CHANGELOG.md: Move unrelease changes to 0.9.0

CHANGELOG.md: Add note about catching errors
dspace_statistics_api/indexer.py: Catch case of no views/downloads
2025-05-10 07:06:01 +02:00 · 2019-01-22 09:02:29 +02:00 · 2019-01-22 09:01:54 +02:00 · 2019-01-22 09:00:22 +02:00 · 2019-01-22 08:41:39 +02:00 · 2019-01-22 08:41:31 +02:00
6 changed files with 111 additions and 41 deletions
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@ -4,6 +4,12 @@ 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
--- a/Pipfile.lock
+++ b/Pipfile.lock
@ -77,10 +77,10 @@
        },
        "six": {
            "hashes": [
-                "sha256:70e8a77beed4562e7f14fe23a786b54f6296e34344c23bc42f07b15018ff98e9",
-                "sha256:832dc0e10feb1aa2c68dcc57dbb658f1c7e65b9b61af69048abc87a2db00a0eb"
+                "sha256:3350809f0555b11f552448330d0b52d5f24c91a322ea4a15ef22629740f3761c",
+                "sha256:d16a0141ec1a18405cd4ce8b4613101da75da0e9a7aec5bdd4fa804d0e0eba73"
            ],
-            "version": "==1.11.0"
+            "version": "==1.12.0"
        },
        "solrclient": {
            "git": "https://github.com/alanorth/SolrClient.git",
@ -126,11 +126,11 @@
        },
        "ipython": {
            "hashes": [
-                "sha256:a5781d6934a3341a1f9acb4ea5acdc7ea0a0855e689dbe755d070ca51e995435",
-                "sha256:b10a7ddd03657c761fc503495bc36471c8158e3fc948573fb9fe82a7029d8efd"
+                "sha256:6a9496209b76463f1dec126ab928919aaf1f55b38beb9219af3fe202f6bbdd12",
+                "sha256:f69932b1e806b38a7818d9a1e918e5821b685715040b48e59c657b3c7961b742"
            ],
            "index": "pypi",
-            "version": "==7.1.1"
+            "version": "==7.2.0"
        },
        "ipython-genutils": {
            "hashes": [
@ -141,10 +141,10 @@
        },
        "jedi": {
            "hashes": [
-                "sha256:0191c447165f798e6a730285f2eee783fff81b0d3df261945ecb80983b5c3ca7",
-                "sha256:b7493f73a2febe0dc33d51c99b474547f7f6c0b2c8fb2b21f453eef204c12148"
+                "sha256:571702b5bd167911fe9036e5039ba67f820d6502832285cde8c881ab2b2149fd",
+                "sha256:c8481b5e59d34a5c7c42e98f6625e633f6ef59353abea6437472c7ec2093f191"
            ],
-            "version": "==0.13.1"
+            "version": "==0.13.2"
        },
        "mccabe": {
            "hashes": [
@ -155,11 +155,11 @@
        },
        "more-itertools": {
            "hashes": [
-                "sha256:c187a73da93e7a8acc0001572aebc7e3c69daf7bf6881a2cea10650bd4420092",
-                "sha256:c476b5d3a34e12d40130bc2f935028b5f636df8f372dc2c1c01dc19681b2039e",
-                "sha256:fcbfeaea0be121980e15bc97b3817b5202ca73d0eae185b4550cbfce2a3ebb3d"
+                "sha256:38a936c0a6d98a38bcc2d03fdaaedaba9f412879461dd2ceff8d37564d6522e4",
+                "sha256:c0a5785b1109a6bd7fac76d6837fd1feca158e54e521ccd2ae8bfe393cc9d4fc",
+                "sha256:fe7a7cae1ccb57d33952113ff4fa1bc5f879963600ed74918f1236e212ee50b9"
            ],
-            "version": "==4.3.0"
+            "version": "==5.0.0"
        },
        "parso": {
            "hashes": [
@ -185,10 +185,10 @@
        },
        "pluggy": {
            "hashes": [
-                "sha256:447ba94990e8014ee25ec853339faf7b0fc8050cdc3289d4d71f7f410fb90095",
-                "sha256:bde19360a8ec4dfd8a20dcb811780a30998101f078fc7ded6162f0076f50508f"
+                "sha256:8ddc32f03971bfdf900a81961a48ccf2fb677cf7715108f85295c67405798616",
+                "sha256:980710797ff6a041e9a73a5787804f848996ecaa6f8a1b1e08224a5894f2074a"
            ],
-            "version": "==0.8.0"
+            "version": "==0.8.1"
        },
        "prompt-toolkit": {
            "hashes": [
@ -228,25 +228,25 @@
        },
        "pygments": {
            "hashes": [
-                "sha256:78f3f434bcc5d6ee09020f92ba487f95ba50f1e3ef83ae96b9d5ffa1bab25c5d",
-                "sha256:dbae1046def0efb574852fab9e90209b23f556367b5a320c0bcb871c77c3e8cc"
+                "sha256:5ffada19f6203563680669ee7f53b64dabbeb100eb51b61996085e99c03b284a",
+                "sha256:e8218dd399a61674745138520d0d4cf2621d7e032439341bc3f647bff125818d"
            ],
-            "version": "==2.2.0"
+            "version": "==2.3.1"
        },
        "pytest": {
            "hashes": [
-                "sha256:3f193df1cfe1d1609d4c583838bea3d532b18d6160fd3f55c9447fdca30848ec",
-                "sha256:e246cf173c01169b9617fc07264b7b1316e78d7a650055235d6d897bc80d9660"
+                "sha256:41568ea7ecb4a68d7f63837cf65b92ce8d0105e43196ff2b26622995bb3dc4b2",
+                "sha256:c3c573a29d7c9547fb90217ece8a8843aa0c1328a797e200290dc3d0b4b823be"
            ],
            "index": "pypi",
-            "version": "==3.10.1"
+            "version": "==4.1.1"
        },
        "six": {
            "hashes": [
-                "sha256:70e8a77beed4562e7f14fe23a786b54f6296e34344c23bc42f07b15018ff98e9",
-                "sha256:832dc0e10feb1aa2c68dcc57dbb658f1c7e65b9b61af69048abc87a2db00a0eb"
+                "sha256:3350809f0555b11f552448330d0b52d5f24c91a322ea4a15ef22629740f3761c",
+                "sha256:d16a0141ec1a18405cd4ce8b4613101da75da0e9a7aec5bdd4fa804d0e0eba73"
            ],
-            "version": "==1.11.0"
+            "version": "==1.12.0"
        },
        "traitlets": {
            "hashes": [
--- a/README.md
+++ b/README.md
@ -85,6 +85,7 @@ The item id is the *internal* id for an item. You can get these from the standar
 - 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
--- a/dspace_statistics_api/indexer.py
+++ b/dspace_statistics_api/indexer.py
@ -32,9 +32,56 @@
 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
@ -52,11 +99,17 @@ def index_views():
        'facet.offset': 0,
        'stats': True,
        'stats.field': 'id',
-        'stats.calcdistinct': True
+        'stats.calcdistinct': True,
+        'shards': shards
    }, rows=0)

-    # get total number of distinct facets (countDistinct)
-    results_totalNumFacets = json.loads(res.get_json())['stats']['stats_fields']['id']['countDistinct']
+    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
@ -78,7 +131,8 @@ def index_views():
                    'facet.field': 'id',
                    'facet.mincount': 1,
                    'facet.limit': results_per_page,
-                    'facet.offset': results_current_page * results_per_page
+                    'facet.offset': results_current_page * results_per_page,
+                    'shards': shards
                }, rows=0)

                # SolrClient's get_facets() returns a dict of dicts
@ -110,11 +164,17 @@ def index_downloads():
        'facet.offset': 0,
        'stats': True,
        'stats.field': 'owningItem',
-        'stats.calcdistinct': True
+        'stats.calcdistinct': True,
+        'shards': shards
    }, rows=0)

-    # get total number of distinct facets (countDistinct)
-    results_totalNumFacets = json.loads(res.get_json())['stats']['stats_fields']['owningItem']['countDistinct']
+    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
@ -136,7 +196,8 @@ def index_downloads():
                    'facet.field': 'owningItem',
                    'facet.mincount': 1,
                    'facet.limit': results_per_page,
-                    'facet.offset': results_current_page * results_per_page
+                    'facet.offset': results_current_page * results_per_page,
+                    'shards': shards
                }, rows=0)

                # SolrClient's get_facets() returns a dict of dicts
@ -167,6 +228,8 @@ with DatabaseManager() as db:
    # commit the table creation before closing the database connection
    db.commit()

+shards = get_statistics_shards()
+
 index_views()
 index_downloads()

--- a/requirements-dev.txt
+++ b/requirements-dev.txt
@ -5,21 +5,21 @@ backcall==0.1.0
 decorator==4.3.0
 flake8==3.6.0
 ipython-genutils==0.2.0
-ipython==7.1.1
-jedi==0.13.1
+ipython==7.2.0
+jedi==0.13.2
 mccabe==0.6.1
-more-itertools==4.3.0
+more-itertools==5.0.0
 parso==0.3.1
 pexpect==4.6.0 ; sys_platform != 'win32'
 pickleshare==0.7.5
-pluggy==0.8.0
+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==2.2.0
-pytest==3.10.1
-six==1.11.0
+pygments==2.3.1
+pytest==4.1.1
+six==1.12.0
 traitlets==4.3.2
 wcwidth==0.1.7
--- a/requirements.txt
+++ b/requirements.txt
@ -4,4 +4,4 @@ git+https://github.com/alanorth/SolrClient.git@c629e3475be37c82770b2be61748be7e2
 gunicorn==19.9.0
 psycopg2-binary==2.7.6.1
 python-mimeparse==1.6.0
-six==1.11.0
+six==1.12.0
Author	SHA1	Message	Date
Alan Orth	914ec52fbb	CHANGELOG.md: Move unrelease changes to 0.9.0	2019-01-22 09:02:29 +02:00
Alan Orth	5524066656	CHANGELOG.md: Add note about catching errors	2019-01-22 09:01:54 +02:00
Alan Orth	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
Alan Orth	bd28353cda	README.md: Remove TODO for fixing querying of shards	2019-01-22 08:41:39 +02:00
Alan Orth	e23d66c2a2	CHANGELOG.md: Add note about fixing querying of sharded cores	2019-01-22 08:41:31 +02:00
Alan Orth	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
Alan Orth	934fa9db9b	README.md: Add TODO about sharded statistics cores	2019-01-21 12:55:43 +02:00
Alan Orth	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
Alan Orth	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
Alan Orth	c95a98dd2d	Pipfile.lock: update dependencies Updated with `pipenv update`.	2019-01-15 10:22:46 +02:00
Alan Orth	3f70f94a10	Pipfile.lock: Run pipenv update	2018-11-26 11:53:37 +02:00
Alan Orth	9b8ad9defd	Merge pull request #9 from ilri/pipenv-update Pipenv update	2018-11-19 23:50:44 +02:00
Alan Orth	d69ab20220	CHANGELOG.md: pytest version 4.0.0	2018-11-19 23:46:03 +02:00
Alan Orth	378f56ddc2	Pipfile.lock: Run pipenv update	2018-11-19 23:34:34 +02:00