Merge branch 'testing' into testing-jwt

docs/architecture.md

+
+# Definitions and notation for the documentation (!= python notation)
+
+## Node
+
+The table (nodes) is a list of nodes: [Node]
+
+Each Node has:
+- a typename
+- a parent_id
+- a name
+
+
+### Each Node has a parent_id
+
+Node A
+├── Node B
+└── Node C
+
+If Node A is Parent of Node B and Node C
+then NodeA.id == NodeB.parent_id == NodeC.parent_id.
+
+### Each Node has a typename
+
+Notation: Node[foo](bar) is a Node of typename "foo" and with name "bar".
+
+Then:
+    - Then Node[project] is a project.
+    - Then Node[corpus] is a corpus.
+    - Then Node[document] is a document.
+
+
+### Each Node as a typename and a parent
+
+
+Node[user](name)
+├── Node[project](myProject1)
+│   ├── Node[corpus](myCorpus1)
+│   ├── Node[corpus](myCorpus2)
+│   └── Node[corpus](myCorpus3)
+└── Node[project](myProject2)
+
+
+/!\ 3 way to manage rights of the Node:
+    1) Then Node[User] is a folder containing all User projects and corpus and
+documents (i.e. Node[user] is the parent_id of the children).
+    2) Each node as a user_id (mainly used today)
+    3) Right management for the groups (implemented already but not
+    used since not connected to the frontend).
+
+
+## Global Parameters
+
+Global User is Gargantua (Node with typename User).
+This node is the parent of the others Nodes for parameters.
+
+Node[user](gargantua) (gargantua.id == Node[user].user_id)
+├── Node[TFIDF-Global](global) : without group
+│   ├── Node[tfidf](database1)
+│   ├── Node[tfidf](database2)
+│   └── Node[tfidf](database2)
+└── Node[anotherMetric](global)
+
+
+
+## NodeNgram
+
+NodeNgram is a relation of a Node with a ngram:
+    - document and ngrams
+    - metrics  and ngrams (position of the node metrics indicates the
+      context)
+
+
+
+
+# Community Parameters
+
+
+# User Parameters
+
+
+

docs/index.md

@@ -8,6 +8,9 @@ Gargantext is a web plateform to explore your corpora using text-mining[...](abo
 
 * [Take a tour](demo.md) of the different features offered by Gargantext
 
+## Architecture
+* [Architecture](architecture.md) Architecture of Gargantext
+
 ##Need some help?
 
 Ask the community at:

gargantext/util/toolchain/parsing.py

@@ -175,7 +175,6 @@ def parse(corpus):
                         hyperdata = hyperdata,
                     )
                     session.add(document)
-                    session.commit()
                     documents_count += 1
 
                     if pending_add_error_stats:
@@ -190,6 +189,9 @@ def parse(corpus):
                         session.add(corpus)
                         session.commit()
 
+                # Commit any pending document
+                session.commit()
+
                 # update info about the resource
                 resource['extracted'] = True
                 #print( "resource n°",i, ":", d, "docs inside this file")

install/gargamelle/nginx.config

+
+##
+# You should look at the following URL's in order to grasp a solid understanding
+# of Nginx configuration files in order to fully unleash the power of Nginx.
+# http://wiki.nginx.org/Pitfalls
+# http://wiki.nginx.org/QuickStart
+# http://wiki.nginx.org/Configuration
+#
+# Generally, you will want to move this file somewhere, and start with a clean
+# file but keep this around for reference. Or just disable in sites-enabled.
+#
+# Please see /usr/share/doc/nginx-doc/examples/ for more detailed examples.
+##
+
+# the upstream component nginx needs to connect to
+upstream gargantext {
+    server unix:///tmp/gargantext.sock; # for a file socket
+    #server 127.0.0.1:8001; # for a web port socket (we'll use this first)
+}
+
+# Default server configuration
+#
+server {
+        listen 80 default_server;
+        listen [::]:80 default_server;
+
+        # SSL configuration
+        #
+        # listen 443 ssl default_server;
+        # listen [::]:443 ssl default_server;
+        #
+        # Note: You should disable gzip for SSL traffic.
+        # See: https://bugs.debian.org/773332
+        #
+        # Read up on ssl_ciphers to ensure a secure configuration.
+        # See: https://bugs.debian.org/765782
+        #
+        # Self signed certs generated by the ssl-cert package
+        # Don't use them in a production server!
+        #
+        # include snippets/snakeoil.conf;
+
+        client_max_body_size 800M;
+        client_body_timeout 12;
+        client_header_timeout 12;
+        keepalive_timeout 15;
+        send_timeout 10;
+
+        root /var/www/html;
+
+        # Add index.php to the list if you are using PHP
+        #index index.html index.htm index.nginx-debian.html;
+
+        server_name _ stable.gargantext.org gargantext.org ;
+
+            # Django media
+
+        location /media  {
+                alias /var/www/gargantext/media;  # your Django project's media files - amend as required
+        }
+
+        location /static {
+                alias /srv/gargantext_static; # your Django project's static files - amend as required
+        }
+
+        # Finally, send all non-media requests to the Django server.
+        location / {
+                uwsgi_pass  gargantext;
+                include     uwsgi_params;
+        }
+        #access_log off;
+        access_log /var/log/nginx/access.log;
+        error_log /var/log/nginx/error.log;
+}
+
+
+server {
+    listen 80 ;
+    listen [::]:80;
+    server_name dl.gargantext.org ;
+    error_page 404 /index.html;
+
+
+    location / {
+        root /var/www/dl ;
+        proxy_set_header Host $host;
+        proxy_buffering off;
+
+}
+    access_log /var/log/nginx/dl.gargantext.org-access.log;
+    error_log /var/log/nginx/dl.gargantext.org-error.log;
+}
+
+