CHANGELOG.md: Release version 0.3.2

SolrClient 0.2.1 currently depends on kazoo 2.2.1, but there is an
issue with Python 3.7 in kazoo <= 2.5.0. Kazoo 2.5.0 fixes the is-
sue with Python 3.7, and for my limited usage of SolrClient it se-
ems to work fine.

See: https://github.com/moonlitesolutions/SolrClient/issues/79

.gitignore

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

.travis.yml

@@ -0,0 +1,9 @@
+language: python
+python:
+  - "3.5"
+  - "3.6"
+  - "3.7"
+install:
+  - pip install -r requirements.txt
+
+# vim: ts=2 sw=2 et

CHANGELOG.md

@@ -4,6 +4,33 @@ 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).
 
+## [0.3.2] - 2018-09-25
+## Changed
+- /item/id route now returns HTTP 404 if an item is not found
+
+## [0.3.1] - 2018-09-25
+### Changed
+- Force SolrClient's kazoo dependency to version 2.5.0 to work with Python 3.7
+- Add Python 3.7 to Travis CI configuration
+
+## [0.3.0] - 2018-09-25
+### Added
+- requirements.txt for pip
+- Travis CI build configuration for Python 3.5 and 3.6
+- Documentation on using the API
+
+### Changed
+- The "all items" route from / to /items
+
+## [0.2.1] - 2018-09-24
+### Changed
+- Environment settings in example systemd unit files
+- Use psycopg2.extras.DictCursor for PostgreSQL connection
+
+## [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

@@ -1,22 +1,30 @@
 # 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 3.5, 3.6, and 3.7. 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
+    $ python -m venv venv
     $ . venv/bin/activate
-    $ pip install falcon gunicorn SolrClient
+    $ pip install -r requirements.txt
     $ gunicorn app:api
 
+## Using the API
+The API exposes the following endpoints:
+
+  - GET `/items` — return views and downloads for all items that Solr knows about¹. Accepts `limit` and `page` query parameters for pagination of results.
+  - GET `/item/id` — return views and downloads for a single item (*id* must be a positive integer). Returns HTTP 404 if an item id is not found.
+
+¹ We are querying the Solr statistics core, which technically only knows about items that have either views or downloads.
+
 ## Todo
 
 - Add API documentation
 - Close up DB connection when gunicorn shuts down gracefully
 - Better logging
-- Return HTTP 404 when item_id is nonexistent
+- Tests
 
 ## License
 This work is licensed under the [GPLv3](https://www.gnu.org/licenses/gpl-3.0.en.html).

app.py

@@ -1,12 +1,9 @@
-# Tested with Python 3.6
+from database import database_connection
-# See DSpace Solr docs for tips about parameters
-# https://wiki.duraspace.org/display/DSPACE/Solr
-
-from database import database_connection_ro
 import falcon
 from solr import solr_connection
 
-db = database_connection_ro()
+db = database_connection()
+db.set_session(readonly=True)
 solr = solr_connection()
 
 class AllItemsResource:
@@ -24,7 +21,7 @@ class AllItemsResource:
         pages = round(cursor.fetchone()[0] / limit)
 
         # get statistics, ordered by id, and use limit and offset to page through results
-        cursor.execute('SELECT id, views, downloads FROM items ORDER BY id ASC LIMIT {0} OFFSET {1}'.format(limit, offset))
+        cursor.execute('SELECT id, views, downloads FROM items ORDER BY id ASC LIMIT {} OFFSET {}'.format(limit, offset))
         results = cursor.fetchmany(limit)
         cursor.close()
 
@@ -49,20 +46,27 @@ class ItemResource:
         """Handles GET requests"""
 
         cursor = db.cursor()
-        cursor.execute('SELECT views, downloads FROM items WHERE id={0}'.format(item_id))
+        cursor.execute('SELECT views, downloads FROM items WHERE id={}'.format(item_id))
-        results = cursor.fetchone()
+        if cursor.rowcount == 0:
+            raise falcon.HTTPNotFound(
+                    title='Item not found',
+                    description='The item with id "{}" was not found.'.format(item_id)
+            )
+        else:
+            results = cursor.fetchone()
+
+            statistics = {
+                'id': item_id,
+                'views': results['views'],
+                'downloads': results['downloads']
+            }
+
+            resp.media = statistics
+
         cursor.close()
 
-        statistics = {
-            'id': item_id,
-            'views': results['views'],
-            'downloads': results['downloads']
-        }
-
-        resp.media = statistics
-
 api = falcon.API()
-api.add_route('/', AllItemsResource())
+api.add_route('/items', AllItemsResource())
 api.add_route('/item/{item_id:int}', ItemResource())
 
 # vim: set sw=4 ts=4 expandtab:

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:

contrib/dspace-statistics-api.service

@@ -3,7 +3,10 @@ Description=DSpace Statistics API
 After=network.target
 
 [Service]
-Environment=SOLR_SERVER=http://localhost:8081/solr
+Environment=DATABASE_NAME=dspacestatistics
+Environment=DATABASE_USER=dspacestatistics
+Environment=DATABASE_PASS=dspacestatistics
+Environment=DATABASE_HOST=localhost
 User=nobody
 Group=nogroup
 WorkingDirectory=/opt/ilri/dspace-statistics-api

contrib/dspace-statistics-indexer.service

@@ -4,6 +4,10 @@ After=tomcat7.target
 
 [Service]
 Environment=SOLR_SERVER=http://localhost:8081/solr
+Environment=DATABASE_NAME=dspacestatistics
+Environment=DATABASE_USER=dspacestatistics
+Environment=DATABASE_PASS=dspacestatistics
+Environment=DATABASE_HOST=localhost
 User=nobody
 Group=nogroup
 WorkingDirectory=/opt/ilri/dspace-statistics-api

database.py

@@ -1,17 +1,12 @@
-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
+import psycopg2.extras
 
-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), cursor_factory=psycopg2.extras.DictCursor)
-    # 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

@@ -20,19 +20,17 @@
 # ---
 #
 # 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 PostgreSQL database for use by other applications (like an API).
 #
-# This script is written for Python 3 and requires several modules that you can
+# This script is written for Python 3.5+ and requires several modules that you
-# install with pip (I recommend setting up a Python virtual environment first):
+# can install with pip (I recommend using a Python virtual environment):
 #
-#   $ pip install SolrClient
+#   $ pip install SolrClient psycopg2-binary
 #
 # See: https://solrclient.readthedocs.io/en/latest/SolrClient.html
 # See: https://wiki.duraspace.org/display/DSPACE/Solr
-#
-# 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():
@@ -52,8 +50,10 @@ 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))
+        print('Page {} of {}.'.format(results_current_page, results_num_pages))
 
         res = solr.query('statistics', {
             'q':'type:2',
@@ -70,7 +70,7 @@ 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 +78,8 @@ def index_views():
 
         results_current_page += 1
 
+    cursor.close()
+
 def index_downloads():
     print("Populating database with item downloads.")
 
@@ -95,8 +97,10 @@ 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))
+        print('Page {} of {}.'.format(results_current_page, results_num_pages))
 
         res = solr.query('statistics', {
             'q':'type:0',
@@ -113,7 +117,7 @@ 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 +125,14 @@ 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()

requirements.txt

@@ -0,0 +1,12 @@
+certifi==2018.8.24
+chardet==3.0.4
+falcon==1.4.1
+gunicorn==19.9.0
+idna==2.7
+kazoo==2.5.0
+psycopg2-binary==2.7.5
+python-mimeparse==1.6.0
+requests==2.19.1
+six==1.11.0
+SolrClient==0.2.1
+urllib3==1.23