Refactor project structure

This follows guidance from several well-known Python best practices
guides. Basically, the idea is create a package for the application
that is comprised of several re-usable modules.

See: https://docs.python-guide.org/writing/structure/
See: https://realpython.com/python-application-layouts/

dspace_statistics_api/app.py

@@ -0,0 +1,73 @@
+from .database import database_connection
+import falcon
+
+db = database_connection()
+db.set_session(readonly=True)
+
+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()
+
+def on_exit(api):
+    print("Shutting down DB")
+
+api = falcon.API()
+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/indexer.py

@@ -0,0 +1,173 @@
+#!/usr/bin/env python
+#
+# 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

@@ -0,0 +1,9 @@
+from .config import SOLR_SERVER
+from SolrClient import SolrClient
+
+def solr_connection():
+    connection = SolrClient(SOLR_SERVER)
+
+    return connection
+
+# vim: set sw=4 ts=4 expandtab: