diff --git a/genshi/filters/i18n.py b/genshi/filters/i18n.py --- a/genshi/filters/i18n.py +++ b/genshi/filters/i18n.py @@ -51,14 +51,14 @@ class I18NDirectiveExtract(I18NDirective): """Simple interface for directives to support messages extraction""" - def extract(self, stream, ctxt): + def extract(self, stream, ctxt, error_callback=None): raise NotImplementedError class CommentDirective(I18NDirective): """Implementation of the ``i18n:comment`` template directive which adds translation comments. - + >>> from genshi.template import MarkupTemplate >>> >>> tmpl = MarkupTemplate(''' @@ -83,7 +83,7 @@ class MsgDirective(I18NDirectiveExtract): r"""Implementation of the ``i18n:msg`` directive which marks inner content as translatable. Consider the following examples: - + >>> from genshi.template import MarkupTemplate >>> tmpl = MarkupTemplate(''' ...
@@ -92,7 +92,7 @@ ...
...

Foo bar!

... ''') - + >>> translator = Translator() >>> translator.setup(tmpl) >>> list(translator.extract(tmpl.stream)) @@ -131,7 +131,7 @@

Foo bar!

>>> - + Starting and ending white-space is stripped of to make it simpler for translators. Stripping it is not that important since it's on the html source, the rendered output will remain the same. @@ -179,8 +179,8 @@ return _apply_directives(_generate(), directives, ctxt) - def extract(self, stream, ctxt): - msgbuf = MessageBuffer(self) + def extract(self, stream, ctxt, error_callback=None): + msgbuf = MessageBuffer(self, error_callback=error_callback) stream = iter(stream) previous = stream.next() @@ -192,7 +192,9 @@ if previous[0] is not END: msgbuf.append(*previous) - yield None, msgbuf.format(), filter(None, [ctxt.get('_i18n.comment')]) + if msgbuf.valid: + yield (None, msgbuf.format(), + filter(None, [ctxt.get('_i18n.comment')])) class InnerChooseDirective(I18NDirective): @@ -241,13 +243,13 @@ class ChooseDirective(I18NDirectiveExtract): """Implementation of the ``i18n:choose`` directive which provides plural internationalisation of strings. - + This directive requires at least one parameter, the one which evaluates to an integer which will allow to choose the plural/singular form. If you also have expressions inside the singular and plural version of the string you also need to pass a name for those parameters. Consider the following examples: - + >>> from genshi.template import MarkupTemplate >>> >>> translator = Translator() @@ -285,7 +287,7 @@ >>> - + When used as a directive and not as an attribute: >>> tmpl = MarkupTemplate('''\ @@ -381,15 +383,15 @@ ctxt.pop() - def extract(self, stream, ctxt): + def extract(self, stream, ctxt, error_callback=None): stream = iter(stream) previous = stream.next() if previous is START: stream.next() - singular_msgbuf = MessageBuffer(self) - plural_msgbuf = MessageBuffer(self) + singular_msgbuf = MessageBuffer(self, error_callback=error_callback) + plural_msgbuf = MessageBuffer(self, error_callback=error_callback) for kind, event, pos in stream: if kind is SUB: @@ -407,15 +409,16 @@ else: singular_msgbuf.append(kind, event, pos) plural_msgbuf.append(kind, event, pos) - yield 'ngettext', \ - (singular_msgbuf.format(), plural_msgbuf.format()), \ - filter(None, [ctxt.get('_i18n.comment')]) + if singular_msgbuf.valid and plural_msgbuf.valid: + yield 'ngettext', \ + (singular_msgbuf.format(), plural_msgbuf.format()), \ + filter(None, [ctxt.get('_i18n.comment')]) class DomainDirective(I18NDirective): """Implementation of the ``i18n:domain`` directive which allows choosing another i18n domain(catalog) to translate from. - + >>> from genshi.template.markup import MarkupTemplate >>> class DummyTranslations(NullTranslations): @@ -479,7 +482,7 @@ def __init__(self, value, template, hints=None, namespaces=None, lineno=-1, offset=-1): Directive.__init__(self, None, template, namespaces, lineno, offset) - self.domain = value and value.strip() or '__DEFAULT__' + self.domain = value and value.strip() or '__DEFAULT__' @classmethod def attach(cls, template, stream, value, namespaces, pos): @@ -498,9 +501,9 @@ class Translator(DirectiveFactory): """Can extract and translate localizable strings from markup streams and templates. - + For example, assume the following template: - + >>> from genshi.template import MarkupTemplate >>> >>> tmpl = MarkupTemplate(''' @@ -512,10 +515,10 @@ ...

${_("Hello, %(name)s") % dict(name=username)}

... ... ''', filename='example.html') - + For demonstration, we define a dummy ``gettext``-style function with a hard-coded translation table, and pass that to the `Translator` initializer: - + >>> def pseudo_gettext(string): ... return { ... 'Example': 'Beispiel', @@ -523,15 +526,15 @@ ... }[string] >>> >>> translator = Translator(pseudo_gettext) - + Next, the translator needs to be prepended to any already defined filters on the template: - + >>> tmpl.filters.insert(0, translator) - + When generating the template output, our hard-coded translations should be applied as expected: - + >>> print tmpl.generate(username='Hans', _=pseudo_gettext) @@ -542,7 +545,7 @@

Hallo, Hans

- + Note that elements defining ``xml:lang`` attributes that do not contain variable expressions are ignored by this filter. That can be used to exclude specific parts of a template from being extracted and translated. @@ -569,7 +572,7 @@ def __init__(self, translate=NullTranslations(), ignore_tags=IGNORE_TAGS, include_attrs=INCLUDE_ATTRS, extract_text=True): """Initialize the translator. - + :param translate: the translation function, for example ``gettext`` or ``ugettext``. :param ignore_tags: a set of tag names that should not be localized @@ -577,7 +580,7 @@ :param extract_text: whether the content of text nodes should be extracted, or only text in explicit ``gettext`` function calls - + :note: Changed in 0.6: the `translate` parameter can now be either a ``gettext``-style function, or an object compatible with the ``NullTransalations`` or ``GNUTranslations`` interface @@ -589,13 +592,13 @@ def __call__(self, stream, ctxt=None, search_text=True): """Translate any localizable strings in the given stream. - + This function shouldn't be called directly. Instead, an instance of the `Translator` class should be registered as a filter with the `Template` or the `TemplateLoader`, or applied as a regular stream filter. If used as a template filter, it should be inserted in front of all the default filters. - + :param stream: the markup event stream :param ctxt: the template context (not used) :param search_text: whether text nodes should be translated (used @@ -720,12 +723,13 @@ 'ugettext', 'ungettext') def extract(self, stream, gettext_functions=GETTEXT_FUNCTIONS, - search_text=True, msgbuf=None, ctxt=Context()): + search_text=True, msgbuf=None, ctxt=Context(), + error_callback=None): """Extract localizable strings from the given template stream. - + For every string found, this function yields a ``(lineno, function, message, comments)`` tuple, where: - + * ``lineno`` is the number of the line on which the string was found, * ``function`` is the name of the ``gettext`` function used (if the string was extracted from embedded Python code), and @@ -734,7 +738,7 @@ arguments). * ``comments`` is a list of comments related to the message, extracted from ``i18n:comment`` attributes found in the markup - + >>> from genshi.template import MarkupTemplate >>> >>> tmpl = MarkupTemplate(''' @@ -754,7 +758,7 @@ 6, None, u'Example' 7, '_', u'Hello, %(name)s' 8, 'ngettext', (u'You have %d item', u'You have %d items', None) - + :param stream: the event stream to extract strings from; can be a regular stream or a template stream :param gettext_functions: a sequence of function names that should be @@ -763,14 +767,17 @@ :param search_text: whether the content of text nodes should be extracted (used internally) :param ctxt: the current extraction context (used internaly) - + :param error_callback: a function that gets called in case of extraction + errors with the following arguments: + (filename, line_number, error_message) + :note: Changed in 0.4.1: For a function with multiple string arguments (such as ``ngettext``), a single item with a tuple of strings is yielded, instead an item for each string argument. :note: Changed in 0.6: The returned tuples now include a 4th element, which is a list of comments for the translator. Added an ``ctxt`` argument which is used to pass arround the current extraction - context. + context. Added an error_callback used to show errors to the user. """ if not self.extract_text: search_text = False @@ -803,8 +810,9 @@ yield pos[1], None, text, [] else: for lineno, funcname, text, comments in self.extract( - _ensure(value), gettext_functions, - search_text=False): + _ensure(value), gettext_functions, + search_text=False, + error_callback=error_callback): yield lineno, funcname, text, comments if msgbuf: @@ -821,7 +829,7 @@ elif not skip and msgbuf and kind is END: msgbuf.append(kind, data, pos) - if not msgbuf.depth: + if not msgbuf.depth and msgbuf.valid: yield msgbuf.lineno, None, msgbuf.format(), \ filter(None, [msgbuf.comment]) msgbuf = None @@ -850,7 +858,8 @@ messages = self.extract( substream, gettext_functions, search_text=search_text and not skip, - msgbuf=msgbuf, ctxt=ctxt) + msgbuf=msgbuf, ctxt=ctxt, + error_callback=error_callback) for lineno, funcname, text, comments in messages: yield lineno, funcname, text, comments directives.pop(idx) @@ -870,13 +879,16 @@ for directive in directives: if isinstance(directive, I18NDirectiveExtract): - messages = directive.extract(substream, ctxt) + messages = directive.extract( + substream, ctxt, error_callback=error_callback + ) for funcname, text, comments in messages: yield pos[1], funcname, text, comments else: messages = self.extract( substream, gettext_functions, - search_text=search_text and not skip, msgbuf=msgbuf) + search_text=search_text and not skip, msgbuf=msgbuf, + error_callback=error_callback) for lineno, funcname, text, comments in messages: yield lineno, funcname, text, comments if comment: @@ -885,7 +897,7 @@ def setup(self, template): """Convenience function to register the `Translator` filter and the related directives with the given template. - + :param template: a `Template` instance """ template.filters.insert(0, self) @@ -895,13 +907,13 @@ class MessageBuffer(object): """Helper class for managing internationalized mixed content. - + :since: version 0.5 """ - def __init__(self, directive=None): + def __init__(self, directive=None, error_callback=None): """Initialize the message buffer. - + :param params: comma-separated list of parameter names :type params: `basestring` :param lineno: the line number on which the first stream event @@ -917,16 +929,21 @@ self.depth = 1 self.order = 1 self.stack = [0] + self.error_callback = error_callback + self.valid = True self.subdirectives = {} def append(self, kind, data, pos): """Append a stream event to the buffer. - + :param kind: the stream event kind :param data: the event data :param pos: the position of the event in the source """ - if kind is SUB: + if not self.valid: + # Buffer is already invalid, no point wasting process time here + return + elif kind is SUB: # The order needs to be +1 because a new START kind event will # happen and we we need to wrap those events into our custom kind(s) order = self.stack[-1] + 1 @@ -948,22 +965,29 @@ if self.params: param = self.params.pop(0) else: - params = ', '.join(['"%s"' % p for p in self.orig_params if p]) - if params: - params = "(%s)" % params - raise IndexError("%d parameters%s given to 'i18n:%s' but " - "%d or more expressions used in '%s', line %s" - % (len(self.orig_params), params, - self.directive.tagname, - len(self.orig_params)+1, - os.path.basename(pos[0] or - 'In Memmory Template'), - pos[1])) + # Failed to get the expression param name + # Invalidate and if possible warn + self.valid = False + if self.error_callback: + params = ', '.join(['"%s"' % p for p in + self.orig_params if p]) + fname, lineno = pos[0] or '(unknown)', pos[1] + if params: + params = "(%s)" % params + self.error_callback( + fname, lineno, + "%d parameters%s given to 'i18n:%s' but %d or more " + "expressions used. Stopped Processing File." + % (len(self.orig_params), params, + self.directive.tagname, len(self.orig_params)+1) + ) + # Nothing else to do here + return self.string.append('%%(%s)s' % param) self.events.setdefault(self.stack[-1], []).append((kind, data, pos)) self.values[param] = (kind, data, pos) else: - if kind is START: + if kind is START: self.string.append(u'[%d:' % self.order) self.stack.append(self.order) self.events.setdefault(self.stack[-1], @@ -986,11 +1010,11 @@ def translate(self, string, regex=re.compile(r'%\((\w+)\)s')): """Interpolate the given message translation with the events in the buffer and return the translated stream. - + :param string: the translated message string """ substream = None - + def yield_parts(string): for idx, part in enumerate(regex.split(string)): if idx % 2: @@ -1077,19 +1101,19 @@ def parse_msg(string, regex=re.compile(r'(?:\[(\d+)\:)|(?>> parse_msg("See [1:Help].") [(0, 'See '), (1, 'Help'), (0, '.')] - + >>> parse_msg("See [1:our [2:Help] page] for details.") [(0, 'See '), (1, 'our '), (2, 'Help'), (1, ' page'), (0, ' for details.')] - + >>> parse_msg("[2:Details] finden Sie in [1:Hilfe].") [(2, 'Details'), (0, ' finden Sie in '), (1, 'Hilfe'), (0, '.')] - + >>> parse_msg("[1:] Bilder pro Seite anzeigen.") [(1, ''), (0, ' Bilder pro Seite anzeigen.')] - + :param string: the translated message string :return: a list of ``(order, string)`` tuples :rtype: `list` @@ -1121,18 +1145,18 @@ def extract_from_code(code, gettext_functions): """Extract strings from Python bytecode. - + >>> from genshi.template.eval import Expression - + >>> expr = Expression('_("Hello")') >>> list(extract_from_code(expr, Translator.GETTEXT_FUNCTIONS)) [('_', u'Hello')] - + >>> expr = Expression('ngettext("You have %(num)s item", ' ... '"You have %(num)s items", num)') >>> list(extract_from_code(expr, Translator.GETTEXT_FUNCTIONS)) [('ngettext', (u'You have %(num)s item', u'You have %(num)s items', None))] - + :param code: the `Code` object :type code: `genshi.template.eval.Code` :param gettext_functions: a sequence of function names @@ -1172,7 +1196,7 @@ def extract(fileobj, keywords, comment_tags, options): """Babel extraction method for Genshi templates. - + :param fileobj: the file-like object the messages should be extracted from :param keywords: a list of keywords (i.e. function names) that should be recognized as translation functions @@ -1205,10 +1229,13 @@ tmpl = template_class(fileobj, filename=getattr(fileobj, 'name', None), encoding=encoding) + error_callback = options.get('error_callback') + translator = Translator(None, ignore_tags, include_attrs, extract_text) if hasattr(tmpl, 'add_directives'): tmpl.add_directives(Translator.NAMESPACE, translator) - for message in translator.extract(tmpl.stream, gettext_functions=keywords): + for message in translator.extract(tmpl.stream, gettext_functions=keywords, + error_callback=error_callback): yield message diff --git a/genshi/filters/tests/i18n.py b/genshi/filters/tests/i18n.py --- a/genshi/filters/tests/i18n.py +++ b/genshi/filters/tests/i18n.py @@ -1427,6 +1427,38 @@

BarFoo

""", tmpl.generate().render()) + def test_translator_error_callback(self): + + self.test_translator_error_callback_error_called = False + self.test_translator_error_callback_error_msg = '' + + def error_callback(filename, line_number, error_message): + self.test_translator_error_callback_error_called = True + self.test_translator_error_callback_error_msg = ( + "Error '%s' in filename %s line number %d." % ( + error_message, filename, line_number + )) + + tmpl = MarkupTemplate(""" +

+ Please see ${ foo } Help for details. +

+ """) + translator = Translator() + translator.setup(tmpl) + + list(translator.extract(tmpl.stream, error_callback=error_callback)) + + self.assertEqual( + self.test_translator_error_callback_error_msg, + "Error '0 parameters given to 'i18n:msg' but 1 or more expressions " + "used. Stopped Processing File.' in filename (unknown) " + "line number 4.") + self.assertEqual(self.test_translator_error_callback_error_called, True) + del self.test_translator_error_callback_error_called + del self.test_translator_error_callback_error_msg + class ExtractTestCase(unittest.TestCase): def test_markup_template_extraction(self):