jinx/python-uncompyle6
1
Fork 0
mirror of https://github.com/rocky/python-uncompyle6.git synced 2025-08-04 01:09:52 +08:00
Code Issues Packages Projects Releases Wiki Activity

Two Bugs ...

Browse Source 
2.7: more stringent comparison and comp_if testing
2.6-2.7: fix botched dict constant translation
This commit is contained in:
rocky
2019-11-18 06:49:36 -05:00
parent 1868b566a1
commit 6659fffc0d
2 changed files with 98 additions and 75 deletions
Download Patch File Download Diff File Expand all files Collapse all files

68
uncompyle6/parsers/parse27.py
View File

@@ -214,13 +214,15 @@ class Python27Parser(Python2Parser):
super(Python27Parser, self).customize_grammar_rules(tokens, customize) super(Python27Parser, self).customize_grammar_rules(tokens, customize)
self.check_reduce['and'] = 'AST' self.check_reduce["and"] = "AST"
# self.check_reduce['or'] = 'AST' self.check_reduce["conditional"] = "AST"
self.check_reduce['raise_stmt1'] = 'AST' # self.check_reduce["or"] = "AST"
self.check_reduce['list_if_not'] = 'AST' self.check_reduce["raise_stmt1"] = "AST"
self.check_reduce['list_if'] = 'AST' self.check_reduce["list_if_not"] = "AST"
self.check_reduce['if_expr_true'] = 'tokens' self.check_reduce["list_if"] = "AST"
self.check_reduce['whilestmt'] = 'tokens' self.check_reduce["comp_if"] = "AST"
self.check_reduce["if_expr_true"] = "tokens"
self.check_reduce["whilestmt"] = "tokens"
return return
def reduce_is_invalid(self, rule, ast, tokens, first, last): def reduce_is_invalid(self, rule, ast, tokens, first, last):
@@ -231,10 +233,10 @@ class Python27Parser(Python2Parser):
if invalid: if invalid:
return invalid return invalid
if rule == ('and', ('expr', 'jmp_false', 'expr', '\\e_come_from_opt')): if rule == ("and", ("expr", "jmp_false", "expr", "\\e_come_from_opt")):
# If the instruction after the instructions formin "and" is an "YIELD_VALUE" # If the instruction after the instructions formin "and" is an "YIELD_VALUE"
# then this is probably an "if" inside a comprehension. # then this is probably an "if" inside a comprehension.
if tokens[last] == 'YIELD_VALUE': if tokens[last] == "YIELD_VALUE":
# Note: We might also consider testing last+1 being "POP_TOP" # Note: We might also consider testing last+1 being "POP_TOP"
return True return True
@@ -244,41 +246,57 @@ class Python27Parser(Python2Parser):
jmp_target = jmp_false.offset + jmp_false.attr + 3 jmp_target = jmp_false.offset + jmp_false.attr + 3
return not (jmp_target == tokens[last].offset or return not (jmp_target == tokens[last].offset or
tokens[last].pattr == jmp_false.pattr) tokens[last].pattr == jmp_false.pattr)
elif rule[0] == ('raise_stmt1'): elif rule == ("comp_if", ("expr", "jmp_false", "comp_iter")):
return ast[0] == 'expr' and ast[0][0] == 'or' jmp_false = ast[1]
elif rule[0] in ('assert', 'assert2'): if jmp_false[0] == "POP_JUMP_IF_FALSE":
return tokens[first].offset < jmp_false[0].attr < tokens[last].offset
pass
elif (rule[0], rule[1][0:5]) == (
"conditional",
("expr", "jmp_false", "expr", "JUMP_ABSOLUTE", "expr")):
jmp_false = ast[1]
if jmp_false[0] == "POP_JUMP_IF_FALSE":
else_instr = ast[4].first_child()
if jmp_false[0].attr != else_instr.offset:
return True
end_offset = ast[3].attr
return end_offset < tokens[last].offset
pass
elif rule[0] == ("raise_stmt1"):
return ast[0] == "expr" and ast[0][0] == "or"
elif rule[0] in ("assert", "assert2"):
jump_inst = ast[1][0] jump_inst = ast[1][0]
jump_target = jump_inst.attr jump_target = jump_inst.attr
return not (last >= len(tokens) return not (last >= len(tokens)
or jump_target == tokens[last].offset or jump_target == tokens[last].offset
or jump_target == next_offset(ast[-1].op, ast[-1].opc, ast[-1].offset)) or jump_target == next_offset(ast[-1].op, ast[-1].opc, ast[-1].offset))
elif rule == ('list_if_not', ('expr', 'jmp_true', 'list_iter')): elif rule == ("list_if_not", ("expr", "jmp_true", "list_iter")):
jump_inst = ast[1][0] jump_inst = ast[1][0]
jump_offset = jump_inst.attr jump_offset = jump_inst.attr
return jump_offset > jump_inst.offset and jump_offset < tokens[last].offset return jump_offset > jump_inst.offset and jump_offset < tokens[last].offset
elif rule == ('list_if', ('expr', 'jmp_false', 'list_iter')): elif rule == ("list_if", ("expr", "jmp_false", "list_iter")):
jump_inst = ast[1][0] jump_inst = ast[1][0]
jump_offset = jump_inst.attr jump_offset = jump_inst.attr
return jump_offset > jump_inst.offset and jump_offset < tokens[last].offset return jump_offset > jump_inst.offset and jump_offset < tokens[last].offset
elif rule == ('or', ('expr', 'jmp_true', 'expr', '\\e_come_from_opt')): elif rule == ("or", ("expr", "jmp_true", "expr", "\\e_come_from_opt")):
# Test that jmp_true doesn't jump inside the middle the "or" # Test that jmp_true doesn"t jump inside the middle the "or"
# or that it jumps to the same place as the end of "and" # or that it jumps to the same place as the end of "and"
jmp_true = ast[1][0] jmp_true = ast[1][0]
jmp_target = jmp_true.offset + jmp_true.attr + 3 jmp_target = jmp_true.offset + jmp_true.attr + 3
return not (jmp_target == tokens[last].offset or return not (jmp_target == tokens[last].offset or
tokens[last].pattr == jmp_true.pattr) tokens[last].pattr == jmp_true.pattr)
elif (rule[0] == 'whilestmt' and elif (rule[0] == "whilestmt" and
rule[1][0:-2] == rule[1][0:-2] ==
('SETUP_LOOP', 'testexpr', 'l_stmts_opt', ("SETUP_LOOP", "testexpr", "l_stmts_opt",
'JUMP_BACK', 'JUMP_BACK')): "JUMP_BACK", "JUMP_BACK")):
# Make sure that the jump backs all go to the same place # Make sure that the jump backs all go to the same place
i = last-1 i = last-1
while (tokens[i] != 'JUMP_BACK'): while (tokens[i] != "JUMP_BACK"):
i -= 1 i -= 1
return tokens[i].attr != tokens[i-1].attr return tokens[i].attr != tokens[i-1].attr
elif rule[0] == 'if_expr_true': elif rule[0] == "if_expr_true":
return (first) > 0 and tokens[first-1] == 'POP_JUMP_IF_FALSE' return (first) > 0 and tokens[first-1] == "POP_JUMP_IF_FALSE"
return False return False
@@ -286,7 +304,7 @@ class Python27Parser(Python2Parser):
class Python27ParserSingle(Python27Parser, PythonParserSingle): class Python27ParserSingle(Python27Parser, PythonParserSingle):
pass pass
if __name__ == '__main__': if __name__ == "__main__":
# Check grammar # Check grammar
p = Python27Parser() p = Python27Parser()
p.check_grammar() p.check_grammar()
@@ -302,9 +320,9 @@ if __name__ == '__main__':
""".split())) """.split()))
remain_tokens = set(tokens) - opcode_set remain_tokens = set(tokens) - opcode_set
import re import re
remain_tokens = set([re.sub(r'_\d+$', '', t) remain_tokens = set([re.sub(r"_\d+$", "", t)
for t in remain_tokens]) for t in remain_tokens])
remain_tokens = set([re.sub('_CONT$', '', t) remain_tokens = set([re.sub("_CONT$", "", t)
for t in remain_tokens]) for t in remain_tokens])
remain_tokens = set(remain_tokens) - opcode_set remain_tokens = set(remain_tokens) - opcode_set
print(remain_tokens) print(remain_tokens)

105
uncompyle6/semantics/pysource.py
View File

@@ -1633,6 +1633,57 @@ class SourceWalker(GenericASTTraversal, object):
self.write(")") self.write(")")
def kv_map(self, kv_node, sep, line_number, indent):
first_time = True
for kv in kv_node:
assert kv in ('kv', 'kv2', 'kv3')
# kv ::= DUP_TOP expr ROT_TWO expr STORE_SUBSCR
# kv2 ::= DUP_TOP expr expr ROT_THREE STORE_SUBSCR
# kv3 ::= expr expr STORE_MAP
# FIXME: DRY this and the above
if kv == 'kv':
self.write(sep)
name = self.traverse(kv[-2], indent='')
if first_time:
line_number = self.indent_if_source_nl(line_number, indent)
first_time = False
pass
line_number = self.line_number
self.write(name, ': ')
value = self.traverse(kv[1], indent=self.indent+(len(name)+2)*' ')
elif kv == 'kv2':
self.write(sep)
name = self.traverse(kv[1], indent='')
if first_time:
line_number = self.indent_if_source_nl(line_number, indent)
first_time = False
pass
line_number = self.line_number
self.write(name, ': ')
value = self.traverse(kv[-3], indent=self.indent+(len(name)+2)*' ')
elif kv == 'kv3':
self.write(sep)
name = self.traverse(kv[-2], indent='')
if first_time:
line_number = self.indent_if_source_nl(line_number, indent)
first_time = False
pass
line_number = self.line_number
self.write(name, ': ')
line_number = self.line_number
value = self.traverse(kv[0], indent=self.indent+(len(name)+2)*' ')
pass
self.write(value)
sep = ", "
if line_number != self.line_number:
sep += "\n" + self.indent + " "
line_number = self.line_number
pass
pass
def n_dict(self, node): def n_dict(self, node):
""" """
prettyprint a dict prettyprint a dict
@@ -1753,14 +1804,15 @@ class SourceWalker(GenericASTTraversal, object):
pass pass
else: else:
# Python 2 style kvlist. Find beginning of kvlist. # Python 2 style kvlist. Find beginning of kvlist.
indent = self.indent + " "
line_number = self.line_number
if node[0].kind.startswith("BUILD_MAP"): if node[0].kind.startswith("BUILD_MAP"):
if len(node) > 1 and node[1].kind in ("kvlist", "kvlist_n"): if len(node) > 1 and node[1].kind in ("kvlist", "kvlist_n"):
kv_node = node[1] kv_node = node[1]
else: else:
kv_node = node[1:] kv_node = node[1:]
self.kv_map(kv_node, sep, line_number, indent)
else: else:
indent = self.indent + " "
line_number = self.line_number
sep = '' sep = ''
opname = node[-1].kind opname = node[-1].kind
if self.is_pypy and self.version >= 3.5: if self.is_pypy and self.version >= 3.5:
@@ -1798,54 +1850,7 @@ class SourceWalker(GenericASTTraversal, object):
pass pass
elif opname.startswith('kvlist'): elif opname.startswith('kvlist'):
kv_node = node[-1] kv_node = node[-1]
first_time = True self.kv_map(node[-1], sep, line_number, indent)
for kv in kv_node:
assert kv in ('kv', 'kv2', 'kv3')
# kv ::= DUP_TOP expr ROT_TWO expr STORE_SUBSCR
# kv2 ::= DUP_TOP expr expr ROT_THREE STORE_SUBSCR
# kv3 ::= expr expr STORE_MAP
# FIXME: DRY this and the above
if kv == 'kv':
self.write(sep)
name = self.traverse(kv[-2], indent='')
if first_time:
line_number = self.indent_if_source_nl(line_number, indent)
first_time = False
pass
line_number = self.line_number
self.write(name, ': ')
value = self.traverse(kv[1], indent=self.indent+(len(name)+2)*' ')
elif kv == 'kv2':
self.write(sep)
name = self.traverse(kv[1], indent='')
if first_time:
line_number = self.indent_if_source_nl(line_number, indent)
first_time = False
pass
line_number = self.line_number
self.write(name, ': ')
value = self.traverse(kv[-3], indent=self.indent+(len(name)+2)*' ')
elif kv == 'kv3':
self.write(sep)
name = self.traverse(kv[-2], indent='')
if first_time:
line_number = self.indent_if_source_nl(line_number, indent)
first_time = False
pass
line_number = self.line_number
self.write(name, ': ')
line_number = self.line_number
value = self.traverse(kv[0], indent=self.indent+(len(name)+2)*' ')
pass
self.write(value)
sep = ", "
if line_number != self.line_number:
sep += "\n" + self.indent + " "
line_number = self.line_number
pass
pass
pass pass
if sep.startswith(",\n"): if sep.startswith(",\n"):