[UPDATE] last stable version

gargantext_web/urls.py

@@ -51,6 +51,7 @@ urlpatterns = patterns('',
     url(r'^corpus/(\d+)/node_link.json$', views.node_link),
     url(r'^corpus/(\d+)/adjacency.json$', views.adjacency),
     url(r'^api/tfidf/(\d+)/(\w+)$', views.tfidf),
+    url(r'^api/tfidf2/(\d+)/(\w+)$', views.tfidf2),
 
     # Data management
     url(r'^api$', gargantext_web.api.Root),

gargantext_web/views.py

@@ -912,6 +912,35 @@ def nodeinfo(request , node_id):
     return HttpResponse(html)
 
 
+def tfidf2(request, corpus_id, ngram_id):
+    """
+    Takes IDs of corpus and ngram and returns list of relevent documents in json format
+    according to TFIDF score (order is decreasing).
+    """
+    #it will receive something like:  api/tfidf/corpus_id/NGRAM1aNGRAM2aNGRAM3aNGRAM4...
+    docsids = ngram_id.split("a")
+
+    tfidf_list = []
+    for i in docsids:
+        pub = Node.objects.get(id=i)
+        finalpub = {}
+        finalpub["id"] = pub.id
+        pubmetadata = pub.metadata
+        if "title" in pubmetadata: finalpub["title"] = pubmetadata['title']
+        if "publication_date" in pubmetadata: finalpub["publication_date"] = pubmetadata['publication_date']
+        if "journal" in pubmetadata: finalpub["journal"] = pubmetadata['journal']
+        if "authors" in pubmetadata: finalpub["authors"] = pubmetadata['authors']
+        if "fields" in pubmetadata: finalpub["fields"] = pubmetadata['fields']
+        tfidf_list.append(finalpub) # doing a dictionary with only available atributes
+        if len(tfidf_list)==6: break # max 6 papers
+    
+    data = json.dumps(tfidf_list) 
+
+
+
+    # data = ["hola","mundo"]
+    return JsonHttpResponse(data)
+
 def tfidf(request, corpus_id, ngram_id):
     """
     Takes IDs of corpus and ngram and returns list of relevent documents in json format

node/models.py

@@ -24,6 +24,9 @@ from gargantext_web.settings import MEDIA_ROOT
 from celery.contrib.methods import task_method
 from celery import current_app
 
+import os
+import subprocess
+
 
 # Some usefull functions
 # TODO: start the function name with an underscore (private)
@@ -278,8 +281,6 @@ class Node(CTENode):
         self.metadata['Processing'] = 0
         self.save()
 
-
-
     def runInParallel(self, *fns):
         proc = []
         for fn in fns:
@@ -484,6 +485,7 @@ class Node(CTENode):
         labels = dict()
         weight = dict()
 
+        print("PRINTING NUMBER OF NODES 01:",len(G))
         for e in G.edges_iter():
             n1 = e[0]
             n2 = e[1]
@@ -528,6 +530,7 @@ class Node(CTENode):
                     G.add_edge(node, "cluster " + str(partition[node]), weight=3)
                 except Exception as error:
                     print("ERROR:",error)
+            print("PRINTING NUMBER OF NODES 02:",len(G))
             data = json_graph.node_link_data(G)
 
         elif type == "adjacency":
@@ -545,14 +548,20 @@ class Node(CTENode):
         
         return data
 
-        
-
     def workflow__MOV(self, keys=None, ngramsextractorscache=None, ngramscaches=None, verbose=False):
         import time
         total = 0
         self.metadata['Processing'] = 1
         self.save()
 
+        # # pwd = subprocess.Popen("cd /srv/gargantext/parsing/Taggers/nlpserver && pwd", stdout=subprocess.PIPE).stdout.read()
+        # # print(subprocess.Popen(['ls', '-lah'], stdout=subprocess.PIPE).communicate()[0].decode('utf-8'))
+        # print("activating nlpserver:")
+        # command = 'cd parsing/Taggers/nlpserver; python3 server.py'
+        # process = subprocess.Popen(command,stdout=subprocess.PIPE , stderr=subprocess.DEVNULL , shell=True)
+        
+
+
         print("LOG::TIME: In workflow()    parse_resources__MOV()")
         start = time.time()
         theMetadata = self.parse_resources__MOV()
@@ -575,6 +584,9 @@ class Node(CTENode):
         total += (end - start)
         print ("LOG::TIME:_ "+datetime.datetime.now().isoformat()+" extract_ngrams__MOV() [s]",(end - start))
 
+        # process.kill()
+        # print("ok, process killed")
+
         start = time.time()
         print("LOG::TIME: In workflow()    do_tfidf()")
         resultDict = self.do_tfidf__MOV( FreqList , theMetadata)
@@ -591,9 +603,6 @@ class Node(CTENode):
         total += (end - start)
         print ("LOG::TIME:_ "+datetime.datetime.now().isoformat()+" do_coocmatrix() [s]",(end - start))
 
-        # import pprint
-        # pprint.pprint(jsongraph)
-
         print("the user:",self.user)
         print("the project id:",self.parent.id)
         print("the corpus id:",self.id)

templates/project.html

@@ -424,8 +424,8 @@
 		//CSS events for changing the Select element
 		function CustomForSelect( selected ) {
 			// show Radio-Inputs and trigger FileOrNotFile>@upload-file events
-			//if(selected=="pubmed" || selected=="istext") {
-			if(selected=="pubmed") {
+			if(selected=="pubmed" || selected=="istext") {
+			// if(selected=="pubmed") {
 				console.log("show the button for: "+selected)
 				$("#pubmedcrawl").css("visibility", "visible"); 
 				$("#pubmedcrawl").show();