def file_translator(file, language):
with open(file, 'r') as fh:
for f in fh:
sentense = TextBlob(f)
if language == "english":
print sentense.translate(to="en")
else:
print sentense.translate(to="es")
return
def word_translator(words):
b = TextBlob(words)
if b.detect_language() == "en":
print "The word " + words + " is in english and means",\
b.translate(to="es")
elif b.detect_language() == "es":
print "La palabra " + words +\
" esta en espanol y en ingles significa", b.translate(to="en")
return
def file_translator(file, language):
with open(file, 'r') as fh:
for f in fh:
sentense = TextBlob(f)
if language == "english":
print sentense.translate(to="en")
else:
print sentense.translate(to="es")
return
def word_translator(words):
b = TextBlob(words)
if b.detect_language() == "en":
print "The word " + words + " is in english and means",\
b.translate(to="es")
elif b.detect_language() == "es":
print "La palabra " + words +\
" esta en espanol y en ingles significa", b.translate(to="en")
return
def get_translate(self, text):
text = text.replace("text:", "")
blob = TextBlob(text)
lan = blob.detect_language()
if lan != 'en':
sentp = blob.translate(to="en")
else:
sentp = blob.translate(to="fa")
sent = self.sender.sendMessage(str(sentp))
self._editor = telepot.helper.Editor(self.bot, sent)
self._edit_msg_ident = telepot.message_identifier(sent)
def flat_doc(document, model, extremes=None):
flat_doc = ""
for field in document:
if not isinstance(document[field], list): continue #No tomamos en cuenta los campos 'id' y '_version_': auto-generados por Solr
for value in document[field]:
## Detección y traducción ##
if field=='author.authors.authorName' or field=='author.authorBio' or field=='description' or field=='quotes.quoteText':
value_blob = TextBlob(value)
try:
if value_blob.detect_language() != 'en':
try:
value = value_blob.translate(to='en')
except Exception as e:
value = value #e = NotTranslated('Translation API returned the input string unchanged.',)
except Exception as e:
value = value #e = TranslatorError('Must provide a string with at least 3 characters.')
############################
flat_doc += str(value)+' ' #Se aplana el documento en un solo string
flat_doc = preprocess_string(flat_doc, CUSTOM_FILTERS) #Preprocesa el string
flat_doc = [w for w in flat_doc if w not in stop_words] #Remueve stop words
if extremes:
flat_doc = [w for w in flat_doc if w not in extremes]
flat_doc = [w for w in flat_doc if w in model.vocab] #Deja sólo palabras del vocabulario
if flat_doc == []:
flat_doc = ['book'] #Si el libro queda vacío, agregarle un token para no tener problemas más adelante
return flat_doc
def handle_message_event(event):
print(event)
text = event.message.text
source = event.source
id = ''
if isinstance(source, SourceUser):
id = source.user_id
elif isinstance(source, SourceGroup):
id = source.group_id
set_send_id(id)
blob = TextBlob(text)
if '狀態' in text:
text = text.replace('狀態', '')
if text == '':
line_bot_api.reply_message(
event.reply_token, TextSendMessage(text=get_all_messages()))
else:
name = text
line_bot_api.reply_message(event.reply_token,
TextSendMessage(text=get_message(name)))
elif '報告' in text:
matches = re.search('(.*)報告(\d*)', text)
if matches.group(1) == '' and matches.group(2) == '':
line_bot_api.reply_message(event.reply_token,
TextSendMessage(text=get_all_reports()))
elif matches.group(2) == '':
line_bot_api.reply_message(
event.reply_token,
TextSendMessage(text=get_report(matches.group(1))))
else:
line_bot_api.reply_message(
event.reply_token,
TextSendMessage(text=get_report_url(matches.group(1),
int(matches.group(2)))))
elif '敬禮' in text:
line_bot_api.reply_message(event.reply_token,
TextSendMessage(text='敬禮'))
elif '安安' in text:
line_bot_api.reply_message(event.reply_token,
TextSendMessage(text='安'))
elif '0.0' in text:
line_bot_api.reply_message(event.reply_token,
TextSendMessage(text='0.0'))
elif blob.detect_language() == 'ru':
line_bot_api.reply_message(
event.reply_token,
TextSendMessage(text=str(blob.translate(to='zh-TW'))))
def __get_blob(self, text):
"""
Translate text with current user locale
@param text as str
"""
try:
locales = GLib.get_language_names()
user_code = locales[0].split(".")[0]
try:
from textblob.blob import TextBlob
except:
return _("You need to install python3-textblob module")
blob = TextBlob(text)
return str(blob.translate(to=user_code))
except Exception as e:
Logger.error("LyricsView::__get_blob(): %s", e)
return _("Can't translate this lyrics")
def main():
# Get our data as an array: [title, author, date, content] from read_in()
lines = read_in()
title = lines[0]
author = lines[1]
date = lines[2]
chinese_blob = TextBlob(lines[3])
en_content = chinese_blob.translate(from_lang="zh-CN", to='en')
info("Translated texts: " + str(en_content)) # print translated result to web console.
# Combine translated result with ada-content-en.csv to produce new csv.
# Make a call to localhost:5000/update with data: [(id),title,author,date,content], "id" field will be automatically generated by reviewing csv file.
# please note that in dev environment, 8080 is node app port, while 5000 is python flask app port.
r = requests.get("http://localhost:5000/update", headers={'X-API-TOKEN': 'FOOBAR1'}, data={'title': title, 'author': author, 'date': date, 'content': en_content})
info("INFO: " + r.text)
# training updated backup.csv.
r_train = requests.get("http://localhost:5000/train", headers={'X-API-TOKEN': 'FOOBAR1'}, data={'data-url': 'backup.csv'})
info("INFO: " + r_train.text)
# predicting updated backup.csv.
r_predict = requests.post("http://localhost:5000/predict", headers={'X-API-TOKEN': 'FOOBAR1'}, data={'item': '-1', 'num': 2, 'data-url': 'backup.csv'})
info("INFO: " + r_predict.text)
from textblob.blob import TextBlob
blob = TextBlob('Уровень')
print(str(blob.translate(to='zh-TW')))
combo = url2content(row['url'])
writer.writerow({'id': row['id'], 'title': combo['title'], 'author': combo['author'], 'date': combo['date'], 'url': row['url'], 'content': combo['combined_string']})
print 'Processing scraper NO.' + str(row['id'])
### Connect with ada-content.csv to translate content to english version.
with open('ada-content-en.csv', 'w') as target:
fieldnames = ['id', 'title', 'author', 'date', 'url', 'content']
writer = csv.DictWriter(target, fieldnames=fieldnames)
writer.writeheader()
with open('ada-content.csv') as source:
reader = csv.DictReader(source.read().splitlines())
for row in reader:
chinese_blob = TextBlob(row['content'].decode('utf-8'))
en_content = chinese_blob.translate(from_lang="zh-CN", to='en')
writer.writerow({'id': row['id'], 'title': row['title'], 'author': row['author'], 'date': row['date'], 'url': row['url'], 'content': en_content})
print 'Processing translator NO. ' + str(row['id'])
for row in reader:
combo = url2content(row['url'])
writer.writerow({
'id': row['id'],
'title': combo['title'],
'author': combo['author'],
'date': combo['date'],
'content': combo['combined_string']
})
print 'Processing scraper NO.' + str(row['id'])
### Connect with ada-content.csv to translate content to english version.
with open('ada-content-en.csv', 'w') as target:
fieldnames = ['id', 'title', 'author', 'date', 'content']
writer = csv.DictWriter(target, fieldnames=fieldnames)
writer.writeheader()
with open('ada-content.csv') as source:
reader = csv.DictReader(source.read().splitlines())
for row in reader:
chinese_blob = TextBlob(row['content'].decode('utf-8'))
en_content = chinese_blob.translate(from_lang="zh-CN", to='en')
writer.writerow({
'id': row['id'],
'title': row['title'],
'author': row['author'],
'date': row['date'],
'content': en_content
})
print 'Processing translator NO. ' + str(row['id'])
