i18n/check-translation.py
author Martin von Zweigbergk <martinvonz@google.com>
Fri, 12 Apr 2019 22:03:04 -0700
changeset 42204 31abb9d713af
parent 40185 19fc5a986669
child 43076 2372284d9457
permissions -rwxr-xr-x
copies: don't include copies that are not in source in directory move I've been working on a rewrite of mergecopies(). I compared the output of the rewritten version with the current version. I noticed that between FIREFOX_NIGHTLY_59_END and FIREFOX_BETA_60_BASE in the mozilla-unified repo, there were many copies that the current version detected that the rewritten version did not. One example was js/src/gc/Iteration.h -> js/src/gc/PublicIterators.h. Then I realized that js/src/gc/Iteration.h doesn't even exist in FIREFOX_NIGHTLY_59_END. This patch adds a filtering step for the "fullcopy" dict. It turns out that that change also affects the test for issue5020 in test-merge-criss-cross.t. The 'dm' action no longer happens there. At first I thought that the test case change meant that this patch was broken, but I think it's actually correct tha the 'dm' action should not happen there. The result of the bid merge is still the same. I suspect this filtering is a better solution for the issue than 41f6af50c0d8 (merge: fix crash on criss cross merge with dir move and delete (issue5020), 2017-01-31). I also suspect that it was broken just a few months earlier by a005c33d0bd7 (mergecopies: add logic to process incomplete data, 2016-10-04). Note that bid merge had been enabled for a few years at that point, since 19903277f035 (merge: use bid merge by default (BC), 2014-10-01). This patch is still just a workaround. It will be cleaned up soon (with the rewrite of mergecopies()). But doing this in a separate patch makes later patches easier to understand and gives a place to explain why this is changing. Differential Revision: https://phab.mercurial-scm.org/D6244

#!/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)