Update docs to remove SQLite stuff

I've decided to use PostgreSQL instead of SQLite because the UPSERT
support is available in versions of PostgreSQL we're alread running,
whereas SQLite needs a VERY new (3.24.0) version that is not avail-
able on any recent long-term support Ubuntu releases.

.gitignore

@@ -1,3 +1,2 @@
 __pycache__
 venv
-*.db

CHANGELOG.md

@@ -4,6 +4,10 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [0.2.0] - 2018-09-24
+### Changed
+- Use PostgreSQL instead of SQLite because UPSERT support needs a very new libsqlite3 whereas it's already in PostgreSQL 9.5+
+
 ## [0.1.0] - 2018-09-24
 ### Changed
 - Rename project to "DSpace Statistics API"

README.md

@@ -1,14 +1,14 @@
 # DSpace Statistics API
 A quick and dirty REST API to expose Solr view and download statistics for items in a DSpace repository.
 
-Written and tested in Python 3.6. SolrClient (0.2.1) does not currently run in Python 3.7.0.
+Written and tested in Python 3.6. SolrClient (0.2.1) does not currently run in Python 3.7.0. Requires PostgreSQL version 9.5 or greater for [`UPSERT` support](https://wiki.postgresql.org/wiki/UPSERT).
 
 ## Installation
 Create a virtual environment and run it:
 
     $ virtualenv -p /usr/bin/python3.6 venv
     $ . venv/bin/activate
-    $ pip install falcon gunicorn SolrClient
+    $ pip install falcon gunicorn SolrClient psycopg2-binary
     $ gunicorn app:api
 
 ## Todo

app.py

@@ -2,11 +2,12 @@
 # See DSpace Solr docs for tips about parameters
 # https://wiki.duraspace.org/display/DSPACE/Solr
 
-from database import database_connection_ro
+from database import database_connection
 import falcon
 from solr import solr_connection
 
-db = database_connection_ro()
+db = database_connection()
+db.set_session(readonly=True)
 solr = solr_connection()
 
 class AllItemsResource:

config.py

@@ -3,6 +3,9 @@ import os
 # Check if Solr connection information was provided in the environment
 SOLR_SERVER = os.environ.get('SOLR_SERVER', 'http://localhost:8080/solr')
 
-SQLITE_DB = os.environ.get('SQLITE_DB', 'statistics.db')
+DATABASE_NAME = os.environ.get('DATABASE_NAME', 'dspacestatistics')
+DATABASE_USER = os.environ.get('DATABASE_USER', 'dspacestatistics')
+DATABASE_PASS = os.environ.get('DATABASE_PASS', 'dspacestatistics')
+DATABASE_HOST = os.environ.get('DATABASE_HOST', 'localhost')
 
 # vim: set sw=4 ts=4 expandtab:

database.py

@@ -1,17 +1,11 @@
-from config import SQLITE_DB
+from config import DATABASE_NAME
-import sqlite3
+from config import DATABASE_USER
+from config import DATABASE_PASS
+from config import DATABASE_HOST
+import psycopg2
 
-def database_connection_rw():
+def database_connection():
-    connection = sqlite3.connect(SQLITE_DB)
+    connection = psycopg2.connect("dbname={} user={} password={} host='{}'".format(DATABASE_NAME, DATABASE_USER, DATABASE_PASS, DATABASE_HOST))
-    # allow iterating over row results by column key
-    connection.row_factory = sqlite3.Row
-
-    return connection
-
-def database_connection_ro():
-    connection = sqlite3.connect('file:{0}?mode=ro'.format(SQLITE_DB), uri=True)
-    # allow iterating over row results by column key
-    connection.row_factory = sqlite3.Row
 
     return connection
 

indexer.py

@@ -20,7 +20,7 @@
 # ---
 #
 # Connects to a DSpace Solr statistics core and ingests item views and downloads
-# into a SQLite database for use with other applications (an API, for example).
+# into a Postgres database for use with other applications (an API, for example).
 #
 # This script is written for Python 3 and requires several modules that you can
 # install with pip (I recommend setting up a Python virtual environment first):
@@ -32,7 +32,7 @@
 #
 # Tested with Python 3.5 and 3.6.
 
-from database import database_connection_rw
+from database import database_connection
 from solr import solr_connection
 
 def index_views():
@@ -52,6 +52,8 @@ def index_views():
     results_num_pages = round(results_numFound / results_per_page)
     results_current_page = 0
 
+    cursor = db.cursor()
+
     while results_current_page <= results_num_pages:
         print('Page {0} of {1}.'.format(results_current_page, results_num_pages))
 
@@ -70,7 +72,7 @@ def index_views():
             views = res.get_facets()
             # in this case iterate over the 'id' dict and get the item ids and views
             for item_id, item_views in views['id'].items():
-                db.execute('''INSERT INTO items(id, views) VALUES(?, ?)
+                cursor.execute('''INSERT INTO items(id, views) VALUES(%s, %s)
                                ON CONFLICT(id) DO UPDATE SET downloads=excluded.views''',
                                (item_id, item_views))
 
@@ -78,6 +80,8 @@ def index_views():
 
         results_current_page += 1
 
+    cursor.close()
+
 def index_downloads():
     print("Populating database with item downloads.")
 
@@ -95,6 +99,8 @@ def index_downloads():
     results_num_pages = round(results_numFound / results_per_page)
     results_current_page = 0
 
+    cursor = db.cursor()
+
     while results_current_page <= results_num_pages:
         print('Page {0} of {1}.'.format(results_current_page, results_num_pages))
 
@@ -113,7 +119,7 @@ def index_downloads():
             downloads = res.get_facets()
             # in this case iterate over the 'owningItem' dict and get the item ids and downloads
             for item_id, item_downloads in downloads['owningItem'].items():
-                db.execute('''INSERT INTO items(id, downloads) VALUES(?, ?)
+                cursor.execute('''INSERT INTO items(id, downloads) VALUES(%s, %s)
                                ON CONFLICT(id) DO UPDATE SET downloads=excluded.downloads''',
                                (item_id, item_downloads))
 
@@ -121,11 +127,14 @@ def index_downloads():
 
         results_current_page += 1
 
-db = database_connection_rw()
+    cursor.close()
+
+db = database_connection()
 solr = solr_connection()
 
 # create table to store item views and downloads
-db.execute('''CREATE TABLE IF NOT EXISTS items
+cursor = db.cursor()
+cursor.execute('''CREATE TABLE IF NOT EXISTS items
                   (id INT PRIMARY KEY, views INT DEFAULT 0, downloads INT DEFAULT 0)''')
 index_views()
 index_downloads()