def start(self, name, attrs, nsmap={}):
# Make sure attrs is a mutable dict--lxml may send an immutable dictproxy.
attrs = dict(attrs)
nsprefix = None
# Fix bug in bs4 _lxml.py that ignores attributes that specify namespaces on this tag
# Invert each namespace map as it comes in.
if len(nsmap) > 0:
# to make later processing easier, remap epub namespaces to use
# epub standard prefixes
new_nsmap = {}
for pfx, ns in list(nsmap.items()):
new_pfx = _standard_epub_prefix_map.get(ns, pfx)
if new_pfx is not None and new_pfx == "opf" and pfx is None:
new_pfx = None
new_nsmap[new_pfx] = ns
nsmap = new_nsmap
# A new namespace mapping has come into play.
inverted_nsmap = dict(
(value, key) for key, value in list(nsmap.items()))
self.nsmaps.append(inverted_nsmap)
# Also treat the namespace mapping as a set of attributes on the
# tag, so we can properly recreate it later.
attrs = attrs.copy()
for prefix, namespace in list(nsmap.items()):
attribute = NamespacedAttribute(
"xmlns", prefix, "http://www.w3.org/2000/xmlns/")
attrs[attribute] = namespace
elif len(self.nsmaps) > 1:
# There are no new namespaces for this tag, but
# non-default namespaces are in play, so we need a
# separate tag stack to know when they end.
self.nsmaps.append(None)
# Namespaces are in play. Find any attributes that came in
# from lxml with namespaces attached to their names, and
# turn then into NamespacedAttribute objects.
new_attrs = {}
for attr, value in list(attrs.items()):
namespace, attr = self._getNsTag(attr)
if namespace is None:
new_attrs[attr] = value
else:
nsprefix = self._prefix_for_attr_namespace(namespace)
attr = NamespacedAttribute(nsprefix, attr, namespace)
new_attrs[attr] = value
attrs = new_attrs
namespace, name = self._getNsTag(name)
nsprefix = self._prefix_for_tag_namespace(namespace)
self.soup.handle_starttag(name, namespace, nsprefix, attrs)
def setAttributes(self, attributes):
if attributes is not None and len(attributes) > 0:
converted_attributes = []
for name, value in list(attributes.items()):
if isinstance(name, tuple):
new_name = NamespacedAttribute(*name)
del attributes[name]
attributes[new_name] = value
self.soup.builder._replace_cdata_list_attribute_values(
self.name, attributes)
for name, value in list(attributes.items()):
self.element[name] = value
# The attributes may contain variables that need substitution.
# Call set_up_substitutions manually.
#
# The Tag constructor called this method when the Tag was created,
# but we just set/changed the attributes, so call it again.
self.soup.builder.set_up_substitutions(self.element)