annotate i18n/hggettext @ 47866:4162f6b40f2c stable

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
#
# hggettext - carefully extract docstrings for Mercurial
#
# Copyright 2009 Olivia Mackall <[e-mail]> and others
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

# The normalize function is taken from pygettext which is distributed
# with Python under the Python License, which is GPL compatible.

"""Extract docstrings from Mercurial commands.

Compared to pygettext, this script knows about the cmdtable and table
dictionaries used by Mercurial, and will only extract docstrings from
functions mentioned therein.

Use xgettext like normal to extract strings marked as translatable and
join the message cataloges to get the final catalog.
"""

from __future__ import absolute_import, print_function

import inspect
import os
import re
import sys


def escape(s):
    # The order is important, the backslash must be escaped first
    # since the other replacements introduce new backslashes
    # themselves.
    s = s.replace('\\', '\\\\')
    s = s.replace('\n', '\\n')
    s = s.replace('\r', '\\r')
    s = s.replace('\t', '\\t')
    s = s.replace('"', '\\"')
    return s


def normalize(s):
    # This converts the various Python string types into a format that
    # is appropriate for .po files, namely much closer to C style.
    lines = s.split('\n')
    if len(lines) == 1:
        s = '"' + escape(s) + '"'
    else:
        if not lines[-1]:
            del lines[-1]
            lines[-1] = lines[-1] + '\n'
        lines = map(escape, lines)
        lineterm = '\\n"\n"'
        s = '""\n"' + lineterm.join(lines) + '"'
    return s


def poentry(path, lineno, s):
    return (
        '#: %s:%d\n' % (path, lineno)
        + 'msgid %s\n' % normalize(s)
        + 'msgstr ""\n'
    )


doctestre = re.compile(r'^ +>>> ', re.MULTILINE)


def offset(src, doc, name, lineno, default):
    """Compute offset or issue a warning on stdout."""
    # remove doctest part, in order to avoid backslash mismatching
    m = doctestre.search(doc)
    if m:
        doc = doc[: m.start()]

    # Backslashes in doc appear doubled in src.
    end = src.find(doc.replace('\\', '\\\\'))
    if end == -1:
        # This can happen if the docstring contains unnecessary escape
        # sequences such as \" in a triple-quoted string. The problem
        # is that \" is turned into " and so doc wont appear in src.
        sys.stderr.write(
            "%s:%d:warning:"
            " unknown docstr offset, assuming %d lines\n"
            % (name, lineno, default)
        )
        return default
    else:
        return src.count('\n', 0, end)


def importpath(path):
    """Import a path like foo/bar/baz.py and return the baz module."""
    if path.endswith('.py'):
        path = path[:-3]
    if path.endswith('/__init__'):
        path = path[:-9]
    path = path.replace('/', '.')
    mod = __import__(path)
    for comp in path.split('.')[1:]:
        mod = getattr(mod, comp)
    return mod


def docstrings(path):
    """Extract docstrings from path.

    This respects the Mercurial cmdtable/table convention and will
    only extract docstrings from functions mentioned in these tables.
    """
    mod = importpath(path)
    if not path.startswith('mercurial/') and mod.__doc__:
        with open(path) as fobj:
            src = fobj.read()
        lineno = 1 + offset(src, mod.__doc__, path, 1, 7)
        print(poentry(path, lineno, mod.__doc__))

    functions = list(getattr(mod, 'i18nfunctions', []))
    functions = [(f, True) for f in functions]

    cmdtable = getattr(mod, 'cmdtable', {})
    if not cmdtable:
        # Maybe we are processing mercurial.commands?
        cmdtable = getattr(mod, 'table', {})
    functions.extend((c[0], False) for c in cmdtable.values())

    for func, rstrip in functions:
        if func.__doc__:
            docobj = func  # this might be a proxy to provide formatted doc
            func = getattr(func, '_origfunc', func)
            funcmod = inspect.getmodule(func)
            extra = ''
            if funcmod.__package__ == funcmod.__name__:
                extra = '/__init__'
            actualpath = '%s%s.py' % (funcmod.__name__.replace('.', '/'), extra)

            src = inspect.getsource(func)
            lineno = inspect.getsourcelines(func)[1]
            doc = docobj.__doc__
            origdoc = getattr(docobj, '_origdoc', '')
            if rstrip:
                doc = doc.rstrip()
                origdoc = origdoc.rstrip()
            if origdoc:
                lineno += offset(src, origdoc, actualpath, lineno, 1)
            else:
                lineno += offset(src, doc, actualpath, lineno, 1)
            print(poentry(actualpath, lineno, doc))


def rawtext(path):
    with open(path) as f:
        src = f.read()
    print(poentry(path, 1, src))


if __name__ == "__main__":
    # It is very important that we import the Mercurial modules from
    # the source tree where hggettext is executed. Otherwise we might
    # accidentally import and extract strings from a Mercurial
    # installation mentioned in PYTHONPATH.
    sys.path.insert(0, os.getcwd())
    from mercurial import demandimport

    demandimport.enable()
    for path in sys.argv[1:]:
        if path.endswith('.txt'):
            rawtext(path)
        else:
            docstrings(path)