Python xml.dom.minidom.parseString() Examples

def _write_pretty_result_xml_to_file(self, xml, filename):
        """Writes a nicely formatted XML file with DOCTYPE, and compressed if necessary."""
        if self.compress_results:
            actual_filename = filename + ".bz2"
            open_func = bz2.BZ2File
        else:
            # write content to temp file first to prevent losing data
            # in existing file if writing fails
            actual_filename = filename + ".tmp"
            open_func = open

        with io.TextIOWrapper(
            open_func(actual_filename, "wb"), encoding="utf-8"
        ) as file:
            rough_string = ElementTree.tostring(xml, encoding="unicode")
            reparsed = minidom.parseString(rough_string)
            doctype = minidom.DOMImplementation().createDocumentType(
                "result", RESULT_XML_PUBLIC_ID, RESULT_XML_SYSTEM_ID
            )
            reparsed.insertBefore(doctype, reparsed.documentElement)
            reparsed.writexml(
                file, indent="", addindent="  ", newl="\n", encoding="utf-8"
            )

        if self.compress_results:
            # try to delete uncompressed file (would have been overwritten in no-compress-mode)
            try:
                os.remove(filename)
            except OSError:
                pass
            self.all_created_files.discard(filename)
            self.all_created_files.add(actual_filename)
        else:
            os.rename(actual_filename, filename)
            self.all_created_files.add(filename)

        return filename 

def test_xpath_from_xml_node(self):
        xml_str = '<?xml version=\'1.0\' ?><test_item_name_matches_repeat ' \
                  'id="repeat_child_name_matches_repeat">' \
                  '<formhub><uuid>c911d71ce1ac48478e5f8bac99addc4e</uuid>' \
                  '</formhub><gps><gps>-1.2625149 36.7924478 0.0 30.0</gps>' \
                  '<info>Yo</info></gps><gps>' \
                  '<gps>-1.2625072 36.7924328 0.0 30.0</gps>' \
                  '<info>What</info></gps></test_item_name_matches_repeat>'
        clean_xml_str = xml_str.strip()
        clean_xml_str = re.sub(ur">\s+<", u"><", clean_xml_str)
        root_node = minidom.parseString(clean_xml_str).documentElement
        # get the first top-level gps element
        gps_node = root_node.firstChild.nextSibling
        self.assertEqual(gps_node.nodeName, u'gps')
        # get the info element within the gps element
        info_node = gps_node.getElementsByTagName(u'info')[0]
        # create an xpath that should look like gps/info
        xpath = xpath_from_xml_node(info_node)
        self.assertEqual(xpath, u'gps/info') 

def testNormalizeDeleteAndCombine(self):
        doc = parseString("<doc/>")
        root = doc.documentElement
        root.appendChild(doc.createTextNode(""))
        root.appendChild(doc.createTextNode("second"))
        root.appendChild(doc.createTextNode(""))
        root.appendChild(doc.createTextNode("fourth"))
        root.appendChild(doc.createTextNode(""))
        self.confirm(len(root.childNodes) == 5
                and root.childNodes.length == 5,
                "testNormalizeDeleteAndCombine -- preparation")
        doc.normalize()
        self.confirm(len(root.childNodes) == 1
                and root.childNodes.length == 1
                and root.firstChild is root.lastChild
                and root.firstChild.data == "secondfourth"
                and root.firstChild.previousSibling is None
                and root.firstChild.nextSibling is None
                , "testNormalizeDeleteAndCombine -- result")
        doc.unlink() 

def parse_xform_instance(xml_str):
    """
    'xml_str' is a str object holding the XML of an XForm
    instance. Return a python object representation of this XML file.
    """
    xml_obj = minidom.parseString(xml_str)
    root_node = xml_obj.documentElement
    # go through the xml object creating a corresponding python object
    # NOTE: THIS WILL DESTROY ANY DATA COLLECTED WITH REPEATABLE NODES
    # THIS IS OKAY FOR OUR USE CASE, BUT OTHER USERS SHOULD BEWARE.
    survey_data = dict(_path_value_pairs(root_node))
    assert len(list(_all_attributes(root_node))) == 1, \
        _(u"There should be exactly one attribute in this document.")
    survey_data.update({
        common_tags.XFORM_ID_STRING: root_node.getAttribute(u"id"),
        common_tags.INSTANCE_DOC_NAME: root_node.nodeName,
    })
    return survey_data 

def testAltNewline(self):
        str = '<?xml version="1.0" ?>\n<a b="c"/>\n'
        dom = parseString(str)
        domstr = dom.toprettyxml(newl="\r\n")
        dom.unlink()
        self.confirm(domstr == str.replace("\n", "\r\n")) 

def get_xml_string(self, tree):
        xml = self.visit(tree)

        ast = ElementTree.Element("ast")
        doc = ElementTree.SubElement(ast, "doc")
        doc.append(xml)

        return minidom.parseString(ElementTree.tostring(doc)).toprettyxml(indent="   ") 

def testWholeText(self):
        doc = parseString("<doc>a</doc>")
        elem = doc.documentElement
        text = elem.childNodes[0]
        self.assertEqual(text.nodeType, Node.TEXT_NODE)

        self.checkWholeText(text, "a")
        elem.appendChild(doc.createTextNode("b"))
        self.checkWholeText(text, "ab")
        elem.insertBefore(doc.createCDATASection("c"), text)
        self.checkWholeText(text, "cab")

        # make sure we don't cross other nodes
        splitter = doc.createComment("comment")
        elem.appendChild(splitter)
        text2 = doc.createTextNode("d")
        elem.appendChild(text2)
        self.checkWholeText(text, "cab")
        self.checkWholeText(text2, "d")

        x = doc.createElement("x")
        elem.replaceChild(x, splitter)
        splitter = x
        self.checkWholeText(text, "cab")
        self.checkWholeText(text2, "d")

        x = doc.createProcessingInstruction("y", "z")
        elem.replaceChild(x, splitter)
        splitter = x
        self.checkWholeText(text, "cab")
        self.checkWholeText(text2, "d")

        elem.removeChild(splitter)
        self.checkWholeText(text, "cabd")
        self.checkWholeText(text2, "cabd") 

def testPatch1094164(self):
        doc = parseString("<doc><e/></doc>")
        elem = doc.documentElement
        e = elem.firstChild
        self.confirm(e.parentNode is elem, "Before replaceChild()")
        # Check that replacing a child with itself leaves the tree unchanged
        elem.replaceChild(e, e)
        self.confirm(e.parentNode is elem, "After replaceChild()") 

def get_xform_root_node_name(xform):
    parsed = minidom.parseString(xform.xml.encode('utf-8'))
    instance_xml = parsed.getElementsByTagName('instance')[0]
    root_node_name = None
    for child in instance_xml.childNodes:
        if child.nodeType == child.ELEMENT_NODE:
            root_node_name = child.nodeName
            break
    return root_node_name 

def prettify(self, elem):
        """Return a pretty-printed XML string for the Element.
        """
        rough_string = ElementTree.tostring(elem, encoding='UTF-8')
        reparsed = minidom.parseString(rough_string)
        return reparsed.toprettyxml(indent="  ")

    # object xml content -> field map 

def prettify_xml(xml: Union[str, etree._Element]) -> str:
    if isinstance(xml, etree._Element):
        result = etree.tostring(xml, pretty_print=True).decode("utf-8")
    else:
        result = parseString(xml).toprettyxml("  ")
    return result 

def testParents(self):
        doc = parseString(
            "<doc><elm1><elm2/><elm2><elm3/></elm2></elm1></doc>")
        root = doc.documentElement
        elm1 = root.childNodes[0]
        (elm2a, elm2b) = elm1.childNodes
        elm3 = elm2b.childNodes[0]

        self.confirm(root.parentNode is doc and
                elm1.parentNode is root and
                elm2a.parentNode is elm1 and
                elm2b.parentNode is elm1 and
                elm3.parentNode is elm2b, "testParents")
        doc.unlink() 

def _download_xform(self):
        client = DigestClient()
        client.set_authorization('bob', 'bob')
        response = client.get(self.download_url)
        response_doc = minidom.parseString(response.content)

        xml_path = os.path.join(self.this_directory, "fixtures",
                                "transportation", "transportation.xml")
        with open(xml_path) as xml_file:
            expected_doc = minidom.parse(xml_file)

        model_node = [
            n for n in
            response_doc.getElementsByTagName("h:head")[0].childNodes
            if n.nodeType == Node.ELEMENT_NODE and
            n.tagName == "model"][0]

        # check for UUID and remove
        uuid_nodes = [node for node in model_node.childNodes
                      if node.nodeType == Node.ELEMENT_NODE and
                      node.getAttribute("nodeset") ==
                      "/transportation/formhub/uuid"]
        self.assertEqual(len(uuid_nodes), 1)
        uuid_node = uuid_nodes[0]
        uuid_node.setAttribute("calculate", "''")

        # check content without UUID
        self.assertEqual(response_doc.toxml(), expected_doc.toxml()) 

def xmlRequest(url, data=None, headers={}, method='GET', contentType='application/json', timeout=None):
    logging.debug('%sing url %s', method, url)
    response = openRequest(buildRequest(url, data, headers, method, contentType), timeout=timeout).read()
    return xmlTransform(minidom.parseString(response).documentElement) 

def prettify(elem):
    """
    Return a pretty-printed XML string for the Element.
    """
    rough_string = ElementTree.tostring(elem, 'utf-8')
    reparsed = minidom.parseString(rough_string)
    return reparsed.toprettyxml(indent="    ") 

def prettify(elem):
    """Return a pretty-printed XML string for the Element.
    """
    rough_string = ET.tostring(elem)
    reparsed = minidom.parseString(rough_string)
    prettyxml = reparsed.documentElement.toprettyxml(indent=" ")
    return prettyxml.encode("utf-8")

################### 

def create_manifest(self):
        if WhichElementTree == 'lxml':
            root = Element('manifest:manifest',
                nsmap=MANIFEST_NAMESPACE_DICT,
                nsdict=MANIFEST_NAMESPACE_DICT,
                )
        else:
            root = Element('manifest:manifest',
                attrib=MANIFEST_NAMESPACE_ATTRIB,
                nsdict=MANIFEST_NAMESPACE_DICT,
                )
        doc = etree.ElementTree(root)
        SubElement(root, 'manifest:file-entry', attrib={
            'manifest:media-type': self.MIME_TYPE,
            'manifest:full-path': '/',
            }, nsdict=MANNSD)
        SubElement(root, 'manifest:file-entry', attrib={
            'manifest:media-type': 'text/xml',
            'manifest:full-path': 'content.xml',
            }, nsdict=MANNSD)
        SubElement(root, 'manifest:file-entry', attrib={
            'manifest:media-type': 'text/xml',
            'manifest:full-path': 'styles.xml',
            }, nsdict=MANNSD)
        SubElement(root, 'manifest:file-entry', attrib={
            'manifest:media-type': 'text/xml',
            'manifest:full-path': 'settings.xml',
            }, nsdict=MANNSD)
        SubElement(root, 'manifest:file-entry', attrib={
            'manifest:media-type': 'text/xml',
            'manifest:full-path': 'meta.xml',
            }, nsdict=MANNSD)
        s1 = ToString(doc)
        doc = minidom.parseString(s1)
        s1 = doc.toprettyxml('  ')
        return s1 

def testEncodings(self):
        doc = parseString('<foo>&#x20ac;</foo>')
        self.confirm(doc.toxml() == u'<?xml version="1.0" ?><foo>\u20ac</foo>'
                and doc.toxml('utf-8') ==
                '<?xml version="1.0" encoding="utf-8"?><foo>\xe2\x82\xac</foo>'
                and doc.toxml('iso-8859-15') ==
                '<?xml version="1.0" encoding="iso-8859-15"?><foo>\xa4</foo>',
                "testEncodings - encoding EURO SIGN")

        # Verify that character decoding errors raise exceptions instead
        # of crashing
        self.assertRaises(UnicodeDecodeError, parseString,
                '<fran\xe7ais>Comment \xe7a va ? Tr\xe8s bien ?</fran\xe7ais>')

        doc.unlink() 

def testNodeListItem(self):
        doc = parseString("<doc><e/><e/></doc>")
        children = doc.childNodes
        docelem = children[0]
        self.confirm(children[0] is children.item(0)
                and children.item(1) is None
                and docelem.childNodes.item(0) is docelem.childNodes[0]
                and docelem.childNodes.item(1) is docelem.childNodes[1]
                and docelem.childNodes.item(0).childNodes.item(0) is None,
                "test NodeList.item()")
        doc.unlink() 

def testCloneDocumentShallow(self):
        doc = parseString("<?xml version='1.0'?>\n"
                    "<!-- comment -->"
                    "<!DOCTYPE doc [\n"
                    "<!NOTATION notation SYSTEM 'http://xml.python.org/'>\n"
                    "]>\n"
                    "<doc attr='value'/>")
        doc2 = doc.cloneNode(0)
        self.confirm(doc2 is None,
                "testCloneDocumentShallow:"
                " shallow cloning of documents makes no sense!") 

def testSiblings(self):
        doc = parseString("<doc><?pi?>text?<elm/></doc>")
        root = doc.documentElement
        (pi, text, elm) = root.childNodes

        self.confirm(pi.nextSibling is text and
                pi.previousSibling is None and
                text.nextSibling is elm and
                text.previousSibling is pi and
                elm.nextSibling is None and
                elm.previousSibling is text, "testSiblings")

        doc.unlink() 

def testBug1433694(self):
        doc = parseString("<o><i/>t</o>")
        node = doc.documentElement
        node.childNodes[1].nodeValue = ""
        node.normalize()
        self.confirm(node.childNodes[-1].nextSibling is None,
                     "Final child's .nextSibling should be None") 

def testNormalizeDeleteWithTwoNonTextSiblings(self):
        doc = parseString("<doc/>")
        root = doc.documentElement
        root.appendChild(doc.createElement("i"))
        root.appendChild(doc.createTextNode(""))
        root.appendChild(doc.createElement("i"))
        self.confirm(len(root.childNodes) == 3
                and root.childNodes.length == 3,
                "testNormalizeDeleteWithTwoSiblings -- preparation")
        doc.normalize()
        self.confirm(len(root.childNodes) == 2
                and root.childNodes.length == 2
                and root.firstChild is not root.lastChild
                and root.firstChild.nextSibling is root.lastChild
                and root.firstChild.previousSibling is None
                and root.lastChild.previousSibling is root.firstChild
                and root.lastChild.nextSibling is None
                , "testNormalizeDeleteWithTwoSiblings -- result")
        doc.unlink() 

def testNormalizeDeleteWithNextSibling(self):
        doc = parseString("<doc/>")
        root = doc.documentElement
        root.appendChild(doc.createTextNode(""))
        root.appendChild(doc.createTextNode("second"))
        self.confirm(len(root.childNodes) == 2
                and root.childNodes.length == 2,
                "testNormalizeDeleteWithNextSibling -- preparation")
        doc.normalize()
        self.confirm(len(root.childNodes) == 1
                and root.childNodes.length == 1
                and root.firstChild.data == "second"
                and root.firstChild is root.lastChild
                and root.firstChild.nextSibling is None
                and root.firstChild.previousSibling is None
                , "testNormalizeDeleteWithNextSibling -- result")
        doc.unlink() 

def testNormalizeDeleteWithPrevSibling(self):
        doc = parseString("<doc/>")
        root = doc.documentElement
        root.appendChild(doc.createTextNode("first"))
        root.appendChild(doc.createTextNode(""))
        self.confirm(len(root.childNodes) == 2
                and root.childNodes.length == 2,
                "testNormalizeDeleteWithPrevSibling -- preparation")
        doc.normalize()
        self.confirm(len(root.childNodes) == 1
                and root.childNodes.length == 1
                and root.firstChild.data == "first"
                and root.firstChild is root.lastChild
                and root.firstChild.nextSibling is None
                and root.firstChild.previousSibling is None
                , "testNormalizeDeleteWithPrevSibling -- result")
        doc.unlink() 

def testNormalize(self):
        doc = parseString("<doc/>")
        root = doc.documentElement
        root.appendChild(doc.createTextNode("first"))
        root.appendChild(doc.createTextNode("second"))
        self.confirm(len(root.childNodes) == 2
                and root.childNodes.length == 2,
                "testNormalize -- preparation")
        doc.normalize()
        self.confirm(len(root.childNodes) == 1
                and root.childNodes.length == 1
                and root.firstChild is root.lastChild
                and root.firstChild.data == "firstsecond"
                , "testNormalize -- result")
        doc.unlink()

        doc = parseString("<doc/>")
        root = doc.documentElement
        root.appendChild(doc.createTextNode(""))
        doc.normalize()
        self.confirm(len(root.childNodes) == 0
                and root.childNodes.length == 0,
                "testNormalize -- single empty node removed")
        doc.unlink() 

def check_clone_pi(self, deep, testName):
        doc = parseString("<?target data?><doc/>")
        pi = doc.firstChild
        self.assertEqual(pi.nodeType, Node.PROCESSING_INSTRUCTION_NODE)
        clone = pi.cloneNode(deep)
        self.confirm(clone.target == pi.target
                and clone.data == pi.data) 

def check_clone_attribute(self, deep, testName):
        doc = parseString("<doc attr='value'/>")
        attr = doc.documentElement.getAttributeNode("attr")
        self.assertNotEqual(attr, None)
        clone = attr.cloneNode(deep)
        self.confirm(not clone.isSameNode(attr))
        self.confirm(not attr.isSameNode(clone))
        self.confirm(clone.ownerElement is None,
                testName + ": ownerElement should be None")
        self.confirm(clone.ownerDocument.isSameNode(attr.ownerDocument),
                testName + ": ownerDocument does not match")
        self.confirm(clone.specified,
                testName + ": cloned attribute must have specified == True") 

def save(self, name, settings=None):
        writer = GXXmlWriter()
        objects = ET.Element("Objects")
        for it in self:
            node = ET.SubElement(objects, "GXDLMS" + GXDLMSConverter.objectTypeToString(it.objectType))
            if it.shortName != 0:
                ET.SubElement(node, "SN").text = str(it.shortName)
            ET.SubElement(node, "LN").text = it.logicalName
            if it.version != 0:
                ET.SubElement(node, "Version").text = str(it.version)
            if it.description:
                ET.SubElement(node, "Description").text = it.description
            if not settings or settings.values:
                writer.objects = []
                writer.objects.append(node)
                it.save(writer)
        str_ = minidom.parseString(ET.tostring(objects, encoding='utf-8', method='xml')).toprettyxml(indent="  ")
        with open(name, "w") as f:
            f.write(str_) 

def check_import_document(self, deep, testName):
        doc1 = parseString("<doc/>")
        doc2 = parseString("<doc/>")
        self.assertRaises(xml.dom.NotSupportedErr, doc1.importNode, doc2, deep)