fix bulk_insert error on associations: new solution mixing first idea about...

fix bulk_insert error on associations: new solution mixing first idea about remainder of loop and new idea about one 'for' loop too much on the languages

gargantext/util/toolchain/ngrams_extraction.py

@@ -51,9 +51,10 @@ def extract_ngrams(corpus, keys=DEFAULT_INDEX_FIELDS, do_subngrams = DEFAULT_IND
         docs = [doc for doc in corpus.children('DOCUMENT') if doc.id not in corpus.skipped_docs]
         tagger_bots = {lang: load_tagger(lang)() for lang in corpus.languages if lang != "__skipped__"}
         #sort docs by lang?
-        for lang, tagger in tagger_bots.items():
+        # for lang, tagger in tagger_bots.items():
         for documents_count, document in enumerate(docs):
-                language_iso2 = document.hyperdata.get('language_iso2', lang)
+            language_iso2 = document.hyperdata.get('language_iso2')
+            tagger = tagger_bots[language_iso2]
             #print(language_iso2)
             for key in keys:
                 try:
@@ -97,9 +98,13 @@ def extract_ngrams(corpus, keys=DEFAULT_INDEX_FIELDS, do_subngrams = DEFAULT_IND
             corpus.save_hyperdata()
             session.add(corpus)
             session.commit()
-            else:
-                # integrate ngrams and nodes-ngrams
+
+        # integrate ngrams and nodes-ngrams (le reste)
+        if len(nodes_ngrams_count) > 0:
             _integrate_associations(nodes_ngrams_count, ngrams_data, db, cursor)
+            nodes_ngrams_count.clear()
+            ngrams_data.clear()
+
         corpus.status('Ngrams', progress=documents_count+1, complete=True)
         corpus.save_hyperdata()
         session.commit()