You've already forked python-uncompyle6
mirror of
https://github.com/rocky/python-uncompyle6.git
synced 2025-08-03 00:45:53 +08:00
f7697ccd7b
I had broken escaping the tail quote by inadvertently switching from """
by default to '''.
Some additional tests have been added to 00_docstring.py for
this. However...
Unicode decoding is still broken. For now I've added errors="ignore" to
.decode("utf-8", ...) until a better fix is found. Sigh.
276 lines
9.2 KiB
Python
276 lines
9.2 KiB
Python
import sys
|
|
|
|
from uncompyle6.parsers.treenode import SyntaxTree
|
|
|
|
from uncompyle6 import PYTHON3
|
|
if PYTHON3:
|
|
minint = -sys.maxsize-1
|
|
maxint = sys.maxsize
|
|
else:
|
|
minint = -sys.maxint-1
|
|
maxint = sys.maxint
|
|
|
|
read_write_global_ops = frozenset(('STORE_GLOBAL', 'DELETE_GLOBAL', 'LOAD_GLOBAL'))
|
|
read_global_ops = frozenset(('STORE_GLOBAL', 'DELETE_GLOBAL'))
|
|
|
|
# NOTE: we also need to check that the variable name is a free variable, not a cell variable.
|
|
nonglobal_ops = frozenset(('STORE_DEREF', 'DELETE_DEREF'))
|
|
|
|
# FIXME: this and find_globals could be paramaterized with one of the
|
|
# above global ops
|
|
def find_all_globals(node, globs):
|
|
"""Search Syntax Tree node to find variable names that are global."""
|
|
for n in node:
|
|
if isinstance(n, SyntaxTree):
|
|
globs = find_all_globals(n, globs)
|
|
elif n.kind in read_write_global_ops:
|
|
globs.add(n.pattr)
|
|
return globs
|
|
|
|
def find_globals_and_nonlocals(node, globs, nonlocals, code, version):
|
|
"""search a node of parse tree to find variable names that need a
|
|
either 'global' or 'nonlocal' statements added."""
|
|
for n in node:
|
|
if isinstance(n, SyntaxTree):
|
|
globs, nonlocals = find_globals_and_nonlocals(n, globs, nonlocals,
|
|
code, version)
|
|
elif n.kind in read_global_ops:
|
|
globs.add(n.pattr)
|
|
elif (version >= 3.0
|
|
and n.kind in nonglobal_ops
|
|
and n.pattr in code.co_freevars
|
|
and n.pattr != code.co_name
|
|
and code.co_name != '<lambda>'):
|
|
nonlocals.add(n.pattr)
|
|
return globs, nonlocals
|
|
|
|
# def find_globals(node, globs, global_ops=mkfunc_globals):
|
|
# """Find globals in this statement."""
|
|
# for n in node:
|
|
# # print("XXX", n.kind, global_ops)
|
|
# if isinstance(n, SyntaxTree):
|
|
# # FIXME: do I need a caser for n.kind="mkfunc"?
|
|
# if n.kind in ("if_expr_lambda", "return_lambda"):
|
|
# globs = find_globals(n, globs, mklambda_globals)
|
|
# else:
|
|
# globs = find_globals(n, globs, global_ops)
|
|
# elif n.kind in frozenset(global_ops):
|
|
# globs.add(n.pattr)
|
|
# return globs
|
|
|
|
def find_none(node):
|
|
for n in node:
|
|
if isinstance(n, SyntaxTree):
|
|
if n not in ('return_stmt', 'return_if_stmt'):
|
|
if find_none(n):
|
|
return True
|
|
elif n.kind == 'LOAD_CONST' and n.pattr is None:
|
|
return True
|
|
return False
|
|
|
|
def escape_string(str, quotes=('"', "'", '"""', "'''")):
|
|
quote = None
|
|
for q in quotes:
|
|
if str.find(q) == -1:
|
|
quote = q
|
|
break
|
|
pass
|
|
if quote is None:
|
|
quote = '"""'
|
|
str = str.replace('"""', '\\"""')
|
|
|
|
for (orig, replace) in (('\t', '\\t'),
|
|
('\n', '\\n'),
|
|
('\r', '\\r')):
|
|
str = str.replace(orig, replace)
|
|
return "%s%s%s" % (quote, str, quote)
|
|
|
|
def strip_quotes(str):
|
|
if str.startswith("'''") and str.endswith("'''"):
|
|
str = str[3:-3]
|
|
elif str.startswith('"""') and str.endswith('"""'):
|
|
str = str[3:-3]
|
|
elif str.startswith("'") and str.endswith("'"):
|
|
str = str[1:-1]
|
|
elif str.startswith('"') and str.endswith('"'):
|
|
str = str[1:-1]
|
|
pass
|
|
return str
|
|
|
|
|
|
def print_docstring(self, indent, docstring):
|
|
quote = '"""'
|
|
if docstring.find(quote) >= 0:
|
|
if docstring.find("'''") == -1:
|
|
quote = "'''"
|
|
|
|
self.write(indent)
|
|
if not PYTHON3 and not isinstance(docstring, str):
|
|
# Must be unicode in Python2
|
|
if self.version >= 2.4:
|
|
if self.version > 2.7:
|
|
docstring = repr(docstring.expandtabs())[2:-1].decode("unicode-escape")
|
|
else:
|
|
self.write('u')
|
|
docstring = repr(docstring.expandtabs())[2:-1].decode("string-escape")\
|
|
.decode("utf-8", errors="ignore")
|
|
else:
|
|
docstring = repr(docstring.expandtabs())[2:-1]
|
|
elif PYTHON3 and 2.4 <= self.version <= 2.7:
|
|
# TODO: check for unicode string
|
|
try:
|
|
docstring = repr(docstring.expandtabs())[1:-1].encode("latin-1").decode("utf-8")
|
|
except UnicodeEncodeError:
|
|
self.write('u')
|
|
docstring = repr(docstring.expandtabs())[1:-1]
|
|
else:
|
|
docstring = repr(docstring.expandtabs())[1:-1]
|
|
|
|
for (orig, replace) in (('\\\\', '\t'),
|
|
('\\r\\n', '\n'),
|
|
('\\n', '\n'),
|
|
('\\r', '\n'),
|
|
('\\"', '"'),
|
|
("\\'", "'")):
|
|
docstring = docstring.replace(orig, replace)
|
|
|
|
# Do a raw string if there are backslashes but no other escaped characters:
|
|
# also check some edge cases
|
|
if ('\t' in docstring
|
|
and '\\' not in docstring
|
|
and len(docstring) >= 2
|
|
and docstring[-1] != '\t'
|
|
and (docstring[-1] != '"'
|
|
or docstring[-2] == '\t')):
|
|
self.write('r') # raw string
|
|
# Restore backslashes unescaped since raw
|
|
docstring = docstring.replace('\t', '\\')
|
|
else:
|
|
# Escape the last character if it is the same as the
|
|
# triple quote character.
|
|
quote1 = quote[-1]
|
|
if len(docstring) and docstring[-1] == quote1:
|
|
docstring = docstring[:-1] + '\\' + quote1
|
|
|
|
# Escape triple quote when needed
|
|
if quote == '"""':
|
|
replace_str = '\\"""'
|
|
else:
|
|
assert quote == "'''"
|
|
replace_str = "\\'''"
|
|
|
|
docstring = docstring.replace(quote, replace_str)
|
|
docstring = docstring.replace('\t', '\\\\')
|
|
|
|
lines = docstring.split('\n')
|
|
calculate_indent = maxint
|
|
for line in lines[1:]:
|
|
stripped = line.lstrip()
|
|
if len(stripped) > 0:
|
|
calculate_indent = min(calculate_indent, len(line) - len(stripped))
|
|
calculate_indent = min(calculate_indent, len(lines[-1]) - len(lines[-1].lstrip()))
|
|
# Remove indentation (first line is special):
|
|
|
|
trimmed = [lines[0]]
|
|
if calculate_indent < maxint:
|
|
trimmed += [line[calculate_indent:] for line in lines[1:]]
|
|
|
|
self.write(quote)
|
|
if len(trimmed) == 0:
|
|
self.println(quote)
|
|
elif len(trimmed) == 1:
|
|
self.println(trimmed[0], quote)
|
|
else:
|
|
self.println(trimmed[0])
|
|
for line in trimmed[1:-1]:
|
|
if line:
|
|
self.println( indent, line )
|
|
else:
|
|
self.println( "\n\n" )
|
|
pass
|
|
pass
|
|
self.println(indent, trimmed[-1], quote)
|
|
return True
|
|
|
|
|
|
def flatten_list(node):
|
|
"""
|
|
List of expressions may be nested in groups of 32 and 1024
|
|
items. flatten that out and return the list
|
|
"""
|
|
flat_elems = []
|
|
for elem in node:
|
|
if elem == 'expr1024':
|
|
for subelem in elem:
|
|
assert subelem == 'expr32'
|
|
for subsubelem in subelem:
|
|
flat_elems.append(subsubelem)
|
|
elif elem == 'expr32':
|
|
for subelem in elem:
|
|
assert subelem == 'expr'
|
|
flat_elems.append(subelem)
|
|
else:
|
|
flat_elems.append(elem)
|
|
pass
|
|
pass
|
|
return flat_elems
|
|
|
|
|
|
# if __name__ == '__main__':
|
|
# if PYTHON3:
|
|
# from io import StringIO
|
|
# else:
|
|
# from StringIO import StringIO
|
|
# class PrintFake():
|
|
# def __init__(self):
|
|
# self.pending_newlines = 0
|
|
# self.f = StringIO()
|
|
|
|
# def write(self, *data):
|
|
# if (len(data) == 0) or (len(data) == 1 and data[0] == ''):
|
|
# return
|
|
# out = ''.join((str(j) for j in data))
|
|
# n = 0
|
|
# for i in out:
|
|
# if i == '\n':
|
|
# n += 1
|
|
# if n == len(out):
|
|
# self.pending_newlines = max(self.pending_newlines, n)
|
|
# return
|
|
# elif n:
|
|
# self.pending_newlines = max(self.pending_newlines, n)
|
|
# out = out[n:]
|
|
# break
|
|
# else:
|
|
# break
|
|
|
|
# if self.pending_newlines > 0:
|
|
# self.f.write('\n'*self.pending_newlines)
|
|
# self.pending_newlines = 0
|
|
|
|
# for i in out[::-1]:
|
|
# if i == '\n':
|
|
# self.pending_newlines += 1
|
|
# else:
|
|
# break
|
|
|
|
# if self.pending_newlines:
|
|
# out = out[:-self.pending_newlines]
|
|
# self.f.write(out)
|
|
# def println(self, *data):
|
|
# if data and not(len(data) == 1 and data[0] ==''):
|
|
# self.write(*data)
|
|
# self.pending_newlines = max(self.pending_newlines, 1)
|
|
# return
|
|
# pass
|
|
|
|
# for doc in (
|
|
# "Now is the time",
|
|
# r'''func placeholder - with ("""\nstring\n""")''',
|
|
# r'''func placeholder - ' and with ("""\nstring\n""")''',
|
|
# r"""func placeholder - ' and with ('''\nstring\n''') and \"\"\"\nstring\n\"\"\" """
|
|
# ):
|
|
# o = PrintFake()
|
|
# print_docstring(o, ' ', doc)
|
|
# print(o.f.getvalue())
|