# The {@link #ElementTree} class can be used to wrap an element # structure, and convert it from and to XML. @@ -113,25 +125,41 @@ from . import ElementPath -# TODO: add support for custom namespace resolvers/default namespaces -# TODO: add improved support for incremental parsing +VERSION = "1.3a2" -VERSION = "1.2.6" +class ParseError(SyntaxError): + pass + +# -------------------------------------------------------------------- ## -# Internal element class. This class defines the Element interface, -# and provides a reference implementation of this interface. +# 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. #
-# You should not create instances of this class directly. Use the
-# appropriate factory functions instead, such as {@link #Element}
-# and {@link #SubElement}.
+# 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.
# @see Element
# @see SubElement
# @see Comment
# @see ProcessingInstruction
-class _ElementInterface:
+class Element:
#
- # 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
-_Element = _ElementInterface
+ # compatibility (FIXME: preserve list behaviour too? see below)
+ getiterator = iter
-##
-# 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 getiterator(self, tag=None):
+ # return list(tag)
-def Element(tag, attrib={}, **extra):
- attrib = attrib.copy()
- attrib.update(extra)
- return _ElementInterface(tag, attrib)
+ ##
+ # 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):
+ 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
##
# Subelement factory. This function creates an element instance, and
@@ -447,7 +479,8 @@
##
# 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 +496,8 @@
##
# 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.
@@ -523,13 +557,15 @@
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:
@@ -564,8 +600,8 @@
# 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.
+ # @keyparam parser An optional parser instance. If not given, the
+ # standard {@link XMLParser} parser is used.
# @return The document root element.
# @defreturn Element
@@ -573,7 +609,7 @@
if not hasattr(source, "read"):
source = open(source, "rb")
if not parser:
- parser = XMLTreeBuilder()
+ parser = XMLParser(target=TreeBuilder())
while 1:
data = source.read(32768)
if not data:
@@ -590,9 +626,11 @@
# @return An iterator.
# @defreturn iterator
- def getiterator(self, tag=None):
+ def iter(self, tag=None):
assert self._root is not None
- return self._root.getiterator(tag)
+ return self._root.iter(tag)
+
+ getiterator = iter
##
# Finds the first toplevel element with given tag.
@@ -606,6 +644,12 @@
assert self._root is not None
if path[:1] == "/":
path = "." + path
+ import warnings
+ warnings.warn(
+ "This search is broken in 1.3 and earlier; if you rely "
+ "on the current behaviour, change it to %r" % path,
+ FutureWarning
+ )
return self._root.find(path)
##
@@ -624,6 +668,12 @@
assert self._root is not None
if path[:1] == "/":
path = "." + path
+ import warnings
+ warnings.warn(
+ "This search is broken in 1.3 and earlier; if you rely "
+ "on the current behaviour, change it to %r" % path,
+ FutureWarning
+ )
return self._root.findtext(path, default)
##
@@ -639,121 +689,273 @@
assert self._root is not None
if path[:1] == "/":
path = "." + path
+ import warnings
+ warnings.warn(
+ "This search is broken in 1.3 and earlier; if you rely "
+ "on the current behaviour, change it to %r" % path,
+ FutureWarning
+ )
return self._root.findall(path)
##
# Writes the element tree to a file, as XML.
#
# @param file A file name, or a file object opened for writing.
- # @param encoding Optional output encoding (default is None)
-
- def write(self, file, encoding=None):
+ # @keyparam encoding Optional output encoding (default is None).
+ # @keyparam method Optional output method ("xml" or "html"; 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,
+ # keyword arguments
+ encoding=None,
+ xml_declaration=None,
+ default_namespace=None,
+ method=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("" % _escape_cdata(node.text), encoding))
- elif tag is ProcessingInstruction:
- file.write(_encode("" % _escape_cdata(node.text), encoding))
+ if encoding:
+ def write(text):
+ try:
+ return file.write(text.encode(encoding,
+ "xmlcharrefreplace"))
+ except (TypeError, AttributeError):
+ _raise_serialization_error(text)
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(_escape_cdata(node.text), encoding))
- for n in node:
- self._write(file, n, encoding, namespaces)
- file.write(_encode("", encoding))
+ write = file.write
+ if not method:
+ method = "xml"
+ if xml_declaration or (encoding and
+ encoding not in ("utf-8", "us-ascii")):
+ 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, encoding)
+ else:
+ qnames, namespaces = _namespaces(
+ self._root, encoding, default_namespace
+ )
+ if method == "xml":
+ _serialize_xml(
+ write, self._root, encoding, qnames, namespaces
+ )
+ elif method == "html":
+ _serialize_html(
+ write, self._root, encoding, qnames, namespaces
+ )
else:
- file.write(_encode(" />", encoding))
- for k, v in xmlns_items:
- del namespaces[v]
- if node.tail:
- file.write(_encode(_escape_cdata(node.tail), encoding))
+ raise ValueError("unknown method %r" % method)
# --------------------------------------------------------------------
-# helpers
+# serialization support
-##
-# 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 _namespaces(elem, encoding, default_namespace=None):
+ # identify namespaces used in this tree
-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")
+ # maps qnames to *encoded* prefix:local names
+ qnames = {None: None}
-##
-# 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.
-#
-# @param elem An element tree or an individual element.
+ # maps uri:s to prefixes
+ namespaces = {}
+ if default_namespace:
+ namespaces[default_namespace] = ""
-def dump(elem):
- # debugging
- if not isinstance(elem, ElementTree):
- elem = ElementTree(elem)
- elem.write(sys.stdout)
- tail = elem.getroot().tail
- if not tail or tail[-1] != "\n":
- sys.stdout.write("\n")
+ def add_qname(qname):
+ # calculate serialized qname representation
+ try:
+ if qname[:1] == "{":
+ uri, tag = qname[1:].split("}", 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)
-def _encode(s, encoding):
- if encoding:
- return s.encode(encoding)
+ # 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, encoding, 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:
- return s
-
-_escape = re.compile(r"[&<>\"\u0080-\uffff]+")
+ tag = qnames[tag]
+ if tag is None:
+ if text:
+ write(_escape_cdata(text))
+ for e in elem:
+ _serialize_xml(write, e, encoding, qnames, None)
+ else:
+ write("<" + tag)
+ items = list(elem.items())
+ if items or namespaces:
+ items.sort() # lexical order
+ for k, v in items:
+ 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 namespaces:
+ items = namespaces.items()
+ items.sort(key=lambda x: x[1]) # sort on prefix
+ for v, k in items:
+ if k:
+ k = ":" + k
+ write(" xmlns%s=\"%s\"" % (
+ k,
+ _escape_attrib(v)
+ ))
+ if text or len(elem):
+ write(">")
+ if text:
+ write(_escape_cdata(text))
+ for e in elem:
+ _serialize_xml(write, e, encoding, 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, encoding, 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, encoding, qnames, None)
+ else:
+ write("<" + tag)
+ items = elem.items()
+ if items or namespaces:
+ items.sort() # lexical order
+ for k, v in items:
+ 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))
+ if namespaces:
+ items = namespaces.items()
+ items.sort(key=lambda x: x[1]) # sort on prefix
+ for v, k in items:
+ if k:
+ k = ":" + k
+ write(" xmlns%s=\"%s\"" % (
+ k,
+ _escape_attrib(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, encoding, qnames, None)
+ if tag not in HTML_EMPTY:
+ write("")
+ if elem.tail:
+ write(_escape_cdata(elem.tail))
+
+def _serialize_text(write, elem, encoding):
+ for part in elem.itertext():
+ write(part)
+ if elem.tail:
+ write(elem.tail)
-_escape_map = {
- "&": "&",
- "<": "<",
- ">": ">",
- '"': """,
-}
+##
+# 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 prefix Namespace prefix.
+# @param uri Namespace uri. Tags and attributes in this namespace
+# will be serialized with the given prefix, if at all possible.
+# @raise ValueError If the prefix is reserved, or is otherwise
+# invalid.
+
+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
@@ -761,6 +963,11 @@
"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",
+ # dublic core
+ "http://purl.org/dc/elements/1.1/": "dc",
}
def _raise_serialization_error(text):
@@ -768,32 +975,18 @@
"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 _escape_cdata(text):
# escape character data
try:
- text = text.replace("&", "&")
- text = text.replace("<", "<")
- text = text.replace(">", ">")
+ # 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)
@@ -801,41 +994,102 @@
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(">", ">")
+ 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 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)
+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.
+# @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:
- xmlns = None
- return "%s:%s" % (prefix, tag), xmlns
+ 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.
+# @return A sequence object containing the XML data.
+# @defreturn sequence
+# @since 1.3
+
+def tostringlist(element, encoding=None):
+ class dummy:
+ pass
+ data = []
+ file = dummy()
+ file.write = data.append
+ ElementTree(element).write(file, encoding)
+ # FIXME: merge small fragments into larger parts
+ return data
+
+##
+# 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.
+#
+# @param elem An element tree or an individual element.
+
+def dump(elem):
+ # debugging
+ if not isinstance(elem, ElementTree):
+ elem = ElementTree(elem)
+ elem.write(sys.stdout)
+ tail = elem.getroot().tail
+ if not tail or tail[-1] != "\n":
+ sys.stdout.write("\n")
+
+# --------------------------------------------------------------------
+# 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):
@@ -850,18 +1104,25 @@
# @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
@@ -889,7 +1150,7 @@
elif event == "start-ns":
def handler(prefix, uri, event=event, append=append):
try:
- uri = _encode(uri, "ascii")
+ uri = uri.encode("ascii")
except UnicodeError:
pass
append((event, (prefix or "", uri)))
@@ -906,10 +1167,7 @@
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
@@ -923,24 +1181,22 @@
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()
@@ -949,11 +1205,14 @@
# 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 = {}
@@ -974,25 +1233,23 @@
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
@@ -1013,11 +1270,11 @@
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.
@@ -1090,22 +1347,30 @@
# 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; expat = pyexpat
+ 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
@@ -1124,10 +1389,18 @@
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
@@ -1146,7 +1419,7 @@
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
@@ -1155,27 +1428,31 @@
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 _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] == "= 100:
- _cache.clear()
- _cache[path] = p
- return p
+# --------------------------------------------------------------------
##
# Find first matching object.
-def find(element, path):
- return _compile(path).find(element)
+def find(elem, path):
+ return next(findall(elem, path), None)
##
-# Find text for first matching object.
+# Find all matching objects.
-def findtext(element, path, default=None):
- return _compile(path).findtext(element, default)
+def findall(elem, path):
+ # compile selector pattern
+ try:
+ selector = _cache[path]
+ except KeyError:
+ if len(_cache) > 100:
+ _cache.clear()
+ if path[:1] == "/":
+ raise SyntaxError("cannot use absolute path on element")
+ stream = iter(xpath_tokenizer(path))
+ next = stream.__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 all matching objects.
+# Find text for first matching object.
-def findall(element, path):
- return _compile(path).findall(element)
+def findtext(elem, path, default=None):
+ try:
+ elem = next(findall(elem, path))
+ return elem.text
+ except StopIteration:
+ return default
Index: Modules/celementtree.h
===================================================================
--- Modules/celementtree.h (revision 0)
+++ Modules/celementtree.h (revision 0)
@@ -0,0 +1,78 @@
+/* Stuff to export relevant entry points from cElementTree */
+
+/* To use this API, do
+
+ struct cElementTree_CAPI *capi;
+ capi = PyCObject_Import("cElementTree", "CAPI");
+
+ Also check that capi->magic and capi->size matches the values from
+ this header, e.g:
+
+ if (strcmp(capi->magic, cElementTree_CAPI_MAGIC) != 0 ||
+ capi->size < sizeof(struct cElementTree_CAPI) ||
+ capi->version < cElementTree_CAPI_VERSION)
+ ... cannot use this version ...
+
+ See below for a summary of the available API functions.
+
+*/
+
+/* major version */
+#define cElementTree_CAPI_MAGIC "cElementTree.CAPI 1.0"
+#define cElementTree_CAPSULE_NAME "cElementTree.CAPI"
+
+/* minor version. new minor versions should always be backwards compatible */
+#define cElementTree_CAPI_VERSION 1
+
+/* struct to store a snapshot of a given Element */
+struct cElementTree_Snapshot
+{
+ /* filled in by snapshot method. members may be Py_None if not present
+ in the internal structure. all references are new; use DECREF to clean
+ up */
+ PyObject* tag;
+ PyObject* attrib;
+ PyObject* text;
+ PyObject* tail;
+ PyObject* children; /* only filled in if mode > 0 */
+
+ /* always add new stuff to the end! */
+};
+
+struct cElementTree_CAPI
+{
+ char* magic; /* set to cElementTree_CAPI_MAGIC */
+ int size; /* set to sizeof(struct cElementTree_CAPI) */
+ int version; /* set to cElementTree_CAPI_VERSION (API version) */
+
+ /* pointers to selected cElementTree helpers. add new functions at
+ the end, if needed */
+
+ /* Element type (to be used for exact type comparisions) */
+ PyObject* type;
+
+ /* Check if object is a cElementTree Element, and raises a TypeError
+ if not. Use this before calling other methods. */
+ /* Returns 0 if ok, -1 if error. */
+ int (*assert)(PyObject* elem);
+
+ /* Get Element snapshot. Use mode=1 to get children too. */
+ /* The 'elem' argument must point to a cElementTree Element. Use
+ 'assert' first when in doubt. */
+ /* All references are new, and point to stable versions (that is,
+ changing the original Element won't affect the snapshot). */
+ /* Py_None may be used for non-existent/empty fields. */
+ /* Returns 0 if ok, -1 if error. */
+ int (*snapshot)(
+ PyObject* elem, struct cElementTree_Snapshot* snapshot, int mode
+ );
+
+ /* Get subelement. */
+ /* The 'elem' argument must point to a cElementTree Element. Use
+ 'assert' first when in doubt. */
+ /* Returns a borrowed reference, or Py_None if the element does not
+ exist. */
+ PyObject* (*getitem)(PyObject* elem, int index);
+
+ /* always add new stuff to the end! */
+};
Index: Modules/_elementtree.c
===================================================================
--- Modules/_elementtree.c (revision 76697)
+++ Modules/_elementtree.c (working copy)
@@ -1,14 +1,12 @@
/*
* ElementTree
- * $Id: _elementtree.c 2657 2006-03-12 20:50:32Z fredrik $
+ * $Id: _elementtree.c 3469 2009-01-10 14:30:13Z fredrik $
*
* elementtree accelerator
*
* History:
* 1999-06-20 fl created (as part of sgmlop)
* 2001-05-29 fl effdom edition
- * 2001-06-05 fl backported to unix; fixed bogus free in clear
- * 2001-07-10 fl added findall helper
* 2003-02-27 fl elementtree edition (alpha)
* 2004-06-03 fl updates for elementtree 1.2
* 2005-01-05 fl added universal name cache, Element/SubElement factories
@@ -35,20 +33,30 @@
* 2005-12-16 fl added support for non-standard encodings
* 2006-03-08 fl fixed a couple of potential null-refs and leaks
* 2006-03-12 fl merge in 2.5 ssize_t changes
+ * 2007-08-25 fl call custom builder's close method from XMLParser
+ * 2007-08-31 fl added iter, extend from ET 1.3
+ * 2007-09-01 fl fixed ParseError exception, setslice source type, etc
+ * 2007-09-03 fl fixed handling of negative insert indexes
+ * 2007-09-04 fl added itertext from ET 1.3
+ * 2007-09-06 fl added position attribute to ParseError exception
+ * 2008-06-06 fl delay error reporting in iterparse (from Hrvoje Niksic)
+ * 2009-01-10 fl added experimental CAPI interface
*
- * Copyright (c) 1999-2006 by Secret Labs AB. All rights reserved.
- * Copyright (c) 1999-2006 by Fredrik Lundh.
+ * Copyright (c) 1999-2009 by Secret Labs AB. All rights reserved.
+ * Copyright (c) 1999-2009 by Fredrik Lundh.
*
* info@pythonware.com
* http://www.pythonware.com
*/
/* Licensed to PSF under a Contributor Agreement. */
-/* See http://www.python.org/2.4/license for licensing details. */
+/* See http://www.python.org/2.6/license for licensing details. */
#include "Python.h"
-#define VERSION "1.0.6"
+#include "celementtree.h" /* CAPI stuff */
+
+#define VERSION "1.0.6a2"
/* -------------------------------------------------------------------- */
/* configuration */
@@ -56,7 +64,7 @@
/* Leave defined to include the expat-based XMLParser type */
#define USE_EXPAT
-/* Define to to all expat calls via pyexpat's embedded expat library */
+/* Define to do all expat calls via pyexpat's embedded expat library */
/* #define USE_PYEXPAT_CAPI */
/* An element can hold this many children without extra memory
@@ -102,9 +110,11 @@
#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 */
@@ -309,7 +319,7 @@
if (element_new_extra(self, attrib) < 0) {
PyObject_Del(self);
return NULL;
- }
+ }
self->extra->length = 0;
self->extra->allocated = STATIC_CHILDREN;
@@ -398,6 +408,14 @@
return 0;
}
+static PyObject*
+element_get_type(void)
+{
+ /* return borrowed reference to type object */
+
+ return (PyObject*) &Element_Type;
+}
+
LOCAL(PyObject*)
element_get_attrib(ElementObject* self)
{
@@ -688,6 +706,8 @@
/* 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 +731,8 @@
/* 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);
@@ -742,6 +763,34 @@
}
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)
+ 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;
@@ -809,18 +858,24 @@
static PyObject*
element_findall(ElementObject* self, PyObject* args)
{
- int i;
- PyObject* out;
+ /* int i;
+ PyObject* out; */
PyObject* tag;
if (!PyArg_ParseTuple(args, "O:findall", &tag))
return NULL;
- if (checkpath(tag))
+ /* Use the Python implementation without condition.
+ The method will return an iterator in all cases.
+ See bug 6472. */
+
+ /* if (checkpath(tag)) */
+
return PyObject_CallMethod(
elementpath_obj, "findall", "OO", self, tag
);
+ /*
out = PyList_New(0);
if (!out)
return NULL;
@@ -840,6 +895,7 @@
}
return out;
+ */
}
static PyObject*
@@ -890,18 +946,18 @@
}
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 +969,37 @@
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);
@@ -984,8 +1070,11 @@
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;
@@ -1156,11 +1245,12 @@
}
static int
-element_setslice(PyObject* self_, Py_ssize_t start, Py_ssize_t end, PyObject* item)
+element_setslice(PyObject* self_, Py_ssize_t start, Py_ssize_t end, PyObject* seq_in)
{
ElementObject* self = (ElementObject*) self_;
Py_ssize_t i, new, old;
PyObject* recycle = NULL;
+ PyObject* seq = NULL;
if (!self->extra)
element_new_extra(self, NULL);
@@ -1177,17 +1267,18 @@
old = end - start;
- if (item == NULL)
+ if (seq_in == 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;
+ else {
+ seq = PySequence_Fast(seq_in, "");
+ if (!seq) {
+ PyErr_Format(
+ PyExc_TypeError,
+ "expected sequence, not \"%.200s\"", Py_TYPE(seq_in)->tp_name
+ );
+ return -1;
+ }
+ new = PySequence_Size(seq);
}
if (old > 0) {
@@ -1205,21 +1296,27 @@
self->extra->children[i + new - old] = self->extra->children[i];
} else if (new > old) {
/* insert slice */
- if (element_resize(self, new - old) < 0)
+ if (element_resize(self, new - old) < 0) {
+ if (seq)
+ Py_DECREF(seq);
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);
+ PyObject* element = PySequence_Fast_GET_ITEM(seq, i);
Py_INCREF(element);
self->extra->children[i + start] = element;
}
self->extra->length += new - old;
+ if (seq)
+ Py_DECREF(seq);
+
/* discard the recycle bin, and everything in it */
Py_XDECREF(recycle);
@@ -1256,6 +1353,161 @@
return 0;
}
+static PyObject*
+element_subscr(PyObject* self_, PyObject* item)
+{
+ ElementObject* self = (ElementObject*) self_;
+
+ if (PyIndex_Check(item)) {
+ Py_ssize_t i = PyNumber_AsSsize_t(item, PyExc_IndexError);
+ 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 (PyIndex_Check(item)) {
+ Py_ssize_t i = PyNumber_AsSsize_t(item, PyExc_IndexError);
+
+ 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,
+ "attempt to assign sequence of size %zd "
+ "to extended slice of size %zd",
+ newlen, slicelen
+ );
+ 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);
+ 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 */
+ if (element_resize(self, newlen - slicelen) < 0) {
+ if (seq)
+ Py_DECREF(seq);
+ return -1;
+ }
+ 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 +1520,14 @@
{"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},
+
+ {"getiterator", (PyCFunction) element_iter, METH_VARARGS},
{"getchildren", (PyCFunction) element_getchildren, METH_VARARGS},
{"items", (PyCFunction) element_items, METH_VARARGS},
@@ -1304,10 +1560,10 @@
char *name = "";
if (PyUnicode_Check(nameobj))
- name = _PyUnicode_AsString(nameobj);
+ name = _PyUnicode_AsString(nameobj);
if (strcmp(name, "tag") == 0)
- res = self->tag;
+ res = self->tag;
else if (strcmp(name, "text") == 0)
res = element_get_text(self);
else if (strcmp(name, "tail") == 0) {
@@ -1315,7 +1571,7 @@
} else if (strcmp(name, "attrib") == 0) {
if (!self->extra)
element_new_extra(self, NULL);
- res = element_get_attrib(self);
+ res = element_get_attrib(self);
} else {
return PyObject_GenericGetAttr((PyObject*) self, nameobj);
}
@@ -1366,9 +1622,15 @@
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 +1645,7 @@
(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 */
@@ -1402,6 +1664,71 @@
0, /* tp_members */
};
+/* -------------------------------------------------------------------- */
+/* CAPI interface */
+
+static int
+element_capi_assert(PyObject* elem)
+{
+ if (Element_CheckExact(elem))
+ return 0;
+ PyErr_Format(
+ PyExc_TypeError,
+ "expected cElementTree.Element, not \"%.200s\"",
+ elem->ob_type->tp_name
+ );
+ return -1;
+}
+
+static PyObject*
+element_capi_getitem(PyObject* self, int index)
+{
+ ElementObject* elem = (ElementObject*) self;
+
+ if (!elem->extra || index < 0 || index >= elem->extra->length)
+ Py_RETURN_NONE;
+
+ Py_INCREF(elem->extra->children[index]);
+ return elem->extra->children[index];
+}
+
+static int
+element_capi_snapshot(PyObject* self, struct cElementTree_Snapshot* snapshot,
+ int mode)
+{
+ ElementObject* elem = (ElementObject*) self;
+
+ snapshot->tag = elem->tag;
+ Py_INCREF(snapshot->tag);
+
+ snapshot->text = element_get_text(elem);
+ Py_INCREF(snapshot->text);
+
+ snapshot->tail = element_get_tail(elem);
+ Py_INCREF(snapshot->tail);
+
+ if (elem->extra)
+ snapshot->attrib = element_get_attrib(elem);
+ else
+ snapshot->attrib = Py_None;
+ Py_INCREF(snapshot->attrib);
+
+ if (!mode)
+ return 0;
+
+ if (elem->extra) {
+ snapshot->children = element_getslice(
+ (PyObject*) elem, 0, elem->extra->length
+ );
+ /* FIXME: clean up if slice fails */
+ } else {
+ snapshot->children = Py_None;
+ Py_INCREF(snapshot->children);
+ }
+
+ return 0;
+}
+
/* ==================================================================== */
/* the tree builder type */
@@ -1537,7 +1864,7 @@
} else {
if (self->root) {
PyErr_SetString(
- PyExc_SyntaxError,
+ elementtree_parseerror_obj,
"multiple elements on top level"
);
goto error;
@@ -1852,6 +2179,7 @@
PyObject* names;
PyObject* handle_xml;
+
PyObject* handle_start;
PyObject* handle_data;
PyObject* handle_end;
@@ -1859,6 +2187,8 @@
PyObject* handle_comment;
PyObject* handle_pi;
+ PyObject* handle_close;
+
} XMLParserObject;
static PyTypeObject XMLParser_Type;
@@ -1930,6 +2260,32 @@
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)
+ return;
+ if (PyObject_SetAttrString(error, "position", position) == -1) {
+ Py_DECREF(position);
+ return;
+ }
+ Py_DECREF(position);
+
+ PyErr_SetObject(elementtree_parseerror_obj, error);
+}
+
/* -------------------------------------------------------------------- */
/* handlers */
@@ -1961,9 +2317,10 @@
res = NULL;
Py_XDECREF(res);
} else {
- PyErr_Format(
- PyExc_SyntaxError, "undefined entity &%s;: line %ld, column %ld",
- PyBytes_AS_STRING(key),
+ char message[128];
+ sprintf(message, "undefined entity &%.100s;", PyBytes_AS_STRING(key));
+ expat_set_error(
+ message,
EXPAT(GetErrorLineNumber)(self->parser),
EXPAT(GetErrorColumnNumber)(self->parser)
);
@@ -2018,9 +2375,15 @@
/* 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);
@@ -2158,10 +2521,10 @@
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 +2608,7 @@
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 +2652,7 @@
{
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 +2683,7 @@
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 +2704,17 @@
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 +2826,7 @@
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;
}
@@ -2530,14 +2898,14 @@
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,
@@ -2617,9 +2985,8 @@
PyObject* m;
PyObject* g;
char* bootstrap;
-#if defined(USE_PYEXPAT_CAPI)
- struct PyExpat_CAPI* capi;
-#endif
+ static struct cElementTree_CAPI capi;
+ PyObject* capi_object;
/* Initialize object types */
if (PyType_Ready(&TreeBuilder_Type) < 0)
@@ -2672,11 +3039,14 @@
" 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 __hash__(self):\n"
+ " return hash(ET.Comment)\n"
+ "cElementTree.Comment = CommentProxy()\n"
"class ElementTree(ET.ElementTree):\n" /* public */
" def parse(self, source, parser=None):\n"
@@ -2695,7 +3065,7 @@
" 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)
@@ -2703,16 +3073,25 @@
" if tag is None or node.tag == tag:\n"
" nodes.append(node)\n"
" for node in node:\n"
- " nodes.extend(getiterator(node, tag))\n"
+ " nodes.extend(iter(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"
" tree.parse(source, parser)\n"
@@ -2723,44 +3102,53 @@
"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 __hash__(self):\n"
+ " return hash(ET.PI)\n"
+ "cElementTree.PI = cElementTree.ProcessingInstruction = PIProxy()\n"
"def XML(text):\n" /* public */
" parser = cElementTree.XMLParser()\n"
@@ -2778,6 +3166,13 @@
" 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"
@@ -2785,11 +3180,11 @@
"cElementTree.tostring = ET.tostring\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 +3199,42 @@
}
} 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);
+
+ capi.size = sizeof(capi);
+ capi.magic = cElementTree_CAPI_MAGIC;
+ capi.version = cElementTree_CAPI_VERSION;
+ capi.type = (PyObject*) &Element_Type;
+ capi.assert = element_capi_assert;
+ capi.snapshot = element_capi_snapshot;
+ capi.getitem = element_capi_getitem;
+
+ /* export as cobject */
+ capi_object = PyCapsule_New(&capi, cElementTree_CAPSULE_NAME, NULL);
+ if (capi_object)
+ PyModule_AddObject(m, "CAPI", capi_object);
}
Index: Lib/test/test_xml_etree_c.py
===================================================================
--- Lib/test/test_xml_etree_c.py (revision 76697)
+++ Lib/test/test_xml_etree_c.py (working copy)
@@ -5,6 +5,12 @@
from test import support
+# Ignore warning about search path starting with "/".
+import warnings
+warnings.filterwarnings("ignore",
+ "This search is broken in 1.3 and earlier; if you rely on the "
+ "current behaviour, change it to '.*'", FutureWarning)
+
ET = support.import_module('xml.etree.cElementTree')
SAMPLE_XML = """
@@ -38,12 +44,16 @@
if not hasattr(method, '__call__'):
print(method, "not callable")
-def serialize(ET, elem):
+def serialize(ET, elem, getvalue=True):
import io
file = io.StringIO()
tree = ET.ElementTree(elem)
tree.write(file)
- return file.getvalue()
+ if getvalue:
+ return file.getvalue()
+ else:
+ file.seek(0)
+ return file
def summarize(elem):
return elem.tag
@@ -74,6 +84,12 @@
>>> check_method(element.items)
>>> check_method(element.getiterator)
+ These methods return an iterable. See bug 6472.
+
+ >>> check_method(element.getiterator("tag").__next__)
+ >>> check_method(element.findall("tag").__next__)
+ >>> check_method(element.findall("*").__next__)
+
Basic method sanity checks.
>>> serialize(ET, element) # 1
@@ -96,6 +112,20 @@
ValueError: list.remove(x): x not in list
>>> serialize(ET, element) # 6
'