Python sax.make_parser函数代码示例

def tree_from_stream(stream, 
                     norm_sp=1, ext_ges=0, ext_pes=0, include_comment=1,
                     encoding='UTF-8', html=0):
    """
    create internal tree from xml stream (open file or IOString)
    if norm_sp = 1, normalize space and new line
    """
    from xml.sax import make_parser, SAXNotRecognizedException
    from xml.sax.handler import feature_namespaces, feature_external_ges, \
         feature_external_pes, property_lexical_handler
    from parser import SaxHandler
    handler = SaxHandler(norm_sp, include_comment, encoding)
    if html:
        parser = make_parser(["xml.sax.drivers2.drv_sgmlop_html"])
    else:
        parser = make_parser()
        # do not perform Namespace processing 
        parser.setFeature(feature_namespaces, 0)
    # do not include any external entities
    try:
        parser.setFeature(feature_external_ges, ext_ges)
        #xml.sax._exceptions.
    except SAXNotRecognizedException:
        print 'Unable to set feature external ges'
    try:
        parser.setFeature(feature_external_pes, ext_pes)
        #xml.sax._exceptions.
    except SAXNotRecognizedException:
        print 'Unable to set feature external pes'
    # add lexical handler for comments,  entities, dtd and cdata
    parser.setProperty(property_lexical_handler, handler)
    parser.setContentHandler(handler)
    parser.parse(stream)
    return handler.get_tree()

    def StartWork(self):
        StatusManager.StatusManager.pushServer=self
        req_GetClientId = ConnectStrings.GetString_ServerHeader()+'?'+ConnectStrings.GetString_GetClientId()
        print req_GetClientId

        getClientIdHandler=GetClientIdHandler.GetClientIdHandler()
        parser=make_parser()
        parser.setContentHandler(getClientIdHandler)
        parser.parse(req_GetClientId)
        print StatusManager.StatusManager.clientId

        req_AddStream=ConnectStrings.GetString_ServerHeader()+'?'+ConnectStrings.GetString_AddToStream()
        print req_AddStream
        addToStreamHandler=AddToStreamHandler.AddToStreamHandler()
        parser2=make_parser()
        parser2.setContentHandler(addToStreamHandler)

        url=req_AddStream
        StatusManager.StatusManager.stream=urllib2.urlopen(url)
        tagList=[]
        str=''
        while 1:
            char=StatusManager.StatusManager.stream.read(1)
            if char=='<':
                nextChar=StatusManager.StatusManager.stream.read(1)
                while nextChar!='>':
                    str+=nextChar
                    nextChar=StatusManager.StatusManager.stream.read(1)
                XmlProcess.ProcessNode(str)
                str=''

def upload_annotations_file(request, project_id=None):
    if not request.user.is_superuser:
        return HttpResponseForbidden("Error: You must be an administrator to use this form")
    if not request.FILES.has_key('fileToUpload') or not request.FILES['fileToUpload']:
        return projectEdit(request,project_id=project_id,error="Please select a file to upload (supported formats are .zip and .xml).")
    f = request.FILES['fileToUpload']
    if (not f.name.endswith('.xml')) and (not f.name.endswith('.zip')):
        return projectEdit(request,project_id=project_id,error="Please select a file to upload (supported formats are .zip and .xml).")
    if fnmatch.fnmatch(f.name, '*.xml'):
        parser = make_parser()
        curHandler = XmlImportHandler(project_id)
        parser.setContentHandler(curHandler)
        data = ""
        for chunk in f.chunks():
            data += chunk
        parser.feed(data)
    if fnmatch.fnmatch(f.name, '*.zip'):
        zipdata = ""
        for chunk in f.chunks():
            zipdata += chunk
        zip = zipfile.ZipFile(StringIO.StringIO(zipdata))
        for file in zip.namelist():
            parser = make_parser()
            curHandler = XmlImportHandler(project_id)
            parser.setContentHandler(curHandler)
            #pdb.set_trace()
            if file.find("__MACOSX/") == -1:
                parser.feed(zip.read(file))
        zip.close()
    return projectEdit(request, project_id=project_id)

    def get_objects_recursive(self, objtype, ids=[], recursive=False):
        """
        Recursively get all osm objects that are listed in the ids.
        If recursive=False, then you get only the objects that are directly
        referenced in relations.
        If recursive=True, then you get all hierarchically referenced
        from the relations.
        """
        relationids = set([])
        wayids = set([])
        nodeids = set([])
        relationdata, waydata, nodedata = '','',''

        if objtype == 'node':
            nodeids = set(ids)
        elif objtype == 'way':
            wayids = set(ids)
        elif objtype == 'relation':
            relationids = set(ids)
        else:
            return ""

        if recursive:
            recursions = 100  # maximum recursion level
        else:
            recursions = 1    # only get all direct members

        loaded_relationids = set([])
        while relationids:
            r_data = self.get_objects('relation', relationids)
            relationdata += '\n' + r_data

            if not recursions:
                break
            else:
                recursions -= 1

            parser = make_parser()
            osm_handler = SubobjectHandler()
            parser.setContentHandler(osm_handler)
            parseString(OSMHEAD + r_data + OSMTAIL, osm_handler)
            nodeids |= osm_handler.nodes
            wayids |= osm_handler.ways
            loaded_relationids |= relationids
            relationids = osm_handler.relations - loaded_relationids

        if wayids:
            waydata = self.get_objects('way', wayids)
            parser = make_parser()
            osm_handler = SubobjectHandler()
            parser.setContentHandler(osm_handler)
            parseString(OSMHEAD + waydata + OSMTAIL, osm_handler)
            nodeids |= osm_handler.nodes

        if nodeids:
            nodedata = self.get_objects('node', nodeids)

        return nodedata + waydata + relationdata

    def __init__(self):
        """
            Create a new Definition Object
        """
        self.map = {}
        self.patches = {}

        handler = DefinitionHandler()
        sax.make_parser()

        for path in [AAPATH, NAPATH]:
            defpath = getDatFile(path)
            if defpath == "":
                raise PDBInternalError("%s not found!" % path)

            acidFile = open(defpath)
            sax.parseString(acidFile.read(), handler)
            acidFile.close()

            self.map.update(handler.map)

        # Now handle patches

        defpath = getDatFile(PATCHPATH)
        if defpath == "":
            raise PDBInternalError("%s not found!" % PATCHPATH)

        handler.map = {}
        patchFile = open(defpath)
        sax.parseString(patchFile.read(), handler)
        patchFile.close()

        # Apply specific patches to the reference object, allowing users
        #  to specify protonation states in the PDB file

        for patch in handler.patches:
            if patch.newname != "":

                # Find all residues matching applyto

                resnames = self.map.keys()
                for name in resnames:
                    regexp = re.compile(patch.applyto).match(name)
                    if not regexp:
                        continue
                    newname = patch.newname.replace("*", name)
                    self.addPatch(patch, name, newname)

            # Either way, make sure the main patch name is available

            self.addPatch(patch, patch.applyto, patch.name)

	def readDotGraphStyles(self):
		p   = make_parser()
		h   = rocks.profile.RollHandler()
		map = {}
		
		for file in os.listdir('.'):
			tokens = os.path.splitext(file)
			if len(tokens) != 2:
				continue
			name = tokens[0]
			ext  = tokens[1]
			tokens = string.split(name, '-')
			if len(tokens) < 2:
				continue
			prefix = tokens[0]
			if prefix == 'roll' and \
			   ext == '.xml' and \
			   os.path.isfile(file):
				fin = open(file, 'r')
				p.setContentHandler(h)
				p.parse(fin)
				fin.close()
				r = h.getRollName()
				map[r] = rocks.util.Struct()
				map[r].edgeColor = h.getEdgeColor()
				map[r].nodeColor = h.getNodeColor()
				map[r].nodeShape = h.getNodeShape()

		return map

 def load_costs(self, dumpfile, iteration, weight):
     # load costs from dumpfile and update memory according to weight and iteration
     if weight <= 0:
         sys.stderr.write("Skipped loading of costs because the weight was %s but should have been > 0\n" % weight)
         return
     assert(weight > 0)
     if self.iteration == None and iteration != 0:
         print "Warning: continuing with empty memory"
     # update memory weights. memory is a weighted average across all runs
     self.memory_factor = self.memory_weight / (self.memory_weight + weight)
     self.memory_weight += weight
     self.iteration = iteration
     self.errors = []
     # mark all edges as unseen
     for edges in self.intervals.itervalues():
         for edgeMemory in edges.itervalues():
             edgeMemory.seen = False
     # parse costs
     self.num_loaded = 0
     parser = make_parser()
     parser.setContentHandler(self)
     parser.parse(dumpfile)
     # decay costs of unseen edges
     self.num_decayed = 0
     for edges in self.intervals.itervalues():
         for edgeMemory in edges.itervalues():
             if edgeMemory.decay_unseen(self.memory_factor):
                 self.num_decayed += 1

 def import_data(self, metadata, output):
     "Imports places data from OpenStreetMap"
     
     old_etag = metadata.get('etag', '')
     
     request = AnyMethodRequest(self._url, method='HEAD')
     response = urllib2.urlopen(request)
     new_etag = response.headers['ETag'][1:-1]
     self.output = output
     
     if False and new_etag == old_etag:
         output.write('OSM data not updated. Not updating.\n')
         return
     
     p = subprocess.Popen([self.SHELL_CMD % self._url], shell=True,
         stdin=subprocess.PIPE, stdout=subprocess.PIPE, close_fds=True)
     
     parser = make_parser()
     parser.setContentHandler(OSMHandler(self._get_source(),
                                         self._get_entity_types(),
                                         lambda tags, type_list=None: self._find_types(tags, self._osm_tags if type_list is None else type_list),
                                         output,
                                         self._lat_north,
                                         self._lat_south,
                                         self._lon_west,
                                         self._lon_east))
     parser.parse(p.stdout)
     
     for lang_code, lang_name in settings.LANGUAGES:
         with override(lang_code):
             self.disambiguate_titles(self._get_source())
     
     return {
         'etag': new_etag,
     }

def readficheroconfig():
    parser = make_parser()
    ParserDTD = uaserver.ParserDTD()
    parser.setContentHandler(ParserDTD)
    parser.parse(open(FICHEROCONFIG))
    TAGS = ParserDTD.get_tags()
    return TAGS

    def test_5027_1(self):
        # The xml prefix (as in xml:lang below) is reserved and bound by
        # definition to http://www.w3.org/XML/1998/namespace.  XMLGenerator had
        # a bug whereby a KeyError is thrown because this namespace is missing
        # from a dictionary.
        #
        # This test demonstrates the bug by parsing a document.
        test_xml = StringIO(
            '<?xml version="1.0"?>'
            '<a:g1 xmlns:a="http://example.com/ns">'
             '<a:g2 xml:lang="en">Hello</a:g2>'
            '</a:g1>')

        parser = make_parser()
        parser.setFeature(feature_namespaces, True)
        result = StringIO()
        gen = XMLGenerator(result)
        parser.setContentHandler(gen)
        parser.parse(test_xml)

        self.assertEqual(result.getvalue(),
                         start + (
                         '<a:g1 xmlns:a="http://example.com/ns">'
                          '<a:g2 xml:lang="en">Hello</a:g2>'
                         '</a:g1>'))

    def read(self, filename):
        self.publications = []
        self.authors = []
        self.author_idx = {}
        self.min_year = None
        self.max_year = None

        handler = DocumentHandler(self)
        parser = make_parser()
        parser.setContentHandler(handler)
        infile = open(filename, "r")
        valid = True
        try:
            parser.parse(infile)
        except SAXException as e:
            valid = False
            print "Error reading file (" + e.getMessage() + ")"
        infile.close()

        for p in self.publications:
            if self.min_year == None or p.year < self.min_year:
                self.min_year = p.year
            if self.max_year == None or p.year > self.max_year:
                self.max_year = p.year

        self.authors_graph = self._build_authors_graph()
        return valid

def parse(opts):
    """
    Entry point for XML Schema parsing into an OME Model.
    """
    # The following two statements are required to "prime" the generateDS
    # code and ensure we have reasonable namespace support.
    filenames = opts.args
    namespace = opts.namespace

    logging.debug("Namespace: %s" % namespace)
    set_type_constants(namespace)
    generateDS.generateDS.XsdNameSpace = namespace
    logging.debug("Type map: %s" % opts.lang.type_map)

    parser = sax.make_parser()
    ch = XschemaHandler()
    parser.setContentHandler(ch)
    for filename in filenames:
        parser.parse(filename)

    root = ch.getRoot()
    if root is None:
        raise ModelProcessingError(
            "No model objects found, have you set the correct namespace?")
    root.annotate()
    return OMEModel.process(ch, opts)

 def __init__(self, arquivo_mapa):
     parser = sax.make_parser()
     self.tmxhandler = TMXHandler(arquivo_mapa)
     parser.setContentHandler(self.tmxhandler)
     print 'Carregando o mapa %s ...' % (arquivo_mapa,)
     parser.parse(arquivo_mapa)
     print 'Pronto !'

 def __init__(self, parent, config):
     C3Object.__init__(self, parent, config)
     self.parser = make_parser()
     self.inputSource = SaxInput()
     self.errorHandler = ErrorHandler()
     self.parser.setErrorHandler(self.errorHandler)
     self.parser.setContentHandler(self)

	def scan(self):
		"""Parse the *.qrc* files"""
		if not has_xml:
			Logs.error('no xml support was found, the rcc dependencies will be incomplete!')
			return ([], [])

		parser = make_parser()
		curHandler = XMLHandler()
		parser.setContentHandler(curHandler)
		fi = open(self.inputs[0].abspath(), 'r')
		try:
			parser.parse(fi)
		finally:
			fi.close()

		nodes = []
		names = []
		root = self.inputs[0].parent
		for x in curHandler.files:
			nd = root.find_resource(x)
			if nd:
				nodes.append(nd)
			else:
				names.append(x)
		return (nodes, names)