view i18n/hggettext @ 36037:8de90e006c78

run-tests: report tests that exception occurred in We now record the test that an exception occurred in. We put this information to use by aggregating the count of failures in each test. For each exception, the exception report now prints the total number of tests having that exception and the test with the least number of exceptions exhibiting that failure. The exception list is now sorted by (total count, tests impacted, count of failures in least failing test). This allows us to: * Assess how widespread a failure is. Some exceptions occur a lot in a few tests. Others occur over many tests. * Easily run a test exhibiting an exception without having to find a failure in test output. * Find and fix low hanging fruit (e.g. exceptions that are the only failure in a test). Here's an example of the new output: 199 (4 tests) /home/gps/src/hg/hgext/blackbox.py:191: %b requires a bytes-like object, or an object that implements __bytes__, not 'str' (test-devel-warnings.t - 1 total) 142 (19 tests) /home/gps/src/hg/hgext/mq.py:655: list indices must be integers or slices, not bytes (test-hardlinks.t - 1 total) 140 (20 tests) /home/gps/src/hg/mercurial/patch.py:296: string argument expected, got 'bytes' (test-audit-subrepo.t - 1 total) 101 (15 tests) /home/gps/src/hg/hgext/convert/convcmd.py:60: encode() argument 1 must be str, not bytes (test-convert-clonebranches.t - 1 total) 90 (2 tests) /home/gps/src/hg/hgext/mq.py:456: can't concat str to bytes (test-mq-qqueue.t - 1 total) 87 (2 tests) /home/gps/src/hg/mercurial/branchmap.py:380: %b requires a bytes-like object, or an object that implements __bytes__, not 'FileNotFoundError' (test-branches.t - 2 total) 85 (22 tests) /home/gps/src/hg/mercurial/sshpeer.py:223: cannot convert 'UUID' object to bytes (test-bundle2-pushback.t - 1 total) 1 (1 tests) /home/gps/src/hg/mercurial/formatter.py:254: %b requires a bytes-like object, or an object that implements __bytes__, not 'str' (test-debugextensions.t - 2 total) 1 (1 tests) /home/gps/src/hg/hgext/convert/convcmd.py:420: startswith first arg must be str or a tuple of str, not bytes (test-convert-authormap.t - 2 total) 1 (1 tests) /home/gps/src/hg/mercurial/revlog.py:797: '>=' not supported between instances of 'NoneType' and 'int' (test-unionrepo.t - 1 total) 1 (1 tests) /home/gps/src/hg/hgext/show.py:129: %b requires a bytes-like object, or an object that implements __bytes__, not 'str' (test-show.t - 1 total) Differential Revision: https://phab.mercurial-scm.org/D2138
author Gregory Szorc <gregory.szorc@gmail.com>
date Sun, 11 Feb 2018 12:42:10 -0800
parents d5ef17608159
children 0585337ea787
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.
"""

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, 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("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 not path.startswith('mercurial/') and 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__:
            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)
            name = "%s.%s" % (actualpath, func.__name__)
            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, name, 1)
            else:
                lineno += offset(src, doc, name, 1)
            print(poentry(actualpath, 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)