itertools import izip_longest as zip_longest
from StringIO import StringIO
from spark_parser import DEFAULT_DEBUG as PARSER_DEFAULT_DEBUG
@@ -97,14 +102,14 @@ TABLE_DIRECT_FRAGMENT = {
'importstmt': ( '%|import %c%x\n', 2, (2, (0, 1)), ),
'importfrom': ( '%|from %[2]{pattr}%x import %c\n', (2, (0, 1)), 3),
'importmultiple': ( '%|import%b %c%c\n', 0, 2, 3 ),
'list_for': (' for %c%x in %c%c', 2, (2,(1,)), 0, 3 ),
'forstmt': ( '%|for%b %c%x in %c:\n%+%c%-\n\n', 0, 3, (3, (2,)), 1, 4 ),
'list_for': (' for %c%x in %c%c', 2, (2, (1, )), 0, 3 ),
'forstmt': ( '%|for%b %c%x in %c:\n%+%c%-\n\n', 0, 3, (3, (2, )), 1, 4 ),
'forelsestmt': (
'%|for %c in %c%x:\n%+%c%-%|else:\n%+%c%-\n\n', 3, (3, (2,)), 1, 4, -2),
'forelselaststmt': (
'%|for %c%x in %c:\n%+%c%-%|else:\n%+%c%-', 3, (3, (2,)), 1, 4, -2),
'forelselaststmtl': (
'%|for %c%x in %c:\n%+%c%-%|else:\n%+%c%-\n\n', 3, (3, (2,)), 1, 4, -2),
'%|for %c%x in %c:\n%+%c%-%|else:\n%+%c%-\n\n', 3, (3, (2, )), 1, 4, -2),
'whilestmt': ( '%|while%b %c:\n%+%c%-\n\n', 0, 1, 2 ),
'whileelsestmt': ( '%|while%b %c:\n%+%c%-%|else:\n%+%c%-\n\n', 0, 1, 2, -2 ),
@@ -163,7 +168,7 @@ class FragmentsWalker(pysource.SourceWalker, object):
None)
def set_pos_info(self, node, start, finish, name=None):
if name == None: name = self.name
if name is None: name = self.name
if hasattr(node, 'offset'):
self.offsets[name, node.offset] = \
NodeInfo(node = node, start = start, finish = finish)
@@ -583,7 +588,7 @@ class FragmentsWalker(pysource.SourceWalker, object):
self.set_pos_info(node[-3], start, len(self.f.getvalue()))
start = len(self.f.getvalue())
self.preorder(ast[iter_index])
self.set_pos_info(iter_index, start, len(self.f.getvalue()))
self.set_pos_info(ast[iter_index], start, len(self.f.getvalue()))
self.prec = p
def comprehension_walk3(self, node, iter_index, code_index=-5):
@@ -622,7 +627,7 @@ class FragmentsWalker(pysource.SourceWalker, object):
n = ast[iter_index]
assert n == 'list_iter'
## FIXME: I'm not totally sure this is right.
# FIXME: I'm not totally sure this is right.
# find innermost node
if_node = None

View File

@@ -71,7 +71,11 @@ def make_function3_annotate(self, node, isLambda, nested=1,
# MAKE_FUNCTION_... or MAKE_CLOSURE_...
assert node[-1].type.startswith('MAKE_')
annotate_tuple = node[annotate_last]
annotate_tuple = None
for annotate_last in range(len(node)-1, -1, -1):
if node[annotate_last] == 'annotate_tuple':
annotate_tuple = node[annotate_last]
break
annotate_args = {}
if (annotate_tuple == 'annotate_tuple'
@@ -148,13 +152,19 @@ def make_function3_annotate(self, node, isLambda, nested=1,
suffix = ''
for param in paramnames[:i]:
self.write(suffix, param)
if param in annotate_args:
value, string = annotate_args[param]
if string:
self.write(': "%s"' % value)
else:
self.write(': %s' % value)
suffix = ', '
if param in annotate_tuple[0].attr:
p = annotate_tuple[0].attr.index(param)
self.write(': ')
self.preorder(node[p])
if (line_number != self.line_number):
suffix = ",\n" + indent
line_number = self.line_number
# value, string = annotate_args[param]
# if string:
# self.write(': "%s"' % value)
# else:
# self.write(': %s' % value)
suffix = ', ' if i > 0 else ''
for n in node:
@@ -163,7 +173,10 @@ def make_function3_annotate(self, node, isLambda, nested=1,
param = paramnames[i]
self.write(param)
if param in annotate_args:
self.write(':"%s' % annotate_args[param])
aa = annotate_args[param]
if isinstance(aa, tuple):
aa = aa[0]
self.write(': "%s"' % aa)
self.write('=')
i += 1
self.preorder(n)
@@ -189,6 +202,9 @@ def make_function3_annotate(self, node, isLambda, nested=1,
i = 0
for n in node[0]:
if n == 'kwarg':
if (line_number != self.line_number):
self.write("\n" + indent)
line_number = self.line_number
self.write('%s=' % n[0].pattr)
self.preorder(n[1])
if i < last:
@@ -207,19 +223,24 @@ def make_function3_annotate(self, node, isLambda, nested=1,
self.write(": ")
else:
self.write(')')
if 'return' in annotate_args:
value, string = annotate_args['return']
if string:
self.write(' -> "%s"' % value)
else:
self.write(' -> %s' % value)
if 'return' in annotate_tuple[0].attr:
if (line_number != self.line_number):
self.write("\n" + indent)
line_number = self.line_number
self.write(' -> ')
# value, string = annotate_args['return']
# if string:
# self.write(' -> "%s"' % value)
# else:
# self.write(' -> %s' % value)
self.preorder(node[annotate_last-1])
self.println(":")
if (len(code.co_consts) > 0 and
code.co_consts[0] is not None and not isLambda): # ugly
# docstring exists, dump it
self.print_docstring(indent, code.co_consts[0])
print_docstring(self, self.indent, code.co_consts[0])
code._tokens = None # save memory
assert ast == 'stmts'

View File

@@ -69,21 +69,30 @@ methods implement most of the below.
"""
from __future__ import print_function
import sys, re
import sys
from uncompyle6 import PYTHON3
from xdis.code import iscode
from xdis.util import COMPILER_FLAG_BIT
from uncompyle6.parser import get_python_parser
from uncompyle6.parsers.astnode import AST
from spark_parser import GenericASTTraversal, DEFAULT_DEBUG as PARSER_DEFAULT_DEBUG
from uncompyle6.scanner import Code, get_scanner
from uncompyle6.scanners.tok import Token, NoneToken
import uncompyle6.parser as python_parser
from uncompyle6.semantics.make_function import (
make_function2, make_function3, make_function3_annotate, find_globals)
from uncompyle6.semantics.parser_error import ParserError
from uncompyle6.semantics.check_ast import checker
from uncompyle6.semantics.helper import print_docstring
from uncompyle6.scanners.tok import Token
from uncompyle6.semantics.consts import (
LINE_LENGTH, RETURN_LOCALS, NONE, RETURN_NONE, PASS,
ASSIGN_DOC_STRING, NAME_MODULE, TAB,
INDENT_PER_LEVEL, TABLE_R, TABLE_DIRECT, MAP_DIRECT,
MAP, PRECEDENCE, ASSIGN_TUPLE_PARAM, escape, maxint, minint)
from uncompyle6.show import (
maybe_show_ast,
@@ -91,344 +100,8 @@ from uncompyle6.show import (
if PYTHON3:
from io import StringIO
minint = -sys.maxsize-1
maxint = sys.maxsize
else:
from StringIO import StringIO
minint = -sys.maxint-1
maxint = sys.maxint
LINE_LENGTH = 80
# Some ASTs used for comparing code fragments (like 'return None' at
# the end of functions).
RETURN_LOCALS = AST('return_stmt',
[ AST('ret_expr', [AST('expr', [ Token('LOAD_LOCALS') ])]),
Token('RETURN_VALUE')])
NONE = AST('expr', [ NoneToken ] )
RETURN_NONE = AST('stmt',
[ AST('return_stmt',
[ NONE, Token('RETURN_VALUE')]) ])
PASS = AST('stmts',
[ AST('sstmt',
[ AST('stmt',
[ AST('passstmt', [])])])])
ASSIGN_DOC_STRING = lambda doc_string: \
AST('stmt',
[ AST('assign',
[ AST('expr', [ Token('LOAD_CONST', pattr=doc_string) ]),
AST('designator', [ Token('STORE_NAME', pattr='__doc__')])
])])
BUILD_TUPLE_0 = AST('expr',
[ AST('build_list',
[ Token('BUILD_TUPLE_0') ])])
NAME_MODULE = AST('stmt',
[ AST('assign',
[ AST('expr', [Token('LOAD_NAME', pattr='__name__')]),
AST('designator', [ Token('STORE_NAME', pattr='__module__')])
])])
# TAB = '\t' # as God intended
TAB = ' ' *4 # is less spacy than "\t"
INDENT_PER_LEVEL = ' ' # additional intent per pretty-print level
TABLE_R = {
'STORE_ATTR': ( '%c.%[1]{pattr}', 0),
# 'STORE_SUBSCR': ( '%c[%c]', 0, 1 ),
'DELETE_ATTR': ( '%|del %c.%[-1]{pattr}\n', 0 ),
# 'EXEC_STMT': ( '%|exec %c in %[1]C\n', 0, (0,maxint,', ') ),
}
TABLE_R0 = {
# 'BUILD_LIST': ( '[%C]', (0,-1,', ') ),
# 'BUILD_TUPLE': ( '(%C)', (0,-1,', ') ),
# 'CALL_FUNCTION': ( '%c(%P)', 0, (1,-1,', ') ),
}
TABLE_DIRECT = {
'BINARY_ADD': ( '+' ,),
'BINARY_SUBTRACT': ( '-' ,),
'BINARY_MULTIPLY': ( '*' ,),
'BINARY_DIVIDE': ( '/' ,),
'BINARY_MATRIX_MULTIPLY': ( '@' ,),
'BINARY_TRUE_DIVIDE': ( '/' ,),
'BINARY_FLOOR_DIVIDE': ( '//' ,),
'BINARY_MODULO': ( '%%',),
'BINARY_POWER': ( '**',),
'BINARY_LSHIFT': ( '<<',),
'BINARY_RSHIFT': ( '>>',),
'BINARY_AND': ( '&' ,),
'BINARY_OR': ( '|' ,),
'BINARY_XOR': ( '^' ,),
'INPLACE_ADD': ( '+=' ,),
'INPLACE_SUBTRACT': ( '-=' ,),
'INPLACE_MULTIPLY': ( '*=' ,),
'INPLACE_MATRIX_MULTIPLY': ( '@=' ,),
'INPLACE_DIVIDE': ( '/=' ,),
'INPLACE_TRUE_DIVIDE': ( '/=' ,),
'INPLACE_FLOOR_DIVIDE': ( '//=' ,),
'INPLACE_MODULO': ( '%%=',),
'INPLACE_POWER': ( '**=',),
'INPLACE_LSHIFT': ( '<<=',),
'INPLACE_RSHIFT': ( '>>=',),
'INPLACE_AND': ( '&=' ,),
'INPLACE_OR': ( '|=' ,),
'INPLACE_XOR': ( '^=' ,),
'binary_expr': ( '%c %c %c', 0, -1, 1 ),
'UNARY_POSITIVE': ( '+',),
'UNARY_NEGATIVE': ( '-',),
'UNARY_INVERT': ( '~%c'),
'unary_expr': ( '%c%c', 1, 0),
'unary_not': ( 'not %c', 0 ),
'unary_convert': ( '`%c`', 0 ),
'get_iter': ( 'iter(%c)', 0 ),
'slice0': ( '%c[:]', 0 ),
'slice1': ( '%c[%p:]', 0, (1, 100) ),
'slice2': ( '%c[:%p]', 0, (1, 100) ),
'slice3': ( '%c[%p:%p]', 0, (1, 100), (2, 100) ),
'IMPORT_FROM': ( '%{pattr}', ),
'load_attr': ( '%c.%[1]{pattr}', 0),
'LOAD_FAST': ( '%{pattr}', ),
'LOAD_NAME': ( '%{pattr}', ),
'LOAD_CLASSNAME': ( '%{pattr}', ),
'LOAD_GLOBAL': ( '%{pattr}', ),
'LOAD_DEREF': ( '%{pattr}', ),
'LOAD_LOCALS': ( 'locals()', ),
'LOAD_ASSERT': ( '%{pattr}', ),
# 'LOAD_CONST': ( '%{pattr}', ), # handled by n_LOAD_CONST
'DELETE_FAST': ( '%|del %{pattr}\n', ),
'DELETE_NAME': ( '%|del %{pattr}\n', ),
'DELETE_GLOBAL': ( '%|del %{pattr}\n', ),
'delete_subscr': ( '%|del %c[%c]\n', 0, 1,),
'binary_subscr': ( '%c[%p]', 0, (1, 100)),
'binary_subscr2': ( '%c[%p]', 0, (1, 100)),
'store_subscr': ( '%c[%c]', 0, 1),
'STORE_FAST': ( '%{pattr}', ),
'STORE_NAME': ( '%{pattr}', ),
'STORE_GLOBAL': ( '%{pattr}', ),
'STORE_DEREF': ( '%{pattr}', ),
'unpack': ( '%C%,', (1, maxint, ', ') ),
# This nonterminal we create on the fly in semantic routines
'unpack_w_parens': ( '(%C%,)', (1, maxint, ', ') ),
'unpack_list': ( '[%C]', (1, maxint, ', ') ),
'build_tuple2': ( '%P', (0, -1, ', ', 100) ),
# 'list_compr': ( '[ %c ]', -2), # handled by n_list_compr
'list_iter': ( '%c', 0),
'list_for': ( ' for %c in %c%c', 2, 0, 3 ),
'list_if': ( ' if %c%c', 0, 2 ),
'list_if_not': ( ' if not %p%c', (0, 22), 2 ),
'lc_body': ( '', ), # ignore when recusing
'comp_iter': ( '%c', 0),
'comp_if': ( ' if %c%c', 0, 2 ),
'comp_ifnot': ( ' if not %p%c', (0, 22), 2 ),
'comp_body': ( '', ), # ignore when recusing
'set_comp_body': ( '%c', 0 ),
'gen_comp_body': ( '%c', 0 ),
'dict_comp_body': ( '%c:%c', 1, 0 ),
'assign': ( '%|%c = %p\n', -1, (0, 200) ),
# The 2nd parameter should have a = suffix.
# There is a rule with a 4th parameter "designator"
# which we don't use here.
'augassign1': ( '%|%c %c %c\n', 0, 2, 1),
'augassign2': ( '%|%c.%[2]{pattr} %c %c\n', 0, -3, -4),
'designList': ( '%c = %c', 0, -1 ),
'and': ( '%c and %c', 0, 2 ),
'ret_and': ( '%c and %c', 0, 2 ),
'and2': ( '%c', 3 ),
'or': ( '%c or %c', 0, 2 ),
'ret_or': ( '%c or %c', 0, 2 ),
'conditional': ( '%p if %p else %p', (2, 27), (0, 27), (4, 27)),
'ret_cond': ( '%p if %p else %p', (2, 27), (0, 27), (-1, 27)),
'conditionalnot': ( '%p if not %p else %p', (2, 27), (0, 22), (4, 27)),
'ret_cond_not': ( '%p if not %p else %p', (2, 27), (0, 22), (-1, 27)),
'conditional_lambda': ( '(%c if %c else %c)', 2, 0, 3),
'return_lambda': ('%c', 0),
'compare': ( '%p %[-1]{pattr} %p', (0, 19), (1, 19) ),
'cmp_list': ( '%p %p', (0, 20), (1, 19)),
'cmp_list1': ( '%[3]{pattr} %p %p', (0, 19), (-2, 19)),
'cmp_list2': ( '%[1]{pattr} %p', (0, 19)),
# 'classdef': (), # handled by n_classdef()
'funcdef': ( '\n\n%|def %c\n', -2), # -2 to handle closures
'funcdefdeco': ( '\n\n%c', 0),
'mkfuncdeco': ( '%|@%c\n%c', 0, 1),
'mkfuncdeco0': ( '%|def %c\n', 0),
'classdefdeco': ( '\n\n%c', 0),
'classdefdeco1': ( '%|@%c\n%c', 0, 1),
'kwarg': ( '%[0]{pattr}=%c', 1),
'kwargs': ( '%D', (0, maxint, ', ') ),
'assert_expr_or': ( '%c or %c', 0, 2 ),
'assert_expr_and': ( '%c and %c', 0, 2 ),
'print_items_stmt': ( '%|print %c%c,\n', 0, 2), # Python 2 only
'print_items_nl_stmt': ( '%|print %c%c\n', 0, 2),
'print_item': ( ', %c', 0),
'print_nl': ( '%|print\n', ),
'print_to': ( '%|print >> %c, %c,\n', 0, 1 ),
'print_to_nl': ( '%|print >> %c, %c\n', 0, 1 ),
'print_nl_to': ( '%|print >> %c\n', 0 ),
'print_to_items': ( '%C', (0, 2, ', ') ),
'call_stmt': ( '%|%p\n', (0, 200)),
'break_stmt': ( '%|break\n', ),
'continue_stmt': ( '%|continue\n', ),
'raise_stmt0': ( '%|raise\n', ),
'raise_stmt1': ( '%|raise %c\n', 0),
'raise_stmt3': ( '%|raise %c, %c, %c\n', 0, 1, 2),
# 'yield': ( 'yield %c', 0),
# 'return_stmt': ( '%|return %c\n', 0),
'ifstmt': ( '%|if %c:\n%+%c%-', 0, 1 ),
'iflaststmt': ( '%|if %c:\n%+%c%-', 0, 1 ),
'iflaststmtl': ( '%|if %c:\n%+%c%-', 0, 1 ),
'testtrue': ( 'not %p', (0, 22) ),
'ifelsestmt': ( '%|if %c:\n%+%c%-%|else:\n%+%c%-', 0, 1, 3 ),
'ifelsestmtc': ( '%|if %c:\n%+%c%-%|else:\n%+%c%-', 0, 1, 3 ),
'ifelsestmtl': ( '%|if %c:\n%+%c%-%|else:\n%+%c%-', 0, 1, 3 ),
'ifelifstmt': ( '%|if %c:\n%+%c%-%c', 0, 1, 3 ),
'elifelifstmt': ( '%|elif %c:\n%+%c%-%c', 0, 1, 3 ),
'elifstmt': ( '%|elif %c:\n%+%c%-', 0, 1 ),
'elifelsestmt': ( '%|elif %c:\n%+%c%-%|else:\n%+%c%-', 0, 1, 3 ),
'ifelsestmtr': ( '%|if %c:\n%+%c%-%|else:\n%+%c%-', 0, 1, 2 ),
'elifelsestmtr': ( '%|elif %c:\n%+%c%-%|else:\n%+%c%-\n\n', 0, 1, 2 ),
'whileTruestmt': ( '%|while True:\n%+%c%-\n\n', 1 ),
'whilestmt': ( '%|while %c:\n%+%c%-\n\n', 1, 2 ),
'while1stmt': ( '%|while 1:\n%+%c%-\n\n', 1 ),
'while1elsestmt': ( '%|while 1:\n%+%c%-%|else:\n%+%c%-\n\n', 1, -2 ),
'whileelsestmt': ( '%|while %c:\n%+%c%-%|else:\n%+%c%-\n\n', 1, 2, -2 ),
'whileelselaststmt': ( '%|while %c:\n%+%c%-%|else:\n%+%c%-', 1, 2, -2 ),
'forstmt': ( '%|for %c in %c:\n%+%c%-\n\n', 3, 1, 4 ),
'forelsestmt': (
'%|for %c in %c:\n%+%c%-%|else:\n%+%c%-\n\n', 3, 1, 4, -2),
'forelselaststmt': (
'%|for %c in %c:\n%+%c%-%|else:\n%+%c%-', 3, 1, 4, -2),
'forelselaststmtl': (
'%|for %c in %c:\n%+%c%-%|else:\n%+%c%-\n\n', 3, 1, 4, -2),
'trystmt': ( '%|try:\n%+%c%-%c\n\n', 1, 3 ),
'tryelsestmt': ( '%|try:\n%+%c%-%c%|else:\n%+%c%-\n\n', 1, 3, 4 ),
'tryelsestmtc': ( '%|try:\n%+%c%-%c%|else:\n%+%c%-', 1, 3, 4 ),
'tryelsestmtl': ( '%|try:\n%+%c%-%c%|else:\n%+%c%-', 1, 3, 4 ),
'tf_trystmt': ( '%c%-%c%+', 1, 3 ),
'tf_tryelsestmt': ( '%c%-%c%|else:\n%+%c', 1, 3, 4 ),
'tryfinallystmt': ( '%|try:\n%+%c%-%|finally:\n%+%c%-\n\n', 1, 5 ),
'except': ( '%|except:\n%+%c%-', 3 ),
'except_cond1': ( '%|except %c:\n', 1 ),
'except_suite': ( '%+%c%-%C', 0, (1, maxint, '') ),
'except_suite_finalize': ( '%+%c%-%C', 1, (3, maxint, '') ),
'withstmt': ( '%|with %c:\n%+%c%-', 0, 3),
'withasstmt': ( '%|with %c as %c:\n%+%c%-', 0, 2, 3),
'passstmt': ( '%|pass\n', ),
'STORE_FAST': ( '%{pattr}', ),
'kv': ( '%c: %c', 3, 1 ),
'kv2': ( '%c: %c', 1, 2 ),
'mapexpr': ( '{%[1]C}', (0, maxint, ', ') ),
'importstmt': ( '%|import %c\n', 2),
'importfrom': ( '%|from %[2]{pattr} import %c\n', 3 ),
'importstar': ( '%|from %[2]{pattr} import *\n', ),
}
MAP_DIRECT = (TABLE_DIRECT, )
MAP_R0 = (TABLE_R0, -1, 0)
MAP_R = (TABLE_R, -1)
MAP = {
'stmt': MAP_R,
'call_function': MAP_R,
'del_stmt': MAP_R,
'designator': MAP_R,
'exprlist': MAP_R0,
}
PRECEDENCE = {
'build_list': 0,
'mapexpr': 0,
'unary_convert': 0,
'dictcomp': 0,
'setcomp': 0,
'list_compr': 0,
'genexpr': 0,
'load_attr': 2,
'binary_subscr': 2,
'binary_subscr2': 2,
'slice0': 2,
'slice1': 2,
'slice2': 2,
'slice3': 2,
'buildslice2': 2,
'buildslice3': 2,
'call_function': 2,
'BINARY_POWER': 4,
'unary_expr': 6,
'BINARY_MULTIPLY': 8,
'BINARY_DIVIDE': 8,
'BINARY_TRUE_DIVIDE': 8,
'BINARY_FLOOR_DIVIDE': 8,
'BINARY_MODULO': 8,
'BINARY_ADD': 10,
'BINARY_SUBTRACT': 10,
'BINARY_LSHIFT': 12,
'BINARY_RSHIFT': 12,
'BINARY_AND': 14,
'BINARY_XOR': 16,
'BINARY_OR': 18,
'cmp': 20,
'unary_not': 22,
'and': 24,
'ret_and': 24,
'or': 26,
'ret_or': 26,
'conditional': 28,
'conditionalnot': 28,
'ret_cond': 28,
'ret_cond_not': 28,
'_mklambda': 30,
'yield': 101,
'yield_from': 101
}
ASSIGN_TUPLE_PARAM = lambda param_name: \
AST('expr', [ Token('LOAD_FAST', pattr=param_name) ])
escape = re.compile(r'''
(?P<prefix> [^%]* )
% ( \[ (?P<child> -? \d+ ) \] )?
((?P<type> [^{] ) |
( [{] (?P<expr> [^}]* ) [}] ))
''', re.VERBOSE)
def is_docstring(node):
try:
@@ -492,7 +165,6 @@ class SourceWalker(GenericASTTraversal, object):
self.write("\n" + self.indent + INDENT_PER_LEVEL[:-1])
return self.line_number
def customize_for_version(self, is_pypy, version):
if is_pypy:
########################
@@ -537,7 +209,6 @@ class SourceWalker(GenericASTTraversal, object):
'raise_stmt2': ( '%|raise %c from %c\n', 0, 1),
})
if version < 2.0:
TABLE_DIRECT.update({
'importlist': ( '%C', (0, maxint, ', ') ),
@@ -546,6 +217,18 @@ class SourceWalker(GenericASTTraversal, object):
TABLE_DIRECT.update({
'importlist2': ( '%C', (0, maxint, ', ') ),
})
if version <= 2.4:
global NAME_MODULE
NAME_MODULE = AST('stmt',
[ AST('assign',
[ AST('expr',
[Token('LOAD_GLOBAL', pattr='__name__',
offset=0, has_arg=True)]),
AST('designator',
[ Token('STORE_NAME', pattr='__module__',
offset=3, has_arg=True)])
])])
pass
if version <= 2.3:
TABLE_DIRECT.update({
'tryfinallystmt': ( '%|try:\n%+%c%-%|finally:\n%+%c%-\n\n', 1, 4 )
@@ -575,7 +258,9 @@ class SourceWalker(GenericASTTraversal, object):
})
else:
TABLE_DIRECT.update({
'except_cond3': ( '%|except %c, %c:\n', 1, 6 ),
'except_cond3': ( '%|except %c, %c:\n', 1, 6 ),
'testtrue_then': ( 'not %p', (0, 22) ),
})
if 2.4 <= version <= 2.6:
TABLE_DIRECT.update({
@@ -608,7 +293,9 @@ class SourceWalker(GenericASTTraversal, object):
code = node[-3]
self.indentMore()
annotate_last = -4 if self.version == 3.1 else -5
for annotate_last in range(len(node)-1, -1, -1):
if node[annotate_last] == 'annotate_tuple':
break
# FIXME: handle and pass full annotate args
make_function3_annotate(self, node, isLambda=False,
@@ -622,7 +309,6 @@ class SourceWalker(GenericASTTraversal, object):
self.prune() # stop recursing
self.n_mkfunc_annotate = n_mkfunc_annotate
if version >= 3.4:
########################
# Python 3.4+ Additions
@@ -630,14 +316,65 @@ class SourceWalker(GenericASTTraversal, object):
TABLE_DIRECT.update({
'LOAD_CLASSDEREF': ( '%{pattr}', ),
})
########################
# Python 3.5+ Additions
#######################
if version >= 3.5:
TABLE_DIRECT.update({
'await_stmt': ( '%|await %c', 0),
'async_for_stmt': (
'%|async for %c in %c:\n%+%c%-\n\n', 9, 1, 25 ),
'async_forelse_stmt': (
'%|async for %c in %c:\n%+%c%-%|else:\n%+%c%-\n\n', 9, 1, 25, 28 ),
'async_with_stmt': (
'%|async with %c:\n%+%c%-', 0, 7),
'async_with_as_stmt': (
'%|async with %c as %c:\n%+%c%-', 0, 6, 7),
})
def n_async_call_function(node):
self.f.write('async ')
node.type == 'call_function'
p = self.prec
self.prec = 80
self.engine(('%c(%P)', 0, (1, -4, ', ', 100)), node)
self.prec = p
self.prune()
self.n_async_call_function = n_async_call_function
def n_funcdef(node):
code_node = node[0][1]
if (code_node == 'LOAD_CONST' and iscode(code_node.attr)
and code_node.attr.co_flags & COMPILER_FLAG_BIT['COROUTINE']):
self.engine(('\n\n%|async def %c\n', -2), node)
else:
self.engine(('\n\n%|def %c\n', -2), node)
self.prune()
self.n_funcdef = n_funcdef
def n_unmapexpr(node):
last_n = node[0][-1]
for n in node[0]:
self.preorder(n)
if n != last_n:
self.f.write(', **')
pass
pass
if version >= 3.6:
self.f.write(')')
self.prune()
pass
self.n_unmapexpr = n_unmapexpr
if version >= 3.6:
########################
# Python 3.6+ Additions
#######################
TABLE_DIRECT.update({
'fstring_expr': ( "{%c%{conversion}}", 0),
'fstring_expr': ( "{%c%{conversion}}", 0),
'fstring_single': ( "f'{%c%{conversion}}'", 0),
'fstring_multi': ( "f'%c'", 0),
'func_args36': ( "%c(**", 0),
})
FSTRING_CONVERSION_MAP = {1: '!s', 2: '!r', 3: '!a'}
@@ -653,7 +390,6 @@ class SourceWalker(GenericASTTraversal, object):
def n_fstring_single(node):
f_conversion(node)
self.default(node)
self.n_fstring_single = n_fstring_single
return
@@ -896,6 +632,8 @@ class SourceWalker(GenericASTTraversal, object):
sep += ' '
pass
pass
if len(tup) == 1:
self.write(", ")
self.write(')')
def n_LOAD_CONST(self, node):
@@ -1134,7 +872,6 @@ class SourceWalker(GenericASTTraversal, object):
assert n == 'lc_body'
self.write( '[ ')
if self.version >= 2.7:
expr = n[0]
list_iter = node[-1]
@@ -1322,7 +1059,7 @@ class SourceWalker(GenericASTTraversal, object):
n = ast[iter_index]
assert n == 'list_iter', n
## FIXME: I'm not totally sure this is right.
# FIXME: I'm not totally sure this is right.
# find innermost node
if_node = None
@@ -1756,23 +1493,29 @@ class SourceWalker(GenericASTTraversal, object):
self.prec = 100
lastnode = node.pop()
lastnodetype = lastnode.type
# If this build list is inside a CALL_FUNCTION_VAR,
# then the first * has already been printed.
# Until I have a better way to check for CALL_FUNCTION_VAR,
# will assume that if the text ends in *.
last_was_star = self.f.getvalue().endswith('*')
have_star = False
if lastnodetype.startswith('BUILD_LIST'):
# 3.5+ has BUILD_LIST_UNPACK
if lastnodetype == 'BUILD_LIST_UNPACK':
# FIXME: need to handle range of BUILD_LIST_UNPACK
have_star = True
endchar = ''
else:
self.write('['); endchar = ']'
elif lastnodetype.startswith('BUILD_TUPLE'):
self.write('('); endchar = ')'
elif lastnodetype.startswith('BUILD_SET'):
self.write('{'); endchar = '}'
elif lastnodetype.startswith('ROT_TWO'):
self.write('('); endchar = ')'
if lastnodetype.endswith('UNPACK'):
# FIXME: need to handle range of BUILD_LIST_UNPACK
have_star = True
endchar = ''
else:
raise 'Internal Error: n_build_list expects list or tuple'
if lastnodetype.startswith('BUILD_LIST'):
self.write('['); endchar = ']'
elif lastnodetype.startswith('BUILD_TUPLE'):
self.write('('); endchar = ')'
elif lastnodetype.startswith('BUILD_SET'):
self.write('{'); endchar = '}'
elif lastnodetype.startswith('ROT_TWO'):
self.write('('); endchar = ')'
else:
raise 'Internal Error: n_build_list expects list or tuple'
flat_elems = []
for elem in node:
@@ -1799,8 +1542,13 @@ class SourceWalker(GenericASTTraversal, object):
sep += '\n' + self.indent + INDENT_PER_LEVEL[:-1]
else:
if sep != '': sep += ' '
if have_star:
sep += '*'
if not last_was_star:
if have_star:
sep += '*'
pass
pass
else:
last_was_star = False
self.write(sep, value)
sep = ','
if lastnode.attr == 1 and lastnodetype.startswith('BUILD_TUPLE'):
@@ -1862,8 +1610,7 @@ class SourceWalker(GenericASTTraversal, object):
beginning of this module for the how we interpret format specifications such as
%c, %C, and so on.
"""
# self.println("----> ", startnode.type)
# self.println("----> ", startnode.type, ', ', entry[0])
fmt = entry[0]
arg = 1
i = 0
@@ -2124,7 +1871,6 @@ class SourceWalker(GenericASTTraversal, object):
self.println()
del ast[i]
# the function defining a class normally returns locals(); we
# don't want this to show up in the source, thus remove the node
if len(ast) > 0 and ast[-1][0] == RETURN_LOCALS:

View File

@@ -184,16 +184,16 @@ def cmp_code_objects(version, is_pypy, code_obj1, code_obj2,
elif member == 'co_code' and not ignore_code:
if version == 2.3:
import uncompyle6.scanners.scanner23 as scan
scanner = scan.Scanner26()
scanner = scan.Scanner23(show_asm=False)
elif version == 2.4:
import uncompyle6.scanners.scanner24 as scan
scanner = scan.Scanner25()
scanner = scan.Scanner24(show_asm=False)
elif version == 2.5:
import uncompyle6.scanners.scanner25 as scan
scanner = scan.Scanner25()
scanner = scan.Scanner25(show_asm=False)
elif version == 2.6:
import uncompyle6.scanners.scanner26 as scan
scanner = scan.Scanner26()
scanner = scan.Scanner26(show_asm=False)
elif version == 2.7:
if is_pypy:
import uncompyle6.scanners.pypy27 as scan
@@ -319,6 +319,9 @@ def cmp_code_objects(version, is_pypy, code_obj1, code_obj2,
elif tokens1[i1].type == 'LOAD_NAME' and tokens2[i2].type == 'LOAD_CONST' \
and tokens1[i1].pattr == 'None' and tokens2[i2].pattr is None:
pass
elif tokens1[i1].type == 'RETURN_VALUE' and \
tokens2[i2].type == 'RETURN_END_IF':
pass
else:
raise CmpErrorCode(name, tokens1[i1].offset, tokens1[i1],
tokens2[i2], tokens1, tokens2)
@@ -353,6 +356,9 @@ def cmp_code_objects(version, is_pypy, code_obj1, code_obj2,
if is_pypy:
# For PYPY for now we don't care about PYPY_SOURCE_IS_UTF8:
flags2 &= ~0x0100 # PYPY_SOURCE_IS_UTF8
# We also don't care about COROUTINE or GENERATOR for now
flags1 &= ~0x000000a0
flags2 &= ~0x000000a0
if flags1 != flags2:
raise CmpErrorMember(name, 'co_flags',
pretty_flags(flags1),
@@ -401,7 +407,8 @@ def compare_code_with_srcfile(pyc_filename, src_filename, weak_verify=False):
try:
code_obj2 = load_file(src_filename)
except SyntaxError as e:
return str(e)
# src_filename can be the first of a group sometimes
return str(e).replace(src_filename, pyc_filename)
cmp_code_objects(version, is_pypy, code_obj1, code_obj2, ignore_code=weak_verify)
return None

View File

@@ -1,3 +1,3 @@
# This file is suitable for sourcing inside bash as
# well as importing into Python
VERSION='2.9.7'
VERSION='2.9.9'