def get_document_type(self, dictname) :
textfname = "../dictionary/text/" + dictname + ".txt"
law_document = LawDocument()
law_document.analyze(filename=textfname)
text = law_document.document_type;
return text
def get_document(self, dictname) :
textfname = "../dictionary/text/" + dictname + ".txt"
law_document = LawDocument()
law_document.analyze(filename=textfname)
text = "\n".join(law_document.document_title);
return text
def get_document_chapiter(self, sims, dictname) :
textfname = "../dictionary/text/" + dictname + ".txt"
law_document = LawDocument()
law_document.analyze(filename=textfname)
text = "";
n_line = 1
for sim in sims :
doc_no, simil = sim[0], sim [1]
if (simil > 0.4) :
text += "******** " + str(n_line) + " ********\n"
text += law_document.get_document_chapiter(doc_no) + "\n"
n_line += 1
if n_line > 2:
break;
else :
break
return text
def search_document(self, textpath, filename) :
ld = LawDocument()
ld.analyze(filename=filename)
doc_tab = []
names = os.listdir("../dictionary/dict")
n_file = 1
for filename in os.listdir("../dictionary/dict") :
if filename.endswith(".dict") :
dictname = filename.replace('.dict', '')
total = 0.0
sentences = []
for sentence in ld.table_contents :
if len(sentence) > 1 :
sims = self.text_search_lsi(textpath, sentence[1])
total += self.get_similarity_value(sims)
doc_tab.append([dictname, total])
doc_tab = sorted(doc_tab, key=lambda total: total[1], reverse=True)
return self.get_document_type(doc_tab[0][0])