view i18n/hggettext @ 21424:d13b4ecdb680

test: split test-largefile.t in multiple file The `test-largefiles.t` unified test is significantly longer (about 30%) than any other tests in the mercurial test suite. As a result, its is alway the last test my test runner is waiting for at the end of a run. In practice, this means that `test-largefile.t` is wasting half a minute of my life every times I'm running the mercurial test suites. This probably mean more a few cumulated day by now. I've finally decided to split it up in multiple smaller tests to bring it back in reasonable length. This changeset extracts independent test cases in two files. One dedicated to wire protocole testing, and another one dedicated to all other tests that could be independently extracted. No test case were haltered in the making of this changeset. Various timing available below. All timing have been done on a with 90 jobs on a 64 cores machine. Similar result are shown on firefly (20 jobs on 12 core). General timing of the whole run -------------------------------- We see a 25% real time improvement for no significant cpu time impact. Before split: real 2m1.149s user 58m4.662s sys 11m28.563s After split: real 1m31.977s user 57m45.993s sys 11m33.634s Last test to finish (using run-test.py --time) ---------------------------------------------- test-largefile.t is now finishing at the same time than other slow tests. Before split: Time Test 119.280 test-largefiles.t 93.995 test-mq.t 89.897 test-subrepo.t 86.920 test-glog.t 85.508 test-rename-merge2.t 83.594 test-revset.t 79.824 test-keyword.t 78.077 test-mq-header-date.t After split: Time Test 90.414 test-mq.t 88.594 test-largefiles.t 85.363 test-subrepo.t 81.059 test-glog.t 78.927 test-rename-merge2.t 78.021 test-revset.t 77.777 test-command-template.t Timing of largefile test themself ----------------------------------- Running only tests prefixed with "test-largefiles". No significant change in cumulated time. Before: Time Test 58.673 test-largefiles.t 2.931 test-largefiles-cache.t 0.583 test-largefiles-small-disk.t After: Time Test 31.754 test-largefiles.t 17.460 test-largefiles-misc.t 8.888 test-largefiles-wireproto.t 2.864 test-largefiles-cache.t 0.580 test-largefiles-small-disk.t
author Pierre-Yves David <pierre-yves.david@fb.com>
date Fri, 16 May 2014 13:18:57 -0700
parents 80deae3bc5ea
children 2516bba643e7
line wrap: on
line source

#!/usr/bin/env python
#
# hggettext - carefully extract docstrings for Mercurial
#
# Copyright 2009 Matt Mackall <mpm@selenic.com> 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.
"""

import os, sys, inspect


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')


def offset(src, doc, name, default):
    """Compute offset or issue a warning on stdout."""
    # 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("warning: unknown offset in %s, assuming %d lines\n"
                         % (name, 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 mod.__doc__:
        src = open(path).read()
        lineno = 1 + offset(src, mod.__doc__, path, 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.itervalues())

    for func, rstrip in functions:
        if func.__doc__:
            src = inspect.getsource(func)
            name = "%s.%s" % (path, func.__name__)
            lineno = func.func_code.co_firstlineno
            doc = func.__doc__
            if rstrip:
                doc = doc.rstrip()
            lineno += offset(src, doc, name, 1)
            print poentry(path, lineno, doc)


def rawtext(path):
    src = open(path).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)