Python pyexpat.ParserCreate方法代码示例

# 需要导入模块: import pyexpat [as 别名]
# 或者: from pyexpat import ParserCreate [as 别名]
def __init__(self):
        import pyexpat
        self.DocumentStartEvent = None
        self.ElementEvent = None
        self.DocumentEndEvent = None
        self.error = pyexpat.error
        self.parser = pyexpat.ParserCreate("UTF-8", " ")
        self.parser.StartElementHandler = self._onStartElement
        self.parser.EndElementHandler = self._onEndElement
        self.parser.CharacterDataHandler = self._onCdata
        self.parser.StartNamespaceDeclHandler = self._onStartNamespace
        self.parser.EndNamespaceDeclHandler = self._onEndNamespace
        self.currElem = None
        self.defaultNsStack = ['']
        self.documentStarted = 0
        self.localPrefixes = {} 

# 需要导入模块: import pyexpat [as 别名]
# 或者: from pyexpat import ParserCreate [as 别名]
def test_incremental_parsing(self):
        """https://github.com/IronLanguages/ironpython3/pull/680"""
        
        res = []
        def start_element(name, attrs):
            res.append("<{}>".format(name))
        def end_element(name):
            res.append("</{}>".format(name))
        def char_data(data):
            res.append(data)
        
        parser = pyexpat.ParserCreate()
        parser.StartElementHandler = start_element
        parser.EndElementHandler = end_element
        parser.CharacterDataHandler = char_data
        
        data = "<e>abc\U00010000xyz</e>"
        parser.Parse(data[:7], False)
        parser.Parse(data[7:], True)
        self.assertEqual(data, "".join(res)) 

# 需要导入模块: import pyexpat [as 别名]
# 或者: from pyexpat import ParserCreate [as 别名]
def __init__(self):
        import pyexpat
        self.DocumentStartEvent = None
        self.ElementEvent = None
        self.DocumentEndEvent = None
        self.error = pyexpat.error
        self.parser = pyexpat.ParserCreate("UTF-8", " ")
        self.parser.StartElementHandler = self._onStartElement
        self.parser.EndElementHandler = self._onEndElement
        self.parser.CharacterDataHandler = self._onCdata
        self.parser.StartNamespaceDeclHandler = self._onStartNamespace
        self.parser.EndNamespaceDeclHandler = self._onEndNamespace
        self.currElem = None
        self.defaultNsStack = ['']
        self.documentStarted = 0        
        self.localPrefixes = {} 

# 需要导入模块: import pyexpat [as 别名]
# 或者: from pyexpat import ParserCreate [as 别名]
def test_ipy2_gh655(self):
        """https://github.com/IronLanguages/ironpython2/issues/655"""
        import pyexpat
        buffer_size = pyexpat.ParserCreate().buffer_size
        self.assertEqual(buffer_size, 8192)

        import xml.etree.ElementTree as ET
        for count in range(buffer_size - 100, buffer_size + 100):
            txt = '<Data>' + '1'*count + '</Data>'
            result = ET.tostring(ET.fromstring(txt))
            self.assertEqual(txt, result) 

# 需要导入模块: import pyexpat [as 别名]
# 或者: from pyexpat import ParserCreate [as 别名]
def _onStartElement(self, name, attrs):
        # Generate a qname tuple from the provided name.  See
        # http://docs.python.org/library/pyexpat.html#xml.parsers.expat.ParserCreate
        # for an explanation of the formatting of name.
        qname = name.rsplit(" ", 1)
        if len(qname) == 1:
            qname = ('', name)

        # Process attributes
        for k, v in attrs.items():
            if " " in k:
                aqname = k.rsplit(" ", 1)
                attrs[(aqname[0], aqname[1])] = v
                del attrs[k]

        # Construct the new element
        e = Element(qname, self.defaultNsStack[-1], attrs, self.localPrefixes)
        self.localPrefixes = {}

        # Document already started
        if self.documentStarted == 1:
            if self.currElem != None:
                self.currElem.children.append(e)
                e.parent = self.currElem
            self.currElem = e

        # New document
        else:
            self.documentStarted = 1
            self.DocumentStartEvent(e) 

# 需要导入模块: import pyexpat [as 别名]
# 或者: from pyexpat import ParserCreate [as 别名]
def __init__(self, html=0, target=None, encoding=None):
        try:
            from xml.parsers import expat
        except ImportError:
            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()
        # 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
        # main callbacks
        parser.DefaultHandlerExpand = self._default
        if hasattr(target, 'start'):
            parser.StartElementHandler = self._start
        if hasattr(target, 'end'):
            parser.EndElementHandler = self._end
        if hasattr(target, 'data'):
            parser.CharacterDataHandler = target.data
        # miscellaneous callbacks
        if hasattr(target, 'comment'):
            parser.CommentHandler = target.comment
        if hasattr(target, 'pi'):
            parser.ProcessingInstructionHandler = target.pi
        # Configure pyexpat: buffering, new-style attribute handling.
        parser.buffer_text = 1
        parser.ordered_attributes = 1
        parser.specified_attributes = 1
        self._doctype = None
        self.entity = {}
        try:
            self.version = "Expat %d.%d.%d" % expat.version_info
        except AttributeError:
            pass # unknown 

# 需要导入模块: import pyexpat [as 别名]
# 或者: from pyexpat import ParserCreate [as 别名]
def test_ipy2_gh655(self):
        """https://github.com/IronLanguages/ironpython2/issues/655"""
        import pyexpat
        buffer_size = pyexpat.ParserCreate().buffer_size
        self.assertEqual(buffer_size, 8192)

        import xml.etree.ElementTree as ET
        for count in range(buffer_size - 100, buffer_size + 100):
            txt = b'<Data>' + b'1'*count + b'</Data>'
            result = ET.tostring(ET.fromstring(txt))
            self.assertEqual(txt, result) 

# 需要导入模块: import pyexpat [as 别名]
# 或者: from pyexpat import ParserCreate [as 别名]
def __init__(self, target=None, encoding=None):
        try:
            from xml.parsers import expat
        except ImportError:
            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 = ET.TreeBuilder()
        self.parser = parser
        self.target = target
        self._error = expat.error
        self._names = {} # name memo cache
        # main callbacks
        parser.DefaultHandlerExpand = self._default
        if hasattr(target, 'start'):
            parser.StartElementHandler = self._start
        if hasattr(target, 'end'):
            parser.EndElementHandler = self._end
        if hasattr(target, 'data'):
            parser.CharacterDataHandler = target.data
        if hasattr(target, 'comment'):
            parser.CommentHandler = target.comment
        if hasattr(target, 'pi'):
            parser.ProcessingInstructionHandler = target.pi
        # Configure pyexpat: buffering, new-style attribute handling.
        parser.buffer_text = 1
        parser.ordered_attributes = 1
        parser.specified_attributes = 1
        self._doctype = None
        self.entity = {}
        try:
            self.version = "Expat %d.%d.%d" % expat.version_info
        except AttributeError:
            pass # unknown 

# 需要导入模块: import pyexpat [as 别名]
# 或者: from pyexpat import ParserCreate [as 别名]
def __init__(self, html=0, target=None, encoding=None):
        try:
            from xml.parsers import expat
        except ImportError:
            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()
        # 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
        # main callbacks
        parser.DefaultHandlerExpand = self._default
        if hasattr(target, 'start'):
            parser.StartElementHandler = self._start
        if hasattr(target, 'end'):
            parser.EndElementHandler = self._end
        if hasattr(target, 'data'):
            parser.CharacterDataHandler = target.data
        # miscellaneous callbacks
        if hasattr(target, 'comment'):
            parser.CommentHandler = target.comment
        if hasattr(target, 'pi'):
            parser.ProcessingInstructionHandler = target.pi
        # let expat do the buffering, if supported
        try:
            parser.buffer_text = 1
        except AttributeError:
            pass
        # use new-style attribute handling, if supported
        try:
            parser.ordered_attributes = 1
            parser.specified_attributes = 1
            if hasattr(target, 'start'):
                parser.StartElementHandler = self._start_list
        except AttributeError:
            pass
        self._doctype = None
        self.entity = {}
        try:
            self.version = "Expat %d.%d.%d" % expat.version_info
        except AttributeError:
            pass # unknown 

# 需要导入模块: import pyexpat [as 别名]
# 或者: from pyexpat import ParserCreate [as 别名]
def __init__(self, html=0, target=None, encoding=None):
        try:
            from xml.parsers import expat
        except ImportError:
            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()
        # 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
        except AttributeError:
            pass
        # use new-style attribute handling, if supported
        try:
            self._parser.ordered_attributes = 1
            self._parser.specified_attributes = 1
            parser.StartElementHandler = self._start_list
        except AttributeError:
            pass
        self._doctype = None
        self.entity = {}
        try:
            self.version = "Expat %d.%d.%d" % expat.version_info
        except AttributeError:
            pass # unknown 

# 需要导入模块: import pyexpat [as 别名]
# 或者: from pyexpat import ParserCreate [as 别名]
def __init__(self, html=_sentinel, target=None, encoding=None):
        if html is not _sentinel:
            warnings.warnpy3k(
                "The html argument of XMLParser() is deprecated",
                DeprecationWarning, stacklevel=2)
        try:
            from xml.parsers import expat
        except ImportError:
            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()
        # 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
        except AttributeError:
            pass
        # use new-style attribute handling, if supported
        try:
            self._parser.ordered_attributes = 1
            self._parser.specified_attributes = 1
            parser.StartElementHandler = self._start_list
        except AttributeError:
            pass
        self._doctype = None
        self.entity = {}
        try:
            self.version = "Expat %d.%d.%d" % expat.version_info
        except AttributeError:
            pass # unknown 

# 需要导入模块: import pyexpat [as 别名]
# 或者: from pyexpat import ParserCreate [as 别名]
def __init__(self, html=_sentinel, target=None, encoding=None):
        if html is not _sentinel:
            warnings.warn(
                "The html argument of XMLParser() is deprecated",
                DeprecationWarning, stacklevel=2)
        try:
            from xml.parsers import expat
        except ImportError:
            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()
        # 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
        # main callbacks
        parser.DefaultHandlerExpand = self._default
        if hasattr(target, 'start'):
            parser.StartElementHandler = self._start
        if hasattr(target, 'end'):
            parser.EndElementHandler = self._end
        if hasattr(target, 'data'):
            parser.CharacterDataHandler = target.data
        # miscellaneous callbacks
        if hasattr(target, 'comment'):
            parser.CommentHandler = target.comment
        if hasattr(target, 'pi'):
            parser.ProcessingInstructionHandler = target.pi
        # Configure pyexpat: buffering, new-style attribute handling.
        parser.buffer_text = 1
        parser.ordered_attributes = 1
        parser.specified_attributes = 1
        self._doctype = None
        self.entity = {}
        try:
            self.version = "Expat %d.%d.%d" % expat.version_info
        except AttributeError:
            pass # unknown