From f15351d938e76c4b2a42a638825d67f108685140 Mon Sep 17 00:00:00 2001 From: Florent Xicluna Date: Sat, 13 Mar 2010 23:24:31 +0000 Subject: [PATCH] Merged revisions 78838-78839,78917,78919,78934,78937 via svnmerge from svn+ssh://pythondev@svn.python.org/python/trunk ........ r78838 | florent.xicluna | 2010-03-11 15:36:19 +0100 (jeu, 11 mar 2010) | 2 lines Issue #6472: The xml.etree package is updated to ElementTree 1.3. The cElementTree module is updated too. ........ r78839 | florent.xicluna | 2010-03-11 16:55:11 +0100 (jeu, 11 mar 2010) | 2 lines Fix repr of tree Element on windows. ........ r78917 | florent.xicluna | 2010-03-13 12:18:49 +0100 (sam, 13 mar 2010) | 2 lines Move the xml test data to their own directory. ........ r78919 | florent.xicluna | 2010-03-13 13:41:48 +0100 (sam, 13 mar 2010) | 2 lines Do not chdir when running test_xml_etree, and enhance the findfile helper. ........ r78934 | florent.xicluna | 2010-03-13 18:56:19 +0100 (sam, 13 mar 2010) | 2 lines Update some parts of the xml.etree documentation. ........ r78937 | florent.xicluna | 2010-03-13 21:30:15 +0100 (sam, 13 mar 2010) | 3 lines Add the keyword argument "method=None" to the .write() method and the tostring/tostringlist functions. Update the function, class and method signatures, according to the new convention. ........ --- Doc/library/xml.etree.elementtree.rst | 530 +++++--- Doc/library/xml.etree.rst | 23 - Lib/test/support.py | 4 +- Lib/test/test_minidom.py | 12 +- Lib/test/test_sax.py | 18 +- Lib/test/test_xml_etree.py | 1617 ++++++++++++++++++++++- Lib/test/test_xml_etree_c.py | 219 +-- Lib/test/xmltestdata/simple-ns.xml | 7 + Lib/test/xmltestdata/simple.xml | 6 + Lib/test/{ => xmltestdata}/test.xml | 0 Lib/test/{ => xmltestdata}/test.xml.out | 0 Lib/xml/etree/ElementInclude.py | 6 +- Lib/xml/etree/ElementPath.py | 367 +++-- Lib/xml/etree/ElementTree.py | 1229 +++++++++++------ Lib/xml/etree/__init__.py | 6 +- Makefile.pre.in | 2 +- Misc/NEWS | 3 + Modules/_elementtree.c | 807 +++++++---- Tools/msi/msi.py | 5 +- 19 files changed, 3534 insertions(+), 1327 deletions(-) delete mode 100644 Doc/library/xml.etree.rst create mode 100644 Lib/test/xmltestdata/simple-ns.xml create mode 100644 Lib/test/xmltestdata/simple.xml rename Lib/test/{ => xmltestdata}/test.xml (100%) rename Lib/test/{ => xmltestdata}/test.xml.out (100%) diff --git a/Doc/library/xml.etree.elementtree.rst b/Doc/library/xml.etree.elementtree.rst index 0d3f61cb34d..d9e1b59cd3d 100644 --- a/Doc/library/xml.etree.elementtree.rst +++ b/Doc/library/xml.etree.elementtree.rst @@ -6,9 +6,9 @@ .. moduleauthor:: Fredrik Lundh -The Element 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. +The :class:`Element` 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. Each element has a number of properties associated with it: @@ -23,7 +23,8 @@ Each element has a number of properties associated with it: * a number of child elements, stored in a Python sequence -To create an element instance, use the Element or SubElement factory functions. +To create an element instance, use the :class:`Element` constructor or the +:func:`SubElement` factory function. The :class:`ElementTree` class can be used to wrap an element structure, and convert it from and to XML. @@ -31,8 +32,14 @@ convert it from and to XML. A C implementation of this API is available as :mod:`xml.etree.cElementTree`. See http://effbot.org/zone/element-index.htm for tutorials and links to other -docs. Fredrik Lundh's page is also the location of the development version of the -xml.etree.ElementTree. +docs. Fredrik Lundh's page is also the location of the development version of +the xml.etree.ElementTree. + +.. versionchanged:: 2.7 + The ElementTree API is updated to 1.3. For more information, see + `Introducing ElementTree 1.3 + `_. + .. _elementtree-functions: @@ -43,16 +50,16 @@ Functions .. function:: Comment(text=None) Comment element factory. This factory function creates a special element - that will be serialized as an XML comment. The comment string can be either - an ASCII-only :class:`bytes` object or a :class:`str` object. *text* is a - string containing the comment string. Returns an element instance + that will be serialized as an XML comment by the standard serializer. The + comment string can be either a bytestring or a Unicode string. *text* is a + string containing the comment string. Returns an element instance representing a comment. .. function:: dump(elem) - Writes an element tree or element structure to sys.stdout. This function should - be used for debugging only. + Writes an element tree or element structure to sys.stdout. This function + should be used for debugging only. The exact output format is implementation dependent. In this version, it's written as an ordinary XML file. @@ -60,38 +67,36 @@ Functions *elem* is an element tree or an individual element. -.. function:: Element(tag, attrib={}, **extra) - - 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 _ElementInterface class in - this module. - - The element name, attribute names, and attribute values can be either an - ASCII-only :class:`bytes` object or a :class:`str` object. *tag* is the - element name. *attrib* is an optional dictionary, containing element - attributes. *extra* contains additional attributes, given as keyword - arguments. Returns an element instance. - - .. function:: fromstring(text) - Parses an XML section from a string constant. Same as XML. *text* is a string - containing XML data. Returns an Element instance. + Parses an XML section from a string constant. Same as XML. *text* is a + string containing XML data. Returns an :class:`Element` instance. + + +.. function:: fromstringlist(sequence, parser=None) + + Parses an XML document from a sequence of string fragments. *sequence* is a + list or other sequence containing XML data fragments. *parser* is an + optional parser instance. If not given, the standard :class:`XMLParser` + parser is used. Returns an :class:`Element` instance. + + .. versionadded:: 2.7 .. function:: iselement(element) - Checks if an object appears to be a valid element object. *element* is an - element instance. Returns a true value if this is an element object. + Checks if an object appears to be a valid element object. *element* is an + element instance. Returns a true value if this is an element object. -.. function:: iterparse(source, events=None) +.. function:: iterparse(source, events=None, parser=None) Parses an XML section into an element tree incrementally, and reports what's - going on to the user. *source* is a filename or file object containing XML data. - *events* is a list of events to report back. If omitted, only "end" events are - reported. Returns an :term:`iterator` providing ``(event, elem)`` pairs. + going on to the user. *source* is a filename or file object containing XML + data. *events* is a list of events to report back. If omitted, only "end" + events are reported. *parser* is an optional parser instance. If not + given, the standard :class:`XMLParser` parser is used. Returns an + :term:`iterator` providing ``(event, elem)`` pairs. .. note:: @@ -106,196 +111,267 @@ Functions .. function:: parse(source, parser=None) - Parses an XML section into an element tree. *source* is a filename or file - object containing XML data. *parser* is an optional parser instance. If not - given, the standard XMLTreeBuilder parser is used. Returns an ElementTree - instance. + Parses an XML section into an element tree. *source* is a filename or file + object containing XML data. *parser* is an optional parser instance. If + not given, the standard :class:`XMLParser` parser is used. Returns an + :class:`ElementTree` instance. .. function:: ProcessingInstruction(target, text=None) - PI element factory. This factory function creates a special element that will - be serialized as an XML processing instruction. *target* is a string containing - the PI target. *text* is a string containing the PI contents, if given. Returns - an element instance, representing a processing instruction. + PI element factory. This factory function creates a special element that + will be serialized as an XML processing instruction. *target* is a string + containing the PI target. *text* is a string containing the PI contents, if + given. Returns an element instance, representing a processing instruction. + + +.. function:: register_namespace(prefix, uri) + + Registers a namespace prefix. The registry is global, and any existing + mapping for either the given prefix or the namespace URI will be removed. + *prefix* is a namespace prefix. *uri* is a namespace uri. Tags and + attributes in this namespace will be serialized with the given prefix, if at + all possible. + + .. versionadded:: 2.7 .. function:: SubElement(parent, tag, attrib={}, **extra) - Subelement factory. This function creates an element instance, and appends it - to an existing element. + Subelement factory. This function creates an element instance, and appends + it to an existing element. - The element name, attribute names, and attribute values can be an ASCII-only - :class:`bytes` object or a :class:`str` object. *parent* is the parent - element. *tag* is the subelement name. *attrib* is an optional dictionary, - containing element attributes. *extra* contains additional attributes, given - as keyword arguments. Returns an element instance. + The element name, attribute names, and attribute values can be either + bytestrings or Unicode strings. *parent* is the parent element. *tag* is + the subelement name. *attrib* is an optional dictionary, containing element + attributes. *extra* contains additional attributes, given as keyword + arguments. Returns an element instance. -.. function:: tostring(element, encoding=None) +.. function:: tostring(element, encoding=None, method=None) - Generates a string representation of an XML element, including all subelements. - *element* is an Element instance. *encoding* is the output encoding (default is - US-ASCII). Returns an encoded string containing the XML data. + Generates a string representation of an XML element, including all + subelements. *element* is an :class:`Element` instance. *encoding* is the + output encoding (default is None). *method* is either ``"xml"``, + ``"html"`` or ``"text"`` (default is ``"xml"``). Returns an (optionally) + encoded string containing the XML data. -.. function:: XML(text) +.. function:: tostringlist(element, encoding=None, method=None) + + Generates a string representation of an XML element, including all + subelements. *element* is an :class:`Element` instance. *encoding* is the + output encoding (default is None). *method* is either ``"xml"``, + ``"html"`` or ``"text"`` (default is ``"xml"``). Returns a sequence object + containing the XML data. + + .. versionadded:: 2.7 + + +.. function:: XML(text, parser=None) Parses an XML section from a string constant. This function can be used to - embed "XML literals" in Python code. *text* is a string containing XML data. - Returns an Element instance. + embed "XML literals" in Python code. *text* is a string containing XML + data. *parser* is an optional parser instance. If not given, the standard + :class:`XMLParser` parser is used. Returns an :class:`Element` instance. -.. function:: XMLID(text) +.. function:: XMLID(text, parser=None) Parses an XML section from a string constant, and also returns a dictionary - which maps from element id:s to elements. *text* is a string containing XML - data. Returns a tuple containing an Element instance and a dictionary. + which maps from element id:s to elements. *text* is a string containing XML + data. *parser* is an optional parser instance. If not given, the standard + :class:`XMLParser` parser is used. Returns a tuple containing an + :class:`Element` instance and a dictionary. -.. _elementtree-element-interface: +.. _elementtree-element-objects: -The Element Interface ---------------------- +Element Objects +--------------- -Element objects returned by Element or SubElement have the following methods -and attributes. +.. class:: Element(tag, attrib={}, **extra) -.. attribute:: Element.tag + Element class. This class defines the Element interface, and provides a + reference implementation of this interface. - A string identifying what kind of data this element represents (the element - type, in other words). + The element name, attribute names, and attribute values can be either + bytestrings or Unicode strings. *tag* is the element name. *attrib* is + an optional dictionary, containing element attributes. *extra* contains + additional attributes, given as keyword arguments. -.. attribute:: Element.text + .. attribute:: tag - The *text* attribute can be used to hold additional data associated with the - element. As the name implies this attribute is usually a string but may be any - application-specific object. If the element is created from an XML file the - attribute will contain any text found between the element tags. + A string identifying what kind of data this element represents (the + element type, in other words). -.. attribute:: Element.tail + .. attribute:: text - The *tail* attribute can be used to hold additional data associated with the - element. This attribute is usually a string but may be any application-specific - object. If the element is created from an XML file the attribute will contain - any text found after the element's end tag and before the next tag. + The *text* attribute can be used to hold additional data associated with + the element. As the name implies this attribute is usually a string but + may be any application-specific object. If the element is created from + an XML file the attribute will contain any text found between the element + tags. -.. attribute:: Element.attrib + .. attribute:: tail - A dictionary containing the element's attributes. Note that while the *attrib* - value is always a real mutable Python dictionary, an ElementTree implementation - may choose to use another internal representation, and create the dictionary - only if someone asks for it. To take advantage of such implementations, use the - dictionary methods below whenever possible. + The *tail* attribute can be used to hold additional data associated with + the element. This attribute is usually a string but may be any + application-specific object. If the element is created from an XML file + the attribute will contain any text found after the element's end tag and + before the next tag. -The following dictionary-like methods work on the element attributes. + .. attribute:: attrib -.. method:: Element.clear() + A dictionary containing the element's attributes. Note that while the + *attrib* value is always a real mutable Python dictionary, an ElementTree + implementation may choose to use another internal representation, and + create the dictionary only if someone asks for it. To take advantage of + such implementations, use the dictionary methods below whenever possible. - Resets an element. This function removes all subelements, clears all - attributes, and sets the text and tail attributes to None. + The following dictionary-like methods work on the element attributes. -.. method:: Element.get(key, default=None) + .. method:: clear() - Gets the element attribute named *key*. + Resets an element. This function removes all subelements, clears all + attributes, and sets the text and tail attributes to None. - Returns the attribute value, or *default* if the attribute was not found. + .. method:: get(key, default=None) -.. method:: Element.items() + Gets the element attribute named *key*. - Returns the element attributes as a sequence of (name, value) pairs. The - attributes are returned in an arbitrary order. + Returns the attribute value, or *default* if the attribute was not found. -.. method:: Element.keys() + .. method:: items() - Returns the elements attribute names as a list. The names are returned in an - arbitrary order. + Returns the element attributes as a sequence of (name, value) pairs. The + attributes are returned in an arbitrary order. -.. method:: Element.set(key, value) + .. method:: keys() - Set the attribute *key* on the element to *value*. + Returns the elements attribute names as a list. The names are returned + in an arbitrary order. -The following methods work on the element's children (subelements). + .. method:: set(key, value) -.. method:: Element.append(subelement) + Set the attribute *key* on the element to *value*. - Adds the element *subelement* to the end of this elements internal list of - subelements. + The following methods work on the element's children (subelements). -.. method:: Element.find(match) + .. method:: append(subelement) - Finds the first subelement matching *match*. *match* may be a tag name or path. - Returns an element instance or ``None``. + Adds the element *subelement* to the end of this elements internal list + of subelements. -.. method:: Element.findall(match) + .. method:: extend(subelements) - Finds all subelements matching *match*. *match* may be a tag name or path. - Returns an iterable yielding all matching elements in document order. + Appends *subelements* from a sequence object with zero or more elements. + Raises :exc:`AssertionError` if a subelement is not a valid object. + .. versionadded:: 2.7 -.. method:: Element.findtext(condition, default=None) - Finds text for the first subelement matching *condition*. *condition* may be a - tag name or path. Returns the text content of the first matching element, or - *default* if no element was found. Note that if the matching element has no - text content an empty string is returned. + .. method:: find(match) + Finds the first subelement matching *match*. *match* may be a tag name + or path. Returns an element instance or ``None``. -.. method:: Element.getchildren() - Returns all subelements. The elements are returned in document order. + .. method:: findall(match) + Finds all matching subelements, by tag name or path. Returns a list + containing all matching elements in document order. -.. method:: Element.getiterator(tag=None) - Creates a tree iterator with the current element as the root. The iterator - iterates over this element and all elements below it, in document (depth first) - order. If *tag* is not ``None`` or ``'*'``, only elements whose tag equals - *tag* are returned from the iterator. + .. method:: findtext(match, default=None) + Finds text for the first subelement matching *match*. *match* may be + a tag name or path. Returns the text content of the first matching + element, or *default* if no element was found. Note that if the matching + element has no text content an empty string is returned. -.. method:: Element.insert(index, element) - Inserts a subelement at the given position in this element. + .. method:: getchildren() + .. deprecated:: 2.7 + Use ``list(elem)`` or iteration. -.. method:: Element.makeelement(tag, attrib) - Creates a new element object of the same type as this element. Do not call this - method, use the SubElement factory function instead. + .. method:: getiterator(tag=None) + .. deprecated:: 2.7 + Use method :meth:`Element.iter` instead. -.. method:: Element.remove(subelement) - Removes *subelement* from the element. Unlike the findXYZ methods this method - compares elements based on the instance identity, not on tag value or contents. + .. method:: insert(index, element) -Element objects also support the following sequence type methods for working -with subelements: :meth:`__delitem__`, :meth:`__getitem__`, :meth:`__setitem__`, -:meth:`__len__`. + Inserts a subelement at the given position in this element. -Caution: Because Element objects do not define a :meth:`__bool__` method, -elements with no subelements will test as ``False``. :: - element = root.find('foo') + .. method:: iter(tag=None) - if not element: # careful! - print("element not found, or element has no subelements") + Creates a tree :term:`iterator` with the current element as the root. + The iterator iterates over this element and all elements below it, in + document (depth first) order. If *tag* is not ``None`` or ``'*'``, only + elements whose tag equals *tag* are returned from the iterator. If the + tree structure is modified during iteration, the result is undefined. - if element is None: - print("element not found") + + .. method:: iterfind(match) + + Finds all matching subelements, by tag name or path. Returns an iterable + yielding all matching elements in document order. + + .. versionadded:: 2.7 + + + .. method:: itertext() + + Creates a text iterator. The iterator loops over this element and all + subelements, in document order, and returns all inner text. + + .. versionadded:: 2.7 + + + .. method:: makeelement(tag, attrib) + + Creates a new element object of the same type as this element. Do not + call this method, use the :func:`SubElement` factory function instead. + + + .. method:: remove(subelement) + + Removes *subelement* from the element. Unlike the find\* methods this + method compares elements based on the instance identity, not on tag value + or contents. + + :class:`Element` objects also support the following sequence type methods + for working with subelements: :meth:`__delitem__`, :meth:`__getitem__`, + :meth:`__setitem__`, :meth:`__len__`. + + Caution: Elements with no subelements will test as ``False``. This behavior + will change in future versions. Use specific ``len(elem)`` or ``elem is + None`` test instead. :: + + element = root.find('foo') + + if not element: # careful! + print("element not found, or element has no subelements") + + if element is None: + print("element not found") .. _elementtree-elementtree-objects: @@ -306,70 +382,88 @@ ElementTree Objects .. class:: ElementTree(element=None, file=None) - ElementTree wrapper class. This class represents an entire element hierarchy, - and adds some extra support for serialization to and from standard XML. + ElementTree wrapper class. This class represents an entire element + hierarchy, and adds some extra support for serialization to and from + standard XML. - *element* is the root element. The tree is initialized with the contents of the - XML *file* if given. + *element* is the root element. The tree is initialized with the contents + of the XML *file* if given. .. method:: _setroot(element) 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. *element* is an element instance. + care. *element* is an element instance. - .. method:: find(path) + .. method:: find(match) - Finds the first toplevel element with given tag. Same as - getroot().find(path). *path* is the element to look for. Returns the - first matching element, or ``None`` if no element was found. + Finds the first toplevel element matching *match*. *match* may be a tag + name or path. Same as getroot().find(match). Returns the first matching + element, or ``None`` if no element was found. - .. method:: findall(path) + .. method:: findall(match) - Finds all toplevel elements with the given tag. Same as - getroot().findall(path). *path* is the element to look for. Returns a - list or :term:`iterator` containing all matching elements, in document - order. + Finds all matching subelements, by tag name or path. Same as + getroot().findall(match). *match* may be a tag name or path. Returns a + list containing all matching elements, in document order. - .. method:: findtext(path, default=None) + .. method:: findtext(match, default=None) Finds the element text for the first toplevel element with given tag. - Same as getroot().findtext(path). *path* is the toplevel element to look - for. *default* is the value to return if the element was not - found. Returns 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. + Same as getroot().findtext(match). *match* may be a tag name or path. + *default* is the value to return if the element was not found. Returns + the text content of the first matching element, or the default value no + element was found. Note that if the element is found, but has no text + content, this method returns an empty string. .. method:: getiterator(tag=None) - Creates and returns a tree iterator for the root element. The iterator - loops over all elements in this tree, in section order. *tag* is the tag - to look for (default is to return all elements) + .. deprecated:: 2.7 + Use method :meth:`ElementTree.iter` instead. .. method:: getroot() - Returns the root element for this tree. + .. method:: iter(tag=None) + + Creates and returns a tree iterator for the root element. The iterator + loops over all elements in this tree, in section order. *tag* is the tag + to look for (default is to return all elements) + + + .. method:: iterfind(match) + + Finds all matching subelements, by tag name or path. Same as + getroot().iterfind(match). Returns an iterable yielding all matching + elements in document order. + + .. versionadded:: 2.7 + + .. method:: parse(source, parser=None) - Loads an external XML section into this element tree. *source* is a file - name or file object. *parser* is an optional parser instance. If not - given, the standard XMLTreeBuilder parser is used. Returns the section + Loads an external XML section into this element tree. *source* is a file + name or file object. *parser* is an optional parser instance. If not + given, the standard XMLParser parser is used. Returns the section root element. - .. method:: write(file, encoding=None) + .. method:: write(file, encoding=None, xml_declaration=None, method=None) - Writes the element tree to a file, as XML. *file* is a file name, or a - file object opened for writing. *encoding* [1]_ is the output encoding - (default is US-ASCII). + Writes the element tree to a file, as XML. *file* is a file name, or a + file object opened for writing. *encoding* [1]_ is the output encoding + (default is None). *xml_declaration* controls if an XML declaration + should be added to the file. Use False for never, True for always, None + for only if not US-ASCII or UTF-8 (default is None). *method* is either + ``"xml"``, ``"html"`` or ``"text"`` (default is ``"xml"``). Returns an + (optionally) encoded string. This is the XML file that is going to be manipulated:: @@ -388,13 +482,13 @@ Example of changing the attribute "target" of every link in first paragraph:: >>> from xml.etree.ElementTree import ElementTree >>> tree = ElementTree() >>> tree.parse("index.xhtml") - + >>> p = tree.find("body/p") # Finds first occurrence of tag p in body >>> p - - >>> links = p.getiterator("a") # Returns list of all links + + >>> links = list(p.iter("a")) # Returns list of all links >>> links - [, ] + [, ] >>> for i in links: # Iterates through all found links ... i.attrib["target"] = "blank" >>> tree.write("output.xhtml") @@ -407,12 +501,12 @@ QName Objects .. class:: QName(text_or_uri, tag=None) - QName wrapper. This can be used to wrap a QName attribute value, in order to - get proper namespace handling on output. *text_or_uri* is a string containing - the QName value, in the form {uri}local, or, if the tag argument is given, the - URI part of a QName. If *tag* is given, the first argument is interpreted as an - URI, and this argument is interpreted as a local name. :class:`QName` instances - are opaque. + QName wrapper. This can be used to wrap a QName attribute value, in order + to get proper namespace handling on output. *text_or_uri* is a string + containing the QName value, in the form {uri}local, or, if the tag argument + is given, the URI part of a QName. If *tag* is given, the first argument is + interpreted as an URI, and this argument is interpreted as a local name. + :class:`QName` instances are opaque. .. _elementtree-treebuilder-objects: @@ -423,74 +517,89 @@ TreeBuilder Objects .. class:: TreeBuilder(element_factory=None) - Generic element structure builder. This builder converts a sequence of start, - data, and end method calls to a well-formed element structure. You can use this - class to build an element structure using a custom XML parser, or a parser for - some other XML-like format. The *element_factory* is called to create new - Element instances when given. + Generic element structure builder. This builder converts a sequence of + start, data, and end method calls to a well-formed element structure. You + can use this class to build an element structure using a custom XML parser, + or a parser for some other XML-like format. The *element_factory* is called + to create new :class:`Element` instances when given. .. method:: close() - Flushes the parser buffers, and returns the toplevel document - element. Returns an Element instance. + Flushes the builder buffers, and returns the toplevel document + element. Returns an :class:`Element` instance. .. method:: data(data) - Adds text to the current element. *data* is a string. This should be - either an ASCII-only :class:`bytes` object or a :class:`str` object. + Adds text to the current element. *data* is a string. This should be + either a bytestring, or a Unicode string. .. method:: end(tag) - Closes the current element. *tag* is the element name. Returns the closed - element. + Closes the current element. *tag* is the element name. Returns the + closed element. .. method:: start(tag, attrs) - Opens a new element. *tag* is the element name. *attrs* is a dictionary - containing element attributes. Returns the opened element. + Opens a new element. *tag* is the element name. *attrs* is a dictionary + containing element attributes. Returns the opened element. -.. _elementtree-xmltreebuilder-objects: + In addition, a custom :class:`TreeBuilder` object can provide the + following method: -XMLTreeBuilder Objects ----------------------- + .. method:: doctype(name, pubid, system) + + Handles a doctype declaration. *name* is the doctype name. *pubid* is + the public identifier. *system* is the system identifier. This method + does not exist on the default :class:`TreeBuilder` class. + + .. versionadded:: 2.7 -.. class:: XMLTreeBuilder(html=0, target=None) +.. _elementtree-xmlparser-objects: - Element structure builder for XML source data, based on the expat parser. *html* - are predefined HTML entities. This flag is not supported by the current - implementation. *target* is the target object. If omitted, the builder uses an - instance of the standard TreeBuilder class. +XMLParser Objects +----------------- + + +.. class:: XMLParser(html=0, target=None, encoding=None) + + :class:`Element` structure builder for XML source data, based on the expat + parser. *html* are predefined HTML entities. This flag is not supported by + the current implementation. *target* is the target object. If omitted, the + builder uses an instance of the standard TreeBuilder class. *encoding* [1]_ + is optional. If given, the value overrides the encoding specified in the + XML file. .. method:: close() - Finishes feeding data to the parser. Returns an element structure. + Finishes feeding data to the parser. Returns an element structure. .. method:: doctype(name, pubid, system) - Handles a doctype declaration. *name* is the doctype name. *pubid* is the - public identifier. *system* is the system identifier. + .. deprecated:: 2.7 + Define the :meth:`TreeBuilder.doctype` method on a custom TreeBuilder + target. .. method:: feed(data) - Feeds data to the parser. *data* is encoded data. + Feeds data to the parser. *data* is encoded data. -:meth:`XMLTreeBuilder.feed` calls *target*\'s :meth:`start` method +:meth:`XMLParser.feed` calls *target*\'s :meth:`start` method for each opening tag, its :meth:`end` method for each closing tag, -and data is processed by method :meth:`data`. :meth:`XMLTreeBuilder.close` +and data is processed by method :meth:`data`. :meth:`XMLParser.close` calls *target*\'s method :meth:`close`. -:class:`XMLTreeBuilder` can be used not only for building a tree structure. +:class:`XMLParser` can be used not only for building a tree structure. This is an example of counting the maximum depth of an XML file:: - >>> from xml.etree.ElementTree import XMLTreeBuilder + >>> from xml.etree.ElementTree import XMLParser >>> class MaxDepth: # The target object of the parser ... maxDepth = 0 ... depth = 0 @@ -506,7 +615,7 @@ This is an example of counting the maximum depth of an XML file:: ... return self.maxDepth ... >>> target = MaxDepth() - >>> parser = XMLTreeBuilder(target=target) + >>> parser = XMLParser(target=target) >>> exampleXml = """ ... ... @@ -526,7 +635,6 @@ This is an example of counting the maximum depth of an XML file:: .. rubric:: Footnotes .. [#] The encoding string included in XML output should conform to the - appropriate standards. For example, "UTF-8" is valid, but "UTF8" is - not. See http://www.w3.org/TR/2006/REC-xml11-20060816/#NT-EncodingDecl + appropriate standards. For example, "UTF-8" is valid, but "UTF8" is + not. See http://www.w3.org/TR/2006/REC-xml11-20060816/#NT-EncodingDecl and http://www.iana.org/assignments/character-sets. - diff --git a/Doc/library/xml.etree.rst b/Doc/library/xml.etree.rst deleted file mode 100644 index a9447654172..00000000000 --- a/Doc/library/xml.etree.rst +++ /dev/null @@ -1,23 +0,0 @@ -:mod:`xml.etree` --- The ElementTree API for XML -================================================ - -.. module:: xml.etree - :synopsis: Package containing common ElementTree modules. -.. moduleauthor:: Fredrik Lundh - - -The ElementTree package is a simple, efficient, and quite popular library for -XML manipulation in Python. The :mod:`xml.etree` package contains the most -common components from the ElementTree API library. In the current release, -this package contains the :mod:`ElementTree`, :mod:`ElementPath`, and -:mod:`ElementInclude` modules from the full ElementTree distribution. - -.. XXX To be continued! - - -.. seealso:: - - `ElementTree Overview `_ - The home page for :mod:`ElementTree`. This includes links to additional - documentation, alternative implementations, and other add-ons. - diff --git a/Lib/test/support.py b/Lib/test/support.py index 769f94a6cf8..a05f420710c 100644 --- a/Lib/test/support.py +++ b/Lib/test/support.py @@ -402,12 +402,14 @@ def temp_cwd(name='tempcwd', quiet=False): rmtree(name) -def findfile(file, here=__file__): +def findfile(file, here=__file__, subdir=None): """Try to find a file on sys.path and the working directory. If it is not found the argument passed to the function is returned (this does not necessarily signal failure; could still be the legitimate path).""" if os.path.isabs(file): return file + if subdir is not None: + file = os.path.join(subdir, file) path = sys.path path = [os.path.dirname(here)] + path for dn in path: diff --git a/Lib/test/test_minidom.py b/Lib/test/test_minidom.py index 0a0a6630822..606fada99da 100644 --- a/Lib/test/test_minidom.py +++ b/Lib/test/test_minidom.py @@ -1,9 +1,7 @@ # test for xml.dom.minidom -import os -import sys import pickle -from test.support import verbose, run_unittest +from test.support import verbose, run_unittest, findfile import unittest import xml.dom @@ -14,12 +12,8 @@ from xml.dom.minidom import parse, Node, Document, parseString from xml.dom.minidom import getDOMImplementation -if __name__ == "__main__": - base = sys.argv[0] -else: - base = __file__ -tstfile = os.path.join(os.path.dirname(base), "test.xml") -del base +tstfile = findfile("test.xml", subdir="xmltestdata") + # The tests of DocumentType importing use these helpers to construct # the documents to work with, since not all DOM builders actually diff --git a/Lib/test/test_sax.py b/Lib/test/test_sax.py index 781cf51782b..9b28b3fa106 100644 --- a/Lib/test/test_sax.py +++ b/Lib/test/test_sax.py @@ -15,7 +15,9 @@ from xml.sax.xmlreader import InputSource, AttributesImpl, AttributesNSImpl from io import StringIO from test.support import findfile, run_unittest import unittest -import os + +TEST_XMLFILE = findfile("test.xml", subdir="xmltestdata") +TEST_XMLFILE_OUT = findfile("test.xml.out", subdir="xmltestdata") ns_uri = "http://www.python.org/xml-ns/saxtest/" @@ -311,7 +313,7 @@ class XMLFilterBaseTest(unittest.TestCase): # # =========================================================================== -xml_test_out = open(findfile("test.xml.out")).read() +xml_test_out = open(TEST_XMLFILE_OUT).read() class ExpatReaderTest(XmlTestBase): @@ -323,7 +325,7 @@ class ExpatReaderTest(XmlTestBase): xmlgen = XMLGenerator(result) parser.setContentHandler(xmlgen) - parser.parse(open(findfile("test.xml"))) + parser.parse(open(TEST_XMLFILE)) self.assertEquals(result.getvalue(), xml_test_out) @@ -452,7 +454,7 @@ class ExpatReaderTest(XmlTestBase): xmlgen = XMLGenerator(result) parser.setContentHandler(xmlgen) - parser.parse(findfile("test.xml")) + parser.parse(TEST_XMLFILE) self.assertEquals(result.getvalue(), xml_test_out) @@ -462,7 +464,7 @@ class ExpatReaderTest(XmlTestBase): xmlgen = XMLGenerator(result) parser.setContentHandler(xmlgen) - parser.parse(InputSource(findfile("test.xml"))) + parser.parse(InputSource(TEST_XMLFILE)) self.assertEquals(result.getvalue(), xml_test_out) @@ -473,7 +475,7 @@ class ExpatReaderTest(XmlTestBase): parser.setContentHandler(xmlgen) inpsrc = InputSource() - inpsrc.setByteStream(open(findfile("test.xml"))) + inpsrc.setByteStream(open(TEST_XMLFILE)) parser.parse(inpsrc) self.assertEquals(result.getvalue(), xml_test_out) @@ -534,9 +536,9 @@ class ExpatReaderTest(XmlTestBase): xmlgen = XMLGenerator(result) parser = create_parser() parser.setContentHandler(xmlgen) - parser.parse(findfile("test.xml")) + parser.parse(TEST_XMLFILE) - self.assertEquals(parser.getSystemId(), findfile("test.xml")) + self.assertEquals(parser.getSystemId(), TEST_XMLFILE) self.assertEquals(parser.getPublicId(), None) diff --git a/Lib/test/test_xml_etree.py b/Lib/test/test_xml_etree.py index 3df18961ba4..3051540b788 100644 --- a/Lib/test/test_xml_etree.py +++ b/Lib/test/test_xml_etree.py @@ -1,22 +1,46 @@ # xml.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. +# all included components work as they should. +# Large parts are extracted from the upstream test suite. + +# IMPORTANT: the same doctests are run from "test_xml_etree_c" in +# order to ensure consistency between the C implementation and the +# Python implementation. +# +# For this purpose, the module-level "ET" symbol is temporarily +# monkey-patched when running the "test_xml_etree_c" test suite. +# Don't re-import "xml.etree.ElementTree" module in the docstring, +# except if the test is specific to the Python implementation. -import doctest import sys from test import support +from test.support import findfile -SAMPLE_XML = """ +from xml.etree import ElementTree as ET + +SIMPLE_XMLFILE = findfile("simple.xml", subdir="xmltestdata") +SIMPLE_NS_XMLFILE = findfile("simple-ns.xml", subdir="xmltestdata") + +SAMPLE_XML = """\ - text - + text +
- subtext + subtext
""" +SAMPLE_SECTION = """\ +
+ subtext + + + + +
+""" + SAMPLE_XML_NS = """ text @@ -27,6 +51,7 @@ SAMPLE_XML_NS = """ """ + def sanity(): """ Import sanity. @@ -40,35 +65,110 @@ def check_method(method): if not hasattr(method, '__call__'): print(method, "not callable") -def serialize(ET, elem): +def serialize(elem, to_string=True, **options): import io + if options.get("encoding"): + file = io.BytesIO() + else: + file = io.StringIO() tree = ET.ElementTree(elem) - file = io.StringIO() - tree.write(file) - return file.getvalue() + tree.write(file, **options) + if to_string: + return file.getvalue() + else: + file.seek(0) + return file def summarize(elem): + if elem.tag == ET.Comment: + return "" return elem.tag def summarize_list(seq): - return list(map(summarize, seq)) + return [summarize(elem) for elem in seq] + +def normalize_crlf(tree): + for elem in tree.iter(): + if elem.text: + elem.text = elem.text.replace("\r\n", "\n") + if elem.tail: + elem.tail = elem.tail.replace("\r\n", "\n") + +def normalize_exception(func, *args, **kwargs): + # Ignore the exception __module__ + try: + func(*args, **kwargs) + except Exception as err: + print("Traceback (most recent call last):") + print("{}: {}".format(err.__class__.__name__, err)) + +def check_string(string): + len(string) + for char in string: + if len(char) != 1: + print("expected one-character string, got %r" % char) + new_string = string + "" + new_string = string + " " + string[:0] + +def check_mapping(mapping): + len(mapping) + keys = mapping.keys() + items = mapping.items() + for key in keys: + item = mapping[key] + mapping["key"] = "value" + if mapping["key"] != "value": + print("expected value string, got %r" % mapping["key"]) + +def check_element(element): + if not ET.iselement(element): + print("not an element") + if not hasattr(element, "tag"): + print("no tag member") + if not hasattr(element, "attrib"): + print("no attrib member") + if not hasattr(element, "text"): + print("no text member") + if not hasattr(element, "tail"): + print("no tail member") + + check_string(element.tag) + check_mapping(element.attrib) + if element.text is not None: + check_string(element.text) + if element.tail is not None: + check_string(element.tail) + for elem in element: + check_element(elem) + +# -------------------------------------------------------------------- +# element tree tests def interface(): """ Test element tree interface. - >>> from xml.etree import ElementTree as ET - - >>> element = ET.Element("tag", key="value") + >>> element = ET.Element("tag") + >>> check_element(element) >>> tree = ET.ElementTree(element) + >>> check_element(tree.getroot()) + + >>> element = ET.Element("t\\xe4g", key="value") + >>> tree = ET.ElementTree(element) + >>> repr(element) # doctest: +ELLIPSIS + "" + >>> element = ET.Element("tag", key="value") Make sure all standard element methods exist. >>> check_method(element.append) + >>> check_method(element.extend) >>> check_method(element.insert) >>> check_method(element.remove) >>> check_method(element.getchildren) >>> check_method(element.find) + >>> check_method(element.iterfind) >>> check_method(element.findall) >>> check_method(element.findtext) >>> check_method(element.clear) @@ -76,38 +176,134 @@ def interface(): >>> check_method(element.set) >>> check_method(element.keys) >>> check_method(element.items) + >>> check_method(element.iter) + >>> check_method(element.itertext) >>> check_method(element.getiterator) + These methods return an iterable. See bug 6472. + + >>> check_method(element.iter("tag").__next__) + >>> check_method(element.iterfind("tag").__next__) + >>> check_method(element.iterfind("*").__next__) + >>> check_method(tree.iter("tag").__next__) + >>> check_method(tree.iterfind("tag").__next__) + >>> check_method(tree.iterfind("*").__next__) + + These aliases are provided: + + >>> assert ET.XML == ET.fromstring + >>> assert ET.PI == ET.ProcessingInstruction + >>> assert ET.XMLParser == ET.XMLTreeBuilder + """ + +def simpleops(): + """ Basic method sanity checks. - >>> serialize(ET, element) # 1 + >>> elem = ET.XML("") + >>> serialize(elem) + '' + >>> e = ET.Element("tag2") + >>> elem.append(e) + >>> serialize(elem) + '' + >>> elem.remove(e) + >>> serialize(elem) + '' + >>> elem.insert(0, e) + >>> serialize(elem) + '' + >>> elem.remove(e) + >>> elem.extend([e]) + >>> serialize(elem) + '' + >>> elem.remove(e) + + >>> element = ET.Element("tag", key="value") + >>> serialize(element) # 1 '' >>> subelement = ET.Element("subtag") >>> element.append(subelement) - >>> serialize(ET, element) # 2 + >>> serialize(element) # 2 '' >>> element.insert(0, subelement) - >>> serialize(ET, element) # 3 + >>> serialize(element) # 3 '' >>> element.remove(subelement) - >>> serialize(ET, element) # 4 + >>> serialize(element) # 4 '' >>> element.remove(subelement) - >>> serialize(ET, element) # 5 + >>> serialize(element) # 5 '' >>> element.remove(subelement) Traceback (most recent call last): ValueError: list.remove(x): x not in list - >>> serialize(ET, element) # 6 + >>> serialize(element) # 6 '' + >>> element[0:0] = [subelement, subelement, subelement] + >>> serialize(element[1]) + '' + >>> element[1:9] == [element[1], element[2]] + True + >>> element[:9:2] == [element[0], element[2]] + True + >>> del element[1:2] + >>> serialize(element) + '' + """ + +def cdata(): + """ + Test CDATA handling (etc). + + >>> serialize(ET.XML("hello")) + 'hello' + >>> serialize(ET.XML("hello")) + 'hello' + >>> serialize(ET.XML("")) + 'hello' + """ + +# Only with Python implementation +def simplefind(): + """ + Test find methods using the elementpath fallback. + + >>> from xml.etree import ElementTree + + >>> CurrentElementPath = ElementTree.ElementPath + >>> ElementTree.ElementPath = ElementTree._SimpleElementPath() + >>> elem = ElementTree.XML(SAMPLE_XML) + >>> elem.find("tag").tag + 'tag' + >>> ElementTree.ElementTree(elem).find("tag").tag + 'tag' + >>> elem.findtext("tag") + 'text' + >>> elem.findtext("tog") + >>> elem.findtext("tog", "default") + 'default' + >>> ElementTree.ElementTree(elem).findtext("tag") + 'text' + >>> summarize_list(elem.findall("tag")) + ['tag', 'tag'] + >>> summarize_list(elem.findall(".//tag")) + ['tag', 'tag', 'tag'] + + Path syntax doesn't work in this case. + + >>> elem.find("section/tag") + >>> elem.findtext("section/tag") + >>> summarize_list(elem.findall("section/tag")) + [] + + >>> ElementTree.ElementPath = CurrentElementPath """ def find(): """ Test find methods (including xpath syntax). - >>> from xml.etree import ElementTree as ET - >>> elem = ET.XML(SAMPLE_XML) >>> elem.find("tag").tag 'tag' @@ -115,39 +311,67 @@ def find(): 'tag' >>> elem.find("section/tag").tag 'tag' + >>> elem.find("./tag").tag + 'tag' + >>> ET.ElementTree(elem).find("./tag").tag + 'tag' + >>> ET.ElementTree(elem).find("/tag").tag + 'tag' + >>> elem[2] = ET.XML(SAMPLE_SECTION) + >>> elem.find("section/nexttag").tag + 'nexttag' >>> ET.ElementTree(elem).find("section/tag").tag 'tag' + >>> ET.ElementTree(elem).find("tog") + >>> ET.ElementTree(elem).find("tog/foo") >>> elem.findtext("tag") 'text' + >>> elem.findtext("section/nexttag") + '' + >>> elem.findtext("section/nexttag", "default") + '' >>> elem.findtext("tog") >>> elem.findtext("tog", "default") 'default' >>> ET.ElementTree(elem).findtext("tag") 'text' + >>> ET.ElementTree(elem).findtext("tog/foo") + >>> ET.ElementTree(elem).findtext("tog/foo", "default") + 'default' + >>> ET.ElementTree(elem).findtext("./tag") + 'text' + >>> ET.ElementTree(elem).findtext("/tag") + 'text' >>> elem.findtext("section/tag") 'subtext' >>> ET.ElementTree(elem).findtext("section/tag") 'subtext' + >>> summarize_list(elem.findall(".")) + ['body'] >>> summarize_list(elem.findall("tag")) ['tag', 'tag'] + >>> summarize_list(elem.findall("tog")) + [] + >>> summarize_list(elem.findall("tog/foo")) + [] >>> summarize_list(elem.findall("*")) ['tag', 'tag', 'section'] >>> summarize_list(elem.findall(".//tag")) - ['tag', 'tag', 'tag'] + ['tag', 'tag', 'tag', 'tag'] >>> summarize_list(elem.findall("section/tag")) ['tag'] >>> summarize_list(elem.findall("section//tag")) - ['tag'] + ['tag', 'tag'] >>> summarize_list(elem.findall("section/*")) - ['tag'] + ['tag', 'nexttag', 'nextsection'] >>> summarize_list(elem.findall("section//*")) - ['tag'] + ['tag', 'nexttag', 'nextsection', 'tag'] >>> summarize_list(elem.findall("section/.//*")) - ['tag'] + ['tag', 'nexttag', 'nextsection', 'tag'] >>> summarize_list(elem.findall("*/*")) - ['tag'] + ['tag', 'nexttag', 'nextsection'] >>> summarize_list(elem.findall("*//*")) - ['tag'] + ['tag', 'nexttag', 'nextsection', 'tag'] >>> summarize_list(elem.findall("*/tag")) ['tag'] >>> summarize_list(elem.findall("*/./tag")) @@ -155,13 +379,40 @@ def find(): >>> summarize_list(elem.findall("./tag")) ['tag', 'tag'] >>> summarize_list(elem.findall(".//tag")) - ['tag', 'tag', 'tag'] + ['tag', 'tag', 'tag', 'tag'] >>> summarize_list(elem.findall("././tag")) ['tag', 'tag'] - >>> summarize_list(ET.ElementTree(elem).findall("/tag")) + >>> summarize_list(elem.findall(".//tag[@class]")) + ['tag', 'tag', 'tag'] + >>> summarize_list(elem.findall(".//tag[@class='a']")) + ['tag'] + >>> summarize_list(elem.findall(".//tag[@class='b']")) + ['tag', 'tag'] + >>> summarize_list(elem.findall(".//tag[@id]")) + ['tag'] + >>> summarize_list(elem.findall(".//section[tag]")) + ['section'] + >>> summarize_list(elem.findall(".//section[element]")) + [] + >>> summarize_list(elem.findall("../tag")) + [] + >>> summarize_list(elem.findall("section/../tag")) ['tag', 'tag'] >>> summarize_list(ET.ElementTree(elem).findall("./tag")) ['tag', 'tag'] + + Following example is invalid in 1.2. + A leading '*' is assumed in 1.3. + + >>> elem.findall("section//") == elem.findall("section//*") + True + + ET's Path module handles this case incorrectly; this gives + a warning in 1.3, and the behaviour will be modified in 1.4. + + >>> summarize_list(ET.ElementTree(elem).findall("/tag")) + ['tag', 'tag'] + >>> elem = ET.XML(SAMPLE_XML_NS) >>> summarize_list(elem.findall("tag")) [] @@ -171,21 +422,227 @@ def find(): ['{http://effbot.org/ns}tag', '{http://effbot.org/ns}tag', '{http://effbot.org/ns}tag'] """ +def file_init(): + """ + >>> import io + + >>> stringfile = io.BytesIO(SAMPLE_XML.encode("utf-8")) + >>> tree = ET.ElementTree(file=stringfile) + >>> tree.find("tag").tag + 'tag' + >>> tree.find("section/tag").tag + 'tag' + + >>> tree = ET.ElementTree(file=SIMPLE_XMLFILE) + >>> tree.find("element").tag + 'element' + >>> tree.find("element/../empty-element").tag + 'empty-element' + """ + +def bad_find(): + """ + Check bad or unsupported path expressions. + + >>> elem = ET.XML(SAMPLE_XML) + >>> elem.findall("/tag") + Traceback (most recent call last): + SyntaxError: cannot use absolute path on element + """ + +def path_cache(): + """ + Check that the path cache behaves sanely. + + >>> elem = ET.XML(SAMPLE_XML) + >>> for i in range(10): ET.ElementTree(elem).find('./'+str(i)) + >>> cache_len_10 = len(ET.ElementPath._cache) + >>> for i in range(10): ET.ElementTree(elem).find('./'+str(i)) + >>> len(ET.ElementPath._cache) == cache_len_10 + True + >>> for i in range(20): ET.ElementTree(elem).find('./'+str(i)) + >>> len(ET.ElementPath._cache) > cache_len_10 + True + >>> for i in range(600): ET.ElementTree(elem).find('./'+str(i)) + >>> len(ET.ElementPath._cache) < 500 + True + """ + +def copy(): + """ + Test copy handling (etc). + + >>> import copy + >>> e1 = ET.XML("hello") + >>> e2 = copy.copy(e1) + >>> e3 = copy.deepcopy(e1) + >>> e1.find("foo").tag = "bar" + >>> serialize(e1) + 'hello' + >>> serialize(e2) + 'hello' + >>> serialize(e3) + 'hello' + + """ + +def attrib(): + """ + Test attribute handling. + + >>> elem = ET.Element("tag") + >>> elem.get("key") # 1.1 + >>> elem.get("key", "default") # 1.2 + 'default' + >>> elem.set("key", "value") + >>> elem.get("key") # 1.3 + 'value' + + >>> elem = ET.Element("tag", key="value") + >>> elem.get("key") # 2.1 + 'value' + >>> elem.attrib # 2.2 + {'key': 'value'} + + >>> attrib = {"key": "value"} + >>> elem = ET.Element("tag", attrib) + >>> attrib.clear() # check for aliasing issues + >>> elem.get("key") # 3.1 + 'value' + >>> elem.attrib # 3.2 + {'key': 'value'} + + >>> attrib = {"key": "value"} + >>> elem = ET.Element("tag", **attrib) + >>> attrib.clear() # check for aliasing issues + >>> elem.get("key") # 4.1 + 'value' + >>> elem.attrib # 4.2 + {'key': 'value'} + + >>> elem = ET.Element("tag", {"key": "other"}, key="value") + >>> elem.get("key") # 5.1 + 'value' + >>> elem.attrib # 5.2 + {'key': 'value'} + + >>> elem = ET.Element('test') + >>> elem.text = "aa" + >>> elem.set('testa', 'testval') + >>> elem.set('testb', 'test2') + >>> ET.tostring(elem) + 'aa' + >>> sorted(elem.keys()) + ['testa', 'testb'] + >>> sorted(elem.items()) + [('testa', 'testval'), ('testb', 'test2')] + >>> elem.attrib['testb'] + 'test2' + >>> elem.attrib['testb'] = 'test1' + >>> elem.attrib['testc'] = 'test2' + >>> ET.tostring(elem) + 'aa' + """ + +def makeelement(): + """ + Test makeelement handling. + + >>> elem = ET.Element("tag") + >>> attrib = {"key": "value"} + >>> subelem = elem.makeelement("subtag", attrib) + >>> if subelem.attrib is attrib: + ... print("attrib aliasing") + >>> elem.append(subelem) + >>> serialize(elem) + '' + + >>> elem.clear() + >>> serialize(elem) + '' + >>> elem.append(subelem) + >>> serialize(elem) + '' + >>> elem.extend([subelem, subelem]) + >>> serialize(elem) + '' + >>> elem[:] = [subelem] + >>> serialize(elem) + '' + >>> elem[:] = tuple([subelem]) + >>> serialize(elem) + '' + + """ + +def parsefile(): + """ + Test parsing from file. + + >>> tree = ET.parse(SIMPLE_XMLFILE) + >>> normalize_crlf(tree) + >>> tree.write(sys.stdout) + + text + texttail + + + >>> tree = ET.parse(SIMPLE_NS_XMLFILE) + >>> normalize_crlf(tree) + >>> tree.write(sys.stdout) + + text + texttail + + + + >>> parser = ET.XMLParser() + >>> parser.version # XXX: Upgrade to 2.0.1? + 'Expat 2.0.0' + >>> parser.feed(open(SIMPLE_XMLFILE).read()) + >>> print(serialize(parser.close())) + + text + texttail + + + + >>> parser = ET.XMLTreeBuilder() # 1.2 compatibility + >>> parser.feed(open(SIMPLE_XMLFILE).read()) + >>> print(serialize(parser.close())) + + text + texttail + + + + >>> target = ET.TreeBuilder() + >>> parser = ET.XMLParser(target=target) + >>> parser.feed(open(SIMPLE_XMLFILE).read()) + >>> print(serialize(parser.close())) + + text + texttail + + + """ + def parseliteral(): - r""" - - >>> from xml.etree import ElementTree as ET - + """ >>> element = ET.XML("text") >>> ET.ElementTree(element).write(sys.stdout) text >>> element = ET.fromstring("text") >>> ET.ElementTree(element).write(sys.stdout) text + >>> sequence = ["", "text"] + >>> element = ET.fromstringlist(sequence) >>> print(ET.tostring(element)) text - >>> print(repr(ET.tostring(element, "ascii"))) - b"\ntext" + >>> print("".join(ET.tostringlist(element))) + text + >>> ET.tostring(element, "ascii") + b"\\ntext" >>> _, ids = ET.XMLID("text") >>> len(ids) 0 @@ -196,25 +653,578 @@ def parseliteral(): 'body' """ - -def check_encoding(ET, encoding): +def iterparse(): """ - >>> from xml.etree import ElementTree as ET + Test iterparse interface. - >>> check_encoding(ET, "ascii") - >>> check_encoding(ET, "us-ascii") - >>> check_encoding(ET, "iso-8859-1") - >>> check_encoding(ET, "iso-8859-15") - >>> check_encoding(ET, "cp437") - >>> check_encoding(ET, "mac-roman") + >>> iterparse = ET.iterparse + + >>> context = iterparse(SIMPLE_XMLFILE) + >>> action, elem = next(context) + >>> print(action, elem.tag) + end element + >>> for action, elem in context: + ... print(action, elem.tag) + end element + end empty-element + end root + >>> context.root.tag + 'root' + + >>> context = iterparse(SIMPLE_NS_XMLFILE) + >>> for action, elem in context: + ... print(action, elem.tag) + end {namespace}element + end {namespace}element + end {namespace}empty-element + end {namespace}root + + >>> events = () + >>> context = iterparse(SIMPLE_XMLFILE, events) + >>> for action, elem in context: + ... print(action, elem.tag) + + >>> events = () + >>> context = iterparse(SIMPLE_XMLFILE, events=events) + >>> for action, elem in context: + ... print(action, elem.tag) + + >>> events = ("start", "end") + >>> context = iterparse(SIMPLE_XMLFILE, events) + >>> for action, elem in context: + ... print(action, elem.tag) + start root + start element + end element + start element + end element + start empty-element + end empty-element + end root + + >>> events = ("start", "end", "start-ns", "end-ns") + >>> context = iterparse(SIMPLE_NS_XMLFILE, events) + >>> for action, elem in context: + ... if action in ("start", "end"): + ... print(action, elem.tag) + ... else: + ... print(action, elem) + start-ns ('', 'namespace') + start {namespace}root + start {namespace}element + end {namespace}element + start {namespace}element + end {namespace}element + start {namespace}empty-element + end {namespace}empty-element + end {namespace}root + end-ns None + + >>> events = ("start", "end", "bogus") + >>> context = iterparse(SIMPLE_XMLFILE, events) + Traceback (most recent call last): + ValueError: unknown event 'bogus' + + >>> import io + + >>> source = io.BytesIO( + ... b"\\n" + ... b"text\\n") + >>> events = ("start-ns",) + >>> context = iterparse(source, events) + >>> for action, elem in context: + ... print(action, elem) + start-ns ('', 'http://\\xe9ffbot.org/ns') + start-ns ('cl\\xe9', 'http://effbot.org/ns') + + >>> source = io.StringIO("junk") + >>> try: + ... for action, elem in iterparse(source): + ... print(action, elem.tag) + ... except ET.ParseError as v: + ... print(v) + junk after document element: line 1, column 12 + """ + +def writefile(): + """ + >>> elem = ET.Element("tag") + >>> elem.text = "text" + >>> serialize(elem) + 'text' + >>> ET.SubElement(elem, "subtag").text = "subtext" + >>> serialize(elem) + 'textsubtext' + + Test tag suppression + >>> elem.tag = None + >>> serialize(elem) + 'textsubtext' + >>> elem.insert(0, ET.Comment("comment")) + >>> serialize(elem) # assumes 1.3 + 'textsubtext' + >>> elem[0] = ET.PI("key", "value") + >>> serialize(elem) + 'textsubtext' + """ + +def custom_builder(): + """ + Test parser w. custom builder. + + >>> class Builder: + ... def start(self, tag, attrib): + ... print("start", tag) + ... def end(self, tag): + ... print("end", tag) + ... def data(self, text): + ... pass + >>> builder = Builder() + >>> parser = ET.XMLParser(target=builder) + >>> parser.feed(open(SIMPLE_XMLFILE, "r").read()) + start root + start element + end element + start element + end element + start empty-element + end empty-element + end root + + >>> class Builder: + ... def start(self, tag, attrib): + ... print("start", tag) + ... def end(self, tag): + ... print("end", tag) + ... def data(self, text): + ... pass + ... def pi(self, target, data): + ... print("pi", target, repr(data)) + ... def comment(self, data): + ... print("comment", repr(data)) + >>> builder = Builder() + >>> parser = ET.XMLParser(target=builder) + >>> parser.feed(open(SIMPLE_NS_XMLFILE, "r").read()) + pi pi 'data' + comment ' comment ' + start {namespace}root + start {namespace}element + end {namespace}element + start {namespace}element + end {namespace}element + start {namespace}empty-element + end {namespace}empty-element + end {namespace}root + + """ + +def getchildren(): + """ + Test Element.getchildren() + + >>> tree = ET.parse(open(SIMPLE_XMLFILE, "rb")) + >>> for elem in tree.getroot().iter(): + ... summarize_list(elem.getchildren()) + ['element', 'element', 'empty-element'] + [] + [] + [] + >>> for elem in tree.getiterator(): + ... summarize_list(elem.getchildren()) + ['element', 'element', 'empty-element'] + [] + [] + [] + + >>> elem = ET.XML(SAMPLE_XML) + >>> len(elem.getchildren()) + 3 + >>> len(elem[2].getchildren()) + 1 + >>> elem[:] == elem.getchildren() + True + >>> child1 = elem[0] + >>> child2 = elem[2] + >>> del elem[1:2] + >>> len(elem.getchildren()) + 2 + >>> child1 == elem[0] + True + >>> child2 == elem[1] + True + >>> elem[0:2] = [child2, child1] + >>> child2 == elem[0] + True + >>> child1 == elem[1] + True + >>> child1 == elem[0] + False + >>> elem.clear() + >>> elem.getchildren() + [] + """ + +def writestring(): + """ + >>> elem = ET.XML("text") + >>> ET.tostring(elem) + 'text' + >>> elem = ET.fromstring("text") + >>> ET.tostring(elem) + 'text' + """ + +def check_encoding(encoding): + """ + >>> check_encoding("ascii") + >>> check_encoding("us-ascii") + >>> check_encoding("iso-8859-1") + >>> check_encoding("iso-8859-15") + >>> check_encoding("cp437") + >>> check_encoding("mac-roman") """ ET.XML("" % encoding) -def processinginstruction(): +def encoding(): r""" - Test ProcessingInstruction directly + Test encoding issues. - >>> from xml.etree import ElementTree as ET + >>> elem = ET.Element("tag") + >>> elem.text = "abc" + >>> serialize(elem) + 'abc' + >>> serialize(elem, encoding="utf-8") + b'abc' + >>> serialize(elem, encoding="us-ascii") + b'abc' + >>> serialize(elem, encoding="iso-8859-1") + b"\nabc" + + >>> elem.text = "<&\"\'>" + >>> serialize(elem) + '<&"\'>' + >>> serialize(elem, encoding="utf-8") + b'<&"\'>' + >>> serialize(elem, encoding="us-ascii") # cdata characters + b'<&"\'>' + >>> serialize(elem, encoding="iso-8859-1") + b'\n<&"\'>' + + >>> elem.attrib["key"] = "<&\"\'>" + >>> elem.text = None + >>> serialize(elem) + '' + >>> serialize(elem, encoding="utf-8") + b'' + >>> serialize(elem, encoding="us-ascii") + b'' + >>> serialize(elem, encoding="iso-8859-1") + b'\n' + + >>> elem.text = '\xe5\xf6\xf6<>' + >>> elem.attrib.clear() + >>> serialize(elem) + '\xe5\xf6\xf6<>' + >>> serialize(elem, encoding="utf-8") + b'\xc3\xa5\xc3\xb6\xc3\xb6<>' + >>> serialize(elem, encoding="us-ascii") + b'åöö<>' + >>> serialize(elem, encoding="iso-8859-1") + b"\n\xe5\xf6\xf6<>" + + >>> elem.attrib["key"] = '\xe5\xf6\xf6<>' + >>> elem.text = None + >>> serialize(elem) + '' + >>> serialize(elem, encoding="utf-8") + b'' + >>> serialize(elem, encoding="us-ascii") + b'' + >>> serialize(elem, encoding="iso-8859-1") + b'\n' + """ + +def methods(): + r""" + Test serialization methods. + + >>> e = ET.XML("") + >>> e.tail = "\n" + >>> serialize(e) + '\n' + >>> serialize(e, method=None) + '\n' + >>> serialize(e, method="xml") + '\n' + >>> serialize(e, method="html") + '\n' + >>> serialize(e, method="text") + '1 < 2\n' + """ + +def iterators(): + """ + Test iterators. + + >>> e = ET.XML("this is a paragraph...") + >>> summarize_list(e.iter()) + ['html', 'body', 'i'] + >>> summarize_list(e.find("body").iter()) + ['body', 'i'] + >>> summarize(next(e.iter())) + 'html' + >>> "".join(e.itertext()) + 'this is a paragraph...' + >>> "".join(e.find("body").itertext()) + 'this is a paragraph.' + >>> next(e.itertext()) + 'this is a ' + + Method iterparse should return an iterator. See bug 6472. + + >>> sourcefile = serialize(e, to_string=False) + >>> next(ET.iterparse(sourcefile)) # doctest: +ELLIPSIS + ('end', ) + + >>> tree = ET.ElementTree(None) + >>> tree.iter() + Traceback (most recent call last): + AttributeError: 'NoneType' object has no attribute 'iter' + """ + +ENTITY_XML = """\ + +%user-entities; +]> +&entity; +""" + +def entity(): + """ + Test entity handling. + + 1) good entities + + >>> e = ET.XML("test") + >>> serialize(e, encoding="us-ascii") + b'test' + >>> serialize(e) + 'test' + + 2) bad entities + + >>> normalize_exception(ET.XML, "&entity;") + Traceback (most recent call last): + ParseError: undefined entity: line 1, column 10 + + >>> normalize_exception(ET.XML, ENTITY_XML) + Traceback (most recent call last): + ParseError: undefined entity &entity;: line 5, column 10 + + 3) custom entity + + >>> parser = ET.XMLParser() + >>> parser.entity["entity"] = "text" + >>> parser.feed(ENTITY_XML) + >>> root = parser.close() + >>> serialize(root) + 'text' + """ + +def error(xml): + """ + + Test error handling. + + >>> issubclass(ET.ParseError, SyntaxError) + True + >>> error("foo").position + (1, 0) + >>> error("&foo;").position + (1, 5) + >>> error("foobar<").position + (1, 6) + + """ + try: + ET.XML(xml) + except ET.ParseError: + return sys.exc_info()[1] + +def namespace(): + """ + Test namespace issues. + + 1) xml namespace + + >>> elem = ET.XML("") + >>> serialize(elem) # 1.1 + '' + + 2) other "well-known" namespaces + + >>> elem = ET.XML("") + >>> serialize(elem) # 2.1 + '' + + >>> elem = ET.XML("") + >>> serialize(elem) # 2.2 + '' + + >>> elem = ET.XML("") + >>> serialize(elem) # 2.3 + '' + + 3) unknown namespaces + >>> elem = ET.XML(SAMPLE_XML_NS) + >>> print(serialize(elem)) + + text + + + subtext + + + """ + +def qname(): + """ + Test QName handling. + + 1) decorated tags + + >>> elem = ET.Element("{uri}tag") + >>> serialize(elem) # 1.1 + '' + >>> elem = ET.Element(ET.QName("{uri}tag")) + >>> serialize(elem) # 1.2 + '' + >>> elem = ET.Element(ET.QName("uri", "tag")) + >>> serialize(elem) # 1.3 + '' + + 2) decorated attributes + + >>> elem.clear() + >>> elem.attrib["{uri}key"] = "value" + >>> serialize(elem) # 2.1 + '' + + >>> elem.clear() + >>> elem.attrib[ET.QName("{uri}key")] = "value" + >>> serialize(elem) # 2.2 + '' + + 3) decorated values are not converted by default, but the + QName wrapper can be used for values + + >>> elem.clear() + >>> elem.attrib["{uri}key"] = "{uri}value" + >>> serialize(elem) # 3.1 + '' + + >>> elem.clear() + >>> elem.attrib["{uri}key"] = ET.QName("{uri}value") + >>> serialize(elem) # 3.2 + '' + + >>> elem.clear() + >>> subelem = ET.Element("tag") + >>> subelem.attrib["{uri1}key"] = ET.QName("{uri2}value") + >>> elem.append(subelem) + >>> elem.append(subelem) + >>> serialize(elem) # 3.3 + '' + + 4) Direct QName tests + + >>> str(ET.QName('ns', 'tag')) + '{ns}tag' + >>> str(ET.QName('{ns}tag')) + '{ns}tag' + >>> q1 = ET.QName('ns', 'tag') + >>> q2 = ET.QName('ns', 'tag') + >>> q1 == q2 + True + >>> q2 = ET.QName('ns', 'other-tag') + >>> q1 == q2 + False + >>> q1 == 'ns:tag' + False + >>> q1 == '{ns}tag' + True + """ + +def doctype_public(): + """ + Test PUBLIC doctype. + + >>> elem = ET.XML('' + ... 'text') + + """ + +def xpath_tokenizer(p): + """ + Test the XPath tokenizer. + + >>> # tests from the xml specification + >>> xpath_tokenizer("*") + ['*'] + >>> xpath_tokenizer("text()") + ['text', '()'] + >>> xpath_tokenizer("@name") + ['@', 'name'] + >>> xpath_tokenizer("@*") + ['@', '*'] + >>> xpath_tokenizer("para[1]") + ['para', '[', '1', ']'] + >>> xpath_tokenizer("para[last()]") + ['para', '[', 'last', '()', ']'] + >>> xpath_tokenizer("*/para") + ['*', '/', 'para'] + >>> xpath_tokenizer("/doc/chapter[5]/section[2]") + ['/', 'doc', '/', 'chapter', '[', '5', ']', '/', 'section', '[', '2', ']'] + >>> xpath_tokenizer("chapter//para") + ['chapter', '//', 'para'] + >>> xpath_tokenizer("//para") + ['//', 'para'] + >>> xpath_tokenizer("//olist/item") + ['//', 'olist', '/', 'item'] + >>> xpath_tokenizer(".") + ['.'] + >>> xpath_tokenizer(".//para") + ['.', '//', 'para'] + >>> xpath_tokenizer("..") + ['..'] + >>> xpath_tokenizer("../@lang") + ['..', '/', '@', 'lang'] + >>> xpath_tokenizer("chapter[title]") + ['chapter', '[', 'title', ']'] + >>> xpath_tokenizer("employee[@secretary and @assistant]") + ['employee', '[', '@', 'secretary', '', 'and', '', '@', 'assistant', ']'] + + >>> # additional tests + >>> xpath_tokenizer("{http://spam}egg") + ['{http://spam}egg'] + >>> xpath_tokenizer("./spam.egg") + ['.', '/', 'spam.egg'] + >>> xpath_tokenizer(".//{http://spam}egg") + ['.', '//', '{http://spam}egg'] + """ + from xml.etree import ElementPath + out = [] + for op, tag in ElementPath.xpath_tokenizer(p): + out.append(op or tag) + return out + +def processinginstruction(): + """ + Test ProcessingInstruction directly >>> ET.tostring(ET.ProcessingInstruction('test', 'instruction')) '' @@ -226,20 +1236,7 @@ def processinginstruction(): >>> ET.tostring(ET.PI('test', '')) '?>' >>> ET.tostring(ET.PI('test', '\xe3'), 'latin1') - b"\n\xe3?>" - - """ - -def check_issue6233(): - """ - >>> from xml.etree import ElementTree as ET - - >>> e = ET.XML("t\xe3g") - >>> ET.tostring(e, 'ascii') - b"\\ntãg" - >>> e = ET.XML("t\xe3g".encode('iso-8859-1')) # create byte string with the right encoding - >>> ET.tostring(e, 'ascii') - b"\\ntãg" + b"\\n\\xe3?>" """ # @@ -306,9 +1303,9 @@ XINCLUDE["default.xml"] = """\

Example.

- + -""" +""".format(SIMPLE_XMLFILE) def xinclude_loader(href, parse="xml", encoding=None): try: @@ -329,7 +1326,7 @@ def xinclude(): >>> document = xinclude_loader("C1.xml") >>> ElementInclude.include(document, xinclude_loader) - >>> print(serialize(ET, document)) # C1 + >>> print(serialize(document)) # C1

120 Mz is adequate for an average home user.

@@ -343,7 +1340,7 @@ def xinclude(): >>> document = xinclude_loader("C2.xml") >>> ElementInclude.include(document, xinclude_loader) - >>> print(serialize(ET, document)) # C2 + >>> print(serialize(document)) # C2

This document has been accessed 324387 times.

@@ -353,7 +1350,7 @@ def xinclude(): >>> document = xinclude_loader("C3.xml") >>> ElementInclude.include(document, xinclude_loader) - >>> print(serialize(ET, document)) # C3 + >>> print(serialize(document)) # C3

The following is the source of the "data.xml" resource:

<?xml version='1.0'?> @@ -370,13 +1367,489 @@ def xinclude(): >>> ElementInclude.include(document, xinclude_loader) Traceback (most recent call last): IOError: resource not found - >>> # print serialize(ET, document) # C5 + >>> # print(serialize(document)) # C5 + """ + +def xinclude_default(): + """ + >>> from xml.etree import ElementInclude + + >>> document = xinclude_loader("default.xml") + >>> ElementInclude.include(document) + >>> print(serialize(document)) # default + +

Example.

+ + text + texttail + + + + """ + +# +# badly formatted xi:include tags + +XINCLUDE_BAD = {} + +XINCLUDE_BAD["B1.xml"] = """\ + + +

120 Mz is adequate for an average home user.

+ + +""" + +XINCLUDE_BAD["B2.xml"] = """\ + +
+ +
+""" + +def xinclude_failures(): + r""" + Test failure to locate included XML file. + + >>> from xml.etree import ElementInclude + + >>> def none_loader(href, parser, encoding=None): + ... return None + + >>> document = ET.XML(XINCLUDE["C1.xml"]) + >>> ElementInclude.include(document, loader=none_loader) + Traceback (most recent call last): + xml.etree.ElementInclude.FatalIncludeError: cannot load 'disclaimer.xml' as 'xml' + + Test failure to locate included text file. + + >>> document = ET.XML(XINCLUDE["C2.xml"]) + >>> ElementInclude.include(document, loader=none_loader) + Traceback (most recent call last): + xml.etree.ElementInclude.FatalIncludeError: cannot load 'count.txt' as 'text' + + Test bad parse type. + + >>> document = ET.XML(XINCLUDE_BAD["B1.xml"]) + >>> ElementInclude.include(document, loader=none_loader) + Traceback (most recent call last): + xml.etree.ElementInclude.FatalIncludeError: unknown parse type in xi:include tag ('BAD_TYPE') + + Test xi:fallback outside xi:include. + + >>> document = ET.XML(XINCLUDE_BAD["B2.xml"]) + >>> ElementInclude.include(document, loader=none_loader) + Traceback (most recent call last): + xml.etree.ElementInclude.FatalIncludeError: xi:fallback tag must be child of xi:include ('{http://www.w3.org/2001/XInclude}fallback') + """ + +# -------------------------------------------------------------------- +# reported bugs + +def bug_xmltoolkit21(): + """ + + marshaller gives obscure errors for non-string values + + >>> elem = ET.Element(123) + >>> serialize(elem) # tag + Traceback (most recent call last): + TypeError: cannot serialize 123 (type int) + >>> elem = ET.Element("elem") + >>> elem.text = 123 + >>> serialize(elem) # text + Traceback (most recent call last): + TypeError: cannot serialize 123 (type int) + >>> elem = ET.Element("elem") + >>> elem.tail = 123 + >>> serialize(elem) # tail + Traceback (most recent call last): + TypeError: cannot serialize 123 (type int) + >>> elem = ET.Element("elem") + >>> elem.set(123, "123") + >>> serialize(elem) # attribute key + Traceback (most recent call last): + TypeError: cannot serialize 123 (type int) + >>> elem = ET.Element("elem") + >>> elem.set("123", 123) + >>> serialize(elem) # attribute value + Traceback (most recent call last): + TypeError: cannot serialize 123 (type int) """ -def test_main(): +def bug_xmltoolkit25(): + """ + + typo in ElementTree.findtext + + >>> elem = ET.XML(SAMPLE_XML) + >>> tree = ET.ElementTree(elem) + >>> tree.findtext("tag") + 'text' + >>> tree.findtext("section/tag") + 'subtext' + + """ + +def bug_xmltoolkit28(): + """ + + .//tag causes exceptions + + >>> tree = ET.XML("
") + >>> summarize_list(tree.findall(".//thead")) + [] + >>> summarize_list(tree.findall(".//tbody")) + ['tbody'] + + """ + +def bug_xmltoolkitX1(): + """ + + dump() doesn't flush the output buffer + + >>> tree = ET.XML("
") + >>> ET.dump(tree); print("tail") +
+ tail + + """ + +def bug_xmltoolkit39(): + """ + + non-ascii element and attribute names doesn't work + + >>> tree = ET.XML(b"") + >>> ET.tostring(tree, "utf-8") + b'' + + >>> tree = ET.XML(b"") + >>> tree.attrib + {'\\xe4ttr': 'v\\xe4lue'} + >>> ET.tostring(tree, "utf-8") + b'' + + >>> tree = ET.XML(b"text") + >>> ET.tostring(tree, "utf-8") + b'text' + + >>> tree = ET.Element("t\u00e4g") + >>> ET.tostring(tree, "utf-8") + b'' + + >>> tree = ET.Element("tag") + >>> tree.set("\u00e4ttr", "v\u00e4lue") + >>> ET.tostring(tree, "utf-8") + b'' + + """ + +def bug_xmltoolkit54(): + """ + + problems handling internally defined entities + + >>> e = ET.XML("]>&ldots;") + >>> serialize(e, encoding="us-ascii") + b'舰' + >>> serialize(e) + '\u8230' + + """ + +def bug_xmltoolkit55(): + """ + + make sure we're reporting the first error, not the last + + >>> normalize_exception(ET.XML, b"&ldots;&ndots;&rdots;") + Traceback (most recent call last): + ParseError: undefined entity &ldots;: line 1, column 36 + + """ + +class ExceptionFile: + def read(self, x): + raise IOError + +def xmltoolkit60(): + """ + + Handle crash in stream source. + >>> tree = ET.parse(ExceptionFile()) + Traceback (most recent call last): + IOError + + """ + +XMLTOOLKIT62_DOC = """ + + + +A new cultivar of Begonia plant named ‘BCT9801BEG’. + +""" + + +def xmltoolkit62(): + """ + + Don't crash when using custom entities. + + >>> xmltoolkit62() + 'A new cultivar of Begonia plant named \u2018BCT9801BEG\u2019.' + + """ + ENTITIES = {'rsquo': '\u2019', 'lsquo': '\u2018'} + parser = ET.XMLTreeBuilder() + parser.entity.update(ENTITIES) + parser.feed(XMLTOOLKIT62_DOC) + t = parser.close() + return t.find('.//paragraph').text + +def xmltoolkit63(): + """ + + Check reference leak. + >>> xmltoolkit63() + >>> count = sys.getrefcount(None) + >>> for i in range(1000): + ... xmltoolkit63() + >>> sys.getrefcount(None) - count + 0 + + """ + tree = ET.TreeBuilder() + tree.start("tag", {}) + tree.data("text") + tree.end("tag") + +# -------------------------------------------------------------------- + + +def bug_200708_newline(): + r""" + + Preserve newlines in attributes. + + >>> e = ET.Element('SomeTag', text="def _f():\n return 3\n") + >>> ET.tostring(e) + '' + >>> ET.XML(ET.tostring(e)).get("text") + 'def _f():\n return 3\n' + >>> ET.tostring(ET.XML(ET.tostring(e))) + '' + + """ + +def bug_200708_close(): + """ + + Test default builder. + >>> parser = ET.XMLParser() # default + >>> parser.feed("some text") + >>> summarize(parser.close()) + 'element' + + Test custom builder. + >>> class EchoTarget: + ... def close(self): + ... return ET.Element("element") # simulate root + >>> parser = ET.XMLParser(EchoTarget()) + >>> parser.feed("some text") + >>> summarize(parser.close()) + 'element' + + """ + +def bug_200709_default_namespace(): + """ + + >>> e = ET.Element("{default}elem") + >>> s = ET.SubElement(e, "{default}elem") + >>> serialize(e, default_namespace="default") # 1 + '' + + >>> e = ET.Element("{default}elem") + >>> s = ET.SubElement(e, "{default}elem") + >>> s = ET.SubElement(e, "{not-default}elem") + >>> serialize(e, default_namespace="default") # 2 + '' + + >>> e = ET.Element("{default}elem") + >>> s = ET.SubElement(e, "{default}elem") + >>> s = ET.SubElement(e, "elem") # unprefixed name + >>> serialize(e, default_namespace="default") # 3 + Traceback (most recent call last): + ValueError: cannot use non-qualified names with default_namespace option + + """ + +def bug_200709_register_namespace(): + """ + + >>> ET.tostring(ET.Element("{http://namespace.invalid/does/not/exist/}title")) + '' + >>> ET.register_namespace("foo", "http://namespace.invalid/does/not/exist/") + >>> ET.tostring(ET.Element("{http://namespace.invalid/does/not/exist/}title")) + '' + + And the Dublin Core namespace is in the default list: + + >>> ET.tostring(ET.Element("{http://purl.org/dc/elements/1.1/}title")) + '' + + """ + +def bug_200709_element_comment(): + """ + + Not sure if this can be fixed, really (since the serializer needs + ET.Comment, not cET.comment). + + >>> a = ET.Element('a') + >>> a.append(ET.Comment('foo')) + >>> a[0].tag == ET.Comment + True + + >>> a = ET.Element('a') + >>> a.append(ET.PI('foo')) + >>> a[0].tag == ET.PI + True + + """ + +def bug_200709_element_insert(): + """ + + >>> a = ET.Element('a') + >>> b = ET.SubElement(a, 'b') + >>> c = ET.SubElement(a, 'c') + >>> d = ET.Element('d') + >>> a.insert(0, d) + >>> summarize_list(a) + ['d', 'b', 'c'] + >>> a.insert(-1, d) + >>> summarize_list(a) + ['d', 'b', 'd', 'c'] + + """ + +def bug_200709_iter_comment(): + """ + + >>> a = ET.Element('a') + >>> b = ET.SubElement(a, 'b') + >>> comment_b = ET.Comment("TEST-b") + >>> b.append(comment_b) + >>> summarize_list(a.iter(ET.Comment)) + [''] + + """ + +# -------------------------------------------------------------------- +# reported on bugs.python.org + +def bug_1534630(): + """ + + >>> bob = ET.TreeBuilder() + >>> e = bob.data("data") + >>> e = bob.start("tag", {}) + >>> e = bob.end("tag") + >>> e = bob.close() + >>> serialize(e) + '' + + """ + +def check_issue6233(): + """ + + >>> e = ET.XML(b"t\\xc3\\xa3g") + >>> ET.tostring(e, 'ascii') + b"\\ntãg" + >>> e = ET.XML(b"t\\xe3g") + >>> ET.tostring(e, 'ascii') + b"\\ntãg" + + """ + +def check_issue3151(): + """ + + >>> e = ET.XML('') + >>> e.tag + '{${stuff}}localname' + >>> t = ET.ElementTree(e) + >>> ET.tostring(e) + '' + + """ + +def check_issue6565(): + """ + + >>> elem = ET.XML("") + >>> summarize_list(elem) + ['tag'] + >>> newelem = ET.XML(SAMPLE_XML) + >>> elem[:] = newelem[:] + >>> summarize_list(elem) + ['tag', 'tag', 'section'] + + """ + +# -------------------------------------------------------------------- + + +class CleanContext(object): + """Provide default namespace mapping and path cache.""" + + def __enter__(self): + from xml.etree import ElementTree + self._nsmap = ElementTree._namespace_map + self._path_cache = ElementTree.ElementPath._cache + # Copy the default namespace mapping + ElementTree._namespace_map = self._nsmap.copy() + # Copy the path cache (should be empty) + ElementTree.ElementPath._cache = self._path_cache.copy() + + def __exit__(self, *args): + from xml.etree import ElementTree + # Restore mapping and path cache + ElementTree._namespace_map = self._nsmap + ElementTree.ElementPath._cache = self._path_cache + + +def test_main(module_name='xml.etree.ElementTree'): + import warnings from test import test_xml_etree - support.run_doctest(test_xml_etree, verbosity=True) + def ignore(message, category=DeprecationWarning): + warnings.filterwarnings("ignore", message, category) + + # The same doctests are used for both the Python and the C implementations + assert test_xml_etree.ET.__name__ == module_name + + with warnings.catch_warnings(), CleanContext(): + # Search behaviour is broken if search path starts with "/". + ignore("This search is broken in 1.3 and earlier, and will be fixed " + "in a future version. If you rely on the current behaviour, " + "change it to '.+'", FutureWarning) + # Element.getchildren() and Element.getiterator() are deprecated. + ignore("This method will be removed in future versions. " + "Use .+ instead.") + # XMLParser.doctype() is deprecated. + ignore("This method of XMLParser is deprecated. " + "Define doctype.. method on the TreeBuilder target.") + + support.run_doctest(test_xml_etree, verbosity=True) + + # The module should not be changed by the tests + assert test_xml_etree.ET.__name__ == module_name if __name__ == '__main__': test_main() diff --git a/Lib/test/test_xml_etree_c.py b/Lib/test/test_xml_etree_c.py index 71973ed2347..ee270f900dd 100644 --- a/Lib/test/test_xml_etree_c.py +++ b/Lib/test/test_xml_etree_c.py @@ -1,31 +1,11 @@ # xml.etree test for cElementTree -import doctest -import sys - from test import support -ET = support.import_module('xml.etree.cElementTree') +cET = support.import_module('xml.etree.cElementTree') -SAMPLE_XML = """ - - text - -
- subtext -
- -""" -SAMPLE_XML_NS = """ - - text - -
- subtext -
- -""" +# cElementTree specific tests def sanity(): """ @@ -34,187 +14,26 @@ def sanity(): >>> from xml.etree import cElementTree """ -def check_method(method): - if not hasattr(method, '__call__'): - print(method, "not callable") - -def serialize(ET, elem): - import io - file = io.StringIO() - tree = ET.ElementTree(elem) - tree.write(file) - return file.getvalue() - -def summarize(elem): - return elem.tag - -def summarize_list(seq): - return list(map(summarize, seq)) - -def interface(): - """ - Test element tree interface. - - >>> 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 - '' - >>> subelement = ET.Element("subtag") - >>> element.append(subelement) - >>> serialize(ET, element) # 2 - '' - >>> element.insert(0, subelement) - >>> serialize(ET, element) # 3 - '' - >>> element.remove(subelement) - >>> serialize(ET, element) # 4 - '' - >>> element.remove(subelement) - >>> serialize(ET, element) # 5 - '' - >>> element.remove(subelement) - Traceback (most recent call last): - ValueError: list.remove(x): x not in list - >>> serialize(ET, element) # 6 - '' - """ - -def find(): - """ - Test find methods (including xpath syntax). - - >>> 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""" - - >>> element = ET.XML("text") - >>> ET.ElementTree(element).write(sys.stdout) - text - >>> element = ET.fromstring("text") - >>> ET.ElementTree(element).write(sys.stdout) - text - >>> print(ET.tostring(element)) - text - >>> print(repr(ET.tostring(element, "ascii"))) - b"\ntext" - >>> _, ids = ET.XMLID("text") - >>> len(ids) - 0 - >>> _, ids = ET.XMLID("text") - >>> len(ids) - 1 - >>> ids["body"].tag - 'body' - """ - -def check_encoding(encoding): - """ - >>> check_encoding("ascii") - >>> check_encoding("us-ascii") - >>> check_encoding("iso-8859-1") - >>> check_encoding("iso-8859-15") - >>> check_encoding("cp437") - >>> check_encoding("mac-roman") - """ - ET.XML( - "" % encoding - ) - -def bug_1534630(): - """ - >>> bob = ET.TreeBuilder() - >>> e = bob.data("data") - >>> e = bob.start("tag", {}) - >>> e = bob.end("tag") - >>> e = bob.close() - >>> serialize(ET, e) - '' - """ def test_main(): - from test import test_xml_etree_c + from test import test_xml_etree, test_xml_etree_c + + # Run the tests specific to the C implementation support.run_doctest(test_xml_etree_c, verbosity=True) + # Assign the C implementation before running the doctests + # Patch the __name__, to prevent confusion with the pure Python test + pyET = test_xml_etree.ET + py__name__ = test_xml_etree.__name__ + test_xml_etree.ET = cET + if __name__ != '__main__': + test_xml_etree.__name__ = __name__ + try: + # Run the same test suite as xml.etree.ElementTree + test_xml_etree.test_main(module_name='xml.etree.cElementTree') + finally: + test_xml_etree.ET = pyET + test_xml_etree.__name__ = py__name__ + if __name__ == '__main__': test_main() diff --git a/Lib/test/xmltestdata/simple-ns.xml b/Lib/test/xmltestdata/simple-ns.xml new file mode 100644 index 00000000000..f1f34b2e29c --- /dev/null +++ b/Lib/test/xmltestdata/simple-ns.xml @@ -0,0 +1,7 @@ + + + + text + texttail + + diff --git a/Lib/test/xmltestdata/simple.xml b/Lib/test/xmltestdata/simple.xml new file mode 100644 index 00000000000..b88c2c7e69a --- /dev/null +++ b/Lib/test/xmltestdata/simple.xml @@ -0,0 +1,6 @@ + + + text + texttail + + diff --git a/Lib/test/test.xml b/Lib/test/xmltestdata/test.xml similarity index 100% rename from Lib/test/test.xml rename to Lib/test/xmltestdata/test.xml diff --git a/Lib/test/test.xml.out b/Lib/test/xmltestdata/test.xml.out similarity index 100% rename from Lib/test/test.xml.out rename to Lib/test/xmltestdata/test.xml.out diff --git a/Lib/xml/etree/ElementInclude.py b/Lib/xml/etree/ElementInclude.py index d7f85b3217c..dde0a41531c 100644 --- a/Lib/xml/etree/ElementInclude.py +++ b/Lib/xml/etree/ElementInclude.py @@ -1,6 +1,6 @@ # # ElementTree -# $Id: ElementInclude.py 1862 2004-06-18 07:31:02Z Fredrik $ +# $Id: ElementInclude.py 3375 2008-02-13 08:05:08Z fredrik $ # # limited xinclude support for element trees # @@ -16,7 +16,7 @@ # -------------------------------------------------------------------- # The ElementTree toolkit is # -# Copyright (c) 1999-2004 by Fredrik Lundh +# Copyright (c) 1999-2008 by Fredrik Lundh # # By obtaining, using, and/or copying this software and/or its # associated documentation, you agree that you have read, understood, @@ -42,7 +42,7 @@ # -------------------------------------------------------------------- # Licensed to PSF under a Contributor Agreement. -# See http://www.python.org/2.4/license for licensing details. +# See http://www.python.org/psf/license for licensing details. ## # Limited XInclude support for the ElementTree package. diff --git a/Lib/xml/etree/ElementPath.py b/Lib/xml/etree/ElementPath.py index 00dbe9d546b..52e65f063da 100644 --- a/Lib/xml/etree/ElementPath.py +++ b/Lib/xml/etree/ElementPath.py @@ -1,6 +1,6 @@ # # ElementTree -# $Id: ElementPath.py 1858 2004-06-17 21:31:41Z Fredrik $ +# $Id: ElementPath.py 3375 2008-02-13 08:05:08Z fredrik $ # # limited xpath support for element trees # @@ -8,8 +8,13 @@ # 2003-05-23 fl created # 2003-05-28 fl added support for // etc # 2003-08-27 fl fixed parsing of periods in element names +# 2007-09-10 fl new selection engine +# 2007-09-12 fl fixed parent selector +# 2007-09-13 fl added iterfind; changed findall to return a list +# 2007-11-30 fl added namespaces support +# 2009-10-30 fl added child element value filter # -# Copyright (c) 2003-2004 by Fredrik Lundh. All rights reserved. +# Copyright (c) 2003-2009 by Fredrik Lundh. All rights reserved. # # fredrik@pythonware.com # http://www.pythonware.com @@ -17,7 +22,7 @@ # -------------------------------------------------------------------- # The ElementTree toolkit is # -# Copyright (c) 1999-2004 by Fredrik Lundh +# Copyright (c) 1999-2009 by Fredrik Lundh # # By obtaining, using, and/or copying this software and/or its # associated documentation, you agree that you have read, understood, @@ -43,7 +48,7 @@ # -------------------------------------------------------------------- # Licensed to PSF under a Contributor Agreement. -# See http://www.python.org/2.4/license for licensing details. +# See http://www.python.org/psf/license for licensing details. ## # Implementation module for XPath support. There's usually no reason @@ -53,146 +58,246 @@ import re -xpath_tokenizer = re.compile( - "(::|\.\.|\(\)|[/.*:\[\]\(\)@=])|((?:\{[^}]+\})?[^/:\[\]\(\)@=\s]+)|\s+" - ).findall +xpath_tokenizer_re = re.compile( + "(" + "'[^']*'|\"[^\"]*\"|" + "::|" + "//?|" + "\.\.|" + "\(\)|" + "[/.*:\[\]\(\)@=])|" + "((?:\{[^}]+\})?[^/\[\]\(\)@=\s]+)|" + "\s+" + ) -class xpath_descendant_or_self: - pass - -## -# Wrapper for a compiled XPath. - -class Path: - - ## - # Create an Path instance from an XPath expression. - - def __init__(self, path): - tokens = xpath_tokenizer(path) - # the current version supports 'path/path'-style expressions only - self.path = [] - self.tag = None - if tokens and tokens[0][0] == "/": - raise SyntaxError("cannot use absolute path on element") - while tokens: - op, tag = tokens.pop(0) - if tag or op == "*": - self.path.append(tag or op) - elif op == ".": - pass - elif op == "/": - self.path.append(xpath_descendant_or_self()) - continue - else: - raise SyntaxError("unsupported path syntax (%s)" % op) - if tokens: - op, tag = tokens.pop(0) - if op != "/": - raise SyntaxError( - "expected path separator (%s)" % (op or tag) - ) - if self.path and isinstance(self.path[-1], xpath_descendant_or_self): - raise SyntaxError("path cannot end with //") - if len(self.path) == 1 and isinstance(self.path[0], type("")): - self.tag = self.path[0] - - ## - # Find first matching object. - - def find(self, element): - tag = self.tag - if tag is None: - nodeset = self.findall(element) - if not nodeset: - return None - return nodeset[0] - for elem in element: - if elem.tag == tag: - return elem - return None - - ## - # Find text for first matching object. - - def findtext(self, element, default=None): - tag = self.tag - if tag is None: - nodeset = self.findall(element) - if not nodeset: - return default - return nodeset[0].text or "" - for elem in element: - if elem.tag == tag: - return elem.text or "" - return default - - ## - # Find all matching objects. - - def findall(self, element): - nodeset = [element] - index = 0 - while 1: +def xpath_tokenizer(pattern, namespaces=None): + for token in xpath_tokenizer_re.findall(pattern): + tag = token[1] + if tag and tag[0] != "{" and ":" in tag: try: - path = self.path[index] - index = index + 1 - except IndexError: - return nodeset - set = [] - if isinstance(path, xpath_descendant_or_self): + prefix, uri = tag.split(":", 1) + if not namespaces: + raise KeyError + yield token[0], "{%s}%s" % (namespaces[prefix], uri) + except KeyError: + raise SyntaxError("prefix %r not found in prefix map" % prefix) + else: + yield token + +def get_parent_map(context): + parent_map = context.parent_map + if parent_map is None: + context.parent_map = parent_map = {} + for p in context.root.iter(): + for e in p: + parent_map[e] = p + return parent_map + +def prepare_child(next, token): + tag = token[1] + def select(context, result): + for elem in result: + for e in elem: + if e.tag == tag: + yield e + return select + +def prepare_star(next, token): + def select(context, result): + for elem in result: + for e in elem: + yield e + return select + +def prepare_self(next, token): + def select(context, result): + for elem in result: + yield elem + return select + +def prepare_descendant(next, token): + token = next() + if token[0] == "*": + tag = "*" + elif not token[0]: + tag = token[1] + else: + raise SyntaxError("invalid descendant") + def select(context, result): + for elem in result: + for e in elem.iter(tag): + if e is not elem: + yield e + return select + +def prepare_parent(next, token): + def select(context, result): + # FIXME: raise error if .. is applied at toplevel? + parent_map = get_parent_map(context) + result_map = {} + for elem in result: + if elem in parent_map: + parent = parent_map[elem] + if parent not in result_map: + result_map[parent] = None + yield parent + return select + +def prepare_predicate(next, token): + # FIXME: replace with real parser!!! refs: + # http://effbot.org/zone/simple-iterator-parser.htm + # http://javascript.crockford.com/tdop/tdop.html + signature = [] + predicate = [] + while 1: + token = next() + if token[0] == "]": + break + if token[0] and token[0][:1] in "'\"": + token = "'", token[0][1:-1] + signature.append(token[0] or "-") + predicate.append(token[1]) + signature = "".join(signature) + # use signature to determine predicate type + if signature == "@-": + # [@attribute] predicate + key = predicate[1] + def select(context, result): + for elem in result: + if elem.get(key) is not None: + yield elem + return select + if signature == "@-='": + # [@attribute='value'] + key = predicate[1] + value = predicate[-1] + def select(context, result): + for elem in result: + if elem.get(key) == value: + yield elem + return select + if signature == "-" and not re.match("\d+$", predicate[0]): + # [tag] + tag = predicate[0] + def select(context, result): + for elem in result: + if elem.find(tag) is not None: + yield elem + return select + if signature == "-='" and not re.match("\d+$", predicate[0]): + # [tag='value'] + tag = predicate[0] + value = predicate[-1] + def select(context, result): + for elem in result: + for e in elem.findall(tag): + if "".join(e.itertext()) == value: + yield elem + break + return select + if signature == "-" or signature == "-()" or signature == "-()-": + # [index] or [last()] or [last()-index] + if signature == "-": + index = int(predicate[0]) - 1 + else: + if predicate[0] != "last": + raise SyntaxError("unsupported function") + if signature == "-()-": try: - tag = self.path[index] - if not isinstance(tag, type("")): - tag = None - else: - index = index + 1 - except IndexError: - tag = None # invalid path - for node in nodeset: - new = list(node.getiterator(tag)) - if new and new[0] is node: - set.extend(new[1:]) - else: - set.extend(new) + index = int(predicate[2]) - 1 + except ValueError: + raise SyntaxError("unsupported expression") else: - for node in nodeset: - for node in node: - if path == "*" or node.tag == path: - set.append(node) - if not set: - return [] - nodeset = set + index = -1 + def select(context, result): + parent_map = get_parent_map(context) + for elem in result: + try: + parent = parent_map[elem] + # FIXME: what if the selector is "*" ? + elems = list(parent.findall(elem.tag)) + if elems[index] is elem: + yield elem + except (IndexError, KeyError): + pass + return select + raise SyntaxError("invalid predicate") + +ops = { + "": prepare_child, + "*": prepare_star, + ".": prepare_self, + "..": prepare_parent, + "//": prepare_descendant, + "[": prepare_predicate, + } _cache = {} -## -# (Internal) Compile path. +class _SelectorContext: + parent_map = None + def __init__(self, root): + self.root = root -def _compile(path): - p = _cache.get(path) - if p is not None: - return p - p = Path(path) - if len(_cache) >= 100: - _cache.clear() - _cache[path] = p - return p +# -------------------------------------------------------------------- + +## +# Generate all matching objects. + +def iterfind(elem, path, namespaces=None): + # compile selector pattern + if path[-1:] == "/": + path = path + "*" # implicit all (FIXME: keep this?) + try: + selector = _cache[path] + except KeyError: + if len(_cache) > 100: + _cache.clear() + if path[:1] == "/": + raise SyntaxError("cannot use absolute path on element") + next = iter(xpath_tokenizer(path, namespaces)).__next__ + token = next() + selector = [] + while 1: + try: + selector.append(ops[token[0]](next, token)) + except StopIteration: + raise SyntaxError("invalid path") + try: + token = next() + if token[0] == "/": + token = next() + except StopIteration: + break + _cache[path] = selector + # execute selector pattern + result = [elem] + context = _SelectorContext(elem) + for select in selector: + result = select(context, result) + return result ## # Find first matching object. -def find(element, path): - return _compile(path).find(element) - -## -# Find text for first matching object. - -def findtext(element, path, default=None): - return _compile(path).findtext(element, default) +def find(elem, path, namespaces=None): + try: + return next(iterfind(elem, path, namespaces)) + except StopIteration: + return None ## # Find all matching objects. -def findall(element, path): - return _compile(path).findall(element) +def findall(elem, path, namespaces=None): + return list(iterfind(elem, path, namespaces)) + +## +# Find text for first matching object. + +def findtext(elem, path, default=None, namespaces=None): + try: + elem = next(iterfind(elem, path, namespaces)) + return elem.text or "" + except StopIteration: + return default diff --git a/Lib/xml/etree/ElementTree.py b/Lib/xml/etree/ElementTree.py index 2663b336e73..c26a7645606 100644 --- a/Lib/xml/etree/ElementTree.py +++ b/Lib/xml/etree/ElementTree.py @@ -1,40 +1,24 @@ # # ElementTree -# $Id: ElementTree.py 2326 2005-03-17 07:45:21Z fredrik $ +# $Id: ElementTree.py 3440 2008-07-18 14:45:01Z fredrik $ # -# light-weight XML support for Python 1.5.2 and later. +# light-weight XML support for Python 2.3 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 +# history (since 1.2.6): +# 2005-11-12 fl added tostringlist/fromstringlist helpers +# 2006-07-05 fl merged in selected changes from the 1.3 sandbox +# 2006-07-05 fl removed support for 2.1 and earlier +# 2007-06-21 fl added deprecation/future warnings +# 2007-08-25 fl added doctype hook, added parser version attribute etc +# 2007-08-26 fl added new serializer code (better namespace handling, etc) +# 2007-08-27 fl warn for broken /tag searches on tree level +# 2007-09-02 fl added html/text methods to serializer (experimental) +# 2007-09-05 fl added method argument to tostring/tostringlist +# 2007-09-06 fl improved error handling +# 2007-09-13 fl added itertext, iterfind; assorted cleanups +# 2007-12-15 fl added C14N hooks, copy method (experimental) # -# Copyright (c) 1999-2005 by Fredrik Lundh. All rights reserved. +# Copyright (c) 1999-2008 by Fredrik Lundh. All rights reserved. # # fredrik@pythonware.com # http://www.pythonware.com @@ -42,7 +26,7 @@ # -------------------------------------------------------------------- # The ElementTree toolkit is # -# Copyright (c) 1999-2005 by Fredrik Lundh +# Copyright (c) 1999-2008 by Fredrik Lundh # # By obtaining, using, and/or copying this software and/or its # associated documentation, you agree that you have read, understood, @@ -68,25 +52,28 @@ # -------------------------------------------------------------------- # Licensed to PSF under a Contributor Agreement. -# See http://www.python.org/2.4/license for licensing details. +# See http://www.python.org/psf/license for licensing details. __all__ = [ # public symbols "Comment", "dump", "Element", "ElementTree", - "fromstring", + "fromstring", "fromstringlist", "iselement", "iterparse", - "parse", + "parse", "ParseError", "PI", "ProcessingInstruction", "QName", "SubElement", - "tostring", + "tostring", "tostringlist", "TreeBuilder", - "VERSION", "XML", + "VERSION", + "XML", "XMLParser", "XMLTreeBuilder", ] +VERSION = "1.3.0" + ## # The Element type is a flexible container object, designed to # store hierarchical data structures in memory. The type can be @@ -102,36 +89,86 @@ __all__ = [ #
  • a number of child elements, stored in a Python sequence
    • # # -# To create an element instance, use the {@link #Element} or {@link -# #SubElement} factory functions. +# To create an element instance, use the {@link #Element} constructor +# or the {@link #SubElement} factory function. #

    # The {@link #ElementTree} class can be used to wrap an element # structure, and convert it from and to XML. ## -import sys, re +import sys +import re +import warnings -from . import ElementPath -# TODO: add support for custom namespace resolvers/default namespaces -# TODO: add improved support for incremental parsing +class _SimpleElementPath: + # emulate pre-1.2 find/findtext/findall behaviour + def find(self, element, tag, namespaces=None): + for elem in element: + if elem.tag == tag: + return elem + return None + def findtext(self, element, tag, default=None, namespaces=None): + elem = self.find(element, tag) + if elem is None: + return default + return elem.text or "" + def iterfind(self, element, tag, namespaces=None): + if tag[:3] == ".//": + for elem in element.iter(tag[3:]): + yield elem + for elem in element: + if elem.tag == tag: + yield elem + def findall(self, element, tag, namespaces=None): + return list(self.iterfind(element, tag, namespaces)) -VERSION = "1.2.6" +try: + from . import ElementPath +except ImportError: + ElementPath = _SimpleElementPath() ## -# Internal element class. This class defines the Element interface, -# and provides a reference implementation of this interface. +# Parser error. This is a subclass of SyntaxError. #

    -# You should not create instances of this class directly. Use the -# appropriate factory functions instead, such as {@link #Element} -# and {@link #SubElement}. +# In addition to the exception value, an exception instance contains a +# specific exception code in the code attribute, and the line and +# column of the error in the position attribute. + +class ParseError(SyntaxError): + pass + +# -------------------------------------------------------------------- + +## +# 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, Element) or hasattr(element, "tag") + +## +# Element class. This class defines the Element interface, and +# provides a reference implementation of this interface. +#

    +# The element name, attribute names, and attribute values can be +# either ASCII strings (ordinary Python strings containing only 7-bit +# ASCII characters) or Unicode strings. +# +# @param tag The element name. +# @param attrib An optional dictionary, containing element attributes. +# @param **extra Additional attributes, given as keyword arguments. # @see Element # @see SubElement # @see Comment # @see ProcessingInstruction -class _ElementInterface: +class Element: # text...tail ## @@ -141,34 +178,41 @@ class _ElementInterface: ## # (Attribute) Element attribute dictionary. Where possible, use - # {@link #_ElementInterface.get}, - # {@link #_ElementInterface.set}, - # {@link #_ElementInterface.keys}, and - # {@link #_ElementInterface.items} to access + # {@link #Element.get}, + # {@link #Element.set}, + # {@link #Element.keys}, and + # {@link #Element.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. + # string or the value None. Note that if there was no text, this + # attribute may be either None or an empty string, depending on + # the parser. 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. + # the value None. Note that if there was no text, this attribute + # may be either None or an empty string, depending on the parser. tail = None # text after end tag, if any - def __init__(self, tag, attrib): + # constructor + + def __init__(self, tag, attrib={}, **extra): + attrib = attrib.copy() + attrib.update(extra) self.tag = tag self.attrib = attrib self._children = [] def __repr__(self): - return "" % (self.tag, id(self)) + return "" % (repr(self.tag), id(self)) ## # Creates a new element object of the same type as this element. @@ -178,18 +222,41 @@ class _ElementInterface: # @return A new element instance. def makeelement(self, tag, attrib): - return Element(tag, attrib) + return self.__class__(tag, attrib) ## - # Returns the number of subelements. + # (Experimental) Copies the current element. This creates a + # shallow copy; subelements will be shared with the original tree. + # + # @return A new element instance. + + def copy(self): + elem = self.makeelement(self.tag, self.attrib) + elem.text = self.text + elem.tail = self.tail + elem[:] = self + return elem + + ## + # Returns the number of subelements. Note that this only counts + # full elements; to check if there's any content in an element, you + # have to check both the length and the text attribute. # # @return The number of subelements. def __len__(self): return len(self._children) + def __bool__(self): + warnings.warn( + "The behavior of this method will change in future versions. " + "Use specific 'len(elem)' or 'elem is not None' test instead.", + FutureWarning, stacklevel=2 + ) + return len(self._children) != 0 # emulate old behaviour, for now + ## - # Returns the given subelement. + # Returns the given subelement, by index. # # @param index What subelement to return. # @return The given subelement. @@ -199,19 +266,22 @@ class _ElementInterface: return self._children[index] ## - # Replaces the given subelement. + # Replaces the given subelement, by index. # # @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) + # if isinstance(index, slice): + # for elt in element: + # assert iselement(elt) + # else: + # assert iselement(element) self._children[index] = element ## - # Deletes the given subelement. + # Deletes the given subelement, by index. # # @param index What subelement to delete. # @exception IndexError If the given element does not exist. @@ -220,118 +290,121 @@ class _ElementInterface: 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. + # Adds a subelement to the end of this element. In document order, + # the new element will appear after the last existing subelement (or + # directly after the text, if it's the first subelement), but before + # the end tag for 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) + # assert iselement(element) self._children.append(element) + ## + # Appends subelements from a sequence. + # + # @param elements A sequence object with zero or more elements. + # @since 1.3 + + def extend(self, elements): + # for element in elements: + # assert iselement(element) + self._children.extend(elements) + ## # 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) + # assert iselement(element) self._children.insert(index, element) ## # Removes a matching subelement. Unlike the find methods, # this method compares elements based on identity, not on tag - # value or contents. + # value or contents. To remove subelements by other means, the + # easiest way is often to use a list comprehension to select what + # elements to keep, and use slice assignment to update the parent + # element. # # @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) + # assert iselement(element) self._children.remove(element) ## - # Returns all subelements. The elements are returned in document - # order. + # (Deprecated) Returns all subelements. The elements are returned + # in document order. # # @return A list of subelements. # @defreturn list of Element instances def getchildren(self): + warnings.warn( + "This method will be removed in future versions. " + "Use 'list(elem)' or iteration over elem instead.", + DeprecationWarning, stacklevel=2 + ) return self._children ## # Finds the first matching subelement, by tag name or path. # # @param path What element to look for. + # @keyparam namespaces Optional namespace prefix map. # @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) + def find(self, path, namespaces=None): + return ElementPath.find(self, path, namespaces) ## # 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. + # @keyparam namespaces Optional namespace prefix map. # @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 + # 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) + def findtext(self, path, default=None, namespaces=None): + return ElementPath.findtext(self, path, default, namespaces) ## # 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, + # @keyparam namespaces Optional namespace prefix map. + # @return A list or other sequence containing all matching elements, # in document order. # @defreturn list of Element instances - def findall(self, path): - return ElementPath.findall(self, path) + def findall(self, path, namespaces=None): + return ElementPath.findall(self, path, namespaces) + + ## + # Finds all matching subelements, by tag name or path. + # + # @param path What element to look for. + # @keyparam namespaces Optional namespace prefix map. + # @return An iterator or sequence containing all matching elements, + # in document order. + # @defreturn a generated sequence of Element instances + + def iterfind(self, path, namespaces=None): + return ElementPath.iterfind(self, path, namespaces) ## # Resets an element. This function removes all subelements, clears - # all attributes, and sets the text and tail attributes to None. + # all attributes, and sets the text and tail attributes + # to None. def clear(self): self.attrib.clear() @@ -339,7 +412,8 @@ class _ElementInterface: self.text = self.tail = None ## - # Gets an element attribute. + # Gets an element attribute. Equivalent to attrib.get, but + # some implementations may handle this a bit more efficiently. # # @param key What attribute to look for. # @param default What to return if the attribute was not found. @@ -351,7 +425,8 @@ class _ElementInterface: return self.attrib.get(key, default) ## - # Sets an element attribute. + # Sets an element attribute. Equivalent to attrib[key] = value, + # but some implementations may handle this a bit more efficiently. # # @param key What attribute to set. # @param value The attribute value. @@ -362,6 +437,7 @@ class _ElementInterface: ## # Gets a list of attribute names. The names are returned in an # arbitrary order (just like for an ordinary Python dictionary). + # Equivalent to attrib.keys(). # # @return A list of element attribute names. # @defreturn list of strings @@ -371,7 +447,7 @@ class _ElementInterface: ## # Gets element attributes, as a sequence. The attributes are - # returned in an arbitrary order. + # returned in an arbitrary order. Equivalent to attrib.items(). # # @return A list of (name, value) tuples for all attributes. # @defreturn list of (string, string) tuples @@ -384,45 +460,55 @@ class _ElementInterface: # and all subelements, in document order, and returns all elements # with a matching tag. #

    - # If the tree structure is modified during iteration, the result - # is undefined. + # If the tree structure is modified during iteration, new or removed + # elements may or may not be included. To get a stable set, use the + # list() function on the iterator, and loop over the resulting list. # # @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 + # @return An iterator containing all the matching elements. + # @defreturn iterator - def getiterator(self, tag=None): - nodes = [] + def iter(self, tag=None): 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 + yield self + for e in self._children: + for e in e.iter(tag): + yield e + + # compatibility + def getiterator(self, tag=None): + # Change for a DeprecationWarning in 1.4 + warnings.warn( + "This method will be removed in future versions. " + "Use 'elem.iter()' or 'list(elem.iter())' instead.", + PendingDeprecationWarning, stacklevel=2 + ) + return list(self.iter(tag)) + + ## + # Creates a text iterator. The iterator loops over this element + # and all subelements, in document order, and returns all inner + # text. + # + # @return An iterator containing all inner text. + # @defreturn iterator + + def itertext(self): + tag = self.tag + if not isinstance(tag, str) and tag is not None: + return + if self.text: + yield self.text + for e in self: + for s in e.itertext(): + yield s + if e.tail: + yield e.tail # 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. -#

    -# 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) +_Element = _ElementInterface = Element ## # Subelement factory. This function creates an element instance, and @@ -447,7 +533,8 @@ def SubElement(parent, tag, attrib={}, **extra): ## # Comment element factory. This factory function creates a special -# element that will be serialized as an XML comment. +# element that will be serialized as an XML comment by the standard +# serializer. #

    # The comment string can be either an 8-bit ASCII string or a Unicode # string. @@ -463,7 +550,8 @@ def Comment(text=None): ## # PI element factory. This factory function creates a special element -# that will be serialized as an XML processing instruction. +# that will be serialized as an XML processing instruction by the standard +# serializer. # # @param target A string containing the PI target. # @param text A string containing the PI contents, if any. @@ -523,19 +611,21 @@ class QName: return self.text != other.text return 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 +# @keyparam file Optional file handle or file 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) + # assert element is None or iselement(element) self._root = element # first node if file: self.parse(file) @@ -557,25 +647,27 @@ class ElementTree: # @param element An element instance. def _setroot(self, element): - assert iselement(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. + # @param source A file name or file object. If a file object is + # given, it only has to implement a read(n) method. + # @keyparam parser An optional parser instance. If not given, the + # standard {@link XMLParser} parser is used. # @return The document root element. # @defreturn Element + # @exception ParseError If the parser fails to parse the document. def parse(self, source, parser=None): if not hasattr(source, "read"): source = open(source, "rb") if not parser: - parser = XMLTreeBuilder() + parser = XMLParser(target=TreeBuilder()) while 1: - data = source.read(32768) + data = source.read(65536) if not data: break parser.feed(data) @@ -590,23 +682,40 @@ class ElementTree: # @return An iterator. # @defreturn iterator + def iter(self, tag=None): + # assert self._root is not None + return self._root.iter(tag) + + # compatibility def getiterator(self, tag=None): - assert self._root is not None - return self._root.getiterator(tag) + # Change for a DeprecationWarning in 1.4 + warnings.warn( + "This method will be removed in future versions. " + "Use 'tree.iter()' or 'list(tree.iter())' instead.", + PendingDeprecationWarning, stacklevel=2 + ) + return list(self.iter(tag)) ## # Finds the first toplevel element with given tag. # Same as getroot().find(path). # # @param path What element to look for. + # @keyparam namespaces Optional namespace prefix map. # @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 + def find(self, path, namespaces=None): + # assert self._root is not None if path[:1] == "/": path = "." + path - return self._root.find(path) + warnings.warn( + "This search is broken in 1.3 and earlier, and will be " + "fixed in a future version. If you rely on the current " + "behaviour, change it to %r" % path, + FutureWarning, stacklevel=2 + ) + return self._root.find(path, namespaces) ## # Finds the element text for the first toplevel element with given @@ -614,113 +723,453 @@ class ElementTree: # # @param path What toplevel element to look for. # @param default What to return if the element was not found. + # @keyparam namespaces Optional namespace prefix map. # @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 + # 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 + def findtext(self, path, default=None, namespaces=None): + # assert self._root is not None if path[:1] == "/": path = "." + path - return self._root.findtext(path, default) + warnings.warn( + "This search is broken in 1.3 and earlier, and will be " + "fixed in a future version. If you rely on the current " + "behaviour, change it to %r" % path, + FutureWarning, stacklevel=2 + ) + return self._root.findtext(path, default, namespaces) ## # Finds all toplevel elements with the given tag. # Same as getroot().findall(path). # # @param path What element to look for. + # @keyparam namespaces Optional namespace prefix map. # @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 + def findall(self, path, namespaces=None): + # assert self._root is not None if path[:1] == "/": path = "." + path - return self._root.findall(path) + warnings.warn( + "This search is broken in 1.3 and earlier, and will be " + "fixed in a future version. If you rely on the current " + "behaviour, change it to %r" % path, + FutureWarning, stacklevel=2 + ) + return self._root.findall(path, namespaces) + + ## + # Finds all matching subelements, by tag name or path. + # Same as getroot().iterfind(path). + # + # @param path What element to look for. + # @keyparam namespaces Optional namespace prefix map. + # @return An iterator or sequence containing all matching elements, + # in document order. + # @defreturn a generated sequence of Element instances + + def iterfind(self, path, namespaces=None): + # assert self._root is not None + if path[:1] == "/": + path = "." + path + warnings.warn( + "This search is broken in 1.3 and earlier, and will be " + "fixed in a future version. If you rely on the current " + "behaviour, change it to %r" % path, + FutureWarning, stacklevel=2 + ) + return self._root.iterfind(path, namespaces) ## # Writes the element tree to a file, as XML. # + # @def write(file, **options) # @param file A file name, or a file object opened for writing. - # @param encoding Optional output encoding (default is None) + # @param **options Options, given as keyword arguments. + # @keyparam encoding Optional output encoding (default is None). + # @keyparam method Optional output method ("xml", "html", "text" or + # "c14n"; default is "xml"). + # @keyparam xml_declaration Controls if an XML declaration should + # be added to the file. Use False for never, True for always, + # None for only if not US-ASCII or UTF-8. None is default. - def write(self, file, encoding=None): - assert self._root is not None - if not hasattr(file, "write"): - if encoding: - file = open(file, "wb") - else: - file = open(file, "w") - if encoding and encoding != "utf-8": - file.write(_encode("\n" % encoding, 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(_encode("" % node.text, encoding)) - elif tag is ProcessingInstruction: - file.write(_encode("" % node.text, encoding)) + def write(self, file_or_filename, + # keyword arguments + encoding=None, + xml_declaration=None, + default_namespace=None, + method=None): + # assert self._root is not None + if not method: + method = "xml" + elif method not in _serialize: + # FIXME: raise an ImportError for c14n if ElementC14N is missing? + raise ValueError("unknown method %r" % method) + if hasattr(file_or_filename, "write"): + file = file_or_filename else: - items = list(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(_encode(" %s=\"%s\"" % (k, _escape_attrib(v)), encoding)) - for k, v in xmlns_items: - file.write(_encode(" %s=\"%s\"" % (k, _escape_attrib(v)), encoding)) - if node.text or len(node): - file.write(_encode(">", encoding)) - if node.text: - file.write(_encode_cdata(node.text, encoding)) - for n in node: - self._write(file, n, encoding, namespaces) - file.write(_encode("", encoding)) + if encoding: + file = open(file_or_filename, "wb") else: - file.write(_encode(" />", encoding)) - for k, v in xmlns_items: - del namespaces[v] - if node.tail: - file.write(_encode_cdata(node.tail, encoding)) + file = open(file_or_filename, "w") + if encoding: + def write(text): + try: + return file.write(text.encode(encoding, + "xmlcharrefreplace")) + except (TypeError, AttributeError): + _raise_serialization_error(text) + else: + write = file.write + if not encoding: + if method == "c14n": + encoding = "utf-8" + else: + encoding = None + elif xml_declaration or (xml_declaration is None and + encoding not in ("utf-8", "us-ascii")): + if method == "xml": + encoding_ = encoding + if not encoding: + # Retrieve the default encoding for the xml declaration + import locale + encoding_ = locale.getpreferredencoding() + write("\n" % encoding_) + if method == "text": + _serialize_text(write, self._root) + else: + qnames, namespaces = _namespaces(self._root, default_namespace) + serialize = _serialize[method] + serialize(write, self._root, qnames, namespaces) + if file_or_filename is not file: + file.close() + + def write_c14n(self, file): + # lxml.etree compatibility. use output method instead + return self.write(file, method="c14n") # -------------------------------------------------------------------- -# helpers +# serialization support + +def _namespaces(elem, default_namespace=None): + # identify namespaces used in this tree + + # maps qnames to *encoded* prefix:local names + qnames = {None: None} + + # maps uri:s to prefixes + namespaces = {} + if default_namespace: + namespaces[default_namespace] = "" + + def add_qname(qname): + # calculate serialized qname representation + try: + if qname[:1] == "{": + uri, tag = qname[1:].rsplit("}", 1) + prefix = namespaces.get(uri) + if prefix is None: + prefix = _namespace_map.get(uri) + if prefix is None: + prefix = "ns%d" % len(namespaces) + if prefix != "xml": + namespaces[uri] = prefix + if prefix: + qnames[qname] = "%s:%s" % (prefix, tag) + else: + qnames[qname] = tag # default element + else: + if default_namespace: + # FIXME: can this be handled in XML 1.0? + raise ValueError( + "cannot use non-qualified names with " + "default_namespace option" + ) + qnames[qname] = qname + except TypeError: + _raise_serialization_error(qname) + + # populate qname and namespaces table + try: + iterate = elem.iter + except AttributeError: + iterate = elem.getiterator # cET compatibility + for elem in iterate(): + tag = elem.tag + if isinstance(tag, QName) and tag.text not in qnames: + add_qname(tag.text) + elif isinstance(tag, str): + if tag not in qnames: + add_qname(tag) + elif tag is not None and tag is not Comment and tag is not PI: + _raise_serialization_error(tag) + for key, value in elem.items(): + if isinstance(key, QName): + key = key.text + if key not in qnames: + add_qname(key) + if isinstance(value, QName) and value.text not in qnames: + add_qname(value.text) + text = elem.text + if isinstance(text, QName) and text.text not in qnames: + add_qname(text.text) + return qnames, namespaces + +def _serialize_xml(write, elem, qnames, namespaces): + tag = elem.tag + text = elem.text + if tag is Comment: + write("" % text) + elif tag is ProcessingInstruction: + write("" % text) + else: + tag = qnames[tag] + if tag is None: + if text: + write(_escape_cdata(text)) + for e in elem: + _serialize_xml(write, e, qnames, None) + else: + write("<" + tag) + items = list(elem.items()) + if items or namespaces: + if namespaces: + for v, k in sorted(namespaces.items(), + key=lambda x: x[1]): # sort on prefix + if k: + k = ":" + k + write(" xmlns%s=\"%s\"" % ( + k, + _escape_attrib(v) + )) + for k, v in sorted(items): # lexical order + if isinstance(k, QName): + k = k.text + if isinstance(v, QName): + v = qnames[v.text] + else: + v = _escape_attrib(v) + write(" %s=\"%s\"" % (qnames[k], v)) + if text or len(elem): + write(">") + if text: + write(_escape_cdata(text)) + for e in elem: + _serialize_xml(write, e, qnames, None) + write("") + else: + write(" />") + if elem.tail: + write(_escape_cdata(elem.tail)) + +HTML_EMPTY = ("area", "base", "basefont", "br", "col", "frame", "hr", + "img", "input", "isindex", "link", "meta" "param") + +try: + HTML_EMPTY = set(HTML_EMPTY) +except NameError: + pass + +def _serialize_html(write, elem, qnames, namespaces): + tag = elem.tag + text = elem.text + if tag is Comment: + write("" % _escape_cdata(text)) + elif tag is ProcessingInstruction: + write("" % _escape_cdata(text)) + else: + tag = qnames[tag] + if tag is None: + if text: + write(_escape_cdata(text)) + for e in elem: + _serialize_html(write, e, qnames, None) + else: + write("<" + tag) + items = list(elem.items()) + if items or namespaces: + if namespaces: + for v, k in sorted(namespaces.items(), + key=lambda x: x[1]): # sort on prefix + if k: + k = ":" + k + write(" xmlns%s=\"%s\"" % ( + k, + _escape_attrib(v) + )) + for k, v in sorted(items): # lexical order + if isinstance(k, QName): + k = k.text + if isinstance(v, QName): + v = qnames[v.text] + else: + v = _escape_attrib_html(v) + # FIXME: handle boolean attributes + write(" %s=\"%s\"" % (qnames[k], v)) + write(">") + tag = tag.lower() + if text: + if tag == "script" or tag == "style": + write(text) + else: + write(_escape_cdata(text)) + for e in elem: + _serialize_html(write, e, qnames, None) + if tag not in HTML_EMPTY: + write("") + if elem.tail: + write(_escape_cdata(elem.tail)) + +def _serialize_text(write, elem): + for part in elem.itertext(): + write(part) + if elem.tail: + write(elem.tail) + +_serialize = { + "xml": _serialize_xml, + "html": _serialize_html, + "text": _serialize_text, +# this optional method is imported at the end of the module +# "c14n": _serialize_c14n, +} ## -# Checks if an object appears to be a valid element object. +# Registers a namespace prefix. The registry is global, and any +# existing mapping for either the given prefix or the namespace URI +# will be removed. # -# @param An element instance. -# @return A true value if this is an element object. -# @defreturn flag +# @param prefix Namespace prefix. +# @param uri Namespace uri. Tags and attributes in this namespace +# will be serialized with the given prefix, if at all possible. +# @exception ValueError If the prefix is reserved, or is otherwise +# invalid. -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") +def register_namespace(prefix, uri): + if re.match("ns\d+$", prefix): + raise ValueError("Prefix format reserved for internal use") + for k, v in _namespace_map.items(): + if k == uri or v == prefix: + del _namespace_map[k] + _namespace_map[uri] = prefix + +_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", + # xml schema + "http://www.w3.org/2001/XMLSchema": "xs", + "http://www.w3.org/2001/XMLSchema-instance": "xsi", + # dublin core + "http://purl.org/dc/elements/1.1/": "dc", +} + +def _raise_serialization_error(text): + raise TypeError( + "cannot serialize %r (type %s)" % (text, type(text).__name__) + ) + +def _escape_cdata(text): + # escape character data + try: + # it's worth avoiding do-nothing calls for strings that are + # shorter than 500 character, or so. assume that's, by far, + # the most common case in most applications. + if "&" in text: + text = text.replace("&", "&") + if "<" in text: + text = text.replace("<", "<") + if ">" in text: + text = text.replace(">", ">") + return text + except (TypeError, AttributeError): + _raise_serialization_error(text) + +def _escape_attrib(text): + # escape attribute value + try: + if "&" in text: + text = text.replace("&", "&") + if "<" in text: + text = text.replace("<", "<") + if ">" in text: + text = text.replace(">", ">") + if "\"" in text: + text = text.replace("\"", """) + if "\n" in text: + text = text.replace("\n", " ") + return text + except (TypeError, AttributeError): + _raise_serialization_error(text) + +def _escape_attrib_html(text): + # escape attribute value + try: + if "&" in text: + text = text.replace("&", "&") + if ">" in text: + text = text.replace(">", ">") + if "\"" in text: + text = text.replace("\"", """) + return text + except (TypeError, AttributeError): + _raise_serialization_error(text) + +# -------------------------------------------------------------------- + +## +# Generates a string representation of an XML element, including all +# subelements. If encoding is None, the return type is a string; +# otherwise it is a bytes array. +# +# @param element An Element instance. +# @keyparam encoding Optional output encoding (default is None). +# @keyparam method Optional output method ("xml", "html", "text" or +# "c14n"; default is "xml"). +# @return An (optionally) encoded string containing the XML data. +# @defreturn string + +def tostring(element, encoding=None, method=None): + class dummy: + pass + data = [] + file = dummy() + file.write = data.append + ElementTree(element).write(file, encoding, method=method) + if encoding: + return b"".join(data) + else: + return "".join(data) + +## +# Generates a string representation of an XML element, including all +# subelements. The string is returned as a sequence of string fragments. +# +# @param element An Element instance. +# @keyparam encoding Optional output encoding (default is US-ASCII). +# @keyparam method Optional output method ("xml", "html", "text" or +# "c14n"; default is "xml"). +# @return A sequence object containing the XML data. +# @defreturn sequence +# @since 1.3 + +def tostringlist(element, encoding=None, method=None): + class dummy: + pass + data = [] + file = dummy() + file.write = data.append + ElementTree(element).write(file, encoding, method=method) + # FIXME: merge small fragments into larger parts + return data ## # Writes an element tree or element structure to sys.stdout. This @@ -740,105 +1189,15 @@ def dump(elem): if not tail or tail[-1] != "\n": sys.stdout.write("\n") -def _encode(s, encoding): - if encoding: - return s.encode(encoding) - else: - return s - -_escape = re.compile(r"[&<>\"\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 "".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 _encode_cdata(text, encoding): - # escape character data - try: - text = text.replace("&", "&") - text = text.replace("<", "<") - text = text.replace(">", ">") - if encoding: - return text.encode(encoding, "xmlcharrefreplace") - else: - return text - except (TypeError, AttributeError): - _raise_serialization_error(text) - -def _escape_attrib(text): - # escape attribute value - try: - text = text.replace("&", "&") - text = text.replace("'", "'") # FIXME: overkill - text = text.replace("\"", """) - text = text.replace("<", "<") - text = text.replace(">", ">") - 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 = tag[1:].split("}", 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 +# -------------------------------------------------------------------- +# parsing ## # 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. +# standard {@link XMLParser} parser is used. # @return An ElementTree instance def parse(source, parser=None): @@ -853,18 +1212,25 @@ def parse(source, parser=None): # @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. +# @param parser An optional parser instance. If not given, the +# standard {@link XMLParser} parser is used. # @return A (event, elem) iterator. -class iterparse: +def iterparse(source, events=None, parser=None): + if not hasattr(source, "read"): + source = open(source, "rb") + if not parser: + parser = XMLParser(target=TreeBuilder()) + return _IterParseIterator(source, events, parser) - def __init__(self, source, events=None): - if not hasattr(source, "read"): - source = open(source, "rb") +class _IterParseIterator: + + def __init__(self, source, events, parser): self._file = source self._events = [] self._index = 0 self.root = self._root = None - self._parser = XMLTreeBuilder() + self._parser = parser # wire up the parser for event reporting parser = self._parser._parser append = self._events.append @@ -891,16 +1257,14 @@ class iterparse: 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))) + append((event, (prefix or "", uri or ""))) parser.StartNamespaceDeclHandler = handler elif event == "end-ns": def handler(prefix, event=event, append=append): append((event, None)) parser.EndNamespaceDeclHandler = handler + else: + raise ValueError("unknown event %r" % event) def __next__(self): while 1: @@ -909,10 +1273,7 @@ class iterparse: except IndexError: if self._parser is None: self.root = self._root - try: - raise StopIteration - except NameError: - raise IndexError + raise StopIteration # load event buffer del self._events[:] self._index = 0 @@ -926,24 +1287,22 @@ class iterparse: self._index = self._index + 1 return item - try: - iter - def __iter__(self): - return self - except NameError: - def __getitem__(self, index): - return self.__next__() + def __iter__(self): + return self ## # 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. +# @param parser An optional parser instance. If not given, the +# standard {@link XMLParser} parser is used. # @return An Element instance. # @defreturn Element -def XML(text): - parser = XMLTreeBuilder() +def XML(text, parser=None): + if not parser: + parser = XMLParser(target=TreeBuilder()) parser.feed(text) return parser.close() @@ -952,15 +1311,18 @@ def XML(text): # a dictionary which maps from element id:s to elements. # # @param source A string containing XML data. +# @param parser An optional parser instance. If not given, the +# standard {@link XMLParser} parser is used. # @return A tuple containing an Element instance and a dictionary. # @defreturn (Element, dictionary) -def XMLID(text): - parser = XMLTreeBuilder() +def XMLID(text, parser=None): + if not parser: + parser = XMLParser(target=TreeBuilder()) parser.feed(text) tree = parser.close() ids = {} - for elem in tree.getiterator(): + for elem in tree.iter(): id = elem.get("id") if id: ids[id] = elem @@ -977,25 +1339,23 @@ def XMLID(text): fromstring = XML ## -# Generates a string representation of an XML element, including all -# subelements. If encoding is None, the return type is a string; -# otherwise it is a bytes array. +# Parses an XML document from a sequence of string fragments. # -# @param element An Element instance. -# @return An (optionally) encoded string containing the XML data. -# @defreturn string +# @param sequence A list or other sequence containing XML data fragments. +# @param parser An optional parser instance. If not given, the +# standard {@link XMLParser} parser is used. +# @return An Element instance. +# @defreturn Element +# @since 1.3 -def tostring(element, encoding=None): - class dummy: - pass - data = [] - file = dummy() - file.write = data.append - ElementTree(element).write(file, encoding) - if encoding: - return b"".join(data) - else: - return "".join(data) +def fromstringlist(sequence, parser=None): + if not parser: + parser = XMLParser(target=TreeBuilder()) + for text in sequence: + parser.feed(text) + return parser.close() + +# -------------------------------------------------------------------- ## # Generic element structure builder. This builder converts a sequence @@ -1016,11 +1376,11 @@ class TreeBuilder: self._last = None # last element self._tail = None # true if we're after an end tag if element_factory is None: - element_factory = _ElementInterface + element_factory = Element self._factory = element_factory ## - # Flushes the parser buffers, and returns the toplevel documen + # Flushes the builder buffers, and returns the toplevel document # element. # # @return An Element instance. @@ -1028,7 +1388,7 @@ class TreeBuilder: def close(self): assert len(self._elem) == 0, "missing end tags" - assert self._last != None, "missing toplevel element" + assert self._last is not None, "missing toplevel element" return self._last def _flush(self): @@ -1093,28 +1453,39 @@ class TreeBuilder: # instance of the standard {@link #TreeBuilder} class. # @keyparam html Predefine HTML entities. This flag is not supported # by the current implementation. +# @keyparam encoding Optional encoding. If given, the value overrides +# the encoding specified in the XML file. # @see #ElementTree # @see #TreeBuilder -class XMLTreeBuilder: +class XMLParser: - def __init__(self, html=0, target=None): + def __init__(self, html=0, target=None, encoding=None): try: from xml.parsers import expat except ImportError: - raise ImportError( - "No module named expat; use SimpleXMLTreeBuilder instead" - ) - self._parser = parser = expat.ParserCreate(None, "}") + try: + import pyexpat as expat + except ImportError: + raise ImportError( + "No module named expat; use SimpleXMLTreeBuilder instead" + ) + parser = expat.ParserCreate(encoding, "}") if target is None: target = TreeBuilder() - self._target = target + # underscored names are provided for compatibility only + self.parser = self._parser = parser + self.target = self._target = target + self._error = expat.error self._names = {} # name memo cache # callbacks parser.DefaultHandlerExpand = self._default parser.StartElementHandler = self._start parser.EndElementHandler = self._end parser.CharacterDataHandler = self._data + # optional callbacks + parser.CommentHandler = self._comment + parser.ProcessingInstructionHandler = self._pi # let expat do the buffering, if supported try: self._parser.buffer_text = 1 @@ -1127,10 +1498,18 @@ class XMLTreeBuilder: parser.StartElementHandler = self._start_list except AttributeError: pass - encoding = "utf-8" - # target.xml(encoding, None) self._doctype = None self.entity = {} + try: + self.version = "Expat %d.%d.%d" % expat.version_info + except AttributeError: + pass # unknown + + def _raiseerror(self, value): + err = ParseError(value) + err.code = value.code + err.position = value.lineno, value.offset + raise err def _fixname(self, key): # expand qname, and convert name string to ascii, if possible @@ -1149,7 +1528,7 @@ class XMLTreeBuilder: attrib = {} for key, value in attrib_in.items(): attrib[fixname(key)] = value - return self._target.start(tag, attrib) + return self.target.start(tag, attrib) def _start_list(self, tag, attrib_in): fixname = self._fixname @@ -1158,27 +1537,47 @@ class XMLTreeBuilder: if attrib_in: for i in range(0, len(attrib_in), 2): attrib[fixname(attrib_in[i])] = attrib_in[i+1] - return self._target.start(tag, attrib) + return self.target.start(tag, attrib) def _data(self, text): - return self._target.data(text) + return self.target.data(text) def _end(self, tag): - return self._target.end(self._fixname(tag)) + return self.target.end(self._fixname(tag)) + + def _comment(self, data): + try: + comment = self.target.comment + except AttributeError: + pass + else: + return comment(data) + + def _pi(self, target, data): + try: + pi = self.target.pi + except AttributeError: + pass + else: + return pi(target, data) def _default(self, text): prefix = text[:1] if prefix == "&": # deal with undefined entities try: - self._target.data(self.entity[text[1:-1]]) + self.target.data(self.entity[text[1:-1]]) except KeyError: from xml.parsers import expat - raise expat.error( + err = expat.error( "undefined entity %s: line %d, column %d" % (text, self._parser.ErrorLineNumber, self._parser.ErrorColumnNumber) ) + err.code = 11 # XML_ERROR_UNDEFINED_ENTITY + err.lineno = self._parser.ErrorLineNumber + err.offset = self._parser.ErrorColumnNumber + raise err elif prefix == "<" and text[:9] == "ob_refcnt) +#define Py_TYPE(ob) (((PyObject*)(ob))->ob_type) +#endif + +#if (PY_VERSION_HEX < 0x02050000) +typedef int Py_ssize_t; +#define lenfunc inquiry +#endif + +#if (PY_VERSION_HEX < 0x02040000) +#define PyDict_CheckExact PyDict_Check + +#if !defined(Py_RETURN_NONE) +#define Py_RETURN_NONE return Py_INCREF(Py_None), Py_None +#endif +#endif + /* macros used to store 'join' flags in string object pointers. note that all use of text and tail as object pointers must be wrapped in JOIN_OBJ. see comments in the ElementObject definition for more @@ -102,9 +122,11 @@ do { memory -= size; printf("%8d - %s\n", memory, comment); } while (0) #define JOIN_OBJ(p) ((PyObject*) ((Py_uintptr_t) (p) & ~1)) /* glue functions (see the init function for details) */ +static PyObject* elementtree_parseerror_obj; static PyObject* elementtree_copyelement_obj; static PyObject* elementtree_deepcopy_obj; -static PyObject* elementtree_getiterator_obj; +static PyObject* elementtree_iter_obj; +static PyObject* elementtree_itertext_obj; static PyObject* elementpath_obj; /* helpers */ @@ -188,23 +210,6 @@ list_join(PyObject* list) return result; } -#if (PY_VERSION_HEX < 0x02020000) -LOCAL(int) -PyDict_Update(PyObject* dict, PyObject* other) -{ - /* PyDict_Update emulation for 2.1 and earlier */ - - PyObject* res; - - res = PyObject_CallMethod(dict, "update", "O", other); - if (!res) - return -1; - - Py_DECREF(res); - return 0; -} -#endif - /* -------------------------------------------------------------------- */ /* the element type */ @@ -309,7 +314,7 @@ element_new(PyObject* tag, PyObject* attrib) if (element_new_extra(self, attrib) < 0) { PyObject_Del(self); return NULL; - } + } self->extra->length = 0; self->extra->allocated = STATIC_CHILDREN; @@ -407,6 +412,7 @@ element_get_attrib(ElementObject* self) PyObject* res = self->extra->attrib; if (res == Py_None) { + Py_DECREF(res); /* create missing dictionary */ res = PyDict_New(); if (!res) @@ -688,6 +694,8 @@ element_deepcopy(ElementObject* self, PyObject* args) /* add object to memo dictionary (so deepcopy won't visit it again) */ id = PyLong_FromLong((Py_uintptr_t) self); + if (!id) + goto error; i = PyDict_SetItem(memo, id, (PyObject*) element); @@ -711,7 +719,8 @@ checkpath(PyObject* tag) /* check if a tag contains an xpath character */ -#define PATHCHAR(ch) (ch == '/' || ch == '*' || ch == '[' || ch == '@') +#define PATHCHAR(ch) \ + (ch == '/' || ch == '*' || ch == '[' || ch == '@' || ch == '.') if (PyUnicode_Check(tag)) { Py_UNICODE *p = PyUnicode_AS_UNICODE(tag); @@ -741,18 +750,52 @@ checkpath(PyObject* tag) return 1; /* unknown type; might be path expression */ } +static PyObject* +element_extend(ElementObject* self, PyObject* args) +{ + PyObject* seq; + Py_ssize_t i, seqlen = 0; + + PyObject* seq_in; + if (!PyArg_ParseTuple(args, "O:extend", &seq_in)) + return NULL; + + seq = PySequence_Fast(seq_in, ""); + if (!seq) { + PyErr_Format( + PyExc_TypeError, + "expected sequence, not \"%.200s\"", Py_TYPE(seq_in)->tp_name + ); + return NULL; + } + + seqlen = PySequence_Size(seq); + for (i = 0; i < seqlen; i++) { + PyObject* element = PySequence_Fast_GET_ITEM(seq, i); + if (element_add_subelement(self, element) < 0) { + Py_DECREF(seq); + return NULL; + } + } + + Py_DECREF(seq); + + Py_RETURN_NONE; +} + static PyObject* element_find(ElementObject* self, PyObject* args) { int i; PyObject* tag; - if (!PyArg_ParseTuple(args, "O:find", &tag)) + PyObject* namespaces = Py_None; + if (!PyArg_ParseTuple(args, "O|O:find", &tag, &namespaces)) return NULL; - if (checkpath(tag)) + if (checkpath(tag) || namespaces != Py_None) return PyObject_CallMethod( - elementpath_obj, "find", "OO", self, tag + elementpath_obj, "find", "OOO", self, tag, namespaces ); if (!self->extra) @@ -777,12 +820,13 @@ element_findtext(ElementObject* self, PyObject* args) PyObject* tag; PyObject* default_value = Py_None; - if (!PyArg_ParseTuple(args, "O|O:findtext", &tag, &default_value)) + PyObject* namespaces = Py_None; + if (!PyArg_ParseTuple(args, "O|OO:findtext", &tag, &default_value, &namespaces)) return NULL; - if (checkpath(tag)) + if (checkpath(tag) || namespaces != Py_None) return PyObject_CallMethod( - elementpath_obj, "findtext", "OOO", self, tag, default_value + elementpath_obj, "findtext", "OOOO", self, tag, default_value, namespaces ); if (!self->extra) { @@ -813,12 +857,13 @@ element_findall(ElementObject* self, PyObject* args) PyObject* out; PyObject* tag; - if (!PyArg_ParseTuple(args, "O:findall", &tag)) + PyObject* namespaces = Py_None; + if (!PyArg_ParseTuple(args, "O|O:findall", &tag, &namespaces)) return NULL; - if (checkpath(tag)) + if (checkpath(tag) || namespaces != Py_None) return PyObject_CallMethod( - elementpath_obj, "findall", "OO", self, tag + elementpath_obj, "findall", "OOO", self, tag, namespaces ); out = PyList_New(0); @@ -842,6 +887,19 @@ element_findall(ElementObject* self, PyObject* args) return out; } +static PyObject* +element_iterfind(ElementObject* self, PyObject* args) +{ + PyObject* tag; + PyObject* namespaces = Py_None; + if (!PyArg_ParseTuple(args, "O|O:iterfind", &tag, &namespaces)) + return NULL; + + return PyObject_CallMethod( + elementpath_obj, "iterfind", "OOO", self, tag, namespaces + ); +} + static PyObject* element_get(ElementObject* self, PyObject* args) { @@ -870,6 +928,8 @@ element_getchildren(ElementObject* self, PyObject* args) int i; PyObject* list; + /* FIXME: report as deprecated? */ + if (!PyArg_ParseTuple(args, ":getchildren")) return NULL; @@ -890,18 +950,18 @@ element_getchildren(ElementObject* self, PyObject* args) } static PyObject* -element_getiterator(ElementObject* self, PyObject* args) +element_iter(ElementObject* self, PyObject* args) { PyObject* result; PyObject* tag = Py_None; - if (!PyArg_ParseTuple(args, "|O:getiterator", &tag)) + if (!PyArg_ParseTuple(args, "|O:iter", &tag)) return NULL; - if (!elementtree_getiterator_obj) { + if (!elementtree_iter_obj) { PyErr_SetString( PyExc_RuntimeError, - "getiterator helper not found" + "iter helper not found" ); return NULL; } @@ -913,7 +973,37 @@ element_getiterator(ElementObject* self, PyObject* args) Py_INCREF(self); PyTuple_SET_ITEM(args, 0, (PyObject*) self); Py_INCREF(tag); PyTuple_SET_ITEM(args, 1, (PyObject*) tag); - result = PyObject_CallObject(elementtree_getiterator_obj, args); + result = PyObject_CallObject(elementtree_iter_obj, args); + + Py_DECREF(args); + + return result; +} + + +static PyObject* +element_itertext(ElementObject* self, PyObject* args) +{ + PyObject* result; + + if (!PyArg_ParseTuple(args, ":itertext")) + return NULL; + + if (!elementtree_itertext_obj) { + PyErr_SetString( + PyExc_RuntimeError, + "itertext helper not found" + ); + return NULL; + } + + args = PyTuple_New(1); + if (!args) + return NULL; + + Py_INCREF(self); PyTuple_SET_ITEM(args, 0, (PyObject*) self); + + result = PyObject_CallObject(elementtree_itertext_obj, args); Py_DECREF(args); @@ -937,39 +1027,6 @@ element_getitem(PyObject* self_, Py_ssize_t index) return self->extra->children[index]; } -static PyObject* -element_getslice(PyObject* self_, Py_ssize_t start, Py_ssize_t end) -{ - ElementObject* self = (ElementObject*) self_; - Py_ssize_t i; - PyObject* list; - - if (!self->extra) - return PyList_New(0); - - /* standard clamping */ - if (start < 0) - start = 0; - if (end < 0) - end = 0; - if (end > self->extra->length) - end = self->extra->length; - if (start > end) - start = end; - - list = PyList_New(end - start); - if (!list) - return NULL; - - for (i = start; i < end; i++) { - PyObject* item = self->extra->children[i]; - Py_INCREF(item); - PyList_SET_ITEM(list, i - start, item); - } - - return list; -} - static PyObject* element_insert(ElementObject* self, PyObject* args) { @@ -984,8 +1041,11 @@ element_insert(ElementObject* self, PyObject* args) if (!self->extra) element_new_extra(self, NULL); - if (index < 0) - index = 0; + if (index < 0) { + index += self->extra->length; + if (index < 0) + index = 0; + } if (index > self->extra->length) index = self->extra->length; @@ -1155,77 +1215,6 @@ element_set(ElementObject* self, PyObject* args) Py_RETURN_NONE; } -static int -element_setslice(PyObject* self_, Py_ssize_t start, Py_ssize_t end, PyObject* item) -{ - ElementObject* self = (ElementObject*) self_; - Py_ssize_t i, new, old; - PyObject* recycle = NULL; - - if (!self->extra) - element_new_extra(self, NULL); - - /* standard clamping */ - if (start < 0) - start = 0; - if (end < 0) - end = 0; - if (end > self->extra->length) - end = self->extra->length; - if (start > end) - start = end; - - old = end - start; - - if (item == NULL) - new = 0; - else if (PyList_CheckExact(item)) { - new = PyList_GET_SIZE(item); - } else { - /* FIXME: support arbitrary sequences? */ - PyErr_Format( - PyExc_TypeError, - "expected list, not \"%.200s\"", Py_TYPE(item)->tp_name - ); - return -1; - } - - if (old > 0) { - /* to avoid recursive calls to this method (via decref), move - old items to the recycle bin here, and get rid of them when - we're done modifying the element */ - recycle = PyList_New(old); - for (i = 0; i < old; i++) - PyList_SET_ITEM(recycle, i, self->extra->children[i + start]); - } - - if (new < old) { - /* delete slice */ - for (i = end; i < self->extra->length; i++) - self->extra->children[i + new - old] = self->extra->children[i]; - } else if (new > old) { - /* insert slice */ - if (element_resize(self, new - old) < 0) - return -1; - for (i = self->extra->length-1; i >= end; i--) - self->extra->children[i + new - old] = self->extra->children[i]; - } - - /* replace the slice */ - for (i = 0; i < new; i++) { - PyObject* element = PyList_GET_ITEM(item, i); - Py_INCREF(element); - self->extra->children[i + start] = element; - } - - self->extra->length += new - old; - - /* discard the recycle bin, and everything in it */ - Py_XDECREF(recycle); - - return 0; -} - static int element_setitem(PyObject* self_, Py_ssize_t index, PyObject* item) { @@ -1256,6 +1245,190 @@ element_setitem(PyObject* self_, Py_ssize_t index, PyObject* item) return 0; } +static PyObject* +element_subscr(PyObject* self_, PyObject* item) +{ + ElementObject* self = (ElementObject*) self_; + +#if (PY_VERSION_HEX < 0x02050000) + if (PyInt_Check(item) || PyLong_Check(item)) { + long i = PyInt_AsLong(item); +#else + if (PyIndex_Check(item)) { + Py_ssize_t i = PyNumber_AsSsize_t(item, PyExc_IndexError); +#endif + + if (i == -1 && PyErr_Occurred()) { + return NULL; + } + if (i < 0 && self->extra) + i += self->extra->length; + return element_getitem(self_, i); + } + else if (PySlice_Check(item)) { + Py_ssize_t start, stop, step, slicelen, cur, i; + PyObject* list; + + if (!self->extra) + return PyList_New(0); + + if (PySlice_GetIndicesEx((PySliceObject *)item, + self->extra->length, + &start, &stop, &step, &slicelen) < 0) { + return NULL; + } + + if (slicelen <= 0) + return PyList_New(0); + else { + list = PyList_New(slicelen); + if (!list) + return NULL; + + for (cur = start, i = 0; i < slicelen; + cur += step, i++) { + PyObject* item = self->extra->children[cur]; + Py_INCREF(item); + PyList_SET_ITEM(list, i, item); + } + + return list; + } + } + else { + PyErr_SetString(PyExc_TypeError, + "element indices must be integers"); + return NULL; + } +} + +static int +element_ass_subscr(PyObject* self_, PyObject* item, PyObject* value) +{ + ElementObject* self = (ElementObject*) self_; + +#if (PY_VERSION_HEX < 0x02050000) + if (PyInt_Check(item) || PyLong_Check(item)) { + long i = PyInt_AsLong(item); +#else + if (PyIndex_Check(item)) { + Py_ssize_t i = PyNumber_AsSsize_t(item, PyExc_IndexError); +#endif + + if (i == -1 && PyErr_Occurred()) { + return -1; + } + if (i < 0 && self->extra) + i += self->extra->length; + return element_setitem(self_, i, value); + } + else if (PySlice_Check(item)) { + Py_ssize_t start, stop, step, slicelen, newlen, cur, i; + + PyObject* recycle = NULL; + PyObject* seq = NULL; + + if (!self->extra) + element_new_extra(self, NULL); + + if (PySlice_GetIndicesEx((PySliceObject *)item, + self->extra->length, + &start, &stop, &step, &slicelen) < 0) { + return -1; + } + + if (value == NULL) + newlen = 0; + else { + seq = PySequence_Fast(value, ""); + if (!seq) { + PyErr_Format( + PyExc_TypeError, + "expected sequence, not \"%.200s\"", Py_TYPE(value)->tp_name + ); + return -1; + } + newlen = PySequence_Size(seq); + } + + if (step != 1 && newlen != slicelen) + { + PyErr_Format(PyExc_ValueError, +#if (PY_VERSION_HEX < 0x02050000) + "attempt to assign sequence of size %d " + "to extended slice of size %d", +#else + "attempt to assign sequence of size %zd " + "to extended slice of size %zd", +#endif + newlen, slicelen + ); + return -1; + } + + + /* Resize before creating the recycle bin, to prevent refleaks. */ + if (newlen > slicelen) { + if (element_resize(self, newlen - slicelen) < 0) { + if (seq) { + Py_DECREF(seq); + } + return -1; + } + } + + if (slicelen > 0) { + /* to avoid recursive calls to this method (via decref), move + old items to the recycle bin here, and get rid of them when + we're done modifying the element */ + recycle = PyList_New(slicelen); + if (!recycle) { + if (seq) { + Py_DECREF(seq); + } + return -1; + } + for (cur = start, i = 0; i < slicelen; + cur += step, i++) + PyList_SET_ITEM(recycle, i, self->extra->children[cur]); + } + + if (newlen < slicelen) { + /* delete slice */ + for (i = stop; i < self->extra->length; i++) + self->extra->children[i + newlen - slicelen] = self->extra->children[i]; + } else if (newlen > slicelen) { + /* insert slice */ + for (i = self->extra->length-1; i >= stop; i--) + self->extra->children[i + newlen - slicelen] = self->extra->children[i]; + } + + /* replace the slice */ + for (cur = start, i = 0; i < newlen; + cur += step, i++) { + PyObject* element = PySequence_Fast_GET_ITEM(seq, i); + Py_INCREF(element); + self->extra->children[cur] = element; + } + + self->extra->length += newlen - slicelen; + + if (seq) { + Py_DECREF(seq); + } + + /* discard the recycle bin, and everything in it */ + Py_XDECREF(recycle); + + return 0; + } + else { + PyErr_SetString(PyExc_TypeError, + "element indices must be integers"); + return -1; + } +} + static PyMethodDef element_methods[] = { {"clear", (PyCFunction) element_clear, METH_VARARGS}, @@ -1268,10 +1441,15 @@ static PyMethodDef element_methods[] = { {"findall", (PyCFunction) element_findall, METH_VARARGS}, {"append", (PyCFunction) element_append, METH_VARARGS}, + {"extend", (PyCFunction) element_extend, METH_VARARGS}, {"insert", (PyCFunction) element_insert, METH_VARARGS}, {"remove", (PyCFunction) element_remove, METH_VARARGS}, - {"getiterator", (PyCFunction) element_getiterator, METH_VARARGS}, + {"iter", (PyCFunction) element_iter, METH_VARARGS}, + {"itertext", (PyCFunction) element_itertext, METH_VARARGS}, + {"iterfind", (PyCFunction) element_iterfind, METH_VARARGS}, + + {"getiterator", (PyCFunction) element_iter, METH_VARARGS}, {"getchildren", (PyCFunction) element_getchildren, METH_VARARGS}, {"items", (PyCFunction) element_items, METH_VARARGS}, @@ -1297,30 +1475,46 @@ static PyMethodDef element_methods[] = { {NULL, NULL} }; -static PyObject* +static PyObject* element_getattro(ElementObject* self, PyObject* nameobj) { PyObject* res; char *name = ""; if (PyUnicode_Check(nameobj)) - name = _PyUnicode_AsString(nameobj); + name = _PyUnicode_AsString(nameobj); - if (strcmp(name, "tag") == 0) - res = self->tag; - else if (strcmp(name, "text") == 0) + /* handle common attributes first */ + if (strcmp(name, "tag") == 0) { + res = self->tag; + Py_INCREF(res); + return res; + } else if (strcmp(name, "text") == 0) { res = element_get_text(self); - else if (strcmp(name, "tail") == 0) { - res = element_get_tail(self); - } else if (strcmp(name, "attrib") == 0) { - if (!self->extra) - element_new_extra(self, NULL); - res = element_get_attrib(self); - } else { - return PyObject_GenericGetAttr((PyObject*) self, nameobj); + Py_INCREF(res); + return res; } - Py_XINCREF(res); + /* methods */ + res = PyObject_GenericGetAttr((PyObject*) self, nameobj); + if (res) + return res; + + /* less common attributes */ + if (strcmp(name, "tail") == 0) { + PyErr_Clear(); + res = element_get_tail(self); + } else if (strcmp(name, "attrib") == 0) { + PyErr_Clear(); + if (!self->extra) + element_new_extra(self, NULL); + res = element_get_attrib(self); + } + + if (!res) + return NULL; + + Py_INCREF(res); return res; } @@ -1366,9 +1560,15 @@ static PySequenceMethods element_as_sequence = { 0, /* sq_concat */ 0, /* sq_repeat */ element_getitem, - element_getslice, + 0, element_setitem, - element_setslice, + 0, +}; + +static PyMappingMethods element_as_mapping = { + (lenfunc) element_length, + (binaryfunc) element_subscr, + (objobjargproc) element_ass_subscr, }; static PyTypeObject Element_Type = { @@ -1383,7 +1583,7 @@ static PyTypeObject Element_Type = { (reprfunc)element_repr, /* tp_repr */ 0, /* tp_as_number */ &element_as_sequence, /* tp_as_sequence */ - 0, /* tp_as_mapping */ + &element_as_mapping, /* tp_as_mapping */ 0, /* tp_hash */ 0, /* tp_call */ 0, /* tp_str */ @@ -1537,7 +1737,7 @@ treebuilder_handle_start(TreeBuilderObject* self, PyObject* tag, } else { if (self->root) { PyErr_SetString( - PyExc_SyntaxError, + elementtree_parseerror_obj, "multiple elements on top level" ); goto error; @@ -1678,7 +1878,7 @@ treebuilder_handle_end(TreeBuilderObject* self, PyObject* tag) LOCAL(void) treebuilder_handle_namespace(TreeBuilderObject* self, int start, - const char* prefix, const char *uri) + PyObject *prefix, PyObject *uri) { PyObject* res; PyObject* action; @@ -1691,8 +1891,7 @@ treebuilder_handle_namespace(TreeBuilderObject* self, int start, if (!self->start_ns_event_obj) return; action = self->start_ns_event_obj; - /* FIXME: prefix and uri use utf-8 encoding! */ - parcel = Py_BuildValue("ss", (prefix) ? prefix : "", uri); + parcel = Py_BuildValue("OO", prefix, uri); if (!parcel) return; Py_INCREF(action); @@ -1852,6 +2051,7 @@ typedef struct { PyObject* names; PyObject* handle_xml; + PyObject* handle_start; PyObject* handle_data; PyObject* handle_end; @@ -1859,6 +2059,8 @@ typedef struct { PyObject* handle_comment; PyObject* handle_pi; + PyObject* handle_close; + } XMLParserObject; static PyTypeObject XMLParser_Type; @@ -1930,6 +2132,36 @@ makeuniversal(XMLParserObject* self, const char* string) return value; } +static void +expat_set_error(const char* message, int line, int column) +{ + PyObject *error; + PyObject *position; + char buffer[256]; + + sprintf(buffer, "%s: line %d, column %d", message, line, column); + + error = PyObject_CallFunction(elementtree_parseerror_obj, "s", buffer); + if (!error) + return; + + /* add position attribute */ + position = Py_BuildValue("(ii)", line, column); + if (!position) { + Py_DECREF(error); + return; + } + if (PyObject_SetAttrString(error, "position", position) == -1) { + Py_DECREF(error); + Py_DECREF(position); + return; + } + Py_DECREF(position); + + PyErr_SetObject(elementtree_parseerror_obj, error); + Py_DECREF(error); +} + /* -------------------------------------------------------------------- */ /* handlers */ @@ -1960,10 +2192,12 @@ expat_default_handler(XMLParserObject* self, const XML_Char* data_in, else res = NULL; Py_XDECREF(res); - } else { - PyErr_Format( - PyExc_SyntaxError, "undefined entity &%s;: line %ld, column %ld", - PyBytes_AS_STRING(key), + } else if (!PyErr_Occurred()) { + /* Report the first error, not the last */ + char message[128]; + sprintf(message, "undefined entity &%.100s;", _PyUnicode_AsString(key)); + expat_set_error( + message, EXPAT(GetErrorLineNumber)(self->parser), EXPAT(GetErrorColumnNumber)(self->parser) ); @@ -2018,9 +2252,15 @@ expat_start_handler(XMLParserObject* self, const XML_Char* tag_in, /* shortcut */ res = treebuilder_handle_start((TreeBuilderObject*) self->target, tag, attrib); - else if (self->handle_start) + else if (self->handle_start) { + if (attrib == Py_None) { + Py_DECREF(attrib); + attrib = PyDict_New(); + if (!attrib) + return; + } res = PyObject_CallFunction(self->handle_start, "OO", tag, attrib); - else + } else res = NULL; Py_DECREF(tag); @@ -2080,9 +2320,28 @@ static void expat_start_ns_handler(XMLParserObject* self, const XML_Char* prefix, const XML_Char *uri) { + PyObject* sprefix = NULL; + PyObject* suri = NULL; + + suri = PyUnicode_DecodeUTF8(uri, strlen(uri), "strict"); + if (!suri) + return; + + if (prefix) + sprefix = PyUnicode_DecodeUTF8(prefix, strlen(prefix), "strict"); + else + sprefix = PyUnicode_FromString(""); + if (!sprefix) { + Py_DECREF(suri); + return; + } + treebuilder_handle_namespace( - (TreeBuilderObject*) self->target, 1, prefix, uri + (TreeBuilderObject*) self->target, 1, sprefix, suri ); + + Py_DECREF(sprefix); + Py_DECREF(suri); } static void @@ -2158,10 +2417,10 @@ expat_unknown_encoding_handler(XMLParserObject *self, const XML_Char *name, p = PyUnicode_AS_UNICODE(u); for (i = 0; i < 256; i++) { - if (p[i] != Py_UNICODE_REPLACEMENT_CHARACTER) - info->map[i] = p[i]; + if (p[i] != Py_UNICODE_REPLACEMENT_CHARACTER) + info->map[i] = p[i]; else - info->map[i] = -1; + info->map[i] = -1; } Py_DECREF(u); @@ -2245,6 +2504,7 @@ xmlparser(PyObject* self_, PyObject* args, PyObject* kw) self->handle_end = PyObject_GetAttrString(target, "end"); self->handle_comment = PyObject_GetAttrString(target, "comment"); self->handle_pi = PyObject_GetAttrString(target, "pi"); + self->handle_close = PyObject_GetAttrString(target, "close"); PyErr_Clear(); @@ -2288,6 +2548,7 @@ xmlparser_dealloc(XMLParserObject* self) { EXPAT(ParserFree)(self->parser); + Py_XDECREF(self->handle_close); Py_XDECREF(self->handle_pi); Py_XDECREF(self->handle_comment); Py_XDECREF(self->handle_end); @@ -2318,8 +2579,7 @@ expat_parse(XMLParserObject* self, char* data, int data_len, int final) return NULL; if (!ok) { - PyErr_Format( - PyExc_SyntaxError, "%s: line %ld, column %ld", + expat_set_error( EXPAT(ErrorString)(EXPAT(GetErrorCode)(self->parser)), EXPAT(GetErrorLineNumber)(self->parser), EXPAT(GetErrorColumnNumber)(self->parser) @@ -2340,13 +2600,17 @@ xmlparser_close(XMLParserObject* self, PyObject* args) return NULL; res = expat_parse(self, "", 0, 1); + if (!res) + return NULL; - if (res && TreeBuilder_CheckExact(self->target)) { + if (TreeBuilder_CheckExact(self->target)) { Py_DECREF(res); return treebuilder_done((TreeBuilderObject*) self->target); - } - - return res; + } if (self->handle_close) { + Py_DECREF(res); + return PyObject_CallFunction(self->handle_close, ""); + } else + return res; } static PyObject* @@ -2458,7 +2722,7 @@ xmlparser_setevents(XMLParserObject* self, PyObject* args) if (event_set == Py_None) { /* default is "end" only */ - target->end_event_obj = PyBytes_FromString("end"); + target->end_event_obj = PyUnicode_FromString("end"); Py_RETURN_NONE; } @@ -2468,9 +2732,13 @@ xmlparser_setevents(XMLParserObject* self, PyObject* args) for (i = 0; i < PyTuple_GET_SIZE(event_set); i++) { PyObject* item = PyTuple_GET_ITEM(event_set, i); char* event; - if (!PyBytes_Check(item)) + if (PyUnicode_Check(item)) { + event = _PyUnicode_AsString(item); + } else if (PyBytes_Check(item)) + event = PyBytes_AS_STRING(item); + else { goto error; - event = PyBytes_AS_STRING(item); + } if (strcmp(event, "start") == 0) { Py_INCREF(item); target->start_event_obj = item; @@ -2530,19 +2798,19 @@ xmlparser_getattro(XMLParserObject* self, PyObject* nameobj) char *name = ""; if (PyUnicode_Check(nameobj)) - name = _PyUnicode_AsString(nameobj); + name = _PyUnicode_AsString(nameobj); PyErr_Clear(); if (strcmp(name, "entity") == 0) - res = self->entity; + res = self->entity; else if (strcmp(name, "target") == 0) - res = self->target; + res = self->target; else if (strcmp(name, "version") == 0) { char buffer[100]; sprintf(buffer, "Expat %d.%d.%d", XML_MAJOR_VERSION, XML_MINOR_VERSION, XML_MICRO_VERSION); - return PyBytes_FromString(buffer); + return PyUnicode_DecodeUTF8(buffer, strlen(buffer), "strict"); } else { return PyObject_GenericGetAttr((PyObject*) self, nameobj); } @@ -2617,9 +2885,6 @@ PyInit__elementtree(void) PyObject* m; PyObject* g; char* bootstrap; -#if defined(USE_PYEXPAT_CAPI) - struct PyExpat_CAPI* capi; -#endif /* Initialize object types */ if (PyType_Ready(&TreeBuilder_Type) < 0) @@ -2651,10 +2916,6 @@ PyInit__elementtree(void) bootstrap = ( -#if (PY_VERSION_HEX >= 0x02020000 && PY_VERSION_HEX < 0x02030000) - "from __future__ import generators\n" /* enable yield under 2.2 */ -#endif - "from copy import copy, deepcopy\n" "try:\n" @@ -2672,11 +2933,14 @@ PyInit__elementtree(void) " def copyelement(elem):\n" " return elem\n" - "def Comment(text=None):\n" /* public */ + "class CommentProxy:\n" + " def __call__(self, text=None):\n" " element = cElementTree.Element(ET.Comment)\n" " element.text = text\n" " return element\n" - "cElementTree.Comment = Comment\n" + " def __eq__(self, other):\n" + " return ET.Comment == other\n" + "cElementTree.Comment = CommentProxy()\n" "class ElementTree(ET.ElementTree):\n" /* public */ " def parse(self, source, parser=None):\n" @@ -2695,23 +2959,23 @@ PyInit__elementtree(void) " return self._root\n" "cElementTree.ElementTree = ElementTree\n" - "def getiterator(node, tag=None):\n" /* helper */ + "def iter(node, tag=None):\n" /* helper */ " if tag == '*':\n" " tag = None\n" -#if (PY_VERSION_HEX < 0x02020000) - " nodes = []\n" /* 2.1 doesn't have yield */ - " if tag is None or node.tag == tag:\n" - " nodes.append(node)\n" - " for node in node:\n" - " nodes.extend(getiterator(node, tag))\n" - " return nodes\n" -#else " if tag is None or node.tag == tag:\n" " yield node\n" " for node in node:\n" - " for node in getiterator(node, tag):\n" + " for node in iter(node, tag):\n" " yield node\n" -#endif + + "def itertext(node):\n" /* helper */ + " if node.text:\n" + " yield node.text\n" + " for e in node:\n" + " for s in e.itertext():\n" + " yield s\n" + " if e.tail:\n" + " yield e.tail\n" "def parse(source, parser=None):\n" /* public */ " tree = ElementTree()\n" @@ -2719,48 +2983,52 @@ PyInit__elementtree(void) " return tree\n" "cElementTree.parse = parse\n" -#if (PY_VERSION_HEX < 0x02020000) - "if hasattr(ET, 'iterparse'):\n" - " cElementTree.iterparse = ET.iterparse\n" /* delegate on 2.1 */ -#else - "class iterparse(object):\n" + "class iterparse:\n" " root = None\n" " def __init__(self, file, events=None):\n" " if not hasattr(file, 'read'):\n" " file = open(file, 'rb')\n" " self._file = file\n" - " self._events = events\n" - " def __iter__(self):\n" - " events = []\n" + " self._events = []\n" + " self._index = 0\n" + " self.root = self._root = None\n" " b = cElementTree.TreeBuilder()\n" - " p = cElementTree.XMLParser(b)\n" - " p._setevents(events, self._events)\n" + " self._parser = cElementTree.XMLParser(b)\n" + " self._parser._setevents(self._events, events)\n" + " def __next__(self):\n" " while 1:\n" - " data = self._file.read(16384)\n" - " if not data:\n" - " break\n" - " p.feed(data)\n" - " for event in events:\n" - " yield event\n" - " del events[:]\n" - " root = p.close()\n" - " for event in events:\n" - " yield event\n" - " self.root = root\n" + " try:\n" + " item = self._events[self._index]\n" + " except IndexError:\n" + " if self._parser is None:\n" + " self.root = self._root\n" + " raise StopIteration\n" + " # load event buffer\n" + " del self._events[:]\n" + " self._index = 0\n" + " data = self._file.read(16384)\n" + " if data:\n" + " self._parser.feed(data)\n" + " else:\n" + " self._root = self._parser.close()\n" + " self._parser = None\n" + " else:\n" + " self._index = self._index + 1\n" + " return item\n" + " def __iter__(self):\n" + " return self\n" "cElementTree.iterparse = iterparse\n" -#endif - "def PI(target, text=None):\n" /* public */ - " element = cElementTree.Element(ET.ProcessingInstruction)\n" + "class PIProxy:\n" + " def __call__(self, target, text=None):\n" + " element = cElementTree.Element(ET.PI)\n" " element.text = target\n" " if text:\n" " element.text = element.text + ' ' + text\n" " return element\n" - - " elem = cElementTree.Element(ET.PI)\n" - " elem.text = text\n" - " return elem\n" - "cElementTree.PI = cElementTree.ProcessingInstruction = PI\n" + " def __eq__(self, other):\n" + " return ET.PI == other\n" + "cElementTree.PI = cElementTree.ProcessingInstruction = PIProxy()\n" "def XML(text):\n" /* public */ " parser = cElementTree.XMLParser()\n" @@ -2771,25 +3039,34 @@ PyInit__elementtree(void) "def XMLID(text):\n" /* public */ " tree = XML(text)\n" " ids = {}\n" - " for elem in tree.getiterator():\n" + " for elem in tree.iter():\n" " id = elem.get('id')\n" " if id:\n" " ids[id] = elem\n" " return tree, ids\n" "cElementTree.XMLID = XMLID\n" + "try:\n" + " register_namespace = ET.register_namespace\n" + "except AttributeError:\n" + " def register_namespace(prefix, uri):\n" + " ET._namespace_map[uri] = prefix\n" + "cElementTree.register_namespace = register_namespace\n" + "cElementTree.dump = ET.dump\n" "cElementTree.ElementPath = ElementPath = ET.ElementPath\n" "cElementTree.iselement = ET.iselement\n" "cElementTree.QName = ET.QName\n" "cElementTree.tostring = ET.tostring\n" + "cElementTree.fromstringlist = ET.fromstringlist\n" + "cElementTree.tostringlist = ET.tostringlist\n" "cElementTree.VERSION = '" VERSION "'\n" "cElementTree.__version__ = '" VERSION "'\n" - "cElementTree.XMLParserError = SyntaxError\n" ); - PyRun_String(bootstrap, Py_file_input, g, NULL); + if (!PyRun_String(bootstrap, Py_file_input, g, NULL)) + return NULL; elementpath_obj = PyDict_GetItemString(g, "ElementPath"); @@ -2804,22 +3081,30 @@ PyInit__elementtree(void) } } else PyErr_Clear(); + elementtree_deepcopy_obj = PyDict_GetItemString(g, "deepcopy"); - elementtree_getiterator_obj = PyDict_GetItemString(g, "getiterator"); + elementtree_iter_obj = PyDict_GetItemString(g, "iter"); + elementtree_itertext_obj = PyDict_GetItemString(g, "itertext"); #if defined(USE_PYEXPAT_CAPI) /* link against pyexpat, if possible */ - capi = PyCapsule_Import(PyExpat_CAPSULE_NAME, 0); - if (capi && - strcmp(capi->magic, PyExpat_CAPI_MAGIC) == 0 && - capi->size <= sizeof(*expat_capi) && - capi->MAJOR_VERSION == XML_MAJOR_VERSION && - capi->MINOR_VERSION == XML_MINOR_VERSION && - capi->MICRO_VERSION == XML_MICRO_VERSION) - expat_capi = capi; - else - expat_capi = NULL; + expat_capi = PyCapsule_Import(PyExpat_CAPSULE_NAME, 0); + if (expat_capi) { + /* check that it's usable */ + if (strcmp(expat_capi->magic, PyExpat_CAPI_MAGIC) != 0 || + expat_capi->size < sizeof(struct PyExpat_CAPI) || + expat_capi->MAJOR_VERSION != XML_MAJOR_VERSION || + expat_capi->MINOR_VERSION != XML_MINOR_VERSION || + expat_capi->MICRO_VERSION != XML_MICRO_VERSION) + expat_capi = NULL; + } #endif - return m; + elementtree_parseerror_obj = PyErr_NewException( + "cElementTree.ParseError", PyExc_SyntaxError, NULL + ); + Py_INCREF(elementtree_parseerror_obj); + PyModule_AddObject(m, "ParseError", elementtree_parseerror_obj); + + return m; } diff --git a/Tools/msi/msi.py b/Tools/msi/msi.py index cd67e996c07..f32bf393d0d 100644 --- a/Tools/msi/msi.py +++ b/Tools/msi/msi.py @@ -1006,8 +1006,6 @@ def add_files(db): lib.add_file("audiotest.au") lib.add_file("cfgparser.1") lib.add_file("sgml_input.html") - lib.add_file("test.xml") - lib.add_file("test.xml.out") lib.add_file("testtar.tar") lib.add_file("test_difflib_expect.html") lib.add_file("check_soundcard.vbs") @@ -1019,6 +1017,9 @@ def add_files(db): lib.add_file("zipdir.zip") if dir=='decimaltestdata': lib.glob("*.decTest") + if dir=='xmltestdata': + lib.glob("*.xml") + lib.add_file("test.xml.out") if dir=='output': lib.glob("test_*") if dir=='idlelib':