def lire_dir_ftb(dossier): reader = XmlReader() print "--------------------------\n| Lecture du dossier ftb |\n--------------------------" treebank = reader.read_dir_xml_nopivot(dossier, dico_fichier_sentlist) print ">>> " + str(reader.nb_trees) + " arbres dans le dossier: " + dossier print ">>> - " + str(len(treebank)) + " arbres napparaissent pas dans le dossier-pivot" print ">>> - " + str(reader.skipped) + " arbres apparaissent dans le dossier-pivot" return treebank
def lire_ftb(fichier): reader = XmlReader() # remettre toujours liste vide else) si ca plante if dico_fichier_sentlist.has_key(fichier): treelist = reader.read_xml_nopivot(dico_fichier_sentlist[fichier]) else: treelist = reader.read_xml_nopivot(fichier, []) print ">>> " + str(len(treelist)) + " arbres dans le fichier: " + fichier
def length_vector_ftb(input_file): reader = XmlReader() treebank = reader.read_dir_xml(input_file) res = [] for tree in treebank: tree.merge_num() tree.merge_cpds() res.append(len(tree.tree_yield())) return res
def main(): _xml_reader = XmlReader() print_number_of_duplicates = True _xml_writer = XmlWriter('D:\\Valgrind\\Test with number of duplicates\\ALL_OUT', print_number_of_duplicates) _summerizer = Summerizer(_xml_writer) _xml_reader.subscribe(_summerizer, "error") _logs_reader = LogsReader(_xml_reader) _logs_reader.read_files('D:\\Valgrind\\Test with number of duplicates\\ALL_IN_SEPERATED\\ALL_3_IN_1') # ALL_IN_SEPERATED\Sequencer _xml_writer.print_duplicate_records(); _xml_writer.print_unique_records();
def parse(self, fileName): reader = XmlReader() root = reader.getById(fileName, self.id) outerElems = root.findall('./brid:outerBridgeConstruction/brid:BridgeConstructionElement', reader.ns) # multiSurface = root.findall('./brid:lod{0}MultiSurface/gml:MultiSurface'.format(self.lod), reader.ns) for elem in outerElems: constElem = ConstructionElement(elem) self.outerConstruction.append(constElem) for elem in self.outerConstruction: elem.parse(self.lod, reader.ns)
def __init__(self, xmlDir, logProblems): ''' Constructor @param xmlDir : Directory where the Doxygen XML files are. @param logProblems : Collection of SrcFile objects in a dictionary. @param danglingProblems: List of issues that could not be mapped to a file. @param memberTypes: List of member types found. ''' self.__fileCount = 0 xmlReader = XmlReader() self.__xmlDir = xmlDir doxyXML = xmlReader.readXML(self.__xmlDir + '/index.xml', None) self.__xmlroot = doxyXML.getroot() self.__doxyLog = logProblems
def rulesEngine_Employer(self,email,UserType,typeOfPlan): try: reader = XmlReader() EmployerPlanName,EmployerPlanCount,EmployerPlanPrice,EmployerMessagePermission = reader.readmyFile(UserType) if self.count == "": fetchJobsCount = FetchJobsCount(mysql,email,'','') self.count,result = fetchJobsCount.getJobsCount() concreteComponent = NormalEmployer() concrete_decorator_planA = Employer_Plan_decorator(concreteComponent) for index, item in enumerate(EmployerPlanName): if typeOfPlan == item: allowPosting,allowMessagePermission = concrete_decorator_planA.plan_rules(EmployerPlanCount[index],self.count,EmployerMessagePermission[index]) return allowPosting,allowMessagePermission except Exception as e: excep_msg = "Error occured in method rulesEngine_Employer_BSL method" level = logging.getLogger().getEffectiveLevel() logmyerror.loadMyExceptionInDb(level,excep_msg,e) logging.info(excep_msg, exc_info=True)
def __init__(self, filename, *args): XmlReader.__init__(self, filename, *args)
#OPTIONS source = str(opts.source) format = str(opts.format) all = bool(opts.all) raw = bool(opts.raw) pos = bool(opts.pos) sym = bool(opts.sym) subcat = bool(opts.subcat) fun = bool(opts.fun) pcfg = bool(opts.pcfg) top = int(opts.top) traces = bool(opts.traces) lncky = bool(opts.lncky) if source == 'xml': reader = XmlReader() if input_file <> None : if os.path.isdir(input_file): treebank = reader.read_dir_xml(input_file) else: instream = open(input_file) treebank = reader.read_xml(instream) else: treebank = reader.read_xml(sys.stdin) elif source=='penn': stream = sys.stdin.read() reader = PtbReader(drparser=True) treebank = reader.parse_treebank(stream) else : print "invalid source format\n" sys.exit(1)
mergenums = True tagfixer = get_tagset2_fixer() if opts.eval_file <> None : eval_file = str(opts.eval_file) compound_subcat_file = None if opts.compound_subcat_file <> None: compound_subcat_file = str(opts.compound_subcat_file) processcompounds = ProcessCompounds(file=compound_subcat_file) #Reads in the whole stuff treebank = [] dev = [] test = [] reader = XmlReader() # needed even for ptbinput (build_eval_data method) if ptbinput: ptbreader = PtbReader() stream = None if input_file <> None : stream = open(input_file) else: stream = sys.stdin treebank = ptbreader.read_mrg(stream) if getterminalsfromfile <> None: ptbreader_from = PtbReader() treebank_from = ptbreader_from.read_mrg(open(getterminalsfromfile)) ntreebank = change_terminals_in_treebank(treebank, treebank_from) printout_ptb_corpus(ntreebank,sys.stdout) exit() else:
#OPTIONS format = str(opts.format) raw = bool(opts.raw) subcat = bool(opts.subcat) fun = bool(opts.fun) cpd = bool(opts.cpd) traces = bool(opts.traces) eval_file = None if opts.eval_file <> None : eval_file = str(opts.eval_file) #Reads in the whole stuff treebank = [] test = [] gold = [] reader = XmlReader() if input_file <> None : if os.path.isdir(input_file): treebank = reader.read_dir_xml(input_file) else: instream = open(input_file) treebank = reader.read_xml(instream) else: treebank = reader.read_xml(sys.stdin) #Check for eval mode if eval_file <> None : (treebank,test,gold) = reader.build_eval_data(treebank) #Prints the corpus (or the training treebank) if raw :