michal.politowski
/
UrlsController
forked from lsmyrnaios/UrlsController
1
0
Fork 0
Code Pull Requests Activity

Update the "findAssignmentsQuery" to check the "attempt.error_class" field for the current pub_url, not the pub_id.

This commit is contained in:
Lampros Smyrnaios 2023-10-06 14:59:26 +03:00
parent ebf8896005
commit 0c79fdea35
1 changed files with 3 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
src/main/java/eu/openaire/urls_controller/services/UrlsServiceImpl.java
View File

@ -121,17 +121,16 @@ public class UrlsServiceImpl implements UrlsService {
" on p.id=pb.id\n" +
" left outer join (select count(at.original_url) as counts, at.original_url from " + DatabaseConnector.databaseName + ".attempt at group by at.original_url) as attempts\n" +
" on attempts.original_url=pu.url\n" +
" left anti join (\n" +
" select a.original_url from " + DatabaseConnector.databaseName + ".assignment a\n" +
" left anti join (select a.original_url from " + DatabaseConnector.databaseName + ".assignment a\n" +
" union all\n" +
" select pl.original_url from " + DatabaseConnector.databaseName + ".payload pl\n" + // Here we access the payload-VIEW which includes the three payload-tables.
" ) as existing\n" +
" ) as existing\n" +
" on existing.original_url=pu.url\n" +
" where d.allow_harvest=true\n" +
((excludedDatasourceIDsStringList != null) ? // If we have an exclusion-list, use it below.
(" and d.id not in " + excludedDatasourceIDsStringList + GenericUtils.endOfLine) : "") +
" and coalesce(attempts.counts, 0) <= " + maxAttemptsPerRecordAtomic.get() + GenericUtils.endOfLine +
" and not exists (select 1 from " + DatabaseConnector.databaseName + ".attempt a where a.id=p.id and a.error_class = 'noRetry' limit 1)\n" +
" and not exists (select 1 from " + DatabaseConnector.databaseName + ".attempt a where a.original_url=pu.url and a.error_class = 'noRetry' limit 1)\n" +
" and pu.url != '' and pu.url is not null\n" + // Some IDs have empty-string urls, there are no "null" urls, but keep the relevant check for future-proofing.
" and (p.year <= " + currentYear + " or p.year > " + (currentYear + 5) + ")\n" + // Exclude the pubs which will be published in the next 5 years. They don't provide full-texts now. (We don't exclude all future pubs, since, some have invalid year, like "9999").
") as distinct_results\n" +