Skip to content

Tools/gdb: Drop Python 2 support. #31717

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Mar 15, 2022
Merged

Tools/gdb: Drop Python 2 support. #31717

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
143 changes: 41 additions & 102 deletions Tools/gdb/libpython.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -41,20 +41,11 @@
The module also extends gdb with some python-specific commands.
'''

# NOTE: some gdbs are linked with Python 3, so this file should be dual-syntax
# compatible (2.6+ and 3.0+). See #19308.

from __future__ import print_function

import gdb
import os
import locale
import sys

if sys.version_info[0] >= 3:
unichr = chr
xrange = range
long = int

# Look up the gdb.Type for some standard types:
# Those need to be refreshed as types (pointer sizes) may change when
Expand All @@ -80,9 +71,6 @@ def _sizeof_void_p():
return gdb.lookup_type('void').pointer().sizeof


# value computed later, see PyUnicodeObjectPtr.proxy()
_is_pep393 = None

Py_TPFLAGS_MANAGED_DICT = (1 << 4)
Py_TPFLAGS_HEAPTYPE = (1 << 9)
Py_TPFLAGS_LONG_SUBCLASS = (1 << 24)
Expand Down Expand Up @@ -119,19 +107,7 @@ def safety_limit(val):
def safe_range(val):
# As per range, but don't trust the value too much: cap it to a safety
# threshold in case the data was corrupted
return xrange(safety_limit(int(val)))

if sys.version_info[0] >= 3:
def write_unicode(file, text):
file.write(text)
else:
def write_unicode(file, text):
# Write a byte or unicode string to file. Unicode strings are encoded to
# ENCODING encoding with 'backslashreplace' error handler to avoid
# UnicodeEncodeError.
if isinstance(text, unicode):
text = text.encode(ENCODING, 'backslashreplace')
file.write(text)
return range(safety_limit(int(val)))

try:
os_fsencode = os.fsencode
Expand Down Expand Up @@ -258,7 +234,7 @@ def type(self):
return PyTypeObjectPtr(self.field('ob_type'))

def is_null(self):
return 0 == long(self._gdbval)
return 0 == int(self._gdbval)

def is_optimized_out(self):
'''
Expand Down Expand Up @@ -320,7 +296,7 @@ def __repr__(self):
return '<%s at remote 0x%x>' % (self.tp_name, self.address)

return FakeRepr(self.safe_tp_name(),
long(self._gdbval))
int(self._gdbval))

def write_repr(self, out, visited):
'''
Expand Down Expand Up @@ -420,7 +396,7 @@ def get_gdb_type(cls):
return gdb.lookup_type(cls._typename).pointer()

def as_address(self):
return long(self._gdbval)
return int(self._gdbval)

class PyVarObjectPtr(PyObjectPtr):
_typename = 'PyVarObject'
Expand Down Expand Up @@ -529,7 +505,7 @@ def get_keys_values(self):
PyDictValuesPtrPtr = gdb.lookup_type("PyDictValues").pointer().pointer()
valuesptr = self._gdbval.cast(PyDictValuesPtrPtr) - 4
values = valuesptr.dereference()
if long(values) == 0:
if int(values) == 0:
return None
values = values['values']
return PyKeysValuesPair(self.get_cached_keys(), values)
Expand Down Expand Up @@ -562,7 +538,7 @@ def proxyval(self, visited):
tp_name = self.safe_tp_name()

# Class:
return InstanceProxy(tp_name, attr_dict, long(self._gdbval))
return InstanceProxy(tp_name, attr_dict, int(self._gdbval))

def write_repr(self, out, visited):
# Guard against infinite loops:
Expand Down Expand Up @@ -737,7 +713,7 @@ def iteritems(self):
'''
keys = self.field('ma_keys')
values = self.field('ma_values')
has_values = long(values)
has_values = int(values)
if has_values:
values = values['values']
if has_values:
Expand Down Expand Up @@ -862,7 +838,7 @@ def proxyval(self, visited):
#define PyLong_SHIFT 30
#define PyLong_SHIFT 15
'''
ob_size = long(self.field('ob_size'))
ob_size = int(self.field('ob_size'))
if ob_size == 0:
return 0

Expand All @@ -873,7 +849,7 @@ def proxyval(self, visited):
else:
SHIFT = 30

digits = [long(ob_digit[i]) * 2**(SHIFT*i)
digits = [int(ob_digit[i]) * 2**(SHIFT*i)
for i in safe_range(abs(ob_size))]
result = sum(digits)
if ob_size < 0:
Expand Down Expand Up @@ -1124,7 +1100,7 @@ def current_line(self):

filename = self.filename()
try:
with open(os_fsencode(filename), 'r') as fp:
with open(os_fsencode(filename), 'r', encoding="utf-8") as fp:
lines = fp.readlines()
except IOError:
return None
Expand Down Expand Up @@ -1159,7 +1135,7 @@ def write_repr(self, out, visited):
out.write(')')

def as_address(self):
return long(self._gdbval)
return int(self._gdbval)

def print_traceback(self):
if self.is_optimized_out():
Expand Down Expand Up @@ -1340,18 +1316,6 @@ def _unichr_is_printable(char):
import unicodedata
return unicodedata.category(char) not in ("C", "Z")

if sys.maxunicode >= 0x10000:
_unichr = unichr
else:
# Needed for proper surrogate support if sizeof(Py_UNICODE) is 2 in gdb
def _unichr(x):
if x < 0x10000:
return unichr(x)
x -= 0x10000
ch1 = 0xD800 | (x >> 10)
ch2 = 0xDC00 | (x & 0x3FF)
return unichr(ch1) + unichr(ch2)


class PyUnicodeObjectPtr(PyObjectPtr):
_typename = 'PyUnicodeObject'
Expand All @@ -1361,42 +1325,31 @@ def char_width(self):
return _type_Py_UNICODE.sizeof

def proxyval(self, visited):
global _is_pep393
if _is_pep393 is None:
fields = gdb.lookup_type('PyUnicodeObject').fields()
_is_pep393 = 'data' in [f.name for f in fields]
if _is_pep393:
# Python 3.3 and newer
may_have_surrogates = False
compact = self.field('_base')
ascii = compact['_base']
state = ascii['state']
is_compact_ascii = (int(state['ascii']) and int(state['compact']))
if not int(state['ready']):
# string is not ready
field_length = long(compact['wstr_length'])
may_have_surrogates = True
field_str = ascii['wstr']
else:
field_length = long(ascii['length'])
if is_compact_ascii:
field_str = ascii.address + 1
elif int(state['compact']):
field_str = compact.address + 1
else:
field_str = self.field('data')['any']
repr_kind = int(state['kind'])
if repr_kind == 1:
field_str = field_str.cast(_type_unsigned_char_ptr())
elif repr_kind == 2:
field_str = field_str.cast(_type_unsigned_short_ptr())
elif repr_kind == 4:
field_str = field_str.cast(_type_unsigned_int_ptr())
may_have_surrogates = False
compact = self.field('_base')
ascii = compact['_base']
state = ascii['state']
is_compact_ascii = (int(state['ascii']) and int(state['compact']))
if not int(state['ready']):
# string is not ready
field_length = int(compact['wstr_length'])
may_have_surrogates = True
field_str = ascii['wstr']
else:
# Python 3.2 and earlier
field_length = long(self.field('length'))
field_str = self.field('str')
may_have_surrogates = self.char_width() == 2
field_length = int(ascii['length'])
if is_compact_ascii:
field_str = ascii.address + 1
elif int(state['compact']):
field_str = compact.address + 1
else:
field_str = self.field('data')['any']
repr_kind = int(state['kind'])
if repr_kind == 1:
field_str = field_str.cast(_type_unsigned_char_ptr())
elif repr_kind == 2:
field_str = field_str.cast(_type_unsigned_short_ptr())
elif repr_kind == 4:
field_str = field_str.cast(_type_unsigned_int_ptr())

# Gather a list of ints from the Py_UNICODE array; these are either
# UCS-1, UCS-2 or UCS-4 code points:
Expand Down Expand Up @@ -1426,10 +1379,7 @@ def proxyval(self, visited):

# Convert the int code points to unicode characters, and generate a
# local unicode instance.
# This splits surrogate pairs if sizeof(Py_UNICODE) is 2 here (in gdb).
result = u''.join([
(_unichr(ucs) if ucs <= 0x10ffff else '\ufffd')
for ucs in Py_UNICODEs])
result = u''.join(map(chr, Py_UNICODEs))
return result

def write_repr(self, out, visited):
Expand Down Expand Up @@ -1478,19 +1428,8 @@ def write_repr(self, out, visited):
else:
ucs = ch
ch2 = None
if sys.maxunicode < 0x10000:
# If sizeof(Py_UNICODE) is 2 here (in gdb), join
# surrogate pairs before calling _unichr_is_printable.
if (i < len(proxy)
and 0xD800 <= ord(ch) < 0xDC00 \
and 0xDC00 <= ord(proxy[i]) <= 0xDFFF):
ch2 = proxy[i]
ucs = ch + ch2
i += 1

# Unfortuately, Python 2's unicode type doesn't seem
# to expose the "isprintable" method
printable = _unichr_is_printable(ucs)

printable = ucs.isprintable()
if printable:
try:
ucs.encode(ENCODING)
Expand Down Expand Up @@ -1559,7 +1498,7 @@ def safe_tp_name(self):

def safe_self_addresss(self):
try:
address = long(self.field('self'))
address = int(self.field('self'))
return '%#x' % address
except (NullPyObjectPtr, RuntimeError):
return '<failed to get self address>'
Expand Down Expand Up @@ -1852,7 +1791,7 @@ def print_summary(self):
while True:
if interp_frame:
line = interp_frame.get_truncated_repr(MAX_OUTPUT_LEN)
write_unicode(sys.stdout, '#%i %s\n' % (self.get_index(), line))
sys.stdout.write('#%i %s\n' % (self.get_index(), line))
if not interp_frame.is_optimized_out():
line = interp_frame.current_line()
if line is not None:
Expand Down Expand Up @@ -1952,7 +1891,7 @@ def invoke(self, args, from_tty):
start = 1

try:
f = open(os_fsencode(filename), 'r')
f = open(os_fsencode(filename), 'r', encoding="utf-8")
except IOError as err:
sys.stdout.write('Unable to open %s: %s\n'
% (filename, err))
Expand Down