Python Examples of xml.etree.ElementTree.ElementTree

Source File: e2m3u2bouquet.py From e2m3u2bouquet with GNU General Public License v3.0

6 votes

def parse_map_xmltvsources_xml(self):
        """Check for a mapping override file and parses it if found
        """
        self._xmltv_sources_list = {}
        mapping_file = self._get_mapping_file()
        if mapping_file:
            try:
                tree = ET.ElementTree(file=mapping_file)
                for group in tree.findall('.//xmltvextrasources/group'):
                    group_name = group.attrib.get('id')
                    urllist = []
                    for url in group:
                        urllist.append(url.text)
                    self._xmltv_sources_list[group_name] = urllist
            except Exception, e:
                msg = 'Corrupt override.xml file'
                print(msg)
                if DEBUG:
                    raise msg

Source File: dspl_model_loader.py From dspl with BSD 3-Clause "New" or "Revised" License

6 votes

def ElementsToAttributes(concept_element):
  """Process the attributes in an an ElementTree concept element.

  Args:
    concept_element: An ElementTree concept element

  Returns:
    A list of dspl_model.Attribute instances, populated with the data from the
    argument concept element.
  """
  attribute_elements = concept_element.findall(
      _DSPL_SCHEMA_PREFIX + 'attribute')

  dspl_attributes = []

  for attribute_element in attribute_elements:
    attribute_concept = attribute_element.get('concept')

    # For now, only handle attributes with a concept reference
    if attribute_concept:
      dspl_attributes.append(
          dspl_model.Attribute(attribute_concept, _GetValue(attribute_element)))

  return dspl_attributes

Source File: parsers.py From sota-extractor with Apache License 2.0

6 votes

def _unwind(cls, el: ElementTree, keep_links) -> "Text":
        start = el.text or ""
        if el.tag == "a":
            links = [Link(title=el.text, url=el.attrib.get("href", None))]
        else:
            links = []

        children = ""
        for child in el:
            t = cls._unwind(child, keep_links=keep_links)
            children += t.text
            links.extend(t.links)

        end = el.tail or ""

        if el.tag == "a" and keep_links:
            return cls(
                text=f"[{start}]({el.attrib.get('href', '')}){children}{end}",
                links=links,
            )
        return cls(text=start + children + end, links=links)

Source File: parsers.py From sota-extractor with Apache License 2.0

6 votes

def parse_subdatasets(
    parent: Dataset, pairs: List[Tuple[ElementTree, ElementTree]]
) -> List[Dataset]:
    subdatasets = []
    for p, table in pairs:
        strong = p.find("strong")
        if strong is None:
            continue
        subdatasets.append(
            Dataset(
                name=strong.text.strip().strip(":"),
                is_subdataset=True,
                parent=parent,
                sota=parse_sota(table),
            )
        )
    return subdatasets

Source File: test_xml_etree.py From BinderFilter with MIT License

6 votes

def parseliteral():
    """
    >>> element = ET.XML("<html><body>text</body></html>")
    >>> ET.ElementTree(element).write(sys.stdout)
    <html><body>text</body></html>
    >>> element = ET.fromstring("<html><body>text</body></html>")
    >>> ET.ElementTree(element).write(sys.stdout)
    <html><body>text</body></html>
    >>> sequence = ["<html><body>", "text</bo", "dy></html>"]
    >>> element = ET.fromstringlist(sequence)
    >>> print ET.tostring(element)
    <html><body>text</body></html>
    >>> print "".join(ET.tostringlist(element))
    <html><body>text</body></html>
    >>> ET.tostring(element, "ascii")
    "<?xml version='1.0' encoding='ascii'?>\\n<html><body>text</body></html>"
    >>> _, ids = ET.XMLID("<html><body>text</body></html>")
    >>> len(ids)
    0
    >>> _, ids = ET.XMLID("<html><body id='body'>text</body></html>")
    >>> len(ids)
    1
    >>> ids["body"].tag
    'body'
    """

Source File: test_xml_etree.py From BinderFilter with MIT License

6 votes

def file_init():
    """
    >>> import StringIO

    >>> stringfile = StringIO.StringIO(SAMPLE_XML)
    >>> 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'
    """

Source File: dspl_model_loader.py From dspl with BSD 3-Clause "New" or "Revised" License

6 votes

def _GetValue(parent_element):
  """Get the text nested inside an XML element's value element.

  Args:
    parent_element: An ElementTree element

  Returns:
    String inside value tag inside parent or, if no such tag can be found, None
  """
  if parent_element is not None:
    value_element = parent_element.find(_DSPL_SCHEMA_PREFIX + 'value')

    if value_element is not None:
      return value_element.text

  return ''

Source File: __init__.py From benchexec with Apache License 2.0

6 votes

def parse_table_definition_file(file):
    """
    Read an parse the XML of a table-definition file.
    @return: an ElementTree object for the table definition
    """
    logging.info("Reading table definition from '%s'...", file)
    if not os.path.isfile(file):
        handle_error("File '%s' does not exist.", file)

    try:
        tableGenFile = ElementTree.ElementTree().parse(file)
    except OSError as e:
        handle_error("Could not read result file %s: %s", file, e)
    except ElementTree.ParseError as e:
        handle_error("Table file %s is invalid: %s", file, e)
    if "table" != tableGenFile.tag:
        handle_error(
            "Table file %s is invalid: It's root element is not named 'table'.", file
        )
    return tableGenFile

Source File: dspl_model_loader.py From dspl with BSD 3-Clause "New" or "Revised" License

6 votes

def _NSParser(input_file):
  """A special ElementTree parser that gets all the imported namespaces.

  Args:
    input_file: A file-like object containing XML

  Returns:
    A list with two elements: the root of the ElementTree, and a list of
    namespace strings imported by the XML file.
  """
  events = ('start', 'start-ns')

  root = None
  namespace_list = []

  for event, element in xml.etree.ElementTree.iterparse(input_file, events):
    if event == 'start-ns':
      namespace_list.append(element)
    elif event == 'start':
      if root is None:
        root = element

  return [xml.etree.ElementTree.ElementTree(root), namespace_list]

Source File: outputhandler.py From benchexec with Apache License 2.0

6 votes

def store_header_in_xml(self, version, memlimit, timelimit, corelimit):

        # store benchmarkInfo in XML
        self.xml_header = ElementTree.Element(
            "result",
            benchmarkname=self.benchmark.name,
            date=self.benchmark.start_time.strftime("%Y-%m-%d %H:%M:%S %Z"),
            starttime=self.benchmark.start_time.isoformat(),
            tool=self.benchmark.tool_name,
            version=version,
            toolmodule=self.benchmark.tool_module,
            generator="BenchExec " + benchexec.__version__,
        )
        if self.benchmark.display_name:
            self.xml_header.set("displayName", self.benchmark.display_name)

        if memlimit is not None:
            self.xml_header.set(MEMLIMIT, memlimit)
        if timelimit is not None:
            self.xml_header.set(TIMELIMIT, timelimit)
        if corelimit is not None:
            self.xml_header.set(CORELIMIT, corelimit)

        if self.benchmark.description:
            description_tag = ElementTree.Element("description")
            description_tag.text = self.benchmark.description
            self.xml_header.append(description_tag)

        # store columnTitles in XML, this are the default columns, that are shown in a default html-table from table-generator
        columntitlesElem = ElementTree.Element("columns")
        columntitlesElem.append(ElementTree.Element("column", title="status"))
        columntitlesElem.append(ElementTree.Element("column", title="cputime"))
        columntitlesElem.append(ElementTree.Element("column", title="walltime"))
        for column in self.benchmark.columns:
            columnElem = ElementTree.Element("column", title=column.title)
            columntitlesElem.append(columnElem)
        self.xml_header.append(columntitlesElem)

Source File: __init__.py From benchexec with Apache License 2.0

6 votes

def test_description(self):
        test_description = """
            äöüß     This tests non-ASCII characters, line breaks, whitespace, and
              <>&"'  XML special characters.
            """
        with tempfile.NamedTemporaryFile(
            prefix="description", suffix=".txt", dir=self.tmp, mode="w+"
        ) as desc:
            desc.write(test_description)
            desc.flush()

            self.run_cmd(
                self.benchmark_test_file,
                "--no-compress-results",
                "--description-file",
                desc.name,
            )

        generated_files = glob.glob(os.path.join(self.output_dir, "*.xml"))
        assert generated_files, "error in test, no results generated"

        for f in generated_files:
            result_xml = ElementTree.ElementTree().parse(f)
            actual_description = result_xml.find("description").text
            self.assertEqual(actual_description, test_description.strip())

Source File: test_xml_etree.py From oss-ftp with MIT License

6 votes

def parseliteral():
    """
    >>> element = ET.XML("<html><body>text</body></html>")
    >>> ET.ElementTree(element).write(sys.stdout)
    <html><body>text</body></html>
    >>> element = ET.fromstring("<html><body>text</body></html>")
    >>> ET.ElementTree(element).write(sys.stdout)
    <html><body>text</body></html>
    >>> sequence = ["<html><body>", "text</bo", "dy></html>"]
    >>> element = ET.fromstringlist(sequence)
    >>> print ET.tostring(element)
    <html><body>text</body></html>
    >>> print "".join(ET.tostringlist(element))
    <html><body>text</body></html>
    >>> ET.tostring(element, "ascii")
    "<?xml version='1.0' encoding='ascii'?>\\n<html><body>text</body></html>"
    >>> _, ids = ET.XMLID("<html><body>text</body></html>")
    >>> len(ids)
    0
    >>> _, ids = ET.XMLID("<html><body id='body'>text</body></html>")
    >>> len(ids)
    1
    >>> ids["body"].tag
    'body'
    """

Source File: outputhandler.py From benchexec with Apache License 2.0

6 votes

def _write_rough_result_xml_to_file(self, xml, filename):
        """Write a rough string version of the XML (for temporary files)."""
        # Write content to temp file first
        error = xml.get("error", None)
        xml.set("error", "incomplete")  # Mark result file as incomplete
        temp_filename = filename + ".tmp"
        with open(temp_filename, "wb") as file:
            ElementTree.ElementTree(xml).write(
                file, encoding="utf-8", xml_declaration=True
            )
        os.rename(temp_filename, filename)
        if error is not None:
            xml.set("error", error)
        else:
            del xml.attrib["error"]

Source File: outputhandler.py From benchexec with Apache License 2.0

6 votes

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

Source File: test_xml_etree.py From oss-ftp with MIT License

6 votes

def file_init():
    """
    >>> import StringIO

    >>> stringfile = StringIO.StringIO(SAMPLE_XML)
    >>> 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'
    """

Source File: document.py From SEM with MIT License

6 votes

def from_xml(cls, xml, chunks_to_load=None, load_subtypes=True, type_separator=u"."):
        if sem.misc.is_string(xml):
            data = ET.parse(xml)
        elif isinstance(xml, ET.ElementTree):
            data = xml
        elif isinstance(xml, type(ET.Element("a"))): # did not ind a better way to do this
            data = xml
        else:
            raise TypeError("Invalid type for loading XML-SEM document: {0}".format(type(xml)))
        
        root = data.getroot()
        if root.tag != "sem":
            raise ValueError("Not sem xml file type: '{0}'".format(root.tag))
        doc_list = []
        for document in list(root):
            doc_list.append(Document.from_xml(document))
        return SEMCorpus(doc_list)

Source File: VisualStudio.py From bob with GNU General Public License v3.0

6 votes

def generateUser(self):
        groups = []
        if self.runTargets:
            # VS can handle only one target per project
            target = self.runTargets[0]
            g = ElementTree.Element("PropertyGroup", {"Condition" : "'$(Configuration)|$(Platform)'=='Build|Win32'"})
            ElementTree.SubElement(g, "LocalDebuggerCommand").text = str(target)
            ElementTree.SubElement(g, "DebuggerFlavor").text = "WindowsLocalDebugger"
            groups.append(ElementTree.tostring(g, encoding="unicode"))

            n = ElementTree.Element("PropertyGroup", {"Condition" : "'$(Configuration)|$(Platform)'=='Checkout+Build|Win32'"})
            ElementTree.SubElement(g, "LocalDebuggerCommand").text = str(target)
            ElementTree.SubElement(g, "DebuggerFlavor").text = "WindowsLocalDebugger"
            groups.append(ElementTree.tostring(g, encoding="unicode"))
            # FIXME: print warning when more than one taget exists

        return USER_TEMPLATE.format(GROUPS="\n".join(groups))

Source File: route_manipulation.py From scenario_runner with MIT License

6 votes

def _get_latlon_ref(world):
    """
    Convert from waypoints world coordinates to CARLA GPS coordinates
    :return: tuple with lat and lon coordinates
    """
    xodr = world.get_map().to_opendrive()
    tree = ET.ElementTree(ET.fromstring(xodr))

    # default reference
    lat_ref = 42.0
    lon_ref = 2.0

    for opendrive in tree.iter("OpenDRIVE"):
        for header in opendrive.iter("header"):
            for georef in header.iter("geoReference"):
                if georef.text:
                    str_list = georef.text.split(' ')
                    for item in str_list:
                        if '+lat_0' in item:
                            lat_ref = float(item.split('=')[1])
                        if '+lon_0' in item:
                            lon_ref = float(item.split('=')[1])
    return lat_ref, lon_ref

Source File: FileUtils.py From ID2T with MIT License

6 votes

def parse_xml(filepath: str):
    """
    Parses an XML File
    It is assumed, that packets are placed on the second hierarchical level and packet-information is encoded
    as attributes

    :param filepath: the path to the XML file to be parsed
    :return: a List of Dictionaries, each Dictionary contains the information of one packet
    """

    tree = ElementTree.parse(filepath)
    root = tree.getroot()

    # Convert Tree to List of Dictionaries
    packets = []
    for child in root:
        packets.append(child.attrib)

    return packets

Source File: bulk.py From SalesforceXyTools with Apache License 2.0

6 votes

def create_job_doc(self, object_name=None, operation=None,
                       contentType='CSV', concurrency=None, external_id_name=None):
        root = ET.Element("jobInfo")
        root.set("xmlns", self.jobNS)
        op = ET.SubElement(root, "operation")
        op.text = operation
        obj = ET.SubElement(root, "object")
        obj.text = object_name
        if external_id_name:
            ext = ET.SubElement(root, 'externalIdFieldName')
            ext.text = external_id_name

        if concurrency:
            con = ET.SubElement(root, "concurrencyMode")
            con.text = concurrency
        ct = ET.SubElement(root, "contentType")
        ct.text = contentType

        buf = BytesIO()
        tree = ET.ElementTree(root)
        tree.write(buf, encoding="UTF-8")
        return buf.getvalue().decode("utf-8")

Source File: test_xml_etree.py From BinderFilter with MIT License

5 votes

def check_issue3151():
    """

    >>> e = ET.XML('<prefix:localname xmlns:prefix="${stuff}"/>')
    >>> e.tag
    '{${stuff}}localname'
    >>> t = ET.ElementTree(e)
    >>> ET.tostring(e)
    '<ns0:localname xmlns:ns0="${stuff}" />'

    """

Source File: test_xml_etree.py From BinderFilter with MIT License

5 votes

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):
        test_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

Source File: test_xml_etree.py From BinderFilter with MIT License

5 votes

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)

Source File: test_xml_etree.py From oss-ftp with MIT License

5 votes

def serialize(elem, to_string=True, **options):
    import StringIO
    file = StringIO.StringIO()
    tree = ET.ElementTree(elem)
    tree.write(file, **options)
    if to_string:
        return file.getvalue()
    else:
        file.seek(0)
        return file

Source File: test_xml_etree.py From BinderFilter with MIT License

5 votes

def bug_xmltoolkit25():
    """

    typo in ElementTree.findtext

    >>> elem = ET.XML(SAMPLE_XML)
    >>> tree = ET.ElementTree(elem)
    >>> tree.findtext("tag")
    'text'
    >>> tree.findtext("section/tag")
    'subtext'

    """

Source File: test_xml_etree.py From BinderFilter with MIT License

5 votes

def iterators():
    """
    Test iterators.

    >>> e = ET.XML("<html><body>this is a <i>paragraph</i>.</body>..</html>")
    >>> 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', <Element 'i' at 0x...>)

    >>> tree = ET.ElementTree(None)
    >>> tree.iter()
    Traceback (most recent call last):
    AttributeError: 'NoneType' object has no attribute 'iter'
    """

Source File: e2m3u2bouquet.py From e2m3u2bouquet with GNU General Public License v3.0

5 votes

def _parse_map_bouquet_xml(self):
        """Check for bouquets within mapping override file and applies if found
        """
        category_order = []
        mapping_file = self._get_mapping_file()
        if mapping_file:
            self._update_status('----Parsing custom bouquet order----')
            print('\n'.format(Status.message))

            try:
                tree = ET.ElementTree(file=mapping_file)
                for node in tree.findall(".//category"):
                    dictoption = {}

                    category = node.attrib.get('name')
                    if not type(category) is unicode:
                        category = category.decode("utf-8")
                    cat_title_override = node.attrib.get('nameOverride', '')
                    if not type(cat_title_override) is unicode:
                        cat_title_override = cat_title_override.decode("utf-8")
                    dictoption['nameOverride'] = cat_title_override
                    dictoption['enabled'] = node.attrib.get('enabled', True) == 'true'
                    category_order.append(category)

                    # If this category is marked as custom and doesn't exist in self._dictchannels then add
                    is_custom_category = node.attrib.get('customCategory', False) == 'true'
                    if is_custom_category:
                        dictoption['customCategory'] = True
                        if category not in self._dictchannels:
                            self._dictchannels[category] = []

                    self._category_options[category] = dictoption

                self._update_status('custom bouquet order applied...')
                print(Status.message)
            except Exception, e:
                msg = 'Corrupt override.xml file'
                print(msg)
                if DEBUG:
                    raise msg

Source File: test_xml_etree.py From BinderFilter with MIT License

5 votes

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
    """

Source File: test_xml_etree.py From BinderFilter with MIT License

5 votes

def xinclude_loader(href, parse="xml", encoding=None):
    try:
        data = XINCLUDE[href]
    except KeyError:
        raise IOError("resource not found")
    if parse == "xml":
        from xml.etree.ElementTree import XML
        return XML(data)
    return data

Source File: test_xml_etree.py From BinderFilter with MIT License

5 votes

def serialize(elem, to_string=True, **options):
    import StringIO
    file = StringIO.StringIO()
    tree = ET.ElementTree(elem)
    tree.write(file, **options)
    if to_string:
        return file.getvalue()
    else:
        file.seek(0)
        return file

Python xml.etree.ElementTree.ElementTree() Examples