mirror of
https://github.com/ilri/dspace-statistics-api.git
synced 2024-06-26 16:13:47 +02:00
GitHub
commit
a6ce44e852
|
|
@ -10,6 +10,9 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
|
|||
- Hound CI configuration to validate pull requests against PEP 8 code style with Flake8
|
||||
- Configuration for [pipenv](https://pipenv.readthedocs.io/en/latest/)
|
||||
|
||||
## Changed
|
||||
- Use a database management class with Python context management to automatically open/close connections and cursors
|
||||
|
||||
## Changed
|
||||
- Validate code against PEP 8 style guide with Flake8
|
||||
|
||||
|
|
|
|||
|
|
@ -70,7 +70,6 @@ The item id is the *internal* id for an item. You can get these from the standar
|
|||
|
||||
## Todo
|
||||
|
||||
- Close DB connection when gunicorn shuts down gracefully
|
||||
- Better logging
|
||||
- Tests
|
||||
- Check if database exists (try/except)
|
||||
|
|
|
|||
|
|
@ -1,9 +1,6 @@
|
|||
from .database import database_connection
|
||||
from .database import DatabaseManager
|
||||
import falcon
|
||||
|
||||
db = database_connection()
|
||||
db.set_session(readonly=True)
|
||||
|
||||
|
||||
class RootResource:
|
||||
def on_get(self, req, resp):
|
||||
|
|
@ -21,23 +18,23 @@ class AllItemsResource:
|
|||
page = req.get_param_as_int("page", min=0) or 0
|
||||
offset = limit * page
|
||||
|
||||
cursor = db.cursor()
|
||||
with DatabaseManager() as db:
|
||||
db.set_session(readonly=True)
|
||||
|
||||
# get total number of items so we can estimate the pages
|
||||
cursor.execute('SELECT COUNT(id) FROM items')
|
||||
pages = round(cursor.fetchone()[0] / limit)
|
||||
with db.cursor() as 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))
|
||||
# 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()
|
||||
# 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()
|
||||
# iterate over results and build statistics object
|
||||
for item in cursor:
|
||||
statistics.append({'id': item['id'], 'views': item['views'], 'downloads': item['downloads']})
|
||||
|
||||
message = {
|
||||
'currentPage': page,
|
||||
|
|
@ -53,25 +50,27 @@ 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()
|
||||
with DatabaseManager() as db:
|
||||
db.set_session(readonly=True)
|
||||
|
||||
statistics = {
|
||||
'id': item_id,
|
||||
'views': results['views'],
|
||||
'downloads': results['downloads']
|
||||
}
|
||||
with db.cursor() as cursor:
|
||||
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()
|
||||
|
||||
resp.media = statistics
|
||||
statistics = {
|
||||
'id': item_id,
|
||||
'views': results['views'],
|
||||
'downloads': results['downloads']
|
||||
}
|
||||
|
||||
cursor.close()
|
||||
resp.media = statistics
|
||||
|
||||
|
||||
api = application = falcon.API()
|
||||
|
|
|
|||
|
|
@ -7,9 +7,17 @@ import psycopg2
|
|||
import psycopg2.extras
|
||||
|
||||
|
||||
def database_connection():
|
||||
connection = psycopg2.connect("dbname={} user={} password={} host={} port={}".format(DATABASE_NAME, DATABASE_USER, DATABASE_PASS, DATABASE_HOST, DATABASE_PORT), cursor_factory=psycopg2.extras.DictCursor)
|
||||
class DatabaseManager():
|
||||
'''Manage database connection.'''
|
||||
|
||||
return connection
|
||||
def __init__(self):
|
||||
self._connection_uri = 'dbname={} user={} password={} host={} port={}'.format(DATABASE_NAME, DATABASE_USER, DATABASE_PASS, DATABASE_HOST, DATABASE_PORT)
|
||||
|
||||
def __enter__(self):
|
||||
self._connection = psycopg2.connect(self._connection_uri, cursor_factory=psycopg2.extras.DictCursor)
|
||||
return self._connection
|
||||
|
||||
def __exit__(self, exc_type, exc_value, exc_traceback):
|
||||
self._connection.close()
|
||||
|
||||
# vim: set sw=4 ts=4 expandtab:
|
||||
|
|
|
|||
|
|
@ -29,7 +29,7 @@
|
|||
# See: https://solrclient.readthedocs.io/en/latest/SolrClient.html
|
||||
# See: https://wiki.duraspace.org/display/DSPACE/Solr
|
||||
|
||||
from .database import database_connection
|
||||
from .database import DatabaseManager
|
||||
import json
|
||||
import psycopg2.extras
|
||||
from .solr import solr_connection
|
||||
|
|
@ -63,41 +63,39 @@ def index_views():
|
|||
results_num_pages = int(results_totalNumFacets / results_per_page)
|
||||
results_current_page = 0
|
||||
|
||||
cursor = db.cursor()
|
||||
with DatabaseManager() as db:
|
||||
with db.cursor() as cursor:
|
||||
# create an empty list to store values for batch insertion
|
||||
data = []
|
||||
|
||||
# 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))
|
||||
|
||||
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)
|
||||
|
||||
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))
|
||||
|
||||
# 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()
|
||||
|
||||
# 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()
|
||||
|
||||
# clear all items from the list so we can populate it with the next batch
|
||||
data.clear()
|
||||
|
||||
results_current_page += 1
|
||||
|
||||
cursor.close()
|
||||
results_current_page += 1
|
||||
|
||||
|
||||
def index_downloads():
|
||||
|
|
@ -123,53 +121,53 @@ def index_downloads():
|
|||
results_num_pages = int(results_totalNumFacets / results_per_page)
|
||||
results_current_page = 0
|
||||
|
||||
cursor = db.cursor()
|
||||
with DatabaseManager() as db:
|
||||
with db.cursor() as cursor:
|
||||
# create an empty list to store values for batch insertion
|
||||
data = []
|
||||
|
||||
# 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))
|
||||
|
||||
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)
|
||||
|
||||
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))
|
||||
|
||||
# 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()
|
||||
|
||||
# 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()
|
||||
|
||||
# clear all items from the list so we can populate it with the next batch
|
||||
data.clear()
|
||||
|
||||
results_current_page += 1
|
||||
|
||||
cursor.close()
|
||||
results_current_page += 1
|
||||
|
||||
|
||||
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
|
||||
with DatabaseManager() as db:
|
||||
with db.cursor() as cursor:
|
||||
# create table to store item views and downloads
|
||||
cursor.execute('''CREATE TABLE IF NOT EXISTS items
|
||||
(id INT PRIMARY KEY, views INT DEFAULT 0, downloads INT DEFAULT 0)''')
|
||||
|
||||
# commit the table creation before closing the database connection
|
||||
db.commit()
|
||||
|
||||
index_views()
|
||||
index_downloads()
|
||||
|
||||
db.close()
|
||||
|
||||
# vim: set sw=4 ts=4 expandtab:
|
||||
|
|
|
|||
Loading…
Reference in New Issue
Block a user