Initial release prep

app/services/ingestion/application.py

@@ -20,11 +20,11 @@ from app.db.models import (
     ScholarPublication,
 )
 from app.logging_utils import structured_log
-from app.services.domains.arxiv.errors import ArxivRateLimitError
-from app.services.domains.doi.normalize import first_doi_from_texts
-from app.services.domains.ingestion import queue as queue_service
-from app.services.domains.ingestion import safety as run_safety_service
-from app.services.domains.ingestion.constants import (
+from app.services.arxiv.errors import ArxivRateLimitError
+from app.services.doi.normalize import first_doi_from_texts
+from app.services.ingestion import queue as queue_service
+from app.services.ingestion import safety as run_safety_service
+from app.services.ingestion.constants import (
     FAILED_STATES,
     FAILURE_BUCKET_BLOCKED,
     FAILURE_BUCKET_INGESTION,
@@ -35,7 +35,7 @@ from app.services.domains.ingestion.constants import (
     RESUMABLE_PARTIAL_REASONS,
     RUN_LOCK_NAMESPACE,
 )
-from app.services.domains.ingestion.fingerprints import (
+from app.services.ingestion.fingerprints import (
     _build_body_excerpt,
     _dedupe_publication_candidates,
     _next_cstart_value,
@@ -45,7 +45,7 @@ from app.services.domains.ingestion.fingerprints import (
     canonical_title_for_dedup,
     normalize_title,
 )
-from app.services.domains.ingestion.types import (
+from app.services.ingestion.types import (
     PagedLoopState,
     PagedParseResult,
     RunAlertSummary,
@@ -56,17 +56,17 @@ from app.services.domains.ingestion.types import (
     RunProgress,
     ScholarProcessingOutcome,
 )
-from app.services.domains.publication_identifiers import application as identifier_service
-from app.services.domains.runs.events import run_events
-from app.services.domains.scholar.parser import (
+from app.services.publication_identifiers import application as identifier_service
+from app.services.runs.events import run_events
+from app.services.scholar.parser import (
     ParsedProfilePage,
     ParseState,
     PublicationCandidate,
     ScholarParserError,
     parse_profile_page,
 )
-from app.services.domains.scholar.source import FetchResult, ScholarSource
-from app.services.domains.settings import application as user_settings_service
+from app.services.scholar.source import FetchResult, ScholarSource
+from app.services.settings import application as user_settings_service
 from app.settings import settings
 
 logger = logging.getLogger(__name__)
@@ -2369,12 +2369,12 @@ class ScholarIngestionService:
         Stops immediately on budget exhaustion (429 with $0 remaining).
         Sleeps 60s and continues on transient rate limits.
         """
-        from app.services.domains.openalex.client import (
+        from app.services.openalex.client import (
             OpenAlexBudgetExhaustedError,
             OpenAlexClient,
             OpenAlexRateLimitError,
         )
-        from app.services.domains.openalex.matching import find_best_match
+        from app.services.openalex.matching import find_best_match
 
         run_result = await db_session.execute(select(CrawlRun.user_id).where(CrawlRun.id == run_id))
         user_id = run_result.scalar_one()
@@ -2480,7 +2480,7 @@ class ScholarIngestionService:
 
         await db_session.flush()
 
-        from app.services.domains.publications.dedup import sweep_identifier_duplicates
+        from app.services.publications.dedup import sweep_identifier_duplicates
 
         merge_count = await sweep_identifier_duplicates(db_session)
         if merge_count:
@@ -2579,8 +2579,8 @@ class ScholarIngestionService:
         if not publications:
             return publications
 
-        from app.services.domains.openalex.client import OpenAlexClient
-        from app.services.domains.openalex.matching import find_best_match
+        from app.services.openalex.client import OpenAlexClient
+        from app.services.openalex.matching import find_best_match
 
         client = OpenAlexClient(api_key=settings.openalex_api_key, mailto=settings.crossref_api_mailto)
 

app/services/ingestion/constants.py

@@ -2,7 +2,7 @@ from __future__ import annotations
 
 import re
 
-from app.services.domains.scholar.parser import ParseState
+from app.services.scholar.parser import ParseState
 
 TITLE_ALNUM_RE = re.compile(r"[^a-z0-9]+")
 WORD_RE = re.compile(r"[a-z0-9]+")

app/services/ingestion/fingerprints.py

@@ -7,14 +7,14 @@ import unicodedata
 from typing import Any
 from urllib.parse import urljoin
 
-from app.services.domains.ingestion.constants import (
+from app.services.ingestion.constants import (
     HTML_TAG_RE,
     INITIAL_PAGE_FINGERPRINT_MAX_PUBLICATIONS,
     SPACE_RE,
     TITLE_ALNUM_RE,
     WORD_RE,
 )
-from app.services.domains.scholar.parser import ParsedProfilePage, ParseState, PublicationCandidate
+from app.services.scholar.parser import ParsedProfilePage, ParseState, PublicationCandidate
 
 # Scholar-specific noise patterns stripped before canonical comparison.
 # Applied in order; each targets a different Scholar metadata injection style.

app/services/ingestion/scheduler.py

@@ -18,14 +18,14 @@ from app.db.models import (
 )
 from app.db.session import get_session_factory
 from app.logging_utils import structured_log
-from app.services.domains.ingestion import queue as queue_service
-from app.services.domains.ingestion.application import (
+from app.services.ingestion import queue as queue_service
+from app.services.ingestion.application import (
     RunAlreadyInProgressError,
     RunBlockedBySafetyPolicyError,
     ScholarIngestionService,
 )
-from app.services.domains.scholar.source import LiveScholarSource
-from app.services.domains.settings import application as user_settings_service
+from app.services.scholar.source import LiveScholarSource
+from app.services.settings import application as user_settings_service
 from app.settings import settings
 
 logger = logging.getLogger(__name__)
@@ -589,7 +589,7 @@ class SchedulerService:
         await self._finalize_queue_job_after_run(job, run_summary)
 
     async def _drain_pdf_queue(self) -> None:
-        from app.services.domains.publications.pdf_queue import drain_ready_jobs
+        from app.services.publications.pdf_queue import drain_ready_jobs
 
         session_factory = get_session_factory()
         async with session_factory() as session:

app/services/ingestion/types.py

@@ -4,8 +4,8 @@ from dataclasses import dataclass, field
 from typing import Any
 
 from app.db.models import RunStatus
-from app.services.domains.scholar.parser import ParsedProfilePage, PublicationCandidate
-from app.services.domains.scholar.source import FetchResult
+from app.services.scholar.parser import ParsedProfilePage, PublicationCandidate
+from app.services.scholar.source import FetchResult
 
 
 @dataclass(frozen=True)