From 9e942736b1b96926b2bedbbe47bafb35bae85695 Mon Sep 17 00:00:00 2001
From: Alan Orth <alan.orth@gmail.com>
Date: Sun, 23 Sep 2018 16:47:00 +0300
Subject: [PATCH] app.py: Get item statistics from SQLite database

It is much more efficient to cache view and download statistics in
a database than to query Solr on demand (not to mention that it is
not possible to page easily with facets in Solr). I decided to use
SQLite because it is fast, native in Python 3, and doesn't require
any extra steps during provisioning (assuming permissions are ok).
---
 app.py      | 30 +++++++++++++++++-------------
 config.py   |  2 ++
 database.py | 11 +++++++++++
 3 files changed, 30 insertions(+), 13 deletions(-)
 create mode 100644 database.py

diff --git a/app.py b/app.py
index 75b7e90..1f54588 100644
--- a/app.py
+++ b/app.py
@@ -3,29 +3,33 @@
 # https://wiki.duraspace.org/display/DSPACE/Solr
 
 from config import SOLR_CORE
+from database import database_connection
 import falcon
 from solr import solr_connection
 
+db = database_connection()
+solr = solr_connection()
 
 class ItemResource:
     def on_get(self, req, resp, item_id):
         """Handles GET requests"""
 
-        # Get views
-        res = solr.query(SOLR_CORE, {
-            'q':'type:2 AND id:{0}'.format(item_id),
-            'fq':'isBot:false AND statistics_type:view'
-        }, rows=0)
+        cursor = db.cursor()
+        # get item views (and catch the TypeError if item doesn't have any views)
+        cursor.execute('SELECT views FROM itemviews WHERE id={0}'.format(item_id))
+        try:
+            views = cursor.fetchone()['views']
+        except:
+            views = 0
 
-        views = res.get_num_found()
+        # get item downloads (and catch the TypeError if item doesn't have any downloads)
+        cursor.execute('SELECT downloads FROM itemdownloads WHERE id={0}'.format(item_id))
+        try:
+            downloads = cursor.fetchone()['downloads']
+        except:
+            downloads = 0
 
-        # Get downloads
-        res = solr.query(SOLR_CORE, {
-            'q':'type:0 AND owningItem:{0}'.format(item_id),
-            'fq':'isBot:false AND statistics_type:view AND bundleName:ORIGINAL'
-        }, rows=0)
-
-        downloads = res.get_num_found() 
+        cursor.close()
 
         statistics = {
             'id': item_id,
diff --git a/config.py b/config.py
index adbc0fe..b4f4fb4 100644
--- a/config.py
+++ b/config.py
@@ -4,4 +4,6 @@ import os
 SOLR_SERVER = os.environ.get('SOLR_SERVER', 'http://localhost:8080/solr')
 SOLR_CORE = os.environ.get('SOLR_CORE', 'statistics')
 
+SQLITE_DB = os.environ.get('SQLITE_DB', 'statistics.db')
+
 # vim: set sw=4 ts=4 expandtab:
diff --git a/database.py b/database.py
new file mode 100644
index 0000000..fa5ed53
--- /dev/null
+++ b/database.py
@@ -0,0 +1,11 @@
+from config import SQLITE_DB
+import sqlite3
+
+def database_connection():
+    connection = sqlite3.connect(SQLITE_DB)
+    # allow iterating over row results by column key
+    connection.row_factory = sqlite3.Row
+
+    return connection
+
+# vim: set sw=4 ts=4 expandtab: