10c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi# xml.etree test. This file contains enough tests to make sure that 20c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi# all included components work as they should. 30c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi# Large parts are extracted from the upstream test suite. 40c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 50c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi# IMPORTANT: the same doctests are run from "test_xml_etree_c" in 60c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi# order to ensure consistency between the C implementation and the 70c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi# Python implementation. 80c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi# 90c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi# For this purpose, the module-level "ET" symbol is temporarily 100c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi# monkey-patched when running the "test_xml_etree_c" test suite. 110c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi# Don't re-import "xml.etree.ElementTree" module in the docstring, 120c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi# except if the test is specific to the Python implementation. 130c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 140c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yiimport sys 150c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yiimport cgi 160c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 170c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yifrom test import test_support 180c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yifrom test.test_support import findfile 190c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 200c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yifrom xml.etree import ElementTree as ET 210c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 220c5958b1636c47ed7c284f859c8e805fd06a0e6Bill YiSIMPLE_XMLFILE = findfile("simple.xml", subdir="xmltestdata") 230c5958b1636c47ed7c284f859c8e805fd06a0e6Bill YiSIMPLE_NS_XMLFILE = findfile("simple-ns.xml", subdir="xmltestdata") 240c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 250c5958b1636c47ed7c284f859c8e805fd06a0e6Bill YiSAMPLE_XML = """\ 260c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi<body> 270c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <tag class='a'>text</tag> 280c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <tag class='b' /> 290c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <section> 300c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <tag class='b' id='inner'>subtext</tag> 310c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi </section> 320c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi</body> 330c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi""" 340c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 350c5958b1636c47ed7c284f859c8e805fd06a0e6Bill YiSAMPLE_SECTION = """\ 360c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi<section> 370c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <tag class='b' id='inner'>subtext</tag> 380c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <nexttag /> 390c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <nextsection> 400c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <tag /> 410c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi </nextsection> 420c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi</section> 430c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi""" 440c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 450c5958b1636c47ed7c284f859c8e805fd06a0e6Bill YiSAMPLE_XML_NS = """ 460c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi<body xmlns="http://effbot.org/ns"> 470c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <tag>text</tag> 480c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <tag /> 490c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <section> 500c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <tag>subtext</tag> 510c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi </section> 520c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi</body> 530c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi""" 540c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 550c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 560c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yidef sanity(): 570c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 580c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi Import sanity. 590c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 600c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> from xml.etree import ElementTree 610c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> from xml.etree import ElementInclude 620c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> from xml.etree import ElementPath 630c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 640c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 650c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yidef check_method(method): 660c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi if not hasattr(method, '__call__'): 670c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi print method, "not callable" 680c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 690c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yidef serialize(elem, to_string=True, **options): 700c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi import StringIO 710c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi file = StringIO.StringIO() 720c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi tree = ET.ElementTree(elem) 730c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi tree.write(file, **options) 740c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi if to_string: 750c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi return file.getvalue() 760c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi else: 770c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi file.seek(0) 780c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi return file 790c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 800c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yidef summarize(elem): 810c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi if elem.tag == ET.Comment: 820c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi return "<Comment>" 830c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi return elem.tag 840c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 850c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yidef summarize_list(seq): 860c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi return [summarize(elem) for elem in seq] 870c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 880c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yidef normalize_crlf(tree): 890c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi for elem in tree.iter(): 900c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi if elem.text: 910c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi elem.text = elem.text.replace("\r\n", "\n") 920c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi if elem.tail: 930c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi elem.tail = elem.tail.replace("\r\n", "\n") 940c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 950c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yidef check_string(string): 960c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi len(string) 970c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi for char in string: 980c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi if len(char) != 1: 990c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi print "expected one-character string, got %r" % char 1000c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi new_string = string + "" 1010c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi new_string = string + " " 1020c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi string[:0] 1030c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 1040c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yidef check_mapping(mapping): 1050c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi len(mapping) 1060c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi keys = mapping.keys() 1070c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi items = mapping.items() 1080c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi for key in keys: 1090c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi item = mapping[key] 1100c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi mapping["key"] = "value" 1110c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi if mapping["key"] != "value": 1120c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi print "expected value string, got %r" % mapping["key"] 1130c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 1140c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yidef check_element(element): 1150c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi if not ET.iselement(element): 1160c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi print "not an element" 1170c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi if not hasattr(element, "tag"): 1180c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi print "no tag member" 1190c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi if not hasattr(element, "attrib"): 1200c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi print "no attrib member" 1210c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi if not hasattr(element, "text"): 1220c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi print "no text member" 1230c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi if not hasattr(element, "tail"): 1240c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi print "no tail member" 1250c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 1260c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi check_string(element.tag) 1270c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi check_mapping(element.attrib) 1280c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi if element.text is not None: 1290c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi check_string(element.text) 1300c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi if element.tail is not None: 1310c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi check_string(element.tail) 1320c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi for elem in element: 1330c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi check_element(elem) 1340c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 1350c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi# -------------------------------------------------------------------- 1360c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi# element tree tests 1370c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 1380c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yidef interface(): 1390c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi r""" 1400c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi Test element tree interface. 1410c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 1420c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> element = ET.Element("tag") 1430c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> check_element(element) 1440c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> tree = ET.ElementTree(element) 1450c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> check_element(tree.getroot()) 1460c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 1470c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> element = ET.Element("t\xe4g", key="value") 1480c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> tree = ET.ElementTree(element) 1490c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> repr(element) # doctest: +ELLIPSIS 1500c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi "<Element 't\\xe4g' at 0x...>" 1510c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> element = ET.Element("tag", key="value") 1520c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 1530c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi Make sure all standard element methods exist. 1540c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 1550c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> check_method(element.append) 1560c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> check_method(element.extend) 1570c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> check_method(element.insert) 1580c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> check_method(element.remove) 1590c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> check_method(element.getchildren) 1600c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> check_method(element.find) 1610c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> check_method(element.iterfind) 1620c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> check_method(element.findall) 1630c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> check_method(element.findtext) 1640c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> check_method(element.clear) 1650c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> check_method(element.get) 1660c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> check_method(element.set) 1670c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> check_method(element.keys) 1680c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> check_method(element.items) 1690c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> check_method(element.iter) 1700c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> check_method(element.itertext) 1710c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> check_method(element.getiterator) 1720c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 1730c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi These methods return an iterable. See bug 6472. 1740c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 1750c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> check_method(element.iter("tag").next) 1760c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> check_method(element.iterfind("tag").next) 1770c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> check_method(element.iterfind("*").next) 1780c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> check_method(tree.iter("tag").next) 1790c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> check_method(tree.iterfind("tag").next) 1800c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> check_method(tree.iterfind("*").next) 1810c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 1820c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi These aliases are provided: 1830c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 1840c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> assert ET.XML == ET.fromstring 1850c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> assert ET.PI == ET.ProcessingInstruction 1860c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> assert ET.XMLParser == ET.XMLTreeBuilder 1870c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 1880c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 1890c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yidef simpleops(): 1900c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 1910c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi Basic method sanity checks. 1920c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 1930c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem = ET.XML("<body><tag/></body>") 1940c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(elem) 1950c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<body><tag /></body>' 1960c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> e = ET.Element("tag2") 1970c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem.append(e) 1980c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(elem) 1990c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<body><tag /><tag2 /></body>' 2000c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem.remove(e) 2010c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(elem) 2020c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<body><tag /></body>' 2030c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem.insert(0, e) 2040c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(elem) 2050c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<body><tag2 /><tag /></body>' 2060c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem.remove(e) 2070c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem.extend([e]) 2080c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(elem) 2090c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<body><tag /><tag2 /></body>' 2100c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem.remove(e) 2110c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 2120c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> element = ET.Element("tag", key="value") 2130c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(element) # 1 2140c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<tag key="value" />' 2150c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> subelement = ET.Element("subtag") 2160c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> element.append(subelement) 2170c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(element) # 2 2180c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<tag key="value"><subtag /></tag>' 2190c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> element.insert(0, subelement) 2200c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(element) # 3 2210c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<tag key="value"><subtag /><subtag /></tag>' 2220c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> element.remove(subelement) 2230c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(element) # 4 2240c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<tag key="value"><subtag /></tag>' 2250c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> element.remove(subelement) 2260c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(element) # 5 2270c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<tag key="value" />' 2280c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> element.remove(subelement) 2290c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi Traceback (most recent call last): 2300c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ValueError: list.remove(x): x not in list 2310c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(element) # 6 2320c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<tag key="value" />' 2330c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> element[0:0] = [subelement, subelement, subelement] 2340c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(element[1]) 2350c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<subtag />' 2360c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> element[1:9] == [element[1], element[2]] 2370c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi True 2380c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> element[:9:2] == [element[0], element[2]] 2390c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi True 2400c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> del element[1:2] 2410c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(element) 2420c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<tag key="value"><subtag /><subtag /></tag>' 2430c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 2440c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 2450c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yidef cdata(): 2460c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 2470c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi Test CDATA handling (etc). 2480c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 2490c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(ET.XML("<tag>hello</tag>")) 2500c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<tag>hello</tag>' 2510c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(ET.XML("<tag>hello</tag>")) 2520c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<tag>hello</tag>' 2530c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(ET.XML("<tag><![CDATA[hello]]></tag>")) 2540c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<tag>hello</tag>' 2550c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 2560c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 2570c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi# Only with Python implementation 2580c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yidef simplefind(): 2590c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 2600c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi Test find methods using the elementpath fallback. 2610c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 2620c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> from xml.etree import ElementTree 2630c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 2640c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> CurrentElementPath = ElementTree.ElementPath 2650c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> ElementTree.ElementPath = ElementTree._SimpleElementPath() 2660c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem = ElementTree.XML(SAMPLE_XML) 2670c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem.find("tag").tag 2680c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 'tag' 2690c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> ElementTree.ElementTree(elem).find("tag").tag 2700c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 'tag' 2710c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem.findtext("tag") 2720c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 'text' 2730c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem.findtext("tog") 2740c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem.findtext("tog", "default") 2750c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 'default' 2760c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> ElementTree.ElementTree(elem).findtext("tag") 2770c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 'text' 2780c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> summarize_list(elem.findall("tag")) 2790c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ['tag', 'tag'] 2800c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> summarize_list(elem.findall(".//tag")) 2810c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ['tag', 'tag', 'tag'] 2820c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 2830c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi Path syntax doesn't work in this case. 2840c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 2850c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem.find("section/tag") 2860c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem.findtext("section/tag") 2870c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> summarize_list(elem.findall("section/tag")) 2880c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi [] 2890c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 2900c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> ElementTree.ElementPath = CurrentElementPath 2910c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 2920c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 2930c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yidef find(): 2940c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 2950c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi Test find methods (including xpath syntax). 2960c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 2970c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem = ET.XML(SAMPLE_XML) 2980c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem.find("tag").tag 2990c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 'tag' 3000c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> ET.ElementTree(elem).find("tag").tag 3010c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 'tag' 3020c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem.find("section/tag").tag 3030c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 'tag' 3040c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem.find("./tag").tag 3050c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 'tag' 3060c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> ET.ElementTree(elem).find("./tag").tag 3070c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 'tag' 3080c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> ET.ElementTree(elem).find("/tag").tag 3090c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 'tag' 3100c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem[2] = ET.XML(SAMPLE_SECTION) 3110c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem.find("section/nexttag").tag 3120c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 'nexttag' 3130c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> ET.ElementTree(elem).find("section/tag").tag 3140c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 'tag' 3150c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> ET.ElementTree(elem).find("tog") 3160c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> ET.ElementTree(elem).find("tog/foo") 3170c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem.findtext("tag") 3180c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 'text' 3190c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem.findtext("section/nexttag") 3200c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '' 3210c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem.findtext("section/nexttag", "default") 3220c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '' 3230c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem.findtext("tog") 3240c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem.findtext("tog", "default") 3250c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 'default' 3260c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> ET.ElementTree(elem).findtext("tag") 3270c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 'text' 3280c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> ET.ElementTree(elem).findtext("tog/foo") 3290c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> ET.ElementTree(elem).findtext("tog/foo", "default") 3300c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 'default' 3310c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> ET.ElementTree(elem).findtext("./tag") 3320c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 'text' 3330c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> ET.ElementTree(elem).findtext("/tag") 3340c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 'text' 3350c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem.findtext("section/tag") 3360c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 'subtext' 3370c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> ET.ElementTree(elem).findtext("section/tag") 3380c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 'subtext' 3390c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> summarize_list(elem.findall(".")) 3400c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ['body'] 3410c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> summarize_list(elem.findall("tag")) 3420c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ['tag', 'tag'] 3430c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> summarize_list(elem.findall("tog")) 3440c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi [] 3450c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> summarize_list(elem.findall("tog/foo")) 3460c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi [] 3470c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> summarize_list(elem.findall("*")) 3480c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ['tag', 'tag', 'section'] 3490c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> summarize_list(elem.findall(".//tag")) 3500c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ['tag', 'tag', 'tag', 'tag'] 3510c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> summarize_list(elem.findall("section/tag")) 3520c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ['tag'] 3530c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> summarize_list(elem.findall("section//tag")) 3540c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ['tag', 'tag'] 3550c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> summarize_list(elem.findall("section/*")) 3560c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ['tag', 'nexttag', 'nextsection'] 3570c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> summarize_list(elem.findall("section//*")) 3580c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ['tag', 'nexttag', 'nextsection', 'tag'] 3590c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> summarize_list(elem.findall("section/.//*")) 3600c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ['tag', 'nexttag', 'nextsection', 'tag'] 3610c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> summarize_list(elem.findall("*/*")) 3620c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ['tag', 'nexttag', 'nextsection'] 3630c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> summarize_list(elem.findall("*//*")) 3640c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ['tag', 'nexttag', 'nextsection', 'tag'] 3650c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> summarize_list(elem.findall("*/tag")) 3660c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ['tag'] 3670c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> summarize_list(elem.findall("*/./tag")) 3680c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ['tag'] 3690c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> summarize_list(elem.findall("./tag")) 3700c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ['tag', 'tag'] 3710c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> summarize_list(elem.findall(".//tag")) 3720c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ['tag', 'tag', 'tag', 'tag'] 3730c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> summarize_list(elem.findall("././tag")) 3740c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ['tag', 'tag'] 3750c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> summarize_list(elem.findall(".//tag[@class]")) 3760c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ['tag', 'tag', 'tag'] 3770c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> summarize_list(elem.findall(".//tag[@class='a']")) 3780c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ['tag'] 3790c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> summarize_list(elem.findall(".//tag[@class='b']")) 3800c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ['tag', 'tag'] 3810c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> summarize_list(elem.findall(".//tag[@id]")) 3820c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ['tag'] 3830c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> summarize_list(elem.findall(".//section[tag]")) 3840c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ['section'] 3850c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> summarize_list(elem.findall(".//section[element]")) 3860c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi [] 3870c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> summarize_list(elem.findall("../tag")) 3880c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi [] 3890c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> summarize_list(elem.findall("section/../tag")) 3900c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ['tag', 'tag'] 3910c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> summarize_list(ET.ElementTree(elem).findall("./tag")) 3920c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ['tag', 'tag'] 3930c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 3940c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi Following example is invalid in 1.2. 3950c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi A leading '*' is assumed in 1.3. 3960c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 3970c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem.findall("section//") == elem.findall("section//*") 3980c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi True 3990c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 4000c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ET's Path module handles this case incorrectly; this gives 4010c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi a warning in 1.3, and the behaviour will be modified in 1.4. 4020c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 4030c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> summarize_list(ET.ElementTree(elem).findall("/tag")) 4040c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ['tag', 'tag'] 4050c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 4060c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem = ET.XML(SAMPLE_XML_NS) 4070c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> summarize_list(elem.findall("tag")) 4080c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi [] 4090c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> summarize_list(elem.findall("{http://effbot.org/ns}tag")) 4100c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ['{http://effbot.org/ns}tag', '{http://effbot.org/ns}tag'] 4110c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> summarize_list(elem.findall(".//{http://effbot.org/ns}tag")) 4120c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ['{http://effbot.org/ns}tag', '{http://effbot.org/ns}tag', '{http://effbot.org/ns}tag'] 4130c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 4140c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 4150c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yidef file_init(): 4160c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 4170c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> import StringIO 4180c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 4190c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> stringfile = StringIO.StringIO(SAMPLE_XML) 4200c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> tree = ET.ElementTree(file=stringfile) 4210c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> tree.find("tag").tag 4220c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 'tag' 4230c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> tree.find("section/tag").tag 4240c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 'tag' 4250c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 4260c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> tree = ET.ElementTree(file=SIMPLE_XMLFILE) 4270c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> tree.find("element").tag 4280c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 'element' 4290c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> tree.find("element/../empty-element").tag 4300c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 'empty-element' 4310c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 4320c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 4330c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yidef bad_find(): 4340c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 4350c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi Check bad or unsupported path expressions. 4360c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 4370c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem = ET.XML(SAMPLE_XML) 4380c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem.findall("/tag") 4390c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi Traceback (most recent call last): 4400c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi SyntaxError: cannot use absolute path on element 4410c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 4420c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 4430c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yidef path_cache(): 4440c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 4450c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi Check that the path cache behaves sanely. 4460c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 4470c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem = ET.XML(SAMPLE_XML) 4480c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> for i in range(10): ET.ElementTree(elem).find('./'+str(i)) 4490c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> cache_len_10 = len(ET.ElementPath._cache) 4500c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> for i in range(10): ET.ElementTree(elem).find('./'+str(i)) 4510c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> len(ET.ElementPath._cache) == cache_len_10 4520c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi True 4530c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> for i in range(20): ET.ElementTree(elem).find('./'+str(i)) 4540c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> len(ET.ElementPath._cache) > cache_len_10 4550c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi True 4560c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> for i in range(600): ET.ElementTree(elem).find('./'+str(i)) 4570c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> len(ET.ElementPath._cache) < 500 4580c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi True 4590c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 4600c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 4610c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yidef copy(): 4620c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 4630c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi Test copy handling (etc). 4640c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 4650c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> import copy 4660c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> e1 = ET.XML("<tag>hello<foo/></tag>") 4670c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> e2 = copy.copy(e1) 4680c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> e3 = copy.deepcopy(e1) 4690c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> e1.find("foo").tag = "bar" 4700c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(e1) 4710c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<tag>hello<bar /></tag>' 4720c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(e2) 4730c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<tag>hello<bar /></tag>' 4740c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(e3) 4750c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<tag>hello<foo /></tag>' 4760c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 4770c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 4780c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 4790c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yidef attrib(): 4800c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 4810c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi Test attribute handling. 4820c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 4830c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem = ET.Element("tag") 4840c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem.get("key") # 1.1 4850c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem.get("key", "default") # 1.2 4860c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 'default' 4870c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem.set("key", "value") 4880c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem.get("key") # 1.3 4890c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 'value' 4900c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 4910c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem = ET.Element("tag", key="value") 4920c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem.get("key") # 2.1 4930c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 'value' 4940c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem.attrib # 2.2 4950c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi {'key': 'value'} 4960c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 4970c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> attrib = {"key": "value"} 4980c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem = ET.Element("tag", attrib) 4990c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> attrib.clear() # check for aliasing issues 5000c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem.get("key") # 3.1 5010c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 'value' 5020c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem.attrib # 3.2 5030c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi {'key': 'value'} 5040c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 5050c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> attrib = {"key": "value"} 5060c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem = ET.Element("tag", **attrib) 5070c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> attrib.clear() # check for aliasing issues 5080c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem.get("key") # 4.1 5090c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 'value' 5100c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem.attrib # 4.2 5110c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi {'key': 'value'} 5120c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 5130c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem = ET.Element("tag", {"key": "other"}, key="value") 5140c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem.get("key") # 5.1 5150c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 'value' 5160c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem.attrib # 5.2 5170c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi {'key': 'value'} 5180c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 5190c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem = ET.Element('test') 5200c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem.text = "aa" 5210c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem.set('testa', 'testval') 5220c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem.set('testb', 'test2') 5230c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> ET.tostring(elem) 5240c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<test testa="testval" testb="test2">aa</test>' 5250c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> sorted(elem.keys()) 5260c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ['testa', 'testb'] 5270c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> sorted(elem.items()) 5280c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi [('testa', 'testval'), ('testb', 'test2')] 5290c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem.attrib['testb'] 5300c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 'test2' 5310c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem.attrib['testb'] = 'test1' 5320c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem.attrib['testc'] = 'test2' 5330c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> ET.tostring(elem) 5340c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<test testa="testval" testb="test1" testc="test2">aa</test>' 5350c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 5360c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 5370c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yidef makeelement(): 5380c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 5390c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi Test makeelement handling. 5400c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 5410c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem = ET.Element("tag") 5420c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> attrib = {"key": "value"} 5430c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> subelem = elem.makeelement("subtag", attrib) 5440c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> if subelem.attrib is attrib: 5450c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ... print "attrib aliasing" 5460c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem.append(subelem) 5470c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(elem) 5480c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<tag><subtag key="value" /></tag>' 5490c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 5500c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem.clear() 5510c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(elem) 5520c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<tag />' 5530c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem.append(subelem) 5540c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(elem) 5550c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<tag><subtag key="value" /></tag>' 5560c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem.extend([subelem, subelem]) 5570c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(elem) 5580c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<tag><subtag key="value" /><subtag key="value" /><subtag key="value" /></tag>' 5590c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem[:] = [subelem] 5600c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(elem) 5610c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<tag><subtag key="value" /></tag>' 5620c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem[:] = tuple([subelem]) 5630c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(elem) 5640c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<tag><subtag key="value" /></tag>' 5650c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 5660c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 5670c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 5680c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yidef parsefile(): 5690c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 5700c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi Test parsing from file. 5710c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 5720c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> tree = ET.parse(SIMPLE_XMLFILE) 5730c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> normalize_crlf(tree) 5740c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> tree.write(sys.stdout) 5750c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <root> 5760c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <element key="value">text</element> 5770c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <element>text</element>tail 5780c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <empty-element /> 5790c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi </root> 5800c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> tree = ET.parse(SIMPLE_NS_XMLFILE) 5810c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> normalize_crlf(tree) 5820c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> tree.write(sys.stdout) 5830c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <ns0:root xmlns:ns0="namespace"> 5840c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <ns0:element key="value">text</ns0:element> 5850c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <ns0:element>text</ns0:element>tail 5860c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <ns0:empty-element /> 5870c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi </ns0:root> 5880c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 5890c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> with open(SIMPLE_XMLFILE) as f: 5900c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ... data = f.read() 5910c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 5920c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> parser = ET.XMLParser() 5930c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> parser.version # doctest: +ELLIPSIS 5940c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 'Expat ...' 5950c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> parser.feed(data) 5960c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> print serialize(parser.close()) 5970c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <root> 5980c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <element key="value">text</element> 5990c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <element>text</element>tail 6000c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <empty-element /> 6010c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi </root> 6020c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 6030c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> parser = ET.XMLTreeBuilder() # 1.2 compatibility 6040c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> parser.feed(data) 6050c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> print serialize(parser.close()) 6060c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <root> 6070c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <element key="value">text</element> 6080c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <element>text</element>tail 6090c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <empty-element /> 6100c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi </root> 6110c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 6120c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> target = ET.TreeBuilder() 6130c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> parser = ET.XMLParser(target=target) 6140c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> parser.feed(data) 6150c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> print serialize(parser.close()) 6160c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <root> 6170c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <element key="value">text</element> 6180c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <element>text</element>tail 6190c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <empty-element /> 6200c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi </root> 6210c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 6220c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 6230c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yidef parseliteral(): 6240c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 6250c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> element = ET.XML("<html><body>text</body></html>") 6260c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> ET.ElementTree(element).write(sys.stdout) 6270c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <html><body>text</body></html> 6280c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> element = ET.fromstring("<html><body>text</body></html>") 6290c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> ET.ElementTree(element).write(sys.stdout) 6300c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <html><body>text</body></html> 6310c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> sequence = ["<html><body>", "text</bo", "dy></html>"] 6320c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> element = ET.fromstringlist(sequence) 6330c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> print ET.tostring(element) 6340c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <html><body>text</body></html> 6350c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> print "".join(ET.tostringlist(element)) 6360c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <html><body>text</body></html> 6370c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> ET.tostring(element, "ascii") 6380c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi "<?xml version='1.0' encoding='ascii'?>\\n<html><body>text</body></html>" 6390c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> _, ids = ET.XMLID("<html><body>text</body></html>") 6400c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> len(ids) 6410c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 0 6420c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> _, ids = ET.XMLID("<html><body id='body'>text</body></html>") 6430c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> len(ids) 6440c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 1 6450c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> ids["body"].tag 6460c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 'body' 6470c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 6480c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 6490c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yidef iterparse(): 6500c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 6510c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi Test iterparse interface. 6520c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 6530c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> iterparse = ET.iterparse 6540c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 6550c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> context = iterparse(SIMPLE_XMLFILE) 6560c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> action, elem = next(context) 6570c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> print action, elem.tag 6580c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi end element 6590c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> for action, elem in context: 6600c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ... print action, elem.tag 6610c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi end element 6620c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi end empty-element 6630c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi end root 6640c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> context.root.tag 6650c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 'root' 6660c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 6670c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> context = iterparse(SIMPLE_NS_XMLFILE) 6680c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> for action, elem in context: 6690c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ... print action, elem.tag 6700c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi end {namespace}element 6710c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi end {namespace}element 6720c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi end {namespace}empty-element 6730c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi end {namespace}root 6740c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 6750c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> events = () 6760c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> context = iterparse(SIMPLE_XMLFILE, events) 6770c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> for action, elem in context: 6780c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ... print action, elem.tag 6790c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 6800c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> events = () 6810c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> context = iterparse(SIMPLE_XMLFILE, events=events) 6820c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> for action, elem in context: 6830c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ... print action, elem.tag 6840c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 6850c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> events = ("start", "end") 6860c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> context = iterparse(SIMPLE_XMLFILE, events) 6870c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> for action, elem in context: 6880c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ... print action, elem.tag 6890c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi start root 6900c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi start element 6910c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi end element 6920c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi start element 6930c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi end element 6940c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi start empty-element 6950c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi end empty-element 6960c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi end root 6970c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 6980c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> events = ("start", "end", "start-ns", "end-ns") 6990c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> context = iterparse(SIMPLE_NS_XMLFILE, events) 7000c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> for action, elem in context: 7010c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ... if action in ("start", "end"): 7020c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ... print action, elem.tag 7030c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ... else: 7040c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ... print action, elem 7050c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi start-ns ('', 'namespace') 7060c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi start {namespace}root 7070c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi start {namespace}element 7080c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi end {namespace}element 7090c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi start {namespace}element 7100c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi end {namespace}element 7110c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi start {namespace}empty-element 7120c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi end {namespace}empty-element 7130c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi end {namespace}root 7140c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi end-ns None 7150c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 7160c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> events = ("start", "end", "bogus") 7170c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> with open(SIMPLE_XMLFILE, "rb") as f: 7180c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ... iterparse(f, events) 7190c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi Traceback (most recent call last): 7200c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ValueError: unknown event 'bogus' 7210c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 7220c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> import StringIO 7230c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 7240c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> source = StringIO.StringIO( 7250c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ... "<?xml version='1.0' encoding='iso-8859-1'?>\\n" 7260c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ... "<body xmlns='http://éffbot.org/ns'\\n" 7270c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ... " xmlns:cl\\xe9='http://effbot.org/ns'>text</body>\\n") 7280c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> events = ("start-ns",) 7290c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> context = iterparse(source, events) 7300c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> for action, elem in context: 7310c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ... print action, elem 7320c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi start-ns ('', u'http://\\xe9ffbot.org/ns') 7330c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi start-ns (u'cl\\xe9', 'http://effbot.org/ns') 7340c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 7350c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> source = StringIO.StringIO("<document />junk") 7360c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> try: 7370c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ... for action, elem in iterparse(source): 7380c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ... print action, elem.tag 7390c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ... except ET.ParseError, v: 7400c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ... print v 7410c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi end document 7420c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi junk after document element: line 1, column 12 7430c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 7440c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 7450c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yidef writefile(): 7460c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 7470c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem = ET.Element("tag") 7480c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem.text = "text" 7490c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(elem) 7500c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<tag>text</tag>' 7510c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> ET.SubElement(elem, "subtag").text = "subtext" 7520c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(elem) 7530c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<tag>text<subtag>subtext</subtag></tag>' 7540c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 7550c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi Test tag suppression 7560c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem.tag = None 7570c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(elem) 7580c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 'text<subtag>subtext</subtag>' 7590c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem.insert(0, ET.Comment("comment")) 7600c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(elem) # assumes 1.3 7610c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 'text<!--comment--><subtag>subtext</subtag>' 7620c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem[0] = ET.PI("key", "value") 7630c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(elem) 7640c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 'text<?key value?><subtag>subtext</subtag>' 7650c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 7660c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 7670c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yidef custom_builder(): 7680c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 7690c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi Test parser w. custom builder. 7700c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 7710c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> with open(SIMPLE_XMLFILE) as f: 7720c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ... data = f.read() 7730c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> class Builder: 7740c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ... def start(self, tag, attrib): 7750c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ... print "start", tag 7760c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ... def end(self, tag): 7770c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ... print "end", tag 7780c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ... def data(self, text): 7790c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ... pass 7800c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> builder = Builder() 7810c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> parser = ET.XMLParser(target=builder) 7820c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> parser.feed(data) 7830c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi start root 7840c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi start element 7850c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi end element 7860c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi start element 7870c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi end element 7880c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi start empty-element 7890c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi end empty-element 7900c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi end root 7910c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 7920c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> with open(SIMPLE_NS_XMLFILE) as f: 7930c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ... data = f.read() 7940c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> class Builder: 7950c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ... def start(self, tag, attrib): 7960c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ... print "start", tag 7970c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ... def end(self, tag): 7980c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ... print "end", tag 7990c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ... def data(self, text): 8000c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ... pass 8010c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ... def pi(self, target, data): 8020c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ... print "pi", target, repr(data) 8030c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ... def comment(self, data): 8040c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ... print "comment", repr(data) 8050c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> builder = Builder() 8060c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> parser = ET.XMLParser(target=builder) 8070c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> parser.feed(data) 8080c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi pi pi 'data' 8090c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi comment ' comment ' 8100c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi start {namespace}root 8110c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi start {namespace}element 8120c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi end {namespace}element 8130c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi start {namespace}element 8140c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi end {namespace}element 8150c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi start {namespace}empty-element 8160c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi end {namespace}empty-element 8170c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi end {namespace}root 8180c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 8190c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 8200c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 8210c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yidef getchildren(): 8220c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 8230c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi Test Element.getchildren() 8240c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 8250c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> with open(SIMPLE_XMLFILE, "r") as f: 8260c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ... tree = ET.parse(f) 8270c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> for elem in tree.getroot().iter(): 8280c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ... summarize_list(elem.getchildren()) 8290c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ['element', 'element', 'empty-element'] 8300c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi [] 8310c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi [] 8320c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi [] 8330c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> for elem in tree.getiterator(): 8340c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ... summarize_list(elem.getchildren()) 8350c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ['element', 'element', 'empty-element'] 8360c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi [] 8370c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi [] 8380c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi [] 8390c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 8400c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem = ET.XML(SAMPLE_XML) 8410c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> len(elem.getchildren()) 8420c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 3 8430c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> len(elem[2].getchildren()) 8440c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 1 8450c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem[:] == elem.getchildren() 8460c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi True 8470c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> child1 = elem[0] 8480c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> child2 = elem[2] 8490c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> del elem[1:2] 8500c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> len(elem.getchildren()) 8510c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 2 8520c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> child1 == elem[0] 8530c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi True 8540c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> child2 == elem[1] 8550c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi True 8560c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem[0:2] = [child2, child1] 8570c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> child2 == elem[0] 8580c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi True 8590c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> child1 == elem[1] 8600c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi True 8610c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> child1 == elem[0] 8620c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi False 8630c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem.clear() 8640c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem.getchildren() 8650c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi [] 8660c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 8670c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 8680c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yidef writestring(): 8690c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 8700c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem = ET.XML("<html><body>text</body></html>") 8710c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> ET.tostring(elem) 8720c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<html><body>text</body></html>' 8730c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem = ET.fromstring("<html><body>text</body></html>") 8740c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> ET.tostring(elem) 8750c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<html><body>text</body></html>' 8760c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 8770c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 8780c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yidef check_encoding(encoding): 8790c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 8800c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> check_encoding("ascii") 8810c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> check_encoding("us-ascii") 8820c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> check_encoding("iso-8859-1") 8830c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> check_encoding("iso-8859-15") 8840c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> check_encoding("cp437") 8850c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> check_encoding("mac-roman") 8860c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 8870c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ET.XML("<?xml version='1.0' encoding='%s'?><xml />" % encoding) 8880c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 8890c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yidef encoding(): 8900c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi r""" 8910c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi Test encoding issues. 8920c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 8930c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem = ET.Element("tag") 8940c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem.text = u"abc" 8950c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(elem) 8960c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<tag>abc</tag>' 8970c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(elem, encoding="utf-8") 8980c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<tag>abc</tag>' 8990c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(elem, encoding="us-ascii") 9000c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<tag>abc</tag>' 9010c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(elem, encoding="iso-8859-1") 9020c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi "<?xml version='1.0' encoding='iso-8859-1'?>\n<tag>abc</tag>" 9030c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 9040c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem.text = "<&\"\'>" 9050c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(elem) 9060c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<tag><&"\'></tag>' 9070c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(elem, encoding="utf-8") 9080c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<tag><&"\'></tag>' 9090c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(elem, encoding="us-ascii") # cdata characters 9100c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<tag><&"\'></tag>' 9110c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(elem, encoding="iso-8859-1") 9120c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<?xml version=\'1.0\' encoding=\'iso-8859-1\'?>\n<tag><&"\'></tag>' 9130c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 9140c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem.attrib["key"] = "<&\"\'>" 9150c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem.text = None 9160c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(elem) 9170c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<tag key="<&"\'>" />' 9180c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(elem, encoding="utf-8") 9190c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<tag key="<&"\'>" />' 9200c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(elem, encoding="us-ascii") 9210c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<tag key="<&"\'>" />' 9220c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(elem, encoding="iso-8859-1") 9230c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<?xml version=\'1.0\' encoding=\'iso-8859-1\'?>\n<tag key="<&"\'>" />' 9240c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 9250c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem.text = u'\xe5\xf6\xf6<>' 9260c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem.attrib.clear() 9270c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(elem) 9280c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<tag>åöö<></tag>' 9290c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(elem, encoding="utf-8") 9300c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<tag>\xc3\xa5\xc3\xb6\xc3\xb6<></tag>' 9310c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(elem, encoding="us-ascii") 9320c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<tag>åöö<></tag>' 9330c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(elem, encoding="iso-8859-1") 9340c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi "<?xml version='1.0' encoding='iso-8859-1'?>\n<tag>\xe5\xf6\xf6<></tag>" 9350c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 9360c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem.attrib["key"] = u'\xe5\xf6\xf6<>' 9370c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem.text = None 9380c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(elem) 9390c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<tag key="åöö<>" />' 9400c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(elem, encoding="utf-8") 9410c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<tag key="\xc3\xa5\xc3\xb6\xc3\xb6<>" />' 9420c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(elem, encoding="us-ascii") 9430c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<tag key="åöö<>" />' 9440c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(elem, encoding="iso-8859-1") 9450c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<?xml version=\'1.0\' encoding=\'iso-8859-1\'?>\n<tag key="\xe5\xf6\xf6<>" />' 9460c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 9470c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 9480c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yidef methods(): 9490c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi r""" 9500c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi Test serialization methods. 9510c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 9520c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> e = ET.XML("<html><link/><script>1 < 2</script></html>") 9530c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> e.tail = "\n" 9540c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(e) 9550c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<html><link /><script>1 < 2</script></html>\n' 9560c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(e, method=None) 9570c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<html><link /><script>1 < 2</script></html>\n' 9580c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(e, method="xml") 9590c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<html><link /><script>1 < 2</script></html>\n' 9600c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(e, method="html") 9610c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<html><link><script>1 < 2</script></html>\n' 9620c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(e, method="text") 9630c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '1 < 2\n' 9640c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 9650c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 9660c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yidef iterators(): 9670c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 9680c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi Test iterators. 9690c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 9700c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> e = ET.XML("<html><body>this is a <i>paragraph</i>.</body>..</html>") 9710c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> summarize_list(e.iter()) 9720c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ['html', 'body', 'i'] 9730c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> summarize_list(e.find("body").iter()) 9740c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ['body', 'i'] 9750c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> summarize(next(e.iter())) 9760c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 'html' 9770c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> "".join(e.itertext()) 9780c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 'this is a paragraph...' 9790c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> "".join(e.find("body").itertext()) 9800c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 'this is a paragraph.' 9810c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> next(e.itertext()) 9820c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 'this is a ' 9830c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 9840c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi Method iterparse should return an iterator. See bug 6472. 9850c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 9860c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> sourcefile = serialize(e, to_string=False) 9870c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> next(ET.iterparse(sourcefile)) # doctest: +ELLIPSIS 9880c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ('end', <Element 'i' at 0x...>) 9890c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 9900c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> tree = ET.ElementTree(None) 9910c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> tree.iter() 9920c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi Traceback (most recent call last): 9930c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi AttributeError: 'NoneType' object has no attribute 'iter' 9940c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 9950c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 9960c5958b1636c47ed7c284f859c8e805fd06a0e6Bill YiENTITY_XML = """\ 9970c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi<!DOCTYPE points [ 9980c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi<!ENTITY % user-entities SYSTEM 'user-entities.xml'> 9990c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi%user-entities; 10000c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi]> 10010c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi<document>&entity;</document> 10020c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi""" 10030c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 10040c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yidef entity(): 10050c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 10060c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi Test entity handling. 10070c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 10080c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 1) good entities 10090c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 10100c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> e = ET.XML("<document title='舰'>test</document>") 10110c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(e) 10120c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<document title="舰">test</document>' 10130c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 10140c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 2) bad entities 10150c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 10160c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> ET.XML("<document>&entity;</document>") 10170c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi Traceback (most recent call last): 10180c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ParseError: undefined entity: line 1, column 10 10190c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 10200c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> ET.XML(ENTITY_XML) 10210c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi Traceback (most recent call last): 10220c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ParseError: undefined entity &entity;: line 5, column 10 10230c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 10240c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 3) custom entity 10250c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 10260c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> parser = ET.XMLParser() 10270c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> parser.entity["entity"] = "text" 10280c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> parser.feed(ENTITY_XML) 10290c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> root = parser.close() 10300c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(root) 10310c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<document>text</document>' 10320c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 10330c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 10340c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yidef error(xml): 10350c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 10360c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 10370c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi Test error handling. 10380c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 10390c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> issubclass(ET.ParseError, SyntaxError) 10400c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi True 10410c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> error("foo").position 10420c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi (1, 0) 10430c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> error("<tag>&foo;</tag>").position 10440c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi (1, 5) 10450c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> error("foobar<").position 10460c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi (1, 6) 10470c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 10480c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 10490c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi try: 10500c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ET.XML(xml) 10510c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi except ET.ParseError: 10520c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi return sys.exc_value 10530c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 10540c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yidef namespace(): 10550c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 10560c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi Test namespace issues. 10570c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 10580c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 1) xml namespace 10590c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 10600c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem = ET.XML("<tag xml:lang='en' />") 10610c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(elem) # 1.1 10620c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<tag xml:lang="en" />' 10630c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 10640c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 2) other "well-known" namespaces 10650c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 10660c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem = ET.XML("<rdf:RDF xmlns:rdf='http://www.w3.org/1999/02/22-rdf-syntax-ns#' />") 10670c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(elem) # 2.1 10680c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<rdf:RDF xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" />' 10690c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 10700c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem = ET.XML("<html:html xmlns:html='http://www.w3.org/1999/xhtml' />") 10710c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(elem) # 2.2 10720c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<html:html xmlns:html="http://www.w3.org/1999/xhtml" />' 10730c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 10740c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem = ET.XML("<soap:Envelope xmlns:soap='http://schemas.xmlsoap.org/soap/envelope' />") 10750c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(elem) # 2.3 10760c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<ns0:Envelope xmlns:ns0="http://schemas.xmlsoap.org/soap/envelope" />' 10770c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 10780c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 3) unknown namespaces 10790c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem = ET.XML(SAMPLE_XML_NS) 10800c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> print serialize(elem) 10810c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <ns0:body xmlns:ns0="http://effbot.org/ns"> 10820c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <ns0:tag>text</ns0:tag> 10830c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <ns0:tag /> 10840c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <ns0:section> 10850c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <ns0:tag>subtext</ns0:tag> 10860c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi </ns0:section> 10870c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi </ns0:body> 10880c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 10890c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 10900c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yidef qname(): 10910c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 10920c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi Test QName handling. 10930c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 10940c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 1) decorated tags 10950c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 10960c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem = ET.Element("{uri}tag") 10970c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(elem) # 1.1 10980c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<ns0:tag xmlns:ns0="uri" />' 10990c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem = ET.Element(ET.QName("{uri}tag")) 11000c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(elem) # 1.2 11010c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<ns0:tag xmlns:ns0="uri" />' 11020c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem = ET.Element(ET.QName("uri", "tag")) 11030c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(elem) # 1.3 11040c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<ns0:tag xmlns:ns0="uri" />' 11050c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem = ET.Element(ET.QName("uri", "tag")) 11060c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> subelem = ET.SubElement(elem, ET.QName("uri", "tag1")) 11070c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> subelem = ET.SubElement(elem, ET.QName("uri", "tag2")) 11080c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(elem) # 1.4 11090c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<ns0:tag xmlns:ns0="uri"><ns0:tag1 /><ns0:tag2 /></ns0:tag>' 11100c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 11110c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 2) decorated attributes 11120c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 11130c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem.clear() 11140c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem.attrib["{uri}key"] = "value" 11150c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(elem) # 2.1 11160c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<ns0:tag xmlns:ns0="uri" ns0:key="value" />' 11170c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 11180c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem.clear() 11190c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem.attrib[ET.QName("{uri}key")] = "value" 11200c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(elem) # 2.2 11210c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<ns0:tag xmlns:ns0="uri" ns0:key="value" />' 11220c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 11230c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 3) decorated values are not converted by default, but the 11240c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi QName wrapper can be used for values 11250c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 11260c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem.clear() 11270c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem.attrib["{uri}key"] = "{uri}value" 11280c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(elem) # 3.1 11290c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<ns0:tag xmlns:ns0="uri" ns0:key="{uri}value" />' 11300c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 11310c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem.clear() 11320c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem.attrib["{uri}key"] = ET.QName("{uri}value") 11330c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(elem) # 3.2 11340c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<ns0:tag xmlns:ns0="uri" ns0:key="ns0:value" />' 11350c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 11360c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem.clear() 11370c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> subelem = ET.Element("tag") 11380c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> subelem.attrib["{uri1}key"] = ET.QName("{uri2}value") 11390c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem.append(subelem) 11400c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem.append(subelem) 11410c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(elem) # 3.3 11420c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<ns0:tag xmlns:ns0="uri" xmlns:ns1="uri1" xmlns:ns2="uri2"><tag ns1:key="ns2:value" /><tag ns1:key="ns2:value" /></ns0:tag>' 11430c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 11440c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 4) Direct QName tests 11450c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 11460c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> str(ET.QName('ns', 'tag')) 11470c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '{ns}tag' 11480c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> str(ET.QName('{ns}tag')) 11490c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '{ns}tag' 11500c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> q1 = ET.QName('ns', 'tag') 11510c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> q2 = ET.QName('ns', 'tag') 11520c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> q1 == q2 11530c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi True 11540c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> q2 = ET.QName('ns', 'other-tag') 11550c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> q1 == q2 11560c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi False 11570c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> q1 == 'ns:tag' 11580c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi False 11590c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> q1 == '{ns}tag' 11600c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi True 11610c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 11620c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 11630c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yidef doctype_public(): 11640c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 11650c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi Test PUBLIC doctype. 11660c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 11670c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem = ET.XML('<!DOCTYPE html PUBLIC' 11680c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ... ' "-//W3C//DTD XHTML 1.0 Transitional//EN"' 11690c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ... ' "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">' 11700c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ... '<html>text</html>') 11710c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 11720c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 11730c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 11740c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yidef xpath_tokenizer(p): 11750c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 11760c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi Test the XPath tokenizer. 11770c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 11780c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> # tests from the xml specification 11790c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> xpath_tokenizer("*") 11800c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ['*'] 11810c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> xpath_tokenizer("text()") 11820c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ['text', '()'] 11830c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> xpath_tokenizer("@name") 11840c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ['@', 'name'] 11850c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> xpath_tokenizer("@*") 11860c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ['@', '*'] 11870c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> xpath_tokenizer("para[1]") 11880c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ['para', '[', '1', ']'] 11890c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> xpath_tokenizer("para[last()]") 11900c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ['para', '[', 'last', '()', ']'] 11910c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> xpath_tokenizer("*/para") 11920c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ['*', '/', 'para'] 11930c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> xpath_tokenizer("/doc/chapter[5]/section[2]") 11940c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ['/', 'doc', '/', 'chapter', '[', '5', ']', '/', 'section', '[', '2', ']'] 11950c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> xpath_tokenizer("chapter//para") 11960c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ['chapter', '//', 'para'] 11970c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> xpath_tokenizer("//para") 11980c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ['//', 'para'] 11990c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> xpath_tokenizer("//olist/item") 12000c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ['//', 'olist', '/', 'item'] 12010c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> xpath_tokenizer(".") 12020c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ['.'] 12030c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> xpath_tokenizer(".//para") 12040c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ['.', '//', 'para'] 12050c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> xpath_tokenizer("..") 12060c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ['..'] 12070c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> xpath_tokenizer("../@lang") 12080c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ['..', '/', '@', 'lang'] 12090c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> xpath_tokenizer("chapter[title]") 12100c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ['chapter', '[', 'title', ']'] 12110c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> xpath_tokenizer("employee[@secretary and @assistant]") 12120c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ['employee', '[', '@', 'secretary', '', 'and', '', '@', 'assistant', ']'] 12130c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 12140c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> # additional tests 12150c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> xpath_tokenizer("{http://spam}egg") 12160c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ['{http://spam}egg'] 12170c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> xpath_tokenizer("./spam.egg") 12180c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ['.', '/', 'spam.egg'] 12190c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> xpath_tokenizer(".//{http://spam}egg") 12200c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ['.', '//', '{http://spam}egg'] 12210c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 12220c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi from xml.etree import ElementPath 12230c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi out = [] 12240c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi for op, tag in ElementPath.xpath_tokenizer(p): 12250c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi out.append(op or tag) 12260c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi return out 12270c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 12280c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yidef processinginstruction(): 12290c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 12300c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi Test ProcessingInstruction directly 12310c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 12320c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> ET.tostring(ET.ProcessingInstruction('test', 'instruction')) 12330c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<?test instruction?>' 12340c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> ET.tostring(ET.PI('test', 'instruction')) 12350c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<?test instruction?>' 12360c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 12370c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi Issue #2746 12380c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 12390c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> ET.tostring(ET.PI('test', '<testing&>')) 12400c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<?test <testing&>?>' 12410c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> ET.tostring(ET.PI('test', u'<testing&>\xe3'), 'latin1') 12420c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi "<?xml version='1.0' encoding='latin1'?>\\n<?test <testing&>\\xe3?>" 12430c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 12440c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 12450c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi# 12460c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi# xinclude tests (samples from appendix C of the xinclude specification) 12470c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 12480c5958b1636c47ed7c284f859c8e805fd06a0e6Bill YiXINCLUDE = {} 12490c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 12500c5958b1636c47ed7c284f859c8e805fd06a0e6Bill YiXINCLUDE["C1.xml"] = """\ 12510c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi<?xml version='1.0'?> 12520c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi<document xmlns:xi="http://www.w3.org/2001/XInclude"> 12530c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <p>120 Mz is adequate for an average home user.</p> 12540c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <xi:include href="disclaimer.xml"/> 12550c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi</document> 12560c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi""" 12570c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 12580c5958b1636c47ed7c284f859c8e805fd06a0e6Bill YiXINCLUDE["disclaimer.xml"] = """\ 12590c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi<?xml version='1.0'?> 12600c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi<disclaimer> 12610c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <p>The opinions represented herein represent those of the individual 12620c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi and should not be interpreted as official policy endorsed by this 12630c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi organization.</p> 12640c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi</disclaimer> 12650c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi""" 12660c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 12670c5958b1636c47ed7c284f859c8e805fd06a0e6Bill YiXINCLUDE["C2.xml"] = """\ 12680c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi<?xml version='1.0'?> 12690c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi<document xmlns:xi="http://www.w3.org/2001/XInclude"> 12700c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <p>This document has been accessed 12710c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <xi:include href="count.txt" parse="text"/> times.</p> 12720c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi</document> 12730c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi""" 12740c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 12750c5958b1636c47ed7c284f859c8e805fd06a0e6Bill YiXINCLUDE["count.txt"] = "324387" 12760c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 12770c5958b1636c47ed7c284f859c8e805fd06a0e6Bill YiXINCLUDE["C2b.xml"] = """\ 12780c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi<?xml version='1.0'?> 12790c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi<document xmlns:xi="http://www.w3.org/2001/XInclude"> 12800c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <p>This document has been <em>accessed</em> 12810c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <xi:include href="count.txt" parse="text"/> times.</p> 12820c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi</document> 12830c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi""" 12840c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 12850c5958b1636c47ed7c284f859c8e805fd06a0e6Bill YiXINCLUDE["C3.xml"] = """\ 12860c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi<?xml version='1.0'?> 12870c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi<document xmlns:xi="http://www.w3.org/2001/XInclude"> 12880c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <p>The following is the source of the "data.xml" resource:</p> 12890c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <example><xi:include href="data.xml" parse="text"/></example> 12900c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi</document> 12910c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi""" 12920c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 12930c5958b1636c47ed7c284f859c8e805fd06a0e6Bill YiXINCLUDE["data.xml"] = """\ 12940c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi<?xml version='1.0'?> 12950c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi<data> 12960c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <item><![CDATA[Brooks & Shields]]></item> 12970c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi</data> 12980c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi""" 12990c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 13000c5958b1636c47ed7c284f859c8e805fd06a0e6Bill YiXINCLUDE["C5.xml"] = """\ 13010c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi<?xml version='1.0'?> 13020c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi<div xmlns:xi="http://www.w3.org/2001/XInclude"> 13030c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <xi:include href="example.txt" parse="text"> 13040c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <xi:fallback> 13050c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <xi:include href="fallback-example.txt" parse="text"> 13060c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <xi:fallback><a href="mailto:bob@example.org">Report error</a></xi:fallback> 13070c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi </xi:include> 13080c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi </xi:fallback> 13090c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi </xi:include> 13100c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi</div> 13110c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi""" 13120c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 13130c5958b1636c47ed7c284f859c8e805fd06a0e6Bill YiXINCLUDE["default.xml"] = """\ 13140c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi<?xml version='1.0'?> 13150c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi<document xmlns:xi="http://www.w3.org/2001/XInclude"> 13160c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <p>Example.</p> 13170c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <xi:include href="{}"/> 13180c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi</document> 13190c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi""".format(cgi.escape(SIMPLE_XMLFILE, True)) 13200c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 13210c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yidef xinclude_loader(href, parse="xml", encoding=None): 13220c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi try: 13230c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi data = XINCLUDE[href] 13240c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi except KeyError: 13250c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi raise IOError("resource not found") 13260c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi if parse == "xml": 13270c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi from xml.etree.ElementTree import XML 13280c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi return XML(data) 13290c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi return data 13300c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 13310c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yidef xinclude(): 13320c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi r""" 13330c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi Basic inclusion example (XInclude C.1) 13340c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 13350c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> from xml.etree import ElementTree as ET 13360c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> from xml.etree import ElementInclude 13370c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 13380c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> document = xinclude_loader("C1.xml") 13390c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> ElementInclude.include(document, xinclude_loader) 13400c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> print serialize(document) # C1 13410c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <document> 13420c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <p>120 Mz is adequate for an average home user.</p> 13430c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <disclaimer> 13440c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <p>The opinions represented herein represent those of the individual 13450c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi and should not be interpreted as official policy endorsed by this 13460c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi organization.</p> 13470c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi </disclaimer> 13480c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi </document> 13490c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 13500c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi Textual inclusion example (XInclude C.2) 13510c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 13520c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> document = xinclude_loader("C2.xml") 13530c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> ElementInclude.include(document, xinclude_loader) 13540c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> print serialize(document) # C2 13550c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <document> 13560c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <p>This document has been accessed 13570c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 324387 times.</p> 13580c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi </document> 13590c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 13600c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi Textual inclusion after sibling element (based on modified XInclude C.2) 13610c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 13620c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> document = xinclude_loader("C2b.xml") 13630c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> ElementInclude.include(document, xinclude_loader) 13640c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> print(serialize(document)) # C2b 13650c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <document> 13660c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <p>This document has been <em>accessed</em> 13670c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 324387 times.</p> 13680c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi </document> 13690c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 13700c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi Textual inclusion of XML example (XInclude C.3) 13710c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 13720c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> document = xinclude_loader("C3.xml") 13730c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> ElementInclude.include(document, xinclude_loader) 13740c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> print serialize(document) # C3 13750c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <document> 13760c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <p>The following is the source of the "data.xml" resource:</p> 13770c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <example><?xml version='1.0'?> 13780c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <data> 13790c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <item><![CDATA[Brooks & Shields]]></item> 13800c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi </data> 13810c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi </example> 13820c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi </document> 13830c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 13840c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi Fallback example (XInclude C.5) 13850c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi Note! Fallback support is not yet implemented 13860c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 13870c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> document = xinclude_loader("C5.xml") 13880c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> ElementInclude.include(document, xinclude_loader) 13890c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi Traceback (most recent call last): 13900c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi IOError: resource not found 13910c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> # print serialize(document) # C5 13920c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 13930c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 13940c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yidef xinclude_default(): 13950c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 13960c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> from xml.etree import ElementInclude 13970c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 13980c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> document = xinclude_loader("default.xml") 13990c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> ElementInclude.include(document) 14000c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> print serialize(document) # default 14010c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <document> 14020c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <p>Example.</p> 14030c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <root> 14040c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <element key="value">text</element> 14050c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <element>text</element>tail 14060c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <empty-element /> 14070c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi </root> 14080c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi </document> 14090c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 14100c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 14110c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi# 14120c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi# badly formatted xi:include tags 14130c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 14140c5958b1636c47ed7c284f859c8e805fd06a0e6Bill YiXINCLUDE_BAD = {} 14150c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 14160c5958b1636c47ed7c284f859c8e805fd06a0e6Bill YiXINCLUDE_BAD["B1.xml"] = """\ 14170c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi<?xml version='1.0'?> 14180c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi<document xmlns:xi="http://www.w3.org/2001/XInclude"> 14190c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <p>120 Mz is adequate for an average home user.</p> 14200c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <xi:include href="disclaimer.xml" parse="BAD_TYPE"/> 14210c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi</document> 14220c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi""" 14230c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 14240c5958b1636c47ed7c284f859c8e805fd06a0e6Bill YiXINCLUDE_BAD["B2.xml"] = """\ 14250c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi<?xml version='1.0'?> 14260c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi<div xmlns:xi="http://www.w3.org/2001/XInclude"> 14270c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <xi:fallback></xi:fallback> 14280c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi</div> 14290c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi""" 14300c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 14310c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yidef xinclude_failures(): 14320c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi r""" 14330c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi Test failure to locate included XML file. 14340c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 14350c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> from xml.etree import ElementInclude 14360c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 14370c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> def none_loader(href, parser, encoding=None): 14380c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ... return None 14390c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 14400c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> document = ET.XML(XINCLUDE["C1.xml"]) 14410c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> ElementInclude.include(document, loader=none_loader) 14420c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi Traceback (most recent call last): 14430c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi FatalIncludeError: cannot load 'disclaimer.xml' as 'xml' 14440c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 14450c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi Test failure to locate included text file. 14460c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 14470c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> document = ET.XML(XINCLUDE["C2.xml"]) 14480c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> ElementInclude.include(document, loader=none_loader) 14490c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi Traceback (most recent call last): 14500c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi FatalIncludeError: cannot load 'count.txt' as 'text' 14510c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 14520c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi Test bad parse type. 14530c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 14540c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> document = ET.XML(XINCLUDE_BAD["B1.xml"]) 14550c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> ElementInclude.include(document, loader=none_loader) 14560c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi Traceback (most recent call last): 14570c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi FatalIncludeError: unknown parse type in xi:include tag ('BAD_TYPE') 14580c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 14590c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi Test xi:fallback outside xi:include. 14600c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 14610c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> document = ET.XML(XINCLUDE_BAD["B2.xml"]) 14620c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> ElementInclude.include(document, loader=none_loader) 14630c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi Traceback (most recent call last): 14640c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi FatalIncludeError: xi:fallback tag must be child of xi:include ('{http://www.w3.org/2001/XInclude}fallback') 14650c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 14660c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 14670c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi# -------------------------------------------------------------------- 14680c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi# reported bugs 14690c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 14700c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yidef bug_xmltoolkit21(): 14710c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 14720c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 14730c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi marshaller gives obscure errors for non-string values 14740c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 14750c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem = ET.Element(123) 14760c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(elem) # tag 14770c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi Traceback (most recent call last): 14780c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi TypeError: cannot serialize 123 (type int) 14790c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem = ET.Element("elem") 14800c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem.text = 123 14810c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(elem) # text 14820c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi Traceback (most recent call last): 14830c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi TypeError: cannot serialize 123 (type int) 14840c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem = ET.Element("elem") 14850c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem.tail = 123 14860c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(elem) # tail 14870c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi Traceback (most recent call last): 14880c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi TypeError: cannot serialize 123 (type int) 14890c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem = ET.Element("elem") 14900c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem.set(123, "123") 14910c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(elem) # attribute key 14920c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi Traceback (most recent call last): 14930c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi TypeError: cannot serialize 123 (type int) 14940c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem = ET.Element("elem") 14950c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem.set("123", 123) 14960c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(elem) # attribute value 14970c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi Traceback (most recent call last): 14980c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi TypeError: cannot serialize 123 (type int) 14990c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 15000c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 15010c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 15020c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yidef bug_xmltoolkit25(): 15030c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 15040c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 15050c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi typo in ElementTree.findtext 15060c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 15070c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem = ET.XML(SAMPLE_XML) 15080c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> tree = ET.ElementTree(elem) 15090c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> tree.findtext("tag") 15100c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 'text' 15110c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> tree.findtext("section/tag") 15120c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 'subtext' 15130c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 15140c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 15150c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 15160c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yidef bug_xmltoolkit28(): 15170c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 15180c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 15190c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi .//tag causes exceptions 15200c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 15210c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> tree = ET.XML("<doc><table><tbody/></table></doc>") 15220c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> summarize_list(tree.findall(".//thead")) 15230c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi [] 15240c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> summarize_list(tree.findall(".//tbody")) 15250c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ['tbody'] 15260c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 15270c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 15280c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 15290c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yidef bug_xmltoolkitX1(): 15300c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 15310c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 15320c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi dump() doesn't flush the output buffer 15330c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 15340c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> tree = ET.XML("<doc><table><tbody/></table></doc>") 15350c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> ET.dump(tree); sys.stdout.write("tail") 15360c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi <doc><table><tbody /></table></doc> 15370c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi tail 15380c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 15390c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 15400c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 15410c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yidef bug_xmltoolkit39(): 15420c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 15430c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 15440c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi non-ascii element and attribute names doesn't work 15450c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 15460c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> tree = ET.XML("<?xml version='1.0' encoding='iso-8859-1'?><t\xe4g />") 15470c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> ET.tostring(tree, "utf-8") 15480c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<t\\xc3\\xa4g />' 15490c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 15500c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> tree = ET.XML("<?xml version='1.0' encoding='iso-8859-1'?><tag \xe4ttr='välue' />") 15510c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> tree.attrib 15520c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi {u'\\xe4ttr': u'v\\xe4lue'} 15530c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> ET.tostring(tree, "utf-8") 15540c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<tag \\xc3\\xa4ttr="v\\xc3\\xa4lue" />' 15550c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 15560c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> tree = ET.XML("<?xml version='1.0' encoding='iso-8859-1'?><t\xe4g>text</t\xe4g>") 15570c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> ET.tostring(tree, "utf-8") 15580c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<t\\xc3\\xa4g>text</t\\xc3\\xa4g>' 15590c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 15600c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> tree = ET.Element(u"t\u00e4g") 15610c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> ET.tostring(tree, "utf-8") 15620c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<t\\xc3\\xa4g />' 15630c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 15640c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> tree = ET.Element("tag") 15650c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> tree.set(u"\u00e4ttr", u"v\u00e4lue") 15660c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> ET.tostring(tree, "utf-8") 15670c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<tag \\xc3\\xa4ttr="v\\xc3\\xa4lue" />' 15680c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 15690c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 15700c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 15710c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yidef bug_xmltoolkit54(): 15720c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 15730c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 15740c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi problems handling internally defined entities 15750c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 15760c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> e = ET.XML("<!DOCTYPE doc [<!ENTITY ldots '舰'>]><doc>&ldots;</doc>") 15770c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(e) 15780c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<doc>舰</doc>' 15790c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 15800c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 15810c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 15820c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yidef bug_xmltoolkit55(): 15830c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 15840c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 15850c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi make sure we're reporting the first error, not the last 15860c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 15870c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> e = ET.XML("<!DOCTYPE doc SYSTEM 'doc.dtd'><doc>&ldots;&ndots;&rdots;</doc>") 15880c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi Traceback (most recent call last): 15890c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ParseError: undefined entity &ldots;: line 1, column 36 15900c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 15910c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 15920c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 15930c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yiclass ExceptionFile: 15940c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi def read(self, x): 15950c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi raise IOError 15960c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 15970c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yidef xmltoolkit60(): 15980c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 15990c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 16000c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi Handle crash in stream source. 16010c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> tree = ET.parse(ExceptionFile()) 16020c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi Traceback (most recent call last): 16030c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi IOError 16040c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 16050c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 16060c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 16070c5958b1636c47ed7c284f859c8e805fd06a0e6Bill YiXMLTOOLKIT62_DOC = """<?xml version="1.0" encoding="UTF-8"?> 16080c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi<!DOCTYPE patent-application-publication SYSTEM "pap-v15-2001-01-31.dtd" []> 16090c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi<patent-application-publication> 16100c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi<subdoc-abstract> 16110c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi<paragraph id="A-0001" lvl="0">A new cultivar of Begonia plant named ‘BCT9801BEG’.</paragraph> 16120c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi</subdoc-abstract> 16130c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi</patent-application-publication>""" 16140c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 16150c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 16160c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yidef xmltoolkit62(): 16170c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 16180c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 16190c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi Don't crash when using custom entities. 16200c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 16210c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> xmltoolkit62() 16220c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi u'A new cultivar of Begonia plant named \u2018BCT9801BEG\u2019.' 16230c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 16240c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 16250c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ENTITIES = {u'rsquo': u'\u2019', u'lsquo': u'\u2018'} 16260c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi parser = ET.XMLTreeBuilder() 16270c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi parser.entity.update(ENTITIES) 16280c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi parser.feed(XMLTOOLKIT62_DOC) 16290c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi t = parser.close() 16300c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi return t.find('.//paragraph').text 16310c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 16320c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yidef xmltoolkit63(): 16330c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 16340c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 16350c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi Check reference leak. 16360c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> xmltoolkit63() 16370c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> count = sys.getrefcount(None) 16380c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> for i in range(1000): 16390c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ... xmltoolkit63() 16400c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> sys.getrefcount(None) - count 16410c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 0 16420c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 16430c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 16440c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi tree = ET.TreeBuilder() 16450c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi tree.start("tag", {}) 16460c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi tree.data("text") 16470c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi tree.end("tag") 16480c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 16490c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi# -------------------------------------------------------------------- 16500c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 16510c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 16520c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yidef bug_200708_newline(): 16530c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi r""" 16540c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 16550c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi Preserve newlines in attributes. 16560c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 16570c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> e = ET.Element('SomeTag', text="def _f():\n return 3\n") 16580c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> ET.tostring(e) 16590c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<SomeTag text="def _f(): return 3 " />' 16600c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> ET.XML(ET.tostring(e)).get("text") 16610c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 'def _f():\n return 3\n' 16620c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> ET.tostring(ET.XML(ET.tostring(e))) 16630c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<SomeTag text="def _f(): return 3 " />' 16640c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 16650c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 16660c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 16670c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yidef bug_200708_close(): 16680c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 16690c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 16700c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi Test default builder. 16710c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> parser = ET.XMLParser() # default 16720c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> parser.feed("<element>some text</element>") 16730c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> summarize(parser.close()) 16740c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 'element' 16750c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 16760c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi Test custom builder. 16770c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> class EchoTarget: 16780c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ... def close(self): 16790c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ... return ET.Element("element") # simulate root 16800c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> parser = ET.XMLParser(EchoTarget()) 16810c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> parser.feed("<element>some text</element>") 16820c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> summarize(parser.close()) 16830c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 'element' 16840c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 16850c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 16860c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 16870c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yidef bug_200709_default_namespace(): 16880c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 16890c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 16900c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> e = ET.Element("{default}elem") 16910c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> s = ET.SubElement(e, "{default}elem") 16920c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(e, default_namespace="default") # 1 16930c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<elem xmlns="default"><elem /></elem>' 16940c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 16950c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> e = ET.Element("{default}elem") 16960c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> s = ET.SubElement(e, "{default}elem") 16970c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> s = ET.SubElement(e, "{not-default}elem") 16980c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(e, default_namespace="default") # 2 16990c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<elem xmlns="default" xmlns:ns1="not-default"><elem /><ns1:elem /></elem>' 17000c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 17010c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> e = ET.Element("{default}elem") 17020c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> s = ET.SubElement(e, "{default}elem") 17030c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> s = ET.SubElement(e, "elem") # unprefixed name 17040c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(e, default_namespace="default") # 3 17050c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi Traceback (most recent call last): 17060c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ValueError: cannot use non-qualified names with default_namespace option 17070c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 17080c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 17090c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 17100c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yidef bug_200709_register_namespace(): 17110c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 17120c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 17130c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> ET.tostring(ET.Element("{http://namespace.invalid/does/not/exist/}title")) 17140c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<ns0:title xmlns:ns0="http://namespace.invalid/does/not/exist/" />' 17150c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> ET.register_namespace("foo", "http://namespace.invalid/does/not/exist/") 17160c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> ET.tostring(ET.Element("{http://namespace.invalid/does/not/exist/}title")) 17170c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<foo:title xmlns:foo="http://namespace.invalid/does/not/exist/" />' 17180c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 17190c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi And the Dublin Core namespace is in the default list: 17200c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 17210c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> ET.tostring(ET.Element("{http://purl.org/dc/elements/1.1/}title")) 17220c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<dc:title xmlns:dc="http://purl.org/dc/elements/1.1/" />' 17230c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 17240c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 17250c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 17260c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yidef bug_200709_element_comment(): 17270c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 17280c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 17290c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi Not sure if this can be fixed, really (since the serializer needs 17300c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ET.Comment, not cET.comment). 17310c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 17320c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> a = ET.Element('a') 17330c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> a.append(ET.Comment('foo')) 17340c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> a[0].tag == ET.Comment 17350c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi True 17360c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 17370c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> a = ET.Element('a') 17380c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> a.append(ET.PI('foo')) 17390c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> a[0].tag == ET.PI 17400c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi True 17410c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 17420c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 17430c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 17440c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yidef bug_200709_element_insert(): 17450c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 17460c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 17470c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> a = ET.Element('a') 17480c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> b = ET.SubElement(a, 'b') 17490c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> c = ET.SubElement(a, 'c') 17500c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> d = ET.Element('d') 17510c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> a.insert(0, d) 17520c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> summarize_list(a) 17530c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ['d', 'b', 'c'] 17540c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> a.insert(-1, d) 17550c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> summarize_list(a) 17560c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ['d', 'b', 'd', 'c'] 17570c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 17580c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 17590c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 17600c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yidef bug_200709_iter_comment(): 17610c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 17620c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 17630c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> a = ET.Element('a') 17640c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> b = ET.SubElement(a, 'b') 17650c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> comment_b = ET.Comment("TEST-b") 17660c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> b.append(comment_b) 17670c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> summarize_list(a.iter(ET.Comment)) 17680c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ['<Comment>'] 17690c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 17700c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 17710c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 17720c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi# -------------------------------------------------------------------- 17730c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi# reported on bugs.python.org 17740c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 17750c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yidef bug_1534630(): 17760c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 17770c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 17780c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> bob = ET.TreeBuilder() 17790c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> e = bob.data("data") 17800c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> e = bob.start("tag", {}) 17810c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> e = bob.end("tag") 17820c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> e = bob.close() 17830c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(e) 17840c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<tag />' 17850c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 17860c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 17870c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 17880c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yidef check_issue6233(): 17890c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 17900c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 17910c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> e = ET.XML("<?xml version='1.0' encoding='utf-8'?><body>t\\xc3\\xa3g</body>") 17920c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> ET.tostring(e, 'ascii') 17930c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi "<?xml version='1.0' encoding='ascii'?>\\n<body>tãg</body>" 17940c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> e = ET.XML("<?xml version='1.0' encoding='iso-8859-1'?><body>t\\xe3g</body>") 17950c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> ET.tostring(e, 'ascii') 17960c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi "<?xml version='1.0' encoding='ascii'?>\\n<body>tãg</body>" 17970c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 17980c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 17990c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 18000c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yidef check_issue3151(): 18010c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 18020c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 18030c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> e = ET.XML('<prefix:localname xmlns:prefix="${stuff}"/>') 18040c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> e.tag 18050c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '{${stuff}}localname' 18060c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> t = ET.ElementTree(e) 18070c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> ET.tostring(e) 18080c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<ns0:localname xmlns:ns0="${stuff}" />' 18090c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 18100c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 18110c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 18120c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yidef check_issue6565(): 18130c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 18140c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 18150c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem = ET.XML("<body><tag/></body>") 18160c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> summarize_list(elem) 18170c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ['tag'] 18180c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> newelem = ET.XML(SAMPLE_XML) 18190c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elem[:] = newelem[:] 18200c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> summarize_list(elem) 18210c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ['tag', 'tag', 'section'] 18220c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 18230c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 18240c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 18250c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yidef check_html_empty_elems_serialization(self): 18260c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi # issue 15970 18270c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi # from http://www.w3.org/TR/html401/index/elements.html 18280c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 18290c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 18300c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> empty_elems = ['AREA', 'BASE', 'BASEFONT', 'BR', 'COL', 'FRAME', 'HR', 18310c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ... 'IMG', 'INPUT', 'ISINDEX', 'LINK', 'META', 'PARAM'] 18320c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elems = ''.join('<%s />' % elem for elem in empty_elems) 18330c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(ET.XML('<html>%s</html>' % elems), method='html') 18340c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<html><AREA><BASE><BASEFONT><BR><COL><FRAME><HR><IMG><INPUT><ISINDEX><LINK><META><PARAM></html>' 18350c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(ET.XML('<html>%s</html>' % elems.lower()), method='html') 18360c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<html><area><base><basefont><br><col><frame><hr><img><input><isindex><link><meta><param></html>' 18370c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> elems = ''.join('<%s></%s>' % (elem, elem) for elem in empty_elems) 18380c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(ET.XML('<html>%s</html>' % elems), method='html') 18390c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<html><AREA><BASE><BASEFONT><BR><COL><FRAME><HR><IMG><INPUT><ISINDEX><LINK><META><PARAM></html>' 18400c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi >>> serialize(ET.XML('<html>%s</html>' % elems.lower()), method='html') 18410c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi '<html><area><base><basefont><br><col><frame><hr><img><input><isindex><link><meta><param></html>' 18420c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 18430c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """ 18440c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 18450c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi# -------------------------------------------------------------------- 18460c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 18470c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 18480c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yiclass CleanContext(object): 18490c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi """Provide default namespace mapping and path cache.""" 18500c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi checkwarnings = None 18510c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 18520c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi def __init__(self, quiet=False): 18530c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi if sys.flags.optimize >= 2: 18540c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi # under -OO, doctests cannot be run and therefore not all warnings 18550c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi # will be emitted 18560c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi quiet = True 18570c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi deprecations = ( 18580c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi # Search behaviour is broken if search path starts with "/". 18590c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ("This search is broken in 1.3 and earlier, and will be fixed " 18600c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi "in a future version. If you rely on the current behaviour, " 18610c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi "change it to '.+'", FutureWarning), 18620c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi # Element.getchildren() and Element.getiterator() are deprecated. 18630c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ("This method will be removed in future versions. " 18640c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi "Use .+ instead.", DeprecationWarning), 18650c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ("This method will be removed in future versions. " 18660c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi "Use .+ instead.", PendingDeprecationWarning), 18670c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi # XMLParser.doctype() is deprecated. 18680c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ("This method of XMLParser is deprecated. Define doctype.. " 18690c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi "method on the TreeBuilder target.", DeprecationWarning)) 18700c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi self.checkwarnings = test_support.check_warnings(*deprecations, 18710c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi quiet=quiet) 18720c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 18730c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi def __enter__(self): 18740c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi from xml.etree import ElementTree 18750c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi self._nsmap = ElementTree._namespace_map 18760c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi self._path_cache = ElementTree.ElementPath._cache 18770c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi # Copy the default namespace mapping 18780c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ElementTree._namespace_map = self._nsmap.copy() 18790c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi # Copy the path cache (should be empty) 18800c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ElementTree.ElementPath._cache = self._path_cache.copy() 18810c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi self.checkwarnings.__enter__() 18820c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 18830c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi def __exit__(self, *args): 18840c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi from xml.etree import ElementTree 18850c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi # Restore mapping and path cache 18860c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ElementTree._namespace_map = self._nsmap 18870c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi ElementTree.ElementPath._cache = self._path_cache 18880c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi self.checkwarnings.__exit__(*args) 18890c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 18900c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 18910c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yidef test_main(module_name='xml.etree.ElementTree'): 18920c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi from test import test_xml_etree 18930c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 18940c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi use_py_module = (module_name == 'xml.etree.ElementTree') 18950c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 18960c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi # The same doctests are used for both the Python and the C implementations 18970c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi assert test_xml_etree.ET.__name__ == module_name 18980c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 18990c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi # XXX the C module should give the same warnings as the Python module 19000c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi with CleanContext(quiet=not use_py_module): 19010c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi test_support.run_doctest(test_xml_etree, verbosity=True) 19020c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 19030c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi # The module should not be changed by the tests 19040c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi assert test_xml_etree.ET.__name__ == module_name 19050c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi 19060c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yiif __name__ == '__main__': 19070c5958b1636c47ed7c284f859c8e805fd06a0e6Bill Yi test_main() 1908