##// END OF EJS Templates
worker: Use buffered input from the pickle stream...
worker: Use buffered input from the pickle stream On Python 3, "pickle.load" will raise an exception ("_pickle.UnpicklingError: pickle data was truncated") when it gets a short read, i.e. it receives fewer bytes than it requested. On our build machine, Mercurial seems to frequently hit this problem while updating a mozilla-central clone iff it gets scheduled in batch mode. It is easy to trigger with: #wipe the workdir rm -rf * hg update null chrt -b 0 hg update default I've also written the following program, which demonstrates the core problem: from __future__ import print_function import io import os import pickle import time obj = {"a": 1, "b": 2} obj_data = pickle.dumps(obj) assert len(obj_data) > 10 rfd, wfd = os.pipe() pid = os.fork() if pid == 0: os.close(rfd) for _ in range(4): time.sleep(0.5) print("First write") os.write(wfd, obj_data[:10]) time.sleep(0.5) print("Second write") os.write(wfd, obj_data[10:]) os._exit(0) try: os.close(wfd) rfile = os.fdopen(rfd, "rb", 0) print("Reading") while True: try: obj_copy = pickle.load(rfile) assert obj == obj_copy except EOFError: break print("Success") finally: os.kill(pid, 15) The program reliably fails with Python 3.8 and succeeds with Python 2.7. Providing the unpickler with a buffered reader fixes the issue, so let "os.fdopen" create one. https://bugzilla.mozilla.org/show_bug.cgi?id=1604486 Differential Revision: https://phab.mercurial-scm.org/D8051

File last commit:

r43346:2372284d default
r44718:cb52e619 stable
Show More
check-config.py
191 lines | 5.5 KiB | text/x-python | PythonLexer
#!/usr/bin/env python
#
# check-config - a config flag documentation checker for Mercurial
#
# Copyright 2015 Matt Mackall <mpm@selenic.com>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.
from __future__ import absolute_import, print_function
import re
import sys
foundopts = {}
documented = {}
allowinconsistent = set()
configre = re.compile(
br'''
# Function call
ui\.config(?P<ctype>|int|bool|list)\(
# First argument.
['"](?P<section>\S+)['"],\s*
# Second argument
['"](?P<option>\S+)['"](,\s+
(?:default=)?(?P<default>\S+?))?
\)''',
re.VERBOSE | re.MULTILINE,
)
configwithre = re.compile(
br'''
ui\.config(?P<ctype>with)\(
# First argument is callback function. This doesn't parse robustly
# if it is e.g. a function call.
[^,]+,\s*
['"](?P<section>\S+)['"],\s*
['"](?P<option>\S+)['"](,\s+
(?:default=)?(?P<default>\S+?))?
\)''',
re.VERBOSE | re.MULTILINE,
)
configpartialre = br"""ui\.config"""
ignorere = re.compile(
br'''
\#\s(?P<reason>internal|experimental|deprecated|developer|inconsistent)\s
config:\s(?P<config>\S+\.\S+)$
''',
re.VERBOSE | re.MULTILINE,
)
if sys.version_info[0] > 2:
def mkstr(b):
if isinstance(b, str):
return b
return b.decode('utf8')
else:
mkstr = lambda x: x
def main(args):
for f in args:
sect = b''
prevname = b''
confsect = b''
carryover = b''
linenum = 0
for l in open(f, 'rb'):
linenum += 1
# check topic-like bits
m = re.match(br'\s*``(\S+)``', l)
if m:
prevname = m.group(1)
if re.match(br'^\s*-+$', l):
sect = prevname
prevname = b''
if sect and prevname:
name = sect + b'.' + prevname
documented[name] = 1
# check docstring bits
m = re.match(br'^\s+\[(\S+)\]', l)
if m:
confsect = m.group(1)
continue
m = re.match(br'^\s+(?:#\s*)?(\S+) = ', l)
if m:
name = confsect + b'.' + m.group(1)
documented[name] = 1
# like the bugzilla extension
m = re.match(br'^\s*(\S+\.\S+)$', l)
if m:
documented[m.group(1)] = 1
# like convert
m = re.match(br'^\s*:(\S+\.\S+):\s+', l)
if m:
documented[m.group(1)] = 1
# quoted in help or docstrings
m = re.match(br'.*?``(\S+\.\S+)``', l)
if m:
documented[m.group(1)] = 1
# look for ignore markers
m = ignorere.search(l)
if m:
if m.group('reason') == b'inconsistent':
allowinconsistent.add(m.group('config'))
else:
documented[m.group('config')] = 1
# look for code-like bits
line = carryover + l
m = configre.search(line) or configwithre.search(line)
if m:
ctype = m.group('ctype')
if not ctype:
ctype = 'str'
name = m.group('section') + b"." + m.group('option')
default = m.group('default')
if default in (
None,
b'False',
b'None',
b'0',
b'[]',
b'""',
b"''",
):
default = b''
if re.match(b'[a-z.]+$', default):
default = b'<variable>'
if (
name in foundopts
and (ctype, default) != foundopts[name]
and name not in allowinconsistent
):
print(mkstr(l.rstrip()))
fctype, fdefault = foundopts[name]
print(
"conflict on %s: %r != %r"
% (
mkstr(name),
(mkstr(ctype), mkstr(default)),
(mkstr(fctype), mkstr(fdefault)),
)
)
print("at %s:%d:" % (mkstr(f), linenum))
foundopts[name] = (ctype, default)
carryover = b''
else:
m = re.search(configpartialre, line)
if m:
carryover = line
else:
carryover = b''
for name in sorted(foundopts):
if name not in documented:
if not (
name.startswith(b"devel.")
or name.startswith(b"experimental.")
or name.startswith(b"debug.")
):
ctype, default = foundopts[name]
if default:
if isinstance(default, bytes):
default = mkstr(default)
default = ' [%s]' % default
elif isinstance(default, bytes):
default = mkstr(default)
print(
"undocumented: %s (%s)%s"
% (mkstr(name), mkstr(ctype), default)
)
if __name__ == "__main__":
if len(sys.argv) > 1:
sys.exit(main(sys.argv[1:]))
else:
sys.exit(main([l.rstrip() for l in sys.stdin]))