def tagging(self, filename, outputfile):
''' if this is not text convert it to text file '''
if (filename.endswith(".txt")):
inputfilename = filename
else:
inputfilename = docutonelocate.convert_file(filename)
documents = self._read_file(inputfilename)
self.outputfile = outputfile
self.file_tagging(documents)
def file_clean(self, filename):
from docutone.core.document import LawDocument
if (filename.endswith(".txt")):
ofile = filename
else:
ofile = docutonelocate.convert_file(filename)
lawdoc = LawDocument()
document = lawdoc.get_fusion_document(ofile)
for sentence in document:
print(' '.join(sentence))
def file_named_tag(self, filename):
from docutone.core.document import LawDocument
if (filename.endswith(".txt")):
ofile = filename
else:
ofile = docutonelocate.convert_file(filename)
lawdoc = LawDocument()
document = lawdoc.get_fusion_document(ofile)
self.new_ner = {}
for sentence in document:
self.get_sentence_named_tag(sentence)
self.write_ner()
def create_test_tagging(self, filename, ftype):
self.fullname = filename
self.filename = os.path.basename(filename).split('.')[0]
if ";" in ftype:
parent, cat = ftype.split(";", 1)
self.categorie = cat.strip()
self.ftype = parent.strip()
else:
if '（' in ftype:
index = ftype.find('（')
elif '(' in ftype:
index = ftype.find('(')
else:
index = 0
if index > 3:
self.categorie = ftype[0:index].strip()
else:
self.categorie = ftype.strip()
self.ftype = None
''' if this is not text convert it to text file '''
if (filename.endswith(".txt")):
inputfilename = filename
else:
inputfilename = docutonelocate.convert_file(filename)
self.dtn_doc = None
if self.categorie == dtn_document.LABOR_CONTRACT:
self.dtn_doc = labor_contract.LaborContract()
elif self.categorie == dtn_document.LOAN_AGREEMENT:
self.dtn_doc = loan_agreement.LoanAgreement()
elif self.categorie == dtn_document.TRANSFER_AGREEMENT:
self.dtn_doc = transfer_agreement.TransferAgreement()
else:
self.dtn_doc = other_document.OtherDocument()
documents = self.dtn_doc.read(inputfilename)
self._add_new_clauses(documents, self.dtn_doc._results)
result = self.tagging.tagging_test(documents)
return result
def _load_document_clauses(self, filename, label):
if (filename.endswith(".txt")):
ofile = filename
else:
ofile = docutonelocate.convert_file(filename)
self._clause.create_clauses(ofile)
if len(self._clause.sections) > 0:
for section in self._clause.sections:
name = label + ":" + section.title
name = section.title
if name in self.labels_index.keys():
label_id = self.labels_index[name]
else:
label_id = len(self.labels_index)
self.labels_index[name] = label_id
self.label_name.append(name)
self.labels.append(label_id)
words = section.toWords()
self.texts.append(words)
def load_predict_document(self, filename):
if (filename.endswith(".txt")):
ofile = filename
else:
ofile = docutonelocate.convert_file(filename)
self._document.read_section(ofile)
texts = []
if len(self._document.sections) > 0:
for section in self._document.sections:
ss = []
if section.title:
pass
if len(section.sentences) > 0:
ss = [p[0] for p in section.sentences]
if len(ss) > 0:
texts.append(doc.sentencesTowords(ss))
else:
for s in self._document.document_header:
texts.append(doc.sentencesTowords([s]))
return texts
def get_terms(self, filename, filetype):
if (filename.endswith(".txt")):
ofile = filename
else:
ofile = docutonelocate.convert_file(filename)
#lawdocument.create_document(ofile, filetype)
self.document.read_section(ofile)
self._title = self.document.document_name
self._contract_date = self.document.document_date
if self._title:
if '文件名称' in self.keywords:
self.verified_terms['文件名称'].add_value(self._title, 1)
elif '合同名称' in self.keywords:
self.verified_terms['合同名称'].add_value(self._title, 1)
if self._contract_date:
if '签约日期' in self.keywords:
self.verified_terms['签约日期'].add_value(self._contract_date, 1)
elif '签发日期' in self.keywords:
self.verified_terms['签发日期'].add_value(self._contract_date, 1)
elif '合同日期' in self.keywords:
self.verified_terms['合同日期'].add_value(self._contract_date, 1)
terms = []
'''
prev_sentence = ''
for s in ld.document_header :
prev_sentence += s
if ld._is_sentence_end(s) :
terms.append([prev_sentence])
prev_sentence = ''
if prev_sentence :
terms.append([prev_sentence])
'''
nb = len(self.document.sections)
if nb > 0:
index = 0
while index < nb:
p = self.document.sections[index]
index += 1
''' if section title = term name add it to verfied table '''
if p.title:
termname = dtn_sentence.get_keywords_by_name(
p.title, self.keywords)
if termname:
if len(p.sentences) > 0:
for s in p.sentences:
if isinstance(s, str):
self.verified_terms[termname].add_value(
s, 1)
else:
s_line = s[0]
self._add_verified_sentences(
termname, s[1], s_line[-1], 1)
while index < nb:
sp = self.document.sections[index]
index += 1
if sp.level > p.level:
for s in sp.sentences:
if isinstance(s, str):
self.verified_terms[
termname].add_value(s, 1)
else:
s_line = s[0]
self._add_verified_sentences(
termname, s[1], s_line[-1], 1)
else:
''' back to prev section '''
index -= 1
break
if len(p.sentences) > 0:
terms.append(p.sentences)
return terms
commd += " -i " + infile
if o_file:
commd += " -o " + o_file
if options.doc_type:
commd += " -t " + options.doc_type
dtn_logger.logger_info("MAIN", commd)
if options.action == 'convert':
'''
conv = Convert(verbose=verbose, restart=options.restart)
o_file = conv.open_output(infile, o_file)
conv.files_to_text(infile, o_file)
conv.close_output()
'''
ofile = docutonelocate.convert_file(infile, True)
elif options.action == 'testfile':
conv = Convert(verbose=verbose, restart=options.restart)
conv.test_files_in_directory(infile, o_file)
elif options.action == 'changebad':
conv = Convert(verbose=verbose, restart=options.restart)
conv.change_root_bad_files(infile, o_file)
elif options.action == 'text4sentences':
