Commit 127210d9ee1e021f494090758db5d8b7f6cd8b42
1 parent
2e75fdc6c4
Exists in
soap
Suppression du phon
Showing 3 changed files with 28 additions and 50 deletions Side-by-side Diff
liaSoap.py
processor/Orkis.py
| ... | ... | @@ -8,11 +8,9 @@ |
| 8 | 8 | def __init__(self,dirtyString): |
| 9 | 9 | self.lem=u"" |
| 10 | 10 | self.tagger=Tagger() |
| 11 | - self.phoner=Phoner() | |
| 12 | 11 | self.dico ={} |
| 13 | 12 | self.string=dirtyString |
| 14 | 13 | def isReady(self): |
| 15 | - self.phoner.isReady() | |
| 16 | 14 | self.tagger.isReady() |
| 17 | 15 | def __unicode__(self): |
| 18 | 16 | string = u"" |
| ... | ... | @@ -20,9 +18,6 @@ |
| 20 | 18 | string += ( unicode(word.decode("utf-8")))+unicode (u";") |
| 21 | 19 | for lemWord in self.dico[word][0]: |
| 22 | 20 | string += (unicode(lemWord.decode("utf-8"))+ unicode(u" ")) |
| 23 | - string +=u";" | |
| 24 | - for phonWord in self.dico[word][1]: | |
| 25 | - string += (unicode(phonWord.decode("utf-8"))+ unicode(u" ")) | |
| 26 | 21 | string+=u"\n" |
| 27 | 22 | return string |
| 28 | 23 | def clean(self): |
| 29 | 24 | |
| ... | ... | @@ -41,24 +36,9 @@ |
| 41 | 36 | self.dico[table[0]]=[set(),set()] |
| 42 | 37 | self.dico[table[0]][0].add(table[2]) |
| 43 | 38 | self.lem = self.lem +"\n"+ table[2] |
| 44 | - def insertPhon(self): | |
| 45 | - prephonedString=self.cleanString + self.lem.rstrip() | |
| 46 | - phonedString=self.phoner.phon(self.cleanString.rstrip() +self.lem.rstrip()) | |
| 47 | - self.tablephon= phonedString.rstrip().split("\n") | |
| 48 | - for line in phonedString.rstrip().split("\n"): | |
| 49 | - if not re.match(r's>',line): | |
| 50 | - table = line.rstrip().split(" ") | |
| 51 | - if table[0] in self.dico and not table[1].isspace() : | |
| 52 | - self.dico[table[0]][1].add(table[1]) | |
| 53 | - elif table[0] not in self.dico and not table[1].isspace() : | |
| 54 | - for mot,sets in self.dico.iteritems(): | |
| 55 | - if table[0] in sets[0]: | |
| 56 | - self.dico[mot][1].add(table[1]) | |
| 57 | - | |
| 58 | 39 | def getDico(self): |
| 59 | 40 | self.clean() |
| 60 | 41 | self.insertLem() |
| 61 | - self.insertPhon() | |
| 62 | 42 | self.table=[] |
| 63 | 43 | for i,v in self.dico.iteritems(): |
| 64 | 44 | if not re.match(r".s>",i): |
| 65 | 45 | |
| ... | ... | @@ -66,10 +46,7 @@ |
| 66 | 46 | list.append(i) |
| 67 | 47 | for indice in v[0]: |
| 68 | 48 | list.append(indice) |
| 69 | - for indice in v[1]: | |
| 70 | - list.append(indice) | |
| 71 | 49 | ligne= " ".join(list) |
| 72 | - | |
| 73 | 50 | self.table.append(ligne) |
| 74 | 51 | return "\n".join(self.table) |
test/functional/testLiaSoap.py
| ... | ... | @@ -3,7 +3,7 @@ |
| 3 | 3 | import threading |
| 4 | 4 | |
| 5 | 5 | ### TODO : Tester en parallele x4 un million de fois pour voir ### |
| 6 | -url = 'http://194.57.216.156:8181/?wsdl' | |
| 6 | +url = 'http://127.0.0.1:9000/?wsdl' | |
| 7 | 7 | client = Client(url) |
| 8 | 8 | filename = "data.txt" |
| 9 | 9 | file = open(filename, "r") |
| 10 | 10 | |
| ... | ... | @@ -11,34 +11,35 @@ |
| 11 | 11 | # Exp 1 |
| 12 | 12 | debut =time.time() |
| 13 | 13 | contents = file.read().decode("utf8").encode("ascii", errors='ignore').rstrip() |
| 14 | -client.service.get_phon(contents) | |
| 14 | +res =client.service.get_phon(contents) | |
| 15 | +print(res) | |
| 15 | 16 | duree= time.time()- debut |
| 16 | 17 | print (" Exper 1 : " + str(duree)) |
| 17 | 18 | # Exp 2 |
| 18 | -debut =time.time() | |
| 19 | -file.seek(0) | |
| 20 | -lines = file.readlines() | |
| 21 | -for line in lines: | |
| 22 | - line = line.decode("utf8").encode("ascii", errors='ignore').rstrip() | |
| 23 | - if line is not None: | |
| 24 | - try: | |
| 25 | - client.service.get_phon(line) | |
| 26 | - except: | |
| 27 | - continue | |
| 28 | -duree= time.time()- debut | |
| 29 | -print (" Exper 2 line by line 1 corpus : " + str(duree)) | |
| 30 | -##Exp 3 | |
| 31 | -debut = time.time() | |
| 32 | -file.seek(0) | |
| 33 | -contents = file.read().decode("utf8").encode("ascii", errors='ignore').rstrip() | |
| 34 | -tabs=[] | |
| 35 | -i=0 | |
| 36 | -while i <= nb_times : | |
| 37 | - tabs.append(contents) | |
| 38 | - i+=1 | |
| 39 | -client.service.get_phon("".join(tabs)) | |
| 40 | -duree= time.time()- debut | |
| 41 | -print ("Exper 3 2pow4 time the content in once shot " + str(duree)) | |
| 19 | +#debut =time.time() | |
| 20 | +#file.seek(0) | |
| 21 | +#lines = file.readlines() | |
| 22 | +#for line in lines: | |
| 23 | +# line = line.decode("utf8").encode("ascii", errors='ignore').rstrip() | |
| 24 | +# if line is not None: | |
| 25 | +# try: | |
| 26 | +# client.service.get_phon(line) | |
| 27 | +# except: | |
| 28 | +# continue | |
| 29 | +#duree= time.time()- debut | |
| 30 | +#print (" Exper 2 line by line 1 corpus : " + str(duree)) | |
| 31 | +###Exp 3 | |
| 32 | +#debut = time.time() | |
| 33 | +#file.seek(0) | |
| 34 | +#contents = file.read().decode("utf8").encode("ascii", errors='ignore').rstrip() | |
| 35 | +#tabs=[] | |
| 36 | +#i=0 | |
| 37 | +#while i <= nb_times : | |
| 38 | +# tabs.append(contents) | |
| 39 | +# i+=1 | |
| 40 | +#client.service.get_phon("".join(tabs)) | |
| 41 | +#duree= time.time()- debut | |
| 42 | +#print ("Exper 3 2pow4 time the content in once shot " + str(duree)) | |
| 42 | 43 | # EXP 4 |
| 43 | 44 | #debut = time.time() |
| 44 | 45 | #contents = file.read().decode("utf8").encode("ascii", errors='ignore').rstrip() |