lxml.tests.selftest2

module documentation

Undocumented

Function attrib Test attribute handling.
Function cdata Test CDATA handling (etc).
Function check​_element Undocumented
Function check​_element​_tree Undocumented
Function check​_mapping Undocumented
Function check​_string Undocumented
Function copy Test copy handling (etc).
Function element Test element tree interface.
Function encoding Test encoding issues.
Function find Test find methods (including xpath syntax).
Function makeelement Test makeelement handling.
Function parsefile Test parsing from file. Note that we're opening the files in here; by default, the 'parse' function opens the file in binary mode, and doctest doesn't filter out carriage returns.
Function qname Test QName handling.
Function serialize Undocumented
Function stdout Undocumented
Function summarize Undocumented
Function summarize​_list Undocumented
Function unserialize Undocumented
Function writefile No summary
Constant ENTITY​_XML Undocumented
Constant SAMPLE​_XML Undocumented
Constant SAMPLE​_XML​_NS Undocumented
def attrib():

Test attribute handling.

>>> elem = ElementTree.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 = ElementTree.Element("tag", key="value")
>>> elem.get("key") # 2.1
'value'
>>> elem.attrib # 2.2
{'key': 'value'}

>>> elem = ElementTree.Element("tag", {"key": "value"})
>>> elem.get("key") # 3.1
'value'
>>> elem.attrib # 3.2
{'key': 'value'}

>>> elem = ElementTree.Element("tag", {"key": "other"}, key="value")
>>> elem.get("key") # 4.1
'value'
>>> elem.attrib # 4.2
{'key': 'value'}
def cdata():

Test CDATA handling (etc).

>>> serialize(unserialize("<tag>hello</tag>"))
'<tag>hello</tag>'
>>> serialize(unserialize("<tag>&#104;&#101;&#108;&#108;&#111;</tag>"))
'<tag>hello</tag>'
>>> serialize(unserialize("<tag><![CDATA[hello]]></tag>"))
'<tag>hello</tag>'
def check_element(element):

Undocumented

def check_element_tree(tree):

Undocumented

def check_mapping(mapping):

Undocumented

def check_string(string):

Undocumented

def copy():

Test copy handling (etc).

>>> import copy
>>> e1 = unserialize("<tag>hello<foo/></tag>")
>>> # e2 = copy.copy(e1)
>>> e3 = copy.deepcopy(e1)
>>> e1.find("foo").tag = "bar"
>>> serialize(e1).replace(' ', '')
'<tag>hello<bar/></tag>'

## >>> serialize(e2).replace(' ', '') ## '<tag>hello<bar/></tag>'

>>> serialize(e3).replace(' ', '')
'<tag>hello<foo/></tag>'
def element():

Test element tree interface.

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

Test encoding issues.

>>> elem = ElementTree.Element("tag")
>>> elem.text = u'abc'
>>> serialize(elem)
'<tag>abc</tag>'
>>> serialize(elem, "utf-8")
'<tag>abc</tag>'
>>> serialize(elem, "us-ascii")
'<tag>abc</tag>'
>>> serialize(elem, "iso-8859-1").lower()
"<?xml version='1.0' encoding='iso-8859-1'?>\n<tag>abc</tag>"

>>> elem.text = "<&\"\'>"
>>> serialize(elem)
'<tag>&lt;&amp;"\'&gt;</tag>'
>>> serialize(elem, "utf-8")
'<tag>&lt;&amp;"\'&gt;</tag>'
>>> serialize(elem, "us-ascii") # cdata characters
'<tag>&lt;&amp;"\'&gt;</tag>'
>>> serialize(elem, "iso-8859-1").lower()
'<?xml version=\'1.0\' encoding=\'iso-8859-1\'?>\n<tag>&lt;&amp;"\'&gt;</tag>'

>>> elem.attrib["key"] = "<&\"\'>"
>>> elem.text = None
>>> serialize(elem)
'<tag key="&lt;&amp;&quot;\'&gt;"/>'
>>> serialize(elem, "utf-8")
'<tag key="&lt;&amp;&quot;\'&gt;"/>'
>>> serialize(elem, "us-ascii")
'<tag key="&lt;&amp;&quot;\'&gt;"/>'
>>> serialize(elem, "iso-8859-1").lower()
'<?xml version=\'1.0\' encoding=\'iso-8859-1\'?>\n<tag key="&lt;&amp;&quot;\'&gt;"/>'

>>> elem.text = u'\xe5\xf6\xf6<>'
>>> elem.attrib.clear()
>>> serialize(elem)
'<tag>&#229;&#246;&#246;&lt;&gt;</tag>'
>>> serialize(elem, "utf-8")
'<tag>\xc3\xa5\xc3\xb6\xc3\xb6&lt;&gt;</tag>'
>>> serialize(elem, "us-ascii")
'<tag>&#229;&#246;&#246;&lt;&gt;</tag>'
>>> serialize(elem, "iso-8859-1").lower()
"<?xml version='1.0' encoding='iso-8859-1'?>\n<tag>\xe5\xf6\xf6&lt;&gt;</tag>"

>>> elem.attrib["key"] = u'\xe5\xf6\xf6<>'
>>> elem.text = None
>>> serialize(elem)
'<tag key="&#229;&#246;&#246;&lt;&gt;"/>'
>>> serialize(elem, "utf-8")
'<tag key="\xc3\xa5\xc3\xb6\xc3\xb6&lt;&gt;"/>'
>>> serialize(elem, "us-ascii")
'<tag key="&#229;&#246;&#246;&lt;&gt;"/>'
>>> serialize(elem, "iso-8859-1").lower()
'<?xml version=\'1.0\' encoding=\'iso-8859-1\'?>\n<tag key="\xe5\xf6\xf6&lt;&gt;"/>'
def find():

Test find methods (including xpath syntax).

>>> elem = SAMPLE_XML
>>> elem.find("tag").tag
'tag'
>>> ElementTree.ElementTree(elem).find("tag").tag
'tag'
>>> elem.find("section/tag").tag
'tag'
>>> ElementTree.ElementTree(elem).find("section/tag").tag
'tag'
>>> elem.findtext("tag")
'text'
>>> elem.findtext("tog", "default")
'default'
>>> ElementTree.ElementTree(elem).findtext("tag")
'text'
>>> elem.findtext("section/tag")
'subtext'
>>> ElementTree.ElementTree(elem).findtext("section/tag")
'subtext'
>>> summarize_list(elem.findall("tag"))
['tag', 'tag']
>>> summarize_list(elem.findall("*"))
['tag', 'tag', 'section']
>>> summarize_list(elem.findall(".//tag"))
['tag', 'tag', 'tag']
>>> summarize_list(elem.findall("section/tag"))
['tag']
>>> summarize_list(elem.findall("section//tag"))
['tag']
>>> summarize_list(elem.findall("section/*"))
['tag']
>>> summarize_list(elem.findall("section//*"))
['tag']
>>> summarize_list(elem.findall("section/.//*"))
['tag']
>>> summarize_list(elem.findall("*/*"))
['tag']
>>> summarize_list(elem.findall("*//*"))
['tag']
>>> summarize_list(elem.findall("*/tag"))
['tag']
>>> summarize_list(elem.findall("*/./tag"))
['tag']
>>> summarize_list(elem.findall("./tag"))
['tag', 'tag']
>>> summarize_list(elem.findall(".//tag"))
['tag', 'tag', 'tag']
>>> summarize_list(elem.findall("././tag"))
['tag', 'tag']
>>> summarize_list(ElementTree.ElementTree(elem).findall("/tag"))
['tag', 'tag']
>>> summarize_list(ElementTree.ElementTree(elem).findall("./tag"))
['tag', 'tag']
>>> elem = SAMPLE_XML_NS
>>> summarize_list(elem.findall("tag"))
[]
>>> summarize_list(elem.findall("{http://effbot.org/ns}tag"))
['{http://effbot.org/ns}tag', '{http://effbot.org/ns}tag']
>>> summarize_list(elem.findall(".//{http://effbot.org/ns}tag"))
['{http://effbot.org/ns}tag', '{http://effbot.org/ns}tag', '{http://effbot.org/ns}tag']
def makeelement():

Test makeelement handling.

>>> elem = ElementTree.Element("tag")
>>> subelem = elem.makeelement("subtag", {"key": "value"})
>>> elem.append(subelem)
>>> serialize(elem)
'<tag><subtag key="value"/></tag>'

>>> elem.clear()
>>> serialize(elem)
'<tag/>'
>>> elem.append(subelem)
>>> serialize(elem)
'<tag><subtag key="value"/></tag>'
def parsefile():

Test parsing from file. Note that we're opening the files in here; by default, the 'parse' function opens the file in binary mode, and doctest doesn't filter out carriage returns.

>>> file = open("samples/simple.xml", "rb")
>>> tree = ElementTree.parse(file)
>>> file.close()
>>> tree.write(stdout())
<root>
   <element key="value">text</element>
   <element>text</element>tail
   <empty-element/>
</root>
>>> file = open("samples/simple-ns.xml", "rb")
>>> tree = ElementTree.parse(file)
>>> file.close()
>>> tree.write(stdout())
<root xmlns="http://namespace/">
   <element key="value">text</element>
   <element>text</element>tail
   <empty-element/>
</root>
def qname():

Test QName handling.

  1. decorated tags
>>> elem = ElementTree.Element("{uri}tag")
>>> serialize(elem) # 1.1
'<ns0:tag xmlns:ns0="uri"/>'

## 2) decorated attributes

## >>> elem.attrib["{uri}key"] = "value" ## >>> serialize(elem) # 2.1 ## '<ns0:tag ns0:key="value" xmlns:ns0="uri"/>'

def serialize(elem, encoding=None):

Undocumented

def stdout():

Undocumented

def summarize(elem):

Undocumented

def summarize_list(seq):

Undocumented

def unserialize(text):

Undocumented

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>'
ENTITY_XML: str =

Undocumented

Value
'''<!DOCTYPE points [
<!ENTITY % user-entities SYSTEM \'user-entities.xml\'>
%user-entities;
]>
<document>&entity;</document>
'''
SAMPLE_XML =

Undocumented

Value
unserialize('''
<body>
  <tag>text</tag>
  <tag />
  <section>
    <tag>subtext</tag>
  </section>
...
SAMPLE_XML_NS =

Undocumented

Value
unserialize('''
<body xmlns="http://effbot.org/ns">
  <tag>text</tag>
  <tag />
  <section>
    <tag>subtext</tag>
  </section>
...