CHANGELOG.md: Move unreleased changes to v0.4.1

I had left this there so I could remember how to get the number of
facets, but I don't need it anymore.

.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).
 
+## [0.4.1] - 2018-09-26
+### Changed
+- Use execute_values() to batch insert records to PostgreSQL
+
+## [0.4.0] - 2018-09-25
+### Fixed
+- Invalid OnCalendar syntax in dspace-statistics-indexer.timer
+- Major logic error in indexer.py
+
+## [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

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. Requires PostgreSQL version 9.5 or greater for [`UPSERT` support](https://wiki.postgresql.org/wiki/UPSERT).
+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 psycopg2-binary
+    $ 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

@@ -47,19 +47,26 @@ class ItemResource:
 
         cursor = db.cursor()
         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:

contrib/dspace-statistics-indexer.timer

@@ -3,7 +3,7 @@ Description=DSpace Statistics Indexer
 
 [Timer]
 # twice a day, at 6AM and 6PM
-OnCalendar=*-*-* 06:00:00,18:00:00
+OnCalendar=*-*-* 06,18:00:00
 # Add a random delay of 0–3600 seconds
 RandomizedDelaySec=3600
 Persistent=true

database.py

@@ -2,8 +2,7 @@ from config import DATABASE_NAME
 from config import DATABASE_USER
 from config import DATABASE_PASS
 from config import DATABASE_HOST
-import psycopg2
-import psycopg2.extras
+import psycopg2, psycopg2.extras
 
 def database_connection():
     connection = psycopg2.connect("dbname={} user={} password={} host='{}'".format(DATABASE_NAME, DATABASE_USER, DATABASE_PASS, DATABASE_HOST), cursor_factory=psycopg2.extras.DictCursor)

indexer.py

@@ -20,111 +20,140 @@
 # ---
 #
 # Connects to a DSpace Solr statistics core and ingests item views and downloads
-# into a Postgres 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
-# install with pip (I recommend setting up a Python virtual environment first):
+# This script is written for Python 3.5+ and requires several modules that you
+# 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
+import json
+import psycopg2.extras
 from solr import solr_connection
 
 def index_views():
-    print("Populating database with item views.")
-
-    # determine the total number of items with views (aka Solr's numFound)
+    # get total number of distinct facets for items with a minimum of 1 view,
+    # otherwise Solr returns all kinds of weird ids that are actually not in
+    # the database. Also, stats are expensive, but we need stats.calcdistinct
+    # so we can get the countDistinct summary.
+    #
+    # see: https://lucene.apache.org/solr/guide/6_6/the-stats-component.html
     res = solr.query('statistics', {
         'q':'type:2',
         'fq':'isBot:false AND statistics_type:view',
         'facet':True,
         'facet.field':'id',
+        'facet.mincount':1,
+        'facet.limit':1,
+        'facet.offset':0,
+        'stats':True,
+        'stats.field':'id',
+        'stats.calcdistinct':True
     }, rows=0)
 
-    # divide results into "pages" (numFound / 100)
-    results_numFound = res.get_num_found()
+    # get total number of distinct facets (countDistinct)
+    results_totalNumFacets = json.loads(res.get_json())['stats']['stats_fields']['id']['countDistinct']
+
+    # divide results into "pages" (cast to int to effectively round down)
     results_per_page = 100
-    results_num_pages = round(results_numFound / results_per_page)
+    results_num_pages = int(results_totalNumFacets / results_per_page)
     results_current_page = 0
 
     cursor = db.cursor()
 
+    # create an empty list to store values for batch insertion
+    data = []
+
     while results_current_page <= results_num_pages:
-        print('Page {} of {}.'.format(results_current_page, results_num_pages))
+        print('Indexing item views (page {} of {})'.format(results_current_page, results_num_pages))
 
         res = solr.query('statistics', {
             'q':'type:2',
             'fq':'isBot:false AND statistics_type:view',
             'facet':True,
             'facet.field':'id',
+            'facet.mincount':1,
             'facet.limit':results_per_page,
             'facet.offset':results_current_page * results_per_page
-        })
+        }, rows=0)
 
-        # make sure total number of results > 0
-        if res.get_num_found() > 0:
-            # SolrClient's get_facets() returns a dict of dicts
-            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():
-                cursor.execute('''INSERT INTO items(id, views) VALUES(%s, %s)
-                               ON CONFLICT(id) DO UPDATE SET downloads=excluded.views''',
-                               (item_id, item_views))
+        # SolrClient's get_facets() returns a dict of dicts
+        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():
+            data.append((item_id, item_views))
 
+        # do a batch insert of values from the current "page" of results
+        sql = 'INSERT INTO items(id, views) VALUES %s ON CONFLICT(id) DO UPDATE SET downloads=excluded.views'
+        psycopg2.extras.execute_values(cursor, sql, data, template='(%s, %s)')
         db.commit()
 
+        # clear all items from the list so we can populate it with the next batch
+        data.clear()
+
         results_current_page += 1
 
     cursor.close()
 
 def index_downloads():
-    print("Populating database with item downloads.")
-
-    # determine the total number of items with downloads (aka Solr's numFound)
+    # get the total number of distinct facets for items with at least 1 download
     res = solr.query('statistics', {
         'q':'type:0',
         'fq':'isBot:false AND statistics_type:view AND bundleName:ORIGINAL',
         'facet':True,
         'facet.field':'owningItem',
+        'facet.mincount':1,
+        'facet.limit':1,
+        'facet.offset':0,
+        'stats':True,
+        'stats.field':'owningItem',
+        'stats.calcdistinct':True
     }, rows=0)
 
-    # divide results into "pages" (numFound / 100)
-    results_numFound = res.get_num_found()
+    # get total number of distinct facets (countDistinct)
+    results_totalNumFacets = json.loads(res.get_json())['stats']['stats_fields']['owningItem']['countDistinct']
+
+    # divide results into "pages" (cast to int to effectively round down)
     results_per_page = 100
-    results_num_pages = round(results_numFound / results_per_page)
+    results_num_pages = int(results_totalNumFacets / results_per_page)
     results_current_page = 0
 
     cursor = db.cursor()
 
+    # create an empty list to store values for batch insertion
+    data = []
+
     while results_current_page <= results_num_pages:
-        print('Page {} of {}.'.format(results_current_page, results_num_pages))
+        print('Indexing item downloads (page {} of {})'.format(results_current_page, results_num_pages))
 
         res = solr.query('statistics', {
             'q':'type:0',
             'fq':'isBot:false AND statistics_type:view AND bundleName:ORIGINAL',
             'facet':True,
             'facet.field':'owningItem',
+            'facet.mincount':1,
             'facet.limit':results_per_page,
             'facet.offset':results_current_page * results_per_page
-        })
+        }, rows=0)
 
-        # make sure total number of results > 0
-        if res.get_num_found() > 0:
-            # SolrClient's get_facets() returns a dict of dicts
-            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():
-                cursor.execute('''INSERT INTO items(id, downloads) VALUES(%s, %s)
-                               ON CONFLICT(id) DO UPDATE SET downloads=excluded.downloads''',
-                               (item_id, item_downloads))
+        # SolrClient's get_facets() returns a dict of dicts
+        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():
+            data.append((item_id, item_downloads))
 
+        # do a batch insert of values from the current "page" of results
+        sql = 'INSERT INTO items(id, downloads) VALUES %s ON CONFLICT(id) DO UPDATE SET downloads=excluded.downloads'
+        psycopg2.extras.execute_values(cursor, sql, data, template='(%s, %s)')
         db.commit()
 
+        # clear all items from the list so we can populate it with the next batch
+        data.clear()
+
         results_current_page += 1
 
     cursor.close()

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