CHANGELOG.md: Add changes for v0.6.1

I had imagined plugging in an interactive Swagger or OpenAPI instance
here, but that's actually much more involved in Falcon than I want to
deal with right now.

.gitignore

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

.travis.yml

@@ -0,0 +1,11 @@
+language: python
+python:
+  - "3.5"
+  - "3.6"
+  - "3.7-dev"
+script: pip install -r requirements.txt
+branches:
+  only:
+    - master
+
+# vim: ts=2 sw=2 et

CHANGELOG.md

@@ -4,6 +4,95 @@ 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).
 
+### [0.6.1] - 2018-10-31
+## Added
+- API documentation at root path (/)
+
+### [0.6.0] - 2018-10-31
+## Changed
+- Refactor project structure (note breaking changes to API and indexing invocation, see contrib and README.md)
+
+### [0.5.2] - 2018-10-28
+## Changed
+- Update library versions in requirements.txt
+
+### [0.5.1] - 2018-10-24
+## Changed
+- Use Python's native json instead of ujson
+
+### [0.5.0] - 2018-10-24
+## Added
+- Example nginx configuration to README.md
+
+## Changed
+- Don't initialize Solr connection in API
+
+### [0.4.3] - 2018-10-17
+## Changed
+- Use pip install as script for Travis CI
+
+## Improved
+- Documentation for deployment and testing
+
+## [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
+
+## [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"
+- Use read-only database connection in API
+- Update systemd units for CGSpace→DSpace rename
+- Use UPSERT to simplify database schema and Python logic
+
+### Added
+- Example systemd service and timer unit for indexer service
+- Add top-level route to expose all item statistics
+
+### Removed
+- Ability to customize SOLR_CORE variable
+
 ## [0.0.4] - 2018-09-23
 ### Added
 - Added example systemd unit file for API

README.md

@@ -1,20 +1,83 @@
-# CGSpace Statistics API
-A quick and dirty REST API to expose Solr view and download statistics for items in a DSpace repository.
+# DSpace Statistics API [![Build Status](https://travis-ci.org/ilri/dspace-statistics-api.svg?branch=master)](https://travis-ci.org/ilri/dspace-statistics-api)
+DSpace versions 4.0 and up include a [REST API](https://wiki.duraspace.org/display/DSDOC5x/REST+API) that allows the repository to be queried programmatically. The API exposes information about communities, collections, items, and bitstreams, but not item views or downloads. This project contains a lightweight indexer and a web application to make the view and download statistics available via a simple REST API that can be deployed simultaneously with DSpace's own.
 
-Written and tested in Python 3.6. SolrClient (0.2.1) does not currently run in Python 3.7.0.
+You can read more about the Solr queries used to gather the item view and download statistics on the [DSpace wiki](https://wiki.duraspace.org/display/DSPACE/Solr).
 
-## Installation
-Create a virtual environment and run it:
+## Requirements
 
-    $ virtualenv -p /usr/bin/python3.6 venv
+- 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 falcon gunicorn SolrClient
-    $ gunicorn app:api
+    $ pip install -r requirements.txt
+
+Set up the environment variables for Solr and PostgreSQL:
+
+    $ export SOLR_SERVER=http://localhost:8080/solr
+    $ export DATABASE_NAME=dspacestatistics
+    $ export DATABASE_USER=dspacestatistics
+    $ export DATABASE_PASS=dspacestatistics
+    $ export DATABASE_HOST=localhost
+
+Index the Solr statistics core to populate the PostgreSQL database:
+
+    $ python -m dspace_statistics_api.indexer
+
+Run the REST API:
+
+    $ gunicorn dspace_statistics_api.app
+
+Test to see if there are any statistics:
+
+    $ curl 'http://localhost:8000/items?limit=1'
+
+## Deployment
+There are example systemd service and timer units in the `contrib` directory. The API service listens on localhost by default so you will need to expose it publicly using a web server like nginx.
+
+An example nginx configuration is:
+
+```
+server {
+    #...
+
+    location ~ /rest/statistics/?(.*) {
+        access_log /var/log/nginx/statistics.log;
+        proxy_pass http://statistics_api/$1$is_args$args;
+    }
+}
+
+upstream statistics_api {
+    server 127.0.0.1:5000;
+}
+```
+
+This would expose the API at `/rest/statistics`.
+
+## Using the API
+The API exposes the following endpoints:
+
+  - GET `/` — return a basic API documentation page.
+  - GET `/items` — return views and downloads for all items that Solr knows about¹. Accepts `limit` and `page` query parameters for pagination of results (`limit` must be an integer between 1 and 100, and `page` must be an integer greater than or equal to 0).
+  - 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.
+
+The item id is the *internal* id for an item. You can get these from the standard DSpace REST API.
+
+¹ We are querying the Solr statistics core, which technically only knows about items that have either views or downloads. If an item is not present here you can assume it has zero views and zero downloads, but not necessarily that it does not exist in the repository.
 
 ## Todo
 
-- Ability to return a paginated list of items (on a different route?)
-- Add API documentation
+- Close DB connection when gunicorn shuts down gracefully
+- Better logging
+- Tests
+- Check if database exists (try/except)
+- Version API
+- Use JSON in PostgreSQL
+- Switch to [Python 3.6+ f-string syntax](https://realpython.com/python-f-strings/)
 
 ## License
 This work is licensed under the [GPLv3](https://www.gnu.org/licenses/gpl-3.0.en.html).

app.py

@@ -1,45 +0,0 @@
-# Tested with Python 3.6
-# See DSpace Solr docs for tips about parameters
-# 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"""
-
-        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
-
-        # 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
-
-        cursor.close()
-
-        statistics = {
-            'id': item_id,
-            'views': views,
-            'downloads': downloads
-        }
-
-        resp.media = statistics
-
-api = falcon.API()
-api.add_route('/item/{item_id:int}', ItemResource())
-
-# vim: set sw=4 ts=4 expandtab:

config.py

@@ -1,9 +0,0 @@
-import os
-
-# Check if Solr connection information was provided in the environment
-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:

contrib/cgspace-statistics-api.service

@@ -1,18 +0,0 @@
-[Unit]
-Description=CGSpace Statistics API
-After=network.target
-
-[Service]
-Environment=SOLR_SERVER=http://localhost:8081/solr
-Environment=SOLR_CORE=statistics
-User=nobody
-Group=nogroup
-WorkingDirectory=/opt/ilri/cgspace-statistics-api
-ExecStart=/opt/ilri/cgspace-statistics-api/venv/bin/gunicorn \
-          --bind 127.0.0.1:5000                              \
-          app:api
-ExecReload=/bin/kill -s HUP $MAINPID
-ExecStop=/bin/kill -s TERM $MAINPID
-
-[Install]
-WantedBy=multi-user.target

contrib/dspace-statistics-api.service

@@ -0,0 +1,20 @@
+[Unit]
+Description=DSpace Statistics API
+After=network.target
+
+[Service]
+Environment=DATABASE_NAME=dspacestatistics
+Environment=DATABASE_USER=dspacestatistics
+Environment=DATABASE_PASS=dspacestatistics
+Environment=DATABASE_HOST=localhost
+User=nobody
+Group=nogroup
+WorkingDirectory=/var/lib/dspace-statistics-api
+ExecStart=/var/lib/dspace-statistics-api/venv/bin/gunicorn \
+          --bind 127.0.0.1:5000                             \
+          dspace_statistics_api.app
+ExecReload=/bin/kill -s HUP $MAINPID
+ExecStop=/bin/kill -s TERM $MAINPID
+
+[Install]
+WantedBy=multi-user.target

contrib/dspace-statistics-indexer.service

@@ -0,0 +1,17 @@
+[Unit]
+Description=DSpace Statistics Indexer
+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=/var/lib/dspace-statistics-api
+ExecStart=/var/lib/dspace-statistics-api/venv/bin/python -m dspace_statistics_api.indexer
+
+[Install]
+WantedBy=multi-user.target

contrib/dspace-statistics-indexer.timer

@@ -0,0 +1,12 @@
+[Unit]
+Description=DSpace Statistics Indexer
+
+[Timer]
+# twice a day, at 6AM and 6PM
+OnCalendar=*-*-* 06,18:00:00
+# Add a random delay of 0–3600 seconds
+RandomizedDelaySec=3600
+Persistent=true
+
+[Install]
+WantedBy=timers.target

database.py

@@ -1,11 +0,0 @@
-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:

dspace_statistics_api/app.py

@@ -0,0 +1,78 @@
+from .database import database_connection
+import falcon
+
+db = database_connection()
+db.set_session(readonly=True)
+
+class RootResource:
+    def on_get(self, req, resp):
+        resp.status = falcon.HTTP_200
+        resp.content_type = 'text/html'
+        with open('dspace_statistics_api/docs/index.html', 'r') as f:
+            resp.body = f.read()
+
+class AllItemsResource:
+    def on_get(self, req, resp):
+        """Handles GET requests"""
+        # Return HTTPBadRequest if id parameter is not present and valid
+        limit = req.get_param_as_int("limit", min=0, max=100) or 100
+        page = req.get_param_as_int("page", min=0) or 0
+        offset = limit * page
+
+        cursor = db.cursor()
+
+        # get total number of items so we can estimate the pages
+        cursor.execute('SELECT COUNT(id) FROM items')
+        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 {} OFFSET {}'.format(limit, offset))
+
+        # create a list to hold dicts of item stats
+        statistics = list()
+
+        # iterate over results and build statistics object
+        for item in cursor:
+            statistics.append({ 'id': item['id'], 'views': item['views'], 'downloads': item['downloads'] })
+
+        cursor.close()
+
+        message = {
+                'currentPage': page,
+                'totalPages': pages,
+                'limit': limit,
+                'statistics': statistics
+        }
+
+        resp.media = message
+
+class ItemResource:
+    def on_get(self, req, resp, item_id):
+        """Handles GET requests"""
+
+        cursor = db.cursor()
+        cursor.execute('SELECT views, downloads FROM items WHERE id={}'.format(item_id))
+        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()
+
+api = application = falcon.API()
+api.add_route('/', RootResource())
+api.add_route('/items', AllItemsResource())
+api.add_route('/item/{item_id:int}', ItemResource())
+
+# vim: set sw=4 ts=4 expandtab:

dspace_statistics_api/config.py

@@ -0,0 +1,11 @@
+import os
+
+# Check if Solr connection information was provided in the environment
+SOLR_SERVER = os.environ.get('SOLR_SERVER', 'http://localhost:8080/solr')
+
+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:

dspace_statistics_api/database.py

@@ -0,0 +1,12 @@
+from .config import DATABASE_NAME
+from .config import DATABASE_USER
+from .config import DATABASE_PASS
+from .config import DATABASE_HOST
+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)
+
+    return connection
+
+# vim: set sw=4 ts=4 expandtab:

dspace_statistics_api/docs/index.html

@@ -0,0 +1,20 @@
+<!DOCTYPE html>
+<html lang="en-US">
+    <head>
+        <meta charset="UTF-8">
+        <title>DSpace Statistics API</title>
+    </head>
+    <body>
+        <h1>DSpace Statistics API</h1>
+        <p>This site is running the <a href="https://github.com/ilri/dspace-statistics-api" title="DSpace Statistics API project">DSpace Statistics API</a>. The following endpoints are available:</p>
+        <ul>
+            <li>GET <code>/</code> — return a basic API documentation page.</li>
+            <li>GET <code>/items</code> — return views and downloads for all items that Solr knows about¹. Accepts <code>limit</code> and <code>page</code> query parameters for pagination of results (<code>limit</code> must be an integer between 1 and 100, and <code>page</code> must be an integer greater than or equal to 0).</li>
+            <li>GET <code>/item/id</code> — return views and downloads for a single item (<code>id</code> must be a positive integer). Returns HTTP 404 if an item id is not found.</li>
+        </ul>
+
+        <p>The item id is the <em>internal</em> id for an item. You can get these from the standard DSpace REST API.</p>
+
+        <p>¹ We are querying the Solr statistics core, which technically only knows about items that have either views or downloads. If an item is not present here you can assume it has zero views and zero downloads, but not necessarily that it does not exist in the repository.</code>
+    </body>
+</html>

dspace_statistics_api/indexer.py

@@ -0,0 +1,172 @@
+#
+# indexer.py
+#
+# Copyright 2018 Alan Orth.
+#
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+#
+# ---
+#
+# Connects to a DSpace Solr statistics core and ingests item views and downloads
+# into a PostgreSQL database for use by other applications (like an API).
+#
+# 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 psycopg2-binary
+#
+# See: https://solrclient.readthedocs.io/en/latest/SolrClient.html
+# See: https://wiki.duraspace.org/display/DSPACE/Solr
+
+from .database import database_connection
+import json
+import psycopg2.extras
+from .solr import solr_connection
+
+def index_views():
+    # 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)
+
+    # 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 = 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('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)
+
+        # 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():
+    # 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)
+
+    # 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 = 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('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)
+
+        # 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()
+
+db = database_connection()
+solr = solr_connection()
+
+# create table to store item views and downloads
+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()
+
+db.close()
+
+# vim: set sw=4 ts=4 expandtab:

dspace_statistics_api/solr.py

@@ -1,4 +1,4 @@
-from config import SOLR_SERVER
+from .config import SOLR_SERVER
 from SolrClient import SolrClient
 
 def solr_connection():

indexer.py

@@ -1,106 +0,0 @@
-#!/usr/bin/env python
-#
-# Tested with Python 3.6
-# See DSpace Solr docs for tips about parameters
-# https://wiki.duraspace.org/display/DSPACE/Solr
-
-from config import SOLR_CORE
-from database import database_connection
-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)
-    res = solr.query(SOLR_CORE, {
-        'q':'type:2',
-        'fq':'isBot:false AND statistics_type:view',
-        'facet':True,
-        'facet.field':'id',
-    }, rows=0)
-
-    # divide results into "pages" (numFound / 100)
-    results_numFound = res.get_num_found()
-    results_per_page = 100
-    results_num_pages = round(results_numFound / results_per_page)
-    results_current_page = 0
-
-    while results_current_page <= results_num_pages:
-        print('Page {0} of {1}.'.format(results_current_page, results_num_pages))
-
-        res = solr.query(SOLR_CORE, {
-            'q':'type:2',
-            'fq':'isBot:false AND statistics_type:view',
-            'facet':True,
-            'facet.field':'id',
-            'facet.limit':results_per_page,
-            'facet.offset':results_current_page * results_per_page
-        })
-
-        # 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():
-                db.execute('''REPLACE INTO itemviews VALUES (?, ?)''', (item_id, item_views))
-
-        db.commit()
-
-        results_current_page += 1
-
-def index_downloads():
-    print("Populating database with item downloads.")
-
-    # determine the total number of items with downloads (aka Solr's numFound)
-    res = solr.query(SOLR_CORE, {
-        'q':'type:0',
-        'fq':'isBot:false AND statistics_type:view AND bundleName:ORIGINAL',
-        'facet':True,
-        'facet.field':'owningItem',
-    }, rows=0)
-
-    # divide results into "pages" (numFound / 100)
-    results_numFound = res.get_num_found()
-    results_per_page = 100
-    results_num_pages = round(results_numFound / results_per_page)
-    results_current_page = 0
-
-    while results_current_page <= results_num_pages:
-        print('Page {0} of {1}.'.format(results_current_page, results_num_pages))
-
-        res = solr.query(SOLR_CORE, {
-            'q':'type:0',
-            'fq':'isBot:false AND statistics_type:view AND bundleName:ORIGINAL',
-            'facet':True,
-            'facet.field':'owningItem',
-            'facet.limit':results_per_page,
-            'facet.offset':results_current_page * results_per_page
-        })
-
-        # 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():
-                db.execute('''REPLACE INTO itemdownloads VALUES (?, ?)''', (item_id, item_downloads))
-
-        db.commit()
-
-        results_current_page += 1
-
-db = database_connection()
-solr = solr_connection()
-
-# use separate views and downloads tables so we can REPLACE INTO carelessly (ie, item may have views but no downloads)
-db.execute('''CREATE TABLE IF NOT EXISTS itemviews
-                  (id integer primary key, views integer)''')
-db.execute('''CREATE TABLE IF NOT EXISTS itemdownloads
-                  (id integer primary key, downloads integer)''')
-index_views()
-index_downloads()
-
-db.close()
-
-# vim: set sw=4 ts=4 expandtab:

requirements.txt

@@ -0,0 +1,12 @@
+certifi==2018.10.15
+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==2.20.0
+six==1.11.0
+-e git://github.com/alanorth/SolrClient.git@c629e3475be37c82770b2be61748be7e29882648#egg=SolrClient
+urllib3==1.24