[FEAT] Async parse and ngrams extract methods: ok

gargantext_web/views.py

@@ -5,11 +5,10 @@ from django.http import Http404, HttpResponse, HttpResponseRedirect
 from django.template.loader import get_template
 from django.template import Context
 
-#from documents.models import Project, Corpus, Document
-
 from node.models import Language, ResourceType, Resource, \
         Node, NodeType, Node_Resource, Project, Corpus, \
         Node_Ngram, NodeNgramNgram
+
 from node.admin import CorpusForm, ProjectForm, ResourceForm
 
 from django.contrib.auth.models import User
@@ -237,12 +236,8 @@ def project(request, project_id):
                     )
 
             try:
-                #corpus.parse_resources.apply_async((), countdown=1)
-                corpus.parse_resources()
-                
-                # async
-                corpus.children.filter(type_id=type_document.pk).extract_ngrams(keys=['title',])
-                #corpus.children.filter(type_id=type_document.pk).extract_ngrams(keys=['title',])
+                #corpus.parse_and_extract_ngrams(keys=['title',])
+                corpus.parse_and_extract_ngrams.apply_async((), countdown=1)
 
             except Exception as error:
                 print(error)

node/models.py

@@ -157,7 +157,6 @@ class Node(CTENode):
         node_resource.save()
         return resource
     
-    @current_app.task(filter=task_method)
     def parse_resources(self, verbose=False):
         # parse all resources into a list of metadata
         metadata_list = []
@@ -200,7 +199,6 @@ class Node(CTENode):
         self.node_resource.update(parsed=True)
 
     
-    @current_app.task(filter=task_method)
     def extract_ngrams(self, keys, ngramsextractorscache=None, ngramscaches=None):
         # if there is no cache...
         if ngramsextractorscache is None:
@@ -235,6 +233,13 @@ class Node(CTENode):
             for ngram_text, weight in associations.items()
         ])
 
+    @current_app.task(filter=task_method)
+    def parse_and_extract_ngrams(self, keys=None, ngramsextractorscache=None, ngramscaches=None, verbose=False):
+        self.parse_resources()
+        type_document   = NodeType.objects.get(name='Document')
+        self.children.filter(type_id=type_document.pk).extract_ngrams(keys=['title',])
+
+
 class Node_Metadata(models.Model):
     node        = models.ForeignKey(Node)
     metadata    = models.ForeignKey(Metadata)