def parse(self):
target = GetXmlAttrs()
parser = XMLParser(target=target)
if self.config:
parser.feed(self.config)
return target
def load(file, env): cXMLParser = CXMLParser(env) parser = XMLParser(target=cXMLParser) f = open(file, 'r+') read_data = f.read(); f.close() parser.feed(read_data) parser.close() return cXMLParser.env
def build(self, root=None):
if root is None:
was_root = True
root = TreeBuilder()
else:
was_root = False
root.start(self.tagname(), self.attrs())
for i, child in enumerate(self.children):
if isinstance(child, HTMLBuilder):
child.build(root=root)
else:
if i in self._formatted:
try:
proxy = TreeProxy(root)
parser = XMLParser(html=True, target=proxy)
parser.feed(child)
proxy.cleanup()
except Exception as e:
print("Bad formatting", e)
root.data(str(child))
else:
root.data(str(child))
root.end(self.tagname())
if was_root:
root = root.close()
return str(tostring(root, method="html").decode('utf-8'))
def get_max_depth(exampleXml):
target = MaxDepth()
parser = XMLParser(target=target)
parser.feed(exampleXml)
depth = parser.close()
return depth
def getQueryResult(query,detailedLog=True):
parser = XMLParser(target=ProcessCSQueryResult())
queryAnswerXML = urllib.urlopen(query).read()
if detailedLog:
log_CSQuery(queryAnswerXML)
parser.feed(queryAnswerXML)
return parser.close()
def getQueryResult(query, detailedLog=True):
parser = XMLParser(target=ProcessCSQueryResult())
queryAnswerXML = urllib.urlopen(query).read()
if detailedLog:
log_CSQuery(queryAnswerXML)
parser.feed(queryAnswerXML)
return parser.close()
def from_dataframe(cls, df, **kwargs):
if isinstance(df, pandas.DataFrame):
return xml.etree.ElementTree.fromstring(
df.to_html(**kwargs),
parser=XMLParser(target=TreeBuilder(element_factory=cls)))
elif isinstance(df, pandas.io.formats.style.Styler):
render = df.render()
render = re.sub(r"colspan=([1234567890]*)>", "colspan=\"\g<1>\">",
render, 0)
try:
return xml.etree.ElementTree.fromstring(
f"<div>{render}</div>",
parser=XMLParser(target=TreeBuilder(element_factory=cls)))
except Exception as parse_err:
if type(parse_err).__name__ == 'ParseError':
x = Elem('div')
x << xml.etree.ElementTree.fromstring(
df.data.to_html(**kwargs),
parser=XMLParser(target=TreeBuilder(
element_factory=cls)))
x << Elem('pre', text=render)
x << Elem('pre', text=str(parse_err))
return x
else:
raise
def Parse(self, data):
if len(data) < sizeof(CryXMLBHeader):
raise ValueError(
"File is not a binary XML file (file size is too small).")
self._data = data
self._header = CryXMLBHeader.from_buffer(data, 0)
# TODO: actually do header validation - see references
if self._header.signature != b"CryXmlB":
if self._header.signature.startswith(b"<"):
# try parsing as a normal xml file
parser = XMLParser(target=self.target)
parser.feed(self._data)
raise _StandardXmlFile()
raise ParseError("Invalid CryXmlB Signature")
self._attributes = [
self._read_attribute(i)
for i in range(self._header.attributes_count)
]
self._child_indices = [
self._read_child_index(i)
for i in range(self._header.child_table_count)
]
self._nodes = [
self._read_node(i) for i in range(self._header.node_count)
]
root_node = self._read_node(0)
assert root_node.parent_index == CRYXML_NO_PARENT
self._iter_parse_nodes(root_node)
def get_ebelge_users():
parser = XMLParser(target=EbelgeUsers())
parser.feed(
frappe.read_file(
frappe.get_site_path("private", "files", "KullaniciListesiXml",
"newUserPkList.xml")))
return parser.close()
def __init__(self, xml_encode):
super().__init__()
parser = XMLParser(target=MaxDepth())
pepe = parser.feed(xml_encode)
parser.close()
print(self.resul_property)
self.xml_encode = xml_encode
def __init__(self,
html=0,
target=None,
encoding=None,
forbid_dtd=False,
forbid_entities=True,
forbid_external=True):
if PY26 or PY31:
_XMLParser.__init__(self, html, target)
else:
# Python 2.x old style class
_XMLParser.__init__(self, html, target, encoding)
self.forbid_dtd = forbid_dtd
self.forbid_entities = forbid_entities
self.forbid_external = forbid_external
if PY3 and not PY31:
parser = self.parser
else:
parser = self._parser
if self.forbid_dtd:
parser.StartDoctypeDeclHandler = self.defused_start_doctype_decl
if self.forbid_entities:
parser.EntityDeclHandler = self.defused_entity_decl
parser.UnparsedEntityDeclHandler = self.defused_unparsed_entity_decl
if self.forbid_external:
parser.ExternalEntityRefHandler = self.defused_external_entity_ref_handler
def build(self, root=None):
if root is None:
was_root = True
root = TreeBuilder()
else:
was_root = False
root.start(self.tagname(), self.attrs())
for i, child in enumerate(self.children):
if isinstance(child, HTMLBuilder):
child.build(root=root)
else:
if i in self._formatted:
try:
proxy = TreeProxy(root)
parser = XMLParser(html=True, target=proxy)
parser.feed(child)
proxy.cleanup()
except Exception as e:
print("Bad formatting", e)
root.data(str(child))
else:
root.data(str(child))
root.end(self.tagname())
if was_root:
root = root.close()
return str(tostring(root, method="html").decode('utf-8'))
def parse(self, fIn, oHolder):
"""Parse XML file into the card set holder"""
oParser = XMLParser(target=self._cState(oHolder))
try:
for sLine in fIn:
oParser.feed(sLine)
except ParseError as oExp:
raise IOError('Not an valid XML file') from oExp
def new_parsetree_from_xml(xml):
# For some reason this does not work with cElementTree.XMLBuilder ...
from xml.etree.ElementTree import XMLParser
from zim.formats import ParseTree
builder = XMLParser()
builder.feed(xml)
root = builder.close()
return ParseTree(root)
def parse(self, fIn, oHolder):
"""Parse XML file into the card set holder"""
oParser = XMLParser(target=self._cState(oHolder))
try:
for sLine in fIn:
oParser.feed(sLine)
except ParseError, oExp:
raise IOError('Not an XML file: %s' % oExp)
def __init__(self, stream, *pos, **kw):
self._stream = stream
self._pending = deque()
builder = _QueueBuilder(self._pending)
self._parser = XMLParser(*pos, target=builder, **kw)
self._builders = [TreeBuilder()]
[method, pos, kw] = self._read()
self.element = getattr(self._builders[-1], method)(*pos, **kw)
def HTMLOfENML(text, resources={}):
target = HTMLCreatorTarget(resources)
parser = XMLParser(target=target)
parser.feed(text)
parser.close()
return tostring(target.root, encoding='utf8', method='html')
def _parse_xml(self, xml_data): """ Parse the xml into a python dictionary """ parser = XMLParser() tree = parser.feed(xml_data) root = parser.close() data_dict = XmlDictConfig(root) return data_dict
def runTest(self):
'''Test OldParseTreeBuilder class'''
# - Test \n before and after h / p / pre
# - Test break line into lines
input = '''\
<?xml version='1.0' encoding='utf-8'?>
<zim-tree>
foo<h level="1">bar</h>baz
dus<pre>ja</pre>hmm
<h level="2">foo
</h>bar
dus ja <emphasis>hmm
dus ja
</emphasis>grrr
<strong>foo
bar
</strong>
<strike></strike><emphasis> </emphasis>.
</zim-tree>'''
wanted = '''\
<?xml version='1.0' encoding='utf-8'?>
<zim-tree>
foo
<h level="1">bar</h>
baz
dus
<pre>ja
</pre>hmm
<h level="2">foo</h>
bar
dus ja <emphasis>hmm</emphasis>
<emphasis>dus ja</emphasis>
grrr
<strong>foo</strong>
<strong>bar</strong>
.
</zim-tree>'''
from xml.etree.ElementTree import XMLParser
builder = XMLParser(target=OldParseTreeBuilder())
builder.feed(input)
root = builder.close()
tree = ParseTree(root)
self.assertEqual(tree.tostring(), wanted)
def __init__(self,
destPacketList,
parse_context_type=structinfo.ParseContext):
#self.interface = interface
self.destination = destPacketList
self.cur_proto = None
self.parse_context_type = parse_context_type
self.parse_context = None
self.parser = XMLParser(target=self)
def mm2otl(*arg, **kwarg):
fname = arg[0][0]
file = codecs.open(fname, 'r', encoding='utf-8')
filelines = file.readlines()
outline = Outline()
parser = XMLParser(target=outline, encoding='utf-8')
parser.feed(filelines[0].encode('utf-8'))
parser.close()
def main(name):
with open(name, "r") as f:
parser = XMLParser()
for line in f:
parser.feed(line)
xml = XMLTree(parser.close(), False)
M.run(xml.get("files"), xml.get("structure"), xml.get("pages"))
def init(self, args):
(image_draw_mode, image, image_draw, image_size, background) = args
image_draw_mode = "RGBA" if image_draw_mode == None else image_draw_mode
if image != None: self.setimage(image)
image_draw = ImageDraw.Draw(
self.im, image_draw_mode) if image_draw == None else image_draw
self.imagesize = (self.im.width,
self.im.height) if image_size == None else image_size
self.target = SvgPainter(image_draw, self.imagesize, background)
self.parser = XMLParser(target=self.target)
def __init__(self, component, config):
asyncore.dispatcher_with_send.__init__(self)
self.config = config
self.parser = XMLParser(target=self)
self.mapping = getOnMapping(self)
self.component = component
self.create_socket(socket.AF_INET, socket.SOCK_STREAM)
self.connect((self.config["xmpp_host"], self.config["xmpp_port"]))
def fromStream(cls, source):
parser = XMLParser(target=WebDAVContentHandler())
try:
while 1:
data = source.read(65536)
if not data:
break
parser.feed(data)
except XMLParseError, e:
raise ValueError(e)
def fromStream(cls, source):
parser = XMLParser(target=WebDAVContentHandler())
try:
while 1:
data = source.read(65536)
if not data:
break
parser.feed(data)
except XMLParseError, e:
raise ValueError(e)
def kplist_parse(plist):
"""Parse a kernel-style property list."""
try:
builder = _KPlistBuilder()
parser = XMLParser(target=builder)
parser.feed(plist)
return parser.close()
except Exception as e:
print(e)
return None
def __init__(self):
f = open(self.config_file)
xml_src = f.read()
f.close()
parser = XMLParser()
parser.feed(xml_src)
self.config_tree = parser.close()
self.parse()
def read(filename):
""" Read an atlas from a XML file.
"""
builder = TreeBuilder(filename)
parser = XMLParser(target=builder)
data = open(filename).read()
parser.feed(data)
return parser.close()
def compare_vtk(vtk1,
vtk2,
absolute=1.2e-7,
relative=1e-2,
zeroValueThreshold={},
verbose=True):
""" Take two vtk files and fuzzy compare them. Returns an exit key as return value.
:param vtk1: The filename of the vtk files to compare
:type vtk1: string
:param vtk2: The filename of the vtk files to compare
:type vtk2: string
:param absolute: The epsilon used for comparing numbers with an absolute criterion
:type absolute: float
:param relative: The epsilon used for comparing numbers with an relative criterion
:type relative: float
:param zeroValueThreshold: A dictionary of parameter value pairs that set the threshold under
which a number is treated as zero for a certain parameter. Use this parameter if
you have to avoid comparisons of very small numbers for a certain parameter.
:type zeroValueThreshold: dict
:param verbose: If the script should produce informative output. Enabled by default as the details
give the tester a lot more information on why tests fail.
:type verbose: bool
"""
# construct element tree from vtk file
root1 = ET.parse(vtk1, parser=XMLParser(target=VTKTreeBuilder())).getroot()
root2 = ET.parse(vtk2, parser=XMLParser(target=VTKTreeBuilder())).getroot()
# sort the vtk file in case nodes appear in different positions
# e.g. because of minor changes in the output code
sortedroot1 = sort_vtk(root1)
sortedroot2 = sort_vtk(root2)
if verbose:
print("Comparing {} and {}".format(vtk1, vtk2))
print(
"...with a maximum relative error of {} and a maximum absolute error of {}*p_max, where p_max is highest absolute parameter value."
.format(relative, absolute))
# sort the vtk file so that the comparison is independent of the
# index numbering (coming e.g. from different grid managers)
sortedroot1, sortedroot2 = sort_vtk_by_coordinates(sortedroot1,
sortedroot2, verbose)
# do the fuzzy compare
if is_fuzzy_equal_node(sortedroot1, sortedroot2, absolute, relative,
zeroValueThreshold, verbose):
return 0
else:
return 1
def get_tree(xml_string):
"""
Get the xml tree associated to an xml string
:param request:
- string
:return:
"""
parser = XMLParser(target=MyParser())
parser.feed(xml_string)
tree = parser.close()
return tree
def makeparser():
"""
Returns an XML parser that knows about a few non-standard XML
entities. If your XML source uses other non-standard XML
entities, add these to ENTITIES above.
"""
parser = XMLParser()
parser.parser.UseForeignDTD(True)
for k in ENTITIES:
parser.entity[k] = ENTITIES[k]
return parser
def load(self, path):
"""
"""
own_xml_parser = CorpusInterTASSXMLParser()
xml_parser = XMLParser(target=own_xml_parser)
with open(path, encoding=self.__encoding) as corpus_file:
for line in corpus_file:
xml_parser.feed(line)
if own_xml_parser.full_doc:
raw_tweet = own_xml_parser.doc
self.__add_document(raw_tweet)
def find_depth(chaine):
target = MaxDepth()
parser = XMLParser(target=target)
exampleXml = """<feed xml:lang='en'>
<title>HackerRank</title>
<subtitle lang='en'>Programming challenges</subtitle>
<link rel='alternate' type='text/html' href='http://hackerrank.com/'/>
<updated>2013-12-25T12:00:00</updated>
</feed>"""
parser.feed(chaine)
print(parser.close()-1)
def main():
N = input()
lines = []
for n in xrange(N):
line = raw_input()
lines.append(line)
parser = XMLParser(target=MaxDepth())
parser.feed("\n".join(lines))
print (parser.close() - 1)
def __init__(self, config_file=None):
if config_file:
self.config_file = config_file
f = open(self.config_file)
xml_src = f.read()
f.close()
parser = XMLParser()
parser.feed(xml_src)
self.config_tree = parser.close()
self.parse()
def from_xml(xml):
"""
Deserialize from a XML string.
:param: xml string
:rtype: object tree from XML string
"""
handler = XMLHandler()
parser = XMLParser(target=handler)
parser.feed(xml)
parser.close()
return handler.root
def __init__(self, config_file=None): if config_file: self.config_file = config_file f = open(self.config_file) xml_src = f.read() f.close() parser = XMLParser() parser.feed(xml_src) self.config_tree = parser.close() self.parse()
def __init__(self, conf):
f = open(conf.uwsgifile)
logging.basicConfig(level=conf.debuglevel)
self.log = logging
xml_src = f.read()
f.close()
parser = XMLParser()
parser.feed(xml_src)
self.config_tree = parser.close()
self.parse()
def main():
if 1 < len(sys.argv): # .xml file path in $1 argument, else use /dev/stdin
path = sys.argv[1]
text = open(path).read()
else:
text = "\n".join(sys.stdin.readlines())
ntg = sys.argv[2] if 2 < len(sys.argv) else None
parser = XMLParser(target=_Parser_xml(ntg))
text = re.sub('\\sxmlns="[^"]+"', '', text, count=1)
parser.feed(text)
parser.close()
def main():
init()
log.info("Parsing '%s'..." % os.path.basename(conf['source_file']))
stopwatch_set()
target = CustomParser()
parser = XMLParser(target=target)
parser.feed(open(conf['source_file']).read())
log.info('')
totals = 'Total: posts: {post}; pages: {page}; comments: {comment}'
log.info(totals.format(**stats))
log.info('Elapsed time: %s s' % stopwatch_get())
def parse(self, source=None, parser=None):
try:
if not parser:
parser = XMLParser(target=TreeBuilder())
while 1:
data = self.mergeScreenConfigs()
if not data:
break
parser.feed(data)
return parser.close()
# self._root = parser.close()
# return self._root
except:
pass
def parse(self, source=None, parser=None):
try:
if not parser:
parser = XMLParser(target=TreeBuilder())
while 1:
data = self.mergeScreenConfigs()
if not data:
break
parser.feed(data)
return parser.close()
# self._root = parser.close()
# return self._root
except:
pass
def main():
super_concat = False
options, args = interface()
xml = ElementTree().parse(options.input, parser=XMLParser(target=MyTreeBuilder()))
# delete the older subs. models from the xml file
for node in ['HKYModel','siteModel']:
xml = delete_node(xml, node, 1)
if super_concat:
xml = delete_node(xml, 'treeLikehood', 1)
# delete the kappa and frequency parameters in 'operators'
for parameter in ['kappa', 'frequencies']:
xml = delete_children_from_node(xml, 'operators', parameter)
xml = delete_children_from_node(xml, 'prior', parameter, 2)
xml = delete_children_from_log_node(xml, 'log', parameter)
# jettison some comments
xml = comment_remover(xml, ['HKY substitution model','site model'])
# get our subs model information
sub_models_from_modeltest = {line.strip().split('\t')[0]:line.strip().split('\t')[1].split('-')[1]
for line in open(options.subs, 'rU')}
model_names, site_names = get_xml_model_names(set(sub_models_from_modeltest.values()))
model_data = ElementTree().parse(options.params, parser=XMLParser(target=MyTreeBuilder()))
# get the xml data that we need to add for the models and their parameters
models_to_add = get_generic_section_to_add(model_names, model_data, 'models')
sites_to_add = get_generic_section_to_add(site_names, model_data, 'sites')
operators_to_add = get_generic_section_children_to_add(model_names, model_data, 'operators')
log_entries_to_add = get_log_entries_to_add(model_names.union(site_names), model_data)
priors_to_add = get_generic_section_children_to_add(model_names, model_data, 'priors')
if super_concat:
likelihood_framework_to_add = get_generic_section_to_add(model_names, model_data, 'likelihoods')
# get the last position of the strictClockBranchRates
insert_position = get_position(xml, 'strictClockBranchRates')
# insert the models and sites we need
insert_position = insert_models_and_sites(xml, insert_position, models_to_add, sites_to_add)
# modify the tree likelihood statements
if not super_concat:
xml = update_tree_likelihoods(xml, sub_models_from_modeltest)
else:
insert_position = get_position(xml, 'siteModel')
xml = insert_tree_likelihoods(xml, sub_models_from_modeltest)
# insert the operators we need
xml = insert_to_generic_sections(xml, operators_to_add, 'operators', 'operators')
# insert the priors we need
xml = insert_to_generic_sections(xml, priors_to_add, 'prior', 'prior')
# alter the log node to collect data
xml = insert_to_generic_sections(xml, log_entries_to_add, 'log', 'fileLog')
# write to the output file
write(xml, options.output)
def __init__(self, html=0, target=None, encoding=None,
forbid_dtd=False, forbid_entities=True,
forbid_external=True):
# Python 2.x old style class
_XMLParser.__init__(self, html, target, encoding)
self.forbid_dtd = forbid_dtd
self.forbid_entities = forbid_entities
self.forbid_external = forbid_external
parser = self._parser
if self.forbid_dtd:
parser.StartDoctypeDeclHandler = self.defused_start_doctype_decl
if self.forbid_entities:
parser.EntityDeclHandler = self.defused_entity_decl
parser.UnparsedEntityDeclHandler = self.defused_unparsed_entity_decl
if self.forbid_external:
parser.ExternalEntityRefHandler = self.defused_external_entity_ref_handler
def __init__(self, stream, *pos, **kw):
self._stream = stream
self._pending = deque()
builder = _QueueBuilder(self._pending)
self._parser = XMLParser(*pos, target=builder, **kw)
self._builders = [TreeBuilder()]
[method, pos, kw] = self._read()
self.element = getattr(self._builders[-1], method)(*pos, **kw)
def parse_reqdata(self, get_data, post_data):
"""
parse query params and POST data into dictionary
"""
print 'debuggery: runing parse_reqdata...'
data_dict = {}
parser = XMLParser()
tree = parser.feed(post_data)
root = parser.close()
data_dict = XmlDictConfig(root)
# merge the query_params data
for k,v in self.parse_getparams(get_data).iteritems():
data_dict[k] = v
print 'debuggery: parsed !'
# return the dictionary data
return data_dict
def read_transaction(self):
parser = XMLParser()
line = ""
while not line.startswith('<?'):
line = yield from self.readline()
parser.feed(line)
key, attrs = yield from self.read_instruction(line)
if key == 'cancel':
self.logger.info('Transaction cancelled')
elif key == 'end':
self.logger.info('Transaction complete')
obj = parser.close()
self.logger.debug(pretty_xml_str(obj))
return obj
elif key == 'start':
self.report_error("Start instruction given mid-transaction")
else:
self.report_error("Unrecognised instruction during transaction: key = {}, attrs = {}".format(key, attrs))
def _unimplement_path_by_id(self,id,spec="9606"): self.pars["cmd"] = "search" self.pars["q"] = id content = self.tnf_obj.ask(self.pars) parser = XMLParser() parser.feed(content) elem = parser.close() # print content print elem.tag print elem.attrib for path in elem: print "hear "+path.tag+" "+path.attrib.keys() return
def main():
init()
log.info("Parsing '%s'..." % os.path.basename(conf['source_file']))
stopwatch_set()
target = CustomParser()
parser = XMLParser(target=target)
if PY2:
text = open(conf['source_file']).read()
else:
text = codecs.open(conf['source_file'], encoding='utf-8').read()
parser.feed(text)
log.info('')
total = '';
for key,value in stats.items():
total += str(key)
total += ': '
total += str(value)
total += '\n'
log.info(total);
log.info('Elapsed time: %s s' % stopwatch_get())
def fromScrollBoxToSigPlus(self,repertoireScroll,repertoireSigPlus):
galerieEnCours=None
fichierScrollBox=os.path.join(repertoireScroll,self.fichierScrollBox)
if os.path.exists(repertoireScroll) and os.path.exists(fichierScrollBox):
if not os.path.exists(repertoireSigPlus):
#on crée un répertoire avec les mêmes droits que le répertoire source
os.mkdir(repertoireSigPlus,os.stat(repertoireScroll).st_mode)
#on va parser le fichier en question
handler = ImageParser()
parser = XMLParser(target=handler)
ficToParse = codecs.open(fichierScrollBox, "r", "utf-8")
donneesXML = u'%s' %(ficToParse.read())
parser.feed(donneesXML)
galerieEnCours=parser.close()
ficSigPlus=open(os.path.join(repertoireSigPlus,self.fichierDescrSigPlus),'w')
for image in galerieEnCours.images:
ficSigPlus.write(u'%s|%s|%s\n' %(image.nomFic,image.titre,image.comment))
shutil.copy(os.path.join(repertoireScroll,image.nomFic), repertoireSigPlus)
msImage=time.mktime(image.date.timetuple())
os.utime(os.path.join(repertoireSigPlus,image.nomFic), (msImage, msImage))
ficSigPlus.close()
else:
print u'le fichier %s n\'a pu être trouvé, abandon\n' %(fichierScrollBox)
def parse_reqdata(self, get_data, post_data):
"""
parse query params and POST data into dictionary
"""
print 'debuggery: runing parse_reqdata...'
data_dict = {}
parser = XMLParser()
try:
parser.feed(post_data)
root = parser.close()
execElement = root.find("executions/execution")
if not execElement:
raise BleepParserError("Did not find executions/execution element in post data")
data_dict['execution_id'] = execElement.attrib["id"]
data_dict['execution_href'] = execElement.attrib["href"]
data_dict['execution_status']= execElement.attrib["status"]
data_dict['execution_user'] = execElement.find("user").text
data_dict['execution_date_started']= execElement.find("date-started").text
data_dict['execution_date_ended']= execElement.find("date-ended").text
data_dict['execution_description']= execElement.find("description").text
data_dict['execution_job_name']= execElement.find("job/name").text
data_dict['execution_job_group']= execElement.find("job/group").text
data_dict['execution_job_project']=execElement.find("job/project").text
data_dict['execution_job_description']= execElement.find("job/description").text
except KeyError as (keyerr):
print "Oops! missing key error: " + str(keyerr)
except AttributeError as (atterr):
print "Oops! missing attribute error" + str(atterr)
except Exception as (parserr):
raise BleepParserError("Unexpected error when parsing post data. "
+ "Cause: " + str(parserr))
# merge the query_params data
for k,v in self.parse_getparams(get_data).iteritems():
data_dict[k] = v
print 'debuggery: parsed !'
# return the dictionary data
return data_dict
def __init__(self, config):
asyncore.dispatcher_with_send.__init__(self)
self.config = config
self.database = get_database(self.config.database)
self.parser = XMLParser(target = self)
members = inspect.getmembers(self, predicate=inspect.ismethod)
for m in members:
if hasattr(m[1], "callback"):
fn = m[1]
fname = m[0]
self.mapping[fn.callback] = getattr(self, fname)
self.create_socket(socket.AF_INET, socket.SOCK_STREAM)
self.connect( (self.config.xmpp_host, self.config.xmpp_port) )
def get_tournaments(self, **kwargs):
"""
Returns set of tournaments from Challonge
Keywords:
state: One of { all, pending, in_progress, ended }
type: One of { single_elimination, double_elimination, round_robin, swiss }
created_after: YYYY-MM-DD
created_before: YYYY-MM-DD
subdomain: String
"""
if kwargs.has_key('state') and kwargs['state'] not in ['all', 'pending', 'in_progress', 'ended']:
raise Exception("Invalid state parameter")
if kwargs.has_key('type') and kwargs['type'] not in ['single_elimination', 'double_elimination', 'round_robin', 'swiss']:
raise Exception("Invalid type parameter")
response = self._call("tournaments", **kwargs)
print "got", response
target = TournamentConstructor()
parser = XMLParser(target=target)
parser.feed(response)
return parser.close()
from itertools import imap, islice, izip
from operator import itemgetter
from xml.etree.ElementTree import iterparse, XMLParser
from StatNewsWriter import DatabaseController, StatNewsWriterInterface
import htmlentitydefs
import datetime
import calendar
import nltk, string
class CustomEntity:
def __getitem__(self, key):
if key == 'umml':
key = 'uuml' # Fix invalid entity
return unichr(htmlentitydefs.name2codepoint[key])
parser = XMLParser()
parser.parser.UseForeignDTD(True)
parser.entity = CustomEntity()
records = []
count = 0
it = imap(itemgetter(1), iter(iterparse('./input/dblp.xml', events=['start'], parser=parser)));
root = next(it)
dbc = DatabaseController('./output/dblp_full.db')
db = StatNewsWriterInterface(dbc)
for node in it:
if (node.tag == 'article'):
count = count + 1
if (count % 1000 == 0):
import xml.etree.ElementTree as etree
from xml.etree.ElementTree import XMLParser
class MaxDepth:
maxDepth = 0
depth = 0
def start(self, tag, attrib):
self.depth += 1
if self.depth > self.maxDepth:
self.maxDepth = self.depth
def end(self, tag):
self.depth -= 1
def data(self, data):
pass
def close(self):
if self.maxDepth > 0:
return self.maxDepth - 1
else:
return self.maxDepth
S = ""
for _ in range(int(input())):
S += input()
target = MaxDepth()
parser = XMLParser(target=target)
parser.feed(S)
print(parser.close())
