-# xmlcore.etree test. This file contains enough tests to make sure that\r
-# all included components work as they should. For a more extensive\r
-# test suite, see the selftest script in the ElementTree distribution.\r
-\r
-import doctest, sys\r
-\r
-from test import test_support\r
-\r
-SAMPLE_XML = """\r
-<body>\r
- <tag>text</tag>\r
- <tag />\r
- <section>\r
- <tag>subtext</tag>\r
- </section>\r
-</body>\r
-"""\r
-\r
-SAMPLE_XML_NS = """\r
-<body xmlns="http://effbot.org/ns">\r
- <tag>text</tag>\r
- <tag />\r
- <section>\r
- <tag>subtext</tag>\r
- </section>\r
-</body>\r
-"""\r
-\r
-def sanity():\r
- """\r
- Import sanity.\r
-\r
- >>> from xmlcore.etree import ElementTree\r
- >>> from xmlcore.etree import ElementInclude\r
- >>> from xmlcore.etree import ElementPath\r
- """\r
-\r
-def check_method(method):\r
- if not callable(method):\r
- print method, "not callable"\r
-\r
-def serialize(ET, elem, encoding=None):\r
- import StringIO\r
- file = StringIO.StringIO()\r
- tree = ET.ElementTree(elem)\r
- if encoding:\r
- tree.write(file, encoding)\r
- else:\r
- tree.write(file)\r
- return file.getvalue()\r
-\r
-def summarize(elem):\r
- return elem.tag\r
-\r
-def summarize_list(seq):\r
- return map(summarize, seq)\r
-\r
-def interface():\r
- """\r
- Test element tree interface.\r
-\r
- >>> from xmlcore.etree import ElementTree as ET\r
-\r
- >>> element = ET.Element("tag", key="value")\r
- >>> tree = ET.ElementTree(element)\r
-\r
- Make sure all standard element methods exist.\r
-\r
- >>> check_method(element.append)\r
- >>> check_method(element.insert)\r
- >>> check_method(element.remove)\r
- >>> check_method(element.getchildren)\r
- >>> check_method(element.find)\r
- >>> check_method(element.findall)\r
- >>> check_method(element.findtext)\r
- >>> check_method(element.clear)\r
- >>> check_method(element.get)\r
- >>> check_method(element.set)\r
- >>> check_method(element.keys)\r
- >>> check_method(element.items)\r
- >>> check_method(element.getiterator)\r
-\r
- Basic method sanity checks.\r
-\r
- >>> serialize(ET, element) # 1\r
- '<tag key="value" />'\r
- >>> subelement = ET.Element("subtag")\r
- >>> element.append(subelement)\r
- >>> serialize(ET, element) # 2\r
- '<tag key="value"><subtag /></tag>'\r
- >>> element.insert(0, subelement)\r
- >>> serialize(ET, element) # 3\r
- '<tag key="value"><subtag /><subtag /></tag>'\r
- >>> element.remove(subelement)\r
- >>> serialize(ET, element) # 4\r
- '<tag key="value"><subtag /></tag>'\r
- >>> element.remove(subelement)\r
- >>> serialize(ET, element) # 5\r
- '<tag key="value" />'\r
- >>> element.remove(subelement)\r
- Traceback (most recent call last):\r
- ValueError: list.remove(x): x not in list\r
- >>> serialize(ET, element) # 6\r
- '<tag key="value" />'\r
- """\r
-\r
-def find():\r
- """\r
- Test find methods (including xpath syntax).\r
-\r
- >>> from xmlcore.etree import ElementTree as ET\r
-\r
- >>> elem = ET.XML(SAMPLE_XML)\r
- >>> elem.find("tag").tag\r
- 'tag'\r
- >>> ET.ElementTree(elem).find("tag").tag\r
- 'tag'\r
- >>> elem.find("section/tag").tag\r
- 'tag'\r
- >>> ET.ElementTree(elem).find("section/tag").tag\r
- 'tag'\r
- >>> elem.findtext("tag")\r
- 'text'\r
- >>> elem.findtext("tog")\r
- >>> elem.findtext("tog", "default")\r
- 'default'\r
- >>> ET.ElementTree(elem).findtext("tag")\r
- 'text'\r
- >>> elem.findtext("section/tag")\r
- 'subtext'\r
- >>> ET.ElementTree(elem).findtext("section/tag")\r
- 'subtext'\r
- >>> summarize_list(elem.findall("tag"))\r
- ['tag', 'tag']\r
- >>> summarize_list(elem.findall("*"))\r
- ['tag', 'tag', 'section']\r
- >>> summarize_list(elem.findall(".//tag"))\r
- ['tag', 'tag', 'tag']\r
- >>> summarize_list(elem.findall("section/tag"))\r
- ['tag']\r
- >>> summarize_list(elem.findall("section//tag"))\r
- ['tag']\r
- >>> summarize_list(elem.findall("section/*"))\r
- ['tag']\r
- >>> summarize_list(elem.findall("section//*"))\r
- ['tag']\r
- >>> summarize_list(elem.findall("section/.//*"))\r
- ['tag']\r
- >>> summarize_list(elem.findall("*/*"))\r
- ['tag']\r
- >>> summarize_list(elem.findall("*//*"))\r
- ['tag']\r
- >>> summarize_list(elem.findall("*/tag"))\r
- ['tag']\r
- >>> summarize_list(elem.findall("*/./tag"))\r
- ['tag']\r
- >>> summarize_list(elem.findall("./tag"))\r
- ['tag', 'tag']\r
- >>> summarize_list(elem.findall(".//tag"))\r
- ['tag', 'tag', 'tag']\r
- >>> summarize_list(elem.findall("././tag"))\r
- ['tag', 'tag']\r
- >>> summarize_list(ET.ElementTree(elem).findall("/tag"))\r
- ['tag', 'tag']\r
- >>> summarize_list(ET.ElementTree(elem).findall("./tag"))\r
- ['tag', 'tag']\r
- >>> elem = ET.XML(SAMPLE_XML_NS)\r
- >>> summarize_list(elem.findall("tag"))\r
- []\r
- >>> summarize_list(elem.findall("{http://effbot.org/ns}tag"))\r
- ['{http://effbot.org/ns}tag', '{http://effbot.org/ns}tag']\r
- >>> summarize_list(elem.findall(".//{http://effbot.org/ns}tag"))\r
- ['{http://effbot.org/ns}tag', '{http://effbot.org/ns}tag', '{http://effbot.org/ns}tag']\r
- """\r
-\r
-def parseliteral():\r
- r"""\r
-\r
- >>> from xmlcore.etree import ElementTree as ET\r
-\r
- >>> element = ET.XML("<html><body>text</body></html>")\r
- >>> ET.ElementTree(element).write(sys.stdout)\r
- <html><body>text</body></html>\r
- >>> element = ET.fromstring("<html><body>text</body></html>")\r
- >>> ET.ElementTree(element).write(sys.stdout)\r
- <html><body>text</body></html>\r
- >>> print ET.tostring(element)\r
- <html><body>text</body></html>\r
- >>> print ET.tostring(element, "ascii")\r
- <?xml version='1.0' encoding='ascii'?>\r
- <html><body>text</body></html>\r
- >>> _, ids = ET.XMLID("<html><body>text</body></html>")\r
- >>> len(ids)\r
- 0\r
- >>> _, ids = ET.XMLID("<html><body id='body'>text</body></html>")\r
- >>> len(ids)\r
- 1\r
- >>> ids["body"].tag\r
- 'body'\r
- """\r
-\r
-#\r
-# xinclude tests (samples from appendix C of the xinclude specification)\r
-\r
-XINCLUDE = {}\r
-\r
-XINCLUDE["C1.xml"] = """\\r
-<?xml version='1.0'?>\r
-<document xmlns:xi="http://www.w3.org/2001/XInclude">\r
- <p>120 Mz is adequate for an average home user.</p>\r
- <xi:include href="disclaimer.xml"/>\r
-</document>\r
-"""\r
-\r
-XINCLUDE["disclaimer.xml"] = """\\r
-<?xml version='1.0'?>\r
-<disclaimer>\r
- <p>The opinions represented herein represent those of the individual\r
- and should not be interpreted as official policy endorsed by this\r
- organization.</p>\r
-</disclaimer>\r
-"""\r
-\r
-XINCLUDE["C2.xml"] = """\\r
-<?xml version='1.0'?>\r
-<document xmlns:xi="http://www.w3.org/2001/XInclude">\r
- <p>This document has been accessed\r
- <xi:include href="count.txt" parse="text"/> times.</p>\r
-</document>\r
-"""\r
-\r
-XINCLUDE["count.txt"] = "324387"\r
-\r
-XINCLUDE["C3.xml"] = """\\r
-<?xml version='1.0'?>\r
-<document xmlns:xi="http://www.w3.org/2001/XInclude">\r
- <p>The following is the source of the "data.xml" resource:</p>\r
- <example><xi:include href="data.xml" parse="text"/></example>\r
-</document>\r
-"""\r
-\r
-XINCLUDE["data.xml"] = """\\r
-<?xml version='1.0'?>\r
-<data>\r
- <item><![CDATA[Brooks & Shields]]></item>\r
-</data>\r
-"""\r
-\r
-XINCLUDE["C5.xml"] = """\\r
-<?xml version='1.0'?>\r
-<div xmlns:xi="http://www.w3.org/2001/XInclude">\r
- <xi:include href="example.txt" parse="text">\r
- <xi:fallback>\r
- <xi:include href="fallback-example.txt" parse="text">\r
- <xi:fallback><a href="mailto:bob@example.org">Report error</a></xi:fallback>\r
- </xi:include>\r
- </xi:fallback>\r
- </xi:include>\r
-</div>\r
-"""\r
-\r
-XINCLUDE["default.xml"] = """\\r
-<?xml version='1.0'?>\r
-<document xmlns:xi="http://www.w3.org/2001/XInclude">\r
- <p>Example.</p>\r
- <xi:include href="samples/simple.xml"/>\r
-</document>\r
-"""\r
-\r
-def xinclude_loader(href, parse="xml", encoding=None):\r
- try:\r
- data = XINCLUDE[href]\r
- except KeyError:\r
- raise IOError("resource not found")\r
- if parse == "xml":\r
- from xmlcore.etree.ElementTree import XML\r
- return XML(data)\r
- return data\r
-\r
-def xinclude():\r
- r"""\r
- Basic inclusion example (XInclude C.1)\r
-\r
- >>> from xmlcore.etree import ElementTree as ET\r
- >>> from xmlcore.etree import ElementInclude\r
-\r
- >>> document = xinclude_loader("C1.xml")\r
- >>> ElementInclude.include(document, xinclude_loader)\r
- >>> print serialize(ET, document) # C1\r
- <document>\r
- <p>120 Mz is adequate for an average home user.</p>\r
- <disclaimer>\r
- <p>The opinions represented herein represent those of the individual\r
- and should not be interpreted as official policy endorsed by this\r
- organization.</p>\r
- </disclaimer>\r
- </document>\r
-\r
- Textual inclusion example (XInclude C.2)\r
-\r
- >>> document = xinclude_loader("C2.xml")\r
- >>> ElementInclude.include(document, xinclude_loader)\r
- >>> print serialize(ET, document) # C2\r
- <document>\r
- <p>This document has been accessed\r
- 324387 times.</p>\r
- </document>\r
-\r
- Textual inclusion of XML example (XInclude C.3)\r
-\r
- >>> document = xinclude_loader("C3.xml")\r
- >>> ElementInclude.include(document, xinclude_loader)\r
- >>> print serialize(ET, document) # C3\r
- <document>\r
- <p>The following is the source of the "data.xml" resource:</p>\r
- <example><?xml version='1.0'?>\r
- <data>\r
- <item><![CDATA[Brooks & Shields]]></item>\r
- </data>\r
- </example>\r
- </document>\r
-\r
- Fallback example (XInclude C.5)\r
- Note! Fallback support is not yet implemented\r
-\r
- >>> document = xinclude_loader("C5.xml")\r
- >>> ElementInclude.include(document, xinclude_loader)\r
- Traceback (most recent call last):\r
- IOError: resource not found\r
- >>> # print serialize(ET, document) # C5\r
-\r
- """\r
-\r
-def test_main():\r
- from test import test_xml_etree\r
- test_support.run_doctest(test_xml_etree, verbosity=True)\r
-\r
-if __name__ == '__main__':\r
- test_main()\r
+# xmlcore.etree test. This file contains enough tests to make sure that
+# all included components work as they should. For a more extensive
+# test suite, see the selftest script in the ElementTree distribution.
+
+import doctest, sys
+
+from test import test_support
+
+SAMPLE_XML = """
+<body>
+ <tag>text</tag>
+ <tag />
+ <section>
+ <tag>subtext</tag>
+ </section>
+</body>
+"""
+
+SAMPLE_XML_NS = """
+<body xmlns="http://effbot.org/ns">
+ <tag>text</tag>
+ <tag />
+ <section>
+ <tag>subtext</tag>
+ </section>
+</body>
+"""
+
+def sanity():
+ """
+ Import sanity.
+
+ >>> from xmlcore.etree import ElementTree
+ >>> from xmlcore.etree import ElementInclude
+ >>> from xmlcore.etree import ElementPath
+ """
+
+def check_method(method):
+ if not callable(method):
+ print method, "not callable"
+
+def serialize(ET, elem, encoding=None):
+ import StringIO
+ file = StringIO.StringIO()
+ tree = ET.ElementTree(elem)
+ if encoding:
+ tree.write(file, encoding)
+ else:
+ tree.write(file)
+ return file.getvalue()
+
+def summarize(elem):
+ return elem.tag
+
+def summarize_list(seq):
+ return map(summarize, seq)
+
+def interface():
+ """
+ Test element tree interface.
+
+ >>> from xmlcore.etree import ElementTree as ET
+
+ >>> element = ET.Element("tag", key="value")
+ >>> tree = ET.ElementTree(element)
+
+ Make sure all standard element methods exist.
+
+ >>> check_method(element.append)
+ >>> check_method(element.insert)
+ >>> check_method(element.remove)
+ >>> check_method(element.getchildren)
+ >>> check_method(element.find)
+ >>> check_method(element.findall)
+ >>> check_method(element.findtext)
+ >>> check_method(element.clear)
+ >>> check_method(element.get)
+ >>> check_method(element.set)
+ >>> check_method(element.keys)
+ >>> check_method(element.items)
+ >>> check_method(element.getiterator)
+
+ Basic method sanity checks.
+
+ >>> serialize(ET, element) # 1
+ '<tag key="value" />'
+ >>> subelement = ET.Element("subtag")
+ >>> element.append(subelement)
+ >>> serialize(ET, element) # 2
+ '<tag key="value"><subtag /></tag>'
+ >>> element.insert(0, subelement)
+ >>> serialize(ET, element) # 3
+ '<tag key="value"><subtag /><subtag /></tag>'
+ >>> element.remove(subelement)
+ >>> serialize(ET, element) # 4
+ '<tag key="value"><subtag /></tag>'
+ >>> element.remove(subelement)
+ >>> serialize(ET, element) # 5
+ '<tag key="value" />'
+ >>> element.remove(subelement)
+ Traceback (most recent call last):
+ ValueError: list.remove(x): x not in list
+ >>> serialize(ET, element) # 6
+ '<tag key="value" />'
+ """
+
+def find():
+ """
+ Test find methods (including xpath syntax).
+
+ >>> from xmlcore.etree import ElementTree as ET
+
+ >>> elem = ET.XML(SAMPLE_XML)
+ >>> elem.find("tag").tag
+ 'tag'
+ >>> ET.ElementTree(elem).find("tag").tag
+ 'tag'
+ >>> elem.find("section/tag").tag
+ 'tag'
+ >>> ET.ElementTree(elem).find("section/tag").tag
+ 'tag'
+ >>> elem.findtext("tag")
+ 'text'
+ >>> elem.findtext("tog")
+ >>> elem.findtext("tog", "default")
+ 'default'
+ >>> ET.ElementTree(elem).findtext("tag")
+ 'text'
+ >>> elem.findtext("section/tag")
+ 'subtext'
+ >>> ET.ElementTree(elem).findtext("section/tag")
+ 'subtext'
+ >>> summarize_list(elem.findall("tag"))
+ ['tag', 'tag']
+ >>> summarize_list(elem.findall("*"))
+ ['tag', 'tag', 'section']
+ >>> summarize_list(elem.findall(".//tag"))
+ ['tag', 'tag', 'tag']
+ >>> summarize_list(elem.findall("section/tag"))
+ ['tag']
+ >>> summarize_list(elem.findall("section//tag"))
+ ['tag']
+ >>> summarize_list(elem.findall("section/*"))
+ ['tag']
+ >>> summarize_list(elem.findall("section//*"))
+ ['tag']
+ >>> summarize_list(elem.findall("section/.//*"))
+ ['tag']
+ >>> summarize_list(elem.findall("*/*"))
+ ['tag']
+ >>> summarize_list(elem.findall("*//*"))
+ ['tag']
+ >>> summarize_list(elem.findall("*/tag"))
+ ['tag']
+ >>> summarize_list(elem.findall("*/./tag"))
+ ['tag']
+ >>> summarize_list(elem.findall("./tag"))
+ ['tag', 'tag']
+ >>> summarize_list(elem.findall(".//tag"))
+ ['tag', 'tag', 'tag']
+ >>> summarize_list(elem.findall("././tag"))
+ ['tag', 'tag']
+ >>> summarize_list(ET.ElementTree(elem).findall("/tag"))
+ ['tag', 'tag']
+ >>> summarize_list(ET.ElementTree(elem).findall("./tag"))
+ ['tag', 'tag']
+ >>> elem = ET.XML(SAMPLE_XML_NS)
+ >>> summarize_list(elem.findall("tag"))
+ []
+ >>> summarize_list(elem.findall("{http://effbot.org/ns}tag"))
+ ['{http://effbot.org/ns}tag', '{http://effbot.org/ns}tag']
+ >>> summarize_list(elem.findall(".//{http://effbot.org/ns}tag"))
+ ['{http://effbot.org/ns}tag', '{http://effbot.org/ns}tag', '{http://effbot.org/ns}tag']
+ """
+
+def parseliteral():
+ r"""
+
+ >>> from xmlcore.etree import ElementTree as ET
+
+ >>> element = ET.XML("<html><body>text</body></html>")
+ >>> ET.ElementTree(element).write(sys.stdout)
+ <html><body>text</body></html>
+ >>> element = ET.fromstring("<html><body>text</body></html>")
+ >>> ET.ElementTree(element).write(sys.stdout)
+ <html><body>text</body></html>
+ >>> print ET.tostring(element)
+ <html><body>text</body></html>
+ >>> print ET.tostring(element, "ascii")
+ <?xml version='1.0' encoding='ascii'?>
+ <html><body>text</body></html>
+ >>> _, ids = ET.XMLID("<html><body>text</body></html>")
+ >>> len(ids)
+ 0
+ >>> _, ids = ET.XMLID("<html><body id='body'>text</body></html>")
+ >>> len(ids)
+ 1
+ >>> ids["body"].tag
+ 'body'
+ """
+
+#
+# xinclude tests (samples from appendix C of the xinclude specification)
+
+XINCLUDE = {}
+
+XINCLUDE["C1.xml"] = """\
+<?xml version='1.0'?>
+<document xmlns:xi="http://www.w3.org/2001/XInclude">
+ <p>120 Mz is adequate for an average home user.</p>
+ <xi:include href="disclaimer.xml"/>
+</document>
+"""
+
+XINCLUDE["disclaimer.xml"] = """\
+<?xml version='1.0'?>
+<disclaimer>
+ <p>The opinions represented herein represent those of the individual
+ and should not be interpreted as official policy endorsed by this
+ organization.</p>
+</disclaimer>
+"""
+
+XINCLUDE["C2.xml"] = """\
+<?xml version='1.0'?>
+<document xmlns:xi="http://www.w3.org/2001/XInclude">
+ <p>This document has been accessed
+ <xi:include href="count.txt" parse="text"/> times.</p>
+</document>
+"""
+
+XINCLUDE["count.txt"] = "324387"
+
+XINCLUDE["C3.xml"] = """\
+<?xml version='1.0'?>
+<document xmlns:xi="http://www.w3.org/2001/XInclude">
+ <p>The following is the source of the "data.xml" resource:</p>
+ <example><xi:include href="data.xml" parse="text"/></example>
+</document>
+"""
+
+XINCLUDE["data.xml"] = """\
+<?xml version='1.0'?>
+<data>
+ <item><![CDATA[Brooks & Shields]]></item>
+</data>
+"""
+
+XINCLUDE["C5.xml"] = """\
+<?xml version='1.0'?>
+<div xmlns:xi="http://www.w3.org/2001/XInclude">
+ <xi:include href="example.txt" parse="text">
+ <xi:fallback>
+ <xi:include href="fallback-example.txt" parse="text">
+ <xi:fallback><a href="mailto:bob@example.org">Report error</a></xi:fallback>
+ </xi:include>
+ </xi:fallback>
+ </xi:include>
+</div>
+"""
+
+XINCLUDE["default.xml"] = """\
+<?xml version='1.0'?>
+<document xmlns:xi="http://www.w3.org/2001/XInclude">
+ <p>Example.</p>
+ <xi:include href="samples/simple.xml"/>
+</document>
+"""
+
+def xinclude_loader(href, parse="xml", encoding=None):
+ try:
+ data = XINCLUDE[href]
+ except KeyError:
+ raise IOError("resource not found")
+ if parse == "xml":
+ from xmlcore.etree.ElementTree import XML
+ return XML(data)
+ return data
+
+def xinclude():
+ r"""
+ Basic inclusion example (XInclude C.1)
+
+ >>> from xmlcore.etree import ElementTree as ET
+ >>> from xmlcore.etree import ElementInclude
+
+ >>> document = xinclude_loader("C1.xml")
+ >>> ElementInclude.include(document, xinclude_loader)
+ >>> print serialize(ET, document) # C1
+ <document>
+ <p>120 Mz is adequate for an average home user.</p>
+ <disclaimer>
+ <p>The opinions represented herein represent those of the individual
+ and should not be interpreted as official policy endorsed by this
+ organization.</p>
+ </disclaimer>
+ </document>
+
+ Textual inclusion example (XInclude C.2)
+
+ >>> document = xinclude_loader("C2.xml")
+ >>> ElementInclude.include(document, xinclude_loader)
+ >>> print serialize(ET, document) # C2
+ <document>
+ <p>This document has been accessed
+ 324387 times.</p>
+ </document>
+
+ Textual inclusion of XML example (XInclude C.3)
+
+ >>> document = xinclude_loader("C3.xml")
+ >>> ElementInclude.include(document, xinclude_loader)
+ >>> print serialize(ET, document) # C3
+ <document>
+ <p>The following is the source of the "data.xml" resource:</p>
+ <example><?xml version='1.0'?>
+ <data>
+ <item><![CDATA[Brooks & Shields]]></item>
+ </data>
+ </example>
+ </document>
+
+ Fallback example (XInclude C.5)
+ Note! Fallback support is not yet implemented
+
+ >>> document = xinclude_loader("C5.xml")
+ >>> ElementInclude.include(document, xinclude_loader)
+ Traceback (most recent call last):
+ IOError: resource not found
+ >>> # print serialize(ET, document) # C5
+
+ """
+
+def test_main():
+ from test import test_xml_etree
+ test_support.run_doctest(test_xml_etree, verbosity=True)
+
+if __name__ == '__main__':
+ test_main()
-#\r
-# ElementTree\r
-# $Id: ElementTree.py 2326 2005-03-17 07:45:21Z fredrik $\r
-#\r
-# light-weight XML support for Python 1.5.2 and later.\r
-#\r
-# history:\r
-# 2001-10-20 fl created (from various sources)\r
-# 2001-11-01 fl return root from parse method\r
-# 2002-02-16 fl sort attributes in lexical order\r
-# 2002-04-06 fl TreeBuilder refactoring, added PythonDoc markup\r
-# 2002-05-01 fl finished TreeBuilder refactoring\r
-# 2002-07-14 fl added basic namespace support to ElementTree.write\r
-# 2002-07-25 fl added QName attribute support\r
-# 2002-10-20 fl fixed encoding in write\r
-# 2002-11-24 fl changed default encoding to ascii; fixed attribute encoding\r
-# 2002-11-27 fl accept file objects or file names for parse/write\r
-# 2002-12-04 fl moved XMLTreeBuilder back to this module\r
-# 2003-01-11 fl fixed entity encoding glitch for us-ascii\r
-# 2003-02-13 fl added XML literal factory\r
-# 2003-02-21 fl added ProcessingInstruction/PI factory\r
-# 2003-05-11 fl added tostring/fromstring helpers\r
-# 2003-05-26 fl added ElementPath support\r
-# 2003-07-05 fl added makeelement factory method\r
-# 2003-07-28 fl added more well-known namespace prefixes\r
-# 2003-08-15 fl fixed typo in ElementTree.findtext (Thomas Dartsch)\r
-# 2003-09-04 fl fall back on emulator if ElementPath is not installed\r
-# 2003-10-31 fl markup updates\r
-# 2003-11-15 fl fixed nested namespace bug\r
-# 2004-03-28 fl added XMLID helper\r
-# 2004-06-02 fl added default support to findtext\r
-# 2004-06-08 fl fixed encoding of non-ascii element/attribute names\r
-# 2004-08-23 fl take advantage of post-2.1 expat features\r
-# 2005-02-01 fl added iterparse implementation\r
-# 2005-03-02 fl fixed iterparse support for pre-2.2 versions\r
-#\r
-# Copyright (c) 1999-2005 by Fredrik Lundh. All rights reserved.\r
-#\r
-# fredrik@pythonware.com\r
-# http://www.pythonware.com\r
-#\r
-# --------------------------------------------------------------------\r
-# The ElementTree toolkit is\r
-#\r
-# Copyright (c) 1999-2005 by Fredrik Lundh\r
-#\r
-# By obtaining, using, and/or copying this software and/or its\r
-# associated documentation, you agree that you have read, understood,\r
-# and will comply with the following terms and conditions:\r
-#\r
-# Permission to use, copy, modify, and distribute this software and\r
-# its associated documentation for any purpose and without fee is\r
-# hereby granted, provided that the above copyright notice appears in\r
-# all copies, and that both that copyright notice and this permission\r
-# notice appear in supporting documentation, and that the name of\r
-# Secret Labs AB or the author not be used in advertising or publicity\r
-# pertaining to distribution of the software without specific, written\r
-# prior permission.\r
-#\r
-# SECRET LABS AB AND THE AUTHOR DISCLAIMS ALL WARRANTIES WITH REGARD\r
-# TO THIS SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANT-\r
-# ABILITY AND FITNESS. IN NO EVENT SHALL SECRET LABS AB OR THE AUTHOR\r
-# BE LIABLE FOR ANY SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY\r
-# DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS,\r
-# WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS\r
-# ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE\r
-# OF THIS SOFTWARE.\r
-# --------------------------------------------------------------------\r
-\r
-__all__ = [\r
- # public symbols\r
- "Comment",\r
- "dump",\r
- "Element", "ElementTree",\r
- "fromstring",\r
- "iselement", "iterparse",\r
- "parse",\r
- "PI", "ProcessingInstruction",\r
- "QName",\r
- "SubElement",\r
- "tostring",\r
- "TreeBuilder",\r
- "VERSION", "XML",\r
- "XMLTreeBuilder",\r
- ]\r
-\r
-##\r
-# The <b>Element</b> type is a flexible container object, designed to\r
-# store hierarchical data structures in memory. The type can be\r
-# described as a cross between a list and a dictionary.\r
-# <p>\r
-# Each element has a number of properties associated with it:\r
-# <ul>\r
-# <li>a <i>tag</i>. This is a string identifying what kind of data\r
-# this element represents (the element type, in other words).</li>\r
-# <li>a number of <i>attributes</i>, stored in a Python dictionary.</li>\r
-# <li>a <i>text</i> string.</li>\r
-# <li>an optional <i>tail</i> string.</li>\r
-# <li>a number of <i>child elements</i>, stored in a Python sequence</li>\r
-# </ul>\r
-#\r
-# To create an element instance, use the {@link #Element} or {@link\r
-# #SubElement} factory functions.\r
-# <p>\r
-# The {@link #ElementTree} class can be used to wrap an element\r
-# structure, and convert it from and to XML.\r
-##\r
-\r
-import string, sys, re\r
-\r
-class _SimpleElementPath:\r
- # emulate pre-1.2 find/findtext/findall behaviour\r
- def find(self, element, tag):\r
- for elem in element:\r
- if elem.tag == tag:\r
- return elem\r
- return None\r
- def findtext(self, element, tag, default=None):\r
- for elem in element:\r
- if elem.tag == tag:\r
- return elem.text or ""\r
- return default\r
- def findall(self, element, tag):\r
- if tag[:3] == ".//":\r
- return element.getiterator(tag[3:])\r
- result = []\r
- for elem in element:\r
- if elem.tag == tag:\r
- result.append(elem)\r
- return result\r
-\r
-try:\r
- import ElementPath\r
-except ImportError:\r
- # FIXME: issue warning in this case?\r
- ElementPath = _SimpleElementPath()\r
-\r
-# TODO: add support for custom namespace resolvers/default namespaces\r
-# TODO: add improved support for incremental parsing\r
-\r
-VERSION = "1.2.6"\r
-\r
-##\r
-# Internal element class. This class defines the Element interface,\r
-# and provides a reference implementation of this interface.\r
-# <p>\r
-# You should not create instances of this class directly. Use the\r
-# appropriate factory functions instead, such as {@link #Element}\r
-# and {@link #SubElement}.\r
-#\r
-# @see Element\r
-# @see SubElement\r
-# @see Comment\r
-# @see ProcessingInstruction\r
-\r
-class _ElementInterface:\r
- # <tag attrib>text<child/>...</tag>tail\r
-\r
- ##\r
- # (Attribute) Element tag.\r
-\r
- tag = None\r
-\r
- ##\r
- # (Attribute) Element attribute dictionary. Where possible, use\r
- # {@link #_ElementInterface.get},\r
- # {@link #_ElementInterface.set},\r
- # {@link #_ElementInterface.keys}, and\r
- # {@link #_ElementInterface.items} to access\r
- # element attributes.\r
-\r
- attrib = None\r
-\r
- ##\r
- # (Attribute) Text before first subelement. This is either a\r
- # string or the value None, if there was no text.\r
-\r
- text = None\r
-\r
- ##\r
- # (Attribute) Text after this element's end tag, but before the\r
- # next sibling element's start tag. This is either a string or\r
- # the value None, if there was no text.\r
-\r
- tail = None # text after end tag, if any\r
-\r
- def __init__(self, tag, attrib):\r
- self.tag = tag\r
- self.attrib = attrib\r
- self._children = []\r
-\r
- def __repr__(self):\r
- return "<Element %s at %x>" % (self.tag, id(self))\r
-\r
- ##\r
- # Creates a new element object of the same type as this element.\r
- #\r
- # @param tag Element tag.\r
- # @param attrib Element attributes, given as a dictionary.\r
- # @return A new element instance.\r
-\r
- def makeelement(self, tag, attrib):\r
- return Element(tag, attrib)\r
-\r
- ##\r
- # Returns the number of subelements.\r
- #\r
- # @return The number of subelements.\r
-\r
- def __len__(self):\r
- return len(self._children)\r
-\r
- ##\r
- # Returns the given subelement.\r
- #\r
- # @param index What subelement to return.\r
- # @return The given subelement.\r
- # @exception IndexError If the given element does not exist.\r
-\r
- def __getitem__(self, index):\r
- return self._children[index]\r
-\r
- ##\r
- # Replaces the given subelement.\r
- #\r
- # @param index What subelement to replace.\r
- # @param element The new element value.\r
- # @exception IndexError If the given element does not exist.\r
- # @exception AssertionError If element is not a valid object.\r
-\r
- def __setitem__(self, index, element):\r
- assert iselement(element)\r
- self._children[index] = element\r
-\r
- ##\r
- # Deletes the given subelement.\r
- #\r
- # @param index What subelement to delete.\r
- # @exception IndexError If the given element does not exist.\r
-\r
- def __delitem__(self, index):\r
- del self._children[index]\r
-\r
- ##\r
- # Returns a list containing subelements in the given range.\r
- #\r
- # @param start The first subelement to return.\r
- # @param stop The first subelement that shouldn't be returned.\r
- # @return A sequence object containing subelements.\r
-\r
- def __getslice__(self, start, stop):\r
- return self._children[start:stop]\r
-\r
- ##\r
- # Replaces a number of subelements with elements from a sequence.\r
- #\r
- # @param start The first subelement to replace.\r
- # @param stop The first subelement that shouldn't be replaced.\r
- # @param elements A sequence object with zero or more elements.\r
- # @exception AssertionError If a sequence member is not a valid object.\r
-\r
- def __setslice__(self, start, stop, elements):\r
- for element in elements:\r
- assert iselement(element)\r
- self._children[start:stop] = list(elements)\r
-\r
- ##\r
- # Deletes a number of subelements.\r
- #\r
- # @param start The first subelement to delete.\r
- # @param stop The first subelement to leave in there.\r
-\r
- def __delslice__(self, start, stop):\r
- del self._children[start:stop]\r
-\r
- ##\r
- # Adds a subelement to the end of this element.\r
- #\r
- # @param element The element to add.\r
- # @exception AssertionError If a sequence member is not a valid object.\r
-\r
- def append(self, element):\r
- assert iselement(element)\r
- self._children.append(element)\r
-\r
- ##\r
- # Inserts a subelement at the given position in this element.\r
- #\r
- # @param index Where to insert the new subelement.\r
- # @exception AssertionError If the element is not a valid object.\r
-\r
- def insert(self, index, element):\r
- assert iselement(element)\r
- self._children.insert(index, element)\r
-\r
- ##\r
- # Removes a matching subelement. Unlike the <b>find</b> methods,\r
- # this method compares elements based on identity, not on tag\r
- # value or contents.\r
- #\r
- # @param element What element to remove.\r
- # @exception ValueError If a matching element could not be found.\r
- # @exception AssertionError If the element is not a valid object.\r
-\r
- def remove(self, element):\r
- assert iselement(element)\r
- self._children.remove(element)\r
-\r
- ##\r
- # Returns all subelements. The elements are returned in document\r
- # order.\r
- #\r
- # @return A list of subelements.\r
- # @defreturn list of Element instances\r
-\r
- def getchildren(self):\r
- return self._children\r
-\r
- ##\r
- # Finds the first matching subelement, by tag name or path.\r
- #\r
- # @param path What element to look for.\r
- # @return The first matching element, or None if no element was found.\r
- # @defreturn Element or None\r
-\r
- def find(self, path):\r
- return ElementPath.find(self, path)\r
-\r
- ##\r
- # Finds text for the first matching subelement, by tag name or path.\r
- #\r
- # @param path What element to look for.\r
- # @param default What to return if the element was not found.\r
- # @return The text content of the first matching element, or the\r
- # default value no element was found. Note that if the element\r
- # has is found, but has no text content, this method returns an\r
- # empty string.\r
- # @defreturn string\r
-\r
- def findtext(self, path, default=None):\r
- return ElementPath.findtext(self, path, default)\r
-\r
- ##\r
- # Finds all matching subelements, by tag name or path.\r
- #\r
- # @param path What element to look for.\r
- # @return A list or iterator containing all matching elements,\r
- # in document order.\r
- # @defreturn list of Element instances\r
-\r
- def findall(self, path):\r
- return ElementPath.findall(self, path)\r
-\r
- ##\r
- # Resets an element. This function removes all subelements, clears\r
- # all attributes, and sets the text and tail attributes to None.\r
-\r
- def clear(self):\r
- self.attrib.clear()\r
- self._children = []\r
- self.text = self.tail = None\r
-\r
- ##\r
- # Gets an element attribute.\r
- #\r
- # @param key What attribute to look for.\r
- # @param default What to return if the attribute was not found.\r
- # @return The attribute value, or the default value, if the\r
- # attribute was not found.\r
- # @defreturn string or None\r
-\r
- def get(self, key, default=None):\r
- return self.attrib.get(key, default)\r
-\r
- ##\r
- # Sets an element attribute.\r
- #\r
- # @param key What attribute to set.\r
- # @param value The attribute value.\r
-\r
- def set(self, key, value):\r
- self.attrib[key] = value\r
-\r
- ##\r
- # Gets a list of attribute names. The names are returned in an\r
- # arbitrary order (just like for an ordinary Python dictionary).\r
- #\r
- # @return A list of element attribute names.\r
- # @defreturn list of strings\r
-\r
- def keys(self):\r
- return self.attrib.keys()\r
-\r
- ##\r
- # Gets element attributes, as a sequence. The attributes are\r
- # returned in an arbitrary order.\r
- #\r
- # @return A list of (name, value) tuples for all attributes.\r
- # @defreturn list of (string, string) tuples\r
-\r
- def items(self):\r
- return self.attrib.items()\r
-\r
- ##\r
- # Creates a tree iterator. The iterator loops over this element\r
- # and all subelements, in document order, and returns all elements\r
- # with a matching tag.\r
- # <p>\r
- # If the tree structure is modified during iteration, the result\r
- # is undefined.\r
- #\r
- # @param tag What tags to look for (default is to return all elements).\r
- # @return A list or iterator containing all the matching elements.\r
- # @defreturn list or iterator\r
-\r
- def getiterator(self, tag=None):\r
- nodes = []\r
- if tag == "*":\r
- tag = None\r
- if tag is None or self.tag == tag:\r
- nodes.append(self)\r
- for node in self._children:\r
- nodes.extend(node.getiterator(tag))\r
- return nodes\r
-\r
-# compatibility\r
-_Element = _ElementInterface\r
-\r
-##\r
-# Element factory. This function returns an object implementing the\r
-# standard Element interface. The exact class or type of that object\r
-# is implementation dependent, but it will always be compatible with\r
-# the {@link #_ElementInterface} class in this module.\r
-# <p>\r
-# The element name, attribute names, and attribute values can be\r
-# either 8-bit ASCII strings or Unicode strings.\r
-#\r
-# @param tag The element name.\r
-# @param attrib An optional dictionary, containing element attributes.\r
-# @param **extra Additional attributes, given as keyword arguments.\r
-# @return An element instance.\r
-# @defreturn Element\r
-\r
-def Element(tag, attrib={}, **extra):\r
- attrib = attrib.copy()\r
- attrib.update(extra)\r
- return _ElementInterface(tag, attrib)\r
-\r
-##\r
-# Subelement factory. This function creates an element instance, and\r
-# appends it to an existing element.\r
-# <p>\r
-# The element name, attribute names, and attribute values can be\r
-# either 8-bit ASCII strings or Unicode strings.\r
-#\r
-# @param parent The parent element.\r
-# @param tag The subelement name.\r
-# @param attrib An optional dictionary, containing element attributes.\r
-# @param **extra Additional attributes, given as keyword arguments.\r
-# @return An element instance.\r
-# @defreturn Element\r
-\r
-def SubElement(parent, tag, attrib={}, **extra):\r
- attrib = attrib.copy()\r
- attrib.update(extra)\r
- element = parent.makeelement(tag, attrib)\r
- parent.append(element)\r
- return element\r
-\r
-##\r
-# Comment element factory. This factory function creates a special\r
-# element that will be serialized as an XML comment.\r
-# <p>\r
-# The comment string can be either an 8-bit ASCII string or a Unicode\r
-# string.\r
-#\r
-# @param text A string containing the comment string.\r
-# @return An element instance, representing a comment.\r
-# @defreturn Element\r
-\r
-def Comment(text=None):\r
- element = Element(Comment)\r
- element.text = text\r
- return element\r
-\r
-##\r
-# PI element factory. This factory function creates a special element\r
-# that will be serialized as an XML processing instruction.\r
-#\r
-# @param target A string containing the PI target.\r
-# @param text A string containing the PI contents, if any.\r
-# @return An element instance, representing a PI.\r
-# @defreturn Element\r
-\r
-def ProcessingInstruction(target, text=None):\r
- element = Element(ProcessingInstruction)\r
- element.text = target\r
- if text:\r
- element.text = element.text + " " + text\r
- return element\r
-\r
-PI = ProcessingInstruction\r
-\r
-##\r
-# QName wrapper. This can be used to wrap a QName attribute value, in\r
-# order to get proper namespace handling on output.\r
-#\r
-# @param text A string containing the QName value, in the form {uri}local,\r
-# or, if the tag argument is given, the URI part of a QName.\r
-# @param tag Optional tag. If given, the first argument is interpreted as\r
-# an URI, and this argument is interpreted as a local name.\r
-# @return An opaque object, representing the QName.\r
-\r
-class QName:\r
- def __init__(self, text_or_uri, tag=None):\r
- if tag:\r
- text_or_uri = "{%s}%s" % (text_or_uri, tag)\r
- self.text = text_or_uri\r
- def __str__(self):\r
- return self.text\r
- def __hash__(self):\r
- return hash(self.text)\r
- def __cmp__(self, other):\r
- if isinstance(other, QName):\r
- return cmp(self.text, other.text)\r
- return cmp(self.text, other)\r
-\r
-##\r
-# ElementTree wrapper class. This class represents an entire element\r
-# hierarchy, and adds some extra support for serialization to and from\r
-# standard XML.\r
-#\r
-# @param element Optional root element.\r
-# @keyparam file Optional file handle or name. If given, the\r
-# tree is initialized with the contents of this XML file.\r
-\r
-class ElementTree:\r
-\r
- def __init__(self, element=None, file=None):\r
- assert element is None or iselement(element)\r
- self._root = element # first node\r
- if file:\r
- self.parse(file)\r
-\r
- ##\r
- # Gets the root element for this tree.\r
- #\r
- # @return An element instance.\r
- # @defreturn Element\r
-\r
- def getroot(self):\r
- return self._root\r
-\r
- ##\r
- # Replaces the root element for this tree. This discards the\r
- # current contents of the tree, and replaces it with the given\r
- # element. Use with care.\r
- #\r
- # @param element An element instance.\r
-\r
- def _setroot(self, element):\r
- assert iselement(element)\r
- self._root = element\r
-\r
- ##\r
- # Loads an external XML document into this element tree.\r
- #\r
- # @param source A file name or file object.\r
- # @param parser An optional parser instance. If not given, the\r
- # standard {@link XMLTreeBuilder} parser is used.\r
- # @return The document root element.\r
- # @defreturn Element\r
-\r
- def parse(self, source, parser=None):\r
- if not hasattr(source, "read"):\r
- source = open(source, "rb")\r
- if not parser:\r
- parser = XMLTreeBuilder()\r
- while 1:\r
- data = source.read(32768)\r
- if not data:\r
- break\r
- parser.feed(data)\r
- self._root = parser.close()\r
- return self._root\r
-\r
- ##\r
- # Creates a tree iterator for the root element. The iterator loops\r
- # over all elements in this tree, in document order.\r
- #\r
- # @param tag What tags to look for (default is to return all elements)\r
- # @return An iterator.\r
- # @defreturn iterator\r
-\r
- def getiterator(self, tag=None):\r
- assert self._root is not None\r
- return self._root.getiterator(tag)\r
-\r
- ##\r
- # Finds the first toplevel element with given tag.\r
- # Same as getroot().find(path).\r
- #\r
- # @param path What element to look for.\r
- # @return The first matching element, or None if no element was found.\r
- # @defreturn Element or None\r
-\r
- def find(self, path):\r
- assert self._root is not None\r
- if path[:1] == "/":\r
- path = "." + path\r
- return self._root.find(path)\r
-\r
- ##\r
- # Finds the element text for the first toplevel element with given\r
- # tag. Same as getroot().findtext(path).\r
- #\r
- # @param path What toplevel element to look for.\r
- # @param default What to return if the element was not found.\r
- # @return The text content of the first matching element, or the\r
- # default value no element was found. Note that if the element\r
- # has is found, but has no text content, this method returns an\r
- # empty string.\r
- # @defreturn string\r
-\r
- def findtext(self, path, default=None):\r
- assert self._root is not None\r
- if path[:1] == "/":\r
- path = "." + path\r
- return self._root.findtext(path, default)\r
-\r
- ##\r
- # Finds all toplevel elements with the given tag.\r
- # Same as getroot().findall(path).\r
- #\r
- # @param path What element to look for.\r
- # @return A list or iterator containing all matching elements,\r
- # in document order.\r
- # @defreturn list of Element instances\r
-\r
- def findall(self, path):\r
- assert self._root is not None\r
- if path[:1] == "/":\r
- path = "." + path\r
- return self._root.findall(path)\r
-\r
- ##\r
- # Writes the element tree to a file, as XML.\r
- #\r
- # @param file A file name, or a file object opened for writing.\r
- # @param encoding Optional output encoding (default is US-ASCII).\r
-\r
- def write(self, file, encoding="us-ascii"):\r
- assert self._root is not None\r
- if not hasattr(file, "write"):\r
- file = open(file, "wb")\r
- if not encoding:\r
- encoding = "us-ascii"\r
- elif encoding != "utf-8" and encoding != "us-ascii":\r
- file.write("<?xml version='1.0' encoding='%s'?>\n" % encoding)\r
- self._write(file, self._root, encoding, {})\r
-\r
- def _write(self, file, node, encoding, namespaces):\r
- # write XML to file\r
- tag = node.tag\r
- if tag is Comment:\r
- file.write("<!-- %s -->" % _escape_cdata(node.text, encoding))\r
- elif tag is ProcessingInstruction:\r
- file.write("<?%s?>" % _escape_cdata(node.text, encoding))\r
- else:\r
- items = node.items()\r
- xmlns_items = [] # new namespaces in this scope\r
- try:\r
- if isinstance(tag, QName) or tag[:1] == "{":\r
- tag, xmlns = fixtag(tag, namespaces)\r
- if xmlns: xmlns_items.append(xmlns)\r
- except TypeError:\r
- _raise_serialization_error(tag)\r
- file.write("<" + _encode(tag, encoding))\r
- if items or xmlns_items:\r
- items.sort() # lexical order\r
- for k, v in items:\r
- try:\r
- if isinstance(k, QName) or k[:1] == "{":\r
- k, xmlns = fixtag(k, namespaces)\r
- if xmlns: xmlns_items.append(xmlns)\r
- except TypeError:\r
- _raise_serialization_error(k)\r
- try:\r
- if isinstance(v, QName):\r
- v, xmlns = fixtag(v, namespaces)\r
- if xmlns: xmlns_items.append(xmlns)\r
- except TypeError:\r
- _raise_serialization_error(v)\r
- file.write(" %s=\"%s\"" % (_encode(k, encoding),\r
- _escape_attrib(v, encoding)))\r
- for k, v in xmlns_items:\r
- file.write(" %s=\"%s\"" % (_encode(k, encoding),\r
- _escape_attrib(v, encoding)))\r
- if node.text or len(node):\r
- file.write(">")\r
- if node.text:\r
- file.write(_escape_cdata(node.text, encoding))\r
- for n in node:\r
- self._write(file, n, encoding, namespaces)\r
- file.write("</" + _encode(tag, encoding) + ">")\r
- else:\r
- file.write(" />")\r
- for k, v in xmlns_items:\r
- del namespaces[v]\r
- if node.tail:\r
- file.write(_escape_cdata(node.tail, encoding))\r
-\r
-# --------------------------------------------------------------------\r
-# helpers\r
-\r
-##\r
-# Checks if an object appears to be a valid element object.\r
-#\r
-# @param An element instance.\r
-# @return A true value if this is an element object.\r
-# @defreturn flag\r
-\r
-def iselement(element):\r
- # FIXME: not sure about this; might be a better idea to look\r
- # for tag/attrib/text attributes\r
- return isinstance(element, _ElementInterface) or hasattr(element, "tag")\r
-\r
-##\r
-# Writes an element tree or element structure to sys.stdout. This\r
-# function should be used for debugging only.\r
-# <p>\r
-# The exact output format is implementation dependent. In this\r
-# version, it's written as an ordinary XML file.\r
-#\r
-# @param elem An element tree or an individual element.\r
-\r
-def dump(elem):\r
- # debugging\r
- if not isinstance(elem, ElementTree):\r
- elem = ElementTree(elem)\r
- elem.write(sys.stdout)\r
- tail = elem.getroot().tail\r
- if not tail or tail[-1] != "\n":\r
- sys.stdout.write("\n")\r
-\r
-def _encode(s, encoding):\r
- try:\r
- return s.encode(encoding)\r
- except AttributeError:\r
- return s # 1.5.2: assume the string uses the right encoding\r
-\r
-if sys.version[:3] == "1.5":\r
- _escape = re.compile(r"[&<>\"\x80-\xff]+") # 1.5.2\r
-else:\r
- _escape = re.compile(eval(r'u"[&<>\"\u0080-\uffff]+"'))\r
-\r
-_escape_map = {\r
- "&": "&",\r
- "<": "<",\r
- ">": ">",\r
- '"': """,\r
-}\r
-\r
-_namespace_map = {\r
- # "well-known" namespace prefixes\r
- "http://www.w3.org/XML/1998/namespace": "xml",\r
- "http://www.w3.org/1999/xhtml": "html",\r
- "http://www.w3.org/1999/02/22-rdf-syntax-ns#": "rdf",\r
- "http://schemas.xmlsoap.org/wsdl/": "wsdl",\r
-}\r
-\r
-def _raise_serialization_error(text):\r
- raise TypeError(\r
- "cannot serialize %r (type %s)" % (text, type(text).__name__)\r
- )\r
-\r
-def _encode_entity(text, pattern=_escape):\r
- # map reserved and non-ascii characters to numerical entities\r
- def escape_entities(m, map=_escape_map):\r
- out = []\r
- append = out.append\r
- for char in m.group():\r
- text = map.get(char)\r
- if text is None:\r
- text = "&#%d;" % ord(char)\r
- append(text)\r
- return string.join(out, "")\r
- try:\r
- return _encode(pattern.sub(escape_entities, text), "ascii")\r
- except TypeError:\r
- _raise_serialization_error(text)\r
-\r
-#\r
-# the following functions assume an ascii-compatible encoding\r
-# (or "utf-16")\r
-\r
-def _escape_cdata(text, encoding=None, replace=string.replace):\r
- # escape character data\r
- try:\r
- if encoding:\r
- try:\r
- text = _encode(text, encoding)\r
- except UnicodeError:\r
- return _encode_entity(text)\r
- text = replace(text, "&", "&")\r
- text = replace(text, "<", "<")\r
- text = replace(text, ">", ">")\r
- return text\r
- except (TypeError, AttributeError):\r
- _raise_serialization_error(text)\r
-\r
-def _escape_attrib(text, encoding=None, replace=string.replace):\r
- # escape attribute value\r
- try:\r
- if encoding:\r
- try:\r
- text = _encode(text, encoding)\r
- except UnicodeError:\r
- return _encode_entity(text)\r
- text = replace(text, "&", "&")\r
- text = replace(text, "'", "'") # FIXME: overkill\r
- text = replace(text, "\"", """)\r
- text = replace(text, "<", "<")\r
- text = replace(text, ">", ">")\r
- return text\r
- except (TypeError, AttributeError):\r
- _raise_serialization_error(text)\r
-\r
-def fixtag(tag, namespaces):\r
- # given a decorated tag (of the form {uri}tag), return prefixed\r
- # tag and namespace declaration, if any\r
- if isinstance(tag, QName):\r
- tag = tag.text\r
- namespace_uri, tag = string.split(tag[1:], "}", 1)\r
- prefix = namespaces.get(namespace_uri)\r
- if prefix is None:\r
- prefix = _namespace_map.get(namespace_uri)\r
- if prefix is None:\r
- prefix = "ns%d" % len(namespaces)\r
- namespaces[namespace_uri] = prefix\r
- if prefix == "xml":\r
- xmlns = None\r
- else:\r
- xmlns = ("xmlns:%s" % prefix, namespace_uri)\r
- else:\r
- xmlns = None\r
- return "%s:%s" % (prefix, tag), xmlns\r
-\r
-##\r
-# Parses an XML document into an element tree.\r
-#\r
-# @param source A filename or file object containing XML data.\r
-# @param parser An optional parser instance. If not given, the\r
-# standard {@link XMLTreeBuilder} parser is used.\r
-# @return An ElementTree instance\r
-\r
-def parse(source, parser=None):\r
- tree = ElementTree()\r
- tree.parse(source, parser)\r
- return tree\r
-\r
-##\r
-# Parses an XML document into an element tree incrementally, and reports\r
-# what's going on to the user.\r
-#\r
-# @param source A filename or file object containing XML data.\r
-# @param events A list of events to report back. If omitted, only "end"\r
-# events are reported.\r
-# @return A (event, elem) iterator.\r
-\r
-class iterparse:\r
-\r
- def __init__(self, source, events=None):\r
- if not hasattr(source, "read"):\r
- source = open(source, "rb")\r
- self._file = source\r
- self._events = []\r
- self._index = 0\r
- self.root = self._root = None\r
- self._parser = XMLTreeBuilder()\r
- # wire up the parser for event reporting\r
- parser = self._parser._parser\r
- append = self._events.append\r
- if events is None:\r
- events = ["end"]\r
- for event in events:\r
- if event == "start":\r
- try:\r
- parser.ordered_attributes = 1\r
- parser.specified_attributes = 1\r
- def handler(tag, attrib_in, event=event, append=append,\r
- start=self._parser._start_list):\r
- append((event, start(tag, attrib_in)))\r
- parser.StartElementHandler = handler\r
- except AttributeError:\r
- def handler(tag, attrib_in, event=event, append=append,\r
- start=self._parser._start):\r
- append((event, start(tag, attrib_in)))\r
- parser.StartElementHandler = handler\r
- elif event == "end":\r
- def handler(tag, event=event, append=append,\r
- end=self._parser._end):\r
- append((event, end(tag)))\r
- parser.EndElementHandler = handler\r
- elif event == "start-ns":\r
- def handler(prefix, uri, event=event, append=append):\r
- try:\r
- uri = _encode(uri, "ascii")\r
- except UnicodeError:\r
- pass\r
- append((event, (prefix or "", uri)))\r
- parser.StartNamespaceDeclHandler = handler\r
- elif event == "end-ns":\r
- def handler(prefix, event=event, append=append):\r
- append((event, None))\r
- parser.EndNamespaceDeclHandler = handler\r
-\r
- def next(self):\r
- while 1:\r
- try:\r
- item = self._events[self._index]\r
- except IndexError:\r
- if self._parser is None:\r
- self.root = self._root\r
- try:\r
- raise StopIteration\r
- except NameError:\r
- raise IndexError\r
- # load event buffer\r
- del self._events[:]\r
- self._index = 0\r
- data = self._file.read(16384)\r
- if data:\r
- self._parser.feed(data)\r
- else:\r
- self._root = self._parser.close()\r
- self._parser = None\r
- else:\r
- self._index = self._index + 1\r
- return item\r
-\r
- try:\r
- iter\r
- def __iter__(self):\r
- return self\r
- except NameError:\r
- def __getitem__(self, index):\r
- return self.next()\r
-\r
-##\r
-# Parses an XML document from a string constant. This function can\r
-# be used to embed "XML literals" in Python code.\r
-#\r
-# @param source A string containing XML data.\r
-# @return An Element instance.\r
-# @defreturn Element\r
-\r
-def XML(text):\r
- parser = XMLTreeBuilder()\r
- parser.feed(text)\r
- return parser.close()\r
-\r
-##\r
-# Parses an XML document from a string constant, and also returns\r
-# a dictionary which maps from element id:s to elements.\r
-#\r
-# @param source A string containing XML data.\r
-# @return A tuple containing an Element instance and a dictionary.\r
-# @defreturn (Element, dictionary)\r
-\r
-def XMLID(text):\r
- parser = XMLTreeBuilder()\r
- parser.feed(text)\r
- tree = parser.close()\r
- ids = {}\r
- for elem in tree.getiterator():\r
- id = elem.get("id")\r
- if id:\r
- ids[id] = elem\r
- return tree, ids\r
-\r
-##\r
-# Parses an XML document from a string constant. Same as {@link #XML}.\r
-#\r
-# @def fromstring(text)\r
-# @param source A string containing XML data.\r
-# @return An Element instance.\r
-# @defreturn Element\r
-\r
-fromstring = XML\r
-\r
-##\r
-# Generates a string representation of an XML element, including all\r
-# subelements.\r
-#\r
-# @param element An Element instance.\r
-# @return An encoded string containing the XML data.\r
-# @defreturn string\r
-\r
-def tostring(element, encoding=None):\r
- class dummy:\r
- pass\r
- data = []\r
- file = dummy()\r
- file.write = data.append\r
- ElementTree(element).write(file, encoding)\r
- return string.join(data, "")\r
-\r
-##\r
-# Generic element structure builder. This builder converts a sequence\r
-# of {@link #TreeBuilder.start}, {@link #TreeBuilder.data}, and {@link\r
-# #TreeBuilder.end} method calls to a well-formed element structure.\r
-# <p>\r
-# You can use this class to build an element structure using a custom XML\r
-# parser, or a parser for some other XML-like format.\r
-#\r
-# @param element_factory Optional element factory. This factory\r
-# is called to create new Element instances, as necessary.\r
-\r
-class TreeBuilder:\r
-\r
- def __init__(self, element_factory=None):\r
- self._data = [] # data collector\r
- self._elem = [] # element stack\r
- self._last = None # last element\r
- self._tail = None # true if we're after an end tag\r
- if element_factory is None:\r
- element_factory = _ElementInterface\r
- self._factory = element_factory\r
-\r
- ##\r
- # Flushes the parser buffers, and returns the toplevel documen\r
- # element.\r
- #\r
- # @return An Element instance.\r
- # @defreturn Element\r
-\r
- def close(self):\r
- assert len(self._elem) == 0, "missing end tags"\r
- assert self._last != None, "missing toplevel element"\r
- return self._last\r
-\r
- def _flush(self):\r
- if self._data:\r
- if self._last is not None:\r
- text = string.join(self._data, "")\r
- if self._tail:\r
- assert self._last.tail is None, "internal error (tail)"\r
- self._last.tail = text\r
- else:\r
- assert self._last.text is None, "internal error (text)"\r
- self._last.text = text\r
- self._data = []\r
-\r
- ##\r
- # Adds text to the current element.\r
- #\r
- # @param data A string. This should be either an 8-bit string\r
- # containing ASCII text, or a Unicode string.\r
-\r
- def data(self, data):\r
- self._data.append(data)\r
-\r
- ##\r
- # Opens a new element.\r
- #\r
- # @param tag The element name.\r
- # @param attrib A dictionary containing element attributes.\r
- # @return The opened element.\r
- # @defreturn Element\r
-\r
- def start(self, tag, attrs):\r
- self._flush()\r
- self._last = elem = self._factory(tag, attrs)\r
- if self._elem:\r
- self._elem[-1].append(elem)\r
- self._elem.append(elem)\r
- self._tail = 0\r
- return elem\r
-\r
- ##\r
- # Closes the current element.\r
- #\r
- # @param tag The element name.\r
- # @return The closed element.\r
- # @defreturn Element\r
-\r
- def end(self, tag):\r
- self._flush()\r
- self._last = self._elem.pop()\r
- assert self._last.tag == tag,\\r
- "end tag mismatch (expected %s, got %s)" % (\r
- self._last.tag, tag)\r
- self._tail = 1\r
- return self._last\r
-\r
-##\r
-# Element structure builder for XML source data, based on the\r
-# <b>expat</b> parser.\r
-#\r
-# @keyparam target Target object. If omitted, the builder uses an\r
-# instance of the standard {@link #TreeBuilder} class.\r
-# @keyparam html Predefine HTML entities. This flag is not supported\r
-# by the current implementation.\r
-# @see #ElementTree\r
-# @see #TreeBuilder\r
-\r
-class XMLTreeBuilder:\r
-\r
- def __init__(self, html=0, target=None):\r
- try:\r
- from xmlcore.parsers import expat\r
- except ImportError:\r
- raise ImportError(\r
- "No module named expat; use SimpleXMLTreeBuilder instead"\r
- )\r
- self._parser = parser = expat.ParserCreate(None, "}")\r
- if target is None:\r
- target = TreeBuilder()\r
- self._target = target\r
- self._names = {} # name memo cache\r
- # callbacks\r
- parser.DefaultHandlerExpand = self._default\r
- parser.StartElementHandler = self._start\r
- parser.EndElementHandler = self._end\r
- parser.CharacterDataHandler = self._data\r
- # let expat do the buffering, if supported\r
- try:\r
- self._parser.buffer_text = 1\r
- except AttributeError:\r
- pass\r
- # use new-style attribute handling, if supported\r
- try:\r
- self._parser.ordered_attributes = 1\r
- self._parser.specified_attributes = 1\r
- parser.StartElementHandler = self._start_list\r
- except AttributeError:\r
- pass\r
- encoding = None\r
- if not parser.returns_unicode:\r
- encoding = "utf-8"\r
- # target.xml(encoding, None)\r
- self._doctype = None\r
- self.entity = {}\r
-\r
- def _fixtext(self, text):\r
- # convert text string to ascii, if possible\r
- try:\r
- return _encode(text, "ascii")\r
- except UnicodeError:\r
- return text\r
-\r
- def _fixname(self, key):\r
- # expand qname, and convert name string to ascii, if possible\r
- try:\r
- name = self._names[key]\r
- except KeyError:\r
- name = key\r
- if "}" in name:\r
- name = "{" + name\r
- self._names[key] = name = self._fixtext(name)\r
- return name\r
-\r
- def _start(self, tag, attrib_in):\r
- fixname = self._fixname\r
- tag = fixname(tag)\r
- attrib = {}\r
- for key, value in attrib_in.items():\r
- attrib[fixname(key)] = self._fixtext(value)\r
- return self._target.start(tag, attrib)\r
-\r
- def _start_list(self, tag, attrib_in):\r
- fixname = self._fixname\r
- tag = fixname(tag)\r
- attrib = {}\r
- if attrib_in:\r
- for i in range(0, len(attrib_in), 2):\r
- attrib[fixname(attrib_in[i])] = self._fixtext(attrib_in[i+1])\r
- return self._target.start(tag, attrib)\r
-\r
- def _data(self, text):\r
- return self._target.data(self._fixtext(text))\r
-\r
- def _end(self, tag):\r
- return self._target.end(self._fixname(tag))\r
-\r
- def _default(self, text):\r
- prefix = text[:1]\r
- if prefix == "&":\r
- # deal with undefined entities\r
- try:\r
- self._target.data(self.entity[text[1:-1]])\r
- except KeyError:\r
- from xmlcore.parsers import expat\r
- raise expat.error(\r
- "undefined entity %s: line %d, column %d" %\r
- (text, self._parser.ErrorLineNumber,\r
- self._parser.ErrorColumnNumber)\r
- )\r
- elif prefix == "<" and text[:9] == "<!DOCTYPE":\r
- self._doctype = [] # inside a doctype declaration\r
- elif self._doctype is not None:\r
- # parse doctype contents\r
- if prefix == ">":\r
- self._doctype = None\r
- return\r
- text = string.strip(text)\r
- if not text:\r
- return\r
- self._doctype.append(text)\r
- n = len(self._doctype)\r
- if n > 2:\r
- type = self._doctype[1]\r
- if type == "PUBLIC" and n == 4:\r
- name, type, pubid, system = self._doctype\r
- elif type == "SYSTEM" and n == 3:\r
- name, type, system = self._doctype\r
- pubid = None\r
- else:\r
- return\r
- if pubid:\r
- pubid = pubid[1:-1]\r
- self.doctype(name, pubid, system[1:-1])\r
- self._doctype = None\r
-\r
- ##\r
- # Handles a doctype declaration.\r
- #\r
- # @param name Doctype name.\r
- # @param pubid Public identifier.\r
- # @param system System identifier.\r
-\r
- def doctype(self, name, pubid, system):\r
- pass\r
-\r
- ##\r
- # Feeds data to the parser.\r
- #\r
- # @param data Encoded data.\r
-\r
- def feed(self, data):\r
- self._parser.Parse(data, 0)\r
-\r
- ##\r
- # Finishes feeding data to the parser.\r
- #\r
- # @return An element structure.\r
- # @defreturn Element\r
-\r
- def close(self):\r
- self._parser.Parse("", 1) # end of data\r
- tree = self._target.close()\r
- del self._target, self._parser # get rid of circular references\r
- return tree\r
+#
+# ElementTree
+# $Id: ElementTree.py 2326 2005-03-17 07:45:21Z fredrik $
+#
+# light-weight XML support for Python 1.5.2 and later.
+#
+# history:
+# 2001-10-20 fl created (from various sources)
+# 2001-11-01 fl return root from parse method
+# 2002-02-16 fl sort attributes in lexical order
+# 2002-04-06 fl TreeBuilder refactoring, added PythonDoc markup
+# 2002-05-01 fl finished TreeBuilder refactoring
+# 2002-07-14 fl added basic namespace support to ElementTree.write
+# 2002-07-25 fl added QName attribute support
+# 2002-10-20 fl fixed encoding in write
+# 2002-11-24 fl changed default encoding to ascii; fixed attribute encoding
+# 2002-11-27 fl accept file objects or file names for parse/write
+# 2002-12-04 fl moved XMLTreeBuilder back to this module
+# 2003-01-11 fl fixed entity encoding glitch for us-ascii
+# 2003-02-13 fl added XML literal factory
+# 2003-02-21 fl added ProcessingInstruction/PI factory
+# 2003-05-11 fl added tostring/fromstring helpers
+# 2003-05-26 fl added ElementPath support
+# 2003-07-05 fl added makeelement factory method
+# 2003-07-28 fl added more well-known namespace prefixes
+# 2003-08-15 fl fixed typo in ElementTree.findtext (Thomas Dartsch)
+# 2003-09-04 fl fall back on emulator if ElementPath is not installed
+# 2003-10-31 fl markup updates
+# 2003-11-15 fl fixed nested namespace bug
+# 2004-03-28 fl added XMLID helper
+# 2004-06-02 fl added default support to findtext
+# 2004-06-08 fl fixed encoding of non-ascii element/attribute names
+# 2004-08-23 fl take advantage of post-2.1 expat features
+# 2005-02-01 fl added iterparse implementation
+# 2005-03-02 fl fixed iterparse support for pre-2.2 versions
+#
+# Copyright (c) 1999-2005 by Fredrik Lundh. All rights reserved.
+#
+# fredrik@pythonware.com
+# http://www.pythonware.com
+#
+# --------------------------------------------------------------------
+# The ElementTree toolkit is
+#
+# Copyright (c) 1999-2005 by Fredrik Lundh
+#
+# By obtaining, using, and/or copying this software and/or its
+# associated documentation, you agree that you have read, understood,
+# and will comply with the following terms and conditions:
+#
+# Permission to use, copy, modify, and distribute this software and
+# its associated documentation for any purpose and without fee is
+# hereby granted, provided that the above copyright notice appears in
+# all copies, and that both that copyright notice and this permission
+# notice appear in supporting documentation, and that the name of
+# Secret Labs AB or the author not be used in advertising or publicity
+# pertaining to distribution of the software without specific, written
+# prior permission.
+#
+# SECRET LABS AB AND THE AUTHOR DISCLAIMS ALL WARRANTIES WITH REGARD
+# TO THIS SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANT-
+# ABILITY AND FITNESS. IN NO EVENT SHALL SECRET LABS AB OR THE AUTHOR
+# BE LIABLE FOR ANY SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY
+# DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS,
+# WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS
+# ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE
+# OF THIS SOFTWARE.
+# --------------------------------------------------------------------
+
+__all__ = [
+ # public symbols
+ "Comment",
+ "dump",
+ "Element", "ElementTree",
+ "fromstring",
+ "iselement", "iterparse",
+ "parse",
+ "PI", "ProcessingInstruction",
+ "QName",
+ "SubElement",
+ "tostring",
+ "TreeBuilder",
+ "VERSION", "XML",
+ "XMLTreeBuilder",
+ ]
+
+##
+# The <b>Element</b> type is a flexible container object, designed to
+# store hierarchical data structures in memory. The type can be
+# described as a cross between a list and a dictionary.
+# <p>
+# Each element has a number of properties associated with it:
+# <ul>
+# <li>a <i>tag</i>. This is a string identifying what kind of data
+# this element represents (the element type, in other words).</li>
+# <li>a number of <i>attributes</i>, stored in a Python dictionary.</li>
+# <li>a <i>text</i> string.</li>
+# <li>an optional <i>tail</i> string.</li>
+# <li>a number of <i>child elements</i>, stored in a Python sequence</li>
+# </ul>
+#
+# To create an element instance, use the {@link #Element} or {@link
+# #SubElement} factory functions.
+# <p>
+# The {@link #ElementTree} class can be used to wrap an element
+# structure, and convert it from and to XML.
+##
+
+import string, sys, re
+
+class _SimpleElementPath:
+ # emulate pre-1.2 find/findtext/findall behaviour
+ def find(self, element, tag):
+ for elem in element:
+ if elem.tag == tag:
+ return elem
+ return None
+ def findtext(self, element, tag, default=None):
+ for elem in element:
+ if elem.tag == tag:
+ return elem.text or ""
+ return default
+ def findall(self, element, tag):
+ if tag[:3] == ".//":
+ return element.getiterator(tag[3:])
+ result = []
+ for elem in element:
+ if elem.tag == tag:
+ result.append(elem)
+ return result
+
+try:
+ import ElementPath
+except ImportError:
+ # FIXME: issue warning in this case?
+ ElementPath = _SimpleElementPath()
+
+# TODO: add support for custom namespace resolvers/default namespaces
+# TODO: add improved support for incremental parsing
+
+VERSION = "1.2.6"
+
+##
+# Internal element class. This class defines the Element interface,
+# and provides a reference implementation of this interface.
+# <p>
+# You should not create instances of this class directly. Use the
+# appropriate factory functions instead, such as {@link #Element}
+# and {@link #SubElement}.
+#
+# @see Element
+# @see SubElement
+# @see Comment
+# @see ProcessingInstruction
+
+class _ElementInterface:
+ # <tag attrib>text<child/>...</tag>tail
+
+ ##
+ # (Attribute) Element tag.
+
+ tag = None
+
+ ##
+ # (Attribute) Element attribute dictionary. Where possible, use
+ # {@link #_ElementInterface.get},
+ # {@link #_ElementInterface.set},
+ # {@link #_ElementInterface.keys}, and
+ # {@link #_ElementInterface.items} to access
+ # element attributes.
+
+ attrib = None
+
+ ##
+ # (Attribute) Text before first subelement. This is either a
+ # string or the value None, if there was no text.
+
+ text = None
+
+ ##
+ # (Attribute) Text after this element's end tag, but before the
+ # next sibling element's start tag. This is either a string or
+ # the value None, if there was no text.
+
+ tail = None # text after end tag, if any
+
+ def __init__(self, tag, attrib):
+ self.tag = tag
+ self.attrib = attrib
+ self._children = []
+
+ def __repr__(self):
+ return "<Element %s at %x>" % (self.tag, id(self))
+
+ ##
+ # Creates a new element object of the same type as this element.
+ #
+ # @param tag Element tag.
+ # @param attrib Element attributes, given as a dictionary.
+ # @return A new element instance.
+
+ def makeelement(self, tag, attrib):
+ return Element(tag, attrib)
+
+ ##
+ # Returns the number of subelements.
+ #
+ # @return The number of subelements.
+
+ def __len__(self):
+ return len(self._children)
+
+ ##
+ # Returns the given subelement.
+ #
+ # @param index What subelement to return.
+ # @return The given subelement.
+ # @exception IndexError If the given element does not exist.
+
+ def __getitem__(self, index):
+ return self._children[index]
+
+ ##
+ # Replaces the given subelement.
+ #
+ # @param index What subelement to replace.
+ # @param element The new element value.
+ # @exception IndexError If the given element does not exist.
+ # @exception AssertionError If element is not a valid object.
+
+ def __setitem__(self, index, element):
+ assert iselement(element)
+ self._children[index] = element
+
+ ##
+ # Deletes the given subelement.
+ #
+ # @param index What subelement to delete.
+ # @exception IndexError If the given element does not exist.
+
+ def __delitem__(self, index):
+ del self._children[index]
+
+ ##
+ # Returns a list containing subelements in the given range.
+ #
+ # @param start The first subelement to return.
+ # @param stop The first subelement that shouldn't be returned.
+ # @return A sequence object containing subelements.
+
+ def __getslice__(self, start, stop):
+ return self._children[start:stop]
+
+ ##
+ # Replaces a number of subelements with elements from a sequence.
+ #
+ # @param start The first subelement to replace.
+ # @param stop The first subelement that shouldn't be replaced.
+ # @param elements A sequence object with zero or more elements.
+ # @exception AssertionError If a sequence member is not a valid object.
+
+ def __setslice__(self, start, stop, elements):
+ for element in elements:
+ assert iselement(element)
+ self._children[start:stop] = list(elements)
+
+ ##
+ # Deletes a number of subelements.
+ #
+ # @param start The first subelement to delete.
+ # @param stop The first subelement to leave in there.
+
+ def __delslice__(self, start, stop):
+ del self._children[start:stop]
+
+ ##
+ # Adds a subelement to the end of this element.
+ #
+ # @param element The element to add.
+ # @exception AssertionError If a sequence member is not a valid object.
+
+ def append(self, element):
+ assert iselement(element)
+ self._children.append(element)
+
+ ##
+ # Inserts a subelement at the given position in this element.
+ #
+ # @param index Where to insert the new subelement.
+ # @exception AssertionError If the element is not a valid object.
+
+ def insert(self, index, element):
+ assert iselement(element)
+ self._children.insert(index, element)
+
+ ##
+ # Removes a matching subelement. Unlike the <b>find</b> methods,
+ # this method compares elements based on identity, not on tag
+ # value or contents.
+ #
+ # @param element What element to remove.
+ # @exception ValueError If a matching element could not be found.
+ # @exception AssertionError If the element is not a valid object.
+
+ def remove(self, element):
+ assert iselement(element)
+ self._children.remove(element)
+
+ ##
+ # Returns all subelements. The elements are returned in document
+ # order.
+ #
+ # @return A list of subelements.
+ # @defreturn list of Element instances
+
+ def getchildren(self):
+ return self._children
+
+ ##
+ # Finds the first matching subelement, by tag name or path.
+ #
+ # @param path What element to look for.
+ # @return The first matching element, or None if no element was found.
+ # @defreturn Element or None
+
+ def find(self, path):
+ return ElementPath.find(self, path)
+
+ ##
+ # Finds text for the first matching subelement, by tag name or path.
+ #
+ # @param path What element to look for.
+ # @param default What to return if the element was not found.
+ # @return The text content of the first matching element, or the
+ # default value no element was found. Note that if the element
+ # has is found, but has no text content, this method returns an
+ # empty string.
+ # @defreturn string
+
+ def findtext(self, path, default=None):
+ return ElementPath.findtext(self, path, default)
+
+ ##
+ # Finds all matching subelements, by tag name or path.
+ #
+ # @param path What element to look for.
+ # @return A list or iterator containing all matching elements,
+ # in document order.
+ # @defreturn list of Element instances
+
+ def findall(self, path):
+ return ElementPath.findall(self, path)
+
+ ##
+ # Resets an element. This function removes all subelements, clears
+ # all attributes, and sets the text and tail attributes to None.
+
+ def clear(self):
+ self.attrib.clear()
+ self._children = []
+ self.text = self.tail = None
+
+ ##
+ # Gets an element attribute.
+ #
+ # @param key What attribute to look for.
+ # @param default What to return if the attribute was not found.
+ # @return The attribute value, or the default value, if the
+ # attribute was not found.
+ # @defreturn string or None
+
+ def get(self, key, default=None):
+ return self.attrib.get(key, default)
+
+ ##
+ # Sets an element attribute.
+ #
+ # @param key What attribute to set.
+ # @param value The attribute value.
+
+ def set(self, key, value):
+ self.attrib[key] = value
+
+ ##
+ # Gets a list of attribute names. The names are returned in an
+ # arbitrary order (just like for an ordinary Python dictionary).
+ #
+ # @return A list of element attribute names.
+ # @defreturn list of strings
+
+ def keys(self):
+ return self.attrib.keys()
+
+ ##
+ # Gets element attributes, as a sequence. The attributes are
+ # returned in an arbitrary order.
+ #
+ # @return A list of (name, value) tuples for all attributes.
+ # @defreturn list of (string, string) tuples
+
+ def items(self):
+ return self.attrib.items()
+
+ ##
+ # Creates a tree iterator. The iterator loops over this element
+ # and all subelements, in document order, and returns all elements
+ # with a matching tag.
+ # <p>
+ # If the tree structure is modified during iteration, the result
+ # is undefined.
+ #
+ # @param tag What tags to look for (default is to return all elements).
+ # @return A list or iterator containing all the matching elements.
+ # @defreturn list or iterator
+
+ def getiterator(self, tag=None):
+ nodes = []
+ if tag == "*":
+ tag = None
+ if tag is None or self.tag == tag:
+ nodes.append(self)
+ for node in self._children:
+ nodes.extend(node.getiterator(tag))
+ return nodes
+
+# compatibility
+_Element = _ElementInterface
+
+##
+# Element factory. This function returns an object implementing the
+# standard Element interface. The exact class or type of that object
+# is implementation dependent, but it will always be compatible with
+# the {@link #_ElementInterface} class in this module.
+# <p>
+# The element name, attribute names, and attribute values can be
+# either 8-bit ASCII strings or Unicode strings.
+#
+# @param tag The element name.
+# @param attrib An optional dictionary, containing element attributes.
+# @param **extra Additional attributes, given as keyword arguments.
+# @return An element instance.
+# @defreturn Element
+
+def Element(tag, attrib={}, **extra):
+ attrib = attrib.copy()
+ attrib.update(extra)
+ return _ElementInterface(tag, attrib)
+
+##
+# Subelement factory. This function creates an element instance, and
+# appends it to an existing element.
+# <p>
+# The element name, attribute names, and attribute values can be
+# either 8-bit ASCII strings or Unicode strings.
+#
+# @param parent The parent element.
+# @param tag The subelement name.
+# @param attrib An optional dictionary, containing element attributes.
+# @param **extra Additional attributes, given as keyword arguments.
+# @return An element instance.
+# @defreturn Element
+
+def SubElement(parent, tag, attrib={}, **extra):
+ attrib = attrib.copy()
+ attrib.update(extra)
+ element = parent.makeelement(tag, attrib)
+ parent.append(element)
+ return element
+
+##
+# Comment element factory. This factory function creates a special
+# element that will be serialized as an XML comment.
+# <p>
+# The comment string can be either an 8-bit ASCII string or a Unicode
+# string.
+#
+# @param text A string containing the comment string.
+# @return An element instance, representing a comment.
+# @defreturn Element
+
+def Comment(text=None):
+ element = Element(Comment)
+ element.text = text
+ return element
+
+##
+# PI element factory. This factory function creates a special element
+# that will be serialized as an XML processing instruction.
+#
+# @param target A string containing the PI target.
+# @param text A string containing the PI contents, if any.
+# @return An element instance, representing a PI.
+# @defreturn Element
+
+def ProcessingInstruction(target, text=None):
+ element = Element(ProcessingInstruction)
+ element.text = target
+ if text:
+ element.text = element.text + " " + text
+ return element
+
+PI = ProcessingInstruction
+
+##
+# QName wrapper. This can be used to wrap a QName attribute value, in
+# order to get proper namespace handling on output.
+#
+# @param text A string containing the QName value, in the form {uri}local,
+# or, if the tag argument is given, the URI part of a QName.
+# @param tag Optional tag. If given, the first argument is interpreted as
+# an URI, and this argument is interpreted as a local name.
+# @return An opaque object, representing the QName.
+
+class QName:
+ def __init__(self, text_or_uri, tag=None):
+ if tag:
+ text_or_uri = "{%s}%s" % (text_or_uri, tag)
+ self.text = text_or_uri
+ def __str__(self):
+ return self.text
+ def __hash__(self):
+ return hash(self.text)
+ def __cmp__(self, other):
+ if isinstance(other, QName):
+ return cmp(self.text, other.text)
+ return cmp(self.text, other)
+
+##
+# ElementTree wrapper class. This class represents an entire element
+# hierarchy, and adds some extra support for serialization to and from
+# standard XML.
+#
+# @param element Optional root element.
+# @keyparam file Optional file handle or name. If given, the
+# tree is initialized with the contents of this XML file.
+
+class ElementTree:
+
+ def __init__(self, element=None, file=None):
+ assert element is None or iselement(element)
+ self._root = element # first node
+ if file:
+ self.parse(file)
+
+ ##
+ # Gets the root element for this tree.
+ #
+ # @return An element instance.
+ # @defreturn Element
+
+ def getroot(self):
+ return self._root
+
+ ##
+ # Replaces the root element for this tree. This discards the
+ # current contents of the tree, and replaces it with the given
+ # element. Use with care.
+ #
+ # @param element An element instance.
+
+ def _setroot(self, element):
+ assert iselement(element)
+ self._root = element
+
+ ##
+ # Loads an external XML document into this element tree.
+ #
+ # @param source A file name or file object.
+ # @param parser An optional parser instance. If not given, the
+ # standard {@link XMLTreeBuilder} parser is used.
+ # @return The document root element.
+ # @defreturn Element
+
+ def parse(self, source, parser=None):
+ if not hasattr(source, "read"):
+ source = open(source, "rb")
+ if not parser:
+ parser = XMLTreeBuilder()
+ while 1:
+ data = source.read(32768)
+ if not data:
+ break
+ parser.feed(data)
+ self._root = parser.close()
+ return self._root
+
+ ##
+ # Creates a tree iterator for the root element. The iterator loops
+ # over all elements in this tree, in document order.
+ #
+ # @param tag What tags to look for (default is to return all elements)
+ # @return An iterator.
+ # @defreturn iterator
+
+ def getiterator(self, tag=None):
+ assert self._root is not None
+ return self._root.getiterator(tag)
+
+ ##
+ # Finds the first toplevel element with given tag.
+ # Same as getroot().find(path).
+ #
+ # @param path What element to look for.
+ # @return The first matching element, or None if no element was found.
+ # @defreturn Element or None
+
+ def find(self, path):
+ assert self._root is not None
+ if path[:1] == "/":
+ path = "." + path
+ return self._root.find(path)
+
+ ##
+ # Finds the element text for the first toplevel element with given
+ # tag. Same as getroot().findtext(path).
+ #
+ # @param path What toplevel element to look for.
+ # @param default What to return if the element was not found.
+ # @return The text content of the first matching element, or the
+ # default value no element was found. Note that if the element
+ # has is found, but has no text content, this method returns an
+ # empty string.
+ # @defreturn string
+
+ def findtext(self, path, default=None):
+ assert self._root is not None
+ if path[:1] == "/":
+ path = "." + path
+ return self._root.findtext(path, default)
+
+ ##
+ # Finds all toplevel elements with the given tag.
+ # Same as getroot().findall(path).
+ #
+ # @param path What element to look for.
+ # @return A list or iterator containing all matching elements,
+ # in document order.
+ # @defreturn list of Element instances
+
+ def findall(self, path):
+ assert self._root is not None
+ if path[:1] == "/":
+ path = "." + path
+ return self._root.findall(path)
+
+ ##
+ # Writes the element tree to a file, as XML.
+ #
+ # @param file A file name, or a file object opened for writing.
+ # @param encoding Optional output encoding (default is US-ASCII).
+
+ def write(self, file, encoding="us-ascii"):
+ assert self._root is not None
+ if not hasattr(file, "write"):
+ file = open(file, "wb")
+ if not encoding:
+ encoding = "us-ascii"
+ elif encoding != "utf-8" and encoding != "us-ascii":
+ file.write("<?xml version='1.0' encoding='%s'?>\n" % encoding)
+ self._write(file, self._root, encoding, {})
+
+ def _write(self, file, node, encoding, namespaces):
+ # write XML to file
+ tag = node.tag
+ if tag is Comment:
+ file.write("<!-- %s -->" % _escape_cdata(node.text, encoding))
+ elif tag is ProcessingInstruction:
+ file.write("<?%s?>" % _escape_cdata(node.text, encoding))
+ else:
+ items = node.items()
+ xmlns_items = [] # new namespaces in this scope
+ try:
+ if isinstance(tag, QName) or tag[:1] == "{":
+ tag, xmlns = fixtag(tag, namespaces)
+ if xmlns: xmlns_items.append(xmlns)
+ except TypeError:
+ _raise_serialization_error(tag)
+ file.write("<" + _encode(tag, encoding))
+ if items or xmlns_items:
+ items.sort() # lexical order
+ for k, v in items:
+ try:
+ if isinstance(k, QName) or k[:1] == "{":
+ k, xmlns = fixtag(k, namespaces)
+ if xmlns: xmlns_items.append(xmlns)
+ except TypeError:
+ _raise_serialization_error(k)
+ try:
+ if isinstance(v, QName):
+ v, xmlns = fixtag(v, namespaces)
+ if xmlns: xmlns_items.append(xmlns)
+ except TypeError:
+ _raise_serialization_error(v)
+ file.write(" %s=\"%s\"" % (_encode(k, encoding),
+ _escape_attrib(v, encoding)))
+ for k, v in xmlns_items:
+ file.write(" %s=\"%s\"" % (_encode(k, encoding),
+ _escape_attrib(v, encoding)))
+ if node.text or len(node):
+ file.write(">")
+ if node.text:
+ file.write(_escape_cdata(node.text, encoding))
+ for n in node:
+ self._write(file, n, encoding, namespaces)
+ file.write("</" + _encode(tag, encoding) + ">")
+ else:
+ file.write(" />")
+ for k, v in xmlns_items:
+ del namespaces[v]
+ if node.tail:
+ file.write(_escape_cdata(node.tail, encoding))
+
+# --------------------------------------------------------------------
+# helpers
+
+##
+# Checks if an object appears to be a valid element object.
+#
+# @param An element instance.
+# @return A true value if this is an element object.
+# @defreturn flag
+
+def iselement(element):
+ # FIXME: not sure about this; might be a better idea to look
+ # for tag/attrib/text attributes
+ return isinstance(element, _ElementInterface) or hasattr(element, "tag")
+
+##
+# Writes an element tree or element structure to sys.stdout. This
+# function should be used for debugging only.
+# <p>
+# The exact output format is implementation dependent. In this
+# version, it's written as an ordinary XML file.
+#
+# @param elem An element tree or an individual element.
+
+def dump(elem):
+ # debugging
+ if not isinstance(elem, ElementTree):
+ elem = ElementTree(elem)
+ elem.write(sys.stdout)
+ tail = elem.getroot().tail
+ if not tail or tail[-1] != "\n":
+ sys.stdout.write("\n")
+
+def _encode(s, encoding):
+ try:
+ return s.encode(encoding)
+ except AttributeError:
+ return s # 1.5.2: assume the string uses the right encoding
+
+if sys.version[:3] == "1.5":
+ _escape = re.compile(r"[&<>\"\x80-\xff]+") # 1.5.2
+else:
+ _escape = re.compile(eval(r'u"[&<>\"\u0080-\uffff]+"'))
+
+_escape_map = {
+ "&": "&",
+ "<": "<",
+ ">": ">",
+ '"': """,
+}
+
+_namespace_map = {
+ # "well-known" namespace prefixes
+ "http://www.w3.org/XML/1998/namespace": "xml",
+ "http://www.w3.org/1999/xhtml": "html",
+ "http://www.w3.org/1999/02/22-rdf-syntax-ns#": "rdf",
+ "http://schemas.xmlsoap.org/wsdl/": "wsdl",
+}
+
+def _raise_serialization_error(text):
+ raise TypeError(
+ "cannot serialize %r (type %s)" % (text, type(text).__name__)
+ )
+
+def _encode_entity(text, pattern=_escape):
+ # map reserved and non-ascii characters to numerical entities
+ def escape_entities(m, map=_escape_map):
+ out = []
+ append = out.append
+ for char in m.group():
+ text = map.get(char)
+ if text is None:
+ text = "&#%d;" % ord(char)
+ append(text)
+ return string.join(out, "")
+ try:
+ return _encode(pattern.sub(escape_entities, text), "ascii")
+ except TypeError:
+ _raise_serialization_error(text)
+
+#
+# the following functions assume an ascii-compatible encoding
+# (or "utf-16")
+
+def _escape_cdata(text, encoding=None, replace=string.replace):
+ # escape character data
+ try:
+ if encoding:
+ try:
+ text = _encode(text, encoding)
+ except UnicodeError:
+ return _encode_entity(text)
+ text = replace(text, "&", "&")
+ text = replace(text, "<", "<")
+ text = replace(text, ">", ">")
+ return text
+ except (TypeError, AttributeError):
+ _raise_serialization_error(text)
+
+def _escape_attrib(text, encoding=None, replace=string.replace):
+ # escape attribute value
+ try:
+ if encoding:
+ try:
+ text = _encode(text, encoding)
+ except UnicodeError:
+ return _encode_entity(text)
+ text = replace(text, "&", "&")
+ text = replace(text, "'", "'") # FIXME: overkill
+ text = replace(text, "\"", """)
+ text = replace(text, "<", "<")
+ text = replace(text, ">", ">")
+ return text
+ except (TypeError, AttributeError):
+ _raise_serialization_error(text)
+
+def fixtag(tag, namespaces):
+ # given a decorated tag (of the form {uri}tag), return prefixed
+ # tag and namespace declaration, if any
+ if isinstance(tag, QName):
+ tag = tag.text
+ namespace_uri, tag = string.split(tag[1:], "}", 1)
+ prefix = namespaces.get(namespace_uri)
+ if prefix is None:
+ prefix = _namespace_map.get(namespace_uri)
+ if prefix is None:
+ prefix = "ns%d" % len(namespaces)
+ namespaces[namespace_uri] = prefix
+ if prefix == "xml":
+ xmlns = None
+ else:
+ xmlns = ("xmlns:%s" % prefix, namespace_uri)
+ else:
+ xmlns = None
+ return "%s:%s" % (prefix, tag), xmlns
+
+##
+# Parses an XML document into an element tree.
+#
+# @param source A filename or file object containing XML data.
+# @param parser An optional parser instance. If not given, the
+# standard {@link XMLTreeBuilder} parser is used.
+# @return An ElementTree instance
+
+def parse(source, parser=None):
+ tree = ElementTree()
+ tree.parse(source, parser)
+ return tree
+
+##
+# Parses an XML document into an element tree incrementally, and reports
+# what's going on to the user.
+#
+# @param source A filename or file object containing XML data.
+# @param events A list of events to report back. If omitted, only "end"
+# events are reported.
+# @return A (event, elem) iterator.
+
+class iterparse:
+
+ def __init__(self, source, events=None):
+ if not hasattr(source, "read"):
+ source = open(source, "rb")
+ self._file = source
+ self._events = []
+ self._index = 0
+ self.root = self._root = None
+ self._parser = XMLTreeBuilder()
+ # wire up the parser for event reporting
+ parser = self._parser._parser
+ append = self._events.append
+ if events is None:
+ events = ["end"]
+ for event in events:
+ if event == "start":
+ try:
+ parser.ordered_attributes = 1
+ parser.specified_attributes = 1
+ def handler(tag, attrib_in, event=event, append=append,
+ start=self._parser._start_list):
+ append((event, start(tag, attrib_in)))
+ parser.StartElementHandler = handler
+ except AttributeError:
+ def handler(tag, attrib_in, event=event, append=append,
+ start=self._parser._start):
+ append((event, start(tag, attrib_in)))
+ parser.StartElementHandler = handler
+ elif event == "end":
+ def handler(tag, event=event, append=append,
+ end=self._parser._end):
+ append((event, end(tag)))
+ parser.EndElementHandler = handler
+ elif event == "start-ns":
+ def handler(prefix, uri, event=event, append=append):
+ try:
+ uri = _encode(uri, "ascii")
+ except UnicodeError:
+ pass
+ append((event, (prefix or "", uri)))
+ parser.StartNamespaceDeclHandler = handler
+ elif event == "end-ns":
+ def handler(prefix, event=event, append=append):
+ append((event, None))
+ parser.EndNamespaceDeclHandler = handler
+
+ def next(self):
+ while 1:
+ try:
+ item = self._events[self._index]
+ except IndexError:
+ if self._parser is None:
+ self.root = self._root
+ try:
+ raise StopIteration
+ except NameError:
+ raise IndexError
+ # load event buffer
+ del self._events[:]
+ self._index = 0
+ data = self._file.read(16384)
+ if data:
+ self._parser.feed(data)
+ else:
+ self._root = self._parser.close()
+ self._parser = None
+ else:
+ self._index = self._index + 1
+ return item
+
+ try:
+ iter
+ def __iter__(self):
+ return self
+ except NameError:
+ def __getitem__(self, index):
+ return self.next()
+
+##
+# Parses an XML document from a string constant. This function can
+# be used to embed "XML literals" in Python code.
+#
+# @param source A string containing XML data.
+# @return An Element instance.
+# @defreturn Element
+
+def XML(text):
+ parser = XMLTreeBuilder()
+ parser.feed(text)
+ return parser.close()
+
+##
+# Parses an XML document from a string constant, and also returns
+# a dictionary which maps from element id:s to elements.
+#
+# @param source A string containing XML data.
+# @return A tuple containing an Element instance and a dictionary.
+# @defreturn (Element, dictionary)
+
+def XMLID(text):
+ parser = XMLTreeBuilder()
+ parser.feed(text)
+ tree = parser.close()
+ ids = {}
+ for elem in tree.getiterator():
+ id = elem.get("id")
+ if id:
+ ids[id] = elem
+ return tree, ids
+
+##
+# Parses an XML document from a string constant. Same as {@link #XML}.
+#
+# @def fromstring(text)
+# @param source A string containing XML data.
+# @return An Element instance.
+# @defreturn Element
+
+fromstring = XML
+
+##
+# Generates a string representation of an XML element, including all
+# subelements.
+#
+# @param element An Element instance.
+# @return An encoded string containing the XML data.
+# @defreturn string
+
+def tostring(element, encoding=None):
+ class dummy:
+ pass
+ data = []
+ file = dummy()
+ file.write = data.append
+ ElementTree(element).write(file, encoding)
+ return string.join(data, "")
+
+##
+# Generic element structure builder. This builder converts a sequence
+# of {@link #TreeBuilder.start}, {@link #TreeBuilder.data}, and {@link
+# #TreeBuilder.end} method calls to a well-formed element structure.
+# <p>
+# You can use this class to build an element structure using a custom XML
+# parser, or a parser for some other XML-like format.
+#
+# @param element_factory Optional element factory. This factory
+# is called to create new Element instances, as necessary.
+
+class TreeBuilder:
+
+ def __init__(self, element_factory=None):
+ self._data = [] # data collector
+ self._elem = [] # element stack
+ self._last = None # last element
+ self._tail = None # true if we're after an end tag
+ if element_factory is None:
+ element_factory = _ElementInterface
+ self._factory = element_factory
+
+ ##
+ # Flushes the parser buffers, and returns the toplevel documen
+ # element.
+ #
+ # @return An Element instance.
+ # @defreturn Element
+
+ def close(self):
+ assert len(self._elem) == 0, "missing end tags"
+ assert self._last != None, "missing toplevel element"
+ return self._last
+
+ def _flush(self):
+ if self._data:
+ if self._last is not None:
+ text = string.join(self._data, "")
+ if self._tail:
+ assert self._last.tail is None, "internal error (tail)"
+ self._last.tail = text
+ else:
+ assert self._last.text is None, "internal error (text)"
+ self._last.text = text
+ self._data = []
+
+ ##
+ # Adds text to the current element.
+ #
+ # @param data A string. This should be either an 8-bit string
+ # containing ASCII text, or a Unicode string.
+
+ def data(self, data):
+ self._data.append(data)
+
+ ##
+ # Opens a new element.
+ #
+ # @param tag The element name.
+ # @param attrib A dictionary containing element attributes.
+ # @return The opened element.
+ # @defreturn Element
+
+ def start(self, tag, attrs):
+ self._flush()
+ self._last = elem = self._factory(tag, attrs)
+ if self._elem:
+ self._elem[-1].append(elem)
+ self._elem.append(elem)
+ self._tail = 0
+ return elem
+
+ ##
+ # Closes the current element.
+ #
+ # @param tag The element name.
+ # @return The closed element.
+ # @defreturn Element
+
+ def end(self, tag):
+ self._flush()
+ self._last = self._elem.pop()
+ assert self._last.tag == tag,\
+ "end tag mismatch (expected %s, got %s)" % (
+ self._last.tag, tag)
+ self._tail = 1
+ return self._last
+
+##
+# Element structure builder for XML source data, based on the
+# <b>expat</b> parser.
+#
+# @keyparam target Target object. If omitted, the builder uses an
+# instance of the standard {@link #TreeBuilder} class.
+# @keyparam html Predefine HTML entities. This flag is not supported
+# by the current implementation.
+# @see #ElementTree
+# @see #TreeBuilder
+
+class XMLTreeBuilder:
+
+ def __init__(self, html=0, target=None):
+ try:
+ from xmlcore.parsers import expat
+ except ImportError:
+ raise ImportError(
+ "No module named expat; use SimpleXMLTreeBuilder instead"
+ )
+ self._parser = parser = expat.ParserCreate(None, "}")
+ if target is None:
+ target = TreeBuilder()
+ self._target = target
+ self._names = {} # name memo cache
+ # callbacks
+ parser.DefaultHandlerExpand = self._default
+ parser.StartElementHandler = self._start
+ parser.EndElementHandler = self._end
+ parser.CharacterDataHandler = self._data
+ # let expat do the buffering, if supported
+ try:
+ self._parser.buffer_text = 1
+ except AttributeError:
+ pass
+ # use new-style attribute handling, if supported
+ try:
+ self._parser.ordered_attributes = 1
+ self._parser.specified_attributes = 1
+ parser.StartElementHandler = self._start_list
+ except AttributeError:
+ pass
+ encoding = None
+ if not parser.returns_unicode:
+ encoding = "utf-8"
+ # target.xml(encoding, None)
+ self._doctype = None
+ self.entity = {}
+
+ def _fixtext(self, text):
+ # convert text string to ascii, if possible
+ try:
+ return _encode(text, "ascii")
+ except UnicodeError:
+ return text
+
+ def _fixname(self, key):
+ # expand qname, and convert name string to ascii, if possible
+ try:
+ name = self._names[key]
+ except KeyError:
+ name = key
+ if "}" in name:
+ name = "{" + name
+ self._names[key] = name = self._fixtext(name)
+ return name
+
+ def _start(self, tag, attrib_in):
+ fixname = self._fixname
+ tag = fixname(tag)
+ attrib = {}
+ for key, value in attrib_in.items():
+ attrib[fixname(key)] = self._fixtext(value)
+ return self._target.start(tag, attrib)
+
+ def _start_list(self, tag, attrib_in):
+ fixname = self._fixname
+ tag = fixname(tag)
+ attrib = {}
+ if attrib_in:
+ for i in range(0, len(attrib_in), 2):
+ attrib[fixname(attrib_in[i])] = self._fixtext(attrib_in[i+1])
+ return self._target.start(tag, attrib)
+
+ def _data(self, text):
+ return self._target.data(self._fixtext(text))
+
+ def _end(self, tag):
+ return self._target.end(self._fixname(tag))
+
+ def _default(self, text):
+ prefix = text[:1]
+ if prefix == "&":
+ # deal with undefined entities
+ try:
+ self._target.data(self.entity[text[1:-1]])
+ except KeyError:
+ from xmlcore.parsers import expat
+ raise expat.error(
+ "undefined entity %s: line %d, column %d" %
+ (text, self._parser.ErrorLineNumber,
+ self._parser.ErrorColumnNumber)
+ )
+ elif prefix == "<" and text[:9] == "<!DOCTYPE":
+ self._doctype = [] # inside a doctype declaration
+ elif self._doctype is not None:
+ # parse doctype contents
+ if prefix == ">":
+ self._doctype = None
+ return
+ text = string.strip(text)
+ if not text:
+ return
+ self._doctype.append(text)
+ n = len(self._doctype)
+ if n > 2:
+ type = self._doctype[1]
+ if type == "PUBLIC" and n == 4:
+ name, type, pubid, system = self._doctype
+ elif type == "SYSTEM" and n == 3:
+ name, type, system = self._doctype
+ pubid = None
+ else:
+ return
+ if pubid:
+ pubid = pubid[1:-1]
+ self.doctype(name, pubid, system[1:-1])
+ self._doctype = None
+
+ ##
+ # Handles a doctype declaration.
+ #
+ # @param name Doctype name.
+ # @param pubid Public identifier.
+ # @param system System identifier.
+
+ def doctype(self, name, pubid, system):
+ pass
+
+ ##
+ # Feeds data to the parser.
+ #
+ # @param data Encoded data.
+
+ def feed(self, data):
+ self._parser.Parse(data, 0)
+
+ ##
+ # Finishes feeding data to the parser.
+ #
+ # @return An element structure.
+ # @defreturn Element
+
+ def close(self):
+ self._parser.Parse("", 1) # end of data
+ tree = self._target.close()
+ del self._target, self._parser # get rid of circular references
+ return tree
projects / python / commitdiff