我们从Python开源项目中，提取了以下42个代码示例，用于说明如何使用xml.sax.saxutils.unescape()。
def __init__(self, xml_string): self.xml_unescape_table = {} self.xml_map = {} try: self.xml = minidom.parseString(xml_string) except: print xml_string self.xml_unescape_tabl = get_xml_unescape_table() self.xml_map = get_xml_unescape_map() for k, v in self.xml_map.items(): xml_string = xml_string.replace(k, v) self.xml = minidom.parseString(xml_string) self.bucket = get_tag_text(self.xml, 'Bucket', convert_to_bool = False) self.object = get_tag_text(self.xml, 'Key', convert_to_bool = False) if self.xml_map: for k, v in self.xml_map.items(): self.object = self.object.replace(v, k) self.object = unescape(self.object, self.xml_unescape_table) self.key = get_tag_text(self.xml, 'Key', convert_to_bool = False) self.upload_id = get_tag_text(self.xml, 'UploadId') self.marker = get_tag_text(self.xml, 'Marker', convert_to_bool = False)
def wrap_field(field): """ Given a field, detect if it has special characters <, > or & and if so wrap it in a CDATA field. """ if not isinstance(field, str): return field if html_chars.search(field): return '<![CDATA[' + field + ']]>' else: # If there's already escaped data like &, I want to unescape it # first, so I can re-escape *everything* field = saxutils.unescape(field) return saxutils.escape(field)
def test_single_download(self): self.set_http_response(status_code=200) response = self.service_connection.get_log_file('db1', 'foo.log') self.assertTrue(isinstance(response, LogFileObject)) self.assertEqual(response.marker, '0:4485') self.assertEqual(response.dbinstance_id, 'db1') self.assertEqual(response.log_filename, 'foo.log') self.assertEqual(response.data, saxutils.unescape(self.logfile_sample)) self.assert_request_parameters({ 'Action': 'DownloadDBLogFilePortion', 'DBInstanceIdentifier': 'db1', 'LogFileName': 'foo.log', }, ignore_params_values=['Version'])
def append_skipped(self, report): """Append xml reports with skipped TC. Args: report(dict): Skipped report """ self.class_logger.info("Appending XML report with skip.") # filename, lineno, skipreason = report['longrepr'] # self.class_logger.debug("Received longrepr: {0}".format(xml_unescape(report['longrepr']))) longrepr = xml_unescape(report['longrepr']) # TODO: fixed bug with longrepr crashing skipreason = get_skipped_reason(report['longrepr']) self.append(self.Junit.skipped("%s" % longrepr, # pylint: disable=no-member type="pytest.skip", message=skipreason)) # self.append(self.Junit.skipped("%s:%s: %s" % longrepr, type="pytest.skip", message=skipreason)) self.skipped += 1
def GetAttributeValue(attr, extract=True): """ Function that extracts data from a tree node @param attr: tree node containing data to extract @param extract: attr is a tree node or not @return: data extracted as string """ if not extract: return attr if len(attr.childNodes) == 1: return unicode(unescape(attr.childNodes[0].data)) else: # content is a CDATA text = u'' for node in attr.childNodes: if not (node.nodeName == "#text" and node.data.strip() == u''): text += unicode(unescape(node.data)) return text
def SendReport(self, report): """Emails an exception report. Args: report: A string containing the report to send. """ subject = ('Daily exception report for app "%s", major version "%s"' % (self.app_id, self.major_version)) report_text = saxutils.unescape(re.sub('<[^>]+>', '', report)) mail_args = { 'sender': self.sender, 'subject': subject, 'body': report_text, 'html': report, } if self.to: mail_args['to'] = self.to self.send_mail(**mail_args) else: self.send_mail_to_admins(**mail_args)
def quiz_func(nick,match,target): if 'quiz' in mb.responses: mb.tell("weak! the answer was "+mb.responses['quiz']['param']['answer'],target) del mb.responses['quiz'] req=urllib2.Request('http://jservice.io/api/random') response=urllib2.urlopen(req).read().decode('utf-8') data=choice(json.loads(response)) answer=re.sub(html_tags,"",data['answer']) answer=answer.replace(r"\'","'") answer=unescape(answer) mb.tell("Category: {}".format(data['category']['title']),target) mb.tell(re.sub(html_tags,"",unescape(data['question']))+" Answer: "+re.sub("[a-zA-Z0-9]","*",answer),target) pattern=re.compile("^(?:murderb[o0]t|mb)?[,\s:!]*"+re.escape(answer)+"\s*$",flags=re.IGNORECASE) answer_response={'func':quiz_answer,'pattern':pattern,'nick':".*",'param':{'answer':answer},'target':target} mb.responses['quiz']=answer_response print(data['question']) print(data['answer']) return
def s2i(keys, inp, out): for key in keys: ind = inp.find(key) if ind: typ = TYPES[key] if ind.contents: val = ind.contents[0].strip() try: if typ == B: res = (val == 'true') elif typ == S: res = str(unescape(val)) elif typ == I: res = int(round(float(c2p(str(val))))) else: res = float(c2p(str(val))) out.__setattr__(key, res) except: pass
def __init__(self, *args, **kwargs): # The inicialization is taken from rst2pdf.flowables.Heading hstyle = kwargs.pop('hstyle') level = 0 text = kwargs.pop('text') self.snum = kwargs.pop('snum') self.parent_id= kwargs.pop('parent_id') #self.stext = Heading.__init__(self,text,hstyle,level=level, parent_id=self.parent_id) # Cleanup title text #self.stext = re.sub(r'<[^>]*?>', '', unescape(self.stext)) #self.stext = self.stext.strip() # Stuff needed for the outline entry MyImage.__init__(self, *args, **kwargs)
def getWeatherReport(self,output): self.loadinginprogress = False trans = { 'ß' : 'ß' , 'ä' : 'ä' , 'ö' : 'ö' , 'ü' : 'ü' , 'Ä' : 'Ä', 'Ö' : 'Ö' , 'Ü' : 'Ü'} output= util.unescape(output,trans) if self.land == "de": startpos = output.find('<!-- Anfang msg_Box Content -->') endpos = output.find('<!-- Ende msg_Box Content -->') bereich = output[startpos:endpos] bereich = bereich.replace('<strong>', '\n') else: startpos = output.find('<div class="content"') endpos = output.find('</div>', startpos) bereich = output[startpos:endpos] bereich = sub('<br\s*/?>',"\n",bereich) bereich = sub('<[^>]*>',"",bereich) bereich = sub('Fronten- und Isobarenkarte.*',"",bereich) bereich = bereich.strip() bereich = sub("\n[\s\n]+", "\n\n", bereich) f = open(self.reportfile, "w") f.write("%s" % bereich) f.close() self.session.open(Console,_("Warnlagebericht"),["cat %s" % self.reportfile])
def HTMLUnescape(text): return unescape(text, Editor.getHtmlUnescapeTable())
def list(self): cl = [] pl = [] for c in self.content_list: key = c.key if self.xml_map: for k, v in self.xml_map.items(): key = key.replace(v, k) key = unescape(key, self.xml_unescape_table) cl.append((key, c.last_modified, c.etag, c.size, c.owner.id, c.owner.display_name, c.storage_class)) for p in self.prefix_list: pl.append(p) return (cl, pl)
def list(self): cl = [] pl = [] for c in self.content_list: key = c.key if self.xml_map: for k, v in self.xml_map.items(): key = key.replace(v, k) key = unescape(key, self.xml_unescape_table) cl.append((key, c.upload_id, c.init_time)) for p in self.prefix_list: pl.append(p) return (cl, pl)
def replace_entity(match): """Return the character corresponding to an HTML entity.""" number = match.group(2) if number: hex = match.group(1) is not None result = chr(int(number, 16 if hex else 10)) else: entity = match.group(3) result = unescape(entity, html.entities.html5) return result
def unescape(string): """ >>> unescape("one <![CDATA[two ]]>three") 'one two three' """ result = list() for index, data in enumerate(cdata.split(string)): if index % 3 != 2: data = _unescape(data, {" ": " "}) result.append(data) return "".join(result)
def unescape_html(s): h = html_parser.HTMLParser() s = h.unescape(s) s = unquote_plus(s) return unescape(s, HTML_UNESCAPE_TABLE)
def clean_filename(s, minimal_change=False): """ Sanitize a string to be used as a filename. If minimal_change is set to true, then we only strip the bare minimum of characters that are problematic for filesystems (namely, ':', '/' and '\x00', '\n'). """ # First, deal with URL encoded strings h = html_parser.HTMLParser() s = h.unescape(s) s = unquote_plus(s) # Strip forbidden characters s = ( s.replace(':', '-') .replace('/', '-') .replace('\x00', '-') .replace('\n', '') ) if minimal_change: return s s = s.replace('(', '').replace(')', '') s = s.rstrip('.') # Remove excess of trailing dots s = s.strip().replace(' ', '_') valid_chars = '-_.()%s%s' % (string.ascii_letters, string.digits) return ''.join(c for c in s if c in valid_chars)
def unescape(self, text): return unescape(text, html_unescape_table)
def get(self, unescape = False): ele_tree = ElementTree.Element('items') for item in self.items: ele_tree.append(item.getXMLElement()) res = ElementTree.tostring(ele_tree) #! ????encoding='utf-8'????????????????alfred???? if unescape: return saxutils.unescape(res) return res
def get_unescaped_data(xmlNode): return saxutils.unescape(xmlNode.childNodes[0].data)
def get_data(xmlnode): data = [] for childnode in xmlnode.childNodes: if childnode.nodeType == Node.ELEMENT_NODE: data.append(get_data(childnode)) elif childnode.nodeType == Node.TEXT_NODE: data.append(saxutils.unescape(childnode.data)) return u''.join(data)
def append_error(self, report, when=""): """Append xml report with error (in case TC failed on setup or teardown). Args: report(dict): Error report when(str): Error occurance stage (setup|call|teardown) """ self.class_logger.info("Appending XML report with error.") if 'longrepr' in list(report.keys()): longrepr = xml_unescape(report['longrepr']) if self.fail_traceback is not None: failure_reason = None if len(self.tests[-1]) > 0: failure_reason = self.tests[-1].pop() if self.update is not None and len(self.tests[-1]) > 0: self.tests[-1].pop() try: self.tests[-1].pop() except IndexError: pass self.append( self.Junit.error(longrepr, # pylint: disable=no-member message="Test error on %s and Test failure" % (when, ))) if hasattr(failure_reason.attr, "message") and failure_reason.attr.message == "Failure Reason": self.tests[-1].append(failure_reason) self.tests[-1][0].extend("\n" + "-" * 80 + "\nTest Case Failure\n" + "-" * 80 + "\n") self.tests[-1][0].extend(self.fail_traceback) else: self.append( self.Junit.error(longrepr, # pylint: disable=no-member message="Test error on %s" % (when, ))) self.errors += 1 self.failed += 1
def append_xfail(self, report): """Append xml report with xfailed TC. Args: report(dict): XFail report """ self.class_logger.info("Appending XML report with xfail.") self.append( self.Junit.skipped(str(xml_unescape(report['keywords']['xfail'])), # pylint: disable=no-member message="expected test failure"))
def append_failure(self, report): """Append xml report with failed TC. Args: report(dict): Failure report """ self.class_logger.info("Appending XML report with fail.") report['sections'] = [xml_unescape(section) for section in report['sections']] # pylint: disable=no-member sec = dict(report['sections']) self.fail_traceback = self.Junit.failure(message="Test failure") # pylint: disable=no-member # Removing BASH escape symbols (decolorizing) # longrepr = xml_unescape(re_sub(r"\x1b.*?m", "", report['longrepr'])) longrepr = xml_unescape(report['longrepr']) # TODO: Change str to encode for unicode text try: self.fail_traceback.append(str(longrepr)) except UnicodeEncodeError as err: self.fail_traceback.append(ud.normalize('NFKD', longrepr)) self.class_logger.warning("Unicode data in traceback: %s" % (err, )) self.append(self.fail_traceback) for name in ("out", "err"): content = sec.get("Captured std{0}".format(name)) if content: tag = getattr(self.Junit, "system-{0}".format(name)) self.append(tag(content)) self.failed += 1
def _transform_page(self, content): content = unescape(content) for placeholder, buffer in self.placeholder_dict.items(): new_text = ", ".join([placeholder] + buffer) content = content.replace(placeholder, new_text) return content
def unquote(txt): from xml.sax.saxutils import unescape return unescape(txt, {"'": "'", """: '"'})
def render_resource(path, **context): """ Render static resource using provided context. Returns: django.utils.safestring.SafeText """ html = Template(resource_string(path)) return html_parser.unescape( html.render(Context(context)) )
def render_template(template_name, **context): """ Render static resource using provided context. Returns: django.utils.safestring.SafeText """ template_dirs = [os.path.join(os.path.dirname(__file__), 'static/html')] engine = Engine(dirs=template_dirs, debug=True) html = engine.get_template(template_name) return html_parser.unescape( html.render(Context(context)) )
def remove_escaping(text): """ Clean text from special `escape` symbols. Reference: https://wiki.python.org/moin/EscapingHtml. """ html_unescape_table = { "&": "&", """: '"', "&#39;": "'", "'": "'", ">": ">", "<": "<" } return unescape(text, html_unescape_table)
def unescape_xml(content): """ Escapes XML content into it's regular string value """ if SAX_UNESCAPE: return unescape(content) return HTMLParser().unescape(content)
def PrepareString(str): return unescape(str, {"'": "'", "'" : "'", "'" : "'", """: '"'})
def xml_unescape(string): """ Strip and XML-unescape 'string'. """ return unescape(string.strip())
def upload_xml(self): start_time = time.time() f = open(self.file_name) domains = [domain for domain in f] f.close() domain_name = self.file_name + '_xml' rule_set = self.rule_name + '_XML' file_dom = (xmlStart % {'expGUID': str(uuid4()).upper()}) for url in domains: file_dom += ('<fpc4:Str dt:dt="string">' + (url.replace('&', '&')) + '</fpc4:Str>') file_dom += (xmlEnd % unescape(domain_name)) dom = win32com.client.Dispatch('Msxml2.DOMDocument.3.0') dom.async = False dom.loadXML(file_dom) isa_array.RuleElements.DomainNameSets.Import(dom, 0) rule = isa_array.ArrayPolicy.PolicyRules.Item(rule_set) rule_sets = rule.AccessProperties.DestinationDomainNameSets rule_sets.Add(domain_name, 0) rule.Save() return time.time() - start_time
def unescape(value, entities=None): _ent = unescape_entities if entities is not None: _ent = _ent.copy() _ent.update(entities) return _unescape(value, entities) # utf-8 is hardcoded on OFS.PropertySheets as the expected # encoding properties will be stored in. Optimally, we should use the # same encoding as the 'default_encoding' property that is used for # the ZMI.
def __init__(self, text, style, bulletText=None, caseSensitive=1, level=0, snum=None, parent_id=None, node=None, section_header_depth=2): # Issue 114: need to convert "&" to "&" and such. # Issue 140: need to make it plain text self.stext=re.sub(r'<[^>]*?>', '', unescape(text)) self.stext = self.stext.strip() self.level = int(level) self.snum = snum self.parent_id=parent_id self.node=node self.section_header_depth = section_header_depth Paragraph.__init__(self, text, style, bulletText)
def quote(s): """Quotes a string in such a way that it is usable inside XPath expressions.""" return unescape(quoteattr(s))
def _parse_menu_tag(self, item): name = None untranslated_name = None query = None icon = None only_unallocated = False dont_display = False flags = [] subcategories = [] sortmode = SortMethods.BY_ALPHABET item_limit = 0 for element in item.getchildren(): # ignore inline translations, we use gettext for this if (element.tag == "Name" and '{http://www.w3.org/XML/1998/namespace}lang' in element.attrib): continue if element.tag == "Name": untranslated_name = element.text # gettext/xml writes stuff from software-center.menu # out into the pot as escaped xml, so we need to escape # the name first, get the translation and unscape it again escaped_name = xml_escape(untranslated_name) name = xml_unescape(gettext.gettext(escaped_name)) elif element.tag == "SCIcon": icon = element.text elif element.tag == 'Flags': flags = self._parse_flags_tag(element) elif element.tag == "Directory": l = self._parse_directory_tag(element) if l: (untranslated_name, name, gettext_domain, icon) = l elif element.tag == "Include": query = self._parse_include_tag(element) elif element.tag == "OnlyUnallocated": only_unallocated = True elif element.tag == "SCDontDisplay": dont_display = True elif element.tag == "SCSortMode": sortmode = int(element.text) if not self._verify_supported_sort_mode(sortmode): return None elif element.tag == "SCItemLimit": item_limit = int(element.text) elif element.tag == "Menu": subcat = self._parse_menu_tag(element) if subcat: subcategories.append(subcat) else: LOG.warn("UNHANDLED tag in _parse_menu_tag: %s" % element.tag) if untranslated_name and query: return Category(untranslated_name, name, icon, query, only_unallocated, dont_display, flags, subcategories, sortmode, item_limit) else: LOG.warn("UNHANDLED entry: %s %s %s %s" % (name, untranslated_name, icon, query)) return None
def hauptmenu(self,output): self.loadinginprogress = False trans = { 'ß' : 'ß' , 'ä' : 'ä' , 'ö' : 'ö' , 'ü' : 'ü' , 'Ä' : 'Ä', 'Ö' : 'Ö' , 'Ü' : 'Ü'} output= util.unescape(output,trans) if self.land == "de": startpos = output.find('<div id="navigation">') endpos = output.find('<li><a class="section-link" title="Unwetterwarnungen Europa"', startpos) bereich = output[startpos:endpos] a = findall(r'href=(?P<text>.*?)</a>',bereich) for x in a: x = x.replace('">',"#").replace('"',"").split('#') if not len(x) > 1: break if x[0] == "index.html": continue name = x[1] link = self.baseurl + x[0] self.menueintrag.append(name) self.link.append(link) else: self.menueintrag.append("Lagebericht") self.link.append(self.weatherreporturl) startpos = output.find('</ul><ul><ul id="level_3">') endpos = output.find('</ul></ul>', startpos) bereich = output[startpos:endpos] a = findall(r'href=(?P<text>.*?)</a>',bereich) for x in a: x = x.replace('">',"#").replace('"',"").split('#') if not len(x) > 1: break if x[0] == "index.html": continue name = x[1] link = self.baseurl + x[0] self.menueintrag.append(name) self.link.append(link) self["statuslabel"].setText("") self["hmenu"].l.setList(self.menueintrag) self["hmenu"].instance.moveSelectionTo(0) self.showThumbLand()
def addTimerByEventID(self, param): print "[WebComponents.Timer] addTimerByEventID", param if param['sRef'] is None: return ( False, _("Missing Parameter: sRef") ) if param['eventid'] is None: return ( False, _("Missing Parameter: eventid") ) justplay = False if param['justplay'] is not None: if param['justplay'] == "1": justplay = True if not justplay and not config.misc.recording_allowed.value: return (False, _("Recording is currently disabled!")) location = preferredTimerPath() if 'dirname' in param and param['dirname']: location = param['dirname'] tags = [] if 'tags' in param and param['tags']: tags = unescape(param['tags']).split(' ') epgcache = eEPGCache.getInstance() event = epgcache.lookupEventId(eServiceReference(param['sRef']), int(param['eventid'])) if event is None: return ( False, _("EventId not found") ) (begin, end, name, description, eit) = parseEvent(event) timer = RecordTimerEntry(ServiceReference(param['sRef']), begin , end, name, description, eit, False, justplay, AFTEREVENT.AUTO, dirname=location, tags=tags) conflicts = self.recordtimer.record(timer) if conflicts is None: return ( True, _("Timer '%s' added") %(timer.name) ) else: print "[WebComponents.Timer] editTimer conflicting Timers: %s" %(conflicts) msg = "" for timer in conflicts: msg = "%s / %s" %(msg, timer.name) return (False, _("Conflicting Timer(s) detected! %s") %(msg))
