alanorth/dspace-statistics-api
1
0
Fork 0
mirror of https://github.com/ilri/dspace-statistics-api.git synced 2024-11-17 03:47:09 +01:00
Code Releases Activity

dspace_statistics_api/indexer.py: Limit to UUIDs

Browse Source 
We need to make sure that the indexer only tries to index UUIDs, as
opposed to legacy IDs that may have been left over from a migration
from earlier DSpace versions. For example, "98110-unmigrated", "-1"
etc.

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

See: https://github.com/ilri/dspace-statistics-api/issues/12
This commit is contained in:
Alan Orth 2021-01-05 12:30:27 +02:00
parent d1c177e146
commit 49751b53f0
Signed by: alanorth
GPG Key ID: 0FB860CC9C45B1B9
1 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
dspace_statistics_api/indexer.py
View File

@ -47,7 +47,7 @@ def index_views(indexType: str, facetField: str):
# #
# see: https://lucene.apache.org/solr/guide/6_6/the-stats-component.html # see: https://lucene.apache.org/solr/guide/6_6/the-stats-component.html
solr_query_params = { solr_query_params = {
"q": "type:2", "q": f"type:2 AND {facetField}:/.{{36}}/",
"fq": "-isBot:true AND statistics_type:view", "fq": "-isBot:true AND statistics_type:view",
"fl": facetField, "fl": facetField,
"facet": "true", "facet": "true",
@ -94,7 +94,7 @@ def index_views(indexType: str, facetField: str):
) )
solr_query_params = { solr_query_params = {
"q": "type:2", "q": f"type:2 AND {facetField}:/.{{36}}/",
"fq": "-isBot:true AND statistics_type:view", "fq": "-isBot:true AND statistics_type:view",
"fl": facetField, "fl": facetField,
"facet": "true", "facet": "true",
@ -130,7 +130,7 @@ def index_views(indexType: str, facetField: str):
def index_downloads(indexType: str, facetField: str): def index_downloads(indexType: str, facetField: str):
# get the total number of distinct facets for items with at least 1 download # get the total number of distinct facets for items with at least 1 download
solr_query_params = { solr_query_params = {
"q": "type:0", "q": f"type:0 AND {facetField}:/.{{36}}/",
"fq": "-isBot:true AND statistics_type:view AND bundleName:ORIGINAL", "fq": "-isBot:true AND statistics_type:view AND bundleName:ORIGINAL",
"fl": facetField, "fl": facetField,
"facet": "true", "facet": "true",
@ -176,7 +176,7 @@ def index_downloads(indexType: str, facetField: str):
) )
solr_query_params = { solr_query_params = {
"q": "type:0", "q": f"type:0 AND {facetField}:/.{{36}}/",
"fq": "-isBot:true AND statistics_type:view AND bundleName:ORIGINAL", "fq": "-isBot:true AND statistics_type:view AND bundleName:ORIGINAL",
"fl": facetField, "fl": facetField,
"facet": "true", "facet": "true",