[FEAT] TurboParser again with us.

gargantext/constants.py

@@ -102,12 +102,12 @@ INDEXED_HYPERDATA = {
 }
 
 
-from gargantext.util.taggers import EnglishMeltTagger, FrenchMeltTagger
+from gargantext.util.taggers import EnglishMeltTagger, FrenchMeltTagger, TurboTagger
 
 LANGUAGES = {
     'en': {
-        'tagger': EnglishMeltTagger,
-        #'tagger': TurboTagger,
+        #'tagger': EnglishMeltTagger,
+        'tagger': TurboTagger,
         #'tagger': NltkTagger,
     },
     'fr': {

gargantext/util/taggers/lib/nlpserver/README.md

@@ -15,13 +15,14 @@ CONFIGURATION
 The settings for the server can be found in `settings.py`.
 Please ensure the TCP port is not already in use on your machine, and that the path to the models are correct.
 
-START for tests
-===============
-python3 server.py
+START server in console
+=======================
+launchServeur.sh
+
 "CTRL + c" to shut down
 
-START/STOP THE SERVER
-=====================
+START/STOP THE DAEMON SERVER (DEPRECATED)
+=========================================
 
 Simply run the following command to start: `./nlpserver start`
 To stop: `./nlpserver stop`

gargantext/util/taggers/lib/nlpserver/launchServeur.sh

+#!/bin/bash
+
+
+export LD_LIBRARY_PATH=":/srv/gargantext_lib/taggers/nlpserver/TurboParser/deps/local/lib:"
+
+source /srv/env_3-5/bin/activate
+
+python server.py
+

gargantext/util/taggers/lib/nlpserver/pipeline.py

@@ -7,25 +7,30 @@ def print(text):
 print('PREPARING TURBOPARSER')
 import turboparser
 turbo_interface = turboparser.PTurboParser()
+print('TURBOPARSER PREPARED')
 
 print('LOADING TOKENIZERS')
 import nltk
 sentence_tokenizer = nltk.data.load(tokenizer_model)
 word_tokenizer = nltk.TreebankWordTokenizer()
+print('TOKENIZERS LOADED')
 
 if 'TAG' in implemented_methods or 'LEMMATIZE' in implemented_methods:
     print('LOADING TAGGER')
     tagger = turbo_interface.create_tagger()
     tagger.load_tagger_model(b_tagger_model)
+    print('TAGGER LOADED')
 
 if 'LEMMATIZE' in implemented_methods or 'TAG' in implemented_methods or 'PARSE' in implemented_methods:
     print('LOADING LEMMATIZER')
     from lemmatizer import lemmatize
+    print('LEMMATIZER LOADED')
 
 if 'PARSE' in implemented_methods:
     print('LOADING PARSER')
     parser = turbo_interface.create_parser()
     parser.load_parser_model(b_parser_model)
+    print('PARSER LOADED')
 
 
 def split_sentences(text):