def test_attribute_name(self):
attribute_xpath = XPath('./element/@attri')
absolute_attribute_xpath = XPath('/ns:root/nss:element/@nss:attribute')
element_xpath = XPath('/root/element/subelement')
with self.subTest():
self.assertEqual(attribute_xpath.attribute_name(), 'attri')
with self.subTest():
self.assertEqual(absolute_attribute_xpath.attribute_name(), 'nss:attribute')
with self.subTest():
with self.assertRaises(ValueError):
element_xpath.attribute_name()
def test_node_xpaths(self):
root = etree.fromstring(sample_no_namespace)
xml_tree = etree.ElementTree(root)
xpath_set = {XPath('/catalog/book[1]'),
XPath('/catalog/book[1]/@id'), XPath('/catalog/book[1]/author'), XPath('/catalog/book[1]/title'), XPath('/catalog/book[1]/genre'),
XPath('/catalog/book[1]/price'), XPath('/catalog/book[1]/publish_date'), XPath('/catalog/book[1]/description'),
XPath('/catalog/book[2]'),
XPath('/catalog/book[2]/@id'), XPath('/catalog/book[2]/author'), XPath('/catalog/book[2]/title'), XPath('/catalog/book[2]/genre'),
XPath('/catalog/book[2]/price'), XPath('/catalog/book[2]/publish_date'), XPath('/catalog/book[2]/description')}
with self.subTest():
self.assertCountEqual(xpath_set, generate_node_xpaths(xml_tree))
with self.subTest():
self.assertSetEqual(xpath_set, set(generate_node_xpaths(xml_tree)))
def test_is_attribute(self):
attribute_node = XPath('/root/element/@attribute')
ns_attribute_node = XPath('/ns:root/nss:element/@nss:attribute')
element_node = XPath('root/element')
with self.subTest():
self.assertTrue(attribute_node.is_attribute())
with self.subTest():
self.assertTrue(ns_attribute_node.is_attribute())
with self.subTest():
self.assertFalse(element_node.is_attribute())
def test_parent(self):
absolute_attribute_xpath = XPath('/ns:root/nss:element/@nss:attribute')
relative_element_xpath = XPath('./element/subelement')
with self.subTest():
self.assertEqual(absolute_attribute_xpath.parent(), XPath('/ns:root/nss:element'))
with self.subTest():
self.assertEqual(relative_element_xpath.parent(), XPath('./element'))
def test_change_attribute_tag(self):
with self.subTest():
xpath = XPath('/adrmsg:ADRMessage/adrmsg:hasMember/aixm:Route/@gml:id')
reference = JSONPath('$.ADRMessage.hasMember.Route._id')
self.assertEqual(reference, xpath.to_json_path(attributes='_', with_namespaces=False))
with self.subTest():
xpath = XPath('/adrmsg:ADRMessage/adrmsg:hasMember/aixm:Route/@gml:id')
reference = JSONPath('$.ADRMessage.hasMember.Route.id')
self.assertEqual(reference, xpath.to_json_path(attributes='', with_namespaces=False))
with self.subTest():
xpath = XPath('/adrmsg:ADRMessage/adrmsg:hasMember/aixm:Route/@gml:id')
reference = JSONPath('$.adrmsg:ADRMessage.adrmsg:hasMember.aixm:Route.attrib_gml:id')
self.assertEqual(reference, xpath.to_json_path(attributes='attrib_', with_namespaces=True))
def test_is_relative(self):
absolute_xpath = XPath('/root/element/subelement')
relative_xpath = XPath('./element/@attribute')
with self.subTest():
self.assertFalse(absolute_xpath.is_relative())
with self.subTest():
self.assertTrue(relative_xpath.is_relative())
def test_sequence_path(self):
with self.subTest():
xpath = XPath("/adrmsg:ADRMessage/adrmsg:hasMember[1]/aixm:Route/@gml:id")
reference = JSONPath("$.adrmsg:ADRMessage.adrmsg:hasMember[0].aixm:Route._gml:id")
self.assertEqual(reference, xpath.to_json_path(attributes="_", with_namespaces=True))
with self.subTest():
xpath = XPath("/adrmsg:ADRMessage/adrmsg:hasMember[1]/aixm:Route/@gml:id")
reference = JSONPath("$.ADRMessage.hasMember[0].Route.id")
self.assertEqual(reference, xpath.to_json_path(attributes="", with_namespaces=False))
with self.subTest():
xpath = XPath("/adrmsg:ADRMessage/adrmsg:hasMember[-1]/aixm:Route/@gml:id")
reference = JSONPath("$.ADRMessage.hasMember[-1].Route.id")
self.assertRaises(ValueError)
def test_index_removal(self):
xpath = XPath('/root/element[10]/subelement/subsubelement[1]/@attribute')
reference = XPath('/root/element/subelement/subsubelement/@attribute')
with self.subTest():
self.assertEqual(xpath.remove_indices(in_place=False), reference)
with self.subTest():
xpath.remove_indices(in_place=True)
self.assertEqual(xpath, reference)
def test_namespace_substitution(self):
xpath = XPath('/adrmsg:ADRMessage/adrmsg:hasMember[1]/aixm:Route/@{http://www.opengis.net/gml/3.2}id')
short_xpath = XPath('/adrmsg:ADRMessage/adrmsg:hasMember[1]/aixm:Route/@gml:id')
with self.subTest():
self.assertEqual(short_xpath, xpath.shorten_namespaces(self.namespaces, in_place=False))
with self.subTest():
xpath.shorten_namespaces(self.namespaces, in_place=True)
self.assertEqual(short_xpath, xpath)
def infer_path_type(path: str) -> Union[XPath, JSONPath]:
"""
Infers the type of a path (XPath or JSONPath) based on its syntax.
It performs some basic sanity checks to differentiate a JSONPath from an XPath.
:param path: A valid XPath or JSONPath string.
:return: An instance of JSONPath or XPath
"""
if not path:
raise ValueError("No path given")
if path[0] in ['$', '@']:
return JSONPath(path)
else:
if path[0] in ['.', '/']:
return XPath(path)
else:
raise ValueError("Couldn't identify the path type for {}".format(path))
def iter_map_xml_document_to_dict(xml_document: Path,
xml_namespaces: Dict = None,
json: Optional[Dict] = None,
ignore_empty: bool = True) -> Iterator[Union[Dict, List]]:
"""
Generator that iteratively maps each node encountered in the input xml_document.
It will infer the output type for each node.
:param xml_document: A Path to the XML document that is to be converted.
:param xml_namespaces: A dictionary defining the XML namespaces with namespace shortname as keys
and the full namespace name as values. Follows the xml standard library
convention for XML namespaces.
:param json: An input dictionary into which the XML document is to be mapped.
Defaults to an empty dictionary if none given.
:param ignore_empty: A boolean indicating if missing XML Nodes should be ignored.
:return: Yields a json serializable dictionary or list
"""
json = json or {}
xml_etree = xml_parse(str(xml_document)) # type: ElementTree
root = xml_etree.getroot()
root_xpath = XPath(xml_etree.getpath(root))
all_elements = xml_etree.iterfind('//*') # type: Iterable[ElementTree]
for element in all_elements:
ns_map = element.nsmap
element_path = xml_etree.getpath(element)
element_xpath = XPath(element_path)
element_xpath.shorten_namespaces(ns_map, in_place=True).relative_to(root_xpath, in_place=True)
attrib_paths = (XPath(f'{element_path}/@{attrib_name}') for attrib_name, _ in element.attrib.items())
for attrib in attrib_paths:
attrib.shorten_namespaces(ns_map, in_place=True)
attrib.relative_to(root_xpath, in_place=True)
yield attrib
for node in generate_nodes(xml_etree, xml_namespaces):
jsonize_mapping = node.to_jsonize(attributes='_')
node_map: XMLNodeToJSONNode = parse_node_map(jsonize_mapping, transformations=[])
node_map.map(xml_etree, json, xml_namespaces=xml_namespaces, ignore_empty=ignore_empty)
yield json
def test_ignore_namespaces(self):
xpath = XPath('/adrmsg:ADRMessage/adrmsg:hasMember/aixm:Route/@gml:id')
reference = JSONPath('$.ADRMessage.hasMember.Route.@id')
self.assertEqual(reference, xpath.to_json_path(attributes='@', with_namespaces=False))
def test_relative_path(self):
xpath = XPath('./adrmsg:ADRMessage/adrmsg:hasMember/aixm:Route/@gml:id')
reference = JSONPath('@.adrmsg:ADRMessage.adrmsg:hasMember.aixm:Route.@gml:id')
self.assertEqual(reference, xpath.to_json_path(attributes='@', with_namespaces=True))
def test_make_relative_path(self):
with self.subTest():
xpath = XPath('/root/element[10]/subelement/subsubelement[1]/@attribute')
parent = XPath('/root/element[10]')
reference = XPath('./subelement/subsubelement[1]/@attribute')
with self.subTest():
self.assertEqual(xpath.relative_to(parent, in_place=False), reference)
with self.subTest():
xpath.relative_to(parent, in_place=True)
self.assertEqual(xpath, reference)
with self.subTest():
xpath = XPath('/root/element[10]/subelement/subsubelement[1]')
parent = xpath
reference = XPath('.')
with self.subTest():
self.assertEqual(xpath.relative_to(parent, in_place=False), reference)
with self.subTest():
xpath.relative_to(parent, in_place=True)
self.assertEqual(xpath, reference)
def test_split(self):
absolute_attribute_xpath = XPath('/ns:root/nss:element/@nss:attribute')
relative_element_xpath = XPath('./element/subelement')
with self.subTest():
# TODO: Evaluate if the numbering convention is appropriate
self.assertEqual(absolute_attribute_xpath.split(1), (XPath(''), XPath('./ns:root/nss:element/@nss:attribute')))
self.assertEqual(absolute_attribute_xpath.split(2), (XPath('/ns:root'), XPath('./nss:element/@nss:attribute')))
with self.subTest():
self.assertEqual(relative_element_xpath.split(1), (XPath('.'), XPath('./element/subelement')))
self.assertEqual(relative_element_xpath.split(2), (XPath('./element'), XPath('./subelement')))
with self.subTest():
with self.assertRaises(ValueError):
relative_element_xpath.split(-1)
def test_descendance(self):
with self.subTest():
ancestor = XPath('/root/element')
descendant = XPath('/root/element/subelement/leaf/@attribute')
self.assertTrue(descendant.is_descendant_of(ancestor))
with self.subTest():
ancestor = XPath('/root/element')
not_descendant = XPath('/root/otherElement/subelement/leaf')
self.assertFalse(not_descendant.is_descendant_of(ancestor))
with self.subTest():
ancestor = XPath('/root/element')
not_descendant = XPath('/root/elemental')
self.assertFalse(not_descendant.is_descendant_of(ancestor))