view i18n/check-translation.py @ 44363:f7459da77f23

nodemap: introduce an option to use mmap to read the nodemap mapping The performance and memory benefit is much greater if we don't have to copy all the data in memory for each information. So we introduce an option (on by default) to read the data using mmap. This changeset is the last one definition the API for index support nodemap data. (they have to be able to use the mmaping). Below are some benchmark comparing the best we currently have in 5.3 with the final step of this series (using the persistent nodemap implementation in Rust). The benchmark run `hg perfindex` with various revset and the following variants: Before: * do not use the persistent nodemap * use the CPython implementation of the index for nodemap * use mmapping of the changelog index After: * use the MixedIndex Rust code, with the NodeTree object for nodemap access (still in review) * use the persistent nodemap data from disk * access the persistent nodemap data through mmap * use mmapping of the changelog index The persistent nodemap greatly speed up most operation on very large repositories. Some of the previously very fast lookup end up a bit slower because the persistent nodemap has to be setup. However the absolute slowdown is very small and won't matters in the big picture. Here are some numbers (in seconds) for the reference copy of mozilla-try: Revset Before After abs-change speedup -10000: 0.004622 0.005532 0.000910 × 0.83 -10: 0.000050 0.000132 0.000082 × 0.37 tip 0.000052 0.000085 0.000033 × 0.61 0 + (-10000:) 0.028222 0.005337 -0.022885 × 5.29 0 0.023521 0.000084 -0.023437 × 280.01 (-10000:) + 0 0.235539 0.005308 -0.230231 × 44.37 (-10:) + :9 0.232883 0.000180 -0.232703 ×1293.79 (-10000:) + (:99) 0.238735 0.005358 -0.233377 × 44.55 :99 + (-10000:) 0.317942 0.005593 -0.312349 × 56.84 :9 + (-10:) 0.313372 0.000179 -0.313193 ×1750.68 :9 0.316450 0.000143 -0.316307 ×2212.93 On smaller repositories, the cost of nodemap related operation is not as big, so the win is much more modest. Yet it helps shaving a handful of millisecond here and there. Here are some numbers (in seconds) for the reference copy of mercurial: Revset Before After abs-change speedup -10: 0.000065 0.000097 0.000032 × 0.67 tip 0.000063 0.000078 0.000015 × 0.80 0 0.000561 0.000079 -0.000482 × 7.10 -10000: 0.004609 0.003648 -0.000961 × 1.26 0 + (-10000:) 0.005023 0.003715 -0.001307 × 1.35 (-10:) + :9 0.002187 0.000108 -0.002079 ×20.25 (-10000:) + 0 0.006252 0.003716 -0.002536 × 1.68 (-10000:) + (:99) 0.006367 0.003707 -0.002660 × 1.71 :9 + (-10:) 0.003846 0.000110 -0.003736 ×34.96 :9 0.003854 0.000099 -0.003755 ×38.92 :99 + (-10000:) 0.007644 0.003778 -0.003866 × 2.02 Differential Revision: https://phab.mercurial-scm.org/D7894
author Pierre-Yves David <pierre-yves.david@octobus.net>
date Tue, 11 Feb 2020 11:18:52 +0100
parents 2372284d9457
children c102b704edb5
line wrap: on
line source

#!/usr/bin/env python
#
# check-translation.py - check Mercurial specific translation problems
from __future__ import absolute_import

import re

import polib

scanners = []
checkers = []


def scanner():
    def decorator(func):
        scanners.append(func)
        return func

    return decorator


def levelchecker(level, msgidpat):
    def decorator(func):
        if msgidpat:
            match = re.compile(msgidpat).search
        else:
            match = lambda msgid: True
        checkers.append((func, level))
        func.match = match
        return func

    return decorator


def match(checker, pe):
    """Examine whether POEntry "pe" is target of specified checker or not
    """
    if not checker.match(pe.msgid):
        return
    # examine suppression by translator comment
    nochecker = 'no-%s-check' % checker.__name__
    for tc in pe.tcomment.split():
        if nochecker == tc:
            return
    return True


####################


def fatalchecker(msgidpat=None):
    return levelchecker('fatal', msgidpat)


@fatalchecker(r'\$\$')
def promptchoice(pe):
    """Check translation of the string given to "ui.promptchoice()"

    >>> pe = polib.POEntry(
    ...     msgid ='prompt$$missing &sep$$missing &amp$$followed by &none',
    ...     msgstr='prompt  missing &sep$$missing  amp$$followed by none&')
    >>> match(promptchoice, pe)
    True
    >>> for e in promptchoice(pe): print(e)
    number of choices differs between msgid and msgstr
    msgstr has invalid choice missing '&'
    msgstr has invalid '&' followed by none
    """
    idchoices = [c.rstrip(' ') for c in pe.msgid.split('$$')[1:]]
    strchoices = [c.rstrip(' ') for c in pe.msgstr.split('$$')[1:]]

    if len(idchoices) != len(strchoices):
        yield "number of choices differs between msgid and msgstr"

    indices = [(c, c.find('&')) for c in strchoices]
    if [c for c, i in indices if i == -1]:
        yield "msgstr has invalid choice missing '&'"
    if [c for c, i in indices if len(c) == i + 1]:
        yield "msgstr has invalid '&' followed by none"


deprecatedpe = None


@scanner()
def deprecatedsetup(pofile):
    pes = [p for p in pofile if p.msgid == '(DEPRECATED)' and p.msgstr]
    if len(pes):
        global deprecatedpe
        deprecatedpe = pes[0]


@fatalchecker(r'\(DEPRECATED\)')
def deprecated(pe):
    """Check for DEPRECATED
    >>> ped = polib.POEntry(
    ...     msgid = '(DEPRECATED)',
    ...     msgstr= '(DETACERPED)')
    >>> deprecatedsetup([ped])
    >>> pe = polib.POEntry(
    ...     msgid = 'Something (DEPRECATED)',
    ...     msgstr= 'something (DEPRECATED)')
    >>> match(deprecated, pe)
    True
    >>> for e in deprecated(pe): print(e)
    >>> pe = polib.POEntry(
    ...     msgid = 'Something (DEPRECATED)',
    ...     msgstr= 'something (DETACERPED)')
    >>> match(deprecated, pe)
    True
    >>> for e in deprecated(pe): print(e)
    >>> pe = polib.POEntry(
    ...     msgid = 'Something (DEPRECATED)',
    ...     msgstr= 'something')
    >>> match(deprecated, pe)
    True
    >>> for e in deprecated(pe): print(e)
    msgstr inconsistently translated (DEPRECATED)
    >>> pe = polib.POEntry(
    ...     msgid = 'Something (DEPRECATED, foo bar)',
    ...     msgstr= 'something (DETACERPED, foo bar)')
    >>> match(deprecated, pe)
    """
    if not (
        '(DEPRECATED)' in pe.msgstr
        or (deprecatedpe and deprecatedpe.msgstr in pe.msgstr)
    ):
        yield "msgstr inconsistently translated (DEPRECATED)"


####################


def warningchecker(msgidpat=None):
    return levelchecker('warning', msgidpat)


@warningchecker()
def taildoublecolons(pe):
    """Check equality of tail '::'-ness between msgid and msgstr

    >>> pe = polib.POEntry(
    ...     msgid ='ends with ::',
    ...     msgstr='ends with ::')
    >>> for e in taildoublecolons(pe): print(e)
    >>> pe = polib.POEntry(
    ...     msgid ='ends with ::',
    ...     msgstr='ends without double-colons')
    >>> for e in taildoublecolons(pe): print(e)
    tail '::'-ness differs between msgid and msgstr
    >>> pe = polib.POEntry(
    ...     msgid ='ends without double-colons',
    ...     msgstr='ends with ::')
    >>> for e in taildoublecolons(pe): print(e)
    tail '::'-ness differs between msgid and msgstr
    """
    if pe.msgid.endswith('::') != pe.msgstr.endswith('::'):
        yield "tail '::'-ness differs between msgid and msgstr"


@warningchecker()
def indentation(pe):
    """Check equality of initial indentation between msgid and msgstr

    This may report unexpected warning, because this doesn't aware
    the syntax of rst document and the context of msgstr.

    >>> pe = polib.POEntry(
    ...     msgid ='    indented text',
    ...     msgstr='  narrowed indentation')
    >>> for e in indentation(pe): print(e)
    initial indentation width differs betweeen msgid and msgstr
    """
    idindent = len(pe.msgid) - len(pe.msgid.lstrip())
    strindent = len(pe.msgstr) - len(pe.msgstr.lstrip())
    if idindent != strindent:
        yield "initial indentation width differs betweeen msgid and msgstr"


####################


def check(pofile, fatal=True, warning=False):
    targetlevel = {'fatal': fatal, 'warning': warning}
    targetcheckers = [
        (checker, level) for checker, level in checkers if targetlevel[level]
    ]
    if not targetcheckers:
        return []

    detected = []
    for checker in scanners:
        checker(pofile)
    for pe in pofile.translated_entries():
        errors = []
        for checker, level in targetcheckers:
            if match(checker, pe):
                errors.extend(
                    (level, checker.__name__, error) for error in checker(pe)
                )
        if errors:
            detected.append((pe, errors))
    return detected


########################################

if __name__ == "__main__":
    import sys
    import optparse

    optparser = optparse.OptionParser(
        """%prog [options] pofile ...

This checks Mercurial specific translation problems in specified
'*.po' files.

Each detected problems are shown in the format below::

    filename:linenum:type(checker): problem detail .....

"type" is "fatal" or "warning". "checker" is the name of the function
detecting corresponded error.

Checking by checker "foo" on the specific msgstr can be suppressed by
the "translator comment" like below. Multiple "no-xxxx-check" should
be separated by whitespaces::

    # no-foo-check
    msgid = "....."
    msgstr = "....."
"""
    )
    optparser.add_option(
        "",
        "--warning",
        help="show also warning level problems",
        action="store_true",
    )
    optparser.add_option(
        "",
        "--doctest",
        help="run doctest of this tool, instead of check",
        action="store_true",
    )
    (options, args) = optparser.parse_args()

    if options.doctest:
        import os

        if 'TERM' in os.environ:
            del os.environ['TERM']
        import doctest

        failures, tests = doctest.testmod()
        sys.exit(failures and 1 or 0)

    detected = []
    warning = options.warning
    for f in args:
        detected.extend(
            (f, pe, errors)
            for pe, errors in check(polib.pofile(f), warning=warning)
        )
    if detected:
        for f, pe, errors in detected:
            for level, checker, error in errors:
                sys.stderr.write(
                    '%s:%d:%s(%s): %s\n'
                    % (f, pe.linenum, level, checker, error)
                )
        sys.exit(1)