[ENG-9044] Add manage command to resync preprint dois v1 #11617
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,239 @@ | ||
| import logging | ||
|
|
||
| from django.contrib.contenttypes.models import ContentType | ||
| from django.core.management.base import BaseCommand | ||
| from django.db.models import Q | ||
|
|
||
| from framework.celery_tasks import app | ||
| from osf.models import Preprint, Identifier | ||
| from osf.models.base import VersionedGuidMixin | ||
| from osf.management.commands.sync_doi_metadata import async_request_identifier_update | ||
|
|
||
| logger = logging.getLogger(__name__) | ||
|
|
||
| def get_preprints_needing_v1_doi(provider_id=None): | ||
| content_type = ContentType.objects.get_for_model(Preprint) | ||
|
|
||
| already_versioned_ids = Identifier.objects.filter( | ||
| content_type=content_type, | ||
| category='doi', | ||
| deleted__isnull=True, | ||
| value__contains=VersionedGuidMixin.GUID_VERSION_DELIMITER, | ||
| ).values_list('object_id', flat=True) | ||
|
|
||
| public_query = Q(is_published=True, is_public=True, deleted__isnull=True) | ||
| withdrawn_query = Q(date_withdrawn__isnull=False, ever_public=True) | ||
|
|
||
| qs = Preprint.objects.filter( | ||
| versioned_guids__version=1, | ||
| ).filter( | ||
| public_query | withdrawn_query | ||
| ).exclude( | ||
| id__in=already_versioned_ids | ||
| ).exclude( | ||
| tags__name='qatest', | ||
| tags__system=True, | ||
| ).select_related('provider').distinct() | ||
|
|
||
| if provider_id: | ||
| qs = qs.filter(provider___id=provider_id) | ||
|
|
||
| return qs | ||
|
|
||
|
|
||
| def resync_preprint_dois_v1(dry_run=True, batch_size=1000, provider_id=None): | ||
| preprints_to_update = get_preprints_needing_v1_doi(provider_id=provider_id) | ||
|
|
||
| total = preprints_to_update.count() | ||
| logger.info( | ||
| f'{"[DRY RUN] " if dry_run else ""}' | ||
| f'{total} preprints need v1 DOI resync' | ||
| + (f' (provider={provider_id})' if provider_id else '') | ||
| ) | ||
|
|
||
| if batch_size: | ||
| preprints_iterable = preprints_to_update[:batch_size] | ||
| else: | ||
| preprints_iterable = preprints_to_update.iterator() | ||
|
|
||
| queued = 0 | ||
| skipped = 0 | ||
| errored = 0 | ||
| for preprint in preprints_iterable: | ||
| if not preprint.provider.doi_prefix: | ||
| logger.warning( | ||
| f'Skipping preprint {preprint._id}: ' | ||
| f'provider {preprint.provider._id} has no DOI prefix' | ||
| ) | ||
| skipped += 1 | ||
| continue | ||
|
|
||
| if dry_run: | ||
| logger.info(f'[DRY RUN] Would resync DOI for preprint {preprint._id}') | ||
| queued += 1 | ||
| continue | ||
|
|
||
| try: | ||
| async_request_identifier_update.apply_async(kwargs={'preprint_id': preprint._id}) | ||
| logger.info(f'Queued DOI resync for preprint {preprint._id}') | ||
| queued += 1 | ||
| except Exception: | ||
| logger.exception(f'Failed to queue DOI resync for preprint {preprint._id}') | ||
| errored += 1 | ||
|
|
||
| logger.info( | ||
| f'{"[DRY RUN] " if dry_run else ""}' | ||
| f'Done: {queued} preprints queued, {skipped} skipped (no DOI prefix), {errored} errored' | ||
| ) | ||
| if not dry_run and batch_size: | ||
| logger.info( | ||
| f'Estimated remaining after this batch: ~{max(0, total - queued - skipped - errored)}. ' | ||
| f'Re-run this command until 0 preprints remain.' | ||
| ) | ||
|
|
||
|
|
||
| def get_preprints_needing_unversioned_doi(provider_id=None): | ||
| content_type = ContentType.objects.get_for_model(Preprint) | ||
|
|
||
| already_has_unversioned = Identifier.objects.filter( | ||
| content_type=content_type, | ||
| category='doi_unversioned', | ||
| deleted__isnull=True, | ||
| ).values_list('object_id', flat=True) | ||
|
|
||
| has_versioned_doi = Identifier.objects.filter( | ||
| content_type=content_type, | ||
| category='doi', | ||
| deleted__isnull=True, | ||
| value__contains=VersionedGuidMixin.GUID_VERSION_DELIMITER, | ||
| ).values_list('object_id', flat=True) | ||
|
|
||
| public_query = Q(is_published=True, is_public=True, deleted__isnull=True) | ||
| withdrawn_query = Q(date_withdrawn__isnull=False, ever_public=True) | ||
|
|
||
| qs = Preprint.objects.filter( | ||
| versioned_guids__version=1, | ||
| id__in=has_versioned_doi, | ||
| ).filter( | ||
| public_query | withdrawn_query | ||
| ).exclude( | ||
| id__in=already_has_unversioned | ||
| ).exclude( | ||
| tags__name='qatest', | ||
| tags__system=True, | ||
| ).select_related('provider').distinct() | ||
|
|
||
| if provider_id: | ||
| qs = qs.filter(provider___id=provider_id) | ||
|
|
||
| return qs | ||
|
|
||
|
|
||
| def register_missing_unversioned_dois(dry_run=True, batch_size=1000, provider_id=None): | ||
| preprints_to_update = get_preprints_needing_unversioned_doi(provider_id=provider_id) | ||
|
|
||
| total = preprints_to_update.count() | ||
| logger.info( | ||
| f'{"[DRY RUN] " if dry_run else ""}' | ||
| f'{total} preprints need unversioned DOI registration' | ||
| + (f' (provider={provider_id})' if provider_id else '') | ||
| ) | ||
|
|
||
| if batch_size: | ||
| preprints_iterable = preprints_to_update[:batch_size] | ||
| else: | ||
| preprints_iterable = preprints_to_update.iterator() | ||
|
|
||
| queued = 0 | ||
| skipped = 0 | ||
| errored = 0 | ||
| for preprint in preprints_iterable: | ||
| if not preprint.provider.doi_prefix: | ||
| logger.warning( | ||
| f'Skipping preprint {preprint._id}: ' | ||
| f'provider {preprint.provider._id} has no DOI prefix' | ||
| ) | ||
| skipped += 1 | ||
| continue | ||
|
|
||
| if dry_run: | ||
| logger.info(f'[DRY RUN] Would register unversioned DOI for preprint {preprint._id}') | ||
| queued += 1 | ||
| continue | ||
|
|
||
| try: | ||
| async_request_identifier_update.apply_async(kwargs={'preprint_id': preprint._id}) | ||
| logger.info(f'Queued unversioned DOI registration for preprint {preprint._id}') | ||
| queued += 1 | ||
| except Exception: | ||
| logger.exception(f'Failed to queue unversioned DOI registration for preprint {preprint._id}') | ||
| errored += 1 | ||
|
|
||
| logger.info( | ||
| f'{"[DRY RUN] " if dry_run else ""}' | ||
| f'Unversioned DOI pass done: {queued} queued, {skipped} skipped, {errored} errored' | ||
| ) | ||
| if not dry_run and batch_size: | ||
| logger.info( | ||
| f'Estimated unversioned remaining after this batch: ~{max(0, total - queued - skipped - errored)}. ' | ||
| f'Re-run until 0 preprints remain.' | ||
| ) | ||
|
|
||
|
|
||
| @app.task(name='osf.management.commands.resync_preprint_dois_v1', max_retries=0) | ||
| def resync_preprint_dois_v1_task(batch_size=1000, dry_run=False, provider_id=None): | ||
| resync_preprint_dois_v1( | ||
| dry_run=dry_run, | ||
| batch_size=batch_size, | ||
| provider_id=provider_id, | ||
| ) | ||
| register_missing_unversioned_dois( | ||
| dry_run=dry_run, | ||
| batch_size=batch_size, | ||
| provider_id=provider_id, | ||
| ) | ||
|
|
||
|
|
||
| class Command(BaseCommand): | ||
| help = ( | ||
| 'Resync DOIs for version-1 preprints that are missing the versioned DOI suffix (_v1). ' | ||
| 'Processes preprints in batches and queues Crossref deposit tasks. ' | ||
| 'IMPORTANT: This command must be run repeatedly until it reports 0 preprints remaining, ' | ||
| 'as each run only processes a single batch. ' | ||
| 'Check remaining count with --dry_run before and after each run.' | ||
| ) | ||
|
|
||
| def add_arguments(self, parser): | ||
| super().add_arguments(parser) | ||
| parser.add_argument( | ||
| '--dry_run', | ||
| action='store_true', | ||
| dest='dry_run', | ||
| help='Log what would be done without submitting to Crossref.', | ||
| ) | ||
| parser.add_argument( | ||
| '--batch_size', | ||
| '-b', | ||
| type=int, | ||
| default=1000, | ||
| help=( | ||
| 'Maximum number of preprints to process per run (default: 1000). ' | ||
| 'The command processes the first N eligible preprints and exits; ' | ||
| 're-run the command to continue with the next batch.' | ||
| ), | ||
|
Comment on lines
+219
to
+223
Collaborator
There was a problem hiding this comment. Oh, I see. This is an OK alternative to the loop I suggested. Just need to make sure whoever runs this command is aware of the fact that they need to keep running this command until none exists. Cc @adlius for your input on this. |
||
| ) | ||
| parser.add_argument( | ||
| '--provider', | ||
| '-p', | ||
| type=str, | ||
| default=None, | ||
| dest='provider_id', | ||
| help='Restrict to a single provider _id (e.g. socarxiv).', | ||
| ) | ||
|
|
||
| def handle(self, *args, **options): | ||
| resync_preprint_dois_v1( | ||
| dry_run=options['dry_run'], | ||
| batch_size=options['batch_size'], | ||
| provider_id=options['provider_id'], | ||
| ) | ||
Oops, something went wrong.
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Uh oh!
There was an error while loading. Please reload this page.