def testSimple(self):
con = Connector(getDataLoader())
self.assertEqual(-5447, con.getCost(1283, 1298))
with self.assertRaises(RuntimeError):
con.getCost(-1, 101)
with self.assertRaises(RuntimeError):
con.getCost(1, 100000001)
def post(self, request, *args, **kwargs):
logging.info('Get a message!')
if request.method == 'POST':
userText = request.POST['text']
addWord = request.POST['word']
addReading = request.POST['reading']
addDefinition = request.POST['definition']
addSentence = request.POST['sentence']
unknownWordsOnly = request.POST['unknownWordsOnly']
logger = logging.getLogger('console')
logger.info('POST settings: userTextLen:%s, word:%s, reading:%s, '
'definition:%s, sentence:%s, unknownWordsOnly:%s',
len(userText), addWord, addReading, addDefinition,
addSentence, unknownWordsOnly)
unknownWordsOnly = int(unknownWordsOnly)
result = []
textProc = TextProcessor(getDataLoader())
contents = textProc.do(userText, Settings.NoExcessiveReading(), True)
for word, startPos, reading, definition, sentence in contents:
isKnown = self.getWordStatus(word)
if not unknownWordsOnly or not isKnown:
result.append((word, reading, definition, sentence, isKnown))
logger.info('# of words to return: %d', len(result))
#contents = list(contents)
# logging.info("%d records sent", len(result))
data = simplejson.dumps(result)
h = HttpResponse(data, mimetype="application/json", status=200)
return h
def testCharCategories(self):
prop = CharProperty(getDataLoader())
self.assertEqual(['DEFAULT', 'SPACE', 'KANJI', 'SYMBOL',
'NUMERIC', 'ALPHA', 'HIRAGANA', 'KATAKANA',
'KANJINUMERIC', 'GREEK', 'CYRILLIC'], prop.getCategories())
self.assertEqual(['SPACE'], prop.getCharCaterogies(' '))
self.assertEqual(['NUMERIC'], prop.getCharCaterogies('1'))
self.assertEqual(['ALPHA'], prop.getCharCaterogies('a'))
self.assertEqual(['KANJI'], prop.getCharCaterogies('吗'))
def __init__(self):
webapp2.WSGIApplication.__init__(self, [('/', MainPage),
('/mydeck', DeckPage),
('/about', AboutPage),
('/addcard', AddCardPage),
('/deletecard', DeleteCardPage),
('/export', ExportDeckPage),
('/backend', BackendPage)],
debug=True)
try:
get_url()
logging.info('Starting backend')
self.textProc = TextProcessor(getDataLoader())
except InvalidBackendError:
logging.info('Starting frontend')
def dryBurn():
from pkgutil import iter_modules
a=iter_modules()
while True:
try: x=a.next()
except: break
print (x[1], '<br>')
setupLogger()
contents = '船が検疫所に着いたのは'
textProc = TextProcessor(getDataLoader())
for word, reading, definition, sentence in textProc.do(contents, Settings.NoExcessiveReading(), True):
line = text_type('{0:<10} {1:<10} {2:<10} {3}\n').format(word, reading, definition,sentence)
line = line.strip('\n')
print(line.encode('utf-8'))
def main():
parser = argparse.ArgumentParser(description='Get the list word in the text.')
parser.add_argument('inputfile', metavar='input file name',
help='input file name')
parser.add_argument('-d', metavar='deck file name', required=False,
help='deck file nime')
parser.add_argument('-t', metavar='tag', required=False,
help='optional tag appended to the list')
parser.add_argument('-o', metavar='output file name', required=False,
help='output file name')
args = parser.parse_args()
if args.o:
sys.stdout = open(args.o, 'w', encoding='utf-8')
setupLogger()
with openInputFile(args.inputfile) as file:
contents = file.read()
if isPy2():
contents = unicode(contents, 'utf-8')
textProc = TextProcessor(getDataLoader())
getUniqueCSVList(textProc, contents, args.d, args.t)
def setUp(self):
self.dictionary = dartsdict.DartsDictionary(getDataLoader().load('jdict'))
def setUp(self):
self.pyparser = PyPortSentenceParser(getDataLoader())
self.exeparser = MecabSentenceParser()
def setUp(self):
self.textProc = TextProcessor(getDataLoader())
self.maxDiff = None
def setUp(self):
self.defaultText = '船が検疫所に着いたのは、朝の四時頃にちがいない。'
self.viterbi = Viterbi(getDataLoader())
def setUp(self):
self.viterbi = Viterbi(getDataLoader())
self.maxDiff = None
def setUp(self):
self.tokenizer = Tokenizer(getDataLoader())
