windows: degrade to py2 behavior when reading a non-symlink as a symlink
While waiting for the push to hg-committed in WSL to complete, I ran a
`phabimport` from Windows and got this traceback:
$ hg phabimport 11313
** Unknown exception encountered with possibly-broken third-party extension "mercurial_keyring" (version N/A)
** which supports versions unknown of Mercurial.
** Please disable "mercurial_keyring" and try your action again.
** If that fixes the bug please report it to https://foss.heptapod.net/mercurial/mercurial_keyring/issues
** Python 3.9.5 (default, May 6 2021, 17:29:31) [MSC v.1928 64 bit (AMD64)]
** Mercurial Distributed SCM (version 5.9rc1+hg32.
0e2f5733563d)
** Extensions loaded: absorb, blackbox, evolve 10.3.3, extdiff, fastannotate, fix, mercurial_keyring, mq, phabblocker
20210126, phabricator, rebase, show, strip, topic 0.22.3
Traceback (most recent call last):
File "mercurial.lock", line 279, in _trylock
File "mercurial.vfs", line 202, in makelock
File "mercurial.util", line 2147, in makelock
FileExistsError: [WinError 183] Cannot create a file when that file already exists: b'hp-omen:78348' -> b'C:\\Users\\Matt\\hg/.hg/store/lock'
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "<string>", line 24, in <module>
File "mercurial.dispatch", line 144, in run
File "mercurial.dispatch", line 250, in dispatch
File "mercurial.dispatch", line 294, in _rundispatch
File "mercurial.dispatch", line 470, in _runcatch
File "mercurial.dispatch", line 480, in _callcatch
File "mercurial.scmutil", line 153, in callcatch
File "mercurial.dispatch", line 460, in _runcatchfunc
File "mercurial.dispatch", line 1273, in _dispatch
File "mercurial.dispatch", line 918, in runcommand
File "mercurial.dispatch", line 1285, in _runcommand
File "mercurial.dispatch", line 1271, in <lambda>
File "mercurial.util", line 1886, in check
File "mercurial.util", line 1886, in check
File "hgext.mq", line 4239, in mqcommand
File "mercurial.util", line 1886, in check
File "mercurial.util", line 1886, in check
File "hgext.phabricator", line 314, in inner
File "hgext.phabricator", line 2222, in phabimport
File "hgext.phabricator", line 2123, in readpatch
File "hgext.phabricator", line 2199, in _write
File "mercurial.localrepo", line 2956, in lock
File "mercurial.localrepo", line 2918, in _lock
File "mercurial.lock", line 152, in trylock
File "mercurial.lock", line 283, in _trylock
File "mercurial.lock", line 314, in _readlock
File "mercurial.vfs", line 221, in readlock
File "mercurial.util", line 2163, in readlock
File "mercurial.windows", line 619, in readlink
ValueError: not a symbolic link
Both exceptions look accurate (the file exists, and the Windows side can't read
WSL side symlinks). I didn't try to reproduce this entirely within the Windows
side, but we can do better than a cryptic stacktrace. With this change, the
same scenario results in this abort:
abort: C:\Users\Matt\hg/.hg/store/lock: The file cannot be accessed by the system
When both the `push` and `phabimport` are done on the Windows side, it prints a
message about waiting for the lock, and successfully applies the patch after the
push completes.
I'm not sure if there's enough info to be able to convert the abort into the
wait scenario. As it stands now, we don't support symlinks on Windows, which
requires either a UAC Administrator level process or an opt-in in developer
mode, and there are several places where the new symlink on Windows support in
py3 was explicitly disabled in order to get tests to pass quicker.
Differential Revision: https://phab.mercurial-scm.org/D11333
#!/usr/bin/env python3
"""
Utility for inspecting files in various ways.
This tool is like the collection of tools found in a unix environment but are
cross platform and stable and suitable for our needs in the test suite.
This can be used instead of tools like:
[
dd
find
head
hexdump
ls
md5sum
readlink
sha1sum
stat
tail
test
readlink.py
md5sum.py
"""
from __future__ import absolute_import
import binascii
import glob
import hashlib
import optparse
import os
import re
import sys
# Python 3 adapters
ispy3 = sys.version_info[0] >= 3
if ispy3:
def iterbytes(s):
for i in range(len(s)):
yield s[i : i + 1]
else:
iterbytes = iter
def visit(opts, filenames, outfile):
"""Process filenames in the way specified in opts, writing output to
outfile."""
for f in sorted(filenames):
isstdin = f == '-'
if not isstdin and not os.path.lexists(f):
outfile.write(b'%s: file not found\n' % f.encode('utf-8'))
continue
quiet = opts.quiet and not opts.recurse or isstdin
isdir = os.path.isdir(f)
islink = os.path.islink(f)
isfile = os.path.isfile(f) and not islink
dirfiles = None
content = None
facts = []
if isfile:
if opts.type:
facts.append(b'file')
if any((opts.hexdump, opts.dump, opts.md5, opts.sha1, opts.sha256)):
with open(f, 'rb') as fobj:
content = fobj.read()
elif islink:
if opts.type:
facts.append(b'link')
content = os.readlink(f).encode('utf8')
elif isstdin:
content = getattr(sys.stdin, 'buffer', sys.stdin).read()
if opts.size:
facts.append(b'size=%d' % len(content))
elif isdir:
if opts.recurse or opts.type:
dirfiles = glob.glob(f + '/*')
facts.append(b'directory with %d files' % len(dirfiles))
elif opts.type:
facts.append(b'type unknown')
if not isstdin:
stat = os.lstat(f)
if opts.size and not isdir:
facts.append(b'size=%d' % stat.st_size)
if opts.mode and not islink:
facts.append(b'mode=%o' % (stat.st_mode & 0o777))
if opts.links:
facts.append(b'links=%d' % stat.st_nlink)
if opts.newer:
# mtime might be in whole seconds so newer file might be same
if stat.st_mtime >= os.stat(opts.newer).st_mtime:
facts.append(
b'newer than %s' % opts.newer.encode('utf8', 'replace')
)
else:
facts.append(
b'older than %s' % opts.newer.encode('utf8', 'replace')
)
if opts.md5 and content is not None:
h = hashlib.md5(content)
facts.append(b'md5=%s' % binascii.hexlify(h.digest())[: opts.bytes])
if opts.sha1 and content is not None:
h = hashlib.sha1(content)
facts.append(
b'sha1=%s' % binascii.hexlify(h.digest())[: opts.bytes]
)
if opts.sha256 and content is not None:
h = hashlib.sha256(content)
facts.append(
b'sha256=%s' % binascii.hexlify(h.digest())[: opts.bytes]
)
if isstdin:
outfile.write(b', '.join(facts) + b'\n')
elif facts:
outfile.write(b'%s: %s\n' % (f.encode('utf-8'), b', '.join(facts)))
elif not quiet:
outfile.write(b'%s:\n' % f.encode('utf-8'))
if content is not None:
chunk = content
if not islink:
if opts.lines:
if opts.lines >= 0:
chunk = b''.join(chunk.splitlines(True)[: opts.lines])
else:
chunk = b''.join(chunk.splitlines(True)[opts.lines :])
if opts.bytes:
if opts.bytes >= 0:
chunk = chunk[: opts.bytes]
else:
chunk = chunk[opts.bytes :]
if opts.hexdump:
for i in range(0, len(chunk), 16):
s = chunk[i : i + 16]
outfile.write(
b'%04x: %-47s |%s|\n'
% (
i,
b' '.join(b'%02x' % ord(c) for c in iterbytes(s)),
re.sub(b'[^ -~]', b'.', s),
)
)
if opts.dump:
if not quiet:
outfile.write(b'>>>\n')
outfile.write(chunk)
if not quiet:
if chunk.endswith(b'\n'):
outfile.write(b'<<<\n')
else:
outfile.write(b'\n<<< no trailing newline\n')
if opts.recurse and dirfiles:
assert not isstdin
visit(opts, dirfiles, outfile)
if __name__ == "__main__":
parser = optparse.OptionParser("%prog [options] [filenames]")
parser.add_option(
"-t",
"--type",
action="store_true",
help="show file type (file or directory)",
)
parser.add_option(
"-m", "--mode", action="store_true", help="show file mode"
)
parser.add_option(
"-l", "--links", action="store_true", help="show number of links"
)
parser.add_option(
"-s", "--size", action="store_true", help="show size of file"
)
parser.add_option(
"-n", "--newer", action="store", help="check if file is newer (or same)"
)
parser.add_option(
"-r", "--recurse", action="store_true", help="recurse into directories"
)
parser.add_option(
"-S",
"--sha1",
action="store_true",
help="show sha1 hash of the content",
)
parser.add_option(
"",
"--sha256",
action="store_true",
help="show sha256 hash of the content",
)
parser.add_option(
"-M", "--md5", action="store_true", help="show md5 hash of the content"
)
parser.add_option(
"-D", "--dump", action="store_true", help="dump file content"
)
parser.add_option(
"-H", "--hexdump", action="store_true", help="hexdump file content"
)
parser.add_option(
"-B", "--bytes", type="int", help="number of characters to dump"
)
parser.add_option(
"-L", "--lines", type="int", help="number of lines to dump"
)
parser.add_option(
"-q", "--quiet", action="store_true", help="no default output"
)
(opts, filenames) = parser.parse_args(sys.argv[1:])
if not filenames:
filenames = ['-']
visit(opts, filenames, getattr(sys.stdout, 'buffer', sys.stdout))