[FIX] merge correction import.

annotations/static/annotations/document.js

@@ -2,10 +2,13 @@
   'use strict';
 
   var annotationsAppDocument = angular.module('annotationsAppDocument', ['annotationsAppHttp']);
-
   annotationsAppDocument.controller('DocController',
     ['$scope', '$rootScope', '$timeout', 'NgramListHttpService', 'DocumentHttpService',
     function ($scope, $rootScope, $timeout, NgramListHttpService, DocumentHttpService) {
+
+      // dataLoading = signal pour afficher wait
+      $scope.dataLoading = true ;
+
       $rootScope.documentResource = DocumentHttpService.get(
         {'docId': $rootScope.docId},
         function(data, responseHeaders) {
@@ -27,6 +30,7 @@
             function(data) {
               $rootScope.annotations = data[$rootScope.corpusId.toString()][$rootScope.docId.toString()];
               $rootScope.lists = data[$rootScope.corpusId.toString()].lists;
+              $scope.dataLoading = false ;
             },
             function(data) {
               console.error("unable to get the list of ngrams");
@@ -34,6 +38,7 @@
           );
 
       });
+
       // TODO setup article pagination
       $scope.onPreviousClick = function () {
         DocumentHttpService.get($scope.docId - 1);

annotations/templates/annotations/main.html

@@ -86,6 +86,16 @@
                 <li class="list-group-item small"><span class="badge">date</span>{[{publication_date}]}</li>
               </ul>
             </div>
+
+            <div ng-if="dataLoading">
+                Loading text...
+                <br>
+                  <center>
+                    <img width="10%" src="{% static 'img/ajax-loader.gif'%}"></img>
+                  </center>
+                <br>
+            </div>
+
             <div ng-if="abstract_text != null">
                 <span class="badge">abstract</span>
             </div>

parsing/NgramsExtractors/NgramsExtractor.py

 # from ..Taggers import NltkTagger
 from ..Taggers import TurboTagger
 import nltk
+from re import sub
 
 
 """Base class for all ngrams extractors.
@@ -33,9 +34,21 @@ class NgramsExtractor:
     Returns a list of the ngrams found in the given text.
     """
     def extract_ngrams(self, contents):
-        tagged_tokens = list(self.tagger.tag_text(contents))
+        clean_contents = self._prepare_text(contents)
+
+        # ici tagging
+        tagged_tokens = list(self.tagger.tag_text(clean_contents))
+
         if len(tagged_tokens):
             grammar_parsed = self._grammar.parse(tagged_tokens)
             for subtree in grammar_parsed.subtrees():
                 if subtree.label() == self._label:
                     yield subtree.leaves()
+
+    @staticmethod
+    def _prepare_text(text_contents):
+        """
+        Clean the text for better POS tagging
+        """
+        # strip xml tags
+        return sub(r"<[^>]{0,45}>","",text_contents)