jinx/python-uncompyle6
1
Fork 0
mirror of https://github.com/rocky/python-uncompyle6.git synced 2025-08-03 00:45:53 +08:00
Code Issues Packages Projects Releases Wiki Activity

Fix up looping by reinstating JUMP_ABSOLUTE -> JUMP_BACK or CONTINUE

Browse Source 
get jump offsets into jump attributes. Fix up 3.2 scanner paritally
and use that in 3.4 for in cross version disassembly.
This commit is contained in:
rocky
2015-12-26 03:06:03 -05:00
parent fe9c8d5734
commit 7a2703634f
13 changed files with 108 additions and 79 deletions
Download Patch File Download Diff File Expand all files Collapse all files

BIN
test/bytecode_3.4/05_try_except.pyc
View File

Binary file not shown.

8
test/simple_source/exception/05_try_except.py
View File

@@ -5,6 +5,14 @@ def handle(module):
module = exc
return module
def handle2(module):
if module == 'foo':
try:
module = 1
except ImportError as exc:
module = exc
return module
try:
pass
except ImportError as exc:

2
test/simple_source/looping/10_while.py Normal file
View File

@@ -0,0 +1,2 @@
while __name__ != '__main__':
b = 4

2
test/simple_source/looping/while.py
View File

@@ -1,2 +0,0 @@
while a:
b = c

0
test/simple_source/simple_stmts/00_assign.py → test/simple_source/stmts/00_assign.py
View File

0
test/simple_source/simple_stmts/00_import.py → test/simple_source/stmts/00_import.py
View File

0
test/simple_source/simple_stmts/00_pass.py → test/simple_source/stmts/00_pass.py
View File

0
test/simple_source/simple_stmts/15_assert.py → test/simple_source/stmts/15_assert.py
View File

5
test/simple_source/stmts/15_for_if.py Normal file
View File

@@ -0,0 +1,5 @@
if __name__:
for i in (1,2):
x = 3
pass
pass

12
uncompyle6/parsers/parse3.py
View File

@@ -71,7 +71,7 @@ class Python3Parser(PythonParser):
_come_from ::= COME_FROM
_come_from ::=
list_for ::= expr FOR_ITER designator list_iter JUMP_ABSOLUTE
list_for ::= expr FOR_ITER designator list_iter JUMP_BACK
list_if ::= expr jmp_false list_iter
list_if_not ::= expr jmp_true list_iter
@@ -407,7 +407,7 @@ class Python3Parser(PythonParser):
testtrue ::= expr jmp_true
_ifstmts_jump ::= return_if_stmts
_ifstmts_jump ::= c_stmts_opt JUMP_FORWARD COME_FROM
_ifstmts_jump ::= c_stmts_opt JUMP_FORWARD COME_FROM _come_from
iflaststmt ::= testexpr c_stmts_opt JUMP_ABSOLUTE
@@ -459,7 +459,7 @@ class Python3Parser(PythonParser):
# This is used in Python 3 in
# "except ... as e" to remove 'e' after the c_stmts_opt finishes
except_suite_finalize ::= SETUP_FINALLY c_stmts_opt except_var_finalize
END_FINALLY JUMP_FORWARD
END_FINALLY _jump
except_var_finalize ::= POP_BLOCK POP_EXCEPT LOAD_CONST COME_FROM LOAD_CONST
designator del_stmt
@@ -490,7 +490,7 @@ class Python3Parser(PythonParser):
whilestmt ::= SETUP_LOOP
testexpr
l_stmts_opt JUMP_ABSOLUTE
l_stmts_opt JUMP_BACK
POP_BLOCK COME_FROM
whilestmt ::= SETUP_LOOP
@@ -515,11 +515,11 @@ class Python3Parser(PythonParser):
_for ::= GET_ITER FOR_ITER
_for ::= LOAD_CONST FOR_LOOP
for_block ::= l_stmts_opt JUMP_ABSOLUTE
for_block ::= l_stmts_opt JUMP_BACK
for_block ::= return_stmts _come_from
forstmt ::= SETUP_LOOP expr _for designator
for_block POP_BLOCK COME_FROM
for_block POP_BLOCK _come_from
forelsestmt ::= SETUP_LOOP expr _for designator
for_block POP_BLOCK else_suite COME_FROM

72
uncompyle6/scanners/scanner32.py
View File

@@ -34,11 +34,11 @@ class Scanner32(scan.Scanner):
tokens = self.tokenize(code_object)
return tokens
def disassemble(self, co):
def disassemble(self, co, classname=None):
"""
Convert code object <co> into a sequence of tokens.
Based on dis.disassemble() function.
The below is based on (an older version?) of Python dis.disassemble_bytes().
"""
# Container for tokens
tokens = []
@@ -47,9 +47,64 @@ class Scanner32(scan.Scanner):
codelen = len(code)
self.build_lines_data(co)
self.build_prev_op()
# Get jump targets
# Format: {target offset: [jump offsets]}
jump_targets = self.find_jump_targets()
# self.lines contains (block,addrLastInstr)
if classname:
classname = '_' + classname.lstrip('_') + '__'
def unmangle(name):
if name.startswith(classname) and name[-2:] != '__':
return name[len(classname) - 2:]
return name
# free = [ unmangle(name) for name in (co.co_cellvars + co.co_freevars) ]
# names = [ unmangle(name) for name in co.co_names ]
# varnames = [ unmangle(name) for name in co.co_varnames ]
else:
# free = co.co_cellvars + co.co_freevars
# names = co.co_names
# varnames = co.co_varnames
pass
# Scan for assertions. Later we will
# turn 'LOAD_GLOBAL' to 'LOAD_ASSERT' for those
# assertions
self.load_asserts = set()
for i in self.op_range(0, codelen):
if self.code[i] == POP_JUMP_IF_TRUE and self.code[i+3] == LOAD_GLOBAL:
if names[self.get_argument(i+3)] == 'AssertionError':
self.load_asserts.add(i+3)
# FIXME: reinstate code
# cf = self.find_jump_targets(self.code)
# # contains (code, [addrRefToCode])
# last_stmt = self.next_stmt[0]
# i = self.next_stmt[last_stmt]
# replace = {}
# while i < n-1:
# if self.lines[last_stmt].next > i:
# if self.code[last_stmt] == PRINT_ITEM:
# if self.code[i] == PRINT_ITEM:
# replace[i] = 'PRINT_ITEM_CONT'
# elif self.code[i] == PRINT_NEWLINE:
# replace[i] = 'PRINT_NEWLINE_CONT'
# last_stmt = i
# i = self.next_stmt[i]
# imports = self.all_instr(0, n, (IMPORT_NAME, IMPORT_FROM, IMPORT_STAR))
# if len(imports) > 1:
# last_import = imports[0]
# for i in imports[1:]:
# if self.lines[last_import].next > i:
# if self.code[last_import] == IMPORT_NAME == self.code[i]:
# replace[i] = 'IMPORT_NAME_CONT'
# last_import = i
# Initialize extended arg at 0. When extended arg op is encountered,
# variable preserved for next cycle and added as arg for next op
extended_arg = 0
@@ -63,6 +118,8 @@ class Scanner32(scan.Scanner):
offset='{}_{}'.format(offset, jump_idx)))
jump_idx += 1
op = code[offset]
op_name = opname[op]
# Create token and fill all the fields we can
# w/o touching arguments
current_token = Token(dis.opname[op])
@@ -97,6 +154,17 @@ class Scanner32(scan.Scanner):
if free is None:
free = co.co_cellvars + co.co_freevars
current_token.pattr = free[oparg]
if op == JUMP_ABSOLUTE:
current_token.pattr = current_token.attr = oparg
target = self.get_target(offset)
if target < offset:
if offset in self.stmts and self.code[offset+3] not in (END_FINALLY, POP_BLOCK) \
and offset not in self.not_continue:
op_name = 'CONTINUE'
else:
op_name = 'JUMP_BACK'
current_token.type = op_name
tokens.append(current_token)
return tokens, customize

80
uncompyle6/scanners/scanner34.py
View File

@@ -20,7 +20,7 @@ from collections import namedtuple
from array import array
from uncompyle6 import PYTHON_VERSION
from uncompyle6.scanner import Token, L65536
from uncompyle6.scanner import Token
import uncompyle6.opcodes.opcode_34
# Get all the opcodes into globals
@@ -145,6 +145,17 @@ class Scanner34(scan.Scanner):
if inst.opname != 'BUILD_SLICE':
customize[opname] = inst.argval
elif opname == 'JUMP_ABSOLUTE':
pattr = inst.argval
target = self.get_target(inst.offset)
if target < inst.offset:
if (inst.offset in self.stmts and
self.code[inst.offset+3] not in (END_FINALLY, POP_BLOCK)
and offset not in self.not_continue):
opname = 'CONTINUE'
else:
opname = 'JUMP_BACK'
elif inst.offset in self.load_asserts:
opname = 'LOAD_ASSERT'
@@ -160,71 +171,8 @@ class Scanner34(scan.Scanner):
pass
return tokens, {}
def disassemble_cross_version(self, co):
"""
Convert code object <co> into a sequence of tokens
FIXME: the below is not based on the current Python 3.4 dis.disassemble_bytes().
Fix that.
"""
# Container for tokens
tokens = []
customize = {}
self.code = code = array('B', co.co_code)
codelen = len(code)
self.build_lines_data(co)
self.build_prev_op()
# Get jump targets
# Format: {target offset: [jump offsets]}
jump_targets = self.find_jump_targets()
# Initialize extended arg at 0. When extended arg op is encountered,
# variable preserved for next cycle and added as arg for next op
extended_arg = 0
free = None
for offset in self.op_range(0, codelen):
# Add jump target tokens
if offset in jump_targets:
jump_idx = 0
for jump_offset in jump_targets[offset]:
tokens.append(Token('COME_FROM', None, repr(jump_offset),
offset='{}_{}'.format(offset, jump_idx)))
jump_idx += 1
op = code[offset]
# Create token and fill all the fields we can
# w/o touching arguments
current_token = Token(dis.opname[op])
current_token.offset = offset
if offset in self.linestarts:
current_token.linestart = self.linestarts[offset]
else:
current_token.linestart = None
if op >= dis.HAVE_ARGUMENT:
# Calculate op's argument value based on its argument and
# preceding extended argument, if any
oparg = code[offset+1] + code[offset+2]*256 + extended_arg
extended_arg = 0
if op == dis.EXTENDED_ARG:
extended_arg = oparg * L65536
# Fill token's attr/pattr fields
current_token.attr = oparg
if op in dis.hasconst:
current_token.pattr = repr(co.co_consts[oparg])
elif op in dis.hasname:
current_token.pattr = co.co_names[oparg]
elif op in dis.hasjrel:
current_token.pattr = repr(offset + 3 + oparg)
elif op in dis.haslocal:
current_token.pattr = co.co_varnames[oparg]
elif op in dis.hascompare:
current_token.pattr = dis.cmp_op[oparg]
elif op in dis.hasfree:
if free is None:
free = co.co_cellvars + co.co_freevars
current_token.pattr = free[oparg]
tokens.append(current_token)
return tokens, customize
def disassemble_cross_version(self, co, classname=None):
return scan.scanner32().disassemble(self, co, classname)
def build_lines_data(self, code_obj):
"""