| quark | |
| ryanmce |
| hg-reviewers |
This is a simpler workaround alternative to D958, "i18n: clean msgcache when
encoding changes." The cache won't be bloated unless you run tons of commands
with different --encoding options on command server, or serve many repositories
of different web.encoding options on hgweb.
The test was originally written by Jun Wu.
| Automatic diff as part of commit; lint not applicable. |
| Automatic diff as part of commit; unit tests not applicable. |
| localedir = os.path.join(datapath, pycompat.sysstr('locale')) | localedir = os.path.join(datapath, pycompat.sysstr('locale')) | ||||
| t = gettextmod.translation('hg', localedir, _languages, fallback=True) | t = gettextmod.translation('hg', localedir, _languages, fallback=True) | ||||
| global _ugettext | global _ugettext | ||||
| try: | try: | ||||
| _ugettext = t.ugettext | _ugettext = t.ugettext | ||||
| except AttributeError: | except AttributeError: | ||||
| _ugettext = t.gettext | _ugettext = t.gettext | ||||
| _msgcache = {} | _msgcache = {} # encoding: {message: translation} | ||||
| def gettext(message): | def gettext(message): | ||||
| """Translate message. | """Translate message. | ||||
| The message is looked up in the catalog to get a Unicode string, | The message is looked up in the catalog to get a Unicode string, | ||||
| which is encoded in the local encoding before being returned. | which is encoded in the local encoding before being returned. | ||||
| Important: message is restricted to characters in the encoding | Important: message is restricted to characters in the encoding | ||||
| given by sys.getdefaultencoding() which is most likely 'ascii'. | given by sys.getdefaultencoding() which is most likely 'ascii'. | ||||
| """ | """ | ||||
| # If message is None, t.ugettext will return u'None' as the | # If message is None, t.ugettext will return u'None' as the | ||||
| # translation whereas our callers expect us to return None. | # translation whereas our callers expect us to return None. | ||||
| if message is None or not _ugettext: | if message is None or not _ugettext: | ||||
| return message | return message | ||||
| if message not in _msgcache: | cache = _msgcache.setdefault(encoding.encoding, {}) | ||||
| if message not in cache: | |||||
| if type(message) is unicode: | if type(message) is unicode: | ||||
| # goofy unicode docstrings in test | # goofy unicode docstrings in test | ||||
| paragraphs = message.split(u'\n\n') | paragraphs = message.split(u'\n\n') | ||||
| else: | else: | ||||
| paragraphs = [p.decode("ascii") for p in message.split('\n\n')] | paragraphs = [p.decode("ascii") for p in message.split('\n\n')] | ||||
| # Be careful not to translate the empty string -- it holds the | # Be careful not to translate the empty string -- it holds the | ||||
| # meta data of the .po file. | # meta data of the .po file. | ||||
| u = u'\n\n'.join([p and _ugettext(p) or u'' for p in paragraphs]) | u = u'\n\n'.join([p and _ugettext(p) or u'' for p in paragraphs]) | ||||
| try: | try: | ||||
| # encoding.tolocal cannot be used since it will first try to | # encoding.tolocal cannot be used since it will first try to | ||||
| # decode the Unicode string. Calling u.decode(enc) really | # decode the Unicode string. Calling u.decode(enc) really | ||||
| # means u.encode(sys.getdefaultencoding()).decode(enc). Since | # means u.encode(sys.getdefaultencoding()).decode(enc). Since | ||||
| # the Python encoding defaults to 'ascii', this fails if the | # the Python encoding defaults to 'ascii', this fails if the | ||||
| # translated string use non-ASCII characters. | # translated string use non-ASCII characters. | ||||
| encodingstr = pycompat.sysstr(encoding.encoding) | encodingstr = pycompat.sysstr(encoding.encoding) | ||||
| _msgcache[message] = u.encode(encodingstr, "replace") | cache[message] = u.encode(encodingstr, "replace") | ||||
| except LookupError: | except LookupError: | ||||
| # An unknown encoding results in a LookupError. | # An unknown encoding results in a LookupError. | ||||
| _msgcache[message] = message | cache[message] = message | ||||
| return _msgcache[message] | return cache[message] | ||||
| def _plain(): | def _plain(): | ||||
| if ('HGPLAIN' not in encoding.environ | if ('HGPLAIN' not in encoding.environ | ||||
| and 'HGPLAINEXCEPT' not in encoding.environ): | and 'HGPLAINEXCEPT' not in encoding.environ): | ||||
| return False | return False | ||||
| exceptions = encoding.environ.get('HGPLAINEXCEPT', '').strip().split(',') | exceptions = encoding.environ.get('HGPLAINEXCEPT', '').strip().split(',') | ||||
| return 'i18n' not in exceptions | return 'i18n' not in exceptions | ||||
| if _plain(): | if _plain(): | ||||
| _ = lambda message: message | _ = lambda message: message | ||||
| else: | else: | ||||
| _ = gettext | _ = gettext | ||||
| Check Mercurial specific translation problems in each *.po files, and | Check Mercurial specific translation problems in each *.po files, and | ||||
| tool itself by doctest | tool itself by doctest | ||||
| $ cd "$TESTDIR"/../i18n | $ cd "$TESTDIR"/../i18n | ||||
| $ $PYTHON check-translation.py *.po | $ $PYTHON check-translation.py *.po | ||||
| $ $PYTHON check-translation.py --doctest | $ $PYTHON check-translation.py --doctest | ||||
| $ cd $TESTTMP | $ cd $TESTTMP | ||||
| Check i18n cache isn't reused after encoding change: | |||||
| $ cat > $TESTTMP/encodingchange.py << EOF | |||||
| > from mercurial import encoding, registrar | |||||
| > from mercurial.i18n import _ | |||||
| > cmdtable = {} | |||||
| > command = registrar.command(cmdtable) | |||||
| > @command(b'encodingchange', norepo=True) | |||||
| > def encodingchange(ui): | |||||
| > for encode in (b'ascii', b'UTF-8', b'ascii', b'UTF-8'): | |||||
| > encoding.encoding = encode | |||||
| > ui.write(b'%s\n' % _(b'(EXPERIMENTAL)')) | |||||
| > EOF | |||||
| $ LANGUAGE=ja hg --config extensions.encodingchange=$TESTTMP/encodingchange.py encodingchange | |||||
| (?????) | |||||
| (\xe5\xae\x9f\xe9\xa8\x93\xe7\x9a\x84\xe5\xae\x9f\xe8\xa3\x85) (esc) | |||||
| (?????) | |||||
| (\xe5\xae\x9f\xe9\xa8\x93\xe7\x9a\x84\xe5\xae\x9f\xe8\xa3\x85) (esc) | |||||