# xml.etree test. This file contains enough tests to make sure that
# all included components work as they should.
# Large parts are extracted from the upstream test suite.
# IMPORTANT: the same doctests are run from "test_xml_etree_c" in
# order to ensure consistency between the C implementation and the
# Python implementation.
#
# For this purpose, the module-level "ET" symbol is temporarily
# monkey-patched when running the "test_xml_etree_c" test suite.
# Don't re-import "xml.etree.ElementTree" module in the docstring,
# except if the test is specific to the Python implementation.
import sys
import html
import unittest
from test import support
from test.support import findfile
from xml.etree import ElementTree as ET
SIMPLE_XMLFILE = findfile("simple.xml", subdir="xmltestdata")
try:
SIMPLE_XMLFILE.encode("utf8")
except UnicodeEncodeError:
raise unittest.SkipTest("filename is not encodable to utf8")
SIMPLE_NS_XMLFILE = findfile("simple-ns.xml", subdir="xmltestdata")
SAMPLE_XML = """\
textsubtext
"""
SAMPLE_SECTION = """\
subtext
"""
SAMPLE_XML_NS = """
textsubtext
"""
def sanity():
"""
Import sanity.
>>> from xml.etree import ElementTree
>>> from xml.etree import ElementInclude
>>> from xml.etree import ElementPath
"""
def check_method(method):
if not hasattr(method, '__call__'):
print(method, "not callable")
def serialize(elem, to_string=True, encoding='unicode', **options):
import io
if encoding != 'unicode':
file = io.BytesIO()
else:
file = io.StringIO()
tree = ET.ElementTree(elem)
tree.write(file, encoding=encoding, **options)
if to_string:
return file.getvalue()
else:
file.seek(0)
return file
def summarize(elem):
if elem.tag == ET.Comment:
return ""
return elem.tag
def summarize_list(seq):
return [summarize(elem) for elem in seq]
def normalize_crlf(tree):
for elem in tree.iter():
if elem.text:
elem.text = elem.text.replace("\r\n", "\n")
if elem.tail:
elem.tail = elem.tail.replace("\r\n", "\n")
def normalize_exception(func, *args, **kwargs):
# Ignore the exception __module__
try:
func(*args, **kwargs)
except Exception as err:
print("Traceback (most recent call last):")
print("{}: {}".format(err.__class__.__name__, err))
def check_string(string):
len(string)
for char in string:
if len(char) != 1:
print("expected one-character string, got %r" % char)
new_string = string + ""
new_string = string + " "
string[:0]
def check_mapping(mapping):
len(mapping)
keys = mapping.keys()
items = mapping.items()
for key in keys:
item = mapping[key]
mapping["key"] = "value"
if mapping["key"] != "value":
print("expected value string, got %r" % mapping["key"])
def check_element(element):
if not ET.iselement(element):
print("not an element")
if not hasattr(element, "tag"):
print("no tag member")
if not hasattr(element, "attrib"):
print("no attrib member")
if not hasattr(element, "text"):
print("no text member")
if not hasattr(element, "tail"):
print("no tail member")
check_string(element.tag)
check_mapping(element.attrib)
if element.text is not None:
check_string(element.text)
if element.tail is not None:
check_string(element.tail)
for elem in element:
check_element(elem)
# --------------------------------------------------------------------
# element tree tests
def interface():
"""
Test element tree interface.
>>> element = ET.Element("tag")
>>> check_element(element)
>>> tree = ET.ElementTree(element)
>>> check_element(tree.getroot())
>>> element = ET.Element("t\\xe4g", key="value")
>>> tree = ET.ElementTree(element)
>>> repr(element) # doctest: +ELLIPSIS
""
>>> element = ET.Element("tag", key="value")
Make sure all standard element methods exist.
>>> check_method(element.append)
>>> check_method(element.extend)
>>> check_method(element.insert)
>>> check_method(element.remove)
>>> check_method(element.getchildren)
>>> check_method(element.find)
>>> check_method(element.iterfind)
>>> check_method(element.findall)
>>> check_method(element.findtext)
>>> check_method(element.clear)
>>> check_method(element.get)
>>> check_method(element.set)
>>> check_method(element.keys)
>>> check_method(element.items)
>>> check_method(element.iter)
>>> check_method(element.itertext)
>>> check_method(element.getiterator)
These methods return an iterable. See bug 6472.
>>> check_method(element.iter("tag").__next__)
>>> check_method(element.iterfind("tag").__next__)
>>> check_method(element.iterfind("*").__next__)
>>> check_method(tree.iter("tag").__next__)
>>> check_method(tree.iterfind("tag").__next__)
>>> check_method(tree.iterfind("*").__next__)
These aliases are provided:
>>> assert ET.XML == ET.fromstring
>>> assert ET.PI == ET.ProcessingInstruction
>>> assert ET.XMLParser == ET.XMLTreeBuilder
"""
def simpleops():
"""
Basic method sanity checks.
>>> elem = ET.XML("")
>>> serialize(elem)
''
>>> e = ET.Element("tag2")
>>> elem.append(e)
>>> serialize(elem)
''
>>> elem.remove(e)
>>> serialize(elem)
''
>>> elem.insert(0, e)
>>> serialize(elem)
''
>>> elem.remove(e)
>>> elem.extend([e])
>>> serialize(elem)
''
>>> elem.remove(e)
>>> element = ET.Element("tag", key="value")
>>> serialize(element) # 1
''
>>> subelement = ET.Element("subtag")
>>> element.append(subelement)
>>> serialize(element) # 2
''
>>> element.insert(0, subelement)
>>> serialize(element) # 3
''
>>> element.remove(subelement)
>>> serialize(element) # 4
''
>>> element.remove(subelement)
>>> serialize(element) # 5
''
>>> element.remove(subelement)
Traceback (most recent call last):
ValueError: list.remove(x): x not in list
>>> serialize(element) # 6
''
>>> element[0:0] = [subelement, subelement, subelement]
>>> serialize(element[1])
''
>>> element[1:9] == [element[1], element[2]]
True
>>> element[:9:2] == [element[0], element[2]]
True
>>> del element[1:2]
>>> serialize(element)
''
"""
def cdata():
"""
Test CDATA handling (etc).
>>> serialize(ET.XML("hello"))
'hello'
>>> serialize(ET.XML("hello"))
'hello'
>>> serialize(ET.XML(""))
'hello'
"""
# Only with Python implementation
def simplefind():
"""
Test find methods using the elementpath fallback.
>>> from xml.etree import ElementTree
>>> CurrentElementPath = ElementTree.ElementPath
>>> ElementTree.ElementPath = ElementTree._SimpleElementPath()
>>> elem = ElementTree.XML(SAMPLE_XML)
>>> elem.find("tag").tag
'tag'
>>> ElementTree.ElementTree(elem).find("tag").tag
'tag'
>>> elem.findtext("tag")
'text'
>>> elem.findtext("tog")
>>> elem.findtext("tog", "default")
'default'
>>> ElementTree.ElementTree(elem).findtext("tag")
'text'
>>> summarize_list(elem.findall("tag"))
['tag', 'tag']
>>> summarize_list(elem.findall(".//tag"))
['tag', 'tag', 'tag']
Path syntax doesn't work in this case.
>>> elem.find("section/tag")
>>> elem.findtext("section/tag")
>>> summarize_list(elem.findall("section/tag"))
[]
>>> ElementTree.ElementPath = CurrentElementPath
"""
def find():
"""
Test find methods (including xpath syntax).
>>> elem = ET.XML(SAMPLE_XML)
>>> elem.find("tag").tag
'tag'
>>> ET.ElementTree(elem).find("tag").tag
'tag'
>>> elem.find("section/tag").tag
'tag'
>>> elem.find("./tag").tag
'tag'
>>> ET.ElementTree(elem).find("./tag").tag
'tag'
>>> ET.ElementTree(elem).find("/tag").tag
'tag'
>>> elem[2] = ET.XML(SAMPLE_SECTION)
>>> elem.find("section/nexttag").tag
'nexttag'
>>> ET.ElementTree(elem).find("section/tag").tag
'tag'
>>> ET.ElementTree(elem).find("tog")
>>> ET.ElementTree(elem).find("tog/foo")
>>> elem.findtext("tag")
'text'
>>> elem.findtext("section/nexttag")
''
>>> elem.findtext("section/nexttag", "default")
''
>>> elem.findtext("tog")
>>> elem.findtext("tog", "default")
'default'
>>> ET.ElementTree(elem).findtext("tag")
'text'
>>> ET.ElementTree(elem).findtext("tog/foo")
>>> ET.ElementTree(elem).findtext("tog/foo", "default")
'default'
>>> ET.ElementTree(elem).findtext("./tag")
'text'
>>> ET.ElementTree(elem).findtext("/tag")
'text'
>>> elem.findtext("section/tag")
'subtext'
>>> ET.ElementTree(elem).findtext("section/tag")
'subtext'
>>> summarize_list(elem.findall("."))
['body']
>>> summarize_list(elem.findall("tag"))
['tag', 'tag']
>>> summarize_list(elem.findall("tog"))
[]
>>> summarize_list(elem.findall("tog/foo"))
[]
>>> summarize_list(elem.findall("*"))
['tag', 'tag', 'section']
>>> summarize_list(elem.findall(".//tag"))
['tag', 'tag', 'tag', 'tag']
>>> summarize_list(elem.findall("section/tag"))
['tag']
>>> summarize_list(elem.findall("section//tag"))
['tag', 'tag']
>>> summarize_list(elem.findall("section/*"))
['tag', 'nexttag', 'nextsection']
>>> summarize_list(elem.findall("section//*"))
['tag', 'nexttag', 'nextsection', 'tag']
>>> summarize_list(elem.findall("section/.//*"))
['tag', 'nexttag', 'nextsection', 'tag']
>>> summarize_list(elem.findall("*/*"))
['tag', 'nexttag', 'nextsection']
>>> summarize_list(elem.findall("*//*"))
['tag', 'nexttag', 'nextsection', 'tag']
>>> summarize_list(elem.findall("*/tag"))
['tag']
>>> summarize_list(elem.findall("*/./tag"))
['tag']
>>> summarize_list(elem.findall("./tag"))
['tag', 'tag']
>>> summarize_list(elem.findall(".//tag"))
['tag', 'tag', 'tag', 'tag']
>>> summarize_list(elem.findall("././tag"))
['tag', 'tag']
>>> summarize_list(elem.findall(".//tag[@class]"))
['tag', 'tag', 'tag']
>>> summarize_list(elem.findall(".//tag[@class='a']"))
['tag']
>>> summarize_list(elem.findall(".//tag[@class='b']"))
['tag', 'tag']
>>> summarize_list(elem.findall(".//tag[@id]"))
['tag']
>>> summarize_list(elem.findall(".//section[tag]"))
['section']
>>> summarize_list(elem.findall(".//section[element]"))
[]
>>> summarize_list(elem.findall("../tag"))
[]
>>> summarize_list(elem.findall("section/../tag"))
['tag', 'tag']
>>> summarize_list(ET.ElementTree(elem).findall("./tag"))
['tag', 'tag']
Following example is invalid in 1.2.
A leading '*' is assumed in 1.3.
>>> elem.findall("section//") == elem.findall("section//*")
True
ET's Path module handles this case incorrectly; this gives
a warning in 1.3, and the behaviour will be modified in 1.4.
>>> summarize_list(ET.ElementTree(elem).findall("/tag"))
['tag', 'tag']
>>> elem = ET.XML(SAMPLE_XML_NS)
>>> summarize_list(elem.findall("tag"))
[]
>>> summarize_list(elem.findall("{http://effbot.org/ns}tag"))
['{http://effbot.org/ns}tag', '{http://effbot.org/ns}tag']
>>> summarize_list(elem.findall(".//{http://effbot.org/ns}tag"))
['{http://effbot.org/ns}tag', '{http://effbot.org/ns}tag', '{http://effbot.org/ns}tag']
"""
def file_init():
"""
>>> import io
>>> stringfile = io.BytesIO(SAMPLE_XML.encode("utf-8"))
>>> tree = ET.ElementTree(file=stringfile)
>>> tree.find("tag").tag
'tag'
>>> tree.find("section/tag").tag
'tag'
>>> tree = ET.ElementTree(file=SIMPLE_XMLFILE)
>>> tree.find("element").tag
'element'
>>> tree.find("element/../empty-element").tag
'empty-element'
"""
def bad_find():
"""
Check bad or unsupported path expressions.
>>> elem = ET.XML(SAMPLE_XML)
>>> elem.findall("/tag")
Traceback (most recent call last):
SyntaxError: cannot use absolute path on element
"""
def path_cache():
"""
Check that the path cache behaves sanely.
>>> elem = ET.XML(SAMPLE_XML)
>>> for i in range(10): ET.ElementTree(elem).find('./'+str(i))
>>> cache_len_10 = len(ET.ElementPath._cache)
>>> for i in range(10): ET.ElementTree(elem).find('./'+str(i))
>>> len(ET.ElementPath._cache) == cache_len_10
True
>>> for i in range(20): ET.ElementTree(elem).find('./'+str(i))
>>> len(ET.ElementPath._cache) > cache_len_10
True
>>> for i in range(600): ET.ElementTree(elem).find('./'+str(i))
>>> len(ET.ElementPath._cache) < 500
True
"""
def copy():
"""
Test copy handling (etc).
>>> import copy
>>> e1 = ET.XML("hello")
>>> e2 = copy.copy(e1)
>>> e3 = copy.deepcopy(e1)
>>> e1.find("foo").tag = "bar"
>>> serialize(e1)
'hello'
>>> serialize(e2)
'hello'
>>> serialize(e3)
'hello'
"""
def attrib():
"""
Test attribute handling.
>>> elem = ET.Element("tag")
>>> elem.get("key") # 1.1
>>> elem.get("key", "default") # 1.2
'default'
>>> elem.set("key", "value")
>>> elem.get("key") # 1.3
'value'
>>> elem = ET.Element("tag", key="value")
>>> elem.get("key") # 2.1
'value'
>>> elem.attrib # 2.2
{'key': 'value'}
>>> attrib = {"key": "value"}
>>> elem = ET.Element("tag", attrib)
>>> attrib.clear() # check for aliasing issues
>>> elem.get("key") # 3.1
'value'
>>> elem.attrib # 3.2
{'key': 'value'}
>>> attrib = {"key": "value"}
>>> elem = ET.Element("tag", **attrib)
>>> attrib.clear() # check for aliasing issues
>>> elem.get("key") # 4.1
'value'
>>> elem.attrib # 4.2
{'key': 'value'}
>>> elem = ET.Element("tag", {"key": "other"}, key="value")
>>> elem.get("key") # 5.1
'value'
>>> elem.attrib # 5.2
{'key': 'value'}
>>> elem = ET.Element('test')
>>> elem.text = "aa"
>>> elem.set('testa', 'testval')
>>> elem.set('testb', 'test2')
>>> ET.tostring(elem)
b'aa'
>>> sorted(elem.keys())
['testa', 'testb']
>>> sorted(elem.items())
[('testa', 'testval'), ('testb', 'test2')]
>>> elem.attrib['testb']
'test2'
>>> elem.attrib['testb'] = 'test1'
>>> elem.attrib['testc'] = 'test2'
>>> ET.tostring(elem)
b'aa'
"""
def makeelement():
"""
Test makeelement handling.
>>> elem = ET.Element("tag")
>>> attrib = {"key": "value"}
>>> subelem = elem.makeelement("subtag", attrib)
>>> if subelem.attrib is attrib:
... print("attrib aliasing")
>>> elem.append(subelem)
>>> serialize(elem)
''
>>> elem.clear()
>>> serialize(elem)
''
>>> elem.append(subelem)
>>> serialize(elem)
''
>>> elem.extend([subelem, subelem])
>>> serialize(elem)
''
>>> elem[:] = [subelem]
>>> serialize(elem)
''
>>> elem[:] = tuple([subelem])
>>> serialize(elem)
''
"""
def parsefile():
"""
Test parsing from file.
>>> tree = ET.parse(SIMPLE_XMLFILE)
>>> normalize_crlf(tree)
>>> tree.write(sys.stdout, encoding='unicode')
texttexttail
>>> tree = ET.parse(SIMPLE_NS_XMLFILE)
>>> normalize_crlf(tree)
>>> tree.write(sys.stdout, encoding='unicode')
texttexttail
>>> with open(SIMPLE_XMLFILE) as f:
... data = f.read()
>>> parser = ET.XMLParser()
>>> parser.version # doctest: +ELLIPSIS
'Expat ...'
>>> parser.feed(data)
>>> print(serialize(parser.close()))
texttexttail
>>> parser = ET.XMLTreeBuilder() # 1.2 compatibility
>>> parser.feed(data)
>>> print(serialize(parser.close()))
texttexttail
>>> target = ET.TreeBuilder()
>>> parser = ET.XMLParser(target=target)
>>> parser.feed(data)
>>> print(serialize(parser.close()))
texttexttail
"""
def parseliteral():
"""
>>> element = ET.XML("text")
>>> ET.ElementTree(element).write(sys.stdout, encoding='unicode')
text
>>> element = ET.fromstring("text")
>>> ET.ElementTree(element).write(sys.stdout, encoding='unicode')
text
>>> sequence = ["", "text"]
>>> element = ET.fromstringlist(sequence)
>>> ET.tostring(element)
b'text'
>>> b"".join(ET.tostringlist(element))
b'text'
>>> ET.tostring(element, "ascii")
b"\\ntext"
>>> _, ids = ET.XMLID("text")
>>> len(ids)
0
>>> _, ids = ET.XMLID("text")
>>> len(ids)
1
>>> ids["body"].tag
'body'
"""
def iterparse():
"""
Test iterparse interface.
>>> iterparse = ET.iterparse
>>> context = iterparse(SIMPLE_XMLFILE)
>>> action, elem = next(context)
>>> print(action, elem.tag)
end element
>>> for action, elem in context:
... print(action, elem.tag)
end element
end empty-element
end root
>>> context.root.tag
'root'
>>> context = iterparse(SIMPLE_NS_XMLFILE)
>>> for action, elem in context:
... print(action, elem.tag)
end {namespace}element
end {namespace}element
end {namespace}empty-element
end {namespace}root
>>> events = ()
>>> context = iterparse(SIMPLE_XMLFILE, events)
>>> for action, elem in context:
... print(action, elem.tag)
>>> events = ()
>>> context = iterparse(SIMPLE_XMLFILE, events=events)
>>> for action, elem in context:
... print(action, elem.tag)
>>> events = ("start", "end")
>>> context = iterparse(SIMPLE_XMLFILE, events)
>>> for action, elem in context:
... print(action, elem.tag)
start root
start element
end element
start element
end element
start empty-element
end empty-element
end root
>>> events = ("start", "end", "start-ns", "end-ns")
>>> context = iterparse(SIMPLE_NS_XMLFILE, events)
>>> for action, elem in context:
... if action in ("start", "end"):
... print(action, elem.tag)
... else:
... print(action, elem)
start-ns ('', 'namespace')
start {namespace}root
start {namespace}element
end {namespace}element
start {namespace}element
end {namespace}element
start {namespace}empty-element
end {namespace}empty-element
end {namespace}root
end-ns None
>>> events = ("start", "end", "bogus")
>>> with open(SIMPLE_XMLFILE, "rb") as f:
... iterparse(f, events)
Traceback (most recent call last):
ValueError: unknown event 'bogus'
>>> import io
>>> source = io.BytesIO(
... b"\\n"
... b"text\\n")
>>> events = ("start-ns",)
>>> context = iterparse(source, events)
>>> for action, elem in context:
... print(action, elem)
start-ns ('', 'http://\\xe9ffbot.org/ns')
start-ns ('cl\\xe9', 'http://effbot.org/ns')
>>> source = io.StringIO("junk")
>>> try:
... for action, elem in iterparse(source):
... print(action, elem.tag)
... except ET.ParseError as v:
... print(v)
end document
junk after document element: line 1, column 12
"""
def writefile():
"""
>>> elem = ET.Element("tag")
>>> elem.text = "text"
>>> serialize(elem)
'text'
>>> ET.SubElement(elem, "subtag").text = "subtext"
>>> serialize(elem)
'textsubtext'
Test tag suppression
>>> elem.tag = None
>>> serialize(elem)
'textsubtext'
>>> elem.insert(0, ET.Comment("comment"))
>>> serialize(elem) # assumes 1.3
'textsubtext'
>>> elem[0] = ET.PI("key", "value")
>>> serialize(elem)
'textsubtext'
"""
def custom_builder():
"""
Test parser w. custom builder.
>>> with open(SIMPLE_XMLFILE) as f:
... data = f.read()
>>> class Builder:
... def start(self, tag, attrib):
... print("start", tag)
... def end(self, tag):
... print("end", tag)
... def data(self, text):
... pass
>>> builder = Builder()
>>> parser = ET.XMLParser(target=builder)
>>> parser.feed(data)
start root
start element
end element
start element
end element
start empty-element
end empty-element
end root
>>> with open(SIMPLE_NS_XMLFILE) as f:
... data = f.read()
>>> class Builder:
... def start(self, tag, attrib):
... print("start", tag)
... def end(self, tag):
... print("end", tag)
... def data(self, text):
... pass
... def pi(self, target, data):
... print("pi", target, repr(data))
... def comment(self, data):
... print("comment", repr(data))
>>> builder = Builder()
>>> parser = ET.XMLParser(target=builder)
>>> parser.feed(data)
pi pi 'data'
comment ' comment '
start {namespace}root
start {namespace}element
end {namespace}element
start {namespace}element
end {namespace}element
start {namespace}empty-element
end {namespace}empty-element
end {namespace}root
"""
def getchildren():
"""
Test Element.getchildren()
>>> with open(SIMPLE_XMLFILE, "rb") as f:
... tree = ET.parse(f)
>>> for elem in tree.getroot().iter():
... summarize_list(elem.getchildren())
['element', 'element', 'empty-element']
[]
[]
[]
>>> for elem in tree.getiterator():
... summarize_list(elem.getchildren())
['element', 'element', 'empty-element']
[]
[]
[]
>>> elem = ET.XML(SAMPLE_XML)
>>> len(elem.getchildren())
3
>>> len(elem[2].getchildren())
1
>>> elem[:] == elem.getchildren()
True
>>> child1 = elem[0]
>>> child2 = elem[2]
>>> del elem[1:2]
>>> len(elem.getchildren())
2
>>> child1 == elem[0]
True
>>> child2 == elem[1]
True
>>> elem[0:2] = [child2, child1]
>>> child2 == elem[0]
True
>>> child1 == elem[1]
True
>>> child1 == elem[0]
False
>>> elem.clear()
>>> elem.getchildren()
[]
"""
def writestring():
"""
>>> elem = ET.XML("text")
>>> ET.tostring(elem)
b'text'
>>> elem = ET.fromstring("text")
>>> ET.tostring(elem)
b'text'
"""
def check_encoding(encoding):
"""
>>> check_encoding("ascii")
>>> check_encoding("us-ascii")
>>> check_encoding("iso-8859-1")
>>> check_encoding("iso-8859-15")
>>> check_encoding("cp437")
>>> check_encoding("mac-roman")
"""
ET.XML("" % encoding)
def encoding():
r"""
Test encoding issues.
>>> elem = ET.Element("tag")
>>> elem.text = "abc"
>>> serialize(elem)
'abc'
>>> serialize(elem, encoding="utf-8")
b'abc'
>>> serialize(elem, encoding="us-ascii")
b'abc'
>>> serialize(elem, encoding="iso-8859-1")
b"\nabc"
>>> elem.text = "<&\"\'>"
>>> serialize(elem)
'<&"\'>'
>>> serialize(elem, encoding="utf-8")
b'<&"\'>'
>>> serialize(elem, encoding="us-ascii") # cdata characters
b'<&"\'>'
>>> serialize(elem, encoding="iso-8859-1")
b'\n<&"\'>'
>>> elem.attrib["key"] = "<&\"\'>"
>>> elem.text = None
>>> serialize(elem)
''
>>> serialize(elem, encoding="utf-8")
b''
>>> serialize(elem, encoding="us-ascii")
b''
>>> serialize(elem, encoding="iso-8859-1")
b'\n'
>>> elem.text = '\xe5\xf6\xf6<>'
>>> elem.attrib.clear()
>>> serialize(elem)
'\xe5\xf6\xf6<>'
>>> serialize(elem, encoding="utf-8")
b'\xc3\xa5\xc3\xb6\xc3\xb6<>'
>>> serialize(elem, encoding="us-ascii")
b'åöö<>'
>>> serialize(elem, encoding="iso-8859-1")
b"\n\xe5\xf6\xf6<>"
>>> elem.attrib["key"] = '\xe5\xf6\xf6<>'
>>> elem.text = None
>>> serialize(elem)
''
>>> serialize(elem, encoding="utf-8")
b''
>>> serialize(elem, encoding="us-ascii")
b''
>>> serialize(elem, encoding="iso-8859-1")
b'\n'
"""
def methods():
r"""
Test serialization methods.
>>> e = ET.XML("")
>>> e.tail = "\n"
>>> serialize(e)
'\n'
>>> serialize(e, method=None)
'\n'
>>> serialize(e, method="xml")
'\n'
>>> serialize(e, method="html")
'\n'
>>> serialize(e, method="text")
'1 < 2\n'
"""
def iterators():
"""
Test iterators.
>>> e = ET.XML("this is a paragraph...")
>>> summarize_list(e.iter())
['html', 'body', 'i']
>>> summarize_list(e.find("body").iter())
['body', 'i']
>>> summarize(next(e.iter()))
'html'
>>> "".join(e.itertext())
'this is a paragraph...'
>>> "".join(e.find("body").itertext())
'this is a paragraph.'
>>> next(e.itertext())
'this is a '
Method iterparse should return an iterator. See bug 6472.
>>> sourcefile = serialize(e, to_string=False)
>>> next(ET.iterparse(sourcefile)) # doctest: +ELLIPSIS
('end', )
>>> tree = ET.ElementTree(None)
>>> tree.iter()
Traceback (most recent call last):
AttributeError: 'NoneType' object has no attribute 'iter'
"""
ENTITY_XML = """\
%user-entities;
]>
&entity;
"""
def entity():
"""
Test entity handling.
1) good entities
>>> e = ET.XML("test")
>>> serialize(e, encoding="us-ascii")
b'test'
>>> serialize(e)
'test'
2) bad entities
>>> normalize_exception(ET.XML, "&entity;")
Traceback (most recent call last):
ParseError: undefined entity: line 1, column 10
>>> normalize_exception(ET.XML, ENTITY_XML)
Traceback (most recent call last):
ParseError: undefined entity &entity;: line 5, column 10
3) custom entity
>>> parser = ET.XMLParser()
>>> parser.entity["entity"] = "text"
>>> parser.feed(ENTITY_XML)
>>> root = parser.close()
>>> serialize(root)
'text'
"""
def error(xml):
"""
Test error handling.
>>> issubclass(ET.ParseError, SyntaxError)
True
>>> error("foo").position
(1, 0)
>>> error("&foo;").position
(1, 5)
>>> error("foobar<").position
(1, 6)
"""
try:
ET.XML(xml)
except ET.ParseError:
return sys.exc_info()[1]
def namespace():
"""
Test namespace issues.
1) xml namespace
>>> elem = ET.XML("")
>>> serialize(elem) # 1.1
''
2) other "well-known" namespaces
>>> elem = ET.XML("")
>>> serialize(elem) # 2.1
''
>>> elem = ET.XML("")
>>> serialize(elem) # 2.2
''
>>> elem = ET.XML("")
>>> serialize(elem) # 2.3
''
3) unknown namespaces
>>> elem = ET.XML(SAMPLE_XML_NS)
>>> print(serialize(elem))
textsubtext
"""
def qname():
"""
Test QName handling.
1) decorated tags
>>> elem = ET.Element("{uri}tag")
>>> serialize(elem) # 1.1
''
>>> elem = ET.Element(ET.QName("{uri}tag"))
>>> serialize(elem) # 1.2
''
>>> elem = ET.Element(ET.QName("uri", "tag"))
>>> serialize(elem) # 1.3
''
>>> elem = ET.Element(ET.QName("uri", "tag"))
>>> subelem = ET.SubElement(elem, ET.QName("uri", "tag1"))
>>> subelem = ET.SubElement(elem, ET.QName("uri", "tag2"))
>>> serialize(elem) # 1.4
''
2) decorated attributes
>>> elem.clear()
>>> elem.attrib["{uri}key"] = "value"
>>> serialize(elem) # 2.1
''
>>> elem.clear()
>>> elem.attrib[ET.QName("{uri}key")] = "value"
>>> serialize(elem) # 2.2
''
3) decorated values are not converted by default, but the
QName wrapper can be used for values
>>> elem.clear()
>>> elem.attrib["{uri}key"] = "{uri}value"
>>> serialize(elem) # 3.1
''
>>> elem.clear()
>>> elem.attrib["{uri}key"] = ET.QName("{uri}value")
>>> serialize(elem) # 3.2
''
>>> elem.clear()
>>> subelem = ET.Element("tag")
>>> subelem.attrib["{uri1}key"] = ET.QName("{uri2}value")
>>> elem.append(subelem)
>>> elem.append(subelem)
>>> serialize(elem) # 3.3
''
4) Direct QName tests
>>> str(ET.QName('ns', 'tag'))
'{ns}tag'
>>> str(ET.QName('{ns}tag'))
'{ns}tag'
>>> q1 = ET.QName('ns', 'tag')
>>> q2 = ET.QName('ns', 'tag')
>>> q1 == q2
True
>>> q2 = ET.QName('ns', 'other-tag')
>>> q1 == q2
False
>>> q1 == 'ns:tag'
False
>>> q1 == '{ns}tag'
True
"""
def doctype_public():
"""
Test PUBLIC doctype.
>>> elem = ET.XML(''
... 'text')
"""
def xpath_tokenizer(p):
"""
Test the XPath tokenizer.
>>> # tests from the xml specification
>>> xpath_tokenizer("*")
['*']
>>> xpath_tokenizer("text()")
['text', '()']
>>> xpath_tokenizer("@name")
['@', 'name']
>>> xpath_tokenizer("@*")
['@', '*']
>>> xpath_tokenizer("para[1]")
['para', '[', '1', ']']
>>> xpath_tokenizer("para[last()]")
['para', '[', 'last', '()', ']']
>>> xpath_tokenizer("*/para")
['*', '/', 'para']
>>> xpath_tokenizer("/doc/chapter[5]/section[2]")
['/', 'doc', '/', 'chapter', '[', '5', ']', '/', 'section', '[', '2', ']']
>>> xpath_tokenizer("chapter//para")
['chapter', '//', 'para']
>>> xpath_tokenizer("//para")
['//', 'para']
>>> xpath_tokenizer("//olist/item")
['//', 'olist', '/', 'item']
>>> xpath_tokenizer(".")
['.']
>>> xpath_tokenizer(".//para")
['.', '//', 'para']
>>> xpath_tokenizer("..")
['..']
>>> xpath_tokenizer("../@lang")
['..', '/', '@', 'lang']
>>> xpath_tokenizer("chapter[title]")
['chapter', '[', 'title', ']']
>>> xpath_tokenizer("employee[@secretary and @assistant]")
['employee', '[', '@', 'secretary', '', 'and', '', '@', 'assistant', ']']
>>> # additional tests
>>> xpath_tokenizer("{http://spam}egg")
['{http://spam}egg']
>>> xpath_tokenizer("./spam.egg")
['.', '/', 'spam.egg']
>>> xpath_tokenizer(".//{http://spam}egg")
['.', '//', '{http://spam}egg']
"""
from xml.etree import ElementPath
out = []
for op, tag in ElementPath.xpath_tokenizer(p):
out.append(op or tag)
return out
def processinginstruction():
"""
Test ProcessingInstruction directly
>>> ET.tostring(ET.ProcessingInstruction('test', 'instruction'))
b''
>>> ET.tostring(ET.PI('test', 'instruction'))
b''
Issue #2746
>>> ET.tostring(ET.PI('test', ''))
b'?>'
>>> ET.tostring(ET.PI('test', '\xe3'), 'latin1')
b"\\n\\xe3?>"
"""
#
# xinclude tests (samples from appendix C of the xinclude specification)
XINCLUDE = {}
XINCLUDE["C1.xml"] = """\
120 Mz is adequate for an average home user.
"""
XINCLUDE["disclaimer.xml"] = """\
The opinions represented herein represent those of the individual
and should not be interpreted as official policy endorsed by this
organization.
'
"""
# --------------------------------------------------------------------
class CleanContext(object):
"""Provide default namespace mapping and path cache."""
checkwarnings = None
def __init__(self, quiet=False):
if sys.flags.optimize >= 2:
# under -OO, doctests cannot be run and therefore not all warnings
# will be emitted
quiet = True
deprecations = (
# Search behaviour is broken if search path starts with "/".
("This search is broken in 1.3 and earlier, and will be fixed "
"in a future version. If you rely on the current behaviour, "
"change it to '.+'", FutureWarning),
# Element.getchildren() and Element.getiterator() are deprecated.
("This method will be removed in future versions. "
"Use .+ instead.", DeprecationWarning),
("This method will be removed in future versions. "
"Use .+ instead.", PendingDeprecationWarning),
# XMLParser.doctype() is deprecated.
("This method of XMLParser is deprecated. Define doctype.. "
"method on the TreeBuilder target.", DeprecationWarning))
self.checkwarnings = support.check_warnings(*deprecations, quiet=quiet)
def __enter__(self):
from xml.etree import ElementTree
self._nsmap = ElementTree._namespace_map
self._path_cache = ElementTree.ElementPath._cache
# Copy the default namespace mapping
ElementTree._namespace_map = self._nsmap.copy()
# Copy the path cache (should be empty)
ElementTree.ElementPath._cache = self._path_cache.copy()
self.checkwarnings.__enter__()
def __exit__(self, *args):
from xml.etree import ElementTree
# Restore mapping and path cache
ElementTree._namespace_map = self._nsmap
ElementTree.ElementPath._cache = self._path_cache
self.checkwarnings.__exit__(*args)
def test_main(module_name='xml.etree.ElementTree'):
from test import test_xml_etree
use_py_module = (module_name == 'xml.etree.ElementTree')
# The same doctests are used for both the Python and the C implementations
assert test_xml_etree.ET.__name__ == module_name
# XXX the C module should give the same warnings as the Python module
with CleanContext(quiet=not use_py_module):
support.run_doctest(test_xml_etree, verbosity=True)
# The module should not be changed by the tests
assert test_xml_etree.ET.__name__ == module_name
if __name__ == '__main__':
test_main()