6507626273

Committed 13 Oct 2023 11:25AM UTC coverage: 42.006% (-53.7%) from 95.72%

Build # 6507626273

Build Type

Pull #433

github

Committed by

odscjames

Commit Message

New "Geo" optional dependencies

https://github.com/OpenDataServices/flatten-tool/issues/424

Pull Request Pull Request #433: New "Geo" optional dependencies

Run Details

38 of 38 new or added lines in 6 files covered. (100.0%)

1466 of 3490 relevant lines covered (42.01%)

4.16 hits per line

Source File
Press 'n' to go to next uncovered line, 'b' for previous

20.0

/flattentool/sort_xml.py

"""
Sort an XML file according to one or more provided schemas.

Based on https://github.com/OpenDataServices/iati-utils/blob/master/sort_iati.py

Copyright (c) 2013-2014 Ben Webb
Copyright (c) 2016 Open Data Services Co-operative Limited

Permission is hereby granted, free of charge, to any person obtaining a copy of
this software and associated documentation files (the "Software"), to deal in
the Software without restriction, including without limitation the rights to
use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of
the Software, and to permit persons to whom the Software is furnished to do so,
subject to the following conditions:

The above copyright notice and this permission notice shall be included in all
copies or substantial portions of the Software.

THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS
FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR
COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER
IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

"""
from collections import OrderedDict
from warnings import warn

try:
    import lxml.etree as ET

    # Note that lxml is now "required" - it's listed as a requirement in
    # setup.py and is needed for the tests to pass.
    # However, stdlib etree still exists as an unsupported feature.
except ImportError:
    import xml.etree.ElementTree as ET

    warn("Using stdlib etree may work, but is not supported. Please install lxml.")

# Namespaces necessary for opening schema files
namespaces = {"xsd": "http://www.w3.org/2001/XMLSchema"}


class XMLSchemaWalker(object):
    """
    Class for traversing one or more XML schemas.

    Based on the Schema2Doc class in https://github.com/IATI/IATI-Standard-SSOT/blob/version-2.02/gen.py
    """

    def __init__(self, schemas):
        """
        schema -- the filename of the schema to use, e.g.
                  'iati-activities-schema.xsd'
        """
        self.trees = [ET.parse(schema) for schema in schemas]

    def get_schema_element(self, tag_name, name_attribute):
        """
        Return the specified element from the schema.

        tag_name -- the name of the tag in the schema, e.g. 'complexType'
        name_attribute -- the value of the 'name' attribute in the schema, ie.
                          the name of the element/type etc. being described,
                          e.g. iati-activities
        """
        for tree in self.trees:
            schema_element = tree.find(
                "xsd:{0}[@name='{1}']".format(tag_name, name_attribute),
                namespaces=namespaces,
            )
            if schema_element is not None:
                return schema_element
        return schema_element

    def handle_complexType(self, complexType):
        type_elements = []
        if complexType is not None:
            extension = complexType.find(
                "xsd:complexContent/xsd:extension", namespaces=namespaces
            )
            if extension:
                base = extension.attrib.get("base")
                complexType = self.get_schema_element("complexType", base)
                type_elements = self.handle_complexType(complexType)
            else:
                type_elements = []
            type_elements += complexType.findall(
                "xsd:choice/xsd:element", namespaces=namespaces
            ) + complexType.findall("xsd:sequence/xsd:element", namespaces=namespaces)
        return type_elements

    def element_loop(self, element, path):
        """
        Return information about the children of the supplied element.
        """
        a = element.attrib
        type_elements = []
        if "type" in a:
            complexType = self.get_schema_element("complexType", a["type"])
            type_elements += self.handle_complexType(complexType)

        children = (
            element.findall(
                "xsd:complexType/xsd:choice/xsd:element", namespaces=namespaces
            )
            + element.findall(
                "xsd:complexType/xsd:sequence/xsd:element", namespaces=namespaces
            )
            + element.findall(
                "xsd:complexType/xsd:all/xsd:element", namespaces=namespaces
            )
            + type_elements
        )
        child_tuples = []
        for child in children:
            a = child.attrib
            if "name" in a:
                child_tuples.append(
                    (a["name"], child, None, a.get("minOccurs"), a.get("maxOccurs"))
                )
            else:
                child_tuples.append(
                    (a["ref"], None, child, a.get("minOccurs"), a.get("maxOccurs"))
                )
        return child_tuples

    def create_schema_dict(self, parent_name, parent_element=None):
        """
        Create a nested OrderedDict representing the structure (and order!) of
        elements in the provided schema.
        """
        if parent_element is None:
            parent_element = self.get_schema_element("element", parent_name)
        if parent_element is None:
            return {}

        return OrderedDict(
            [
                (name, self.create_schema_dict(name, element))
                for name, element, _, _, _ in self.element_loop(parent_element, "")
            ]
        )


def sort_element(element, schema_subdict):
    """
    Sort the given element's children according to the order of schema_subdict.
    """
    children = list(element)
    for child in children:
        element.remove(child)
    keys = list(schema_subdict.keys())

    def index_key(x):
        if x.tag in keys:
            return keys.index(x.tag)
        else:
            return len(keys) + 1

    for child in sorted(children, key=index_key):
        element.append(child)
        sort_element(child, schema_subdict.get(child.tag, {}))

1	"""
2	Sort an XML file according to one or more provided schemas.
3
4	Based on https://github.com/OpenDataServices/iati-utils/blob/master/sort_iati.py
5
6	Copyright (c) 2013-2014 Ben Webb
7	Copyright (c) 2016 Open Data Services Co-operative Limited
8
9	Permission is hereby granted, free of charge, to any person obtaining a copy of
10	this software and associated documentation files (the "Software"), to deal in
11	the Software without restriction, including without limitation the rights to
12	use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of
13	the Software, and to permit persons to whom the Software is furnished to do so,
14	subject to the following conditions:
15
16	The above copyright notice and this permission notice shall be included in all
17	copies or substantial portions of the Software.
18
19	THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
20	IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS
21	FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR
22	COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER
23	IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
24	CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
25
26	"""
27	from collections import OrderedDict	10✔
28	from warnings import warn	10✔
29
30	try:	10✔
31	import lxml.etree as ET	10✔
32
33	# Note that lxml is now "required" - it's listed as a requirement in
34	# setup.py and is needed for the tests to pass.
35	# However, stdlib etree still exists as an unsupported feature.
36	except ImportError:	×
37	import xml.etree.ElementTree as ET	×
38
39	warn("Using stdlib etree may work, but is not supported. Please install lxml.")	×
40
41	# Namespaces necessary for opening schema files
42	namespaces = {"xsd": "http://www.w3.org/2001/XMLSchema"}	10✔
43
44
45	class XMLSchemaWalker(object):	10✔
46	"""
47	Class for traversing one or more XML schemas.
48
49	Based on the Schema2Doc class in https://github.com/IATI/IATI-Standard-SSOT/blob/version-2.02/gen.py
50	"""
51
52	def __init__(self, schemas):	10✔
53	"""
54	schema -- the filename of the schema to use, e.g.
55	'iati-activities-schema.xsd'
56	"""
57	self.trees = [ET.parse(schema) for schema in schemas]	×
58
59	def get_schema_element(self, tag_name, name_attribute):	10✔
60	"""
61	Return the specified element from the schema.
62
63	tag_name -- the name of the tag in the schema, e.g. 'complexType'
64	name_attribute -- the value of the 'name' attribute in the schema, ie.
65	the name of the element/type etc. being described,
66	e.g. iati-activities
67	"""
68	for tree in self.trees:	×
69	schema_element = tree.find(	×
70	"xsd:{0}[@name='{1}']".format(tag_name, name_attribute),
71	namespaces=namespaces,
72	)
73	if schema_element is not None:	×
74	return schema_element	×
75	return schema_element	×
76
77	def handle_complexType(self, complexType):	10✔
78	type_elements = []	×
79	if complexType is not None:	×
80	extension = complexType.find(	×
81	"xsd:complexContent/xsd:extension", namespaces=namespaces
82	)
83	if extension:	×
84	base = extension.attrib.get("base")	×
85	complexType = self.get_schema_element("complexType", base)	×
86	type_elements = self.handle_complexType(complexType)	×
87	else:
88	type_elements = []	×
89	type_elements += complexType.findall(	×
90	"xsd:choice/xsd:element", namespaces=namespaces
91	) + complexType.findall("xsd:sequence/xsd:element", namespaces=namespaces)
92	return type_elements	×
93
94	def element_loop(self, element, path):	10✔
95	"""
96	Return information about the children of the supplied element.
97	"""
98	a = element.attrib	×
99	type_elements = []	×
100	if "type" in a:	×
101	complexType = self.get_schema_element("complexType", a["type"])	×
102	type_elements += self.handle_complexType(complexType)	×
103
104	children = (	×
105	element.findall(
106	"xsd:complexType/xsd:choice/xsd:element", namespaces=namespaces
107	)
108	+ element.findall(
109	"xsd:complexType/xsd:sequence/xsd:element", namespaces=namespaces
110	)
111	+ element.findall(
112	"xsd:complexType/xsd:all/xsd:element", namespaces=namespaces
113	)
114	+ type_elements
115	)
116	child_tuples = []	×
117	for child in children:	×
118	a = child.attrib	×
119	if "name" in a:	×
120	child_tuples.append(	×
121	(a["name"], child, None, a.get("minOccurs"), a.get("maxOccurs"))
122	)
123	else:
124	child_tuples.append(	×
125	(a["ref"], None, child, a.get("minOccurs"), a.get("maxOccurs"))
126	)
127	return child_tuples	×
128
129	def create_schema_dict(self, parent_name, parent_element=None):	10✔
130	"""
131	Create a nested OrderedDict representing the structure (and order!) of
132	elements in the provided schema.
133	"""
134	if parent_element is None:	×
135	parent_element = self.get_schema_element("element", parent_name)	×
136	if parent_element is None:	×
137	return {}	×
138
139	return OrderedDict(	×
140	[
141	(name, self.create_schema_dict(name, element))
142	for name, element, _, _, _ in self.element_loop(parent_element, "")
143	]
144	)
145
146
147	def sort_element(element, schema_subdict):	10✔
148	"""
149	Sort the given element's children according to the order of schema_subdict.
150	"""
151	children = list(element)	×
152	for child in children:	×
153	element.remove(child)	×
154	keys = list(schema_subdict.keys())	×
155
156	def index_key(x):	×
157	if x.tag in keys:	×
158	return keys.index(x.tag)	×
159	else:
160	return len(keys) + 1	×
161
162	for child in sorted(children, key=index_key):	×
163	element.append(child)	×
164	sort_element(child, schema_subdict.get(child.tag, {}))	×

OpenDataServices / flatten-tool / 6507626273

Source File Press 'n' to go to next uncovered line, 'b' for previous

Source File
Press 'n' to go to next uncovered line, 'b' for previous