def _escape_cdata(text, encoding=None, replace=string.replace):
try:
if encoding:
text = _encode(text, encoding)
text = replace(text, "&", "&")
text = replace(text, "<", "<")
text = replace(text, ">", ">")
return text
except (TypeError, AttributeError):
_raise_serialization_error(text)
def _escape_cdata(text):
try:
if str.startswith(text, "<![CDATA[") and str.endswith(text, "]]>"):
return text
if "&" in text:
text = text.replace("&", "&")
if "<" in text:
text = text.replace("<", "<")
if ">" in text:
text = text.replace(">", ">")
return text
except (TypeError, AttributeError):
_raise_serialization_error(text)
def _escape_attrib(attr_val, encoding=None, replace=string.replace):
# escape attribute value
text = str(attr_val)
try:
if encoding:
text = _encode(text, encoding)
text = replace(text, "&", "&")
#text = replace(text, "'", "'") # FIXME: overkill
text = replace(text, "\"", """)
text = replace(text, "<", "<")
text = replace(text, ">", ">")
return text
except (TypeError, AttributeError):
_raise_serialization_error(text)
def _escape_cdata(text):
# escape character data
try:
# it's worth avoiding do-nothing calls for strings that are
# shorter than 500 character, or so. assume that's, by far,
# the most common case in most applications.
if "&" in text:
text = text.replace("&", "&")
if "<" in text:
text = text.replace("<", "<")
if ">" in text:
text = text.replace(">", ">")
if "'" in text:
text = text.replace("'", "'")
if '"' in text:
text = text.replace('"', """)
return text
except (TypeError, AttributeError):
_raise_serialization_error(text)
def _prettywrite(self, file, node, encoding, namespaces, depth=0):
# write XML to file
tag = node.tag
if tag is Comment:
file.write("\r\n" + " " * depth)
file.write("<!-- %s -->" % _escape_cdata(node.text, encoding))
elif tag is ProcessingInstruction:
file.write("\r\n" + " " * depth)
file.write("<?%s?>" % _escape_cdata(node.text, encoding))
else:
items = node.items()
xmlns_items = [] # new namespaces in this scope
try:
if isinstance(tag, QName) or tag[:1] == "{":
tag, xmlns = myfixtag(tag, namespaces)
if xmlns:
xmlns_items.append(xmlns)
except TypeError:
_raise_serialization_error(tag)
file.write("\r\n" + " " * depth)
file.write("<" + _encode(tag, encoding))
if items or xmlns_items:
items.sort() # lexical order
for k, v in items:
try:
if isinstance(k, QName) or k[:1] == "{":
k, xmlns = myfixtag(k, namespaces)
if xmlns:
xmlns_items.append(xmlns)
except TypeError:
_raise_serialization_error(k)
try:
if isinstance(v, QName):
v, xmlns = myfixtag(v, namespaces)
if xmlns:
xmlns_items.append(xmlns)
except TypeError:
_raise_serialization_error(v)
file.write(" %s=\"%s\"" % (_encode(k, encoding),
_escape_attrib(v, encoding)))
for k, v in xmlns_items:
file.write(" %s=\"%s\"" % (_encode(k, encoding),
_escape_attrib(v, encoding)))
if node.text or len(node):
file.write(">")
if node.text:
file.write(_escape_cdata(node.text, encoding))
for n in node:
self._prettywrite(file, n, encoding, namespaces, depth=depth + 1)
if not node.text or len(node):
file.write("\r\n" + " " * depth)
file.write("</" + _encode(tag, encoding) + ">")
else:
file.write(" />")
for k, v in xmlns_items:
del namespaces[v]
if node.tail:
file.write(_escape_cdata(node.tail, encoding))
def _write(self, file, node, encoding, namespaces):
# write XML to file
tag = node.tag
if tag is Comment:
file.write("\n<!-- %s -->" % _escape_cdata(node.text, encoding))
elif tag is ProcessingInstruction:
file.write("\n<?%s?>" % _escape_cdata(node.text, encoding))
else:
items = node.items()
xmlns_items = [] # new namespaces in this scope
try:
if isinstance(tag, QName) or tag[:1] == "{":
tag, xmlns = fixtag(tag, namespaces)
if xmlns: xmlns_items.append(xmlns)
except TypeError:
_raise_serialization_error(tag)
file.write("\n<" + _encode(tag, encoding))
if items or xmlns_items:
items.sort() # lexical order
for k, v in items:
try:
if isinstance(k, QName) or k[:1] == "{":
k, xmlns = fixtag(k, namespaces)
if xmlns: xmlns_items.append(xmlns)
except TypeError:
_raise_serialization_error(k)
try:
if isinstance(v, QName):
v, xmlns = fixtag(v, namespaces)
if xmlns: xmlns_items.append(xmlns)
except TypeError:
_raise_serialization_error(v)
file.write(
" %s=\"%s\"" %
(_encode(k, encoding), _escape_attrib(v, encoding)))
for k, v in xmlns_items:
file.write(
" %s=\"%s\"" %
(_encode(k, encoding), _escape_attrib(v, encoding)))
if node.text or len(node):
file.write(">")
if node.text:
file.write(_escape_cdata(node.text, encoding))
for n in node:
self._write(file, n, encoding, namespaces)
file.write("</" + _encode(tag, encoding) + ">")
else:
file.write(" />")
for k, v in xmlns_items:
del namespaces[v]
if node.tail:
file.write(_escape_cdata(node.tail, encoding))
def _print_node(self, node, encoding):
tree_string = ""
tag = node.tag
if tag is Comment:
tree_string += "<!-- %s -->" % _escape_cdata(node.text, encoding)
elif tag is ProcessingInstruction:
tree_string += "<?%s?>" % _escape_cdata(node.text, encoding)
else:
items = node.items()
xmlns_items = [] # new namespaces in this scope
try:
if isinstance(tag, QName) or tag[:1] == "{":
tag, xmlns = fixtag(tag, namespaces)
if xmlns: xmlns_items.append(xmlns)
except TypeError:
_raise_serialization_error(tag)
tree_string += "<" + _encode(tag, encoding)
if items or xmlns_items:
items.sort() # lexical order
for k, v in items:
try:
if isinstance(k, QName) or k[:1] == "{":
k, xmlns = fixtag(k, namespaces)
if xmlns: xmlns_items.append(xmlns)
except TypeError:
_raise_serialization_error(k)
try:
if isinstance(v, QName):
v, xmlns = fixtag(v, namespaces)
if xmlns: xmlns_items.append(xmlns)
except TypeError:
_raise_serialization_error(v)
tree_string += " %s=\"%s\"" % (_encode(k, encoding),
_escape_attrib(v, encoding))
for k, v in xmlns_items:
tree_string += " %s=\"%s\"" % (_encode(k, encoding),
_escape_attrib(v, encoding))
tree_string += ">"
if node.text:
tree_string += _escape_cdata(node.text, encoding).replace('"', '"')
for n in node:
tree_string += self._print_node(n, encoding)
tree_string += "</" + _encode(tag, encoding) + ">"
for k, v in xmlns_items:
del namespaces[v]
if node.tail:
tree_string += _escape_cdata(node.tail, encoding)
return tree_string
