temp commit

app/services/domains/publication_identifiers/application.py

@@ -21,7 +21,7 @@ from app.services.domains.publication_identifiers.types import (
 
 if TYPE_CHECKING:
     from app.services.domains.publications.pdf_queue import PdfQueueListItem
-    from app.services.domains.publications.types import PublicationListItem
+    from app.services.domains.publications.types import PublicationListItem, UnreadPublicationItem
 
 CONFIDENCE_HIGH = 0.98
 CONFIDENCE_MEDIUM = 0.9
@@ -117,9 +117,76 @@ async def sync_identifiers_for_publication_fields(
     await _upsert_publication_candidates(db_session, publication_id=int(publication.id), candidates=candidates)
 
 
+async def discover_and_sync_identifiers_for_publication(
+    db_session: AsyncSession,
+    *,
+    publication: Publication,
+    scholar_label: str,
+) -> None:
+    await sync_identifiers_for_publication_fields(db_session, publication=publication)
+    
+    existing_doi = await _existing_identifier_by_kind(
+        db_session,
+        publication_id=int(publication.id),
+        kind=IdentifierKind.DOI.value,
+    )
+    if existing_doi is not None:
+        return
+
+    from app.services.domains.crossref import application as crossref_service
+    from app.services.domains.publications.types import UnreadPublicationItem
+    
+    item = UnreadPublicationItem(
+        publication_id=int(publication.id),
+        scholar_profile_id=0,
+        scholar_label=scholar_label,
+        title=str(publication.title_raw or ""),
+        year=publication.year,
+        citation_count=publication.citation_count,
+        venue_text=publication.venue_text,
+        pub_url=publication.pub_url,
+        pdf_url=publication.pdf_url,
+    )
+    
+    discovered_doi = await crossref_service.discover_doi_for_publication(item=item)
+    if discovered_doi:
+        normalized_doi = normalize_doi(discovered_doi)
+        if normalized_doi:
+            candidate = _candidate(
+                IdentifierKind.DOI,
+                discovered_doi,
+                normalized_doi,
+                "crossref_api",
+                CONFIDENCE_MEDIUM,
+                None,
+            )
+            await _upsert_publication_candidate(db_session, publication_id=int(publication.id), candidate=candidate)
+
+    existing_arxiv = await _existing_identifier_by_kind(
+        db_session,
+        publication_id=int(publication.id),
+        kind=IdentifierKind.ARXIV.value,
+    )
+    if existing_arxiv is None:
+        from app.services.domains.arxiv import application as arxiv_service
+        discovered_arxiv = await arxiv_service.discover_arxiv_id_for_publication(item=item)
+        if discovered_arxiv:
+            normalized_arxiv = normalize_arxiv_id(discovered_arxiv)
+            if normalized_arxiv:
+                candidate = _candidate(
+                    IdentifierKind.ARXIV,
+                    discovered_arxiv,
+                    normalized_arxiv,
+                    "arxiv_api",
+                    CONFIDENCE_MEDIUM,
+                    None,
+                )
+                await _upsert_publication_candidate(db_session, publication_id=int(publication.id), candidate=candidate)
+
+
 def _publication_field_candidates(publication: Publication) -> list[IdentifierCandidate]:
     return _fallback_candidates_from_values(
-        doi=publication.doi,
+        doi=None,
         pub_url=publication.pub_url,
         pdf_url=publication.pdf_url,
     )
@@ -194,6 +261,21 @@ async def _existing_identifier(
     return result.scalar_one_or_none()
 
 
+async def _existing_identifier_by_kind(
+    db_session: AsyncSession,
+    *,
+    publication_id: int,
+    kind: str,
+) -> PublicationIdentifier | None:
+    result = await db_session.execute(
+        select(PublicationIdentifier).where(
+            PublicationIdentifier.publication_id == publication_id,
+            PublicationIdentifier.kind == kind,
+        ).order_by(PublicationIdentifier.confidence_score.desc()).limit(1)
+    )
+    return result.scalar_one_or_none()
+
+
 def _new_identifier_row(
     *,
     publication_id: int,
@@ -234,7 +316,7 @@ def _overlay_publication_item(
     item: PublicationListItem,
     display_identifier: DisplayIdentifier | None,
 ) -> PublicationListItem:
-    fallback = display_identifier or derive_display_identifier_from_values(doi=item.doi, pub_url=item.pub_url, pdf_url=item.pdf_url)
+    fallback = display_identifier or derive_display_identifier_from_values(doi=None, pub_url=item.pub_url, pdf_url=item.pdf_url)
     return replace(item, display_identifier=fallback)
 
 
@@ -253,7 +335,7 @@ def _overlay_queue_item(
     item: PdfQueueListItem,
     display_identifier: DisplayIdentifier | None,
 ) -> PdfQueueListItem:
-    fallback = display_identifier or derive_display_identifier_from_values(doi=item.doi, pdf_url=item.pdf_url)
+    fallback = display_identifier or derive_display_identifier_from_values(doi=None, pdf_url=item.pdf_url)
     return replace(item, display_identifier=fallback)