1
0
mirror of https://github.com/ilri/dspace-statistics-api.git synced 2025-05-10 15:16:02 +02:00

Compare commits

..

91 Commits

Author SHA1 Message Date
a524068cf6 Bump version to 1.4.3-dev
All checks were successful
continuous-integration/drone/push Build is passing
2021-04-15 14:44:44 +03:00
964d5dff06 Version 1.4.2 2021-04-15 14:23:07 +03:00
a9252d1771 Update requirements-dev.txt
Generated with poetry export:

    $ poetry export --without-hashes --dev -f requirements.txt > requirements-dev.txt

The `--without-hashes` is required to work around an issue with
gunicorn pulling in a dependency on setuptools that poetry ignores.

See: https://github.com/python-poetry/poetry/issues/1584
2021-04-15 14:19:48 +03:00
a63687d516 poetry.lock: Run poetry update 2021-04-15 14:17:17 +03:00
73dc3a292e README.md: Remove TODO about Swagger
All checks were successful
continuous-integration/drone/push Build is passing
I added the SwaggerUI interface a few months ago.
2021-04-06 20:28:10 +03:00
1e742bad41 CHANGELOG.md: Add note about valid page tests
All checks were successful
continuous-integration/drone/push Build is passing
2021-04-06 09:07:51 +03:00
164008981e CHANGELOG.md: Add notes about Falcon 3.0.0
All checks were successful
continuous-integration/drone/push Build is passing
2021-04-06 08:58:00 +03:00
dd1769b954 tests: Fix totalPages
A few months ago I fixed the totalPages display to show 1 when we
only have one page of results (the page itself is still 0), but I
didn't update the tests.

See: 4f8cd1097bd0b1384540518304cbfdb88f73d151
2021-04-06 08:54:54 +03:00
b009820fb4 Update requirements
Generated with poetry export:

    $ poetry export --without-hashes -f requirements.txt > requirements.txt
    $ poetry export --without-hashes --dev -f requirements.txt > requirements-dev.txt

The `--without-hashes` is required to work around an issue with
gunicorn pulling in a dependency on setuptools that poetry ignores.

See: https://github.com/python-poetry/poetry/issues/1584
2021-04-06 08:32:22 +03:00
9830295978 poetry.lock: Run poetry update 2021-04-06 08:31:50 +03:00
c93a4d7455 pyproject.toml: Falcon 3.0.0
Release notes: https://falcon.readthedocs.io/en/latest/changes/3.0.0.html
2021-04-06 08:31:39 +03:00
2f8e4f8a0a Changes for Falcon 3.0.0
Mostly it seems we just need to use resp.text instead of resp.body,
including in falcon-swagger-ui (I forked the upstream one to make
this change).

See: https://falcon.readthedocs.io/en/latest/changes/3.0.0.html
2021-04-06 08:30:28 +03:00
0650c5985e Add SPDX short license identifier to all Python files
All checks were successful
continuous-integration/drone/push Build is passing
See: https://spdx.github.io/spdx-spec/appendix-V-using-SPDX-short-identifiers-in-source-files/
2021-03-22 13:42:42 +02:00
d814f1c4f0 CHANGELOG.md: Fix heading
All checks were successful
continuous-integration/drone/push Build is passing
2021-03-21 19:50:39 +02:00
00f30591c4 CHANGELOG.md: Add notes about GitHub Actions 2021-03-21 19:49:35 +02:00
acfe87b91a Add GitHub Actions badge and remove sr.ht
All checks were successful
continuous-integration/drone/push Build is passing
2021-03-21 11:48:05 +02:00
bc6d84dda2 Add GitHub Actions workflow
My first time setting up a PostgreSQL service container on GitHub
actions. Note that there are two different kinds of environment
variables: those passed to the Docker container, and those used by
the PostgreSQL utilities.

See: https://docs.github.com/en/actions/guides/creating-postgresql-service-containers
See: https://hub.docker.com/_/postgres
2021-03-21 11:44:39 +02:00
889fb2f74a Update requirements
All checks were successful
continuous-integration/drone/push Build is passing
Generated with poetry export:

    $ poetry export --without-hashes -f requirements.txt > requirements.txt
    $ poetry export --without-hashes --dev -f requirements.txt > requirements-dev.txt

The `--without-hashes` is required to work around an issue with
gunicorn pulling in a dependency on setuptools that poetry ignores.

See: https://github.com/python-poetry/poetry/issues/1584
2021-03-21 08:59:41 +02:00
c42cd7a818 poetry.lock: Run poetry update 2021-03-21 08:59:04 +02:00
f8bba59d66 .gitignore: Ignore .egg-info
All checks were successful
continuous-integration/drone/push Build is passing
2021-03-14 21:50:47 +02:00
b8cb752a29 CHANGELOG.md: Add note about updated poetry deps
All checks were successful
continuous-integration/drone/push Build is passing
2021-03-11 11:23:18 +02:00
09496aa2b5 Update requirements
Generated with poetry export:

    $ poetry export --without-hashes -f requirements.txt > requirements.txt
    $ poetry export --without-hashes --dev -f requirements.txt > requirements-dev.txt

The `--without-hashes` is required to work around an issue with
gunicorn pulling in a dependency on setuptools that poetry ignores.

See: https://github.com/python-poetry/poetry/issues/1584
2021-03-11 11:22:05 +02:00
ff5dc7506d poetry.lock: Run poetry update 2021-03-11 11:21:02 +02:00
80a11ead97 Version 1.4.1
All checks were successful
continuous-integration/drone/push Build is passing
2021-01-14 14:19:50 +02:00
a282c95933 CHANGELOG.md: Minor syntax fix 2021-01-14 14:15:57 +02:00
fd7cc36306 Update requirements-dev.txt
Generated with poetry export:

    $ poetry export --without-hashes --dev -f requirements.txt > requirements-dev.txt

The `--without-hashes` is required to work around an issue with
gunicorn pulling in a dependency on setuptools that poetry ignores.

See: https://github.com/python-poetry/poetry/issues/1584
2021-01-14 14:14:16 +02:00
a20ff09570 poetry.lock: Run poetry update
All tests still pass.
2021-01-14 14:13:32 +02:00
fdc0e73088 tests: Sort imports with isort 2021-01-14 14:12:59 +02:00
b15afc9f39 CHANGELOG.md: Add note about UUIDs
All checks were successful
continuous-integration/drone/push Build is passing
2021-01-05 12:41:21 +02:00
2bc18ef719 README.md: Make a note about migrating UUIDs 2021-01-05 12:35:23 +02:00
49751b53f0 dspace_statistics_api/indexer.py: Limit to UUIDs
We need to make sure that the indexer only tries to index UUIDs, as
opposed to legacy IDs that may have been left over from a migration
from earlier DSpace versions. For example, "98110-unmigrated", "-1"
etc.

For matching the UUIDs in Solr I decided that it is sufficient for
our use case to simply match thirty-six characters, where a UUID is
composed of thirty-two hexadecimal characters and four dashes. We
don't need to do any verification of "real" UUIDs because it would
be needlessly complex in our case.

See: https://github.com/ilri/dspace-statistics-api/issues/12
2021-01-05 12:30:27 +02:00
d1c177e146 .drone.yml: Add git to python container
All checks were successful
continuous-integration/drone/push Build is passing
Now that I am installing my own fork of falcon-swagger-ui we need
to have git so we can install it with pip.
2020-12-27 14:22:23 +02:00
33dc210452 dspace_statistics_api/docs/openapi.json: Minor edit
Better to leave the version in there because Swagger Editor doesn't
like it without. Also, change the example page parameter for POSTing
to /items and /collections, as it doesn't make sense to start on a
later page if we have less items than our limit.
2020-12-27 13:53:59 +02:00
282d5f644a Move unreleased change to v1.4.0 2020-12-27 12:52:24 +02:00
05e0e8bdca openapi.json: Set the API version from config
We don't need to hard code this in the JSON anymore since we are
reading and modifying it now for the server config anyways.
2020-12-27 12:48:13 +02:00
2567bb8604 dspace_statistics_api/app.py: Format with black 2020-12-27 12:27:01 +02:00
4af3c656a3 CHANGELOG.md: Add note about totalPages 2020-12-27 12:26:32 +02:00
4f8cd1097b Rework paging
The "totalPages" value in our response is calculated incorrectly.
Instead of casting to int and rounding, we should rather round up
to the next integer with math.ceil. This is a more correct way to
get the value.

Also update the indexer to use the same logic, although there the
values are printed with +1 so they are more readable.
2020-12-27 12:22:07 +02:00
a02211fd60 Update requirements
Some checks failed
continuous-integration/drone/push Build is failing
Generated with poetry export:

    $ poetry export --without-hashes -f requirements.txt > requirements.txt
    $ poetry export --without-hashes --dev -f requirements.txt > requirements-dev.txt

The `--without-hashes` is required to work around an issue with
gunicorn pulling in a dependency on setuptools that poetry ignores.

See: https://github.com/python-poetry/poetry/issues/1584
2020-12-25 13:03:32 +02:00
fc814593c7 Use my fork of falcon-swagger-ui
It has a newer Swagger UI (v3.38.0).
2020-12-25 12:57:58 +02:00
7de1084f60 Add whitespace before vim modeline
All checks were successful
continuous-integration/drone/push Build is passing
black wants this...
2020-12-24 13:12:06 +02:00
6b78e82fe9 Add vim modeline to all tests 2020-12-24 13:11:12 +02:00
4004515967 pyproject.toml: Update description
All checks were successful
continuous-integration/drone/push Build is passing
2020-12-23 16:15:46 +02:00
d1229c2387 Adjust docs at root
Don't use a static HTML file anymore. Now I simply print an XHTML
page from the Falcon resource. This way I can use variables to add
in the API version as well as a link to the Swagger UI.

The list of API calls is still present on the README.md, though in
the long run I might move them to some dedicated documentation or
a GitHub wiki.
2020-12-23 16:12:50 +02:00
be83514de1 Re-work Swagger UI configuration
All checks were successful
continuous-integration/drone/push Build is passing
It turns out that Swagger UI mostly does the "right" thing for our
use cases here, but it assumes that API paths are relative to the
root of the host where it is being served. This works in the local
development environment because we are serving on "/", but it does
not work in production where the API is deployed beneath the DSpace
REST API, for example at "/rest/statistics".

The solution here is to allow configuration of the DSpace Statistics
API path and use that when registering the Swagger UI as well as in
a new "server" block in the OpenAPI JSON schema.

By default it is configured to work out of the box in a development
environment. Set the DSPACE_STATISTICS_API_URL environment variable
to something like "/rest/statistics" when running in production.
2020-12-23 13:25:17 +02:00
70b2ba83ba Allow configuration of Swagger and OpenAPI JSON URL
All checks were successful
continuous-integration/drone/push Build is passing
When running in production your statistics API might be deployed to
a path like /rest/statistics instead of at the root.
2020-12-22 12:50:03 +02:00
893039bc6a Update requirements
Generated with poetry export:

    $ poetry export --without-hashes -f requirements.txt > requirements.txt
    $ poetry export --without-hashes --dev -f requirements.txt > requirements-dev.txt

The `--without-hashes` is required to work around an issue with
gunicorn pulling in a dependency on setuptools that poetry ignores.

See: https://github.com/python-poetry/poetry/issues/1584
2020-12-22 12:07:07 +02:00
a4628dde4e Update requirements
Generated with poetry export:

    $ poetry export -f requirements.txt > requirements.txt
    $ poetry export --dev -f requirements.txt > requirements-dev.txt
2020-12-22 11:45:39 +02:00
68418ea053 dspace_statistics_api/docs/openapi.json: Add /status
Add a /status to the Swagger UI schema.
2020-12-22 11:41:47 +02:00
6bbee7919e Bump version to 1.4.0-dev 2020-12-22 11:31:46 +02:00
8f0061ce29 CHANGELOG.md: Add note about the /status page 2020-12-22 11:30:50 +02:00
4b1398c67f Add /status route
Currently this only prints the API version.
2020-12-22 11:30:09 +02:00
a9d2a6d9be CHANGELOG.md: Add note about Swagger UI 2020-12-22 11:21:46 +02:00
a35ecf2394 Add Swagger UI on /swagger
This includes a Swagger UI with an OpenAPI 3.0 JSON schema for easy
interactive demonstration and testing of the API. The JSON schema
was created with the standalone swagger-editor. Includes tests to
make sure that the /swagger and /docs/openapi.json paths are acce-
ssible.
2020-12-22 11:18:47 +02:00
3e271c7852 tests/dspacestatistics.sql: Update data
All checks were successful
continuous-integration/drone/push Build is passing
Add a new database snapshot with communities and collections.
2020-12-20 22:31:41 +02:00
d7ba14c590 tests: Add tests for communities and collections
Also, separate tests for items, communities, and collections into
their own files, leaving a single test for docs in its own file.
2020-12-20 22:12:13 +02:00
ab82e90773 dspace_statistics_api/stats.py: Use -isBot:true
All checks were successful
continuous-integration/drone/push Build is passing
Minor change to bot filtering. We should use a negated match for
documents that have `isBot:true` rather than looking for documents
that are tagged with `isBot:false` (the distinction is subtle, but
important).
2020-12-20 16:56:03 +02:00
8a1244d2d0 Update changelog and docs 2020-12-20 16:45:49 +02:00
04f0756c7f dspace_statistics_api/util.py: Add vim modeline 2020-12-20 16:31:52 +02:00
830e4415f5 dspace_statistics_api/app.py: Run isort 2020-12-20 16:29:35 +02:00
47b4eb3df7 Rename items.py to stats.py
It is no longer used only for item-related statistics functions.
2020-12-20 16:28:56 +02:00
3339bf8d9c Add communities and collections support to API
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
2020-12-20 16:14:46 +02:00
fba6f1ead1 CHANGELOG.md: Update unreleased changes
All checks were successful
continuous-integration/drone/push Build is passing
2020-12-18 22:54:01 +02:00
20c8ba0cf8 indexer.py: Add support for communities and collections
The logic to get views and downloads is very similar to that used
for items, but we facet by different fields. This uses a generic
function for indexing that takes an "indexType" and a "facetField"
parameter. The indexType parameter controls which database table
to insert into, and the facetField parameter indicates which field
to facet by in Solr.
2020-12-18 22:53:16 +02:00
b486f51dd7 indexer.py: Rename index functions for items
Start making plans for indexing communities and collections.
2020-12-18 22:53:16 +02:00
787eec20ea CHANGELOG.md: Add note about imports
All checks were successful
continuous-integration/drone/push Build is passing
2020-12-18 22:52:14 +02:00
9e6fcf279b dspace_statistics_api/items.py: Format with black 2020-12-18 22:45:39 +02:00
4dbf734a4b Move all imports to top of file
A few months ago I had an issue setting up mocking because I was
trying to be clever importing these libraries only when I needed
them rather than at the global scope. Someone pointed out to me
that if the imports are at the top of the file Falcon will load
them once when the WSGI server starts, whereas if they are in the
on_get() or on_post() they will load for every request! Also, it
seems that PEP8 recommends keeping imports at the top of the file
anyways, so I will just do that.

Imports sorted with isort.

See: https://www.python.org/dev/peps/pep-0008/#imports
2020-12-18 22:42:06 +02:00
a0d0a47150 items.py: Add fl paramter to Solr queries
I forgot to add the fl parameter here as well.
2020-12-18 16:12:34 +02:00
01e9756cf2 Update requirements
All checks were successful
continuous-integration/drone/push Build is passing
Generated with poetry export:

    $ poetry export -f requirements.txt > requirements.txt
    $ poetry export --dev -f requirements.txt > requirements-dev.txt
2020-12-18 11:20:17 +02:00
b2b4eb2939 poetry.lock: Run poetry update 2020-12-18 11:19:16 +02:00
4bbbaa4af3 dspace_statistics_api/indexer.py: Use fl parameter
All checks were successful
continuous-integration/drone/push Build is passing
I forgot to add the fl parameter to the downloads function.
2020-12-18 10:44:02 +02:00
7e4d5f4b13 README.md: Minor edit to intro 2020-12-18 10:42:48 +02:00
428172854d README.md: Add TODO
All checks were successful
continuous-integration/drone/push Build is passing
2020-12-17 20:44:25 +02:00
2707cb37d5 CHANGELOG.md: Add note about fl parameter
Some checks failed
continuous-integration/drone/push Build is failing
2020-12-17 12:27:11 +02:00
2407aeec70 dspace_statistics_api/indexer.py: Use fl parameter
When indexing item views and downloads the only field we need is the
the id. The `fl` parameter tells Solr which fields to return in the
search results. This should theoretically be more efficient, though
I don't have any time to figure out how to measure it right now.
2020-12-17 12:25:28 +02:00
f3a0e3a671 CHANGELOG.md: Add note about ORDER BY
All checks were successful
continuous-integration/drone/push Build is passing
2020-12-17 10:17:23 +02:00
4590fc8708 dspace_statistics_api/app.py: Use ORDER BY in /items
Since we are paging through the results by limit/offset we need to
be sure that we are returning results deterministically.
2020-12-17 10:10:40 +02:00
8b924cf450 Remove TravisCI config
All checks were successful
continuous-integration/drone/push Build is passing
I will use other CIs since TravisCI changed their business model.
2020-12-15 09:38:51 +02:00
ea24c73a6a .drone.yml: Install gcc for Python 3.9
It appears to be needed to compile typed-ast:

    gcc -pthread -Wno-unused-result -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -fPIC -Iast27/Include -I/usr/local/include/python3.9 -c ast27/Custom/typed_ast.c -o build/temp.linux-x86_64-3.9/ast27/Custom/typed_ast.o
    error: command 'gcc' failed: No such file or directory
    ----------------------------------------
    ERROR: Failed building wheel for typed-ast
2020-12-14 22:50:21 +02:00
cd98d33615 .drone.yml: Only install requirements-dev.txt
It seems that Poetry's --dev export includes both dev and non-dev
libraries so we don't need to install both.
2020-12-14 22:42:00 +02:00
9d112266ca Update requirements-dev.txt
Generated with poetry export:

    $ poetry export --dev -f requirements.txt > requirements-dev.txt
2020-12-14 22:05:18 +02:00
2b067050ff Remove pytest-clarity
It is missing a six dependency which causes the build to fail. I
could simply add six to the virtualenv but it feels dirty. I don't
actually *need* pytest-clarity for anything so I'll just remove it.

See: https://github.com/darrenburns/pytest-clarity/issues/14
2020-12-14 22:05:03 +02:00
dc683f2d1c pytest.ini: Change --strict to --strict-markers
This is deprecated since pytest 6.2.0.

See: https://docs.pytest.org/en/stable/deprecations.html#the-strict-command-line-option
2020-12-14 19:07:02 +02:00
f60f529bd7 Update requirements
Generated with poetry export:

    $ poetry export -f requirements.txt > requirements.txt
    $ poetry export --dev -f requirements.txt > requirements-dev.txt
2020-12-14 15:41:40 +02:00
7db8458201 poetry.lock: Run poetry update
[SKIP CI]
2020-12-14 15:40:06 +02:00
707f878b94 Add .drone.yml
Uses multiple pipelines to test several versions of Python. A few
things to note:

- I use the -slim Python packages, which are smaller and yet still
have no problem installing psycopg2-binary with pip
- I have to start a PostgreSQL database service for each pipeline
separately
2020-12-14 15:38:50 +02:00
930250352a Update docs about POST /items 2020-12-13 20:09:20 +02:00
e27f30ba4d README.md: Use travis-ci.com domain for badge link 2020-12-08 09:11:38 +02:00
28d1917038 README.md: Use travis-ci.com domain for badge 2020-12-08 09:09:19 +02:00
fc6a9c2ad1 tests: Update for real data
Now that CGSpace is running DSpace 6 I will use some real UUIDs to
make things easier in the future.
2020-11-25 14:56:47 +02:00
26 changed files with 3610 additions and 4618 deletions

View File

@ -1,21 +0,0 @@
image: archlinux
packages:
- python-poetry
- postgresql
sources:
- https://git.sr.ht/~alanorth/dspace-statistics-api
tasks:
- setup: |
id
psql --version
sudo su - postgres -c "initdb --locale en_US.UTF-8 -E UTF8 -D '/var/lib/postgres/data'"
sudo systemctl start postgresql
createuser -U postgres dspacestatistics
psql -U postgres -c "ALTER USER dspacestatistics WITH PASSWORD 'dspacestatistics'"
createdb -U postgres -O dspacestatistics --encoding=UNICODE dspacestatistics
cd dspace-statistics-api
psql -U postgres -d dspacestatistics < tests/dspacestatistics.sql
poetry install --no-root
- test: |
cd dspace-statistics-api
poetry run pytest

156
.drone.yml Normal file
View File

@ -0,0 +1,156 @@
kind: pipeline
type: docker
name: python39
steps:
- name: setup
image: postgres:10-alpine
environment:
PGPASSWORD: postgres
commands:
- id
- psql --version
- sleep 5
- pg_isready -h database -U postgres -d dspacestatistics
- createuser -h database -U postgres dspacestatistics
- psql -h database -U postgres -c "ALTER USER dspacestatistics WITH PASSWORD 'dspacestatistics'"
- psql -h database -U postgres -d dspacestatistics < tests/dspacestatistics.sql
- name: test
image: python:3.9-slim
environment:
PGPASSWORD: dspacestatistics
DATABASE_HOST: database
commands:
- id
- python -V
- apt update && apt install -y gcc git
- pip install -r requirements-dev.txt
- pytest
services:
- name: database
image: postgres:10-alpine
environment:
POSTGRES_USER: postgres
POSTGRES_PASSWORD: postgres
POSTGRES_DB: dspacestatistics
---
kind: pipeline
type: docker
name: python38
steps:
- name: database
image: postgres:10-alpine
detach: true
environment:
POSTGRES_USER: postgres
POSTGRES_PASSWORD: postgres
POSTGRES_DB: dspacestatistics
- name: setup
image: postgres:10-alpine
environment:
PGPASSWORD: postgres
commands:
- id
- psql --version
- sleep 5
- pg_isready -h database -U postgres -d dspacestatistics
- createuser -h database -U postgres dspacestatistics
- psql -h database -U postgres -c "ALTER USER dspacestatistics WITH PASSWORD 'dspacestatistics'"
- psql -h database -U postgres -d dspacestatistics < tests/dspacestatistics.sql
- name: test
image: python:3.8-slim
environment:
PGPASSWORD: dspacestatistics
DATABASE_HOST: database
commands:
- id
- python -V
- apt update && apt install -y git
- pip install -r requirements-dev.txt
- pytest
---
kind: pipeline
type: docker
name: python37
steps:
- name: database
image: postgres:10-alpine
detach: true
environment:
POSTGRES_USER: postgres
POSTGRES_PASSWORD: postgres
POSTGRES_DB: dspacestatistics
- name: setup
image: postgres:10-alpine
environment:
PGPASSWORD: postgres
commands:
- id
- psql --version
- sleep 5
- pg_isready -h database -U postgres -d dspacestatistics
- createuser -h database -U postgres dspacestatistics
- psql -h database -U postgres -c "ALTER USER dspacestatistics WITH PASSWORD 'dspacestatistics'"
- psql -h database -U postgres -d dspacestatistics < tests/dspacestatistics.sql
- name: test
image: python:3.7-slim
environment:
PGPASSWORD: dspacestatistics
DATABASE_HOST: database
commands:
- id
- python -V
- apt update && apt install -y git
- pip install -r requirements-dev.txt
- pytest
---
kind: pipeline
type: docker
name: python36
steps:
- name: database
image: postgres:10-alpine
detach: true
environment:
POSTGRES_USER: postgres
POSTGRES_PASSWORD: postgres
POSTGRES_DB: dspacestatistics
- name: setup
image: postgres:10-alpine
environment:
PGPASSWORD: postgres
commands:
- id
- psql --version
- sleep 5
- pg_isready -h database -U postgres -d dspacestatistics
- createuser -h database -U postgres dspacestatistics
- psql -h database -U postgres -c "ALTER USER dspacestatistics WITH PASSWORD 'dspacestatistics'"
- psql -h database -U postgres -d dspacestatistics < tests/dspacestatistics.sql
- name: test
image: python:3.6-slim
environment:
PGPASSWORD: dspacestatistics
DATABASE_HOST: database
commands:
- id
- python -V
- apt update && apt install -y git
- pip install -r requirements-dev.txt
- pytest
# vim: ts=2 sw=2 et

61
.github/workflows/python-app.yml vendored Normal file
View File

@ -0,0 +1,61 @@
# This workflow will install Python dependencies, run tests and lint with a single version of Python
# For more information see: https://help.github.com/actions/language-and-framework-guides/using-python-with-github-actions
name: Build and Test
on: ['push', 'pull_request']
jobs:
build:
runs-on: ubuntu-latest
services:
database:
image: postgres:10-alpine
env:
# password for postgres user in the Docker container
POSTGRES_PASSWORD: postgres
# default database to create
POSTGRES_DB: dspacestatistics
options: >-
--health-cmd pg_isready
--health-interval 10s
--health-timeout 5s
--health-retries 5
ports:
- 5432:5432
steps:
- uses: actions/checkout@v2
- name: Set up Python 3.9
uses: actions/setup-python@v2
with:
python-version: 3.9
- name: Install dependencies
run: |
python -m pip install --upgrade pip
pip install flake8 pytest
if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
if [ -f requirements-dev.txt ]; then pip install -r requirements-dev.txt; fi
- name: Lint with flake8
run: |
# stop the build if there are Python syntax errors or undefined names
flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
# exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
- name: Set up PostgreSQL
run: |
pg_isready -U postgres -d dspacestatistics
createuser -U postgres dspacestatistics
psql -U postgres -c "ALTER USER dspacestatistics WITH PASSWORD 'dspacestatistics'"
psql -U postgres -d dspacestatistics < tests/dspacestatistics.sql
env:
PGHOST: localhost
PGPASSWORD: postgres
- name: Test with pytest
run: |
pytest
env:
PGHOST: localhost
PGPASSWORD: dspacestatistics

1
.gitignore vendored
View File

@ -1,2 +1,3 @@
__pycache__
venv
*.egg-info

View File

@ -1,25 +0,0 @@
dist: bionic
language: python
python:
- "3.6"
- "3.7"
- "3.8"
- "3.9"
- "nightly"
jobs:
allow_failures:
- python: "nightly"
addons:
postgresql: "10"
before_script:
- psql --version
- createuser -U postgres dspacestatistics
- psql -U postgres -c "ALTER USER dspacestatistics WITH PASSWORD 'dspacestatistics'"
- createdb -U postgres -O dspacestatistics --encoding=UNICODE dspacestatistics
- psql -U postgres -d dspacestatistics < tests/dspacestatistics.sql
install:
- "pip install -r requirements.txt"
- "pip install -r requirements-dev.txt"
script: pytest
# vim: ts=2 sw=2 et

View File

@ -4,6 +4,39 @@ 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).
## 1.4.2 - 2021-04-14
### Updated
- Update dependencies with `poetry update`
- Falcon 3.0.0, a minor change for us, but good to be using a current upstream
version
### Fixed
- Bug in several of the "valid page" tests
### Added
- GitHub Actions workflow to build and test the API
## [1.4.1] - 2021-01-14
### Changed
- Limit Solr query to UUIDs to avoid errors with unmigrated legacy stats (https://github.com/ilri/dspace-statistics-api/issues/12)
### Updated
- Dev dependencies
## [1.4.0] - 2020-12-27
### Added
- indexer.py now indexes views and downloads for communities and collections
- API endpoints for /communities, /community/id, /collections, and /collections/id
- Swagger UI interface on /swagger
- /status page which lists the API version
### Changed
- Add ORDER BY to /items resource to make sure results are returned
deterministically
- Use `fl` parameter in indexer to return only the field we are faceting by
- Minor refactoring of imports for PEP8 style
- More correct calculation of `totalPages` parameter in REST API response
## [1.3.2] - 2020-11-18
### Fixed
- Minor issue with limit parameter (> 0)
@ -58,7 +91,7 @@ and gunicorn 20.0.4
- Minor syntax issues highlighted by flake8
## [1.1.0] - 2019-05-05
## Updated
### Updated
- Falcon 2.0.0 (@alanorth)
## [1.0.0] - 2019-04-15
@ -76,7 +109,7 @@ and gunicorn 20.0.4
## [0.9.0] - 2019-01-22
### Updated
- pytest version 4.0.0
- Fix indexing of sharded statistics cores ([#10))
- Fix indexing of sharded statistics cores (#10)
- Handle case of missing views/downloads gracefully
## [0.8.1] - 2018-11-14

View File

@ -1,10 +1,11 @@
# DSpace Statistics API [![Build Status](https://travis-ci.org/ilri/dspace-statistics-api.svg?branch=master)](https://travis-ci.org/ilri/dspace-statistics-api) [![builds.sr.ht status](https://builds.sr.ht/~alanorth/dspace-statistics-api.svg)](https://builds.sr.ht/~alanorth/dspace-statistics-api?)
DSpace stores item view and download events in a Solr "statistics" core. This information is available for use in the various DSpace user interfaces, but is not exposed externally via any APIs. The DSpace 4/5/6 [REST API](https://wiki.lyrasis.org/display/DSDOC5x/REST+API), for example, only exposes information about communities, collections, item metadata, and bitstreams.
# DSpace Statistics API [![Build Status](https://ci.mjanja.ch/api/badges/alanorth/dspace-statistics-api/status.svg?ref=refs/heads/v6_x)](https://ci.mjanja.ch/alanorth/dspace-statistics-api) [![Build and Test](https://github.com/ilri/dspace-statistics-api/actions/workflows/python-app.yml/badge.svg)](https://github.com/ilri/dspace-statistics-api/actions/workflows/python-app.yml)
DSpace stores item view and download events in a Solr "statistics" core. This information is available for use in the various DSpace user interfaces, but is not exposed externally via any APIs. The DSpace 4/5/6 [REST API](https://wiki.lyrasis.org/display/DSDOC5x/REST+API), for example, only exposes _metadata_ about communities, collections, items, and bitstreams.
- If your DSpace is version 4 or 5, use [dspace-statistics-api v1.1.1](https://github.com/ilri/dspace-statistics-api/releases/tag/v1.1.1)
- If your DSpace is version 6+, use [dspace-statistics-api v1.2.0 or greater](https://github.com/ilri/dspace-statistics-api/releases/tag/v1.2.0)
- Please make sure your statistics have been migrated from integers to UUIDs with the [solr-upgrade-statistics-6x](https://wiki.lyrasis.org/display/DSDOC6x/SOLR+Statistics+Maintenance) command
This project contains an indexer and a [Falcon-based](https://falcon.readthedocs.io/) web application to make the statistics available via a simple REST API. You can read more about the Solr queries used to gather the item view and download statistics on the [DSpace wiki](https://wiki.lyrasis.org/display/DSPACE/Solr).
This project contains an indexer and a [Falcon-based](https://falcon.readthedocs.io/) web application to make the item, community, and collection statistics available via a simple REST API. You can read more about the Solr queries used to gather the item view and download statistics on the [DSpace wiki](https://wiki.lyrasis.org/display/DSPACE/Solr).
If you use the DSpace Statistics API please cite:
@ -81,14 +82,20 @@ 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).
- POST `/items`return views and downloads for an arbitrary list of items. Accepts `limit`, `page`, `dateFrom`, and `dateTo` parameters².
- POST `/items`return views and downloads for an arbitrary list of items with an optional date range. Accepts `limit`, `page`, `dateFrom`, and `dateTo` parameters².
- GET `/item/id`return views and downloads for a single item (`id` must be a UUID). Returns HTTP 404 if an item id is not found.
- GET `/communities`return views and downloads for all communities 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).
- POST `/communities`return views and downloads for an arbitrary list of communities with an optional date range. Accepts `limit`, `page`, `dateFrom`, and `dateTo` parameters².
- GET `/community/id`return views and downloads for a single community (`id` must be a UUID). Returns HTTP 404 if a community id is not found.
- GET `/collections`return views and downloads for all collections 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).
- POST `/collections`return views and downloads for an arbitrary list of collections with an optional date range. Accepts `limit`, `page`, `dateFrom`, and `dateTo` parameters².
- GET `/collection/id`return views and downloads for a single collection (`id` must be a UUID). Returns HTTP 404 if an collection id is not found.
The item id is the *internal* UUID for an item. You can get these from the standard DSpace REST API.
The id is the *internal* UUID for an item, community, or collection. 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.
¹ We are querying the Solr statistics core, which technically only knows about items, communities, or collections that have either views or downloads. If an item, community, or collection 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.
² POST requests to `/items` should be in JSON format with the following parameters:
² POST requests to `/items`, `/communities`, and `/collections` should be in JSON format with the following parameters (substitute the "items" list for communities or collections accordingly):
```
{
@ -109,11 +116,10 @@ The item id is the *internal* UUID for an item. You can get these from the stand
- Better logging
- Version API (or at least include a /version endpoint?)
- Probably use /status with a version in the response
- Use JSON in PostgreSQL
- Add top items endpoint, perhaps `/top/items` or `/items/top`?
- Actually we could add `/items?limit=10&sort=views`
- Make community and collection stats available
- Check IDs in database to see if they are deleted...
## License
This work is licensed under the [GPLv3](https://www.gnu.org/licenses/gpl-3.0.en.html).

View File

@ -1,19 +1,73 @@
import falcon
# SPDX-License-Identifier: GPL-3.0-only
import json
import math
import falcon
import psycopg2.extras
from falcon_swagger_ui import register_swaggerui_app
from .config import DSPACE_STATISTICS_API_URL, VERSION
from .database import DatabaseManager
from .items import get_downloads, get_views
from .util import validate_items_post_parameters
from .stats import get_downloads, get_views
from .util import set_statistics_scope, validate_post_parameters
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()
docs_html = (
"<!DOCTYPE html>"
'<html lang="en-US">'
" <head>"
' <meta charset="UTF-8">'
" <title>DSpace Statistics API</title>"
" </head>"
" <body>"
f" <h1>DSpace Statistics API {VERSION}</h1>"
f" <p>This site is running the <a href=\"https://github.com/ilri/dspace-statistics-api\" title=\"DSpace Statistics API project\">DSpace Statistics API</a>. For more information see the project's README.md or the interactive <a href=\"{DSPACE_STATISTICS_API_URL + '/swagger'}\">Swagger UI</a> built into this API.</p>"
" </body>"
"</html"
)
resp.text = docs_html
class AllItemsResource:
class StatusResource:
def on_get(self, req, resp):
message = {"version": VERSION}
resp.status = falcon.HTTP_200
resp.media = message
class OpenAPIJSONResource:
def on_get(self, req, resp):
resp.status = falcon.HTTP_200
resp.content_type = "text/html"
with open("dspace_statistics_api/docs/openapi.json", "r") as f:
# Load the openapi.json schema
data = json.load(f)
# Swagger assumes your API is at the root of the current host unless
# you configure a "servers" block in the schema. The problem is that
# I want this to work in both development and production, so we need
# to make this configurable.
#
# If the DSPACE_STATISTICS_API_URL is configured then we will add a
# server entry to the openapi.json schema before sending it.
if DSPACE_STATISTICS_API_URL != "":
data["servers"] = [{"url": DSPACE_STATISTICS_API_URL}]
# Set the version in the schema so Swagger UI can display it
data["info"]["version"] = VERSION
resp.text = json.dumps(data)
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
@ -25,26 +79,26 @@ 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")
pages = round(cursor.fetchone()[0] / limit)
# 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 = math.ceil(cursor.fetchone()[0] / limit)
# get statistics and use limit and offset to page through results
cursor.execute(
"SELECT id, views, downloads FROM items 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"],
}
)
@ -57,9 +111,15 @@ 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:
@ -73,10 +133,10 @@ 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 = math.ceil(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:
@ -87,20 +147,24 @@ 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]})
@ -116,12 +180,11 @@ 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"""
import psycopg2.extras
# Adapt Pythons uuid.UUID type to PostgreSQLs uuid
# See: https://www.psycopg.org/docs/extras.html
psycopg2.extras.register_uuid()
@ -132,18 +195,19 @@ 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"],
}
@ -151,9 +215,45 @@ class ItemResource:
resp.media = statistics
api = application = falcon.API()
api.add_route("/", RootResource())
api.add_route("/items", AllItemsResource())
api.add_route("/item/{item_id:uuid}", ItemResource())
app = application = falcon.App()
app.add_route("/", RootResource())
app.add_route("/status", StatusResource())
# Item routes
app.add_route("/items", AllStatisticsResource())
app.add_route("/item/{id_:uuid}", SingleStatisticsResource())
# Community routes
app.add_route("/communities", AllStatisticsResource())
app.add_route("/community/{id_:uuid}", SingleStatisticsResource())
# Collection routes
app.add_route("/collections", AllStatisticsResource())
app.add_route("/collection/{id_:uuid}", SingleStatisticsResource())
# Route to the Swagger UI Openapp schema
app.add_route("/docs/openapi.json", OpenAPIJSONResource())
# Path to host the Swagger UI. Keep in mind that Falcon will add a route for
# this automatically when we register Swagger and the path will be relative
# to the Falcon app like all other routes, not the absolute root.
SWAGGERUI_PATH = "/swagger"
# The *absolute* path to the OpenJSON schema. This must be absolute because
# it will be requested by the client and must resolve absolutely. Note: the
# name of this variable is misleading because it is actually the schema URL
# but we pass it into the register_swaggerui_app() function as the app_url
# parameter.
SWAGGERUI_API_URL = f"{DSPACE_STATISTICS_API_URL}/docs/openapi.json"
register_swaggerui_app(
app,
SWAGGERUI_PATH,
SWAGGERUI_API_URL,
config={
"supportedSubmitMethods": ["get", "post"],
},
uri_prefix=DSPACE_STATISTICS_API_URL,
)
# vim: set sw=4 ts=4 expandtab:

View File

@ -1,3 +1,5 @@
# SPDX-License-Identifier: GPL-3.0-only
import os
# Check if Solr connection information was provided in the environment
@ -9,4 +11,13 @@ DATABASE_PASS = os.environ.get("DATABASE_PASS", "dspacestatistics")
DATABASE_HOST = os.environ.get("DATABASE_HOST", "localhost")
DATABASE_PORT = os.environ.get("DATABASE_PORT", "5432")
# URL to DSpace Statistics API, which will be used as a prefix to API calls in
# the Swagger UI. An empty string will allow this to work out of the box in a
# local development environment, but for production it should be set to a value
# like "/rest/statistics", assuming that the statistics API is deployed next to
# the vanilla DSpace REST API.
DSPACE_STATISTICS_API_URL = os.environ.get("DSPACE_STATISTICS_API_URL", "")
VERSION = "1.4.3-dev"
# vim: set sw=4 ts=4 expandtab:

View File

@ -1,3 +1,5 @@
# SPDX-License-Identifier: GPL-3.0-only
import falcon
import psycopg2
import psycopg2.extras

View File

@ -1,37 +0,0 @@
<!DOCTYPE html>
<html lang="en-US">
<head>
<meta charset="UTF-8">
<title>DSpace Statistics API</title>
</head>
<body>
<h1>DSpace Statistics API v1.3.2</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>POST <code>/items</code>return views and downloads for an arbitrary list of items. Accepts <code>limit</code>, <code>page</code>, <code>dateFrom</code>, and <code>dateTo</code> parameters².</li>
<li>GET <code>/item/id</code>return views and downloads for a single item (<code>id</code> must be a UUID). Returns HTTP 404 if an item id is not found.</li>
</ul>
<p>The item id is the <em>internal</em> uuid for an item. You can get these from the standard DSpace REST API.</p>
<hr/>
<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.</p>
<p>² POST requests to <code>/items</code> should be in JSON format with the following parameters:
<pre><code>{
"limit": 100, // optional, integer between 1 and 100, default 100
"page": 0, // optional, integer greater than 0, default 0
"dateFrom": "2020-01-01T00:00:00Z", // optional, default *
"dateTo": "2020-09-09T00:00:00Z", // optional, default *
"items": [
"f44cf173-2344-4eb2-8f00-ee55df32c76f",
"2324aa41-e9de-4a2b-bc36-16241464683e",
"8542f9da-9ce1-4614-abf4-f2e3fdb4b305",
"0fe573e7-042a-4240-a4d9-753b61233908"
]
}</code></pre>
</p>
</body>
</html>

View File

@ -0,0 +1,616 @@
{
"openapi": "3.0.3",
"info": {
"version": "1.4.3-dev",
"title": "DSpace Statistics API",
"description": "A [Falcon-based](https://falcon.readthedocs.io/) web application to make DSpace's item, community, and collection statistics available via a simple REST API. This Swagger interface is powered by [falcon-swagger-ui](https://github.com/rdidyk/falcon-swagger-ui).",
"license": {
"name": "GPLv3.0",
"url": "https://www.gnu.org/licenses/gpl-3.0.en.html"
}
},
"paths": {
"/item/{item_uuid}": {
"get": {
"summary": "Statistics for a specific item",
"operationId": "getItem",
"tags": [
"item"
],
"parameters": [
{
"name": "item_uuid",
"in": "path",
"required": true,
"description": "The UUID of the item to retrieve",
"schema": {
"type": "string",
"format": "uuid",
"example": "9596aeff-0b90-47d3-9fec-02d578920507"
}
}
],
"responses": {
"200": {
"description": "Expected response to a valid request",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/SingleElementResponse"
}
}
}
},
"404": {
"description": "Item not found"
}
}
}
},
"/items": {
"get": {
"summary": "Get statistics for all items",
"operationId": "getItems",
"tags": [
"items"
],
"parameters": [
{
"name": "limit",
"in": "query",
"description": "How many items to return at once (optional)",
"required": false,
"schema": {
"type": "integer",
"format": "int32",
"minimum": 1,
"maximum": 100,
"default": 100,
"example": 100
}
},
{
"name": "page",
"in": "query",
"description": "Page of results to start on (optional)",
"required": false,
"schema": {
"type": "integer",
"format": "int32",
"minimum": 0,
"default": 0,
"example": 0
}
}
],
"responses": {
"200": {
"description": "A paged array of items",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/SingleElementResponse"
}
}
}
},
"400": {
"description": "Bad request"
}
}
},
"post": {
"summary": "Get statistics for a list of items with an optional date range",
"operationId": "postItems",
"tags": [
"items"
],
"requestBody": {
"content": {
"application/json": {
"schema": {
"type": "object",
"properties": {
"limit": {
"type": "integer",
"format": "int32",
"minimum": 1,
"maximum": 100,
"default": 100
},
"page": {
"type": "integer",
"format": "int32",
"minimum": 0,
"default": 0
},
"dateFrom": {
"type": "string",
"format": "date"
},
"dateTo": {
"type": "string",
"format": "date"
},
"items": {
"type": "array",
"items": {
"type": "string",
"format": "uuid"
}
}
},
"example": {
"limit": 100,
"page": 0,
"dateFrom": "2020-01-01T00:00:00Z",
"dateTo": "2020-12-31T00:00:00Z",
"items": [
"f44cf173-2344-4eb2-8f00-ee55df32c76f",
"2324aa41-e9de-4a2b-bc36-16241464683e",
"8542f9da-9ce1-4614-abf4-f2e3fdb4b305",
"0fe573e7-042a-4240-a4d9-753b61233908"
]
}
}
}
}
},
"responses": {
"200": {
"description": "Expected response to a valid request",
"content": {
"application/json": {
"schema": {
"type": "object",
"properties": {
"currentPage": {
"type": "integer",
"format": "int32"
},
"limit": {
"type": "integer",
"format": "int32"
},
"totalPages": {
"type": "integer",
"format": "int32"
},
"statistics": {
"$ref": "#/components/schemas/ListOfElements"
}
}
}
}
}
},
"400": {
"description": "Bad request"
}
}
}
},
"/community/{community_uuid}": {
"get": {
"summary": "Statistics for a specific community",
"operationId": "getCommunity",
"tags": [
"community"
],
"parameters": [
{
"name": "community_uuid",
"in": "path",
"required": true,
"description": "The UUID of the community to retrieve",
"schema": {
"type": "string",
"format": "uuid",
"example": "bde7139c-d321-46bb-aef6-ae70799e5edb"
}
}
],
"responses": {
"200": {
"description": "Expected response to a valid request",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/SingleElementResponse"
}
}
}
},
"404": {
"description": "Community not found"
}
}
}
},
"/communities": {
"get": {
"summary": "Get statistics for all communities",
"operationId": "getCommunities",
"tags": [
"communities"
],
"parameters": [
{
"name": "limit",
"in": "query",
"description": "How many communities to return at once (optional)",
"required": false,
"schema": {
"type": "integer",
"format": "int32",
"minimum": 1,
"maximum": 100,
"default": 100,
"example": 100
}
},
{
"name": "page",
"in": "query",
"description": "Zero-based page of results to start on (optional)",
"required": false,
"schema": {
"type": "integer",
"format": "int32",
"minimum": 0,
"default": 0,
"example": 0
}
}
],
"responses": {
"200": {
"description": "A paged array of communities",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/SingleElementResponse"
}
}
}
},
"400": {
"description": "Bad request"
}
}
},
"post": {
"summary": "Get statistics for a list of communities with an optional date range",
"operationId": "postCommunities",
"tags": [
"communities"
],
"requestBody": {
"content": {
"application/json": {
"schema": {
"type": "object",
"properties": {
"limit": {
"type": "integer",
"format": "int32",
"minimum": 1,
"maximum": 100,
"default": 100
},
"page": {
"type": "integer",
"format": "int32",
"minimum": 0,
"default": 0
},
"dateFrom": {
"type": "string",
"format": "date"
},
"dateTo": {
"type": "string",
"format": "date"
},
"communities": {
"type": "array",
"items": {
"type": "string",
"format": "uuid"
}
}
},
"example": {
"limit": 100,
"page": 0,
"dateFrom": "2020-01-01T00:00:00Z",
"dateTo": "2020-12-31T00:00:00Z",
"communities": [
"bde7139c-d321-46bb-aef6-ae70799e5edb",
"8a8aeed1-077e-4360-bdf8-a5f3020193b1",
"47d0498a-203c-407d-afb8-1d44bf29badc",
"d3fe99a9-e27d-4035-9339-084c93228c82"
]
}
}
}
}
},
"responses": {
"200": {
"description": "Expected response to a valid request",
"content": {
"application/json": {
"schema": {
"type": "object",
"properties": {
"currentPage": {
"type": "integer",
"format": "int32"
},
"limit": {
"type": "integer",
"format": "int32"
},
"totalPages": {
"type": "integer",
"format": "int32"
},
"statistics": {
"$ref": "#/components/schemas/ListOfElements"
}
}
}
}
}
},
"400": {
"description": "Bad request"
}
}
}
},
"/collection/{collection_uuid}": {
"get": {
"summary": "Statistics for a specific collection",
"operationId": "getCollection",
"tags": [
"collection"
],
"parameters": [
{
"name": "collection_uuid",
"in": "path",
"required": true,
"description": "The UUID of the collection to retrieve",
"schema": {
"type": "string",
"format": "uuid",
"example": "49dc95d8-bf2f-4e68-b30f-41ea266c37ae"
}
}
],
"responses": {
"200": {
"description": "Expected response to a valid request",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/SingleElementResponse"
}
}
}
},
"404": {
"description": "Collection not found"
}
}
}
},
"/collections": {
"get": {
"summary": "Get statistics for all collections",
"operationId": "getCollections",
"tags": [
"collections"
],
"parameters": [
{
"name": "limit",
"in": "query",
"description": "How many collections to return at once (optional)",
"required": false,
"schema": {
"type": "integer",
"format": "int32",
"minimum": 1,
"maximum": 100,
"default": 100,
"example": 100
}
},
{
"name": "page",
"in": "query",
"description": "Zero-based page of results to start on (optional)",
"required": false,
"schema": {
"type": "integer",
"format": "int32",
"minimum": 0,
"default": 0,
"example": 0
}
}
],
"responses": {
"200": {
"description": "A paged array of collections",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/SingleElementResponse"
}
}
}
},
"400": {
"description": "Bad request"
}
}
},
"post": {
"summary": "Get statistics for a list of collections with an optional date range",
"operationId": "postCollections",
"tags": [
"collections"
],
"requestBody": {
"content": {
"application/json": {
"schema": {
"type": "object",
"properties": {
"limit": {
"type": "integer",
"format": "int32",
"minimum": 1,
"maximum": 100,
"default": 100
},
"page": {
"type": "integer",
"format": "int32",
"minimum": 0,
"default": 0
},
"dateFrom": {
"type": "string",
"format": "date"
},
"dateTo": {
"type": "string",
"format": "date"
},
"collections": {
"type": "array",
"items": {
"type": "string",
"format": "uuid"
}
}
},
"example": {
"limit": 100,
"page": 0,
"dateFrom": "2020-01-01T00:00:00Z",
"dateTo": "2020-12-31T00:00:00Z",
"collections": [
"5eeef6cf-b91b-42d0-9549-ea61bc8a758f",
"6aac3269-b4a9-4924-a24d-9e6ee2b410d2",
"551698dd-cd2b-4327-948e-54b5eb6deda5",
"39358713-bbaf-4149-a453-e2b18c09fd5d"
]
}
}
}
}
},
"responses": {
"200": {
"description": "Expected response to a valid request",
"content": {
"application/json": {
"schema": {
"type": "object",
"properties": {
"currentPage": {
"type": "integer",
"format": "int32"
},
"limit": {
"type": "integer",
"format": "int32"
},
"totalPages": {
"type": "integer",
"format": "int32"
},
"statistics": {
"$ref": "#/components/schemas/ListOfElements"
}
}
}
}
}
},
"400": {
"description": "Bad request"
}
}
}
},
"/status": {
"get": {
"summary": "Get API status",
"operationId": "getStatus",
"tags": [
"status"
],
"responses": {
"200": {
"description": "OK",
"content": {
"application/json": {
"schema": {
"type": "object",
"properties": {
"version": {
"type": "string",
"example": "1.4.0-dev"
}
}
}
}
}
},
"405": {
"description": "Method Not Allowed"
}
}
}
}
},
"components": {
"schemas": {
"SingleElementResponse": {
"type": "object",
"required": [
"id",
"views",
"downloads"
],
"properties": {
"id": {
"type": "string",
"format": "uuid"
},
"views": {
"type": "integer",
"example": 450
},
"downloads": {
"type": "integer",
"example": 1337
}
}
},
"ListOfElements": {
"type": "array",
"items": {
"$ref": "#/components/schemas/SingleElementResponse"
}
}
}
}
}

View File

@ -1,25 +1,9 @@
# SPDX-License-Identifier: GPL-3.0-only
#
# 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).
# Connects to a DSpace Solr statistics core and ingests views and downloads for
# communities, collections, and items into a PostgreSQL database.
#
# This script is written for Python 3.6+ and requires several modules that you
# can install with pip (I recommend using a Python virtual environment):
@ -28,6 +12,8 @@
#
# See: https://wiki.duraspace.org/display/DSPACE/Solr
import math
import psycopg2.extras
import requests
@ -36,7 +22,7 @@ from .database import DatabaseManager
from .util import get_statistics_shards
def index_views():
def index_views(indexType: str, facetField: str):
# 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
@ -45,15 +31,16 @@ def index_views():
#
# see: https://lucene.apache.org/solr/guide/6_6/the-stats-component.html
solr_query_params = {
"q": "type:2",
"q": f"type:2 AND {facetField}:/.{{36}}/",
"fq": "-isBot:true AND statistics_type:view",
"fl": facetField,
"facet": "true",
"facet.field": "id",
"facet.field": facetField,
"facet.mincount": 1,
"facet.limit": 1,
"facet.offset": 0,
"stats": "true",
"stats.field": "id",
"stats.field": facetField,
"stats.calcdistinct": "true",
"shards": shards,
"rows": 0,
@ -66,17 +53,17 @@ def index_views():
try:
# get total number of distinct facets (countDistinct)
results_totalNumFacets = res.json()["stats"]["stats_fields"]["id"][
results_totalNumFacets = res.json()["stats"]["stats_fields"][facetField][
"countDistinct"
]
except TypeError:
print("No item views to index, exiting.")
print(f"{indexType}: no views, exiting.")
exit(0)
# divide results into "pages" (cast to int to effectively round down)
# divide results into "pages" and round up to next integer
results_per_page = 100
results_num_pages = int(results_totalNumFacets / results_per_page)
results_num_pages = math.ceil(results_totalNumFacets / results_per_page)
results_current_page = 0
with DatabaseManager() as db:
@ -87,14 +74,15 @@ def index_views():
while results_current_page <= results_num_pages:
# "pages" are zero based, but one based is more human readable
print(
f"Indexing item views (page {results_current_page + 1} of {results_num_pages + 1})"
f"{indexType}: indexing views (page {results_current_page + 1} of {results_num_pages + 1})"
)
solr_query_params = {
"q": "type:2",
"q": f"type:2 AND {facetField}:/.{{36}}/",
"fq": "-isBot:true AND statistics_type:view",
"fl": facetField,
"facet": "true",
"facet.field": "id",
"facet.field": facetField,
"facet.mincount": 1,
"facet.limit": results_per_page,
"facet.offset": results_current_page * results_per_page,
@ -108,12 +96,12 @@ def index_views():
# Solr returns facets as a dict of dicts (see json.nl parameter)
views = res.json()["facet_counts"]["facet_fields"]
# 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))
# iterate over the facetField dict and get the ids and views
for id_, views in views[facetField].items():
data.append((id_, 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"
sql = f"INSERT INTO {indexType}(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()
@ -123,18 +111,19 @@ def index_views():
results_current_page += 1
def index_downloads():
def index_downloads(indexType: str, facetField: str):
# get the total number of distinct facets for items with at least 1 download
solr_query_params = {
"q": "type:0",
"q": f"type:0 AND {facetField}:/.{{36}}/",
"fq": "-isBot:true AND statistics_type:view AND bundleName:ORIGINAL",
"fl": facetField,
"facet": "true",
"facet.field": "owningItem",
"facet.field": facetField,
"facet.mincount": 1,
"facet.limit": 1,
"facet.offset": 0,
"stats": "true",
"stats.field": "owningItem",
"stats.field": facetField,
"stats.calcdistinct": "true",
"shards": shards,
"rows": 0,
@ -147,17 +136,16 @@ def index_downloads():
try:
# get total number of distinct facets (countDistinct)
results_totalNumFacets = res.json()["stats"]["stats_fields"]["owningItem"][
results_totalNumFacets = res.json()["stats"]["stats_fields"][facetField][
"countDistinct"
]
except TypeError:
print("No item downloads to index, exiting.")
print(f"{indexType}: no downloads, exiting.")
exit(0)
# 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_num_pages = math.ceil(results_totalNumFacets / results_per_page)
results_current_page = 0
with DatabaseManager() as db:
@ -168,14 +156,15 @@ def index_downloads():
while results_current_page <= results_num_pages:
# "pages" are zero based, but one based is more human readable
print(
f"Indexing item downloads (page {results_current_page + 1} of {results_num_pages + 1})"
f"{indexType}: indexing downloads (page {results_current_page + 1} of {results_num_pages + 1})"
)
solr_query_params = {
"q": "type:0",
"q": f"type:0 AND {facetField}:/.{{36}}/",
"fq": "-isBot:true AND statistics_type:view AND bundleName:ORIGINAL",
"fl": facetField,
"facet": "true",
"facet.field": "owningItem",
"facet.field": facetField,
"facet.mincount": 1,
"facet.limit": results_per_page,
"facet.offset": results_current_page * results_per_page,
@ -189,12 +178,12 @@ def index_downloads():
# Solr returns facets as a dict of dicts (see json.nl parameter)
downloads = res.json()["facet_counts"]["facet_fields"]
# 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))
# iterate over the facetField dict and get the item ids and downloads
for id_, downloads in downloads[facetField].items():
data.append((id_, 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"
sql = f"INSERT INTO {indexType}(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()
@ -211,13 +200,32 @@ with DatabaseManager() as db:
"""CREATE TABLE IF NOT EXISTS items
(id UUID PRIMARY KEY, views INT DEFAULT 0, downloads INT DEFAULT 0)"""
)
# create table to store community views and downloads
cursor.execute(
"""CREATE TABLE IF NOT EXISTS communities
(id UUID PRIMARY KEY, views INT DEFAULT 0, downloads INT DEFAULT 0)"""
)
# create table to store collection views and downloads
cursor.execute(
"""CREATE TABLE IF NOT EXISTS collections
(id UUID PRIMARY KEY, views INT DEFAULT 0, downloads INT DEFAULT 0)"""
)
# commit the table creation before closing the database connection
db.commit()
shards = get_statistics_shards()
index_views()
index_downloads()
# Index views and downloads for items, communities, and collections. Here the
# first parameter is the type of indexing to perform, and the second parameter
# is the field to facet by in Solr's statistics to get this information.
index_views("items", "id")
index_views("communities", "owningComm")
index_views("collections", "owningColl")
index_downloads("items", "owningItem")
index_downloads("communities", "owningComm")
index_downloads("collections", "owningColl")
# vim: set sw=4 ts=4 expandtab:

View File

@ -1,105 +0,0 @@
import requests
from .config import SOLR_SERVER
def get_views(solr_date_string: str, items: list):
"""
Get view statistics for a list of items from Solr.
:parameter solr_date_string (str): Solr date string, for example "[* TO *]"
:parameter items (list): a list of item IDs
:returns: A dict of item IDs and views
"""
from .util import get_statistics_shards
shards = get_statistics_shards()
# Join the UUIDs with "OR" and escape the hyphens for Solr
solr_items_string: str = " OR ".join(items).replace("-", r"\-")
solr_query_params = {
"q": f"id:({solr_items_string})",
"fq": f"type:2 AND isBot:false AND statistics_type:view AND time:{solr_date_string}",
"facet": "true",
"facet.field": "id",
"facet.mincount": 1,
"shards": shards,
"rows": 0,
"wt": "json",
"json.nl": "map", # return facets as a dict instead of a flat list
}
solr_url = SOLR_SERVER + "/statistics/select"
res = requests.get(solr_url, params=solr_query_params)
# Create an empty dict to store views
data = {}
# Solr returns facets as a dict of dicts (see the json.nl parameter)
views = res.json()["facet_counts"]["facet_fields"]
# iterate over the 'id' dict and get the item ids and views
for item_id, item_views in views["id"].items():
data[item_id] = item_views
# Check if any items have missing stats so we can set them to 0
if len(data) < len(items):
# List comprehension to get a list of item ids (keys) in the data
data_ids = [k for k, v in data.items()]
for item_id in items:
if item_id not in data_ids:
data[item_id] = 0
continue
return data
def get_downloads(solr_date_string: str, items: list):
"""
Get download statistics for a list of items from Solr.
:parameter solr_date_string (str): Solr date string, for example "[* TO *]"
:parameter items (list): a list of item IDs
:returns: A dict of item IDs and downloads
"""
from .util import get_statistics_shards
shards = get_statistics_shards()
# Join the UUIDs with "OR" and escape the hyphens for Solr
solr_items_string: str = " OR ".join(items).replace("-", r"\-")
solr_query_params = {
"q": f"owningItem:({solr_items_string})",
"fq": f"type:0 AND isBot:false AND statistics_type:view AND bundleName:ORIGINAL AND time:{solr_date_string}",
"facet": "true",
"facet.field": "owningItem",
"facet.mincount": 1,
"shards": shards,
"rows": 0,
"wt": "json",
"json.nl": "map", # return facets as a dict instead of a flat list
}
solr_url = SOLR_SERVER + "/statistics/select"
res = requests.get(solr_url, params=solr_query_params)
# Create an empty dict to store downloads
data = {}
# Solr returns facets as a dict of dicts (see the json.nl parameter)
downloads = res.json()["facet_counts"]["facet_fields"]
# Iterate over the 'owningItem' dict and get the item ids and downloads
for item_id, item_downloads in downloads["owningItem"].items():
data[item_id] = item_downloads
# Check if any items have missing stats so we can set them to 0
if len(data) < len(items):
# List comprehension to get a list of item ids (keys) in the data
data_ids = [k for k, v in data.items()]
for item_id in items:
if item_id not in data_ids:
data[item_id] = 0
continue
return data
# vim: set sw=4 ts=4 expandtab:

View File

@ -0,0 +1,126 @@
# SPDX-License-Identifier: GPL-3.0-only
import requests
from .config import SOLR_SERVER
from .util import get_statistics_shards
def get_views(solr_date_string: str, elements: list, facetField: str):
"""
Get view statistics for a list of elements from Solr. Depending on the req-
uest this could be items, communities, or collections.
:parameter solr_date_string (str): Solr date string, for example "[* TO *]"
:parameter elements (list): a list of IDs
:parameter facetField (str): Solr field to facet by, for example "id"
:returns: A dict of IDs and views
"""
shards = get_statistics_shards()
# Join the UUIDs with "OR" and escape the hyphens for Solr
solr_elements_string: str = " OR ".join(elements).replace("-", r"\-")
solr_query_params = {
"q": f"{facetField}:({solr_elements_string})",
"fq": f"type:2 AND -isBot:true AND statistics_type:view AND time:{solr_date_string}",
"fl": facetField,
"facet": "true",
"facet.field": facetField,
"facet.mincount": 1,
"shards": shards,
"rows": 0,
"wt": "json",
"json.nl": "map", # return facets as a dict instead of a flat list
}
solr_url = SOLR_SERVER + "/statistics/select"
res = requests.get(solr_url, params=solr_query_params)
# Create an empty dict to store views
data = {}
# Solr returns facets as a dict of dicts (see the json.nl parameter)
views = res.json()["facet_counts"]["facet_fields"]
# iterate over the facetField dict and ids and views
for id_, views in views[facetField].items():
# For items we can rely on Solr returning facets for the *only* the ids
# in our query, but for communities and collections, the owningComm and
# owningColl fields are multi-value so Solr will return facets with the
# values in our query as well as *any others* that happen to be present
# in the field (which looks like Solr returning unrelated results until
# you realize that the field is multi-value and this is correct).
#
# To work around this I make sure that each id in the returned dict are
# present in the elements list POSTed by the user.
if id_ in elements:
data[id_] = views
# Check if any ids have missing stats so we can set them to 0
if len(data) < len(elements):
# List comprehension to get a list of ids (keys) in the data
data_ids = [k for k, v in data.items()]
for element_id in elements:
if element_id not in data_ids:
data[element_id] = 0
continue
return data
def get_downloads(solr_date_string: str, elements: list, facetField: str):
"""
Get download statistics for a list of items from Solr. Depending on the req-
uest this could be items, communities, or collections.
:parameter solr_date_string (str): Solr date string, for example "[* TO *]"
:parameter elements (list): a list of IDs
:parameter facetField (str): Solr field to facet by, for example "id"
:returns: A dict of IDs and downloads
"""
shards = get_statistics_shards()
# Join the UUIDs with "OR" and escape the hyphens for Solr
solr_elements_string: str = " OR ".join(elements).replace("-", r"\-")
solr_query_params = {
"q": f"{facetField}:({solr_elements_string})",
"fq": f"type:0 AND -isBot:true AND statistics_type:view AND bundleName:ORIGINAL AND time:{solr_date_string}",
"fl": facetField,
"facet": "true",
"facet.field": facetField,
"facet.mincount": 1,
"shards": shards,
"rows": 0,
"wt": "json",
"json.nl": "map", # return facets as a dict instead of a flat list
}
solr_url = SOLR_SERVER + "/statistics/select"
res = requests.get(solr_url, params=solr_query_params)
# Create an empty dict to store downloads
data = {}
# Solr returns facets as a dict of dicts (see the json.nl parameter)
downloads = res.json()["facet_counts"]["facet_fields"]
# Iterate over the facetField dict and get the ids and downloads
for id_, downloads in downloads[facetField].items():
# Make sure that each id in the returned dict are present in the
# elements list POSTed by the user.
if id_ in elements:
data[id_] = downloads
# Check if any elements have missing stats so we can set them to 0
if len(data) < len(elements):
# List comprehension to get a list of ids (keys) in the data
data_ids = [k for k, v in data.items()]
for element_id in elements:
if element_id not in data_ids:
data[element_id] = 0
continue
return data
# vim: set sw=4 ts=4 expandtab:

View File

@ -1,4 +1,13 @@
# SPDX-License-Identifier: GPL-3.0-only
import datetime
import json
import re
import falcon
import requests
from .config import SOLR_SERVER
def get_statistics_shards():
@ -8,11 +17,6 @@ def get_statistics_shards():
Returns:
str:A list of Solr statistics shards separated by commas.
"""
import re
import requests
from .config import SOLR_SERVER
# Initialize an empty list for statistics core years
statistics_core_years = []
@ -58,7 +62,6 @@ def get_statistics_shards():
def is_valid_date(date):
import datetime
try:
# Solr date format is: 2020-01-01T00:00:00Z
@ -73,12 +76,12 @@ def is_valid_date(date):
)
def validate_items_post_parameters(req, resp, resource, params):
"""Check the POSTed request parameters for the `/items` endpoint.
def validate_post_parameters(req, resp, resource, params):
"""Check the POSTed request parameters for the `/items`, `/communities` and
`/collections` endpoints.
Meant to be used as a `before` hook.
"""
import json
# Only attempt to read the POSTed request if its length is not 0 (or
# rather, in the Python sense, if length is not a False-y value).
@ -125,14 +128,67 @@ def validate_items_post_parameters(req, resp, resource, params):
else:
req.context.page = 0
# Parse the list of items from the POST request body
if "items" in doc:
if isinstance(doc["items"], list) and len(doc["items"]) > 0:
req.context.items = doc["items"]
# Parse the list of elements from the POST request body
if req.context.statistics_scope in doc:
if (
isinstance(doc[req.context.statistics_scope], list)
and len(doc[req.context.statistics_scope]) > 0
):
req.context.elements = doc[req.context.statistics_scope]
else:
raise falcon.HTTPBadRequest(
title="Invalid parameter",
description='The "items" parameter is invalid. The value must be a comma-separated list of item UUIDs.',
description=f'The "{req.context.statistics_scope}" parameter is invalid. The value must be a comma-separated list of UUIDs.',
)
else:
req.context.items = list()
req.context.elements = list()
def set_statistics_scope(req, resp, resource, params):
"""Set the statistics scope (item, collection, or community) of the request
as well as the appropriate database (for GET requests) and Solr facet fields
(for POST requests).
Meant to be used as a `before` hook.
"""
# Extract the scope from the request path. This is *guaranteed* to be one
# of the following values because we only send requests matching these few
# patterns to routes using this set_statistics_scope hook.
#
# Note: this regex is ordered so that "items" and "collections" match before
# "item" and "collection".
req.context.statistics_scope = re.findall(
r"^/(communities|community|collections|collection|items|item)", req.path
)[0]
# Set the correct database based on the statistics_scope. The database is
# used for all GET requests where statistics are returned directly from the
# database. In this case we can return early.
if req.method == "GET":
if re.findall(r"^(item|items)$", req.context.statistics_scope):
req.context.database = "items"
elif re.findall(r"^(community|communities)$", req.context.statistics_scope):
req.context.database = "communities"
elif re.findall(r"^(collection|collections)$", req.context.statistics_scope):
req.context.database = "collections"
# GET requests only need the scope and the database so we can return now
return
# If the current request is for a plural items, communities, or collections
# that includes a list of element ids POSTed with the request body then we
# need to set the Solr facet field so we can get the live results.
if req.method == "POST":
if req.context.statistics_scope == "items":
req.context.views_facet_field = "id"
req.context.downloads_facet_field = "owningItem"
elif req.context.statistics_scope == "communities":
req.context.views_facet_field = "owningComm"
req.context.downloads_facet_field = "owningComm"
elif req.context.statistics_scope == "collections":
req.context.views_facet_field = "owningColl"
req.context.downloads_facet_field = "owningColl"
# vim: set sw=4 ts=4 expandtab:

645
poetry.lock generated

File diff suppressed because it is too large Load Diff

View File

@ -1,16 +1,17 @@
[tool.poetry]
name = "dspace-statistics-api"
version = "1.3.2"
description = "A simple REST API to expose Solr view and download statistics for items in a DSpace repository."
version = "1.4.3-dev"
description = "A simple REST API to expose Solr view and download statistics for items, communities, and collections in a DSpace repository."
authors = ["Alan Orth <aorth@mjanja.ch>"]
license = "GPL-3.0-only"
[tool.poetry.dependencies]
python = "^3.6"
gunicorn = "^20.0.4"
falcon = "^2.0.0"
falcon = "3.0.0"
psycopg2-binary = "^2.8.6"
requests = "^2.24.0"
falcon-swagger-ui = {git = "https://github.com/alanorth/falcon-swagger-ui.git", rev="falcon-300b1"}
[tool.poetry.dev-dependencies]
ipython = { version = "^7.18.1", python = "^3.7" }
@ -18,7 +19,6 @@ flake8 = "^3.8.4"
pytest = "^6.1.1"
isort = "^5.5.4"
black = "^20.8b1"
pytest-clarity = "^0.3.0-alpha.0"
[build-system]
requires = ["poetry>=0.12"]

View File

@ -1,4 +1,4 @@
[pytest]
addopts= -rsxX -s -v --strict
addopts= -rsxX -s -v --strict-markers
filterwarnings =
error::UserWarning

View File

@ -1,51 +1,51 @@
appdirs==1.4.4
appnope==0.1.0; python_version >= "3.7" and python_version < "4.0" and sys_platform == "darwin"
atomicwrites==1.4.0; sys_platform == "win32"
attrs==20.3.0
appdirs==1.4.4; python_version >= "3.6"
appnope==0.1.2; python_version >= "3.7" and python_version < "4.0" and sys_platform == "darwin"
atomicwrites==1.4.0; python_version >= "3.6" and python_full_version < "3.0.0" and sys_platform == "win32" or sys_platform == "win32" and python_version >= "3.6" and python_full_version >= "3.4.0"
attrs==20.3.0; python_version >= "3.6" and python_full_version < "3.0.0" or python_full_version >= "3.4.0" and python_version >= "3.6"
backcall==0.2.0; python_version >= "3.7" and python_version < "4.0"
black==20.8b1
certifi==2020.11.8
chardet==3.0.4
click==7.1.2
colorama==0.4.4; python_version >= "3.7" and python_version < "4.0" and sys_platform == "win32" or sys_platform == "win32"
dataclasses==0.6; python_version < "3.7"
decorator==4.4.2; python_version >= "3.7" and python_version < "4.0"
falcon==2.0.0
flake8==3.8.4
gunicorn==20.0.4
idna==2.10
importlib-metadata==2.0.0; python_version < "3.8"
iniconfig==1.1.1
ipython==7.19.0; python_version >= "3.7" and python_version < "4.0"
black==20.8b1; python_version >= "3.6"
certifi==2020.12.5; python_version >= "2.7" and python_full_version < "3.0.0" or python_full_version >= "3.5.0"
chardet==4.0.0; python_version >= "2.7" and python_full_version < "3.0.0" or python_full_version >= "3.5.0"
click==7.1.2; python_version >= "3.6" and python_full_version < "3.0.0" or python_full_version >= "3.5.0" and python_version >= "3.6"
colorama==0.4.4; python_version >= "3.7" and python_full_version < "3.0.0" and python_version < "4.0" and sys_platform == "win32" or python_version >= "3.7" and python_version < "4.0" and sys_platform == "win32" and python_full_version >= "3.5.0"
dataclasses==0.8; python_version >= "3.6" and python_version < "3.7"
decorator==5.0.7; python_version >= "3.7" and python_version < "4.0"
falcon-swagger-ui @ git+https://github.com/alanorth/falcon-swagger-ui.git@falcon-300b1
falcon==3.0.0; python_version >= "3.5"
flake8==3.9.0; (python_version >= "2.7" and python_full_version < "3.0.0") or (python_full_version >= "3.5.0")
gunicorn==20.1.0; python_version >= "3.5"
idna==2.10; python_version >= "2.7" and python_full_version < "3.0.0" or python_full_version >= "3.5.0"
importlib-metadata==3.10.1; python_version >= "3.6" and python_full_version < "3.0.0" and python_version < "3.8" or python_full_version >= "3.5.0" and python_version < "3.8" and python_version >= "3.6"
iniconfig==1.1.1; python_version >= "3.6"
ipython-genutils==0.2.0; python_version >= "3.7" and python_version < "4.0"
isort==5.6.4
jedi==0.17.2; python_version >= "3.7" and python_version < "4.0"
mccabe==0.6.1
mypy-extensions==0.4.3
packaging==20.4
parso==0.7.1; python_version >= "3.7" and python_version < "4.0"
pathspec==0.8.1
ipython==7.22.0; python_version >= "3.7" and python_version < "4.0"
isort==5.8.0; python_version >= "3.6" and python_version < "4.0"
jedi==0.18.0; python_version >= "3.7" and python_version < "4.0"
jinja2==2.11.3; python_version >= "2.7" and python_full_version < "3.0.0" or python_full_version >= "3.5.0"
markupsafe==1.1.1; python_version >= "2.7" and python_full_version < "3.0.0" or python_full_version >= "3.5.0"
mccabe==0.6.1; python_version >= "2.7" and python_full_version < "3.0.0" or python_full_version >= "3.5.0"
mypy-extensions==0.4.3; python_version >= "3.6"
packaging==20.9; python_version >= "3.6" and python_full_version < "3.0.0" or python_full_version >= "3.4.0" and python_version >= "3.6"
parso==0.8.2; python_version >= "3.7" and python_version < "4.0"
pathspec==0.8.1; python_version >= "3.6" and python_full_version < "3.0.0" or python_full_version >= "3.5.0" and python_version >= "3.6"
pexpect==4.8.0; python_version >= "3.7" and python_version < "4.0" and sys_platform != "win32"
pickleshare==0.7.5; python_version >= "3.7" and python_version < "4.0"
pluggy==0.13.1
prompt-toolkit==3.0.8; python_version >= "3.7" and python_version < "4.0"
psycopg2-binary==2.8.6
ptyprocess==0.6.0; python_version >= "3.7" and python_version < "4.0" and sys_platform != "win32"
py==1.9.0
pycodestyle==2.6.0
pyflakes==2.2.0
pygments==2.7.2; python_version >= "3.7" and python_version < "4.0"
pyparsing==2.4.7
pytest==6.1.2
pytest-clarity==0.3.0a0
regex==2020.11.13
requests==2.25.0
six==1.15.0
termcolor==1.1.0
toml==0.10.2
pluggy==0.13.1; python_version >= "3.6" and python_full_version < "3.0.0" or python_full_version >= "3.4.0" and python_version >= "3.6"
prompt-toolkit==3.0.18; python_version >= "3.7" and python_version < "4.0" and python_full_version >= "3.6.1"
psycopg2-binary==2.8.6; (python_version >= "2.7" and python_full_version < "3.0.0") or (python_full_version >= "3.4.0")
ptyprocess==0.7.0; python_version >= "3.7" and python_version < "4.0" and sys_platform != "win32"
py==1.10.0; python_version >= "3.6" and python_full_version < "3.0.0" or python_full_version >= "3.4.0" and python_version >= "3.6"
pycodestyle==2.7.0; python_version >= "2.7" and python_full_version < "3.0.0" or python_full_version >= "3.5.0"
pyflakes==2.3.1; python_version >= "2.7" and python_full_version < "3.0.0" or python_full_version >= "3.5.0"
pygments==2.8.1; python_version >= "3.7" and python_version < "4.0"
pyparsing==2.4.7; python_version >= "3.6" and python_full_version < "3.0.0" or python_full_version >= "3.4.0" and python_version >= "3.6"
pytest==6.2.3; python_version >= "3.6"
regex==2021.4.4; python_version >= "3.6"
requests==2.25.1; (python_version >= "2.7" and python_full_version < "3.0.0") or (python_full_version >= "3.5.0")
toml==0.10.2; python_version >= "3.6" and python_full_version < "3.0.0" or python_full_version >= "3.3.0" and python_version >= "3.6"
traitlets==5.0.5; python_version >= "3.7" and python_version < "4.0"
typed-ast==1.4.1
typing-extensions==3.7.4.3
urllib3==1.26.2
wcwidth==0.2.5; python_version >= "3.7" and python_version < "4.0"
zipp==3.4.0; python_version < "3.8"
typed-ast==1.4.3; python_version >= "3.6"
typing-extensions==3.7.4.3; python_version >= "3.6" and python_full_version < "3.0.0" and python_version < "3.8" or python_full_version >= "3.5.0" and python_version < "3.8" and python_version >= "3.6"
urllib3==1.26.4; python_version >= "2.7" and python_full_version < "3.0.0" or python_full_version >= "3.5.0" and python_version < "4"
wcwidth==0.2.5; python_version >= "3.7" and python_version < "4.0" and python_full_version >= "3.6.1"
zipp==3.4.1; python_version >= "3.6" and python_full_version < "3.0.0" and python_version < "3.8" or python_full_version >= "3.5.0" and python_version < "3.8" and python_version >= "3.6"

View File

@ -1,8 +1,11 @@
certifi==2020.11.8
chardet==3.0.4
falcon==2.0.0
gunicorn==20.0.4
idna==2.10
psycopg2-binary==2.8.6
requests==2.25.0
urllib3==1.26.2
certifi==2020.12.5; python_version >= "2.7" and python_full_version < "3.0.0" or python_full_version >= "3.5.0"
chardet==4.0.0; python_version >= "2.7" and python_full_version < "3.0.0" or python_full_version >= "3.5.0"
falcon-swagger-ui @ git+https://github.com/alanorth/falcon-swagger-ui.git@falcon-300b1
falcon==3.0.0; python_version >= "3.5"
gunicorn==20.1.0; python_version >= "3.5"
idna==2.10; python_version >= "2.7" and python_full_version < "3.0.0" or python_full_version >= "3.5.0"
jinja2==2.11.3; python_version >= "2.7" and python_full_version < "3.0.0" or python_full_version >= "3.5.0"
markupsafe==1.1.1; python_version >= "2.7" and python_full_version < "3.0.0" or python_full_version >= "3.5.0"
psycopg2-binary==2.8.6; (python_version >= "2.7" and python_full_version < "3.0.0") or (python_full_version >= "3.4.0")
requests==2.25.1; (python_version >= "2.7" and python_full_version < "3.0.0") or (python_full_version >= "3.5.0")
urllib3==1.26.4; python_version >= "2.7" and python_full_version < "3.0.0" or python_full_version >= "3.5.0" and python_version < "4"

File diff suppressed because it is too large Load Diff

View File

@ -0,0 +1,379 @@
# SPDX-License-Identifier: GPL-3.0-only
import json
from unittest.mock import patch
import pytest
from falcon import testing
from dspace_statistics_api.app import app
@pytest.fixture
def client():
return testing.TestClient(app)
def test_get_collection(client):
"""Test requesting a single collection."""
response = client.simulate_get("/collection/8ea4b611-1f59-4d4e-b78d-a9921a72cfe7")
response_doc = json.loads(response.text)
assert isinstance(response_doc["downloads"], int)
assert isinstance(response_doc["id"], str)
assert isinstance(response_doc["views"], int)
assert response.status_code == 200
def test_get_missing_collection(client):
"""Test requesting a single non-existing collection."""
response = client.simulate_get("/collection/508abe0a-689f-402e-885d-2f6b02e7a39c")
assert response.status_code == 404
def test_get_collections(client):
"""Test requesting 100 collections."""
response = client.simulate_get("/collections", query_string="limit=100")
response_doc = json.loads(response.text)
assert isinstance(response_doc["currentPage"], int)
assert isinstance(response_doc["totalPages"], int)
assert isinstance(response_doc["statistics"], list)
assert response.status_code == 200
def test_get_collections_invalid_limit(client):
"""Test requesting 100 collections with an invalid limit parameter."""
response = client.simulate_get("/collections", query_string="limit=101")
assert response.status_code == 400
def test_get_collections_invalid_page(client):
"""Test requesting 100 collections with an invalid page parameter."""
response = client.simulate_get("/collections", query_string="page=-1")
assert response.status_code == 400
@pytest.mark.xfail
def test_post_collections_valid_dateFrom(client):
"""Test POSTing a request to /collections with a valid dateFrom parameter in the request body."""
request_body = {
"dateFrom": "2020-01-01T00:00:00Z",
"collections": [
"8ea4b611-1f59-4d4e-b78d-a9921a72cfe7",
"260548c8-fda4-4dc8-a979-03495753cdd5",
],
}
response = client.simulate_post("/collections", json=request_body)
assert response.status_code == 200
assert response.json["limit"] == 100
assert response.json["currentPage"] == 0
assert isinstance(response.json["totalPages"], int)
assert len(response.json["statistics"]) == 2
assert isinstance(response.json["statistics"][0]["views"], int)
assert isinstance(response.json["statistics"][0]["downloads"], int)
assert isinstance(response.json["statistics"][1]["views"], int)
assert isinstance(response.json["statistics"][1]["downloads"], int)
def test_post_collections_valid_dateFrom_mocked(client):
"""Mock test POSTing a request to /collections with a valid dateFrom parameter in the request body."""
request_body = {
"dateFrom": "2020-01-01T00:00:00Z",
"collections": [
"8ea4b611-1f59-4d4e-b78d-a9921a72cfe7",
"260548c8-fda4-4dc8-a979-03495753cdd5",
],
}
get_views_return_value = {
"8ea4b611-1f59-4d4e-b78d-a9921a72cfe7": 21,
"260548c8-fda4-4dc8-a979-03495753cdd5": 0,
}
get_downloads_return_value = {
"8ea4b611-1f59-4d4e-b78d-a9921a72cfe7": 575,
"260548c8-fda4-4dc8-a979-03495753cdd5": 899,
}
with patch(
"dspace_statistics_api.app.get_views", return_value=get_views_return_value
):
with patch(
"dspace_statistics_api.app.get_downloads",
return_value=get_downloads_return_value,
):
response = client.simulate_post("/collections", json=request_body)
assert response.status_code == 200
assert response.json["limit"] == 100
assert response.json["currentPage"] == 0
assert isinstance(response.json["totalPages"], int)
assert len(response.json["statistics"]) == 2
assert isinstance(response.json["statistics"][0]["views"], int)
assert isinstance(response.json["statistics"][0]["downloads"], int)
assert isinstance(response.json["statistics"][1]["views"], int)
assert isinstance(response.json["statistics"][1]["downloads"], int)
def test_post_collections_invalid_dateFrom(client):
"""Test POSTing a request to /collections with an invalid dateFrom parameter in the request body."""
request_body = {
"dateFrom": "2020-01-01T00:00:00",
"collections": [
"8ea4b611-1f59-4d4e-b78d-a9921a72cfe7",
"260548c8-fda4-4dc8-a979-03495753cdd5",
],
}
response = client.simulate_post("/collections", json=request_body)
assert response.status_code == 400
@pytest.mark.xfail
def test_post_collections_valid_dateTo(client):
"""Test POSTing a request to /collections with a valid dateTo parameter in the request body."""
request_body = {
"dateTo": "2020-01-01T00:00:00Z",
"collections": [
"8ea4b611-1f59-4d4e-b78d-a9921a72cfe7",
"260548c8-fda4-4dc8-a979-03495753cdd5",
],
}
response = client.simulate_post("/collections", json=request_body)
assert response.status_code == 200
assert response.json["limit"] == 100
assert response.json["currentPage"] == 0
assert isinstance(response.json["totalPages"], int)
assert len(response.json["statistics"]) == 2
assert isinstance(response.json["statistics"][0]["views"], int)
assert isinstance(response.json["statistics"][0]["downloads"], int)
assert isinstance(response.json["statistics"][1]["views"], int)
assert isinstance(response.json["statistics"][1]["downloads"], int)
def test_post_collections_valid_dateTo_mocked(client):
"""Mock test POSTing a request to /collections with a valid dateTo parameter in the request body."""
request_body = {
"dateTo": "2020-01-01T00:00:00Z",
"collections": [
"8ea4b611-1f59-4d4e-b78d-a9921a72cfe7",
"260548c8-fda4-4dc8-a979-03495753cdd5",
],
}
get_views_return_value = {
"8ea4b611-1f59-4d4e-b78d-a9921a72cfe7": 21,
"260548c8-fda4-4dc8-a979-03495753cdd5": 0,
}
get_downloads_return_value = {
"8ea4b611-1f59-4d4e-b78d-a9921a72cfe7": 575,
"260548c8-fda4-4dc8-a979-03495753cdd5": 899,
}
with patch(
"dspace_statistics_api.app.get_views", return_value=get_views_return_value
):
with patch(
"dspace_statistics_api.app.get_downloads",
return_value=get_downloads_return_value,
):
response = client.simulate_post("/collections", json=request_body)
assert response.status_code == 200
assert response.json["limit"] == 100
assert response.json["currentPage"] == 0
assert isinstance(response.json["totalPages"], int)
assert len(response.json["statistics"]) == 2
assert isinstance(response.json["statistics"][0]["views"], int)
assert isinstance(response.json["statistics"][0]["downloads"], int)
assert isinstance(response.json["statistics"][1]["views"], int)
assert isinstance(response.json["statistics"][1]["downloads"], int)
def test_post_collections_invalid_dateTo(client):
"""Test POSTing a request to /collections with an invalid dateTo parameter in the request body."""
request_body = {
"dateFrom": "2020-01-01T00:00:00",
"collections": [
"8ea4b611-1f59-4d4e-b78d-a9921a72cfe7",
"260548c8-fda4-4dc8-a979-03495753cdd5",
],
}
response = client.simulate_post("/collections", json=request_body)
assert response.status_code == 400
@pytest.mark.xfail
def test_post_collections_valid_limit(client):
"""Test POSTing a request to /collections with a valid limit parameter in the request body."""
request_body = {
"limit": 1,
"collections": [
"8ea4b611-1f59-4d4e-b78d-a9921a72cfe7",
"260548c8-fda4-4dc8-a979-03495753cdd5",
],
}
response = client.simulate_post("/collections", json=request_body)
assert response.status_code == 200
assert response.json["limit"] == 1
assert response.json["currentPage"] == 0
assert isinstance(response.json["totalPages"], int)
assert len(response.json["statistics"]) == 1
assert isinstance(response.json["statistics"][0]["views"], int)
assert isinstance(response.json["statistics"][0]["downloads"], int)
def test_post_collections_valid_limit_mocked(client):
"""Mock test POSTing a request to /collections with a valid limit parameter in the request body."""
request_body = {
"limit": 1,
"collections": [
"8ea4b611-1f59-4d4e-b78d-a9921a72cfe7",
"260548c8-fda4-4dc8-a979-03495753cdd5",
],
}
get_views_return_value = {"8ea4b611-1f59-4d4e-b78d-a9921a72cfe7": 21}
get_downloads_return_value = {"8ea4b611-1f59-4d4e-b78d-a9921a72cfe7": 575}
with patch(
"dspace_statistics_api.app.get_views", return_value=get_views_return_value
):
with patch(
"dspace_statistics_api.app.get_downloads",
return_value=get_downloads_return_value,
):
response = client.simulate_post("/collections", json=request_body)
assert response.status_code == 200
assert response.json["limit"] == 1
assert response.json["currentPage"] == 0
assert isinstance(response.json["totalPages"], int)
assert len(response.json["statistics"]) == 1
assert isinstance(response.json["statistics"][0]["views"], int)
assert isinstance(response.json["statistics"][0]["downloads"], int)
def test_post_collections_invalid_limit(client):
"""Test POSTing a request to /collections with an invalid limit parameter in the request body."""
request_body = {
"limit": -1,
"collections": [
"8ea4b611-1f59-4d4e-b78d-a9921a72cfe7",
"260548c8-fda4-4dc8-a979-03495753cdd5",
],
}
response = client.simulate_post("/collections", json=request_body)
assert response.status_code == 400
@pytest.mark.xfail
def test_post_collections_valid_page(client):
"""Test POSTing a request to /collections with a valid page parameter in the request body."""
request_body = {
"page": 0,
"collections": [
"8ea4b611-1f59-4d4e-b78d-a9921a72cfe7",
"260548c8-fda4-4dc8-a979-03495753cdd5",
],
}
response = client.simulate_post("/collections", json=request_body)
assert response.status_code == 200
assert response.json["limit"] == 100
assert response.json["currentPage"] == 0
assert response.json["totalPages"] == 1
assert len(response.json["statistics"]) == 2
assert isinstance(response.json["statistics"][0]["views"], int)
assert isinstance(response.json["statistics"][0]["downloads"], int)
assert isinstance(response.json["statistics"][1]["views"], int)
assert isinstance(response.json["statistics"][1]["downloads"], int)
def test_post_collections_valid_page_mocked(client):
"""Mock test POSTing a request to /collections with a valid page parameter in the request body."""
request_body = {
"page": 0,
"collections": [
"8ea4b611-1f59-4d4e-b78d-a9921a72cfe7",
"260548c8-fda4-4dc8-a979-03495753cdd5",
],
}
get_views_return_value = {
"8ea4b611-1f59-4d4e-b78d-a9921a72cfe7": 21,
"260548c8-fda4-4dc8-a979-03495753cdd5": 0,
}
get_downloads_return_value = {
"8ea4b611-1f59-4d4e-b78d-a9921a72cfe7": 575,
"260548c8-fda4-4dc8-a979-03495753cdd5": 899,
}
with patch(
"dspace_statistics_api.app.get_views", return_value=get_views_return_value
):
with patch(
"dspace_statistics_api.app.get_downloads",
return_value=get_downloads_return_value,
):
response = client.simulate_post("/collections", json=request_body)
assert response.status_code == 200
assert response.json["limit"] == 100
assert response.json["currentPage"] == 0
assert isinstance(response.json["totalPages"], int)
assert len(response.json["statistics"]) == 2
assert isinstance(response.json["statistics"][0]["views"], int)
assert isinstance(response.json["statistics"][0]["downloads"], int)
assert isinstance(response.json["statistics"][1]["views"], int)
assert isinstance(response.json["statistics"][1]["downloads"], int)
def test_post_collections_invalid_page(client):
"""Test POSTing a request to /collections with an invalid page parameter in the request body."""
request_body = {
"page": -1,
"collections": [
"8ea4b611-1f59-4d4e-b78d-a9921a72cfe7",
"260548c8-fda4-4dc8-a979-03495753cdd5",
],
}
response = client.simulate_post("/collections", json=request_body)
assert response.status_code == 400
# vim: set sw=4 ts=4 expandtab:

View File

@ -0,0 +1,379 @@
# SPDX-License-Identifier: GPL-3.0-only
import json
from unittest.mock import patch
import pytest
from falcon import testing
from dspace_statistics_api.app import app
@pytest.fixture
def client():
return testing.TestClient(app)
def test_get_community(client):
"""Test requesting a single community."""
response = client.simulate_get("/community/bde7139c-d321-46bb-aef6-ae70799e5edb")
response_doc = json.loads(response.text)
assert isinstance(response_doc["downloads"], int)
assert isinstance(response_doc["id"], str)
assert isinstance(response_doc["views"], int)
assert response.status_code == 200
def test_get_missing_community(client):
"""Test requesting a single non-existing community."""
response = client.simulate_get("/item/dec6bfc6-efeb-4f74-8436-79fa80bb5c21")
assert response.status_code == 404
def test_get_communities(client):
"""Test requesting 100 communities."""
response = client.simulate_get("/communities", query_string="limit=100")
response_doc = json.loads(response.text)
assert isinstance(response_doc["currentPage"], int)
assert isinstance(response_doc["totalPages"], int)
assert isinstance(response_doc["statistics"], list)
assert response.status_code == 200
def test_get_communities_invalid_limit(client):
"""Test requesting 100 communities with an invalid limit parameter."""
response = client.simulate_get("/communities", query_string="limit=101")
assert response.status_code == 400
def test_get_communities_invalid_page(client):
"""Test requesting 100 communities with an invalid page parameter."""
response = client.simulate_get("/communities", query_string="page=-1")
assert response.status_code == 400
@pytest.mark.xfail
def test_post_communities_valid_dateFrom(client):
"""Test POSTing a request to /communities with a valid dateFrom parameter in the request body."""
request_body = {
"dateFrom": "2020-01-01T00:00:00Z",
"communities": [
"bde7139c-d321-46bb-aef6-ae70799e5edb",
"2a920a61-b08a-4642-8e5d-2639c6702b1f",
],
}
response = client.simulate_post("/communities", json=request_body)
assert response.status_code == 200
assert response.json["limit"] == 100
assert response.json["currentPage"] == 0
assert isinstance(response.json["totalPages"], int)
assert len(response.json["statistics"]) == 2
assert isinstance(response.json["statistics"][0]["views"], int)
assert isinstance(response.json["statistics"][0]["downloads"], int)
assert isinstance(response.json["statistics"][1]["views"], int)
assert isinstance(response.json["statistics"][1]["downloads"], int)
def test_post_communities_valid_dateFrom_mocked(client):
"""Mock test POSTing a request to /communities with a valid dateFrom parameter in the request body."""
request_body = {
"dateFrom": "2020-01-01T00:00:00Z",
"communities": [
"bde7139c-d321-46bb-aef6-ae70799e5edb",
"2a920a61-b08a-4642-8e5d-2639c6702b1f",
],
}
get_views_return_value = {
"bde7139c-d321-46bb-aef6-ae70799e5edb": 309,
"2a920a61-b08a-4642-8e5d-2639c6702b1f": 0,
}
get_downloads_return_value = {
"bde7139c-d321-46bb-aef6-ae70799e5edb": 400,
"2a920a61-b08a-4642-8e5d-2639c6702b1f": 290,
}
with patch(
"dspace_statistics_api.app.get_views", return_value=get_views_return_value
):
with patch(
"dspace_statistics_api.app.get_downloads",
return_value=get_downloads_return_value,
):
response = client.simulate_post("/communities", json=request_body)
assert response.status_code == 200
assert response.json["limit"] == 100
assert response.json["currentPage"] == 0
assert isinstance(response.json["totalPages"], int)
assert len(response.json["statistics"]) == 2
assert isinstance(response.json["statistics"][0]["views"], int)
assert isinstance(response.json["statistics"][0]["downloads"], int)
assert isinstance(response.json["statistics"][1]["views"], int)
assert isinstance(response.json["statistics"][1]["downloads"], int)
def test_post_communities_invalid_dateFrom(client):
"""Test POSTing a request to /communities with an invalid dateFrom parameter in the request body."""
request_body = {
"dateFrom": "2020-01-01T00:00:00",
"communities": [
"bde7139c-d321-46bb-aef6-ae70799e5edb",
"2a920a61-b08a-4642-8e5d-2639c6702b1f",
],
}
response = client.simulate_post("/communities", json=request_body)
assert response.status_code == 400
@pytest.mark.xfail
def test_post_communities_valid_dateTo(client):
"""Test POSTing a request to /communities with a valid dateTo parameter in the request body."""
request_body = {
"dateTo": "2020-01-01T00:00:00Z",
"communities": [
"bde7139c-d321-46bb-aef6-ae70799e5edb",
"2a920a61-b08a-4642-8e5d-2639c6702b1f",
],
}
response = client.simulate_post("/communities", json=request_body)
assert response.status_code == 200
assert response.json["limit"] == 100
assert response.json["currentPage"] == 0
assert isinstance(response.json["totalPages"], int)
assert len(response.json["statistics"]) == 2
assert isinstance(response.json["statistics"][0]["views"], int)
assert isinstance(response.json["statistics"][0]["downloads"], int)
assert isinstance(response.json["statistics"][1]["views"], int)
assert isinstance(response.json["statistics"][1]["downloads"], int)
def test_post_communities_valid_dateTo_mocked(client):
"""Mock test POSTing a request to /communities with a valid dateTo parameter in the request body."""
request_body = {
"dateTo": "2020-01-01T00:00:00Z",
"communities": [
"bde7139c-d321-46bb-aef6-ae70799e5edb",
"2a920a61-b08a-4642-8e5d-2639c6702b1f",
],
}
get_views_return_value = {
"bde7139c-d321-46bb-aef6-ae70799e5edb": 21,
"2a920a61-b08a-4642-8e5d-2639c6702b1f": 0,
}
get_downloads_return_value = {
"bde7139c-d321-46bb-aef6-ae70799e5edb": 575,
"2a920a61-b08a-4642-8e5d-2639c6702b1f": 899,
}
with patch(
"dspace_statistics_api.app.get_views", return_value=get_views_return_value
):
with patch(
"dspace_statistics_api.app.get_downloads",
return_value=get_downloads_return_value,
):
response = client.simulate_post("/communities", json=request_body)
assert response.status_code == 200
assert response.json["limit"] == 100
assert response.json["currentPage"] == 0
assert isinstance(response.json["totalPages"], int)
assert len(response.json["statistics"]) == 2
assert isinstance(response.json["statistics"][0]["views"], int)
assert isinstance(response.json["statistics"][0]["downloads"], int)
assert isinstance(response.json["statistics"][1]["views"], int)
assert isinstance(response.json["statistics"][1]["downloads"], int)
def test_post_communities_invalid_dateTo(client):
"""Test POSTing a request to /communities with an invalid dateTo parameter in the request body."""
request_body = {
"dateFrom": "2020-01-01T00:00:00",
"communities": [
"bde7139c-d321-46bb-aef6-ae70799e5edb",
"2a920a61-b08a-4642-8e5d-2639c6702b1f",
],
}
response = client.simulate_post("/communities", json=request_body)
assert response.status_code == 400
@pytest.mark.xfail
def test_post_communities_valid_limit(client):
"""Test POSTing a request to /communities with a valid limit parameter in the request body."""
request_body = {
"limit": 1,
"communities": [
"bde7139c-d321-46bb-aef6-ae70799e5edb",
"2a920a61-b08a-4642-8e5d-2639c6702b1f",
],
}
response = client.simulate_post("/communities", json=request_body)
assert response.status_code == 200
assert response.json["limit"] == 1
assert response.json["currentPage"] == 0
assert isinstance(response.json["totalPages"], int)
assert len(response.json["statistics"]) == 1
assert isinstance(response.json["statistics"][0]["views"], int)
assert isinstance(response.json["statistics"][0]["downloads"], int)
def test_post_communities_valid_limit_mocked(client):
"""Mock test POSTing a request to /communities with a valid limit parameter in the request body."""
request_body = {
"limit": 1,
"communities": [
"bde7139c-d321-46bb-aef6-ae70799e5edb",
"2a920a61-b08a-4642-8e5d-2639c6702b1f",
],
}
get_views_return_value = {"bde7139c-d321-46bb-aef6-ae70799e5edb": 200}
get_downloads_return_value = {"bde7139c-d321-46bb-aef6-ae70799e5edb": 309}
with patch(
"dspace_statistics_api.app.get_views", return_value=get_views_return_value
):
with patch(
"dspace_statistics_api.app.get_downloads",
return_value=get_downloads_return_value,
):
response = client.simulate_post("/communities", json=request_body)
assert response.status_code == 200
assert response.json["limit"] == 1
assert response.json["currentPage"] == 0
assert isinstance(response.json["totalPages"], int)
assert len(response.json["statistics"]) == 1
assert isinstance(response.json["statistics"][0]["views"], int)
assert isinstance(response.json["statistics"][0]["downloads"], int)
def test_post_communities_invalid_limit(client):
"""Test POSTing a request to /communities with an invalid limit parameter in the request body."""
request_body = {
"limit": -1,
"communities": [
"bde7139c-d321-46bb-aef6-ae70799e5edb",
"2a920a61-b08a-4642-8e5d-2639c6702b1f",
],
}
response = client.simulate_post("/communities", json=request_body)
assert response.status_code == 400
@pytest.mark.xfail
def test_post_communities_valid_page(client):
"""Test POSTing a request to /communities with a valid page parameter in the request body."""
request_body = {
"page": 0,
"communities": [
"bde7139c-d321-46bb-aef6-ae70799e5edb",
"2a920a61-b08a-4642-8e5d-2639c6702b1f",
],
}
response = client.simulate_post("/communities", json=request_body)
assert response.status_code == 200
assert response.json["limit"] == 100
assert response.json["currentPage"] == 0
assert response.json["totalPages"] == 1
assert len(response.json["statistics"]) == 2
assert isinstance(response.json["statistics"][0]["views"], int)
assert isinstance(response.json["statistics"][0]["downloads"], int)
assert isinstance(response.json["statistics"][1]["views"], int)
assert isinstance(response.json["statistics"][1]["downloads"], int)
def test_post_communities_valid_page_mocked(client):
"""Mock test POSTing a request to communities with a valid page parameter in the request body."""
request_body = {
"page": 0,
"communities": [
"bde7139c-d321-46bb-aef6-ae70799e5edb",
"2a920a61-b08a-4642-8e5d-2639c6702b1f",
],
}
get_views_return_value = {
"bde7139c-d321-46bb-aef6-ae70799e5edb": 21,
"2a920a61-b08a-4642-8e5d-2639c6702b1f": 0,
}
get_downloads_return_value = {
"bde7139c-d321-46bb-aef6-ae70799e5edb": 575,
"2a920a61-b08a-4642-8e5d-2639c6702b1f": 899,
}
with patch(
"dspace_statistics_api.app.get_views", return_value=get_views_return_value
):
with patch(
"dspace_statistics_api.app.get_downloads",
return_value=get_downloads_return_value,
):
response = client.simulate_post("/communities", json=request_body)
assert response.status_code == 200
assert response.json["limit"] == 100
assert response.json["currentPage"] == 0
assert isinstance(response.json["totalPages"], int)
assert len(response.json["statistics"]) == 2
assert isinstance(response.json["statistics"][0]["views"], int)
assert isinstance(response.json["statistics"][0]["downloads"], int)
assert isinstance(response.json["statistics"][1]["views"], int)
assert isinstance(response.json["statistics"][1]["downloads"], int)
def test_post_communities_invalid_page(client):
"""Test POSTing a request to /communities with an invalid page parameter in the request body."""
request_body = {
"page": -1,
"communities": [
"bde7139c-d321-46bb-aef6-ae70799e5edb",
"2a920a61-b08a-4642-8e5d-2639c6702b1f",
],
}
response = client.simulate_post("/communities", json=request_body)
assert response.status_code == 400
# vim: set sw=4 ts=4 expandtab:

50
tests/test_api_docs.py Normal file
View File

@ -0,0 +1,50 @@
# SPDX-License-Identifier: GPL-3.0-only
import pytest
from falcon import testing
from dspace_statistics_api.app import app
@pytest.fixture
def client():
return testing.TestClient(app)
def test_get_docs(client):
"""Test requesting the documentation at the root."""
response = client.simulate_get("/")
assert isinstance(response.content, bytes)
assert response.status_code == 200
def test_get_openapi_json(client):
"""Test requesting the OpenAPI JSON schema."""
response = client.simulate_get("/docs/openapi.json")
assert isinstance(response.content, bytes)
assert response.status_code == 200
def test_get_swagger_ui(client):
"""Test requesting the Swagger UI."""
response = client.simulate_get("/swagger")
assert isinstance(response.content, bytes)
assert response.status_code == 200
def test_get_status(client):
"""Test requesting the status page."""
response = client.simulate_get("/status")
assert isinstance(response.content, bytes)
assert response.status_code == 200
# vim: set sw=4 ts=4 expandtab:

View File

@ -1,29 +1,23 @@
from falcon import testing
# SPDX-License-Identifier: GPL-3.0-only
import json
import pytest
from unittest.mock import patch
from dspace_statistics_api.app import api
import pytest
from falcon import testing
from dspace_statistics_api.app import app
@pytest.fixture
def client():
return testing.TestClient(api)
def test_get_docs(client):
"""Test requesting the documentation at the root."""
response = client.simulate_get("/")
assert isinstance(response.content, bytes)
assert response.status_code == 200
return testing.TestClient(app)
def test_get_item(client):
"""Test requesting a single item."""
response = client.simulate_get("/item/c3910974-c3a5-4053-9dce-104aa7bb1621")
response = client.simulate_get("/item/fd8a46d5-1480-4e69-b187-cd3db96d8e4d")
response_doc = json.loads(response.text)
assert isinstance(response_doc["downloads"], int)
@ -70,13 +64,13 @@ def test_get_items_invalid_page(client):
@pytest.mark.xfail
def test_post_items_valid_dateFrom(client):
"""Test POSTing a request with a valid dateFrom parameter in the request body."""
"""Test POSTing a request to /items with a valid dateFrom parameter in the request body."""
request_body = {
"dateFrom": "2020-01-01T00:00:00Z",
"items": [
"c3910974-c3a5-4053-9dce-104aa7bb1620",
"887cc5f8-b5e7-4a2f-9053-49c91ab81313",
"fd8a46d5-1480-4e69-b187-cd3db96d8e4d",
"e53a2eab-1e31-448d-907b-3656ca4e86c1",
],
}
@ -94,23 +88,23 @@ def test_post_items_valid_dateFrom(client):
def test_post_items_valid_dateFrom_mocked(client):
"""Mock test POSTing a request with a valid dateFrom parameter in the request body."""
"""Mock test POSTing a request to /items with a valid dateFrom parameter in the request body."""
request_body = {
"dateFrom": "2020-01-01T00:00:00Z",
"items": [
"c3910974-c3a5-4053-9dce-104aa7bb1620",
"887cc5f8-b5e7-4a2f-9053-49c91ab81313",
"fd8a46d5-1480-4e69-b187-cd3db96d8e4d",
"e53a2eab-1e31-448d-907b-3656ca4e86c1",
],
}
get_views_return_value = {
"c3910974-c3a5-4053-9dce-104aa7bb1620": 21,
"887cc5f8-b5e7-4a2f-9053-49c91ab81313": 0,
"fd8a46d5-1480-4e69-b187-cd3db96d8e4d": 21,
"e53a2eab-1e31-448d-907b-3656ca4e86c1": 0,
}
get_downloads_return_value = {
"c3910974-c3a5-4053-9dce-104aa7bb1620": 575,
"887cc5f8-b5e7-4a2f-9053-49c91ab81313": 899,
"fd8a46d5-1480-4e69-b187-cd3db96d8e4d": 575,
"e53a2eab-1e31-448d-907b-3656ca4e86c1": 899,
}
with patch(
@ -134,13 +128,13 @@ def test_post_items_valid_dateFrom_mocked(client):
def test_post_items_invalid_dateFrom(client):
"""Test POSTing a request with an invalid dateFrom parameter in the request body."""
"""Test POSTing a request to /items with an invalid dateFrom parameter in the request body."""
request_body = {
"dateFrom": "2020-01-01T00:00:00",
"items": [
"c3910974-c3a5-4053-9dce-104aa7bb1620",
"887cc5f8-b5e7-4a2f-9053-49c91ab81313",
"fd8a46d5-1480-4e69-b187-cd3db96d8e4d",
"e53a2eab-1e31-448d-907b-3656ca4e86c1",
],
}
@ -151,13 +145,13 @@ def test_post_items_invalid_dateFrom(client):
@pytest.mark.xfail
def test_post_items_valid_dateTo(client):
"""Test POSTing a request with a valid dateTo parameter in the request body."""
"""Test POSTing a request to /items with a valid dateTo parameter in the request body."""
request_body = {
"dateTo": "2020-01-01T00:00:00Z",
"items": [
"c3910974-c3a5-4053-9dce-104aa7bb1620",
"887cc5f8-b5e7-4a2f-9053-49c91ab81313",
"fd8a46d5-1480-4e69-b187-cd3db96d8e4d",
"e53a2eab-1e31-448d-907b-3656ca4e86c1",
],
}
@ -175,23 +169,23 @@ def test_post_items_valid_dateTo(client):
def test_post_items_valid_dateTo_mocked(client):
"""Mock test POSTing a request with a valid dateTo parameter in the request body."""
"""Mock test POSTing a request to /items with a valid dateTo parameter in the request body."""
request_body = {
"dateTo": "2020-01-01T00:00:00Z",
"items": [
"c3910974-c3a5-4053-9dce-104aa7bb1620",
"887cc5f8-b5e7-4a2f-9053-49c91ab81313",
"fd8a46d5-1480-4e69-b187-cd3db96d8e4d",
"e53a2eab-1e31-448d-907b-3656ca4e86c1",
],
}
get_views_return_value = {
"c3910974-c3a5-4053-9dce-104aa7bb1620": 21,
"887cc5f8-b5e7-4a2f-9053-49c91ab81313": 0,
"fd8a46d5-1480-4e69-b187-cd3db96d8e4d": 21,
"e53a2eab-1e31-448d-907b-3656ca4e86c1": 0,
}
get_downloads_return_value = {
"c3910974-c3a5-4053-9dce-104aa7bb1620": 575,
"887cc5f8-b5e7-4a2f-9053-49c91ab81313": 899,
"fd8a46d5-1480-4e69-b187-cd3db96d8e4d": 575,
"e53a2eab-1e31-448d-907b-3656ca4e86c1": 899,
}
with patch(
@ -215,13 +209,13 @@ def test_post_items_valid_dateTo_mocked(client):
def test_post_items_invalid_dateTo(client):
"""Test POSTing a request with an invalid dateTo parameter in the request body."""
"""Test POSTing a request to /items with an invalid dateTo parameter in the request body."""
request_body = {
"dateFrom": "2020-01-01T00:00:00",
"items": [
"c3910974-c3a5-4053-9dce-104aa7bb1620",
"887cc5f8-b5e7-4a2f-9053-49c91ab81313",
"fd8a46d5-1480-4e69-b187-cd3db96d8e4d",
"e53a2eab-1e31-448d-907b-3656ca4e86c1",
],
}
@ -232,13 +226,13 @@ def test_post_items_invalid_dateTo(client):
@pytest.mark.xfail
def test_post_items_valid_limit(client):
"""Test POSTing a request with a valid limit parameter in the request body."""
"""Test POSTing a request to /items with a valid limit parameter in the request body."""
request_body = {
"limit": 1,
"items": [
"c3910974-c3a5-4053-9dce-104aa7bb1620",
"887cc5f8-b5e7-4a2f-9053-49c91ab81313",
"fd8a46d5-1480-4e69-b187-cd3db96d8e4d",
"e53a2eab-1e31-448d-907b-3656ca4e86c1",
],
}
@ -254,18 +248,18 @@ def test_post_items_valid_limit(client):
def test_post_items_valid_limit_mocked(client):
"""Mock test POSTing a request with a valid limit parameter in the request body."""
"""Mock test POSTing a request to /items with a valid limit parameter in the request body."""
request_body = {
"limit": 1,
"items": [
"c3910974-c3a5-4053-9dce-104aa7bb1620",
"887cc5f8-b5e7-4a2f-9053-49c91ab81313",
"fd8a46d5-1480-4e69-b187-cd3db96d8e4d",
"e53a2eab-1e31-448d-907b-3656ca4e86c1",
],
}
get_views_return_value = {"c3910974-c3a5-4053-9dce-104aa7bb1620": 21}
get_downloads_return_value = {"c3910974-c3a5-4053-9dce-104aa7bb1620": 575}
get_views_return_value = {"fd8a46d5-1480-4e69-b187-cd3db96d8e4d": 21}
get_downloads_return_value = {"fd8a46d5-1480-4e69-b187-cd3db96d8e4d": 575}
with patch(
"dspace_statistics_api.app.get_views", return_value=get_views_return_value
@ -286,13 +280,13 @@ def test_post_items_valid_limit_mocked(client):
def test_post_items_invalid_limit(client):
"""Test POSTing a request with an invalid limit parameter in the request body."""
"""Test POSTing a request to /items with an invalid limit parameter in the request body."""
request_body = {
"limit": -1,
"items": [
"c3910974-c3a5-4053-9dce-104aa7bb1620",
"887cc5f8-b5e7-4a2f-9053-49c91ab81313",
"fd8a46d5-1480-4e69-b187-cd3db96d8e4d",
"e53a2eab-1e31-448d-907b-3656ca4e86c1",
],
}
@ -303,13 +297,13 @@ def test_post_items_invalid_limit(client):
@pytest.mark.xfail
def test_post_items_valid_page(client):
"""Test POSTing a request with a valid page parameter in the request body."""
"""Test POSTing a request to /items with a valid page parameter in the request body."""
request_body = {
"page": 0,
"items": [
"c3910974-c3a5-4053-9dce-104aa7bb1620",
"887cc5f8-b5e7-4a2f-9053-49c91ab81313",
"fd8a46d5-1480-4e69-b187-cd3db96d8e4d",
"e53a2eab-1e31-448d-907b-3656ca4e86c1",
],
}
@ -318,7 +312,7 @@ def test_post_items_valid_page(client):
assert response.status_code == 200
assert response.json["limit"] == 100
assert response.json["currentPage"] == 0
assert response.json["totalPages"] == 0
assert response.json["totalPages"] == 1
assert len(response.json["statistics"]) == 2
assert isinstance(response.json["statistics"][0]["views"], int)
assert isinstance(response.json["statistics"][0]["downloads"], int)
@ -327,23 +321,23 @@ def test_post_items_valid_page(client):
def test_post_items_valid_page_mocked(client):
"""Mock test POSTing a request with a valid page parameter in the request body."""
"""Mock test POSTing a request to /items with a valid page parameter in the request body."""
request_body = {
"page": 0,
"items": [
"c3910974-c3a5-4053-9dce-104aa7bb1620",
"887cc5f8-b5e7-4a2f-9053-49c91ab81313",
"fd8a46d5-1480-4e69-b187-cd3db96d8e4d",
"e53a2eab-1e31-448d-907b-3656ca4e86c1",
],
}
get_views_return_value = {
"c3910974-c3a5-4053-9dce-104aa7bb1620": 21,
"887cc5f8-b5e7-4a2f-9053-49c91ab81313": 0,
"fd8a46d5-1480-4e69-b187-cd3db96d8e4d": 21,
"e53a2eab-1e31-448d-907b-3656ca4e86c1": 0,
}
get_downloads_return_value = {
"c3910974-c3a5-4053-9dce-104aa7bb1620": 575,
"887cc5f8-b5e7-4a2f-9053-49c91ab81313": 899,
"fd8a46d5-1480-4e69-b187-cd3db96d8e4d": 575,
"e53a2eab-1e31-448d-907b-3656ca4e86c1": 899,
}
with patch(
@ -367,16 +361,19 @@ def test_post_items_valid_page_mocked(client):
def test_post_items_invalid_page(client):
"""Test POSTing a request with an invalid page parameter in the request body."""
"""Test POSTing a request to /items with an invalid page parameter in the request body."""
request_body = {
"page": -1,
"items": [
"c3910974-c3a5-4053-9dce-104aa7bb1620",
"887cc5f8-b5e7-4a2f-9053-49c91ab81313",
"fd8a46d5-1480-4e69-b187-cd3db96d8e4d",
"e53a2eab-1e31-448d-907b-3656ca4e86c1",
],
}
response = client.simulate_post("/items", json=request_body)
assert response.status_code == 400
# vim: set sw=4 ts=4 expandtab: