Python xml.sax.handler.ErrorHandler() Examples
The following are 9
code examples of xml.sax.handler.ErrorHandler().
You can vote up the ones you like or vote down the ones you don't like,
and go to the original project or source file by following the links above each example.
You may also want to check out all available functions/classes of the module
xml.sax.handler
, or try the search function
.
Example #1
Source File: config.py From uniconvertor with GNU Affero General Public License v3.0 | 6 votes |
def load(self, filename=None): self.filename = filename if fsutils.exists(filename): content_handler = XMLPrefReader(pref=self) error_handler = ErrorHandler() entity_resolver = EntityResolver() dtd_handler = DTDHandler() try: input_file = get_fileptr(filename) input_source = InputSource() input_source.setByteStream(input_file) xml_reader = xml.sax.make_parser() xml_reader.setContentHandler(content_handler) xml_reader.setErrorHandler(error_handler) xml_reader.setEntityResolver(entity_resolver) xml_reader.setDTDHandler(dtd_handler) xml_reader.parse(input_source) input_file.close() except Exception as e: LOG.error('Cannot read preferences from %s %s', filename, e)
Example #2
Source File: recipe-149284.py From code with MIT License | 5 votes |
def filter_rdf (input, output): """filter_rdf(input:file, output:file) Parses the XML input from the input stream, filtering out all elements and attributes that are in the RDF namespace. """ output_gen = saxutils.XMLGenerator(output) parser = sax.make_parser() filter = RDFFilter(parser) filter.setFeature(handler.feature_namespaces, True) filter.setContentHandler(output_gen) filter.setErrorHandler(handler.ErrorHandler()) filter.parse(input)
Example #3
Source File: __init__.py From qpid-python with Apache License 2.0 | 5 votes |
def xml_parse(filename, path=()): source = "file://%s" % os.path.abspath(filename) h = parsers.XMLParser() p = xml.sax.make_parser() p.setContentHandler(h) p.setErrorHandler(ErrorHandler()) p.setEntityResolver(Resolver(path)) p.parse(source) return h.parser.tree
Example #4
Source File: odfmanifest.py From lambda-text-extractor with Apache License 2.0 | 5 votes |
def manifestlist(manifestxml): odhandler = ODFManifestHandler() parser = make_parser() parser.setFeature(handler.feature_namespaces, 1) parser.setContentHandler(odhandler) parser.setErrorHandler(handler.ErrorHandler()) inpsrc = InputSource() if not isinstance(manifestxml, str): manifestxml=manifestxml.decode("utf-8") inpsrc.setByteStream(StringIO(manifestxml)) parser.parse(inpsrc) return odhandler.manifest
Example #5
Source File: odfmanifest.py From lambda-text-extractor with Apache License 2.0 | 5 votes |
def manifestlist(manifestxml): odhandler = ODFManifestHandler() parser = make_parser() parser.setFeature(handler.feature_namespaces, 1) parser.setContentHandler(odhandler) parser.setErrorHandler(handler.ErrorHandler()) inpsrc = InputSource() if not isinstance(manifestxml, str): manifestxml=manifestxml.decode("utf-8") inpsrc.setByteStream(StringIO(manifestxml)) parser.parse(inpsrc) return odhandler.manifest
Example #6
Source File: generic_filters.py From uniconvertor with GNU Affero General Public License v3.0 | 5 votes |
def init_load(self): self.input_source = InputSource() self.input_source.setByteStream(self.fileptr) self.xml_reader = xml.sax.make_parser() self.xml_reader.setContentHandler(self) self.xml_reader.setErrorHandler(handler.ErrorHandler()) self.xml_reader.setEntityResolver(handler.EntityResolver()) self.xml_reader.setDTDHandler(handler.DTDHandler()) self.xml_reader.setFeature(handler.feature_external_ges, False) self.do_load()
Example #7
Source File: pdxf_filters.py From uniconvertor with GNU Affero General Public License v3.0 | 5 votes |
def _build_model(self): content_handler = XMLDocReader(self.presenter) error_handler = ErrorHandler() entity_resolver = EntityResolver() dtd_handler = DTDHandler() try: filename = os.path.join(self.presenter.doc_dir, 'content.xml') handler = open(filename, 'r') lines = float(sum(1 for l in handler)) handler.close() self.file_handler = open(filename, "r") input_source = InputSource() input_source.setByteStream(self.file_handler) content_handler.lines = lines xml_reader = xml.sax.make_parser() xml_reader.setContentHandler(content_handler) xml_reader.setErrorHandler(error_handler) xml_reader.setEntityResolver(entity_resolver) xml_reader.setDTDHandler(dtd_handler) xml_reader.parse(input_source) self.file_handler.close() content_handler.file = None except: errtype, value, traceback = sys.exc_info() msg = 'It seems content.xml is corrupted' + '\n' + value events.emit(events.MESSAGES, msgconst.ERROR, msg) raise IOError(errtype, msg, traceback) self.model = content_handler.model msg = 'Content.xml is parsed successfully' events.emit(events.MESSAGES, msgconst.OK, msg)
Example #8
Source File: opendocument.py From lambda-text-extractor with Apache License 2.0 | 4 votes |
def __loadxmlparts(z, manifest, doc, objectpath): """ Parses a document from its zipfile @param z an instance of zipfile.ZipFile @param manifest Manifest data structured in a dictionary @param doc instance of OpenDocument to feed in @param objectpath unicode string: path to an object """ assert(isinstance(z, zipfile.ZipFile)) assert(type(manifest)==type(dict())) assert(isinstance(doc, OpenDocument)) assert(type(objectpath)==type(u"")) from load import LoadParser from xml.sax import make_parser, handler for xmlfile in (objectpath+u'settings.xml', objectpath+u'meta.xml', objectpath+u'content.xml', objectpath+u'styles.xml'): if xmlfile not in manifest: continue ########################################################## # this one is added to debug the bad behavior with Python2 # which raises exceptions of type SAXParseException from xml.sax._exceptions import SAXParseException ########################################################## try: xmlpart = z.read(xmlfile).decode("utf-8") doc._parsing = xmlfile parser = make_parser() parser.setFeature(handler.feature_namespaces, 1) parser.setFeature(handler.feature_external_ges, 0) parser.setContentHandler(LoadParser(doc)) parser.setErrorHandler(handler.ErrorHandler()) inpsrc = InputSource() ################# # There may be a SAXParseException triggered because of # a missing xmlns prefix like meta, config, etc. # So i add such declarations when needed (GK, 2014/10/21). # Is there any option to prevent xmlns checks by SAX? xmlpart=__fixXmlPart(xmlpart) inpsrc.setByteStream(BytesIO(xmlpart.encode("utf-8"))) parser.parse(inpsrc) del doc._parsing except KeyError as v: pass except SAXParseException: print (u"====== SAX FAILED TO PARSE ==========\n", xmlpart)
Example #9
Source File: opendocument.py From lambda-text-extractor with Apache License 2.0 | 4 votes |
def __loadxmlparts(z, manifest, doc, objectpath): """ Parses a document from its zipfile @param z an instance of zipfile.ZipFile @param manifest Manifest data structured in a dictionary @param doc instance of OpenDocument to feed in @param objectpath unicode string: path to an object """ assert(isinstance(z, zipfile.ZipFile)) assert(type(manifest)==type(dict())) assert(isinstance(doc, OpenDocument)) assert(type(objectpath)==type(u"")) from load import LoadParser from xml.sax import make_parser, handler for xmlfile in (objectpath+u'settings.xml', objectpath+u'meta.xml', objectpath+u'content.xml', objectpath+u'styles.xml'): if xmlfile not in manifest: continue ########################################################## # this one is added to debug the bad behavior with Python2 # which raises exceptions of type SAXParseException from xml.sax._exceptions import SAXParseException ########################################################## try: xmlpart = z.read(xmlfile).decode("utf-8") doc._parsing = xmlfile parser = make_parser() parser.setFeature(handler.feature_namespaces, 1) parser.setFeature(handler.feature_external_ges, 0) parser.setContentHandler(LoadParser(doc)) parser.setErrorHandler(handler.ErrorHandler()) inpsrc = InputSource() ################# # There may be a SAXParseException triggered because of # a missing xmlns prefix like meta, config, etc. # So i add such declarations when needed (GK, 2014/10/21). # Is there any option to prevent xmlns checks by SAX? xmlpart=__fixXmlPart(xmlpart) inpsrc.setByteStream(BytesIO(xmlpart.encode("utf-8"))) parser.parse(inpsrc) del doc._parsing except KeyError as v: pass except SAXParseException: print (u"====== SAX FAILED TO PARSE ==========\n", xmlpart)