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

Compare commits

...

214 Commits

Author SHA1 Message Date
914ec52fbb CHANGELOG.md: Move unrelease changes to 0.9.0 2019-01-22 09:02:29 +02:00
5524066656 CHANGELOG.md: Add note about catching errors 2019-01-22 09:01:54 +02:00
043d897cef dspace_statistics_api/indexer.py: Catch case of no views/downloads
Don't fail with an exception when there are no views or downloads,
for example on a new DSpace installation.
2019-01-22 09:00:22 +02:00
bd28353cda README.md: Remove TODO for fixing querying of shards 2019-01-22 08:41:39 +02:00
e23d66c2a2 CHANGELOG.md: Add note about fixing querying of sharded cores 2019-01-22 08:41:31 +02:00
40e284dac0 dspace_statistics_api/indexer.py: Query multiple shards
DSpace's stats-util script splits the Solr statistics core into yearly
shards. We need to use Solr's `shards` query parameter in order to get
the statistics for previous years. This commit adds a helper function
to enumerate the active Solr cores to find yearly shards matching the
statistics-YYYY pattern and add them to the query.
2019-01-22 08:39:36 +02:00
934fa9db9b README.md: Add TODO about sharded statistics cores 2019-01-21 12:55:43 +02:00
1fabb72b58 Update requirements
Generated from pipenv with:

  $ pipenv lock -r > requirements.txt
  $ pipenv lock -r -d > requirements-dev.txt
2019-01-16 12:34:50 +02:00
c7f95f0b60 README.md: Update TODO
I think it might be possible to compute community and collection
statistics from Solr and make them available at new endpoints:

  - /communities
  - /community/id
  - /collections
  - /collection/id
2019-01-16 09:59:29 +02:00
c95a98dd2d Pipfile.lock: update dependencies
Updated with `pipenv update`.
2019-01-15 10:22:46 +02:00
3f70f94a10 Pipfile.lock: Run pipenv update 2018-11-26 11:53:37 +02:00
9b8ad9defd Merge pull request #9 from ilri/pipenv-update
Pipenv update
2018-11-19 23:50:44 +02:00
d69ab20220 CHANGELOG.md: pytest version 4.0.0 2018-11-19 23:46:03 +02:00
378f56ddc2 Pipfile.lock: Run pipenv update 2018-11-19 23:34:34 +02:00
5a2a7d684c CHANGELOG.md: Move unreleased changes to version 0.8.1 2018-11-14 09:37:00 +02:00
18276e910f CHANGELOG.md: Add notes about pipenv 2018-11-14 09:36:13 +02:00
8de8c2765f Merge pull request #8 from ilri/update-dependencies
Update dependencies
2018-11-14 09:34:45 +02:00
11a1755e59 Update requirements.txt
Generated from pipenv with:

    $ pipenv lock -r > requirements.txt
2018-11-14 09:19:47 +02:00
a835b0fdc5 Re-create pipenv environment from scratch
When I originally created the pipenv environment I used the standard
pip requirements.txt that I already had, which captured all the mod-
ules and their exact versions at the time. This makes it hard to se-
parate the project's actual dependencies from the dependencies' dep-
endencies, complicating the Pipfile and making it hard to update mo-
dule versions later.

I've re-created the environment with the following commands:

    $ pipenv install gunicorn falcon psycopg2-binary git+https://github.com/alanorth/SolrClient.git@kazoo-2.5.0#egg=SolrClient
    $ pipenv install --dev ipython flake8 pytest
2018-11-14 09:07:32 +02:00
a88600c92b README.md: Add note about GPLv3 2018-11-13 12:34:31 +02:00
019d9242c9 Merge pull request #7 from ilri/use-pip
Rework to use pip instead of pipenv
2018-11-12 09:17:16 +02:00
f4d7312a3f CHANGELOG.md: Add unreleased changes 2018-11-12 09:02:04 +02:00
9c46cfc7e2 Use Python 3.7 for pipenv
Now that I'm only using pipenv locally it shouldn't create problems
for people. They can still just create a vanilla virtualenv and use
pip to install the dependencies.
2018-11-12 08:54:54 +02:00
c1c2e319ac README.md: Rework to use pip instead of pipenv
Pipenv is great for local development, but I don't think many people
are using it yet. I can use it locally and on Travis, but still keep
vanilla requirements.txt for use with pip. The requirements.txt file
can be generated easily from pipenv itself:

    $ pipenv lock -r > requirements.txt

The same for the development requirements:

    $ pipenv lock -r -d > requirements-dev.txt
2018-11-12 08:49:02 +02:00
0895b4f469 Add requirements-dev.txt for pip
Generated with pipenv lock -r -d. Will be used for separating the
development dependencies.
2018-11-12 08:48:45 +02:00
dcfef06a65 Pipfile.lock: Run pipenv update 2018-11-12 08:20:47 +02:00
13736d6359 CHANGELOG.md: Move unreleased changes to verison 0.8.0 2018-11-11 17:16:26 +02:00
4fc64edeb8 Merge pull request #6 from ilri/pytest
Pytest
2018-11-11 17:14:49 +02:00
2a8901dc4f CHANGELOG.md: Update notes 2018-11-11 17:10:45 +02:00
e25c974796 README.md: We have tests now 2018-11-11 17:08:51 +02:00
ffc62e9ee6 tests/test_api.py: Use response.text for all json.loads()
This allows the code to work in Python 3.5 as well as 3.6+.
2018-11-11 17:05:31 +02:00
556c5ae088 tests/test_api.py: Use response.text instead of content
Falcon's response content is raw bytes, while its text is a string.
Let's use the latter so we can use json.loads() in Python 3.5, 3.6,
and 3.7 with the same code.

See: https://falcon.readthedocs.io/en/stable/api/testing.html
2018-11-11 17:01:17 +02:00
d94134f80a tests/test_api.py: Try to add workaround for Python 3.5
In Python 3.5 it seems that json.loads() cannot decode a bytes, but
it works in Python 3.6 and 3.7. Let's try a workaround to see if we
can get it working on both Python 3.5 and 3.6+.

See: https://docs.python.org/3.5/library/json.html#json.loads
See: https://docs.python.org/3.6/library/json.html#json.loads
2018-11-11 17:00:20 +02:00
586231eb2d .travis.yml: Use PostgreSQL 9.5
Default PostgreSQL in Travis CI is 9.2 which is very old, so let's
try to use 9.5.

See: https://docs.travis-ci.com/user/database-setup/#postgresql
2018-11-11 16:41:35 +02:00
766b77a3b6 .travis.yml: Use PostgreSQL directly
It seems that Travis CI already has a PostgreSQL service running.
2018-11-11 16:35:28 +02:00
1959e8154e .travis.yml: Use localhost for Docker's PostgreSQL ports
See: https://docs.travis-ci.com/user/docker/
2018-11-11 16:28:18 +02:00
d40b2f0b2e Test API using pytest and PostgreSQL on Travis
First attempt at getting the Travis Docker setup correct. Inspired
by the Travis pipenv setup used in Responder.

See: https://docs.travis-ci.com/user/docker/
See: https://github.com/kennethreitz/responder/blob/master/.travis.yml
2018-11-11 16:25:16 +02:00
061d0a8f5f CHANGELOG.md: Add API tests to unreleased changes 2018-11-11 16:24:54 +02:00
e57660ff88 Add initial pytest configuration
From: https://github.com/kennethreitz/responder/blob/master/pytest.ini
2018-11-11 16:24:54 +02:00
5c8756bede Add pytest to pipenv development packages 2018-11-11 16:24:54 +02:00
bae9fb80e4 Add initial API tests
Test the basic assumptions of the API like response codes and types.
2018-11-11 16:24:54 +02:00
8a65d99e08 .travis.yml: Don't limit builds to master
This is good in theory but it means we can't trigger builds for other
branches on the fly from the Travis web interface.
2018-11-11 16:21:48 +02:00
d479b7dc6c CHANGELOG.md: Syntax fixes 2018-11-11 00:08:44 +02:00
40aac8bf89 Merge pull request #5 from ilri/database-error-handling
Database error handling
2018-11-11 00:07:25 +02:00
53ba6f2936 CHANGELOG.md: Add database try/except to unreleased changes 2018-11-11 00:05:49 +02:00
140cc4cb07 README.md: Remove TODO for database try/except
Now database connection errors are properly excepted and raised.
2018-11-11 00:04:28 +02:00
d5d2d2149b dspace_statistics_api/database.py: Raise HTTP 500 on error
Properly except on database connection error and raise an HTTP 500
instead of spamming the console/log with twenty lines of text.
2018-11-10 23:58:58 +02:00
4c51d12eb4 CHANGELOG.md: Move unreleased changes to version 0.7.0 2018-11-07 17:55:01 +02:00
a6ce44e852 Merge pull request #4 from ilri/database-refactor
Database refactor
2018-11-07 17:54:04 +02:00
f6e866a589 dspace_statistics_api/indexer.py: Remove debug code 2018-11-07 17:51:24 +02:00
eb5c187d41 CHANGELOG.md: Add note about database re-factor 2018-11-07 17:50:46 +02:00
b06c82bb16 README.md: Remove TODO about closing database connection
Now I'm using a database manager class with Python's "with" context
blocks to automatically and concisely open and close connections.
2018-11-07 17:47:59 +02:00
2f342be948 Refactor database code to use a context manager
Instead of opening one global persistent database connection when
the application I am now abstracting it to a class that I can use
in combination with Python's "with" context. Both connections and
cursors are kept for the context of each "with" block and closed
automatically when exiting.

See: https://alysivji.github.io/managing-resources-with-context-managers-pythonic.html
See: http://initd.org/psycopg/docs/connection.html#connection.close
2018-11-07 17:41:21 +02:00
e39f2b260c Merge pull request #3 from ilri/ipython
Add ipython to pipenv dev packages
2018-11-07 17:09:09 +02:00
60ad474b88 Add ipython to pipenv dev packages
This is very useful for debugging Python code interactively.
2018-11-07 17:07:14 +02:00
888f85d19e README.md: Adjust installation for pipenv
It's nicer to manager module versions using pipenv, and I can still
generate a requirements.txt for deploying the exact versions on the
production server.
2018-11-04 16:07:27 +02:00
df7de93964 CHANGELOG.md: Add pipenv to unreleased changes 2018-11-04 15:59:11 +02:00
7218631cc4 requirements.txt: Regenerate
Created from pipenv with the following command:

    $ pipenv lock -r > requirements.txt
2018-11-04 15:58:31 +02:00
085e525b2f Regenerate pipenv
Uses 'kazoo-2.5.0' branch name for installing SolrClient instead of
the commit hash and adds flake8 as a dev package. This means that I
can track dependencies for production and development and still end
up with a requirements.txt for produciton.
2018-11-04 15:55:28 +02:00
e1580df12f requirements.txt: Update packages
Generated from pipenv with:

    $ pipenv run pip freeze > requirements.txt
2018-11-04 15:39:09 +02:00
be18779ff9 Add flake8 to pipenv 2018-11-04 15:38:51 +02:00
60cfd8f23b Add Pipfile for pipenv
Eventually I'd like to be able to use pipenv instead of plain pip.
For now I'll just keep using pipenv and generating requirements.txt
like this:

    $ pipenv run pip freeze > requirements.txt

Then I can kinda have the best of both worlds, where I use pipenv
on my local machine and pip with requirements.txt on the server.
2018-11-04 15:35:47 +02:00
87fd117d77 .hound.yml: Set pull requests to failed if build fails 2018-11-04 00:53:37 +02:00
f262ebdca2 CHANGELOG.md: Add unreleased changes 2018-11-04 00:50:46 +02:00
64d7f1a3b2 Enable Flake8 validation in Hound CI
Will check all pull requests in the project to make sure they don't
violate PEP 8 style (except the E501 for long lines because I think
it makes code hard to read).
2018-11-04 00:48:06 +02:00
a238a727d2 CHANGELOG.md: Add unreleased changes 2018-11-04 00:05:16 +02:00
cc5ce3ab98 Correct issues highlighted by Flake8
Flake8 validates code style against PEP 8 in order to encourage the
writing of idiomatic Python. For reference, I am currently ignoring
errors about line length (E501) because I feel it makes code harder
to read.

This is the invocation I am using:

    $ flake8 --ignore E501 dspace_statistics_api
2018-11-04 00:04:27 +02:00
70dfcb93c5 dspace_statistics_api/database.py: Don't quote host in connect() 2018-11-03 22:43:05 +02:00
69bcd1b5e4 CHANGELOG.md: Add unreleased changes 2018-11-03 22:42:08 +02:00
5f3bd61998 Allow configuration of PostgreSQL port
Defaults to port 5432, but can be overridden with DATABASE_PORT.
2018-11-03 22:40:45 +02:00
e54dd8888f README.md: Update requirements 2018-11-01 16:31:36 +02:00
2ba09f8693 README.md: Improve introduction
Obsessed with the text presentation and line length in GitHub!
2018-11-01 16:28:01 +02:00
a468a87a5a README.md: Improve introduction 2018-11-01 15:58:12 +02:00
6a30b6550d README.md: Improve introduction 2018-11-01 15:45:53 +02:00
18f013bfa0 README.md: Add Falcon to introduction 2018-11-01 10:24:37 +02:00
78900b5d85 CHANGELOG.md: Add changes for v0.6.1 2018-11-01 00:39:12 +02:00
eb08832bf8 Sync API documentation HTML with README.md 2018-11-01 00:37:52 +02:00
c2ec780ad9 README.md: Improve API documentation 2018-11-01 00:37:40 +02:00
df8ebc8bf1 README.md: Improve API endpoint documentation 2018-11-01 00:31:16 +02:00
0d4be5f4c8 README.md: Add API documentation endpoint 2018-11-01 00:22:16 +02:00
30dc7f1939 Add basic API documentation on root (/)
I had imagined plugging in an interactive Swagger or OpenAPI instance
here, but that's actually much more involved in Falcon than I want to
deal with right now.
2018-11-01 00:19:39 +02:00
77194707fd README.md: Improve introduction 2018-11-01 00:08:24 +02:00
10c1f8bdcc README.md: Update Travis CI badge 2018-10-31 23:14:38 +02:00
da74943da2 README.md: Update introduction 2018-10-31 22:40:36 +02:00
fc8348ab29 README.md: Add acknoledgement about the Solr queries 2018-10-31 19:36:50 +02:00
15c3299b99 CHANGELOG.md: Add changes for v0.6.0 2018-10-31 19:26:45 +02:00
d36be5ee50 contrib: Update systemd unit files for refactor 2018-10-28 11:14:21 +02:00
2f45d27554 dspace_statistics_api/app.py: remove unused code
This was added accidentally when I refactored. I was trying to see
if I could use Falcon's on_exit() hook.
2018-10-28 11:14:21 +02:00
b8356f7a87 Add "application" alias to API object
By default gunicorn looks for an "application" object to run, so this
saves us having to type api:app.
2018-10-28 11:14:21 +02:00
2136dc79ce Remove shebang from indexer.py
This is run as a Python module now so does not need a shebang.
2018-10-28 11:14:21 +02:00
ed60120cef Remove executable bit from indexer.py
Now it is run as a Python module.
2018-10-28 11:14:21 +02:00
c027f01b48 Refactor project structure
This follows guidance from several well-known Python best practices
guides. Basically, the idea is create a package for the application
that is comprised of several re-usable modules.

See: https://docs.python-guide.org/writing/structure/
See: https://realpython.com/python-application-layouts/
2018-10-28 11:14:21 +02:00
754663f062 CHANGELOG.md: Add changes for version 0.5.2 2018-10-28 11:12:27 +02:00
507699e58a requirements.txt: Update libraries
Switch to a personal fork of SolrClient so that we can use kazoo 2.5.0
and get rid of the error about the 'async' keyword on Python 3.7. Also
this bumps some of the other libraries to their latest versions.
2018-10-28 11:09:47 +02:00
a016916995 CHANGELOD.md: Add note about ujson 2018-10-24 14:15:03 +03:00
6fd2827a7c Use Python's native json instead of ujson
Falcon can optionally use ujson to speed up JSON (de)serialization,
but Falcon's already really fast and requiring ujson actually makes
deployment trickier in some cases (for example in Docker containers
that are based on Alpine Linux).

Here are some tests of Falcon 1.4.1 on Python 3.5 from my laptop:

    1. falcon...............60172 req/sec or 16.62 μs/req (36x)
    2. falcon-ext...........34186 req/sec or 29.25 μs/req (20x)
    3. bottle...............32924 req/sec or 30.37 μs/req (20x)
    4. werkzeug.............11948 req/sec or 83.70 μs/req (7x)
    5. flask.................6654 req/sec or 150.30 μs/req (4x)
    6. django................4565 req/sec or 219.04 μs/req (3x)
    7. pecan.................1672 req/sec or 598.19 μs/req (1x)

The tests were conducted with Falcon's official Docker benchmarking
tools on my Intel(R) Core(TM) i7-8550U CPU @ 1.80GHz on Arch Linux.

See: https://github.com/falconry/falcon/tree/master/docker
2018-10-24 14:08:23 +03:00
62142eb79e CHANGELOG.md: Move unreleased changes to v0.5.0 2018-10-24 12:02:42 +03:00
fda0321942 CHANGELOG.md: Add note about Solr in API component 2018-10-24 12:01:47 +03:00
963aa245c8 app.py: Don't initialize Solr connection
We only need Solr in the indexing component, not for the API itself.
2018-10-24 11:59:50 +03:00
568ff2eebb CHANGELOG.md: Add note about nginx configuration 2018-10-23 14:56:44 +03:00
deecb8a10b README.md: Add example nginx configuration 2018-10-23 14:55:36 +03:00
12f45d7c08 contrib: Adjust example path 2018-10-23 14:34:29 +03:00
f65089f9ce CHANGELOG.md: Update and move to 0.4.3 release 2018-10-17 09:51:44 +03:00
1db5cf1c29 README.md: Grammar 2018-10-17 09:51:35 +03:00
e581c4b1aa README.md: Improve documentation 2018-10-17 09:50:30 +03:00
e8d356c9ca README.md: Add TODO about Python 3.6+ f-string syntax
They are faster.
2018-10-17 09:13:25 +03:00
34a9b8d629 CHANGELOG.md: Add unreleased changes for Travis CI 2018-10-14 19:02:09 +03:00
41e3d66a0e .travis.yml: Only build master branch 2018-10-14 19:00:31 +03:00
9b2a6137b4 README.md: Add Travis CI badge
For now this is only an indicator that the Python requirements can
be satisfied and installed.
2018-10-14 18:58:12 +03:00
600b986f99 .travis.yml: Use Python 3.7-dev instead of 3.7
I don't think Travis supports Python 3.7 yet because the builds for
that version keep failing.
2018-10-14 18:57:30 +03:00
49a7790794 .travis.yml: Move script to one line 2018-10-14 18:53:45 +03:00
f2deba627c .travis.yml: Run pip install as script
Basically for now there are no tests so I just want to just check
that requirements.txt is correct and that all dependencies can be
installed.
2018-10-14 18:47:14 +03:00
9323513794 README.md: Update instructions 2018-10-14 18:45:40 +03:00
daf15610f2 CHANGELOG.md: Update changes and move to 0.4.2 2018-10-05 00:19:18 +03:00
4ede966dbb indexer.py: Fix logic error in SQL insert
This was inserting correctly on the first run, but subsequent runs
were inserting into the incorrect column on conflict. This made it
seem like there were downloads for items where there were none.
2018-10-05 00:16:24 +03:00
3580473a6d README.md: Add TODO about JSON in PostgreSQL 2018-10-03 20:08:18 +03:00
071c24535f README.md: Add TODO about API versions 2018-10-03 11:12:18 +03:00
4291aecac4 README.md: Formatting 2018-09-27 12:45:15 +03:00
46bf537e88 CHANGELOG.md: Add note about cursor change 2018-09-27 11:08:42 +03:00
eaca5354d3 app.py: Iterate directly on cursor
We don't need to create an intermediate variable for the results of
the SQL query because psycopg2's cursor is iterable.

See: http://initd.org/psycopg/docs/cursor.html
2018-09-27 11:03:44 +03:00
4600288ee4 CHANGELOG.md: Add note about ujson 2018-09-27 09:53:42 +03:00
8179563378 requirements.txt: pip freeze 2018-09-27 09:53:16 +03:00
b14c3eef4d indexer.py: Use ujson instead of json
Falcon optionally makes use of the ujson library to speed up media
(de)serialization, error serialization, and query string parsing.

See: https://falcon.readthedocs.io/en/stable/user/install.html
2018-09-27 09:51:40 +03:00
71a789b13f CHANGELOG.md. Add unreleased changes 2018-09-27 09:30:48 +03:00
c68ddacaa4 README.md: Add note about systemd units for deployment 2018-09-27 09:26:47 +03:00
9c9e79769e README.md: Add TODO 2018-09-27 09:17:45 +03:00
2ad5ade556 README.md: Improve introduction 2018-09-27 09:12:52 +03:00
7412a09670 README.md: Improve introduction 2018-09-27 09:07:28 +03:00
bb744a00b8 README.md: Add requirements 2018-09-27 08:57:27 +03:00
7499b89d99 CHANGELOG.md: Move unreleased changes to v0.4.1 2018-09-27 08:15:54 +03:00
2c1e4952b1 indexer.py: Remove comment
I had left this there so I could remember how to get the number of
facets, but I don't need it anymore.
2018-09-26 23:27:48 +03:00
379f202c3f CHANGELOG.md: Add unreleased changes 2018-09-26 23:26:48 +03:00
560fa6056d README.md: Remove batch inserts from TODO 2018-09-26 23:25:35 +03:00
385a34e5d0 indexer.py: Use psycopg2's execute_values to batch inserts
Batch inserts are much faster than a series of individual inserts
because they drastically reduce the overhead caused by round-trip
communication with the server. My tests in development confirm:

  - cursor.execute(): 19 seconds
  - execute_values(): 14 seconds

I'm currently only working with 4,500 rows, but I will experiment
with larger data sets, as well as larger batches. For example, on
the PostgreSQL mailing list a user reports doing 10,000 rows with
a page size of 100.

See: http://initd.org/psycopg/docs/extras.html#psycopg2.extras.execute_values
See: https://github.com/psycopg/psycopg2/issues/491#issuecomment-276551038
2018-09-26 23:10:29 +03:00
d0ea62d2bd database.py: Use one line for psycopg2 imports 2018-09-26 22:23:24 +03:00
366ae25b8e README.md: Add link to psycopg2 issue about batch inserts 2018-09-26 22:23:08 +03:00
0f3054ae03 README.md: Add TODO about batch DB inserts 2018-09-26 16:31:13 +03:00
6bf34235d4 CHANGELOG.md: Move unreleased changes to version 0.4.0 2018-09-26 02:51:27 +03:00
e604d8ca81 indexer.py: Major refactor
Basically Solr's numFound has nothing to do with the actual number
of distinct facets that are returned. You need to use Solr's stats
component to get the number of distinct facets, aka countDistinct.
This is apparently deprecated in newer Solr versions, but we're on
version 4.10 and it works there.

Also, I realized that there is no need to return facets for items
without any views or downloads. Using facet.mincount=1 reduces the
result set size and also means we can store less data in the data-
base. The API returns HTTP 404 Not Found if an item is not in the
database anyways.

I can't figure it out exactly, but there is some weird issue with
Solr's facet results when you don't use facet.mincount=1. For some
reason you get tons of results with an id that doesn't even exist
in the document database, let alone as an actual DSpace item!

See: https://lucene.apache.org/solr/guide/6_6/the-stats-component.html
2018-09-26 02:41:10 +03:00
fc35b816f3 CHANGELOG.md: Add unreleased changes 2018-09-25 23:09:44 +03:00
9e6a2f7559 contrib/dspace-statistics-indexer.timer: Fix syntax
You can test OnCalendar strings using systemd-analyze calendar, eg:

    # systemd-analyze calendar '*-*-* 06:00:00,18:00:00'
    Failed to parse calendar specification '*-*-* 06:00:00,18:00:00':
    Invalid argument
    # systemd-analyze calendar '*-*-* 06,18:00:00'
    Normalized form: *-*-* 06,18:00:00
        Next elapse: Wed 2018-09-26 06:00:00 EEST
           (in UTC): Wed 2018-09-26 03:00:00 UTC
           From now: 6h left
2018-09-25 23:07:03 +03:00
46cfc3ffbc CHANGELOG.md: Release version 0.3.2 2018-09-25 13:14:08 +03:00
2850035a4c Return HTTP 404 when an item id is not found 2018-09-25 13:12:53 +03:00
c0b550109a README.md: Improve wording 2018-09-25 12:24:52 +03:00
bfceffd84d indexer.py: Improve inline documentation 2018-09-25 12:23:31 +03:00
d0552f5047 CHANGELOG.md: Move unreleased changes to version 0.3.1 2018-09-25 12:18:26 +03:00
c3a0bf7f44 CHANGELOG.md: Add Python 3.7 to Travis CI config 2018-09-25 12:17:49 +03:00
6e47e9c9ee .travis.yml: Add Python 3.7 2018-09-25 12:17:20 +03:00
cd90d618d6 CHANGELOG.md: Fix error in old release 2018-09-25 12:17:01 +03:00
280d211d56 CHANGELOG.md: Add note about kazoo 2.5.0 2018-09-25 12:12:10 +03:00
806d63137f requirements.txt: Use kazoo 2.5.0
SolrClient 0.2.1 currently depends on kazoo 2.2.1, but there is an
issue with Python 3.7 in kazoo <= 2.5.0. Kazoo 2.5.0 fixes the is-
sue with Python 3.7, and for my limited usage of SolrClient it se-
ems to work fine.

See: https://github.com/moonlitesolutions/SolrClient/issues/79
2018-09-25 12:08:28 +03:00
f7c7390e4f README.md: Add note about Python 3.7 2018-09-25 12:07:58 +03:00
702724e8a4 CHANGELOG.md: Move unreleased changes to version 0.3.0 2018-09-25 11:38:36 +03:00
36818d03ef CHANGELOG.md: Update unreleased changes 2018-09-25 11:37:56 +03:00
4cf8656b35 Change / route to /items
I think it's more obvious if the "all items" route is plural. Also,
this will allow me to eventually put documentation at the root.
2018-09-25 11:34:07 +03:00
f30a464cd1 README.md: Add notes about API endpoints 2018-09-25 11:28:12 +03:00
93ae12e313 README.md: Update introduction 2018-09-25 11:15:12 +03:00
dc978e9333 CHANGELOG.md: Add note about requirements.txt and Travis CI 2018-09-25 11:09:02 +03:00
295436fea0 Add .travis.yml 2018-09-25 11:08:01 +03:00
46a1476ab0 Add requirements.txt
Generated with `pip freeze`. This is so I can pin the versions of
packages that I've tested with as well as to allow Travis to test
whether the project runs on various Pythons and to let GitHub in-
form me of vulnerabilities in some libraries.
2018-09-25 11:02:50 +03:00
87dbb6c4df CHANGELOG.md: Release version 0.2.1 2018-09-25 02:21:44 +03:00
3160c44566 app.py: Remove comment
This comment was added when I first began the application and the
testing status is documented in the README now.
2018-09-25 02:20:51 +03:00
4b72f626d9 Update string substitution format
Instead of doing numbered strings I will just depend on the order,
at least to be consistent.
2018-09-25 02:19:29 +03:00
2d3b7620e3 CHANGELOG.md: Add note about psycopg2.extras.DictCursor 2018-09-25 02:08:54 +03:00
6e4bc630f7 database.py: Use psycopg2.extras.DictCursor
This allows us to access records using their column name. I didn't
notice that this was not working, as I had been testing the wrong
server!

See: http://initd.org/psycopg/docs/extras.html
2018-09-25 02:06:29 +03:00
44884140e5 CHANGELOG.md: Add new unreleased changes 2018-09-25 01:11:37 +03:00
74ff86ee3b contrib: Update environment settings in system units 2018-09-25 01:10:14 +03:00
3327884f21 Update docs to remove SQLite stuff
I've decided to use PostgreSQL instead of SQLite because the UPSERT
support is available in versions of PostgreSQL we're alread running,
whereas SQLite needs a VERY new (3.24.0) version that is not avail-
able on any recent long-term support Ubuntu releases.
2018-09-25 00:56:01 +03:00
8f7450f67a Use PostgreSQL instead of SQLite
I was very surprised how easy and fast and robust SQLite was, but in
the end I realized that its UPSERT support only came in version 3.24
and both Ubuntu 16.04 and 18.04 have older versions than that! I did
manage to install libsqlite3-0 from Ubuntu 18.04 cosmic on my xenial
host, but that feels dirty.

PostgreSQL has support for UPSERT since 9.5, not to mention the same
nice LIMIT and OFFSET clauses.
2018-09-25 00:49:47 +03:00
28d61fb041 README.md: Add notes about Python and SQLite versions 2018-09-24 17:26:48 +03:00
cbc98991b4 CHANGELOG.md: Move unreleased notes to version 0.1.0 2018-09-24 16:14:14 +03:00
6c28be0463 README.md: Add note about route for all items 2018-09-24 16:13:26 +03:00
42e8f17305 CHANGELOG.md: Add note about route for all items 2018-09-24 16:13:05 +03:00
19a45f3f6f app.py: Add route to page through all item statistics
This route exposes all item statistics and uses the limit and offset
parameters to control paging throug the result set. The logic here
is extremely easy thanks to the brilliant LIMIT and OFFSET features
of SQLite (of course the SQL query sorts the results by some unique
field to ensure the order is already the same).
2018-09-24 16:07:26 +03:00
505ef31101 CHANGELOG.md: Add note about UPSERT 2018-09-24 14:31:05 +03:00
1543cacc54 app.py: Update SQL logic to use single table
The indexer.py script was updated to use a single table because I
learned about UPSERT. This simplifies the database schema and the
Python logic, and makes it easier to page all views and downloads
at once without complicated JOIN queries.
2018-09-24 14:28:00 +03:00
2cab456f16 indexer.py: Use single items table with UPSERT
I was using two separate tables for item views and downloads without
realizing that SQLite didn't support FULL OUTER JOIN, which would be
needed to get views and downloads for a given item in a single query.

Instead I can use one table with a default value of 0 for both views
and downloads, and then use "UPSERT" to populate the statistics. This
is a newish SQL concept that allows you to attempt an INSERT and then
specify an action to perform in case of conflict. This works well in
SQLite and actually simplifies my Python logic greatly!

Note that the "excluded" table qualifier is a special keyword that
allows you to reference the value that would have been inserted.

See: https://www.sqlite.org/lang_UPSERT.html
2018-09-24 14:19:50 +03:00
53615dea2d indexer.py: Add license and documentation 2018-09-24 09:18:50 +03:00
2d8d1e6833 README.md: Add TODO for nonexistent items 2018-09-24 00:48:02 +03:00
e26e595ea1 README.md: Add more TODOs 2018-09-24 00:35:00 +03:00
a9151b5bbf CHANGELOG.md: Update unreleased notes 2018-09-24 00:30:58 +03:00
76833d6f5f contrib: Update some old CGSpace references to DSpace 2018-09-24 00:30:26 +03:00
a51422273c Remove SOLR_CORE configuration variable
This parameter is not customizable. All DSpace instances use this
name for the Solr statistics core.
2018-09-24 00:20:54 +03:00
89621af85d Split database access into RW and RO
The indexer need to be able to write to the database, but the API only
needs to read it.
2018-09-24 00:00:05 +03:00
c554404d7f CHANGELOG.md: Add systemd units for indexer 2018-09-23 23:15:27 +03:00
90d7a452bd contrib: Add systemd units for indexer
An example systemd service unit for the indexer and an accompanying
timer unit.
2018-09-23 23:13:43 +03:00
431a1c9d64 CHANGELOG.md: Add unreleased changes 2018-09-23 23:04:01 +03:00
e1b9d1284f Rename project to DSpace Statistics API
At first I called it "CGSpace" because I was making it specifically
for our CGSpace DSpace repository, but the potential here is bigger
than that!
2018-09-23 23:02:21 +03:00
bac764a0a4 CHANGELOG.md: Move entries to version 0.0.4 2018-09-23 16:49:25 +03:00
1a650e57c0 CHANGELOG.md: Update unreleased features 2018-09-23 16:48:39 +03:00
2db5e02be9 Add indexer.py
Standalone script to ingest item views and downloads from Solr into
SQLite.
2018-09-23 16:47:48 +03:00
9e942736b1 app.py: Get item statistics from SQLite database
It is much more efficient to cache view and download statistics in
a database than to query Solr on demand (not to mention that it is
not possible to page easily with facets in Solr). I decided to use
SQLite because it is fast, native in Python 3, and doesn't require
any extra steps during provisioning (assuming permissions are ok).
2018-09-23 16:47:00 +03:00
ea85393b13 app.py: Use parameterized URI instead of query for /item
Falcon's get_param_as_int() is really nice in that it gets a query
parameter and does validation for you, but I really wanted to have
cleaner URIs for API routes so I am now using a route URI template
with a field converter. This is cleaner, but means that parameters
not matching the template will return HTTP 404.

See: https://falcon.readthedocs.io/en/stable/api/routing.html#field-converters
2018-09-23 16:23:33 +03:00
cbeb7c89a7 CHANGELOG.md: Add note about Solr connection refactor 2018-09-23 13:27:43 +03:00
b0d81a543c Refactor Solr components
This makes it so we only need to define and connect once and then we
can re-use the connection everywhere else.
2018-09-23 13:24:30 +03:00
84801a4ab5 Add vim modeline to all Python files
Uses four spaces for tab and shift widths, and turns on expansion of
tabs to spaces.
2018-09-23 11:33:26 +03:00
4e8621e3d9 README.md: Add TODO about API documentation 2018-09-23 09:52:36 +03:00
2c8430171d CHANGELOG.md: Add note about systemd unit file 2018-09-23 07:58:15 +03:00
fb60133713 Add example systemd unit for statistics API 2018-09-23 07:50:04 +03:00
9e01a80011 CHANGELOG.md: Move changes to version 0.0.3 2018-09-20 17:41:47 +03:00
a263996582 app.py: Fix Solr queries for item views
According to dspace-api's Constants.java, items are type 2 and they
use a unique ID field of `id` instead of `owningItem`. There is no
need to check the bundleName for item types.

Also, I decided to use the main Solr query for item IDs because the
filter query parameter (fq) stores results in the filterCache and
can be quite expensive with cores storing tens of millions of docu-
ments (we currently have 149 million docs!). It makes sense to use
the filter query parameter to reduce the result set returned by the
main Solr query.
2018-09-20 17:37:13 +03:00
ed9d25294e app.py: Use SolrClient's rows parameter
Instead of putting this in the raw query we can just use SolrClient's
native rows parameter.
2018-09-19 12:48:28 +03:00
5e165d2e88 CHANGELOG.md: Add note about using rows=0 in Solr queries 2018-09-19 01:50:14 +03:00
8e29fd8a43 app.py: Use rows=0 for Solr queries
There is no need to return any rows of the result because I am only
interested in the numFound.
2018-09-19 01:48:35 +03:00
24af83b03f CHANGELOG.md: Add note about simplified Solr query 2018-09-19 00:30:28 +03:00
a87aaba812 app.py: Simplify Solr query for bitstream downloads
This whole business with negative query ranges is confusing as hell
and I'll definitely forget it in the future. In DSpace's Solr term-
inology a "download" is a view to some bitstream that lives in the
ORIGINAL bundle. This is where bitstreams that are uploaded during
the item submission process go, versus generated thumbnails, etc.
2018-09-19 00:24:23 +03:00
57faec59c8 CHANGELOG.md: Add note about config refactor 2018-09-18 17:01:24 +03:00
06ab254017 Refactor configuration into separate module
There is a good example of this in the Project Weekend GitHub profile.

See: https://github.com/projectweekend/Falcon-PostgreSQL-API-Seed
2018-09-18 16:59:28 +03:00
5b5cab8b34 README.md: Update todo 2018-09-18 15:59:27 +03:00
40ce3c72a9 CHANGELOG.md: Update for version 0.0.2 2018-09-18 15:36:56 +03:00
ea2283355b Add CHANGELOG.md
See: https://keepachangelog.com/en/1.0.0/
2018-09-18 15:35:42 +03:00
4b4a959a1c Add ability to get Solr parameters from environment
You can use the SOLR_SERVER and SOLR_CORE variables to make deployment
via systemd, etc easier.
2018-09-18 15:34:25 +03:00
1e16beed30 README.md: Add todo list 2018-09-18 14:19:14 +03:00
182e13efca Add GPLv3 license 2018-09-18 14:16:07 +03:00
25 changed files with 78990 additions and 52 deletions

2
.flake8 Normal file
View File

@ -0,0 +1,2 @@
[flake8]
ignore = E501

4
.hound.yml Normal file
View File

@ -0,0 +1,4 @@
flake8:
enabled: true
config_file: .flake8
fail_on_violations: true

19
.travis.yml Normal file
View File

@ -0,0 +1,19 @@
language: python
python:
- "3.5"
- "3.6"
- "3.7-dev"
addons:
postgresql: "9.5"
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 pipenv --upgrade-strategy=only-if-needed"
- "pipenv install --dev"
script: pytest
# vim: ts=2 sw=2 et

151
CHANGELOG.md Normal file
View File

@ -0,0 +1,151 @@
# Changelog
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).
## [0.9.0] - 2019-01-22
### Updated
- pytest version 4.0.0
- Fix indexing of sharded statistics cores ([#10))
- Handle case of missing views/downloads gracefully
## [0.8.1] - 2018-11-14
### Changed
- README.md to recommend using vanilla Python virtual environments and pip instead of pipenv
- Regenerate pipenv environment to capture only direct dependencies
### Added
- `requirements-dev.txt` for installing development packages with pip
## [0.8.0] - 2018-11-11
### Changed
- Properly handle database connection errors
### Added
- API tests with pytest
## [0.7.0] - 2018-11-07
### Added
- Ability to configure PostgreSQL database port with DATABASE_PORT environment variable (defaults to 5432)
- Hound CI configuration to validate pull requests against PEP 8 code style with Flake8
- Configuration for [pipenv](https://pipenv.readthedocs.io/en/latest/)
### Changed
- Use a database management class with Python context management to automatically open/close connections and cursors
### Changed
- Validate code against PEP 8 style guide with Flake8
## [0.6.1] - 2018-10-31
### Added
- API documentation at root path (/)
## [0.6.0] - 2018-10-31
### Changed
- Refactor project structure (note breaking changes to API and indexing invocation, see contrib and README.md)
## [0.5.2] - 2018-10-28
### Changed
- Update library versions in requirements.txt
## [0.5.1] - 2018-10-24
### Changed
- Use Python's native json instead of ujson
## [0.5.0] - 2018-10-24
### Added
- Example nginx configuration to README.md
### Changed
- Don't initialize Solr connection in API
## [0.4.3] - 2018-10-17
### Changed
- Use pip install as script for Travis CI
### Improved
- Documentation for deployment and testing
## [0.4.2] - 2018-10-04
### Changed
- README.md introduction and requirements
- Use ujson instead of json
- Iterate directly on SQL cursor in `/items` route
### Fixed
- Logic error in SQL for item views
## [0.4.1] - 2018-09-26
### Changed
- Use `execute_values()` to batch insert records to PostgreSQL
## [0.4.0] - 2018-09-25
### Fixed
- Invalid OnCalendar syntax in dspace-statistics-indexer.timer
- Major logic error in indexer.py
## [0.3.2] - 2018-09-25
## Changed
- /item/id route now returns HTTP 404 if an item is not found
## [0.3.1] - 2018-09-25
### Changed
- Force SolrClient's kazoo dependency to version 2.5.0 to work with Python 3.7
- Add Python 3.7 to Travis CI configuration
## [0.3.0] - 2018-09-25
### Added
- requirements.txt for pip
- Travis CI build configuration for Python 3.5 and 3.6
- Documentation on using the API
### Changed
- The "all items" route from / to /items
## [0.2.1] - 2018-09-24
### Changed
- Environment settings in example systemd unit files
- Use psycopg2.extras.DictCursor for PostgreSQL connection
## [0.2.0] - 2018-09-24
### Changed
- Use PostgreSQL instead of SQLite because UPSERT support needs a very new libsqlite3 whereas it's already in PostgreSQL 9.5+
## [0.1.0] - 2018-09-24
### Changed
- Rename project to "DSpace Statistics API"
- Use read-only database connection in API
- Update systemd units for CGSpace→DSpace rename
- Use UPSERT to simplify database schema and Python logic
### Added
- Example systemd service and timer unit for indexer service
- Add top-level route to expose all item statistics
### Removed
- Ability to customize SOLR_CORE variable
## [0.0.4] - 2018-09-23
### Added
- Added example systemd unit file for API
- Added indexer.py to ingest views and downloads from Solr to a SQLite database
### Changed
- Refactor Solr configuration and connection
- /item route now expects id as part of the URI instead of a query parameter: /item/id
- View and download stats are now fetched from a SQLite database
## [0.0.3] - 2018-09-20
### Changed
- Refactor environment variables into config module
- Simplify Solr query for "downloads"
- Optimize Solr query by using rows=0
- Fix Solr queries for item views
## [0.0.2] - 2018-09-18
### Added
- Ability to get Solr parameters from environment (`SOLR_SERVER` and `SOLR_CORE`)
## [0.0.1] - 2018-09-18
- Initial release

674
LICENSE.txt Normal file
View File

@ -0,0 +1,674 @@
GNU GENERAL PUBLIC LICENSE
Version 3, 29 June 2007
Copyright (C) 2007 Free Software Foundation, Inc. <https://fsf.org/>
Everyone is permitted to copy and distribute verbatim copies
of this license document, but changing it is not allowed.
Preamble
The GNU General Public License is a free, copyleft license for
software and other kinds of works.
The licenses for most software and other practical works are designed
to take away your freedom to share and change the works. By contrast,
the GNU General Public License is intended to guarantee your freedom to
share and change all versions of a program--to make sure it remains free
software for all its users. We, the Free Software Foundation, use the
GNU General Public License for most of our software; it applies also to
any other work released this way by its authors. You can apply it to
your programs, too.
When we speak of free software, we are referring to freedom, not
price. Our General Public Licenses are designed to make sure that you
have the freedom to distribute copies of free software (and charge for
them if you wish), that you receive source code or can get it if you
want it, that you can change the software or use pieces of it in new
free programs, and that you know you can do these things.
To protect your rights, we need to prevent others from denying you
these rights or asking you to surrender the rights. Therefore, you have
certain responsibilities if you distribute copies of the software, or if
you modify it: responsibilities to respect the freedom of others.
For example, if you distribute copies of such a program, whether
gratis or for a fee, you must pass on to the recipients the same
freedoms that you received. You must make sure that they, too, receive
or can get the source code. And you must show them these terms so they
know their rights.
Developers that use the GNU GPL protect your rights with two steps:
(1) assert copyright on the software, and (2) offer you this License
giving you legal permission to copy, distribute and/or modify it.
For the developers' and authors' protection, the GPL clearly explains
that there is no warranty for this free software. For both users' and
authors' sake, the GPL requires that modified versions be marked as
changed, so that their problems will not be attributed erroneously to
authors of previous versions.
Some devices are designed to deny users access to install or run
modified versions of the software inside them, although the manufacturer
can do so. This is fundamentally incompatible with the aim of
protecting users' freedom to change the software. The systematic
pattern of such abuse occurs in the area of products for individuals to
use, which is precisely where it is most unacceptable. Therefore, we
have designed this version of the GPL to prohibit the practice for those
products. If such problems arise substantially in other domains, we
stand ready to extend this provision to those domains in future versions
of the GPL, as needed to protect the freedom of users.
Finally, every program is threatened constantly by software patents.
States should not allow patents to restrict development and use of
software on general-purpose computers, but in those that do, we wish to
avoid the special danger that patents applied to a free program could
make it effectively proprietary. To prevent this, the GPL assures that
patents cannot be used to render the program non-free.
The precise terms and conditions for copying, distribution and
modification follow.
TERMS AND CONDITIONS
0. Definitions.
"This License" refers to version 3 of the GNU General Public License.
"Copyright" also means copyright-like laws that apply to other kinds of
works, such as semiconductor masks.
"The Program" refers to any copyrightable work licensed under this
License. Each licensee is addressed as "you". "Licensees" and
"recipients" may be individuals or organizations.
To "modify" a work means to copy from or adapt all or part of the work
in a fashion requiring copyright permission, other than the making of an
exact copy. The resulting work is called a "modified version" of the
earlier work or a work "based on" the earlier work.
A "covered work" means either the unmodified Program or a work based
on the Program.
To "propagate" a work means to do anything with it that, without
permission, would make you directly or secondarily liable for
infringement under applicable copyright law, except executing it on a
computer or modifying a private copy. Propagation includes copying,
distribution (with or without modification), making available to the
public, and in some countries other activities as well.
To "convey" a work means any kind of propagation that enables other
parties to make or receive copies. Mere interaction with a user through
a computer network, with no transfer of a copy, is not conveying.
An interactive user interface displays "Appropriate Legal Notices"
to the extent that it includes a convenient and prominently visible
feature that (1) displays an appropriate copyright notice, and (2)
tells the user that there is no warranty for the work (except to the
extent that warranties are provided), that licensees may convey the
work under this License, and how to view a copy of this License. If
the interface presents a list of user commands or options, such as a
menu, a prominent item in the list meets this criterion.
1. Source Code.
The "source code" for a work means the preferred form of the work
for making modifications to it. "Object code" means any non-source
form of a work.
A "Standard Interface" means an interface that either is an official
standard defined by a recognized standards body, or, in the case of
interfaces specified for a particular programming language, one that
is widely used among developers working in that language.
The "System Libraries" of an executable work include anything, other
than the work as a whole, that (a) is included in the normal form of
packaging a Major Component, but which is not part of that Major
Component, and (b) serves only to enable use of the work with that
Major Component, or to implement a Standard Interface for which an
implementation is available to the public in source code form. A
"Major Component", in this context, means a major essential component
(kernel, window system, and so on) of the specific operating system
(if any) on which the executable work runs, or a compiler used to
produce the work, or an object code interpreter used to run it.
The "Corresponding Source" for a work in object code form means all
the source code needed to generate, install, and (for an executable
work) run the object code and to modify the work, including scripts to
control those activities. However, it does not include the work's
System Libraries, or general-purpose tools or generally available free
programs which are used unmodified in performing those activities but
which are not part of the work. For example, Corresponding Source
includes interface definition files associated with source files for
the work, and the source code for shared libraries and dynamically
linked subprograms that the work is specifically designed to require,
such as by intimate data communication or control flow between those
subprograms and other parts of the work.
The Corresponding Source need not include anything that users
can regenerate automatically from other parts of the Corresponding
Source.
The Corresponding Source for a work in source code form is that
same work.
2. Basic Permissions.
All rights granted under this License are granted for the term of
copyright on the Program, and are irrevocable provided the stated
conditions are met. This License explicitly affirms your unlimited
permission to run the unmodified Program. The output from running a
covered work is covered by this License only if the output, given its
content, constitutes a covered work. This License acknowledges your
rights of fair use or other equivalent, as provided by copyright law.
You may make, run and propagate covered works that you do not
convey, without conditions so long as your license otherwise remains
in force. You may convey covered works to others for the sole purpose
of having them make modifications exclusively for you, or provide you
with facilities for running those works, provided that you comply with
the terms of this License in conveying all material for which you do
not control copyright. Those thus making or running the covered works
for you must do so exclusively on your behalf, under your direction
and control, on terms that prohibit them from making any copies of
your copyrighted material outside their relationship with you.
Conveying under any other circumstances is permitted solely under
the conditions stated below. Sublicensing is not allowed; section 10
makes it unnecessary.
3. Protecting Users' Legal Rights From Anti-Circumvention Law.
No covered work shall be deemed part of an effective technological
measure under any applicable law fulfilling obligations under article
11 of the WIPO copyright treaty adopted on 20 December 1996, or
similar laws prohibiting or restricting circumvention of such
measures.
When you convey a covered work, you waive any legal power to forbid
circumvention of technological measures to the extent such circumvention
is effected by exercising rights under this License with respect to
the covered work, and you disclaim any intention to limit operation or
modification of the work as a means of enforcing, against the work's
users, your or third parties' legal rights to forbid circumvention of
technological measures.
4. Conveying Verbatim Copies.
You may convey verbatim copies of the Program's source code as you
receive it, in any medium, provided that you conspicuously and
appropriately publish on each copy an appropriate copyright notice;
keep intact all notices stating that this License and any
non-permissive terms added in accord with section 7 apply to the code;
keep intact all notices of the absence of any warranty; and give all
recipients a copy of this License along with the Program.
You may charge any price or no price for each copy that you convey,
and you may offer support or warranty protection for a fee.
5. Conveying Modified Source Versions.
You may convey a work based on the Program, or the modifications to
produce it from the Program, in the form of source code under the
terms of section 4, provided that you also meet all of these conditions:
a) The work must carry prominent notices stating that you modified
it, and giving a relevant date.
b) The work must carry prominent notices stating that it is
released under this License and any conditions added under section
7. This requirement modifies the requirement in section 4 to
"keep intact all notices".
c) You must license the entire work, as a whole, under this
License to anyone who comes into possession of a copy. This
License will therefore apply, along with any applicable section 7
additional terms, to the whole of the work, and all its parts,
regardless of how they are packaged. This License gives no
permission to license the work in any other way, but it does not
invalidate such permission if you have separately received it.
d) If the work has interactive user interfaces, each must display
Appropriate Legal Notices; however, if the Program has interactive
interfaces that do not display Appropriate Legal Notices, your
work need not make them do so.
A compilation of a covered work with other separate and independent
works, which are not by their nature extensions of the covered work,
and which are not combined with it such as to form a larger program,
in or on a volume of a storage or distribution medium, is called an
"aggregate" if the compilation and its resulting copyright are not
used to limit the access or legal rights of the compilation's users
beyond what the individual works permit. Inclusion of a covered work
in an aggregate does not cause this License to apply to the other
parts of the aggregate.
6. Conveying Non-Source Forms.
You may convey a covered work in object code form under the terms
of sections 4 and 5, provided that you also convey the
machine-readable Corresponding Source under the terms of this License,
in one of these ways:
a) Convey the object code in, or embodied in, a physical product
(including a physical distribution medium), accompanied by the
Corresponding Source fixed on a durable physical medium
customarily used for software interchange.
b) Convey the object code in, or embodied in, a physical product
(including a physical distribution medium), accompanied by a
written offer, valid for at least three years and valid for as
long as you offer spare parts or customer support for that product
model, to give anyone who possesses the object code either (1) a
copy of the Corresponding Source for all the software in the
product that is covered by this License, on a durable physical
medium customarily used for software interchange, for a price no
more than your reasonable cost of physically performing this
conveying of source, or (2) access to copy the
Corresponding Source from a network server at no charge.
c) Convey individual copies of the object code with a copy of the
written offer to provide the Corresponding Source. This
alternative is allowed only occasionally and noncommercially, and
only if you received the object code with such an offer, in accord
with subsection 6b.
d) Convey the object code by offering access from a designated
place (gratis or for a charge), and offer equivalent access to the
Corresponding Source in the same way through the same place at no
further charge. You need not require recipients to copy the
Corresponding Source along with the object code. If the place to
copy the object code is a network server, the Corresponding Source
may be on a different server (operated by you or a third party)
that supports equivalent copying facilities, provided you maintain
clear directions next to the object code saying where to find the
Corresponding Source. Regardless of what server hosts the
Corresponding Source, you remain obligated to ensure that it is
available for as long as needed to satisfy these requirements.
e) Convey the object code using peer-to-peer transmission, provided
you inform other peers where the object code and Corresponding
Source of the work are being offered to the general public at no
charge under subsection 6d.
A separable portion of the object code, whose source code is excluded
from the Corresponding Source as a System Library, need not be
included in conveying the object code work.
A "User Product" is either (1) a "consumer product", which means any
tangible personal property which is normally used for personal, family,
or household purposes, or (2) anything designed or sold for incorporation
into a dwelling. In determining whether a product is a consumer product,
doubtful cases shall be resolved in favor of coverage. For a particular
product received by a particular user, "normally used" refers to a
typical or common use of that class of product, regardless of the status
of the particular user or of the way in which the particular user
actually uses, or expects or is expected to use, the product. A product
is a consumer product regardless of whether the product has substantial
commercial, industrial or non-consumer uses, unless such uses represent
the only significant mode of use of the product.
"Installation Information" for a User Product means any methods,
procedures, authorization keys, or other information required to install
and execute modified versions of a covered work in that User Product from
a modified version of its Corresponding Source. The information must
suffice to ensure that the continued functioning of the modified object
code is in no case prevented or interfered with solely because
modification has been made.
If you convey an object code work under this section in, or with, or
specifically for use in, a User Product, and the conveying occurs as
part of a transaction in which the right of possession and use of the
User Product is transferred to the recipient in perpetuity or for a
fixed term (regardless of how the transaction is characterized), the
Corresponding Source conveyed under this section must be accompanied
by the Installation Information. But this requirement does not apply
if neither you nor any third party retains the ability to install
modified object code on the User Product (for example, the work has
been installed in ROM).
The requirement to provide Installation Information does not include a
requirement to continue to provide support service, warranty, or updates
for a work that has been modified or installed by the recipient, or for
the User Product in which it has been modified or installed. Access to a
network may be denied when the modification itself materially and
adversely affects the operation of the network or violates the rules and
protocols for communication across the network.
Corresponding Source conveyed, and Installation Information provided,
in accord with this section must be in a format that is publicly
documented (and with an implementation available to the public in
source code form), and must require no special password or key for
unpacking, reading or copying.
7. Additional Terms.
"Additional permissions" are terms that supplement the terms of this
License by making exceptions from one or more of its conditions.
Additional permissions that are applicable to the entire Program shall
be treated as though they were included in this License, to the extent
that they are valid under applicable law. If additional permissions
apply only to part of the Program, that part may be used separately
under those permissions, but the entire Program remains governed by
this License without regard to the additional permissions.
When you convey a copy of a covered work, you may at your option
remove any additional permissions from that copy, or from any part of
it. (Additional permissions may be written to require their own
removal in certain cases when you modify the work.) You may place
additional permissions on material, added by you to a covered work,
for which you have or can give appropriate copyright permission.
Notwithstanding any other provision of this License, for material you
add to a covered work, you may (if authorized by the copyright holders of
that material) supplement the terms of this License with terms:
a) Disclaiming warranty or limiting liability differently from the
terms of sections 15 and 16 of this License; or
b) Requiring preservation of specified reasonable legal notices or
author attributions in that material or in the Appropriate Legal
Notices displayed by works containing it; or
c) Prohibiting misrepresentation of the origin of that material, or
requiring that modified versions of such material be marked in
reasonable ways as different from the original version; or
d) Limiting the use for publicity purposes of names of licensors or
authors of the material; or
e) Declining to grant rights under trademark law for use of some
trade names, trademarks, or service marks; or
f) Requiring indemnification of licensors and authors of that
material by anyone who conveys the material (or modified versions of
it) with contractual assumptions of liability to the recipient, for
any liability that these contractual assumptions directly impose on
those licensors and authors.
All other non-permissive additional terms are considered "further
restrictions" within the meaning of section 10. If the Program as you
received it, or any part of it, contains a notice stating that it is
governed by this License along with a term that is a further
restriction, you may remove that term. If a license document contains
a further restriction but permits relicensing or conveying under this
License, you may add to a covered work material governed by the terms
of that license document, provided that the further restriction does
not survive such relicensing or conveying.
If you add terms to a covered work in accord with this section, you
must place, in the relevant source files, a statement of the
additional terms that apply to those files, or a notice indicating
where to find the applicable terms.
Additional terms, permissive or non-permissive, may be stated in the
form of a separately written license, or stated as exceptions;
the above requirements apply either way.
8. Termination.
You may not propagate or modify a covered work except as expressly
provided under this License. Any attempt otherwise to propagate or
modify it is void, and will automatically terminate your rights under
this License (including any patent licenses granted under the third
paragraph of section 11).
However, if you cease all violation of this License, then your
license from a particular copyright holder is reinstated (a)
provisionally, unless and until the copyright holder explicitly and
finally terminates your license, and (b) permanently, if the copyright
holder fails to notify you of the violation by some reasonable means
prior to 60 days after the cessation.
Moreover, your license from a particular copyright holder is
reinstated permanently if the copyright holder notifies you of the
violation by some reasonable means, this is the first time you have
received notice of violation of this License (for any work) from that
copyright holder, and you cure the violation prior to 30 days after
your receipt of the notice.
Termination of your rights under this section does not terminate the
licenses of parties who have received copies or rights from you under
this License. If your rights have been terminated and not permanently
reinstated, you do not qualify to receive new licenses for the same
material under section 10.
9. Acceptance Not Required for Having Copies.
You are not required to accept this License in order to receive or
run a copy of the Program. Ancillary propagation of a covered work
occurring solely as a consequence of using peer-to-peer transmission
to receive a copy likewise does not require acceptance. However,
nothing other than this License grants you permission to propagate or
modify any covered work. These actions infringe copyright if you do
not accept this License. Therefore, by modifying or propagating a
covered work, you indicate your acceptance of this License to do so.
10. Automatic Licensing of Downstream Recipients.
Each time you convey a covered work, the recipient automatically
receives a license from the original licensors, to run, modify and
propagate that work, subject to this License. You are not responsible
for enforcing compliance by third parties with this License.
An "entity transaction" is a transaction transferring control of an
organization, or substantially all assets of one, or subdividing an
organization, or merging organizations. If propagation of a covered
work results from an entity transaction, each party to that
transaction who receives a copy of the work also receives whatever
licenses to the work the party's predecessor in interest had or could
give under the previous paragraph, plus a right to possession of the
Corresponding Source of the work from the predecessor in interest, if
the predecessor has it or can get it with reasonable efforts.
You may not impose any further restrictions on the exercise of the
rights granted or affirmed under this License. For example, you may
not impose a license fee, royalty, or other charge for exercise of
rights granted under this License, and you may not initiate litigation
(including a cross-claim or counterclaim in a lawsuit) alleging that
any patent claim is infringed by making, using, selling, offering for
sale, or importing the Program or any portion of it.
11. Patents.
A "contributor" is a copyright holder who authorizes use under this
License of the Program or a work on which the Program is based. The
work thus licensed is called the contributor's "contributor version".
A contributor's "essential patent claims" are all patent claims
owned or controlled by the contributor, whether already acquired or
hereafter acquired, that would be infringed by some manner, permitted
by this License, of making, using, or selling its contributor version,
but do not include claims that would be infringed only as a
consequence of further modification of the contributor version. For
purposes of this definition, "control" includes the right to grant
patent sublicenses in a manner consistent with the requirements of
this License.
Each contributor grants you a non-exclusive, worldwide, royalty-free
patent license under the contributor's essential patent claims, to
make, use, sell, offer for sale, import and otherwise run, modify and
propagate the contents of its contributor version.
In the following three paragraphs, a "patent license" is any express
agreement or commitment, however denominated, not to enforce a patent
(such as an express permission to practice a patent or covenant not to
sue for patent infringement). To "grant" such a patent license to a
party means to make such an agreement or commitment not to enforce a
patent against the party.
If you convey a covered work, knowingly relying on a patent license,
and the Corresponding Source of the work is not available for anyone
to copy, free of charge and under the terms of this License, through a
publicly available network server or other readily accessible means,
then you must either (1) cause the Corresponding Source to be so
available, or (2) arrange to deprive yourself of the benefit of the
patent license for this particular work, or (3) arrange, in a manner
consistent with the requirements of this License, to extend the patent
license to downstream recipients. "Knowingly relying" means you have
actual knowledge that, but for the patent license, your conveying the
covered work in a country, or your recipient's use of the covered work
in a country, would infringe one or more identifiable patents in that
country that you have reason to believe are valid.
If, pursuant to or in connection with a single transaction or
arrangement, you convey, or propagate by procuring conveyance of, a
covered work, and grant a patent license to some of the parties
receiving the covered work authorizing them to use, propagate, modify
or convey a specific copy of the covered work, then the patent license
you grant is automatically extended to all recipients of the covered
work and works based on it.
A patent license is "discriminatory" if it does not include within
the scope of its coverage, prohibits the exercise of, or is
conditioned on the non-exercise of one or more of the rights that are
specifically granted under this License. You may not convey a covered
work if you are a party to an arrangement with a third party that is
in the business of distributing software, under which you make payment
to the third party based on the extent of your activity of conveying
the work, and under which the third party grants, to any of the
parties who would receive the covered work from you, a discriminatory
patent license (a) in connection with copies of the covered work
conveyed by you (or copies made from those copies), or (b) primarily
for and in connection with specific products or compilations that
contain the covered work, unless you entered into that arrangement,
or that patent license was granted, prior to 28 March 2007.
Nothing in this License shall be construed as excluding or limiting
any implied license or other defenses to infringement that may
otherwise be available to you under applicable patent law.
12. No Surrender of Others' Freedom.
If conditions are imposed on you (whether by court order, agreement or
otherwise) that contradict the conditions of this License, they do not
excuse you from the conditions of this License. If you cannot convey a
covered work so as to satisfy simultaneously your obligations under this
License and any other pertinent obligations, then as a consequence you may
not convey it at all. For example, if you agree to terms that obligate you
to collect a royalty for further conveying from those to whom you convey
the Program, the only way you could satisfy both those terms and this
License would be to refrain entirely from conveying the Program.
13. Use with the GNU Affero General Public License.
Notwithstanding any other provision of this License, you have
permission to link or combine any covered work with a work licensed
under version 3 of the GNU Affero General Public License into a single
combined work, and to convey the resulting work. The terms of this
License will continue to apply to the part which is the covered work,
but the special requirements of the GNU Affero General Public License,
section 13, concerning interaction through a network will apply to the
combination as such.
14. Revised Versions of this License.
The Free Software Foundation may publish revised and/or new versions of
the GNU General Public License from time to time. Such new versions will
be similar in spirit to the present version, but may differ in detail to
address new problems or concerns.
Each version is given a distinguishing version number. If the
Program specifies that a certain numbered version of the GNU General
Public License "or any later version" applies to it, you have the
option of following the terms and conditions either of that numbered
version or of any later version published by the Free Software
Foundation. If the Program does not specify a version number of the
GNU General Public License, you may choose any version ever published
by the Free Software Foundation.
If the Program specifies that a proxy can decide which future
versions of the GNU General Public License can be used, that proxy's
public statement of acceptance of a version permanently authorizes you
to choose that version for the Program.
Later license versions may give you additional or different
permissions. However, no additional obligations are imposed on any
author or copyright holder as a result of your choosing to follow a
later version.
15. Disclaimer of Warranty.
THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY
APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT
HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY
OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO,
THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM
IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF
ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
16. Limitation of Liability.
IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS
THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY
GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE
USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF
DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD
PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS),
EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF
SUCH DAMAGES.
17. Interpretation of Sections 15 and 16.
If the disclaimer of warranty and limitation of liability provided
above cannot be given local legal effect according to their terms,
reviewing courts shall apply local law that most closely approximates
an absolute waiver of all civil liability in connection with the
Program, unless a warranty or assumption of liability accompanies a
copy of the Program in return for a fee.
END OF TERMS AND CONDITIONS
How to Apply These Terms to Your New Programs
If you develop a new program, and you want it to be of the greatest
possible use to the public, the best way to achieve this is to make it
free software which everyone can redistribute and change under these terms.
To do so, attach the following notices to the program. It is safest
to attach them to the start of each source file to most effectively
state the exclusion of warranty; and each file should have at least
the "copyright" line and a pointer to where the full notice is found.
<one line to give the program's name and a brief idea of what it does.>
Copyright (C) <year> <name of author>
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 <https://www.gnu.org/licenses/>.
Also add information on how to contact you by electronic and paper mail.
If the program does terminal interaction, make it output a short
notice like this when it starts in an interactive mode:
<program> Copyright (C) <year> <name of author>
This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
This is free software, and you are welcome to redistribute it
under certain conditions; type `show c' for details.
The hypothetical commands `show w' and `show c' should show the appropriate
parts of the General Public License. Of course, your program's commands
might be different; for a GUI interface, you would use an "about box".
You should also get your employer (if you work as a programmer) or school,
if any, to sign a "copyright disclaimer" for the program, if necessary.
For more information on this, and how to apply and follow the GNU GPL, see
<https://www.gnu.org/licenses/>.
The GNU General Public License does not permit incorporating your program
into proprietary programs. If your program is a subroutine library, you
may consider it more useful to permit linking proprietary applications with
the library. If this is what you want to do, use the GNU Lesser General
Public License instead of this License. But first, please read
<https://www.gnu.org/licenses/why-not-lgpl.html>.

18
Pipfile Normal file
View File

@ -0,0 +1,18 @@
[[source]]
url = "https://pypi.org/simple"
verify_ssl = true
name = "pypi"
[packages]
gunicorn = "*"
falcon = "*"
"psycopg2-binary" = "*"
solrclient = {ref = "kazoo-2.5.0", git = "https://github.com/alanorth/SolrClient.git"}
[dev-packages]
ipython = "*"
"flake8" = "*"
pytest = "*"
[requires]
python_version = "3.7"

266
Pipfile.lock generated Normal file
View File

@ -0,0 +1,266 @@
{
"_meta": {
"hash": {
"sha256": "a846fdab4de5765a7e7fc19424a97a6196248e29f87285cf81fd76e8e9ae3e28"
},
"pipfile-spec": 6,
"requires": {
"python_version": "3.7"
},
"sources": [
{
"name": "pypi",
"url": "https://pypi.org/simple",
"verify_ssl": true
}
]
},
"default": {
"falcon": {
"hashes": [
"sha256:0a66b33458fab9c1e400a9be1a68056abda178eb02a8cb4b8f795e9df20b053b",
"sha256:3981f609c0358a9fcdb25b0e7fab3d9e23019356fb429c635ce4133135ae1bc4"
],
"index": "pypi",
"version": "==1.4.1"
},
"gunicorn": {
"hashes": [
"sha256:aa8e0b40b4157b36a5df5e599f45c9c76d6af43845ba3b3b0efe2c70473c2471",
"sha256:fa2662097c66f920f53f70621c6c58ca4a3c4d3434205e608e121b5b3b71f4f3"
],
"index": "pypi",
"version": "==19.9.0"
},
"psycopg2-binary": {
"hashes": [
"sha256:036bcb198a7cc4ce0fe43344f8c2c9a8155aefa411633f426c8c6ed58a6c0426",
"sha256:1d770fcc02cdf628aebac7404d56b28a7e9ebec8cfc0e63260bd54d6edfa16d4",
"sha256:1fdc6f369dcf229de6c873522d54336af598b9470ccd5300e2f58ee506f5ca13",
"sha256:21f9ddc0ff6e07f7d7b6b484eb9da2c03bc9931dd13e36796b111d631f7135a3",
"sha256:247873cda726f7956f745a3e03158b00de79c4abea8776dc2f611d5ba368d72d",
"sha256:3aa31c42f29f1da6f4fd41433ad15052d5ff045f2214002e027a321f79d64e2c",
"sha256:475f694f87dbc619010b26de7d0fc575a4accf503f2200885cc21f526bffe2ad",
"sha256:4b5e332a24bf6e2fda1f51ca2a57ae1083352293a08eeea1fa1112dc7dd542d1",
"sha256:570d521660574aca40be7b4d532dfb6f156aad7b16b5ed62d1534f64f1ef72d8",
"sha256:59072de7def0690dd13112d2bdb453e20570a97297070f876fbbb7cbc1c26b05",
"sha256:5f0b658989e918ef187f8a08db0420528126f2c7da182a7b9f8bf7f85144d4e4",
"sha256:649199c84a966917d86cdc2046e03d536763576c0b2a756059ae0b3a9656bc20",
"sha256:6645fc9b4705ae8fbf1ef7674f416f89ae1559deec810f6dd15197dfa52893da",
"sha256:6872dd54d4e398d781efe8fe2e2d7eafe4450d61b5c4898aced7610109a6df75",
"sha256:6ce34fbc251fc0d691c8d131250ba6f42fd2b28ef28558d528ba8c558cb28804",
"sha256:73920d167a0a4d1006f5f3b9a3efce6f0e5e883a99599d38206d43f27697df00",
"sha256:8a671732b87ae423e34b51139628123bc0306c2cb85c226e71b28d3d57d7e42a",
"sha256:8d517e8fda2efebca27c2018e14c90ed7dc3f04d7098b3da2912e62a1a5585fe",
"sha256:9475a008eb7279e20d400c76471843c321b46acacc7ee3de0b47233a1e3fa2cf",
"sha256:96947b8cd7b3148fb0e6549fcb31258a736595d6f2a599f8cd450e9a80a14781",
"sha256:abf229f24daa93f67ac53e2e17c8798a71a01711eb9fcdd029abba8637164338",
"sha256:b1ab012f276df584beb74f81acb63905762c25803ece647016613c3d6ad4e432",
"sha256:b22b33f6f0071fe57cb4e9158f353c88d41e739a3ec0d76f7b704539e7076427",
"sha256:b3b2d53274858e50ad2ffdd6d97ce1d014e1e530f82ec8b307edd5d4c921badf",
"sha256:bab26a729befc7b9fab9ded1bba9c51b785188b79f8a2796ba03e7e734269e2e",
"sha256:daa1a593629aa49f506eddc9d23dc7f89b35693b90e1fbcd4480182d1203ea90",
"sha256:dd111280ce40e89fd17b19c1269fd1b74a30fce9d44a550840e86edb33924eb8",
"sha256:e0b86084f1e2e78c451994410de756deba206884d6bed68d5a3d7f39ff5fea1d",
"sha256:eb86520753560a7e89639500e2a254bb6f683342af598088cb72c73edcad21e6",
"sha256:ff18c5c40a38d41811c23e2480615425c97ea81fd7e9118b8b899c512d97c737"
],
"index": "pypi",
"version": "==2.7.6.1"
},
"python-mimeparse": {
"hashes": [
"sha256:76e4b03d700a641fd7761d3cd4fdbbdcd787eade1ebfac43f877016328334f78",
"sha256:a295f03ff20341491bfe4717a39cd0a8cc9afad619ba44b77e86b0ab8a2b8282"
],
"version": "==1.6.0"
},
"six": {
"hashes": [
"sha256:3350809f0555b11f552448330d0b52d5f24c91a322ea4a15ef22629740f3761c",
"sha256:d16a0141ec1a18405cd4ce8b4613101da75da0e9a7aec5bdd4fa804d0e0eba73"
],
"version": "==1.12.0"
},
"solrclient": {
"git": "https://github.com/alanorth/SolrClient.git",
"ref": "c629e3475be37c82770b2be61748be7e29882648"
}
},
"develop": {
"atomicwrites": {
"hashes": [
"sha256:0312ad34fcad8fac3704d441f7b317e50af620823353ec657a53e981f92920c0",
"sha256:ec9ae8adaae229e4f8446952d204a3e4b5fdd2d099f9be3aaf556120135fb3ee"
],
"version": "==1.2.1"
},
"attrs": {
"hashes": [
"sha256:10cbf6e27dbce8c30807caf056c8eb50917e0eaafe86347671b57254006c3e69",
"sha256:ca4be454458f9dec299268d472aaa5a11f67a4ff70093396e1ceae9c76cf4bbb"
],
"version": "==18.2.0"
},
"backcall": {
"hashes": [
"sha256:38ecd85be2c1e78f77fd91700c76e14667dc21e2713b63876c0eb901196e01e4",
"sha256:bbbf4b1e5cd2bdb08f915895b51081c041bac22394fdfcfdfbe9f14b77c08bf2"
],
"version": "==0.1.0"
},
"decorator": {
"hashes": [
"sha256:2c51dff8ef3c447388fe5e4453d24a2bf128d3a4c32af3fabef1f01c6851ab82",
"sha256:c39efa13fbdeb4506c476c9b3babf6a718da943dab7811c206005a4a956c080c"
],
"version": "==4.3.0"
},
"flake8": {
"hashes": [
"sha256:6a35f5b8761f45c5513e3405f110a86bea57982c3b75b766ce7b65217abe1670",
"sha256:c01f8a3963b3571a8e6bd7a4063359aff90749e160778e03817cd9b71c9e07d2"
],
"index": "pypi",
"version": "==3.6.0"
},
"ipython": {
"hashes": [
"sha256:6a9496209b76463f1dec126ab928919aaf1f55b38beb9219af3fe202f6bbdd12",
"sha256:f69932b1e806b38a7818d9a1e918e5821b685715040b48e59c657b3c7961b742"
],
"index": "pypi",
"version": "==7.2.0"
},
"ipython-genutils": {
"hashes": [
"sha256:72dd37233799e619666c9f639a9da83c34013a73e8bbc79a7a6348d93c61fab8",
"sha256:eb2e116e75ecef9d4d228fdc66af54269afa26ab4463042e33785b887c628ba8"
],
"version": "==0.2.0"
},
"jedi": {
"hashes": [
"sha256:571702b5bd167911fe9036e5039ba67f820d6502832285cde8c881ab2b2149fd",
"sha256:c8481b5e59d34a5c7c42e98f6625e633f6ef59353abea6437472c7ec2093f191"
],
"version": "==0.13.2"
},
"mccabe": {
"hashes": [
"sha256:ab8a6258860da4b6677da4bd2fe5dc2c659cff31b3ee4f7f5d64e79735b80d42",
"sha256:dd8d182285a0fe56bace7f45b5e7d1a6ebcbf524e8f3bd87eb0f125271b8831f"
],
"version": "==0.6.1"
},
"more-itertools": {
"hashes": [
"sha256:38a936c0a6d98a38bcc2d03fdaaedaba9f412879461dd2ceff8d37564d6522e4",
"sha256:c0a5785b1109a6bd7fac76d6837fd1feca158e54e521ccd2ae8bfe393cc9d4fc",
"sha256:fe7a7cae1ccb57d33952113ff4fa1bc5f879963600ed74918f1236e212ee50b9"
],
"version": "==5.0.0"
},
"parso": {
"hashes": [
"sha256:35704a43a3c113cce4de228ddb39aab374b8004f4f2407d070b6a2ca784ce8a2",
"sha256:895c63e93b94ac1e1690f5fdd40b65f07c8171e3e53cbd7793b5b96c0e0a7f24"
],
"version": "==0.3.1"
},
"pexpect": {
"hashes": [
"sha256:2a8e88259839571d1251d278476f3eec5db26deb73a70be5ed5dc5435e418aba",
"sha256:3fbd41d4caf27fa4a377bfd16fef87271099463e6fa73e92a52f92dfee5d425b"
],
"markers": "sys_platform != 'win32'",
"version": "==4.6.0"
},
"pickleshare": {
"hashes": [
"sha256:87683d47965c1da65cdacaf31c8441d12b8044cdec9aca500cd78fc2c683afca",
"sha256:9649af414d74d4df115d5d718f82acb59c9d418196b7b4290ed47a12ce62df56"
],
"version": "==0.7.5"
},
"pluggy": {
"hashes": [
"sha256:8ddc32f03971bfdf900a81961a48ccf2fb677cf7715108f85295c67405798616",
"sha256:980710797ff6a041e9a73a5787804f848996ecaa6f8a1b1e08224a5894f2074a"
],
"version": "==0.8.1"
},
"prompt-toolkit": {
"hashes": [
"sha256:c1d6aff5252ab2ef391c2fe498ed8c088066f66bc64a8d5c095bbf795d9fec34",
"sha256:d4c47f79b635a0e70b84fdb97ebd9a274203706b1ee5ed44c10da62755cf3ec9",
"sha256:fd17048d8335c1e6d5ee403c3569953ba3eb8555d710bfc548faf0712666ea39"
],
"version": "==2.0.7"
},
"ptyprocess": {
"hashes": [
"sha256:923f299cc5ad920c68f2bc0bc98b75b9f838b93b599941a6b63ddbc2476394c0",
"sha256:d7cc528d76e76342423ca640335bd3633420dc1366f258cb31d05e865ef5ca1f"
],
"version": "==0.6.0"
},
"py": {
"hashes": [
"sha256:bf92637198836372b520efcba9e020c330123be8ce527e535d185ed4b6f45694",
"sha256:e76826342cefe3c3d5f7e8ee4316b80d1dd8a300781612ddbc765c17ba25a6c6"
],
"version": "==1.7.0"
},
"pycodestyle": {
"hashes": [
"sha256:cbc619d09254895b0d12c2c691e237b2e91e9b2ecf5e84c26b35400f93dcfb83",
"sha256:cbfca99bd594a10f674d0cd97a3d802a1fdef635d4361e1a2658de47ed261e3a"
],
"version": "==2.4.0"
},
"pyflakes": {
"hashes": [
"sha256:9a7662ec724d0120012f6e29d6248ae3727d821bba522a0e6b356eff19126a49",
"sha256:f661252913bc1dbe7fcfcbf0af0db3f42ab65aabd1a6ca68fe5d466bace94dae"
],
"version": "==2.0.0"
},
"pygments": {
"hashes": [
"sha256:5ffada19f6203563680669ee7f53b64dabbeb100eb51b61996085e99c03b284a",
"sha256:e8218dd399a61674745138520d0d4cf2621d7e032439341bc3f647bff125818d"
],
"version": "==2.3.1"
},
"pytest": {
"hashes": [
"sha256:41568ea7ecb4a68d7f63837cf65b92ce8d0105e43196ff2b26622995bb3dc4b2",
"sha256:c3c573a29d7c9547fb90217ece8a8843aa0c1328a797e200290dc3d0b4b823be"
],
"index": "pypi",
"version": "==4.1.1"
},
"six": {
"hashes": [
"sha256:3350809f0555b11f552448330d0b52d5f24c91a322ea4a15ef22629740f3761c",
"sha256:d16a0141ec1a18405cd4ce8b4613101da75da0e9a7aec5bdd4fa804d0e0eba73"
],
"version": "==1.12.0"
},
"traitlets": {
"hashes": [
"sha256:9c4bd2d267b7153df9152698efb1050a5d84982d3384a37b2c1f7723ba3e7835",
"sha256:c6cb5e6f57c5a9bdaa40fa71ce7b4af30298fbab9ece9815b5d995ab6217c7d9"
],
"version": "==4.3.2"
},
"wcwidth": {
"hashes": [
"sha256:3df37372226d6e63e1b1e1eda15c594bca98a22d33a23832a90998faa96bc65e",
"sha256:f4ebe71925af7b40a864553f761ed559b43544f8f71746c2d756c7fe788ade7c"
],
"version": "==0.1.7"
}
}
}

View File

@ -1,13 +1,94 @@
# CGSpace Statistics API
A quick and dirty REST API to expose Solr view and download statistics for items in a DSpace repository.
# DSpace Statistics API [![Build Status](https://travis-ci.org/ilri/dspace-statistics-api.svg?branch=master)](https://travis-ci.org/ilri/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+ [REST API](https://wiki.duraspace.org/display/DSDOC5x/REST+API), for example, only exposes information about communities, collections, item metadata, and bitstreams.
Written and tested in Python 3.6. SolrClient (0.2.1) does not currently run in Python 3.7.0.
This project contains an indexer and a [Falcon-based](https://falcon.readthedocs.io/) web application to make the statistics available via 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.duraspace.org/display/DSPACE/Solr).
## Requirements
- Python 3.5+
- PostgreSQL version 9.5+ (due to [`UPSERT` support](https://wiki.postgresql.org/wiki/UPSERT))
- DSpace with [Solr usage statistics enabled](https://wiki.duraspace.org/display/DSDOC5x/SOLR+Statistics) (tested with 5.x)
## Installation
Create a virtual environment and run it:
Create a Python virtual environment and install the dependencies:
$ virtualenv -p /usr/bin/python3.6 venv
$ . venv/bin/activate
$ pip install falcon gunicorn SolrClient
$ gunicorn app:api
$ python3 -m venv venv
$ source venv/bin/activate
$ pip install -r requirements.txt
## Running
Set up the environment variables for Solr and PostgreSQL:
$ export SOLR_SERVER=http://localhost:8080/solr
$ export DATABASE_NAME=dspacestatistics
$ export DATABASE_USER=dspacestatistics
$ export DATABASE_PASS=dspacestatistics
$ export DATABASE_HOST=localhost
Index the Solr statistics core to populate the PostgreSQL database:
$ python -m dspace_statistics_api.indexer
Run the REST API:
$ gunicorn dspace_statistics_api.app
Test to see if there are any statistics:
$ curl 'http://localhost:8000/items?limit=1'
## Testing
Install development packages using pip:
$ pip install -r requirements-dev.txt
Run tests:
$ pytest
## Deployment
There are example systemd service and timer units in the `contrib` directory. The API service listens on localhost by default so you will need to expose it publicly using a web server like nginx.
An example nginx configuration is:
```
server {
#...
location ~ /rest/statistics/?(.*) {
access_log /var/log/nginx/statistics.log;
proxy_pass http://statistics_api/$1$is_args$args;
}
}
upstream statistics_api {
server 127.0.0.1:5000;
}
```
This would expose the API at `/rest/statistics`.
## Using the API
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).
- GET `/item/id`return views and downloads for a single item (`id` must be a positive integer). Returns HTTP 404 if an item id is not found.
The item id is the *internal* id for an item. 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.
## Todo
- Better logging
- Version API
- Use JSON in PostgreSQL
- Make community and collection stats available
- Switch to [Python 3.6+ f-string syntax](https://realpython.com/python-f-strings/)
## License
This work is licensed under the [GPLv3](https://www.gnu.org/licenses/gpl-3.0.en.html).
The license allows you to use and modify the work for personal and commercial purposes, but if you distribute the work you must provide users with a means to access the source code for the version you are distributing. Read more about the [GPLv3 at TL;DR Legal](https://tldrlegal.com/license/gnu-general-public-license-v3-(gpl-3)).

44
app.py
View File

@ -1,44 +0,0 @@
# Tested with Python 3.6
# See DSpace Solr docs for tips about parameters
# https://wiki.duraspace.org/display/DSPACE/Solr
import falcon
from SolrClient import SolrClient
solr_server = 'http://localhost:3000/solr'
solr_core = 'statistics'
class ItemResource:
def on_get(self, req, resp):
"""Handles GET requests"""
# Return HTTPBadRequest if id parameter is not present and valid
item_id = req.get_param_as_int("id", required=True, min=0)
solr = SolrClient(solr_server)
# Get views
res = solr.query(solr_core, {
'q':'type:0',
'fq':'owningItem:{0} AND isBot:false AND statistics_type:view AND -bundleName:ORIGINAL'.format(item_id)
})
views = res.get_num_found()
# Get downloads
res = solr.query(solr_core, {
'q':'type:0',
'fq':'owningItem:{0} AND isBot:false AND statistics_type:view AND -(bundleName:[* TO *] -bundleName:ORIGINAL)'.format(item_id)
})
downloads = res.get_num_found()
statistics = {
'id': item_id,
'views': views,
'downloads': downloads
}
resp.media = statistics
api = falcon.API()
api.add_route('/item', ItemResource())

View File

@ -0,0 +1,20 @@
[Unit]
Description=DSpace Statistics API
After=network.target
[Service]
Environment=DATABASE_NAME=dspacestatistics
Environment=DATABASE_USER=dspacestatistics
Environment=DATABASE_PASS=dspacestatistics
Environment=DATABASE_HOST=localhost
User=nobody
Group=nogroup
WorkingDirectory=/var/lib/dspace-statistics-api
ExecStart=/var/lib/dspace-statistics-api/venv/bin/gunicorn \
--bind 127.0.0.1:5000 \
dspace_statistics_api.app
ExecReload=/bin/kill -s HUP $MAINPID
ExecStop=/bin/kill -s TERM $MAINPID
[Install]
WantedBy=multi-user.target

View File

@ -0,0 +1,17 @@
[Unit]
Description=DSpace Statistics Indexer
After=tomcat7.target
[Service]
Environment=SOLR_SERVER=http://localhost:8081/solr
Environment=DATABASE_NAME=dspacestatistics
Environment=DATABASE_USER=dspacestatistics
Environment=DATABASE_PASS=dspacestatistics
Environment=DATABASE_HOST=localhost
User=nobody
Group=nogroup
WorkingDirectory=/var/lib/dspace-statistics-api
ExecStart=/var/lib/dspace-statistics-api/venv/bin/python -m dspace_statistics_api.indexer
[Install]
WantedBy=multi-user.target

View File

@ -0,0 +1,12 @@
[Unit]
Description=DSpace Statistics Indexer
[Timer]
# twice a day, at 6AM and 6PM
OnCalendar=*-*-* 06,18:00:00
# Add a random delay of 03600 seconds
RandomizedDelaySec=3600
Persistent=true
[Install]
WantedBy=timers.target

View File

View File

@ -0,0 +1,81 @@
from .database import DatabaseManager
import falcon
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()
class AllItemsResource:
def on_get(self, req, resp):
"""Handles GET requests"""
# Return HTTPBadRequest if id parameter is not present and valid
limit = req.get_param_as_int("limit", min=0, max=100) or 100
page = req.get_param_as_int("page", min=0) or 0
offset = limit * page
with DatabaseManager() as db:
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 statistics, ordered by id, and use limit and offset to page through results
cursor.execute('SELECT id, views, downloads FROM items ORDER BY id ASC LIMIT {} OFFSET {}'.format(limit, offset))
# create a list to hold dicts of item stats
statistics = list()
# iterate over results and build statistics object
for item in cursor:
statistics.append({'id': item['id'], 'views': item['views'], 'downloads': item['downloads']})
message = {
'currentPage': page,
'totalPages': pages,
'limit': limit,
'statistics': statistics
}
resp.media = message
class ItemResource:
def on_get(self, req, resp, item_id):
"""Handles GET requests"""
with DatabaseManager() as db:
db.set_session(readonly=True)
with db.cursor() as cursor:
cursor = db.cursor()
cursor.execute('SELECT views, downloads FROM items WHERE id={}'.format(item_id))
if cursor.rowcount == 0:
raise falcon.HTTPNotFound(
title='Item not found',
description='The item with id "{}" was not found.'.format(item_id)
)
else:
results = cursor.fetchone()
statistics = {
'id': item_id,
'views': results['views'],
'downloads': results['downloads']
}
resp.media = statistics
api = application = falcon.API()
api.add_route('/', RootResource())
api.add_route('/items', AllItemsResource())
api.add_route('/item/{item_id:int}', ItemResource())
# vim: set sw=4 ts=4 expandtab:

View File

@ -0,0 +1,12 @@
import os
# Check if Solr connection information was provided in the environment
SOLR_SERVER = os.environ.get('SOLR_SERVER', 'http://localhost:8080/solr')
DATABASE_NAME = os.environ.get('DATABASE_NAME', 'dspacestatistics')
DATABASE_USER = os.environ.get('DATABASE_USER', 'dspacestatistics')
DATABASE_PASS = os.environ.get('DATABASE_PASS', 'dspacestatistics')
DATABASE_HOST = os.environ.get('DATABASE_HOST', 'localhost')
DATABASE_PORT = os.environ.get('DATABASE_PORT', '5432')
# vim: set sw=4 ts=4 expandtab:

View File

@ -0,0 +1,30 @@
from .config import DATABASE_NAME
from .config import DATABASE_USER
from .config import DATABASE_PASS
from .config import DATABASE_HOST
from .config import DATABASE_PORT
import falcon
import psycopg2
import psycopg2.extras
class DatabaseManager():
'''Manage database connection.'''
def __init__(self):
self._connection_uri = 'dbname={} user={} password={} host={} port={}'.format(DATABASE_NAME, DATABASE_USER, DATABASE_PASS, DATABASE_HOST, DATABASE_PORT)
def __enter__(self):
try:
self._connection = psycopg2.connect(self._connection_uri, cursor_factory=psycopg2.extras.DictCursor)
except psycopg2.OperationalError:
title = '500 Internal Server Error'
description = 'Could not connect to database'
raise falcon.HTTPInternalServerError(title, description)
return self._connection
def __exit__(self, exc_type, exc_value, exc_traceback):
self._connection.close()
# vim: set sw=4 ts=4 expandtab:

View File

@ -0,0 +1,20 @@
<!DOCTYPE html>
<html lang="en-US">
<head>
<meta charset="UTF-8">
<title>DSpace Statistics API</title>
</head>
<body>
<h1>DSpace Statistics API</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>GET <code>/item/id</code>return views and downloads for a single item (<code>id</code> must be a positive integer). Returns HTTP 404 if an item id is not found.</li>
</ul>
<p>The item id is the <em>internal</em> id for an item. You can get these from the standard DSpace REST API.</p>
<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.</code>
</body>
</html>

View File

@ -0,0 +1,236 @@
#
# indexer.py
#
# Copyright 2018 Alan Orth.
#
# This program is free software: you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program. If not, see <http://www.gnu.org/licenses/>.
#
# ---
#
# Connects to a DSpace Solr statistics core and ingests item views and downloads
# into a PostgreSQL database for use by other applications (like an API).
#
# This script is written for Python 3.5+ and requires several modules that you
# can install with pip (I recommend using a Python virtual environment):
#
# $ pip install SolrClient psycopg2-binary
#
# See: https://solrclient.readthedocs.io/en/latest/SolrClient.html
# See: https://wiki.duraspace.org/display/DSPACE/Solr
from .database import DatabaseManager
import json
import psycopg2.extras
import re
import requests
from .solr import solr_connection
# Enumerate the cores in Solr to determine if statistics have been sharded into
# yearly shards by DSpace's stats-util or not (for example: statistics-2018).
def get_statistics_shards():
# Initialize an empty list for statistics core years
statistics_core_years = []
# URL for Solr status to check active cores
solr_url = solr.host + '/admin/cores?action=STATUS&wt=json'
res = requests.get(solr_url)
if res.status_code == requests.codes.ok:
data = res.json()
# Iterate over active cores from Solr's STATUS response (cores are in
# the status array of this response).
for core in data['status']:
# Pattern to match, for example: statistics-2018
pattern = re.compile('^statistics-[0-9]{4}$')
if not pattern.match(core):
continue
# Append current core to list
statistics_core_years.append(core)
# Initialize a string to hold our shards (may end up being empty if the Solr
# core has not been processed by stats-util).
shards = str()
if len(statistics_core_years) > 0:
# Begin building a string of shards starting with the default one
shards = '{}/statistics'.format(solr.host)
for core in statistics_core_years:
# Create a comma-separated list of shards to pass to our Solr query
#
# See: https://wiki.apache.org/solr/DistributedSearch
shards += ',{}/{}'.format(solr.host, core)
# Return the string of shards, which may actually be empty. Solr doesn't
# seem to mind if the shards query parameter is empty and I haven't seen
# any negative performance impact so this should be fine.
return shards
def index_views():
# get total number of distinct facets for items with a minimum of 1 view,
# otherwise Solr returns all kinds of weird ids that are actually not in
# the database. Also, stats are expensive, but we need stats.calcdistinct
# so we can get the countDistinct summary.
#
# see: https://lucene.apache.org/solr/guide/6_6/the-stats-component.html
res = solr.query('statistics', {
'q': 'type:2',
'fq': 'isBot:false AND statistics_type:view',
'facet': True,
'facet.field': 'id',
'facet.mincount': 1,
'facet.limit': 1,
'facet.offset': 0,
'stats': True,
'stats.field': 'id',
'stats.calcdistinct': True,
'shards': shards
}, rows=0)
try:
# get total number of distinct facets (countDistinct)
results_totalNumFacets = json.loads(res.get_json())['stats']['stats_fields']['id']['countDistinct']
except TypeError:
print('No item views to index, 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_current_page = 0
with DatabaseManager() as db:
with db.cursor() as cursor:
# create an empty list to store values for batch insertion
data = []
while results_current_page <= results_num_pages:
print('Indexing item views (page {} of {})'.format(results_current_page, results_num_pages))
res = solr.query('statistics', {
'q': 'type:2',
'fq': 'isBot:false AND statistics_type:view',
'facet': True,
'facet.field': 'id',
'facet.mincount': 1,
'facet.limit': results_per_page,
'facet.offset': results_current_page * results_per_page,
'shards': shards
}, rows=0)
# SolrClient's get_facets() returns a dict of dicts
views = res.get_facets()
# in this case iterate over the 'id' dict and get the item ids and views
for item_id, item_views in views['id'].items():
data.append((item_id, item_views))
# do a batch insert of values from the current "page" of results
sql = 'INSERT INTO items(id, views) VALUES %s ON CONFLICT(id) DO UPDATE SET views=excluded.views'
psycopg2.extras.execute_values(cursor, sql, data, template='(%s, %s)')
db.commit()
# clear all items from the list so we can populate it with the next batch
data.clear()
results_current_page += 1
def index_downloads():
# get the total number of distinct facets for items with at least 1 download
res = solr.query('statistics', {
'q': 'type:0',
'fq': 'isBot:false AND statistics_type:view AND bundleName:ORIGINAL',
'facet': True,
'facet.field': 'owningItem',
'facet.mincount': 1,
'facet.limit': 1,
'facet.offset': 0,
'stats': True,
'stats.field': 'owningItem',
'stats.calcdistinct': True,
'shards': shards
}, rows=0)
try:
# get total number of distinct facets (countDistinct)
results_totalNumFacets = json.loads(res.get_json())['stats']['stats_fields']['owningItem']['countDistinct']
except TypeError:
print('No item downloads to index, 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_current_page = 0
with DatabaseManager() as db:
with db.cursor() as cursor:
# create an empty list to store values for batch insertion
data = []
while results_current_page <= results_num_pages:
print('Indexing item downloads (page {} of {})'.format(results_current_page, results_num_pages))
res = solr.query('statistics', {
'q': 'type:0',
'fq': 'isBot:false AND statistics_type:view AND bundleName:ORIGINAL',
'facet': True,
'facet.field': 'owningItem',
'facet.mincount': 1,
'facet.limit': results_per_page,
'facet.offset': results_current_page * results_per_page,
'shards': shards
}, rows=0)
# SolrClient's get_facets() returns a dict of dicts
downloads = res.get_facets()
# in this case iterate over the 'owningItem' dict and get the item ids and downloads
for item_id, item_downloads in downloads['owningItem'].items():
data.append((item_id, item_downloads))
# do a batch insert of values from the current "page" of results
sql = 'INSERT INTO items(id, downloads) VALUES %s ON CONFLICT(id) DO UPDATE SET downloads=excluded.downloads'
psycopg2.extras.execute_values(cursor, sql, data, template='(%s, %s)')
db.commit()
# clear all items from the list so we can populate it with the next batch
data.clear()
results_current_page += 1
solr = solr_connection()
with DatabaseManager() as db:
with db.cursor() as cursor:
# create table to store item views and downloads
cursor.execute('''CREATE TABLE IF NOT EXISTS items
(id INT PRIMARY KEY, views INT DEFAULT 0, downloads INT DEFAULT 0)''')
# commit the table creation before closing the database connection
db.commit()
shards = get_statistics_shards()
index_views()
index_downloads()
# vim: set sw=4 ts=4 expandtab:

View File

@ -0,0 +1,10 @@
from .config import SOLR_SERVER
from SolrClient import SolrClient
def solr_connection():
connection = SolrClient(SOLR_SERVER)
return connection
# vim: set sw=4 ts=4 expandtab:

4
pytest.ini Normal file
View File

@ -0,0 +1,4 @@
[pytest]
addopts= -rsxX -s -v --strict
filterwarnings =
error::UserWarning

25
requirements-dev.txt Normal file
View File

@ -0,0 +1,25 @@
-i https://pypi.org/simple
atomicwrites==1.2.1
attrs==18.2.0
backcall==0.1.0
decorator==4.3.0
flake8==3.6.0
ipython-genutils==0.2.0
ipython==7.2.0
jedi==0.13.2
mccabe==0.6.1
more-itertools==5.0.0
parso==0.3.1
pexpect==4.6.0 ; sys_platform != 'win32'
pickleshare==0.7.5
pluggy==0.8.1
prompt-toolkit==2.0.7
ptyprocess==0.6.0
py==1.7.0
pycodestyle==2.4.0
pyflakes==2.0.0
pygments==2.3.1
pytest==4.1.1
six==1.12.0
traitlets==4.3.2
wcwidth==0.1.7

7
requirements.txt Normal file
View File

@ -0,0 +1,7 @@
-i https://pypi.org/simple
falcon==1.4.1
git+https://github.com/alanorth/SolrClient.git@c629e3475be37c82770b2be61748be7e29882648#egg=solrclient
gunicorn==19.9.0
psycopg2-binary==2.7.6.1
python-mimeparse==1.6.0
six==1.12.0

0
tests/__init__.py Normal file
View File

77226
tests/dspacestatistics.sql Normal file

File diff suppressed because it is too large Load Diff

67
tests/test_api.py Normal file
View File

@ -0,0 +1,67 @@
from falcon import testing
import json
import pytest
from dspace_statistics_api.app import api
@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
def test_get_item(client):
'''Test requesting a single item.'''
response = client.simulate_get('/item/17')
response_doc = json.loads(response.text)
assert isinstance(response_doc['downloads'], int)
assert isinstance(response_doc['id'], int)
assert isinstance(response_doc['views'], int)
assert response.status_code == 200
def test_get_missing_item(client):
'''Test requesting a single non-existing item.'''
response = client.simulate_get('/item/1')
assert response.status_code == 404
def test_get_items(client):
'''Test requesting 100 items.'''
response = client.simulate_get('/items', 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_items_invalid_limit(client):
'''Test requesting 100 items with an invalid limit parameter.'''
response = client.simulate_get('/items', query_string='limit=101')
assert response.status_code == 400
def test_get_items_invalid_page(client):
'''Test requesting 100 items with an invalid page parameter.'''
response = client.simulate_get('/items', query_string='page=-1')
assert response.status_code == 400