def _make_start_format(tag_uri, tag_name, attributes, encoding):
# We must search for translatable attributes
result = [(u'<%s' % get_qname(tag_uri, tag_name), False, None)]
for attr_uri, attr_name in attributes:
qname = get_attribute_qname(attr_uri, attr_name)
qname = Unicode.decode(qname, encoding=encoding)
value = attributes[(attr_uri, attr_name)]
value = Unicode.decode(value, encoding=encoding)
value = XMLAttribute.encode(value)
datatype = get_attr_datatype(tag_uri, tag_name, attr_uri, attr_name,
attributes)
if issubclass(datatype, Unicode):
result[-1] = (result[-1][0] + u' %s="' % qname, False, None)
context = _get_attr_context(datatype, tag_name, attr_name)
result.append((value, True, context))
result.append((u'"', False, None))
else:
result[-1] = (result[-1][0] + u' %s="%s"' % (qname, value), False, None)
# Close the start tag
if is_empty(tag_uri, tag_name):
result[-1] = (result[-1][0] + u'/>', False, None)
else:
result[-1] = (result[-1][0] + u'>', False, None)
return result
def normalize(data):
"""
Normalize data
http://www.w3.org/TR/html401/struct/text.html#h-9.1
collapse input white space sequences when producing output inter-word
space.
"""
# decode the data
data = Unicode.decode(data, encoding)
return ' '.join(data.split())
def normalize(data):
"""
Normalize data
http://www.w3.org/TR/html401/struct/text.html#h-9.1
collapse input white space sequences when producing output inter-word
space.
"""
# decode the data
data = Unicode.decode(data, encoding)
return ' '.join(data.split())
def decode(cls, data):
# Neither upper() nor lower() to preserve enumerates
value = Unicode.decode(data.strip())
# Allow single "=" as equals
value = single_eq.sub(ur"==", value)
value = (value
# Alternative to name variables
.replace(u'#', u'')
# Non-break spaces
.replace(u'\u00a0', u'')
# F*****g replacement
.replace(u'«', u'"').replace(u'»', u'"'))
return value
def join_content(data):
data = ''.join(data)
data = Unicode.decode(data, encoding)
return data
def test_Unicode(self):
x = u'العربيه 中文 Español Français'
data = Unicode.encode(x)
self.assertEqual(x, Unicode.decode(data))
def decode(cls, data):
value = Unicode.decode(data)
return {
#'name': checkid(value) or '',
'name': value,
'value': value}
def to_text(self):
result = {}
site_root = self.get_site_root()
languages = site_root.get_property('website_languages')
product_model = self.get_product_model()
schema = {}
if product_model:
schema = product_model.get_model_schema()
purchase_options_schema = self.get_purchase_options_schema()
declinations = list(self.search_resources(cls=Declination))
for language in languages:
texts = result.setdefault(language, [])
for key in ('title', 'description'):
value = self.get_property(key, language=language)
if value:
texts.append(value)
# Parent category
current_category = self.parent
while current_category.class_id == 'category':
texts.append(current_category.get_title(language=language))
current_category = current_category.parent
# data (html)
events = self.get_property('data', language=language)
if events:
text = [ unicode(value, 'utf-8') for event, value, line in events
if event == TEXT ]
if text:
texts.append(u' '.join(text))
# Dynamic properties
for key, datatype in schema.iteritems():
value = self.get_property(key)
if value:
text = None
multiple = datatype.multiple
if issubclass(datatype, Unicode):
if multiple:
text = ' '.join([ x for x in value ])
else:
text = value
elif issubclass(datatype, String):
if multiple:
text = ' '.join([ Unicode.decode(x)
for x in value ])
else:
text = Unicode.decode(value)
elif issubclass(datatype, Enumerate):
values = value
if multiple is False:
values = [value]
# XXX use multilingual label
text = ' '.join(values)
if text:
texts.append(text)
# Manufacturer
manufacturer = self.get_property('manufacturer')
if manufacturer:
manufacturer = site_root.get_resource(manufacturer)
texts.append(manufacturer.get_title())
# Purchase options
for declination in declinations:
for key, datatype in purchase_options_schema.iteritems():
name = declination.get_property(key)
value = datatype.to_text(name, languages)
if value:
texts.append(value)
# Join
for language, texts in result.iteritems():
result[language] = u'\n'.join(texts)
return result
def join_content(data):
data = ''.join(data)
data = Unicode.decode(data, encoding)
return data
def to_text(self):
result = {}
site_root = self.get_site_root()
languages = site_root.get_property('website_languages')
product_model = self.get_product_model()
schema = {}
if product_model:
schema = product_model.get_model_schema()
purchase_options_schema = self.get_purchase_options_schema()
declinations = list(self.search_resources(cls=Declination))
for language in languages:
texts = result.setdefault(language, [])
for key in ('title', 'description'):
value = self.get_property(key, language=language)
if value:
texts.append(value)
# Parent category
current_category = self.parent
while current_category.class_id == 'category':
texts.append(current_category.get_title(language=language))
current_category = current_category.parent
# data (html)
events = self.get_property('data', language=language)
if events:
text = [
unicode(value, 'utf-8') for event, value, line in events
if event == TEXT
]
if text:
texts.append(u' '.join(text))
# Dynamic properties
for key, datatype in schema.iteritems():
value = self.get_property(key)
if value:
text = None
multiple = datatype.multiple
if issubclass(datatype, Unicode):
if multiple:
text = ' '.join([x for x in value])
else:
text = value
elif issubclass(datatype, String):
if multiple:
text = ' '.join([Unicode.decode(x) for x in value])
else:
text = Unicode.decode(value)
elif issubclass(datatype, Enumerate):
values = value
if multiple is False:
values = [value]
# XXX use multilingual label
text = ' '.join(values)
if text:
texts.append(text)
# Manufacturer
manufacturer = self.get_property('manufacturer')
if manufacturer:
manufacturer = site_root.get_resource(manufacturer)
texts.append(manufacturer.get_title())
# Purchase options
for declination in declinations:
for key, datatype in purchase_options_schema.iteritems():
name = declination.get_property(key)
value = datatype.to_text(name, languages)
if value:
texts.append(value)
# Join
for language, texts in result.iteritems():
result[language] = u'\n'.join(texts)
return result