alanorth/dspace-statistics-api
1
0
Fork 0
mirror of https://github.com/ilri/dspace-statistics-api.git synced 2025-05-22 04:09:02 +02:00
Code Releases Activity

Add communities and collections support to API

Browse Source 
The basic logic is similar to items, where you can request single
item statistics with a UUID, all item statistics, and item statis-
tics for a list of items (optionally with a date range). Most of
the item code was re-purposed to work on "elements", which can be
items, communities, or collections depending on the request, with
the use of Falcon's `before` hooks to set the statistics scope so
we know how to behave for the current request.

Other than the minor difference in facet fields, another issue I
had with communities and collections is that the owningComm and
owningColl fields are multi-valued (unlike items' id field). This
means that, when you facet the results of your query, Solr returns
ids that seem unrelated, but are actually present in the field, so
I had to make sure I checked all returned ids to see if they were
in the user's POSTed elements list.

TODO:
  - Add tests
  - Revise docstrings
  - Refactor items.py as it is now generic
This commit is contained in:
Alan Orth
2020-12-20 16:14:46 +02:00
parent fba6f1ead1
commit 3339bf8d9c
3 changed files with 164 additions and 72 deletions
dspace_statistics_api
app.pyitems.pyutil.py

84
dspace_statistics_api/app.py

@ -3,7 +3,8 @@ import psycopg2.extras
from .database import DatabaseManager
from .items import get_downloads, get_views
from .util import validate_items_post_parameters
from .util import set_statistics_scope
from .util import validate_post_parameters
class RootResource:
@ -14,7 +15,8 @@ class RootResource:
resp.body = f.read()
class AllItemsResource:
class AllStatisticsResource:
@falcon.before(set_statistics_scope)
def on_get(self, req, resp):
"""Handles GET requests"""
# Return HTTPBadRequest if id parameter is not present and valid
@ -26,26 +28,26 @@ class AllItemsResource:
db.set_session(readonly=True)
with db.cursor() as cursor:
# get total number of items so we can estimate the pages
cursor.execute("SELECT COUNT(id) FROM items")
# get total number of communities/collections/items so we can estimate the pages
cursor.execute(f"SELECT COUNT(id) FROM {req.context.statistics_scope}")
pages = round(cursor.fetchone()[0] / limit)
# get statistics and use limit and offset to page through results
cursor.execute(
"SELECT id, views, downloads FROM items ORDER BY id LIMIT %s OFFSET %s",
f"SELECT id, views, downloads FROM {req.context.statistics_scope} ORDER BY id LIMIT %s OFFSET %s",
[limit, offset],
)
# create a list to hold dicts of item stats
# create a list to hold dicts of stats
statistics = list()
# iterate over results and build statistics object
for item in cursor:
for result in cursor:
statistics.append(
{
"id": str(item["id"]),
"views": item["views"],
"downloads": item["downloads"],
"id": str(result["id"]),
"views": result["views"],
"downloads": result["downloads"],
}
)
@ -58,9 +60,15 @@ class AllItemsResource:
resp.media = message
@falcon.before(validate_items_post_parameters)
@falcon.before(set_statistics_scope)
@falcon.before(validate_post_parameters)
def on_post(self, req, resp):
"""Handles POST requests"""
"""Handles POST requests.
Uses two `before` hooks to set the statistics "scope" and validate the
POST parameters. The "scope" is the type of statistics we want, which
will be items, communities, or collections, depending on the request.
"""
# Build the Solr date string, ie: [* TO *]
if req.context.dateFrom and req.context.dateTo:
@ -74,10 +82,10 @@ class AllItemsResource:
# Helper variables to make working with pages/items/results easier and
# to make the code easier to understand
number_of_items: int = len(req.context.items)
pages: int = int(number_of_items / req.context.limit)
first_item: int = req.context.page * req.context.limit
last_item: int = first_item + req.context.limit
number_of_elements: int = len(req.context.elements)
pages: int = int(number_of_elements / req.context.limit)
first_element: int = req.context.page * req.context.limit
last_element: int = first_element + req.context.limit
# Get a subset of the POSTed items based on our limit. Note that Python
# list slicing and indexing are both zero based, but the first and last
# items in a slice can be confusing. See this ASCII diagram:
@ -88,20 +96,24 @@ class AllItemsResource:
# Slice position: 0 1 2 3 4 5 6
# Index position: 0 1 2 3 4 5
#
# So if we have a list items with 240 items:
# So if we have a list of items with 240 items:
#
# 1st set: items[0:100] would give items at indexes 0 to 99
# 2nd set: items[100:200] would give items at indexes 100 to 199
# 3rd set: items[200:300] would give items at indexes 200 to 239
items_subset: list = req.context.items[first_item:last_item]
elements_subset: list = req.context.elements[first_element:last_element]
views: dict = get_views(solr_date_string, items_subset)
downloads: dict = get_downloads(solr_date_string, items_subset)
views: dict = get_views(
solr_date_string, elements_subset, req.context.views_facet_field
)
downloads: dict = get_downloads(
solr_date_string, elements_subset, req.context.downloads_facet_field
)
# create a list to hold dicts of item stats
# create a list to hold dicts of stats
statistics = list()
# iterate over views dict to extract views and use the item id as an
# iterate over views dict to extract views and use the element id as an
# index to the downloads dict to extract downloads.
for k, v in views.items():
statistics.append({"id": k, "views": v, "downloads": downloads[k]})
@ -117,8 +129,9 @@ class AllItemsResource:
resp.media = message
class ItemResource:
def on_get(self, req, resp, item_id):
class SingleStatisticsResource:
@falcon.before(set_statistics_scope)
def on_get(self, req, resp, id_):
"""Handles GET requests"""
# Adapt Python’s uuid.UUID type to PostgreSQL’s uuid
@ -131,18 +144,19 @@ class ItemResource:
with db.cursor() as cursor:
cursor = db.cursor()
cursor.execute(
"SELECT views, downloads FROM items WHERE id=%s", [str(item_id)]
f"SELECT views, downloads FROM {req.context.database} WHERE id=%s",
[str(id_)],
)
if cursor.rowcount == 0:
raise falcon.HTTPNotFound(
title="Item not found",
description=f'The item with id "{str(item_id)}" was not found.',
title=f"{req.context.statistics_scope} not found",
description=f'The {req.context.statistics_scope} with id "{str(id_)}" was not found.',
)
else:
results = cursor.fetchone()
statistics = {
"id": str(item_id),
"id": str(id_),
"views": results["views"],
"downloads": results["downloads"],
}
@ -152,7 +166,17 @@ class ItemResource:
api = application = falcon.API()
api.add_route("/", RootResource())
api.add_route("/items", AllItemsResource())
api.add_route("/item/{item_id:uuid}", ItemResource())
# Item routes
api.add_route("/items", AllStatisticsResource())
api.add_route("/item/{id_:uuid}", SingleStatisticsResource())
# Community routes
api.add_route("/communities", AllStatisticsResource())
api.add_route("/community/{id_:uuid}", SingleStatisticsResource())
# Collection routes
api.add_route("/collections", AllStatisticsResource())
api.add_route("/collection/{id_:uuid}", SingleStatisticsResource())
# vim: set sw=4 ts=4 expandtab: