From f8cf59e8aa1a1657e5255504c847f52ec621aac5 Mon Sep 17 00:00:00 2001 From: Serhiy Storchaka Date: Mon, 25 Feb 2013 17:20:59 +0200 Subject: Issue #15083: Convert ElementTree doctests to unittests. --- Lib/test/test_xml_etree.py | 2505 ++++++++++++++++++++------------------------ 1 file changed, 1132 insertions(+), 1373 deletions(-) diff --git a/Lib/test/test_xml_etree.py b/Lib/test/test_xml_etree.py index 61161b6..5e389e3 100644 --- a/Lib/test/test_xml_etree.py +++ b/Lib/test/test_xml_etree.py @@ -87,21 +87,26 @@ SAMPLE_XML_NS_ELEMS = """ """ -def sanity(): - """ - Import sanity. +ENTITY_XML = """\ + +%user-entities; +]> +&entity; +""" + + +class ModuleTest(unittest.TestCase): - >>> from xml.etree import ElementTree - >>> from xml.etree import ElementInclude - >>> from xml.etree import ElementPath - """ + def test_sanity(self): + # 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: @@ -114,68 +119,9 @@ def serialize(elem, to_string=True, encoding='unicode', **options): 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") + return [elem.tag for elem in seq] -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) class ElementTestCase: @classmethod @@ -212,837 +158,757 @@ class ElementTestCase: # -------------------------------------------------------------------- # 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.iterfind("tag").__next__) - >>> check_method(element.iterfind("*").__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' - """ - -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 path_cache(): - """ - Check that the path cache behaves sanely. - - >>> from xml.etree import ElementPath - - >>> elem = ET.XML(SAMPLE_XML) - >>> for i in range(10): ET.ElementTree(elem).find('./'+str(i)) - >>> cache_len_10 = len(ElementPath._cache) - >>> for i in range(10): ET.ElementTree(elem).find('./'+str(i)) - >>> len(ElementPath._cache) == cache_len_10 - True - >>> for i in range(20): ET.ElementTree(elem).find('./'+str(i)) - >>> len(ElementPath._cache) > cache_len_10 - True - >>> for i in range(600): ET.ElementTree(elem).find('./'+str(i)) - >>> len(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') - - text - texttail - - - >>> tree = ET.parse(SIMPLE_NS_XMLFILE) - >>> normalize_crlf(tree) - >>> tree.write(sys.stdout, encoding='unicode') - - text - texttail - - - - >>> with open(SIMPLE_XMLFILE) as f: - ... data = f.read() - - >>> parser = ET.XMLParser() - >>> parser.version # doctest: +ELLIPSIS - 'Expat ...' - >>> parser.feed(data) - >>> print(serialize(parser.close())) - - text - texttail - - - - >>> parser = ET.XMLTreeBuilder() # 1.2 compatibility - >>> parser.feed(data) - >>> print(serialize(parser.close())) - - text - texttail - - - - >>> target = ET.TreeBuilder() - >>> parser = ET.XMLParser(target=target) - >>> parser.feed(data) - >>> print(serialize(parser.close())) - - text - texttail - - - """ - -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 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' - """ +class ElementTreeTest(unittest.TestCase): -ENTITY_XML = """\ - -%user-entities; -]> -&entity; -""" + def serialize_check(self, elem, expected): + self.assertEqual(serialize(elem), expected) + + def test_interface(self): + # Test element tree interface. + + def check_string(string): + len(string) + for char in string: + self.assertEqual(len(char), 1, + msg="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" + self.assertEqual(mapping["key"], "value", + msg="expected value string, got %r" % mapping["key"]) + + def check_element(element): + self.assertTrue(ET.iselement(element), msg="not an element") + self.assertTrue(hasattr(element, "tag"), msg="no tag member") + self.assertTrue(hasattr(element, "attrib"), msg="no attrib member") + self.assertTrue(hasattr(element, "text"), msg="no text member") + self.assertTrue(hasattr(element, "tail"), msg="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 = 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) + self.assertRegex(repr(element), r"^$") + element = ET.Element("tag", key="value") + + # Make sure all standard element methods exist. + + def check_method(method): + self.assertTrue(hasattr(method, '__call__'), + msg="%s not callable" % method) + + 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. + + def check_iter(it): + check_method(it.__next__) + + check_iter(element.iterfind("tag")) + check_iter(element.iterfind("*")) + check_iter(tree.iterfind("tag")) + check_iter(tree.iterfind("*")) + + # These aliases are provided: + + self.assertEqual(ET.XML, ET.fromstring) + self.assertEqual(ET.PI, ET.ProcessingInstruction) + self.assertEqual(ET.XMLParser, ET.XMLTreeBuilder) + + def test_simpleops(self): + # Basic method sanity checks. + + elem = ET.XML("") + self.serialize_check(elem, '') + e = ET.Element("tag2") + elem.append(e) + self.serialize_check(elem, '') + elem.remove(e) + self.serialize_check(elem, '') + elem.insert(0, e) + self.serialize_check(elem, '') + elem.remove(e) + elem.extend([e]) + self.serialize_check(elem, '') + elem.remove(e) + + element = ET.Element("tag", key="value") + self.serialize_check(element, '') # 1 + subelement = ET.Element("subtag") + element.append(subelement) + self.serialize_check(element, '') # 2 + element.insert(0, subelement) + self.serialize_check(element, + '') # 3 + element.remove(subelement) + self.serialize_check(element, '') # 4 + element.remove(subelement) + self.serialize_check(element, '') # 5 + with self.assertRaises(ValueError) as cm: + element.remove(subelement) + self.assertEqual(str(cm.exception), 'list.remove(x): x not in list') + self.serialize_check(element, '') # 6 + element[0:0] = [subelement, subelement, subelement] + self.serialize_check(element[1], '') + self.assertEqual(element[1:9], [element[1], element[2]]) + self.assertEqual(element[:9:2], [element[0], element[2]]) + del element[1:2] + self.serialize_check(element, + '') + + def test_cdata(self): + # Test CDATA handling (etc). + + self.serialize_check(ET.XML("hello"), + 'hello') + self.serialize_check(ET.XML("hello"), + 'hello') + self.serialize_check(ET.XML(""), + 'hello') + + def test_file_init(self): + stringfile = io.BytesIO(SAMPLE_XML.encode("utf-8")) + tree = ET.ElementTree(file=stringfile) + self.assertEqual(tree.find("tag").tag, 'tag') + self.assertEqual(tree.find("section/tag").tag, 'tag') + + tree = ET.ElementTree(file=SIMPLE_XMLFILE) + self.assertEqual(tree.find("element").tag, 'element') + self.assertEqual(tree.find("element/../empty-element").tag, + 'empty-element') + + def test_path_cache(self): + # Check that the path cache behaves sanely. + + from xml.etree import ElementPath + + elem = ET.XML(SAMPLE_XML) + for i in range(10): ET.ElementTree(elem).find('./'+str(i)) + cache_len_10 = len(ElementPath._cache) + for i in range(10): ET.ElementTree(elem).find('./'+str(i)) + self.assertEqual(len(ElementPath._cache), cache_len_10) + for i in range(20): ET.ElementTree(elem).find('./'+str(i)) + self.assertGreater(len(ElementPath._cache), cache_len_10) + for i in range(600): ET.ElementTree(elem).find('./'+str(i)) + self.assertLess(len(ElementPath._cache), 500) + + def test_copy(self): + # Test copy handling (etc). + + import copy + e1 = ET.XML("hello") + e2 = copy.copy(e1) + e3 = copy.deepcopy(e1) + e1.find("foo").tag = "bar" + self.serialize_check(e1, 'hello') + self.serialize_check(e2, 'hello') + self.serialize_check(e3, 'hello') + + def test_attrib(self): + # Test attribute handling. + + elem = ET.Element("tag") + elem.get("key") # 1.1 + self.assertEqual(elem.get("key", "default"), 'default') # 1.2 + + elem.set("key", "value") + self.assertEqual(elem.get("key"), 'value') # 1.3 + + elem = ET.Element("tag", key="value") + self.assertEqual(elem.get("key"), 'value') # 2.1 + self.assertEqual(elem.attrib, {'key': 'value'}) # 2.2 + + attrib = {"key": "value"} + elem = ET.Element("tag", attrib) + attrib.clear() # check for aliasing issues + self.assertEqual(elem.get("key"), 'value') # 3.1 + self.assertEqual(elem.attrib, {'key': 'value'}) # 3.2 + + attrib = {"key": "value"} + elem = ET.Element("tag", **attrib) + attrib.clear() # check for aliasing issues + self.assertEqual(elem.get("key"), 'value') # 4.1 + self.assertEqual(elem.attrib, {'key': 'value'}) # 4.2 + + elem = ET.Element("tag", {"key": "other"}, key="value") + self.assertEqual(elem.get("key"), 'value') # 5.1 + self.assertEqual(elem.attrib, {'key': 'value'}) # 5.2 + + elem = ET.Element('test') + elem.text = "aa" + elem.set('testa', 'testval') + elem.set('testb', 'test2') + self.assertEqual(ET.tostring(elem), + b'aa') + self.assertEqual(sorted(elem.keys()), ['testa', 'testb']) + self.assertEqual(sorted(elem.items()), + [('testa', 'testval'), ('testb', 'test2')]) + self.assertEqual(elem.attrib['testb'], 'test2') + elem.attrib['testb'] = 'test1' + elem.attrib['testc'] = 'test2' + self.assertEqual(ET.tostring(elem), + b'aa') + + def test_makeelement(self): + # Test makeelement handling. + + elem = ET.Element("tag") + attrib = {"key": "value"} + subelem = elem.makeelement("subtag", attrib) + self.assertIsNot(subelem.attrib, attrib, msg="attrib aliasing") + elem.append(subelem) + self.serialize_check(elem, '') + + elem.clear() + self.serialize_check(elem, '') + elem.append(subelem) + self.serialize_check(elem, '') + elem.extend([subelem, subelem]) + self.serialize_check(elem, + '') + elem[:] = [subelem] + self.serialize_check(elem, '') + elem[:] = tuple([subelem]) + self.serialize_check(elem, '') + + def test_parsefile(self): + # Test parsing from file. + + tree = ET.parse(SIMPLE_XMLFILE) + stream = io.StringIO() + tree.write(stream, encoding='unicode') + self.assertEqual(stream.getvalue(), + '\n' + ' text\n' + ' texttail\n' + ' \n' + '') + tree = ET.parse(SIMPLE_NS_XMLFILE) + stream = io.StringIO() + tree.write(stream, encoding='unicode') + self.assertEqual(stream.getvalue(), + '\n' + ' text\n' + ' texttail\n' + ' \n' + '') + + with open(SIMPLE_XMLFILE) as f: + data = f.read() + + parser = ET.XMLParser() + self.assertRegex(parser.version, r'^Expat ') + parser.feed(data) + self.serialize_check(parser.close(), + '\n' + ' text\n' + ' texttail\n' + ' \n' + '') + + parser = ET.XMLTreeBuilder() # 1.2 compatibility + parser.feed(data) + self.serialize_check(parser.close(), + '\n' + ' text\n' + ' texttail\n' + ' \n' + '') + + target = ET.TreeBuilder() + parser = ET.XMLParser(target=target) + parser.feed(data) + self.serialize_check(parser.close(), + '\n' + ' text\n' + ' texttail\n' + ' \n' + '') + + def test_parseliteral(self): + element = ET.XML("text") + self.assertEqual(ET.tostring(element, encoding='unicode'), + 'text') + element = ET.fromstring("text") + self.assertEqual(ET.tostring(element, encoding='unicode'), + 'text') + sequence = ["", "text"] + element = ET.fromstringlist(sequence) + self.assertEqual(ET.tostring(element), + b'text') + self.assertEqual(b"".join(ET.tostringlist(element)), + b'text') + self.assertEqual(ET.tostring(element, "ascii"), + b"\n" + b"text") + _, ids = ET.XMLID("text") + self.assertEqual(len(ids), 0) + _, ids = ET.XMLID("text") + self.assertEqual(len(ids), 1) + self.assertEqual(ids["body"].tag, 'body') + + def test_iterparse(self): + # Test iterparse interface. + + iterparse = ET.iterparse + + context = iterparse(SIMPLE_XMLFILE) + action, elem = next(context) + self.assertEqual((action, elem.tag), ('end', 'element')) + self.assertEqual([(action, elem.tag) for action, elem in context], [ + ('end', 'element'), + ('end', 'empty-element'), + ('end', 'root'), + ]) + self.assertEqual(context.root.tag, 'root') + + context = iterparse(SIMPLE_NS_XMLFILE) + self.assertEqual([(action, elem.tag) for action, elem in context], [ + ('end', '{namespace}element'), + ('end', '{namespace}element'), + ('end', '{namespace}empty-element'), + ('end', '{namespace}root'), + ]) + + events = () + context = iterparse(SIMPLE_XMLFILE, events) + self.assertEqual([(action, elem.tag) for action, elem in context], []) + + events = () + context = iterparse(SIMPLE_XMLFILE, events=events) + self.assertEqual([(action, elem.tag) for action, elem in context], []) + + events = ("start", "end") + context = iterparse(SIMPLE_XMLFILE, events) + self.assertEqual([(action, elem.tag) for action, elem in context], [ + ('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) + self.assertEqual([(action, elem.tag) if action in ("start", "end") else (action, elem) + for action, elem in context], [ + ('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 self.assertRaises(ValueError) as cm: + with open(SIMPLE_XMLFILE, "rb") as f: + iterparse(f, events) + self.assertEqual(str(cm.exception), "unknown event 'bogus'") + + source = io.BytesIO( + b"\n" + b"text\n") + events = ("start-ns",) + context = iterparse(source, events) + self.assertEqual([(action, elem) for action, elem in context], [ + ('start-ns', ('', 'http://\xe9ffbot.org/ns')), + ('start-ns', ('cl\xe9', 'http://effbot.org/ns')), + ]) + + source = io.StringIO("junk") + it = iterparse(source) + action, elem = next(it) + self.assertEqual((action, elem.tag), ('end', 'document')) + with self.assertRaises(ET.ParseError) as cm: + next(it) + self.assertEqual(str(cm.exception), + 'junk after document element: line 1, column 12') + + def test_writefile(self): + elem = ET.Element("tag") + elem.text = "text" + self.serialize_check(elem, 'text') + ET.SubElement(elem, "subtag").text = "subtext" + self.serialize_check(elem, 'textsubtext') + + # Test tag suppression + elem.tag = None + self.serialize_check(elem, 'textsubtext') + elem.insert(0, ET.Comment("comment")) + self.serialize_check(elem, + 'textsubtext') # assumes 1.3 + + elem[0] = ET.PI("key", "value") + self.serialize_check(elem, 'textsubtext') + + def test_custom_builder(self): + # Test parser w. custom builder. + + with open(SIMPLE_XMLFILE) as f: + data = f.read() + class Builder(list): + def start(self, tag, attrib): + self.append(("start", tag)) + def end(self, tag): + self.append(("end", tag)) + def data(self, text): + pass + builder = Builder() + parser = ET.XMLParser(target=builder) + parser.feed(data) + self.assertEqual(builder, [ + ('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(list): + def start(self, tag, attrib): + self.append(("start", tag)) + def end(self, tag): + self.append(("end", tag)) + def data(self, text): + pass + def pi(self, target, data): + self.append(("pi", target, data)) + def comment(self, data): + self.append(("comment", data)) + builder = Builder() + parser = ET.XMLParser(target=builder) + parser.feed(data) + self.assertEqual(builder, [ + ('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 test_getchildren(self): + # Test Element.getchildren() + + with open(SIMPLE_XMLFILE, "rb") as f: + tree = ET.parse(f) + self.assertEqual([summarize_list(elem.getchildren()) + for elem in tree.getroot().iter()], [ + ['element', 'element', 'empty-element'], + [], + [], + [], + ]) + self.assertEqual([summarize_list(elem.getchildren()) + for elem in tree.getiterator()], [ + ['element', 'element', 'empty-element'], + [], + [], + [], + ]) + + elem = ET.XML(SAMPLE_XML) + self.assertEqual(len(elem.getchildren()), 3) + self.assertEqual(len(elem[2].getchildren()), 1) + self.assertEqual(elem[:], elem.getchildren()) + child1 = elem[0] + child2 = elem[2] + del elem[1:2] + self.assertEqual(len(elem.getchildren()), 2) + self.assertEqual(child1, elem[0]) + self.assertEqual(child2, elem[1]) + elem[0:2] = [child2, child1] + self.assertEqual(child2, elem[0]) + self.assertEqual(child1, elem[1]) + self.assertNotEqual(child1, elem[0]) + elem.clear() + self.assertEqual(elem.getchildren(), []) + + def test_writestring(self): + elem = ET.XML("text") + self.assertEqual(ET.tostring(elem), b'text') + elem = ET.fromstring("text") + self.assertEqual(ET.tostring(elem), b'text') + + def test_encoding(encoding): + def check(encoding): + ET.XML("" % encoding) + check("ascii") + check("us-ascii") + check("iso-8859-1") + check("iso-8859-15") + check("cp437") + check("mac-roman") + + def test_methods(self): + # Test serialization methods. + + e = ET.XML("") + e.tail = "\n" + self.assertEqual(serialize(e), + '\n') + self.assertEqual(serialize(e, method=None), + '\n') + self.assertEqual(serialize(e, method="xml"), + '\n') + self.assertEqual(serialize(e, method="html"), + '\n') + self.assertEqual(serialize(e, method="text"), '1 < 2\n') + + def test_entity(self): + # Test entity handling. + + # 1) good entities + + e = ET.XML("test") + self.assertEqual(serialize(e, encoding="us-ascii"), + b'test') + self.serialize_check(e, 'test') + + # 2) bad entities + + with self.assertRaises(ET.ParseError) as cm: + ET.XML("&entity;") + self.assertEqual(str(cm.exception), + 'undefined entity: line 1, column 10') + + with self.assertRaises(ET.ParseError) as cm: + ET.XML(ENTITY_XML) + self.assertEqual(str(cm.exception), + 'undefined entity &entity;: line 5, column 10') + + # 3) custom entity + + parser = ET.XMLParser() + parser.entity["entity"] = "text" + parser.feed(ENTITY_XML) + root = parser.close() + self.serialize_check(root, 'text') + + def test_namespace(self): + # Test namespace issues. + + # 1) xml namespace + + elem = ET.XML("") + self.serialize_check(elem, '') # 1.1 + + # 2) other "well-known" namespaces + + elem = ET.XML("") + self.serialize_check(elem, + '') # 2.1 + + elem = ET.XML("") + self.serialize_check(elem, + '') # 2.2 + + elem = ET.XML("") + self.serialize_check(elem, + '') # 2.3 + + # 3) unknown namespaces + elem = ET.XML(SAMPLE_XML_NS) + self.serialize_check(elem, + '\n' + ' text\n' + ' \n' + ' \n' + ' subtext\n' + ' \n' + '') + + def test_qname(self): + # Test QName handling. + + # 1) decorated tags + + elem = ET.Element("{uri}tag") + self.serialize_check(elem, '') # 1.1 + elem = ET.Element(ET.QName("{uri}tag")) + self.serialize_check(elem, '') # 1.2 + elem = ET.Element(ET.QName("uri", "tag")) + self.serialize_check(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")) + self.serialize_check(elem, + '') # 1.4 + + # 2) decorated attributes + + elem.clear() + elem.attrib["{uri}key"] = "value" + self.serialize_check(elem, + '') # 2.1 + + elem.clear() + elem.attrib[ET.QName("{uri}key")] = "value" + self.serialize_check(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" + self.serialize_check(elem, + '') # 3.1 + + elem.clear() + elem.attrib["{uri}key"] = ET.QName("{uri}value") + self.serialize_check(elem, + '') # 3.2 + + elem.clear() + subelem = ET.Element("tag") + subelem.attrib["{uri1}key"] = ET.QName("{uri2}value") + elem.append(subelem) + elem.append(subelem) + self.serialize_check(elem, + '' + '' + '' + '') # 3.3 + + # 4) Direct QName tests + + self.assertEqual(str(ET.QName('ns', 'tag')), '{ns}tag') + self.assertEqual(str(ET.QName('{ns}tag')), '{ns}tag') + q1 = ET.QName('ns', 'tag') + q2 = ET.QName('ns', 'tag') + self.assertEqual(q1, q2) + q2 = ET.QName('ns', 'other-tag') + self.assertNotEqual(q1, q2) + self.assertNotEqual(q1, 'ns:tag') + self.assertEqual(q1, '{ns}tag') + + def test_doctype_public(self): + # Test PUBLIC doctype. + + elem = ET.XML('' + 'text') + + def test_xpath_tokenizer(self): + # Test the XPath tokenizer. + from xml.etree import ElementPath + def check(p, expected): + self.assertEqual([op or tag + for op, tag in ElementPath.xpath_tokenizer(p)], + expected) + + # tests from the xml specification + check("*", ['*']) + check("text()", ['text', '()']) + check("@name", ['@', 'name']) + check("@*", ['@', '*']) + check("para[1]", ['para', '[', '1', ']']) + check("para[last()]", ['para', '[', 'last', '()', ']']) + check("*/para", ['*', '/', 'para']) + check("/doc/chapter[5]/section[2]", + ['/', 'doc', '/', 'chapter', '[', '5', ']', + '/', 'section', '[', '2', ']']) + check("chapter//para", ['chapter', '//', 'para']) + check("//para", ['//', 'para']) + check("//olist/item", ['//', 'olist', '/', 'item']) + check(".", ['.']) + check(".//para", ['.', '//', 'para']) + check("..", ['..']) + check("../@lang", ['..', '/', '@', 'lang']) + check("chapter[title]", ['chapter', '[', 'title', ']']) + check("employee[@secretary and @assistant]", ['employee', + '[', '@', 'secretary', '', 'and', '', '@', 'assistant', ']']) + + # additional tests + check("{http://spam}egg", ['{http://spam}egg']) + check("./spam.egg", ['.', '/', 'spam.egg']) + check(".//{http://spam}egg", ['.', '//', '{http://spam}egg']) + + def test_processinginstruction(self): + # Test ProcessingInstruction directly + + self.assertEqual(ET.tostring(ET.ProcessingInstruction('test', 'instruction')), + b'') + self.assertEqual(ET.tostring(ET.PI('test', 'instruction')), + b'') + + # Issue #2746 + + self.assertEqual(ET.tostring(ET.PI('test', '')), + b'?>') + self.assertEqual(ET.tostring(ET.PI('test', '\xe3'), 'latin-1'), + b"\n" + b"\xe3?>") + + def test_html_empty_elems_serialization(self): + # issue 15970 + # from http://www.w3.org/TR/html401/index/elements.html + for element in ['AREA', 'BASE', 'BASEFONT', 'BR', 'COL', 'FRAME', 'HR', + 'IMG', 'INPUT', 'ISINDEX', 'LINK', 'META', 'PARAM']: + for elem in [element, element.lower()]: + expected = '<%s>' % elem + serialized = serialize(ET.XML('<%s />' % elem), method='html') + self.assertEqual(serialized, expected) + serialized = serialize(ET.XML('<%s>' % (elem,elem)), + method='html') + self.assertEqual(serialized, expected) -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 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)) - - text - - - subtext - - - """ - -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'), 'latin-1') - b"\\n\\xe3?>" - """ # # xinclude tests (samples from appendix C of the xinclude specification) @@ -1120,79 +986,6 @@ XINCLUDE["default.xml"] = """\ """.format(html.escape(SIMPLE_XMLFILE, True)) - -def xinclude_loader(href, parse="xml", encoding=None): - try: - data = XINCLUDE[href] - except KeyError: - raise OSError("resource not found") - if parse == "xml": - data = ET.XML(data) - return data - -def xinclude(): - r""" - Basic inclusion example (XInclude C.1) - - >>> from xml.etree import ElementInclude - - >>> document = xinclude_loader("C1.xml") - >>> ElementInclude.include(document, xinclude_loader) - >>> print(serialize(document)) # C1 - -

120 Mz is adequate for an average home user.

- -

The opinions represented herein represent those of the individual - and should not be interpreted as official policy endorsed by this - organization.

-
-
- - Textual inclusion example (XInclude C.2) - - >>> document = xinclude_loader("C2.xml") - >>> ElementInclude.include(document, xinclude_loader) - >>> print(serialize(document)) # C2 - -

This document has been accessed - 324387 times.

-
- - Textual inclusion after sibling element (based on modified XInclude C.2) - - >>> document = xinclude_loader("C2b.xml") - >>> ElementInclude.include(document, xinclude_loader) - >>> print(serialize(document)) # C2b - -

This document has been accessed - 324387 times.

-
- - Textual inclusion of XML example (XInclude C.3) - - >>> document = xinclude_loader("C3.xml") - >>> ElementInclude.include(document, xinclude_loader) - >>> print(serialize(document)) # C3 - -

The following is the source of the "data.xml" resource:

- <?xml version='1.0'?> - <data> - <item><![CDATA[Brooks & Shields]]></item> - </data> - -
- - Fallback example (XInclude C.5) - Note! Fallback support is not yet implemented - - >>> document = xinclude_loader("C5.xml") - >>> ElementInclude.include(document, xinclude_loader) - Traceback (most recent call last): - OSError: resource not found - >>> # print(serialize(document)) # C5 - """ - - # # badly formatted xi:include tags @@ -1213,410 +1006,412 @@ XINCLUDE_BAD["B2.xml"] = """\ """ -def xinclude_failures(): - r""" - Test failure to locate included XML file. - - >>> from xml.etree import ElementInclude +class XIncludeTest(unittest.TestCase): - >>> def none_loader(href, parser, encoding=None): - ... return None - - >>> document = ET.XML(XINCLUDE["C1.xml"]) - >>> ElementInclude.include(document, loader=none_loader) - Traceback (most recent call last): - xml.etree.ElementInclude.FatalIncludeError: cannot load 'disclaimer.xml' as 'xml' - - Test failure to locate included text file. + def xinclude_loader(self, href, parse="xml", encoding=None): + try: + data = XINCLUDE[href] + except KeyError: + raise OSError("resource not found") + if parse == "xml": + data = ET.XML(data) + return data - >>> document = ET.XML(XINCLUDE["C2.xml"]) - >>> ElementInclude.include(document, loader=none_loader) - Traceback (most recent call last): - xml.etree.ElementInclude.FatalIncludeError: cannot load 'count.txt' as 'text' + def none_loader(self, href, parser, encoding=None): + return None - Test bad parse type. + def _my_loader(self, href, parse): + # Used to avoid a test-dependency problem where the default loader + # of ElementInclude uses the pyET parser for cET tests. + if parse == 'xml': + with open(href, 'rb') as f: + return ET.parse(f).getroot() + else: + return None - >>> document = ET.XML(XINCLUDE_BAD["B1.xml"]) - >>> ElementInclude.include(document, loader=none_loader) - Traceback (most recent call last): - xml.etree.ElementInclude.FatalIncludeError: unknown parse type in xi:include tag ('BAD_TYPE') + def test_xinclude_default(self): + from xml.etree import ElementInclude + doc = self.xinclude_loader('default.xml') + ElementInclude.include(doc, self._my_loader) + self.assertEqual(serialize(doc), + '\n' + '

Example.

\n' + ' \n' + ' text\n' + ' texttail\n' + ' \n' + '\n' + '
') + + def test_xinclude(self): + from xml.etree import ElementInclude - Test xi:fallback outside xi:include. + # Basic inclusion example (XInclude C.1) + document = self.xinclude_loader("C1.xml") + ElementInclude.include(document, self.xinclude_loader) + self.assertEqual(serialize(document), + '\n' + '

120 Mz is adequate for an average home user.

\n' + ' \n' + '

The opinions represented herein represent those of the individual\n' + ' and should not be interpreted as official policy endorsed by this\n' + ' organization.

\n' + '
\n' + '
') # C1 + + # Textual inclusion example (XInclude C.2) + document = self.xinclude_loader("C2.xml") + ElementInclude.include(document, self.xinclude_loader) + self.assertEqual(serialize(document), + '\n' + '

This document has been accessed\n' + ' 324387 times.

\n' + '
') # C2 + + # Textual inclusion after sibling element (based on modified XInclude C.2) + document = self.xinclude_loader("C2b.xml") + ElementInclude.include(document, self.xinclude_loader) + self.assertEqual(serialize(document), + '\n' + '

This document has been accessed\n' + ' 324387 times.

\n' + '
') # C2b + + # Textual inclusion of XML example (XInclude C.3) + document = self.xinclude_loader("C3.xml") + ElementInclude.include(document, self.xinclude_loader) + self.assertEqual(serialize(document), + '\n' + '

The following is the source of the "data.xml" resource:

\n' + " <?xml version='1.0'?>\n" + '<data>\n' + ' <item><![CDATA[Brooks & Shields]]></item>\n' + '</data>\n' + '\n' + '
') # C3 + + # Fallback example (XInclude C.5) + # Note! Fallback support is not yet implemented + document = self.xinclude_loader("C5.xml") + with self.assertRaises(OSError) as cm: + ElementInclude.include(document, self.xinclude_loader) + self.assertEqual(str(cm.exception), 'resource not found') + self.assertEqual(serialize(document), + '
\n' + ' \n' + ' \n' + ' \n' + ' Report error\n' + ' \n' + ' \n' + ' \n' + '
') # C5 + + def test_xinclude_failures(self): + from xml.etree import ElementInclude - >>> document = ET.XML(XINCLUDE_BAD["B2.xml"]) - >>> ElementInclude.include(document, loader=none_loader) - Traceback (most recent call last): - xml.etree.ElementInclude.FatalIncludeError: xi:fallback tag must be child of xi:include ('{http://www.w3.org/2001/XInclude}fallback') - """ + # Test failure to locate included XML file. + document = ET.XML(XINCLUDE["C1.xml"]) + with self.assertRaises(ElementInclude.FatalIncludeError) as cm: + ElementInclude.include(document, loader=self.none_loader) + self.assertEqual(str(cm.exception), + "cannot load 'disclaimer.xml' as 'xml'") + + # Test failure to locate included text file. + document = ET.XML(XINCLUDE["C2.xml"]) + with self.assertRaises(ElementInclude.FatalIncludeError) as cm: + ElementInclude.include(document, loader=self.none_loader) + self.assertEqual(str(cm.exception), + "cannot load 'count.txt' as 'text'") + + # Test bad parse type. + document = ET.XML(XINCLUDE_BAD["B1.xml"]) + with self.assertRaises(ElementInclude.FatalIncludeError) as cm: + ElementInclude.include(document, loader=self.none_loader) + self.assertEqual(str(cm.exception), + "unknown parse type in xi:include tag ('BAD_TYPE')") + + # Test xi:fallback outside xi:include. + document = ET.XML(XINCLUDE_BAD["B2.xml"]) + with self.assertRaises(ElementInclude.FatalIncludeError) as cm: + ElementInclude.include(document, loader=self.none_loader) + self.assertEqual(str(cm.exception), + "xi:fallback tag must be child of xi:include " + "('{http://www.w3.org/2001/XInclude}fallback')") # -------------------------------------------------------------------- # reported bugs -def bug_xmltoolkit21(): - """ - - marshaller gives obscure errors for non-string values - - >>> elem = ET.Element(123) - >>> serialize(elem) # tag - Traceback (most recent call last): - TypeError: cannot serialize 123 (type int) - >>> elem = ET.Element("elem") - >>> elem.text = 123 - >>> serialize(elem) # text - Traceback (most recent call last): - TypeError: cannot serialize 123 (type int) - >>> elem = ET.Element("elem") - >>> elem.tail = 123 - >>> serialize(elem) # tail - Traceback (most recent call last): - TypeError: cannot serialize 123 (type int) - >>> elem = ET.Element("elem") - >>> elem.set(123, "123") - >>> serialize(elem) # attribute key - Traceback (most recent call last): - TypeError: cannot serialize 123 (type int) - >>> elem = ET.Element("elem") - >>> elem.set("123", 123) - >>> serialize(elem) # attribute value - Traceback (most recent call last): - TypeError: cannot serialize 123 (type int) - - """ - -def bug_xmltoolkit25(): - """ - - typo in ElementTree.findtext +class BugsTest(unittest.TestCase): - >>> elem = ET.XML(SAMPLE_XML) - >>> tree = ET.ElementTree(elem) - >>> tree.findtext("tag") - 'text' - >>> tree.findtext("section/tag") - 'subtext' + def test_bug_xmltoolkit21(self): + # marshaller gives obscure errors for non-string values - """ + def check(elem): + with self.assertRaises(TypeError) as cm: + serialize(elem) + self.assertEqual(str(cm.exception), + 'cannot serialize 123 (type int)') -def bug_xmltoolkit28(): - """ + elem = ET.Element(123) + check(elem) # tag - .//tag causes exceptions + elem = ET.Element("elem") + elem.text = 123 + check(elem) # text - >>> tree = ET.XML("
") - >>> summarize_list(tree.findall(".//thead")) - [] - >>> summarize_list(tree.findall(".//tbody")) - ['tbody'] + elem = ET.Element("elem") + elem.tail = 123 + check(elem) # tail - """ + elem = ET.Element("elem") + elem.set(123, "123") + check(elem) # attribute key -def bug_xmltoolkitX1(): - """ + elem = ET.Element("elem") + elem.set("123", 123) + check(elem) # attribute value - dump() doesn't flush the output buffer + def test_bug_xmltoolkit25(self): + # typo in ElementTree.findtext - >>> tree = ET.XML("
") - >>> ET.dump(tree); print("tail") -
- tail + elem = ET.XML(SAMPLE_XML) + tree = ET.ElementTree(elem) + self.assertEqual(tree.findtext("tag"), 'text') + self.assertEqual(tree.findtext("section/tag"), 'subtext') - """ + def test_bug_xmltoolkit28(self): + # .//tag causes exceptions -def bug_xmltoolkit39(): - """ + tree = ET.XML("
") + self.assertEqual(summarize_list(tree.findall(".//thead")), []) + self.assertEqual(summarize_list(tree.findall(".//tbody")), ['tbody']) - non-ascii element and attribute names doesn't work + def test_bug_xmltoolkitX1(self): + # dump() doesn't flush the output buffer - >>> tree = ET.XML(b"") - >>> ET.tostring(tree, "utf-8") - b'' + tree = ET.XML("
") + with support.captured_stdout() as stdout: + ET.dump(tree) + self.assertEqual(stdout.getvalue(), '
\n') - >>> tree = ET.XML(b"") - >>> tree.attrib - {'\\xe4ttr': 'v\\xe4lue'} - >>> ET.tostring(tree, "utf-8") - b'' + def test_bug_xmltoolkit39(self): + # non-ascii element and attribute names doesn't work - >>> tree = ET.XML(b"text") - >>> ET.tostring(tree, "utf-8") - b'text' + tree = ET.XML(b"") + self.assertEqual(ET.tostring(tree, "utf-8"), b'') - >>> tree = ET.Element("t\u00e4g") - >>> ET.tostring(tree, "utf-8") - b'' + tree = ET.XML(b"" + b"") + self.assertEqual(tree.attrib, {'\xe4ttr': 'v\xe4lue'}) + self.assertEqual(ET.tostring(tree, "utf-8"), + b'') - >>> tree = ET.Element("tag") - >>> tree.set("\u00e4ttr", "v\u00e4lue") - >>> ET.tostring(tree, "utf-8") - b'' + tree = ET.XML(b"" + b'text') + self.assertEqual(ET.tostring(tree, "utf-8"), + b'text') - """ + tree = ET.Element("t\u00e4g") + self.assertEqual(ET.tostring(tree, "utf-8"), b'') -def bug_xmltoolkit54(): - """ + tree = ET.Element("tag") + tree.set("\u00e4ttr", "v\u00e4lue") + self.assertEqual(ET.tostring(tree, "utf-8"), + b'') - problems handling internally defined entities + def test_bug_xmltoolkit54(self): + # problems handling internally defined entities - >>> e = ET.XML("]>&ldots;") - >>> serialize(e, encoding="us-ascii") - b'' - >>> serialize(e) - '\u8230' + e = ET.XML("]>" + '&ldots;') + self.assertEqual(serialize(e, encoding="us-ascii"), + b'') + self.assertEqual(serialize(e), '\u8230') - """ + def test_bug_xmltoolkit55(self): + # make sure we're reporting the first error, not the last -def bug_xmltoolkit55(): - """ + with self.assertRaises(ET.ParseError) as cm: + ET.XML(b"" + b'&ldots;&ndots;&rdots;') + self.assertEqual(str(cm.exception), + 'undefined entity &ldots;: line 1, column 36') - make sure we're reporting the first error, not the last + def test_bug_xmltoolkit60(self): + # Handle crash in stream source. - >>> normalize_exception(ET.XML, b"&ldots;&ndots;&rdots;") - Traceback (most recent call last): - ParseError: undefined entity &ldots;: line 1, column 36 + class ExceptionFile: + def read(self, x): + raise OSError - """ + self.assertRaises(OSError, ET.parse, ExceptionFile()) -class ExceptionFile: - def read(self, x): - raise OSError + def test_bug_xmltoolkit62(self): + # Don't crash when using custom entities. -def xmltoolkit60(): - """ - - Handle crash in stream source. - >>> tree = ET.parse(ExceptionFile()) - Traceback (most recent call last): - OSError - - """ - -XMLTOOLKIT62_DOC = """ + ENTITIES = {'rsquo': '\u2019', 'lsquo': '\u2018'} + parser = ET.XMLTreeBuilder() + parser.entity.update(ENTITIES) + parser.feed(""" A new cultivar of Begonia plant named ‘BCT9801BEG’. -""" - - -def xmltoolkit62(): - """ - - Don't crash when using custom entities. - - >>> xmltoolkit62() - 'A new cultivar of Begonia plant named \u2018BCT9801BEG\u2019.' - - """ - ENTITIES = {'rsquo': '\u2019', 'lsquo': '\u2018'} - parser = ET.XMLTreeBuilder() - parser.entity.update(ENTITIES) - parser.feed(XMLTOOLKIT62_DOC) - t = parser.close() - return t.find('.//paragraph').text - -def xmltoolkit63(): - """ - - Check reference leak. - >>> xmltoolkit63() - >>> count = sys.getrefcount(None) - >>> for i in range(1000): - ... xmltoolkit63() - >>> sys.getrefcount(None) - count - 0 - - """ - tree = ET.TreeBuilder() - tree.start("tag", {}) - tree.data("text") - tree.end("tag") - -# -------------------------------------------------------------------- - - -def bug_200708_newline(): - r""" - - Preserve newlines in attributes. - - >>> e = ET.Element('SomeTag', text="def _f():\n return 3\n") - >>> ET.tostring(e) - b'' - >>> ET.XML(ET.tostring(e)).get("text") - 'def _f():\n return 3\n' - >>> ET.tostring(ET.XML(ET.tostring(e))) - b'' - - """ - -def bug_200708_close(): - """ - - Test default builder. - >>> parser = ET.XMLParser() # default - >>> parser.feed("some text") - >>> summarize(parser.close()) - 'element' - - Test custom builder. - >>> class EchoTarget: - ... def close(self): - ... return ET.Element("element") # simulate root - >>> parser = ET.XMLParser(EchoTarget()) - >>> parser.feed("some text") - >>> summarize(parser.close()) - 'element' - - """ - -def bug_200709_default_namespace(): - """ - - >>> e = ET.Element("{default}elem") - >>> s = ET.SubElement(e, "{default}elem") - >>> serialize(e, default_namespace="default") # 1 - '' - - >>> e = ET.Element("{default}elem") - >>> s = ET.SubElement(e, "{default}elem") - >>> s = ET.SubElement(e, "{not-default}elem") - >>> serialize(e, default_namespace="default") # 2 - '' - - >>> e = ET.Element("{default}elem") - >>> s = ET.SubElement(e, "{default}elem") - >>> s = ET.SubElement(e, "elem") # unprefixed name - >>> serialize(e, default_namespace="default") # 3 - Traceback (most recent call last): - ValueError: cannot use non-qualified names with default_namespace option - - """ - -def bug_200709_register_namespace(): - """ - - >>> ET.tostring(ET.Element("{http://namespace.invalid/does/not/exist/}title")) - b'' - >>> ET.register_namespace("foo", "http://namespace.invalid/does/not/exist/") - >>> ET.tostring(ET.Element("{http://namespace.invalid/does/not/exist/}title")) - b'' - - And the Dublin Core namespace is in the default list: - - >>> ET.tostring(ET.Element("{http://purl.org/dc/elements/1.1/}title")) - b'' - - """ - -def bug_200709_element_comment(): - """ - - Not sure if this can be fixed, really (since the serializer needs - ET.Comment, not cET.comment). - - >>> a = ET.Element('a') - >>> a.append(ET.Comment('foo')) - >>> a[0].tag == ET.Comment - True - - >>> a = ET.Element('a') - >>> a.append(ET.PI('foo')) - >>> a[0].tag == ET.PI - True - - """ - -def bug_200709_element_insert(): - """ - - >>> a = ET.Element('a') - >>> b = ET.SubElement(a, 'b') - >>> c = ET.SubElement(a, 'c') - >>> d = ET.Element('d') - >>> a.insert(0, d) - >>> summarize_list(a) - ['d', 'b', 'c'] - >>> a.insert(-1, d) - >>> summarize_list(a) - ['d', 'b', 'd', 'c'] - - """ - -def bug_200709_iter_comment(): - """ - - >>> a = ET.Element('a') - >>> b = ET.SubElement(a, 'b') - >>> comment_b = ET.Comment("TEST-b") - >>> b.append(comment_b) - >>> summarize_list(a.iter(ET.Comment)) - [''] - - """ - -# -------------------------------------------------------------------- -# reported on bugs.python.org - -def bug_1534630(): - """ - - >>> bob = ET.TreeBuilder() - >>> e = bob.data("data") - >>> e = bob.start("tag", {}) - >>> e = bob.end("tag") - >>> e = bob.close() - >>> serialize(e) - '' - - """ - -def check_issue6233(): - """ - - >>> e = ET.XML(b"t\\xc3\\xa3g") - >>> ET.tostring(e, 'ascii') - b"\\ntãg" - >>> e = ET.XML(b"t\\xe3g") - >>> ET.tostring(e, 'ascii') - b"\\ntãg" - - """ - -def check_issue3151(): - """ - - >>> e = ET.XML('') - >>> e.tag - '{${stuff}}localname' - >>> t = ET.ElementTree(e) - >>> ET.tostring(e) - b'' - - """ - -def check_issue6565(): - """ - - >>> elem = ET.XML("") - >>> summarize_list(elem) - ['tag'] - >>> newelem = ET.XML(SAMPLE_XML) - >>> elem[:] = newelem[:] - >>> summarize_list(elem) - ['tag', 'tag', 'section'] +""") + t = parser.close() + self.assertEqual(t.find('.//paragraph').text, + 'A new cultivar of Begonia plant named \u2018BCT9801BEG\u2019.') + + def test_bug_xmltoolkit63(self): + # Check reference leak. + def xmltoolkit63(): + tree = ET.TreeBuilder() + tree.start("tag", {}) + tree.data("text") + tree.end("tag") + + xmltoolkit63() + count = sys.getrefcount(None) + for i in range(1000): + xmltoolkit63() + self.assertEqual(sys.getrefcount(None), count) + + def test_bug_200708_newline(self): + # Preserve newlines in attributes. + + e = ET.Element('SomeTag', text="def _f():\n return 3\n") + self.assertEqual(ET.tostring(e), + b'') + self.assertEqual(ET.XML(ET.tostring(e)).get("text"), + 'def _f():\n return 3\n') + self.assertEqual(ET.tostring(ET.XML(ET.tostring(e))), + b'') + + def test_bug_200708_close(self): + # Test default builder. + parser = ET.XMLParser() # default + parser.feed("some text") + self.assertEqual(parser.close().tag, 'element') + + # Test custom builder. + class EchoTarget: + def close(self): + return ET.Element("element") # simulate root + parser = ET.XMLParser(EchoTarget()) + parser.feed("some text") + self.assertEqual(parser.close().tag, 'element') + + def test_bug_200709_default_namespace(self): + e = ET.Element("{default}elem") + s = ET.SubElement(e, "{default}elem") + self.assertEqual(serialize(e, default_namespace="default"), # 1 + '') + + e = ET.Element("{default}elem") + s = ET.SubElement(e, "{default}elem") + s = ET.SubElement(e, "{not-default}elem") + self.assertEqual(serialize(e, default_namespace="default"), # 2 + '' + '' + '' + '') + + e = ET.Element("{default}elem") + s = ET.SubElement(e, "{default}elem") + s = ET.SubElement(e, "elem") # unprefixed name + with self.assertRaises(ValueError) as cm: + serialize(e, default_namespace="default") # 3 + self.assertEqual(str(cm.exception), + 'cannot use non-qualified names with default_namespace option') + + def test_bug_200709_register_namespace(self): + e = ET.Element("{http://namespace.invalid/does/not/exist/}title") + self.assertEqual(ET.tostring(e), + b'') + ET.register_namespace("foo", "http://namespace.invalid/does/not/exist/") + e = ET.Element("{http://namespace.invalid/does/not/exist/}title") + self.assertEqual(ET.tostring(e), + b'') + + # And the Dublin Core namespace is in the default list: + + e = ET.Element("{http://purl.org/dc/elements/1.1/}title") + self.assertEqual(ET.tostring(e), + b'') + + def test_bug_200709_element_comment(self): + # Not sure if this can be fixed, really (since the serializer needs + # ET.Comment, not cET.comment). - """ + a = ET.Element('a') + a.append(ET.Comment('foo')) + self.assertEqual(a[0].tag, ET.Comment) -def check_issue10777(): - """ - Registering a namespace twice caused a "dictionary changed size during - iteration" bug. + a = ET.Element('a') + a.append(ET.PI('foo')) + self.assertEqual(a[0].tag, ET.PI) - >>> ET.register_namespace('test10777', 'http://myuri/') - >>> ET.register_namespace('test10777', 'http://myuri/') - """ + def test_bug_200709_element_insert(self): + a = ET.Element('a') + b = ET.SubElement(a, 'b') + c = ET.SubElement(a, 'c') + d = ET.Element('d') + a.insert(0, d) + self.assertEqual(summarize_list(a), ['d', 'b', 'c']) + a.insert(-1, d) + self.assertEqual(summarize_list(a), ['d', 'b', 'd', 'c']) + + def test_bug_200709_iter_comment(self): + a = ET.Element('a') + b = ET.SubElement(a, 'b') + comment_b = ET.Comment("TEST-b") + b.append(comment_b) + self.assertEqual(summarize_list(a.iter(ET.Comment)), [ET.Comment]) + + # -------------------------------------------------------------------- + # reported on bugs.python.org + + def test_bug_1534630(self): + bob = ET.TreeBuilder() + e = bob.data("data") + e = bob.start("tag", {}) + e = bob.end("tag") + e = bob.close() + self.assertEqual(serialize(e), '') + + def test_issue6233(self): + e = ET.XML(b"" + b't\xc3\xa3g') + self.assertEqual(ET.tostring(e, 'ascii'), + b"\n" + b'tãg') + e = ET.XML(b"" + b't\xe3g') + self.assertEqual(ET.tostring(e, 'ascii'), + b"\n" + b'tãg') + + def test_issue3151(self): + e = ET.XML('') + self.assertEqual(e.tag, '{${stuff}}localname') + t = ET.ElementTree(e) + self.assertEqual(ET.tostring(e), b'') + + def test_issue6565(self): + elem = ET.XML("") + self.assertEqual(summarize_list(elem), ['tag']) + newelem = ET.XML(SAMPLE_XML) + elem[:] = newelem[:] + self.assertEqual(summarize_list(elem), ['tag', 'tag', 'section']) + + def test_issue10777(self): + # Registering a namespace twice caused a "dictionary changed size during + # iteration" bug. + + ET.register_namespace('test10777', 'http://myuri/') + ET.register_namespace('test10777', 'http://myuri/') # -------------------------------------------------------------------- @@ -1698,7 +1493,7 @@ class BasicElementTest(ElementTestCase, unittest.TestCase): self.assertEqual(len(e2), 2) self.assertEqualElements(e, e2) -class ElementTreeTest(unittest.TestCase): +class ElementTreeTypeTest(unittest.TestCase): def test_istype(self): self.assertIsInstance(ET.ParseError, type) self.assertIsInstance(ET.QName, type) @@ -1738,19 +1533,6 @@ class ElementTreeTest(unittest.TestCase): mye = MyElement('joe') self.assertEqual(mye.newmethod(), 'joe') - def test_html_empty_elems_serialization(self): - # issue 15970 - # from http://www.w3.org/TR/html401/index/elements.html - for element in ['AREA', 'BASE', 'BASEFONT', 'BR', 'COL', 'FRAME', 'HR', - 'IMG', 'INPUT', 'ISINDEX', 'LINK', 'META', 'PARAM']: - for elem in [element, element.lower()]: - expected = '<%s>' % elem - serialized = serialize(ET.XML('<%s />' % elem), method='html') - self.assertEqual(serialized, expected) - serialized = serialize(ET.XML('<%s>' % (elem,elem)), - method='html') - self.assertEqual(serialized, expected) - class ElementFindTest(unittest.TestCase): def test_find_simple(self): @@ -2059,31 +1841,6 @@ class TreeBuilderTest(unittest.TestCase): 'http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd')) -class XincludeTest(unittest.TestCase): - def _my_loader(self, href, parse): - # Used to avoid a test-dependency problem where the default loader - # of ElementInclude uses the pyET parser for cET tests. - if parse == 'xml': - with open(href, 'rb') as f: - return ET.parse(f).getroot() - else: - return None - - def test_xinclude_default(self): - from xml.etree import ElementInclude - doc = xinclude_loader('default.xml') - ElementInclude.include(doc, self._my_loader) - s = serialize(doc) - self.assertEqual(s.strip(), ''' -

Example.

- - text - texttail - - -
''') - - class XMLParserTest(unittest.TestCase): sample1 = '22' sample2 = ('