def extract(self,
stream,
gettext_functions=GETTEXT_FUNCTIONS,
search_text=True,
msgbuf=None):
"""Extract localizable strings from the given template stream.
For every string found, this function yields a ``(lineno, function,
message)`` 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
* ``message`` is the string itself (a ``unicode`` object, or a tuple
of ``unicode`` objects for functions with multiple string arguments).
>>> from genshi.template import MarkupTemplate
>>>
>>> tmpl = MarkupTemplate('''<html xmlns:py="http://genshi.edgewall.org/">
... <head>
... <title>Example</title>
... </head>
... <body>
... <h1>Example</h1>
... <p>${_("Hello, %(name)s") % dict(name=username)}</p>
... <p>${ngettext("You have %d item", "You have %d items", num)}</p>
... </body>
... </html>''', filename='example.html')
>>>
>>> for lineno, funcname, message in Translator().extract(tmpl.stream):
... print "%d, %r, %r" % (lineno, funcname, message)
3, None, u'Example'
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
treated as gettext-style localization
functions
:param search_text: whether the content of text nodes should be
extracted (used internally)
: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.
"""
if not self.extract_text:
search_text = False
skip = 0
i18n_msg = I18N_NAMESPACE['msg']
xml_lang = XML_NAMESPACE['lang']
for kind, data, pos in stream:
if skip:
if kind is START:
skip += 1
if kind is END:
skip -= 1
if kind is START and not skip:
tag, attrs = data
if tag in self.ignore_tags or \
isinstance(attrs.get(xml_lang), basestring):
skip += 1
continue
for name, value in attrs:
if search_text and isinstance(value, basestring):
if name in self.include_attrs:
text = value.strip()
if text:
yield pos[1], None, text
else:
for lineno, funcname, text in self.extract(
_ensure(value),
gettext_functions,
search_text=False):
yield lineno, funcname, text
if msgbuf:
msgbuf.append(kind, data, pos)
elif i18n_msg in attrs:
params = attrs.get(i18n_msg)
if params and type(params) is list: # event tuple
params = params[0][1]
msgbuf = MessageBuffer(params, pos[1])
elif not skip and search_text and kind is TEXT:
if not msgbuf:
text = data.strip()
if text and filter(None, [ch.isalpha() for ch in text]):
yield pos[1], None, text
else:
msgbuf.append(kind, data, pos)
elif not skip and msgbuf and kind is END:
msgbuf.append(kind, data, pos)
if not msgbuf.depth:
yield msgbuf.lineno, None, msgbuf.format()
msgbuf = None
elif kind is EXPR or kind is EXEC:
if msgbuf:
msgbuf.append(kind, data, pos)
for funcname, strings in extract_from_code(
data, gettext_functions):
yield pos[1], funcname, strings
elif kind is SUB:
subkind, substream = data
messages = self.extract(substream,
gettext_functions,
search_text=search_text and not skip,
msgbuf=msgbuf)
for lineno, funcname, text in messages:
yield lineno, funcname, text
def __call__(self, stream, ctxt=None, search_text=True, msgbuf=None):
"""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
internally)
:param msgbuf: a `MessageBuffer` object or `None` (used internally)
:return: the localized stream
"""
ignore_tags = self.ignore_tags
include_attrs = self.include_attrs
translate = self.translate
if not self.extract_text:
search_text = False
skip = 0
i18n_msg = I18N_NAMESPACE['msg']
ns_prefixes = []
xml_lang = XML_NAMESPACE['lang']
for kind, data, pos in stream:
# skip chunks that should not be localized
if skip:
if kind is START:
skip += 1
elif kind is END:
skip -= 1
yield kind, data, pos
continue
# handle different events that can be localized
if kind is START:
tag, attrs = data
if tag in self.ignore_tags or \
isinstance(attrs.get(xml_lang), basestring):
skip += 1
yield kind, data, pos
continue
new_attrs = []
changed = False
for name, value in attrs:
newval = value
if search_text and isinstance(value, basestring):
if name in include_attrs:
newval = self.translate(value)
else:
newval = list(
self(_ensure(value),
ctxt,
search_text=False,
msgbuf=msgbuf))
if newval != value:
value = newval
changed = True
new_attrs.append((name, value))
if changed:
attrs = Attrs(new_attrs)
if msgbuf:
msgbuf.append(kind, data, pos)
continue
elif i18n_msg in attrs:
params = attrs.get(i18n_msg)
if params and type(params) is list: # event tuple
params = params[0][1]
msgbuf = MessageBuffer(params)
attrs -= i18n_msg
yield kind, (tag, attrs), pos
elif search_text and kind is TEXT:
if not msgbuf:
text = data.strip()
if text:
data = data.replace(text, unicode(translate(text)))
yield kind, data, pos
else:
msgbuf.append(kind, data, pos)
elif msgbuf and kind is EXPR:
msgbuf.append(kind, data, pos)
elif not skip and msgbuf and kind is END:
msgbuf.append(kind, data, pos)
if not msgbuf.depth:
for event in msgbuf.translate(translate(msgbuf.format())):
yield event
msgbuf = None
yield kind, data, pos
elif kind is SUB:
subkind, substream = data
new_substream = list(self(substream, ctxt, msgbuf=msgbuf))
yield kind, (subkind, new_substream), pos
elif kind is START_NS and data[1] == I18N_NAMESPACE:
ns_prefixes.append(data[0])
elif kind is END_NS and data in ns_prefixes:
ns_prefixes.remove(data)
else:
yield kind, data, pos
def __call__(self, stream, ctxt=None, search_text=True, msgbuf=None):
"""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
internally)
:param msgbuf: a `MessageBuffer` object or `None` (used internally)
:return: the localized stream
"""
ignore_tags = self.ignore_tags
include_attrs = self.include_attrs
translate = self.translate
if not self.extract_text:
search_text = False
skip = 0
i18n_msg = I18N_NAMESPACE['msg']
ns_prefixes = []
xml_lang = XML_NAMESPACE['lang']
for kind, data, pos in stream:
# skip chunks that should not be localized
if skip:
if kind is START:
skip += 1
elif kind is END:
skip -= 1
yield kind, data, pos
continue
# handle different events that can be localized
if kind is START:
tag, attrs = data
if tag in self.ignore_tags or \
isinstance(attrs.get(xml_lang), basestring):
skip += 1
yield kind, data, pos
continue
new_attrs = []
changed = False
for name, value in attrs:
newval = value
if search_text and isinstance(value, basestring):
if name in include_attrs:
newval = self.translate(value)
else:
newval = list(self(_ensure(value), ctxt,
search_text=False, msgbuf=msgbuf)
)
if newval != value:
value = newval
changed = True
new_attrs.append((name, value))
if changed:
attrs = Attrs(new_attrs)
if msgbuf:
msgbuf.append(kind, data, pos)
continue
elif i18n_msg in attrs:
params = attrs.get(i18n_msg)
if params and type(params) is list: # event tuple
params = params[0][1]
msgbuf = MessageBuffer(params)
attrs -= i18n_msg
yield kind, (tag, attrs), pos
elif search_text and kind is TEXT:
if not msgbuf:
text = data.strip()
if text:
data = data.replace(text, unicode(translate(text)))
yield kind, data, pos
else:
msgbuf.append(kind, data, pos)
elif msgbuf and kind is EXPR:
msgbuf.append(kind, data, pos)
elif not skip and msgbuf and kind is END:
msgbuf.append(kind, data, pos)
if not msgbuf.depth:
for event in msgbuf.translate(translate(msgbuf.format())):
yield event
msgbuf = None
yield kind, data, pos
elif kind is SUB:
subkind, substream = data
new_substream = list(self(substream, ctxt, msgbuf=msgbuf))
yield kind, (subkind, new_substream), pos
elif kind is START_NS and data[1] == I18N_NAMESPACE:
ns_prefixes.append(data[0])
elif kind is END_NS and data in ns_prefixes:
ns_prefixes.remove(data)
else:
yield kind, data, pos
def extract(self, stream, gettext_functions=GETTEXT_FUNCTIONS,
search_text=True, msgbuf=None):
"""Extract localizable strings from the given template stream.
For every string found, this function yields a ``(lineno, function,
message)`` 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
* ``message`` is the string itself (a ``unicode`` object, or a tuple
of ``unicode`` objects for functions with multiple string arguments).
>>> from genshi.template import MarkupTemplate
>>>
>>> tmpl = MarkupTemplate('''<html xmlns:py="http://genshi.edgewall.org/">
... <head>
... <title>Example</title>
... </head>
... <body>
... <h1>Example</h1>
... <p>${_("Hello, %(name)s") % dict(name=username)}</p>
... <p>${ngettext("You have %d item", "You have %d items", num)}</p>
... </body>
... </html>''', filename='example.html')
>>>
>>> for lineno, funcname, message in Translator().extract(tmpl.stream):
... print "%d, %r, %r" % (lineno, funcname, message)
3, None, u'Example'
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
treated as gettext-style localization
functions
:param search_text: whether the content of text nodes should be
extracted (used internally)
: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.
"""
if not self.extract_text:
search_text = False
skip = 0
i18n_msg = I18N_NAMESPACE['msg']
xml_lang = XML_NAMESPACE['lang']
for kind, data, pos in stream:
if skip:
if kind is START:
skip += 1
if kind is END:
skip -= 1
if kind is START and not skip:
tag, attrs = data
if tag in self.ignore_tags or \
isinstance(attrs.get(xml_lang), basestring):
skip += 1
continue
for name, value in attrs:
if search_text and isinstance(value, basestring):
if name in self.include_attrs:
text = value.strip()
if text:
yield pos[1], None, text
else:
for lineno, funcname, text in self.extract(
_ensure(value), gettext_functions,
search_text=False):
yield lineno, funcname, text
if msgbuf:
msgbuf.append(kind, data, pos)
elif i18n_msg in attrs:
params = attrs.get(i18n_msg)
if params and type(params) is list: # event tuple
params = params[0][1]
msgbuf = MessageBuffer(params, pos[1])
elif not skip and search_text and kind is TEXT:
if not msgbuf:
text = data.strip()
if text and filter(None, [ch.isalpha() for ch in text]):
yield pos[1], None, text
else:
msgbuf.append(kind, data, pos)
elif not skip and msgbuf and kind is END:
msgbuf.append(kind, data, pos)
if not msgbuf.depth:
yield msgbuf.lineno, None, msgbuf.format()
msgbuf = None
elif kind is EXPR or kind is EXEC:
if msgbuf:
msgbuf.append(kind, data, pos)
for funcname, strings in extract_from_code(data,
gettext_functions):
yield pos[1], funcname, strings
elif kind is SUB:
subkind, substream = data
messages = self.extract(substream, gettext_functions,
search_text=search_text and not skip,
msgbuf=msgbuf)
for lineno, funcname, text in messages:
yield lineno, funcname, text
def _inject(self):
content = self.content
if callable(content):
content = content()
for event in _ensure(content):
yield None, event
