Lib/test/test_xml_etree.py

   1 # xml.etree test.  This file contains enough tests to make sure that
   2 # all included components work as they should.  For a more extensive
   3 # test suite, see the selftest script in the ElementTree distribution.
   4
   5 import doctest
   6 import sys
   7
   8 from test import test_support
   9
  10 SAMPLE_XML = """
  11 <body>
  12   <tag>text</tag>
  13   <tag />
  14   <section>
  15     <tag>subtext</tag>
  16   </section>
  17 </body>
  18 """
  19
  20 SAMPLE_XML_NS = """
  21 <body xmlns="http://effbot.org/ns">
  22   <tag>text</tag>
  23   <tag />
  24   <section>
  25     <tag>subtext</tag>
  26   </section>
  27 </body>
  28 """
  29
  30 def sanity():
  31     """
  32     Import sanity.
  33
  34     >>> from xml.etree import ElementTree
  35     >>> from xml.etree import ElementInclude
  36     >>> from xml.etree import ElementPath
  37     """
  38
  39 def check_method(method):
  40     if not callable(method):
  41         print method, "not callable"
  42
  43 def serialize(ET, elem, encoding=None):
  44     import StringIO
  45     file = StringIO.StringIO()
  46     tree = ET.ElementTree(elem)
  47     if encoding:
  48         tree.write(file, encoding)
  49     else:
  50         tree.write(file)
  51     return file.getvalue()
  52
  53 def summarize(elem):
  54     return elem.tag
  55
  56 def summarize_list(seq):
  57     return map(summarize, seq)
  58
  59 def interface():
  60     """
  61     Test element tree interface.
  62
  63     >>> from xml.etree import ElementTree as ET
  64
  65     >>> element = ET.Element("tag", key="value")
  66     >>> tree = ET.ElementTree(element)
  67
  68     Make sure all standard element methods exist.
  69
  70     >>> check_method(element.append)
  71     >>> check_method(element.insert)
  72     >>> check_method(element.remove)
  73     >>> check_method(element.getchildren)
  74     >>> check_method(element.find)
  75     >>> check_method(element.findall)
  76     >>> check_method(element.findtext)
  77     >>> check_method(element.clear)
  78     >>> check_method(element.get)
  79     >>> check_method(element.set)
  80     >>> check_method(element.keys)
  81     >>> check_method(element.items)
  82     >>> check_method(element.getiterator)
  83
  84     Basic method sanity checks.
  85
  86     >>> serialize(ET, element) # 1
  87     '<tag key="value" />'
  88     >>> subelement = ET.Element("subtag")
  89     >>> element.append(subelement)
  90     >>> serialize(ET, element) #  2
  91     '<tag key="value"><subtag /></tag>'
  92     >>> element.insert(0, subelement)
  93     >>> serialize(ET, element) # 3
  94     '<tag key="value"><subtag /><subtag /></tag>'
  95     >>> element.remove(subelement)
  96     >>> serialize(ET, element) # 4
  97     '<tag key="value"><subtag /></tag>'
  98     >>> element.remove(subelement)
  99     >>> serialize(ET, element) # 5
 100     '<tag key="value" />'
 101     >>> element.remove(subelement)
 102     Traceback (most recent call last):
 103     ValueError: list.remove(x): x not in list
 104     >>> serialize(ET, element) # 6
 105     '<tag key="value" />'
 106     """
 107
 108 def find():
 109     """
 110     Test find methods (including xpath syntax).
 111
 112     >>> from xml.etree import ElementTree as ET
 113
 114     >>> elem = ET.XML(SAMPLE_XML)
 115     >>> elem.find("tag").tag
 116     'tag'
 117     >>> ET.ElementTree(elem).find("tag").tag
 118     'tag'
 119     >>> elem.find("section/tag").tag
 120     'tag'
 121     >>> ET.ElementTree(elem).find("section/tag").tag
 122     'tag'
 123     >>> elem.findtext("tag")
 124     'text'
 125     >>> elem.findtext("tog")
 126     >>> elem.findtext("tog", "default")
 127     'default'
 128     >>> ET.ElementTree(elem).findtext("tag")
 129     'text'
 130     >>> elem.findtext("section/tag")
 131     'subtext'
 132     >>> ET.ElementTree(elem).findtext("section/tag")
 133     'subtext'
 134     >>> summarize_list(elem.findall("tag"))
 135     ['tag', 'tag']
 136     >>> summarize_list(elem.findall("*"))
 137     ['tag', 'tag', 'section']
 138     >>> summarize_list(elem.findall(".//tag"))
 139     ['tag', 'tag', 'tag']
 140     >>> summarize_list(elem.findall("section/tag"))
 141     ['tag']
 142     >>> summarize_list(elem.findall("section//tag"))
 143     ['tag']
 144     >>> summarize_list(elem.findall("section/*"))
 145     ['tag']
 146     >>> summarize_list(elem.findall("section//*"))
 147     ['tag']
 148     >>> summarize_list(elem.findall("section/.//*"))
 149     ['tag']
 150     >>> summarize_list(elem.findall("*/*"))
 151     ['tag']
 152     >>> summarize_list(elem.findall("*//*"))
 153     ['tag']
 154     >>> summarize_list(elem.findall("*/tag"))
 155     ['tag']
 156     >>> summarize_list(elem.findall("*/./tag"))
 157     ['tag']
 158     >>> summarize_list(elem.findall("./tag"))
 159     ['tag', 'tag']
 160     >>> summarize_list(elem.findall(".//tag"))
 161     ['tag', 'tag', 'tag']
 162     >>> summarize_list(elem.findall("././tag"))
 163     ['tag', 'tag']
 164     >>> summarize_list(ET.ElementTree(elem).findall("/tag"))
 165     ['tag', 'tag']
 166     >>> summarize_list(ET.ElementTree(elem).findall("./tag"))
 167     ['tag', 'tag']
 168     >>> elem = ET.XML(SAMPLE_XML_NS)
 169     >>> summarize_list(elem.findall("tag"))
 170     []
 171     >>> summarize_list(elem.findall("{http://effbot.org/ns}tag"))
 172     ['{http://effbot.org/ns}tag', '{http://effbot.org/ns}tag']
 173     >>> summarize_list(elem.findall(".//{http://effbot.org/ns}tag"))
 174     ['{http://effbot.org/ns}tag', '{http://effbot.org/ns}tag', '{http://effbot.org/ns}tag']
 175     """
 176
 177 def parseliteral():
 178     r"""
 179
 180     >>> from xml.etree import ElementTree as ET
 181
 182     >>> element = ET.XML("<html><body>text</body></html>")
 183     >>> ET.ElementTree(element).write(sys.stdout)
 184     <html><body>text</body></html>
 185     >>> element = ET.fromstring("<html><body>text</body></html>")
 186     >>> ET.ElementTree(element).write(sys.stdout)
 187     <html><body>text</body></html>
 188     >>> print ET.tostring(element)
 189     <html><body>text</body></html>
 190     >>> print ET.tostring(element, "ascii")
 191     <?xml version='1.0' encoding='ascii'?>
 192     <html><body>text</body></html>
 193     >>> _, ids = ET.XMLID("<html><body>text</body></html>")
 194     >>> len(ids)
 195     0
 196     >>> _, ids = ET.XMLID("<html><body id='body'>text</body></html>")
 197     >>> len(ids)
 198     1
 199     >>> ids["body"].tag
 200     'body'
 201     """
 202
 203
 204 def check_encoding(ET, encoding):
 205     """
 206     >>> from xml.etree import ElementTree as ET
 207
 208     >>> check_encoding(ET, "ascii")
 209     >>> check_encoding(ET, "us-ascii")
 210     >>> check_encoding(ET, "iso-8859-1")
 211     >>> check_encoding(ET, "iso-8859-15")
 212     >>> check_encoding(ET, "cp437")
 213     >>> check_encoding(ET, "mac-roman")
 214     """
 215     ET.XML("<?xml version='1.0' encoding='%s'?><xml />" % encoding)
 216
 217
 218 #
 219 # xinclude tests (samples from appendix C of the xinclude specification)
 220
 221 XINCLUDE = {}
 222
 223 XINCLUDE["C1.xml"] = """\
 224 <?xml version='1.0'?>
 225 <document xmlns:xi="http://www.w3.org/2001/XInclude">
 226   <p>120 Mz is adequate for an average home user.</p>
 227   <xi:include href="disclaimer.xml"/>
 228 </document>
 229 """
 230
 231 XINCLUDE["disclaimer.xml"] = """\
 232 <?xml version='1.0'?>
 233 <disclaimer>
 234   <p>The opinions represented herein represent those of the individual
 235   and should not be interpreted as official policy endorsed by this
 236   organization.</p>
 237 </disclaimer>
 238 """
 239
 240 XINCLUDE["C2.xml"] = """\
 241 <?xml version='1.0'?>
 242 <document xmlns:xi="http://www.w3.org/2001/XInclude">
 243   <p>This document has been accessed
 244   <xi:include href="count.txt" parse="text"/> times.</p>
 245 </document>
 246 """
 247
 248 XINCLUDE["count.txt"] = "324387"
 249
 250 XINCLUDE["C3.xml"] = """\
 251 <?xml version='1.0'?>
 252 <document xmlns:xi="http://www.w3.org/2001/XInclude">
 253   <p>The following is the source of the "data.xml" resource:</p>
 254   <example><xi:include href="data.xml" parse="text"/></example>
 255 </document>
 256 """
 257
 258 XINCLUDE["data.xml"] = """\
 259 <?xml version='1.0'?>
 260 <data>
 261   <item><![CDATA[Brooks & Shields]]></item>
 262 </data>
 263 """
 264
 265 XINCLUDE["C5.xml"] = """\
 266 <?xml version='1.0'?>
 267 <div xmlns:xi="http://www.w3.org/2001/XInclude">
 268   <xi:include href="example.txt" parse="text">
 269     <xi:fallback>
 270       <xi:include href="fallback-example.txt" parse="text">
 271         <xi:fallback><a href="mailto:bob@example.org">Report error</a></xi:fallback>
 272       </xi:include>
 273     </xi:fallback>
 274   </xi:include>
 275 </div>
 276 """
 277
 278 XINCLUDE["default.xml"] = """\
 279 <?xml version='1.0'?>
 280 <document xmlns:xi="http://www.w3.org/2001/XInclude">
 281   <p>Example.</p>
 282   <xi:include href="samples/simple.xml"/>
 283 </document>
 284 """
 285
 286 def xinclude_loader(href, parse="xml", encoding=None):
 287     try:
 288         data = XINCLUDE[href]
 289     except KeyError:
 290         raise IOError("resource not found")
 291     if parse == "xml":
 292         from xml.etree.ElementTree import XML
 293         return XML(data)
 294     return data
 295
 296 def xinclude():
 297     r"""
 298     Basic inclusion example (XInclude C.1)
 299
 300     >>> from xml.etree import ElementTree as ET
 301     >>> from xml.etree import ElementInclude
 302
 303     >>> document = xinclude_loader("C1.xml")
 304     >>> ElementInclude.include(document, xinclude_loader)
 305     >>> print serialize(ET, document) # C1
 306     <document>
 307       <p>120 Mz is adequate for an average home user.</p>
 308       <disclaimer>
 309       <p>The opinions represented herein represent those of the individual
 310       and should not be interpreted as official policy endorsed by this
 311       organization.</p>
 312     </disclaimer>
 313     </document>
 314
 315     Textual inclusion example (XInclude C.2)
 316
 317     >>> document = xinclude_loader("C2.xml")
 318     >>> ElementInclude.include(document, xinclude_loader)
 319     >>> print serialize(ET, document) # C2
 320     <document>
 321       <p>This document has been accessed
 322       324387 times.</p>
 323     </document>
 324
 325     Textual inclusion of XML example (XInclude C.3)
 326
 327     >>> document = xinclude_loader("C3.xml")
 328     >>> ElementInclude.include(document, xinclude_loader)
 329     >>> print serialize(ET, document) # C3
 330     <document>
 331       <p>The following is the source of the "data.xml" resource:</p>
 332       <example>&lt;?xml version='1.0'?&gt;
 333     &lt;data&gt;
 334       &lt;item&gt;&lt;![CDATA[Brooks &amp; Shields]]&gt;&lt;/item&gt;
 335     &lt;/data&gt;
 336     </example>
 337     </document>
 338
 339     Fallback example (XInclude C.5)
 340     Note! Fallback support is not yet implemented
 341
 342     >>> document = xinclude_loader("C5.xml")
 343     >>> ElementInclude.include(document, xinclude_loader)
 344     Traceback (most recent call last):
 345     IOError: resource not found
 346     >>> # print serialize(ET, document) # C5
 347
 348     """
 349
 350 def test_main():
 351     from test import test_xml_etree
 352     test_support.run_doctest(test_xml_etree, verbosity=True)
 353
 354 if __name__ == '__main__':
 355     test_main()