rjawor/concordia-preprocessor
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

is first lemmatized

Browse Source
This commit is contained in:
rjawor 2019-07-15 10:49:48 +02:00
parent 053ee2e040
commit daee1668b0
2 changed files with 18 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
server/lemmatizer_resource.py
View File

@ -30,8 +30,17 @@ class LemmatizerResource(Resource):
return result, 200 return result, 200
def processSentence(self, sentence, language): def processSentence(self, sentence, language):
tokens = [self.lemmatizeWord(token, language) for token in sentence.split()] raw_tokens = sentence.split()
return {'tokens':' '.join(tokens)} tokens = [self.lemmatizeWord(token, language) for token in raw_tokens]
return {'tokens':' '.join(tokens), 'isFirstLemmatized':self.isFirstLemmatized(raw_tokens, language)}
def isFirstLemmatized(self, raw_tokens, language):
if language == 'pl':
first_token = raw_tokens[0]
if self.lemmatizeWord(first_token, language) != first_token:
return False
return True
def lemmatizeWord(self, word, language): def lemmatizeWord(self, word, language):
if len(word) == 1: if len(word) == 1:

8
tests/lemmatize_verbose.py
View File

@ -2,9 +2,15 @@
import requests, json import requests, json
local = False
if local:
port = 9001
else:
port = 10002
def do_lemmatize(data): def do_lemmatize(data):
response = requests.post(url = 'http://127.0.0.1:10002/lemmatize', json = data) response = requests.post(url = 'http://127.0.0.1:%d/lemmatize' % port, json = data)
return json.loads(response.text) return json.loads(response.text)