CHANGELOG.md: Update changes and move to 0.4.2

This was inserting correctly on the first run, but subsequent runs
were inserting into the incorrect column on conflict. This made it
seem like there were downloads for items where there were none.

CHANGELOG.md

@@ -4,6 +4,24 @@ 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).
 
+## [0.4.2] - 2018-10-04
+### Changed
+- README.md introduction and requirements
+- Use ujson instead of json
+- Iterate directly on SQL cursor in `/items` route
+
+### Fixed
+- Logic error in SQL for item views
+
+## [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

README.md

@@ -1,16 +1,28 @@
 # DSpace Statistics API
-A quick and dirty REST API to expose Solr view and download statistics for items in a DSpace repository.
+A simple REST API to expose Solr view and download statistics for items in a DSpace repository. This project contains a standalone indexing component and a WSGI application.
 
-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).
+## Requirements
 
-## Installation
-Create a virtual environment and run it:
+- Python 3.5+
+- PostgreSQL version 9.5+ (due to [`UPSERT` support](https://wiki.postgresql.org/wiki/UPSERT))
+- DSpace 4+ with [Solr usage statistics enabled](https://wiki.duraspace.org/display/DSDOC5x/SOLR+Statistics)
+
+## Installation and Testing
+Create a Python virtual environment and install the dependencies:
 
     $ python -m venv venv
     $ . venv/bin/activate
     $ pip install -r requirements.txt
+
+Set up the environment variables Solr and PostgreSQL:
+
+    $ export SOLR_SERVER=http://localhost:8080/solr
+    $ 
     $ gunicorn app:api
 
+## Deployment
+There are example systemd service and timer units in the `contrib` directory.
+
 ## Using the API
 The API exposes the following endpoints:
 
@@ -25,6 +37,9 @@ The API exposes the following endpoints:
 - Close up DB connection when gunicorn shuts down gracefully
 - Better logging
 - Tests
+- Check if database exists (try/except)
+- Version API
+- Use JSON in PostgreSQL
 
 ## License
 This work is licensed under the [GPLv3](https://www.gnu.org/licenses/gpl-3.0.en.html).

app.py

@@ -22,16 +22,16 @@ class AllItemsResource:
 
         # 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 {} OFFSET {}'.format(limit, offset))
-        results = cursor.fetchmany(limit)
-        cursor.close()
 
         # create a list to hold dicts of item stats
         statistics = list()
 
         # iterate over results and build statistics object
-        for item in results:
+        for item in cursor:
             statistics.append({ 'id': item['id'], 'views': item['views'], 'downloads': item['downloads'] })
 
+        cursor.close()
+
         message = {
                 'currentPage': page,
                 'totalPages': pages,

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

@@ -31,98 +31,129 @@
 # See: https://wiki.duraspace.org/display/DSPACE/Solr
 
 from database import database_connection
+import ujson
+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 = ujson.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 views=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 = ujson.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

@@ -9,4 +9,5 @@ python-mimeparse==1.6.0
 requests==2.19.1
 six==1.11.0
 SolrClient==0.2.1
+ujson==1.35
 urllib3==1.23