10282417405

Committed 07 Aug 2024 10:14AM UTC coverage: 95.709% (+0.01%) from 95.698%

Build # 10282417405

Build Type

push

github

Committed by

web-flow

Commit Message

Merge pull request #452 from OpenDataServices/450-451-custom-warnings-exceptions

Use custom warnings and exceptions

Run Details

27 of 46 new or added lines in 7 files covered. (58.7%)

1 existing line in 1 file now uncovered.

3390 of 3542 relevant lines covered (95.71%)

11.42 hits per line

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

93.44

/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

from flattentool.exceptions import FlattenToolWarning

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.",
        FlattenToolWarning,
    )

# 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	12✔
28	from warnings import warn	12✔
29
30	from flattentool.exceptions import FlattenToolWarning	12✔
31
32	try:	12✔
33	import lxml.etree as ET	12✔
34
35	# Note that lxml is now "required" - it's listed as a requirement in
36	# setup.py and is needed for the tests to pass.
37	# However, stdlib etree still exists as an unsupported feature.
38	except ImportError:	×
39	import xml.etree.ElementTree as ET	×
40
NEW 41	warn(	×
42	"Using stdlib etree may work, but is not supported. Please install lxml.",
43	FlattenToolWarning,
44	)
45
46	# Namespaces necessary for opening schema files
47	namespaces = {"xsd": "http://www.w3.org/2001/XMLSchema"}	12✔
48
49
50	class XMLSchemaWalker(object):	12✔
51	"""
52	Class for traversing one or more XML schemas.
53
54	Based on the Schema2Doc class in https://github.com/IATI/IATI-Standard-SSOT/blob/version-2.02/gen.py
55	"""
56
57	def __init__(self, schemas):	12✔
58	"""
59	schema -- the filename of the schema to use, e.g.
60	'iati-activities-schema.xsd'
61	"""
62	self.trees = [ET.parse(schema) for schema in schemas]	12✔
63
64	def get_schema_element(self, tag_name, name_attribute):	12✔
65	"""
66	Return the specified element from the schema.
67
68	tag_name -- the name of the tag in the schema, e.g. 'complexType'
69	name_attribute -- the value of the 'name' attribute in the schema, ie.
70	the name of the element/type etc. being described,
71	e.g. iati-activities
72	"""
73	for tree in self.trees:	12✔
74	schema_element = tree.find(	12✔
75	"xsd:{0}[@name='{1}']".format(tag_name, name_attribute),
76	namespaces=namespaces,
77	)
78	if schema_element is not None:	12✔
79	return schema_element	12✔
80	return schema_element	12✔
81
82	def handle_complexType(self, complexType):	12✔
83	type_elements = []	12✔
84	if complexType is not None:	12✔
85	extension = complexType.find(	12✔
86	"xsd:complexContent/xsd:extension", namespaces=namespaces
87	)
88	if extension:	12✔
89	base = extension.attrib.get("base")	12✔
90	complexType = self.get_schema_element("complexType", base)	12✔
91	type_elements = self.handle_complexType(complexType)	12✔
92	else:
93	type_elements = []	12✔
94	type_elements += complexType.findall(	12✔
95	"xsd:choice/xsd:element", namespaces=namespaces
96	) + complexType.findall("xsd:sequence/xsd:element", namespaces=namespaces)
97	return type_elements	12✔
98
99	def element_loop(self, element, path):	12✔
100	"""
101	Return information about the children of the supplied element.
102	"""
103	a = element.attrib	12✔
104	type_elements = []	12✔
105	if "type" in a:	12✔
106	complexType = self.get_schema_element("complexType", a["type"])	12✔
107	type_elements += self.handle_complexType(complexType)	12✔
108
109	children = (	12✔
110	element.findall(
111	"xsd:complexType/xsd:choice/xsd:element", namespaces=namespaces
112	)
113	+ element.findall(
114	"xsd:complexType/xsd:sequence/xsd:element", namespaces=namespaces
115	)
116	+ element.findall(
117	"xsd:complexType/xsd:all/xsd:element", namespaces=namespaces
118	)
119	+ type_elements
120	)
121	child_tuples = []	12✔
122	for child in children:	12✔
123	a = child.attrib	12✔
124	if "name" in a:	12✔
125	child_tuples.append(	12✔
126	(a["name"], child, None, a.get("minOccurs"), a.get("maxOccurs"))
127	)
128	else:
129	child_tuples.append(	12✔
130	(a["ref"], None, child, a.get("minOccurs"), a.get("maxOccurs"))
131	)
132	return child_tuples	12✔
133
134	def create_schema_dict(self, parent_name, parent_element=None):	12✔
135	"""
136	Create a nested OrderedDict representing the structure (and order!) of
137	elements in the provided schema.
138	"""
139	if parent_element is None:	12✔
140	parent_element = self.get_schema_element("element", parent_name)	12✔
141	if parent_element is None:	12✔
142	return {}	×
143
144	return OrderedDict(	12✔
145	[
146	(name, self.create_schema_dict(name, element))
147	for name, element, _, _, _ in self.element_loop(parent_element, "")
148	]
149	)
150
151
152	def sort_element(element, schema_subdict):	12✔
153	"""
154	Sort the given element's children according to the order of schema_subdict.
155	"""
156	children = list(element)	12✔
157	for child in children:	12✔
158	element.remove(child)	12✔
159	keys = list(schema_subdict.keys())	12✔
160
161	def index_key(x):	12✔
162	if x.tag in keys:	12✔
163	return keys.index(x.tag)	12✔
164	else:
165	return len(keys) + 1	12✔
166
167	for child in sorted(children, key=index_key):	12✔
168	element.append(child)	12✔
169	sort_element(child, schema_subdict.get(child.tag, {}))	12✔

OpenDataServices / flatten-tool / 10282417405

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