Merge branch 'unstable' of ssh://delanoe.org:1979/gargantext into samuel

analysis/functions.py

@@ -54,6 +54,9 @@ def create_whitelist(user, corpus, size=100):
             n.type_id = %d
         AND
         ngX.n >= 2
+        AND
+        ngX.n <= 3
+
 
         GROUP BY
             ngX.id
@@ -254,7 +257,7 @@ def tfidf(corpus, document, ngram):
         # result = tf * idf
         result = term_frequency * inverse_d_frequency
     except Exception as error:
-        print(error)
+        print(error, ngram)
         result = 0
     return result
 

gargantext_web/views.py

@@ -341,41 +341,41 @@ def corpus(request, project_id, corpus_id):
 #    except:
 #        sources_donut = []
     # Do a javascript query/api for that
-    query_date = """
-        SELECT
-            id,
-            metadata -> 'publication_year' as year,
-            metadata -> 'publication_month' as month, 
-            metadata -> 'publication_day' as day,
-            metadata -> 'title'
-        FROM
-            node_node AS n
-        WHERE
-            n.parent_id = %d
-        ORDER BY
-            year, month, day DESC
-        LIMIT
-            20
-        OFFSET
-            %d
-    """ % (corpus.id, 0)
-    try:
-        cursor = connection.cursor()
-
-        cursor.execute(query_date)
-        documents = list()
-        while True:
-            document = dict()
-            row = cursor.fetchone()
-            
-            if row is None:
-                break
-            document['id']      = row[0]
-            document['date']    = row[1] + '/' + row[2] + '/' + row[3]
-            document['title']   = row[4]
-            documents.append(document)
-    except Exception as error:
-        print(error)
+#    query_date = """
+#        SELECT
+#            id,
+#            metadata -> 'publication_year' as year,
+#            metadata -> 'publication_month' as month, 
+#            metadata -> 'publication_day' as day,
+#            metadata -> 'title'
+#        FROM
+#            node_node AS n
+#        WHERE
+#            n.parent_id = %d
+#        ORDER BY
+#            year, month, day DESC
+#        LIMIT
+#            20
+#        OFFSET
+#            %d
+#    """ % (corpus.id, 0)
+#    try:
+#        cursor = connection.cursor()
+#
+#        cursor.execute(query_date)
+#        documents = list()
+#        while True:
+#            document = dict()
+#            row = cursor.fetchone()
+#            
+#            if row is None:
+#                break
+#            document['id']      = row[0]
+#            document['date']    = row[1] + '/' + row[2] + '/' + row[3]
+#            document['title']   = row[4]
+#            documents.append(document)
+#    except Exception as error:
+#        print(error)
 
     try:
         chart = dict()
@@ -390,7 +390,7 @@ def corpus(request, project_id, corpus_id):
             'date': date,\
             'project': project,\
             'corpus' : corpus,\
-            'documents': documents,\
+#            'documents': documents,\
             'number' : number,\
             'dates' : chart,\
             }))

init/README.rst

@@ -139,4 +139,18 @@ Start the Django server
 -----------------------
 in bash to launch python env : /srv/gargantext_env/bin/activate
 In Pyvenv:
-python manage.py runserver
+$ python manage.py runserver
+
+
+For Production Server
+---------------------
+
+git checkout stable
+
+$ sudo aptitude install rabbitmq-server
+$ sudo aptitude install tmux
+# In your python envrionment:
+$ tmux -c ./manage.py celery worker --loglevel=info
+$ python manage.py runserver
+
+

init/README_old.txt

-Here informations for installation:
------------------------------------
-
-
-I - Local Installation
-All informations are in init folder
-
-1) Create virtualenv with python version 3.4
-
-2) pip install -r requirements.txt
-
-3) Manually install nltk (inside the sources)
-	nltk==3.0a4
-
-4) adapt database configuration in gargantext_web settings 
-(Development done on postgresql)
-
-5) source env/bin/activate
-
-6) ./manage.py runserver
-
-That's all

parsing/FileParsers/EuropressFileParser.py

@@ -28,11 +28,12 @@ class EuropressFileParser(FileParser):
         if encoding != "utf-8":
             try:
                 contents = contents.decode("latin1", errors='replace').encode(codif)
-            except :
-                try:
-                    contents = contents.decode(encoding, errors='replace').encode(codif)
-                except Exception as error:
-                    print(error)
+            except Exception as error:
+                print(error)
+#                try:
+#                    contents = contents.decode(encoding, errors='replace').encode(codif)
+#                except Exception as error:
+#                    print(error)
 
         try:
             html_parser = etree.HTMLParser(encoding=codif)

templates/home.html

@@ -24,12 +24,16 @@
 				<div class="row">
 						<div class="content">
 						<center>
+						<img src="http://s3.lprs1.fr/images/2015/01/08/4429565_je-suis-charlie_545x460_autocrop.jpg" alt="Je suis Charlie" style="100px; height:150px">
+
+						<!--
 						<h2>Introduction Video</h2>
 						<video width="320" height="240" controls>
 						<source src="movie.mp4" type="video/mp4">
 						<source src="movie.ogg" type="video/ogg">
 						Your browser does not support this video sorry. Try Firefox or Chromium.
 						</video>
+						--!>
 						</center>
 				</div>
 				</div>

templates/subcorpus.html

@@ -22,7 +22,6 @@
 
 {% if documents %}
 
-<p>Paginator stuff</p>
 <ul>
 {% for doc in documents %}
     {% if doc.date %}
@@ -31,4 +30,4 @@
 {% endfor %}
 </ul>
 
-{% endif %}
\ No newline at end of file
+{% endif %}