Python elementtree.ElementTree.ElementTree() Examples

def writetext(self, elem, compact=0):
        if len(elem):
            if compact and len(elem) == 1 and elem[0].tag == "p":
                elem = elem[0]
                self.file.write(html_encode(elem.text))
                for e in elem:
                    ET.ElementTree(e).write(self.file)
                self.file.write(html_encode(elem.tail))
            else:
                for e in elem:
                    ET.ElementTree(e).write(self.file)
        elif elem is not None and elem.text:
            if compact:
                self.file.write(html_encode(elem.text))
            else:
                self.file.write("<p>%s</p>\n" % html_encode(elem.text))

    ##
    # Writes an object description (the description text, parameters,
    # return values) etc.
    #
    # @param object The object element.
    # @param summary If true, use summary instead of full description. 

def unknown_endtag(self, tag):
            self.handle_endtag(tag)

##
# ElementTree builder for HTML source code.  This builder converts an
# HTML document or fragment to an ElementTree.
# <p>
# The parser is relatively picky, and requires balanced tags for most
# elements.  However, elements belonging to the following group are
# automatically closed: P, LI, TR, TH, and TD.  In addition, the
# parser automatically inserts end tags immediately after the start
# tag, and ignores any end tags for the following group: IMG, HR,
# META, and LINK.
#
# @keyparam builder Optional builder object.  If omitted, the parser
#     uses the standard <b>elementtree</b> builder.
# @keyparam encoding Optional character encoding, if known.  If omitted,
#     the parser looks for META tags inside the document.  If no tags
#     are found, the parser defaults to ISO-8859-1.  Note that if your
#     document uses a non-ASCII compatible encoding, you must decode
#     the document before parsing. 

def writetext(self, elem, compact=0):
        if len(elem):
            if compact and len(elem) == 1 and elem[0].tag == "p":
                elem = elem[0]
                self.file.write(html_encode(elem.text))
                for e in elem:
                    ET.ElementTree(e).write(self.file)
                self.file.write(html_encode(elem.tail))
            else:
                for e in elem:
                    ET.ElementTree(e).write(self.file)
        elif elem is not None and elem.text:
            if compact:
                self.file.write(html_encode(elem.text))
            else:
                self.file.write("<p>%s</p>\n" % html_encode(elem.text))

    ##
    # Writes an object description (the description text, parameters,
    # return values) etc.
    #
    # @param object The object element.
    # @param summary If true, use summary instead of full description. 

def unknown_endtag(self, tag):
            self.handle_endtag(tag)

##
# ElementTree builder for HTML source code.  This builder converts an
# HTML document or fragment to an ElementTree.
# <p>
# The parser is relatively picky, and requires balanced tags for most
# elements.  However, elements belonging to the following group are
# automatically closed: P, LI, TR, TH, and TD.  In addition, the
# parser automatically inserts end tags immediately after the start
# tag, and ignores any end tags for the following group: IMG, HR,
# META, and LINK.
#
# @keyparam builder Optional builder object.  If omitted, the parser
#     uses the standard <b>elementtree</b> builder.
# @keyparam encoding Optional character encoding, if known.  If omitted,
#     the parser looks for META tags inside the document.  If no tags
#     are found, the parser defaults to ISO-8859-1.  Note that if your
#     document uses a non-ASCII compatible encoding, you must decode
#     the document before parsing. 

def entity():
    """
    Test entity handling.

    1) bad entities

    >>> ElementTree.XML("<document>&entity;</document>")
    Traceback (most recent call last):
    ExpatError: undefined entity: line 1, column 10

    >>> ElementTree.XML(ENTITY_XML)
    Traceback (most recent call last):
    ExpatError: undefined entity &entity;: line 5, column 10

    (add more tests here)

    """ 

def parsefile():
    """
    Test parsing from file.

    >>> tree = ElementTree.parse("samples/simple.xml")
    >>> normalize_crlf(tree)
    >>> tree.write(sys.stdout)
    <root>
       <element key="value">text</element>
       <element>text</element>tail
       <empty-element />
    </root>
    >>> tree = ElementTree.parse("samples/simple-ns.xml")
    >>> normalize_crlf(tree)
    >>> tree.write(sys.stdout)
    <ns0:root xmlns:ns0="namespace">
       <ns0:element key="value">text</ns0:element>
       <ns0:element>text</ns0:element>tail
       <ns0:empty-element />
    </ns0:root>
    """ 

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

def simpleparsefile():
    """
    Test the xmllib-based parser.

    >>> from elementtree import SimpleXMLTreeBuilder
    >>> parser = SimpleXMLTreeBuilder.TreeBuilder()
    >>> tree = ElementTree.parse("samples/simple.xml", parser)
    >>> normalize_crlf(tree)
    >>> tree.write(sys.stdout)
    <root>
       <element key="value">text</element>
       <element>text</element>tail
       <empty-element />
    </root>
    """ 

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 astext(self):
        root = self.content_tree.getroot()
        et = etree.ElementTree(root)
        s1 = ToString(et)
        return s1 

def serialize(elem, encoding=None):
    import cStringIO
    file = cStringIO.StringIO()
    tree = ElementTree.ElementTree(elem)
    if encoding:
        tree.write(file, encoding)
    else:
        tree.write(file)
    return file.getvalue() 

def sanity():
    """
    >>> from elementtree.ElementTree import *
    >>> from elementtree.ElementInclude import *
    >>> from elementtree.ElementPath import *
    >>> from elementtree.HTMLTreeBuilder import *
    >>> from elementtree.SimpleXMLTreeBuilder import *
    >>> from elementtree.SimpleXMLWriter import *
    >>> from elementtree.TidyTools import *
    >>> from elementtree.XMLTreeBuilder import *
    """ 

def version():
    """
    >>> ElementTree.VERSION
    '1.2.7'
    """ 

def interface():
    """
    Test element tree interface.

    >>> element = ElementTree.Element("tag")
    >>> check_element(element)
    >>> tree = ElementTree.ElementTree(element)
    >>> check_element_tree(tree)
    """ 

def simplefind():
    """
    Test find methods using the elementpath fallback.

    >>> CurrentElementPath = ElementTree.ElementPath
    >>> ElementTree.ElementPath = ElementTree._SimpleElementPath()
    >>> elem = 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")
    >>> elem.findall("section/tag")
    []

    >>> ElementTree.ElementPath = CurrentElementPath
    """ 

def astext(self):
        root = self.content_tree.getroot()
        et = etree.ElementTree(root)
        s1 = ToString(et)
        return s1 

def fancyparsefile():
    """
    Test the "fancy" parser.

    Sanity check.
    >>> from elementtree import XMLTreeBuilder
    >>> parser = XMLTreeBuilder.FancyTreeBuilder()
    >>> tree = ElementTree.parse("samples/simple.xml", parser)
    >>> normalize_crlf(tree)
    >>> tree.write(sys.stdout)
    <root>
       <element key="value">text</element>
       <element>text</element>tail
       <empty-element />
    </root>

    Callback check.
    >>> class MyFancyParser(XMLTreeBuilder.FancyTreeBuilder):
    ...     def start(self, elem):
    ...         print "START", elem.tag
    ...     def end(self, elem):
    ...         print "END", elem.tag
    >>> parser = MyFancyParser()
    >>> tree = ElementTree.parse("samples/simple.xml", parser)
    START root
    START element
    END element
    START element
    END element
    START empty-element
    END empty-element
    END root
    """ 

def writefile():
    """
    >>> elem = ElementTree.Element("tag")
    >>> elem.text = "text"
    >>> serialize(elem)
    '<tag>text</tag>'
    >>> ElementTree.SubElement(elem, "subtag").text = "subtext"
    >>> serialize(elem)
    '<tag>text<subtag>subtext</subtag></tag>'
    """ 

def namespace():
    """
    Test namespace issues.

    1) xml namespace

    >>> elem = ElementTree.XML("<tag xml:lang='en' />")
    >>> serialize(elem) # 1.1
    '<tag xml:lang="en" />'

    2) other "well-known" namespaces

    >>> elem = ElementTree.XML("<rdf:RDF xmlns:rdf='http://www.w3.org/1999/02/22-rdf-syntax-ns#' />")
    >>> serialize(elem) # 2.1
    '<rdf:RDF xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" />'

    >>> elem = ElementTree.XML("<html:html xmlns:html='http://www.w3.org/1999/xhtml' />")
    >>> serialize(elem) # 2.2
    '<html:html xmlns:html="http://www.w3.org/1999/xhtml" />'

    >>> elem = ElementTree.XML("<soap:Envelope xmlns:soap='http://schemas.xmlsoap.org/soap/envelope' />")
    >>> serialize(elem) # 2.3
    '<ns0:Envelope xmlns:ns0="http://schemas.xmlsoap.org/soap/envelope" />'

    3) unknown namespaces

    """ 

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

def bug_xmltoolkit21():
    """
    marshaller gives obscure errors for non-string values

    >>> elem = ElementTree.Element(123)
    >>> serialize(elem) # tag
    Traceback (most recent call last):
    TypeError: cannot serialize 123 (type int)
    >>> elem = ElementTree.Element("elem")
    >>> elem.text = 123
    >>> serialize(elem) # text
    Traceback (most recent call last):
    TypeError: cannot serialize 123 (type int)
    >>> elem = ElementTree.Element("elem")
    >>> elem.tail = 123
    >>> serialize(elem) # tail
    Traceback (most recent call last):
    TypeError: cannot serialize 123 (type int)
    >>> elem = ElementTree.Element("elem")
    >>> elem.set(123, "123")
    >>> serialize(elem) # attribute key
    Traceback (most recent call last):
    TypeError: cannot serialize 123 (type int)
    >>> elem = ElementTree.Element("elem")
    >>> elem.set("123", 123)
    >>> serialize(elem) # attribute value
    Traceback (most recent call last):
    TypeError: cannot serialize 123 (type int)

    """ 

def bug_xmltoolkit28():
    """
    .//tag causes exceptions

    >>> tree = ElementTree.XML("<doc><table><tbody/></table></doc>")
    >>> summarize_list(tree.findall(".//thead"))
    []
    >>> summarize_list(tree.findall(".//tbody"))
    ['tbody']
    """ 

def bug_xmltoolkitX1():
    """
    dump() doesn't flush the output buffer

    >>> tree = ElementTree.XML("<doc><table><tbody/></table></doc>")
    >>> ElementTree.dump(tree); sys.stdout.write("tail")
    <doc><table><tbody /></table></doc>
    tail
    """ 

def bug_xmltoolkit39():
    """
    non-ascii element and attribute names doesn't work

    >>> tree = ElementTree.XML("<?xml version='1.0' encoding='iso-8859-1'?><t�g />")
    >>> ElementTree.tostring(tree, "utf-8")
    '<t\\xc3\\xa4g />'

    >>> tree = ElementTree.XML("<?xml version='1.0' encoding='iso-8859-1'?><tag �ttr='v&#228;lue' />")
    >>> tree.attrib
    {u'\\xe4ttr': u'v\\xe4lue'}
    >>> ElementTree.tostring(tree, "utf-8")
    '<tag \\xc3\\xa4ttr="v\\xc3\\xa4lue" />'

    >>> tree = ElementTree.XML("<?xml version='1.0' encoding='iso-8859-1'?><t�g>text</t�g>")
    >>> ElementTree.tostring(tree, "utf-8")
    '<t\\xc3\\xa4g>text</t\\xc3\\xa4g>'

    >>> tree = ElementTree.Element(u"t�g")
    >>> ElementTree.tostring(tree, "utf-8")
    '<t\\xc3\\xa4g />'

    >>> tree = ElementTree.Element("tag")
    >>> tree.set(u"�ttr", u"v�lue")
    >>> ElementTree.tostring(tree, "utf-8")
    '<tag \\xc3\\xa4ttr="v\\xc3\\xa4lue" />'

    """ 

def bug_xmltoolkit54():
    """
    problems handling internally defined entities

    >>> e = ElementTree.XML("<!DOCTYPE doc [<!ENTITY ldots '&#x8230;'>]><doc>&ldots;</doc>")
    >>> serialize(e)
    '<doc>&#33328;</doc>'
    """ 

def bug_xmltoolkit55():
    """
    make sure we're reporting the first error, not the last

    >>> e = ElementTree.XML("<!DOCTYPE doc SYSTEM 'doc.dtd'><doc>&ldots;&ndots;&rdots;</doc>")
    Traceback (most recent call last):
    ExpatError: undefined entity &ldots;: line 1, column 36
    """

# -------------------------------------------------------------------- 

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 astext(self):
        root = self.content_tree.getroot()
        et = etree.ElementTree(root)
        s1 = ToString(et)
        return s1 

def astext(self):
        root = self.content_tree.getroot()
        et = etree.ElementTree(root)
        s1 = ToString(et)
        return s1 

def get_field_marker_hierarchy(self) :
        # Find root field marker
        root = None
        for fm in self.get_markers() :
            fmmd = self.get_metadata_by_marker(fm)            
            if not fmmd.get_parent_marker() :
                root = fm

        # Build tree for field markers
        builder = ElementTree.TreeBuilder()
        builder.start(root, {})
        self.build_tree(root, builder)
        builder.end(root)
        return ElementTree.ElementTree(builder.close())