mirror of
https://github.com/ilri/dspace-statistics-api.git
synced 2024-11-22 14:25:01 +01:00
Alan Orth
73c71fa8a0
You can now POST a JSON request to /items with a list of items and
a date range. This allows the possibility to get view and download
statistics for arbitrary items and arbitrary date ranges.
The JSON request should be in the following format:
{
"limit": 100,
"page": 0,
"dateFrom": "2020-01-01T00:00:00Z",
"dateTo": "2020-09-09T00:00:00Z",
"items": [
"f44cf173-2344-4eb2-8f00-ee55df32c76f",
"2324aa41-e9de-4a2b-bc36-16241464683e",
"8542f9da-9ce1-4614-abf4-f2e3fdb4b305",
"0fe573e7-042a-4240-a4d9-753b61233908"
]
}
The limit, page, and date parameters are all optional. By default
it will use a limit of 100, page 0, and [* TO *] Solr date range.
71 lines
2.4 KiB
Python
71 lines
2.4 KiB
Python
def get_statistics_shards():
|
|
"""Enumerate the cores in Solr to determine if statistics have been sharded into
|
|
yearly shards by DSpace's stats-util or not (for example: statistics-2018).
|
|
|
|
Returns:
|
|
str:A list of Solr statistics shards separated by commas.
|
|
"""
|
|
from .config import SOLR_SERVER
|
|
|
|
import re
|
|
import requests
|
|
|
|
# Initialize an empty list for statistics core years
|
|
statistics_core_years = []
|
|
|
|
# URL for Solr status to check active cores
|
|
solr_query_params = {"action": "STATUS", "wt": "json"}
|
|
solr_url = SOLR_SERVER + "/admin/cores"
|
|
res = requests.get(solr_url, params=solr_query_params)
|
|
|
|
if res.status_code == requests.codes.ok:
|
|
data = res.json()
|
|
|
|
# Iterate over active cores from Solr's STATUS response (cores are in
|
|
# the status array of this response).
|
|
for core in data["status"]:
|
|
# Pattern to match, for example: statistics-2018
|
|
pattern = re.compile("^statistics-[0-9]{4}$")
|
|
|
|
if not pattern.match(core):
|
|
continue
|
|
|
|
# Append current core to list
|
|
statistics_core_years.append(core)
|
|
|
|
# Initialize a string to hold our shards (may end up being empty if the Solr
|
|
# core has not been processed by stats-util).
|
|
shards = str()
|
|
|
|
if len(statistics_core_years) > 0:
|
|
# Begin building a string of shards starting with the default one
|
|
shards = f"{SOLR_SERVER}/statistics"
|
|
|
|
for core in statistics_core_years:
|
|
# Create a comma-separated list of shards to pass to our Solr query
|
|
#
|
|
# See: https://wiki.apache.org/solr/DistributedSearch
|
|
shards += f",{SOLR_SERVER}/{core}"
|
|
|
|
# Return the string of shards, which may actually be empty. Solr doesn't
|
|
# seem to mind if the shards query parameter is empty and I haven't seen
|
|
# any negative performance impact so this should be fine.
|
|
return shards
|
|
|
|
|
|
def is_valid_date(date):
|
|
import datetime
|
|
import falcon
|
|
|
|
try:
|
|
# Solr date format is: 2020-01-01T00:00:00Z
|
|
# See: https://docs.python.org/3/library/datetime.html#strftime-strptime-behavior
|
|
datetime.datetime.strptime(date, "%Y-%m-%dT%H:%M:%SZ")
|
|
|
|
return True
|
|
except ValueError:
|
|
raise falcon.HTTPBadRequest(
|
|
title="Invalid parameter",
|
|
description=f"Invalid date format: {date}. The value must be in format: 2020-01-01T00:00:00Z.",
|
|
)
|