harden domain architecture and add lazy Crossref+Unpaywall PDF enrichment with publications workspace refactor

tests/unit/test_crossref_lookup.py

@@ -0,0 +1,75 @@
+from __future__ import annotations
+
+from types import SimpleNamespace
+
+import pytest
+
+from app.services.domains.crossref import application as crossref_app
+
+
+def _item(*, title: str, year: int | None, scholar_label: str = "Shinya Yamanaka"):
+    return SimpleNamespace(
+        publication_id=1,
+        scholar_label=scholar_label,
+        title=title,
+        year=year,
+    )
+
+
+@pytest.mark.asyncio
+async def test_crossref_discovers_doi_from_best_title_match(monkeypatch: pytest.MonkeyPatch) -> None:
+    responses = [
+        [],
+        [
+            {
+                "DOI": "10.1000/noisy",
+                "title": ["Completely unrelated paper"],
+                "issued": {"date-parts": [[2014]]},
+                "author": [{"family": "Other"}],
+            },
+            {
+                "DOI": "10.1016/j.cell.2007.11.019",
+                "title": ["Induction of Pluripotent Stem Cells from Adult Human Fibroblasts"],
+                "issued": {"date-parts": [[2007]]},
+                "author": [{"family": "Yamanaka"}],
+            },
+        ],
+    ]
+
+    async def _fake_fetch_items(**_kwargs):
+        return responses.pop(0) if responses else []
+
+    monkeypatch.setattr(crossref_app, "_fetch_items", _fake_fetch_items)
+    doi = await crossref_app.discover_doi_for_publication(
+        item=_item(
+            title="Induction of Pluripotent Stem Cells from Adult Human Fibroblasts",
+            year=2007,
+        ),
+        max_rows=10,
+        email="user@example.com",
+    )
+    assert doi == "10.1016/j.cell.2007.11.019"
+
+
+@pytest.mark.asyncio
+async def test_crossref_rejects_large_year_mismatch(monkeypatch: pytest.MonkeyPatch) -> None:
+    async def _fake_fetch_items(**_kwargs):
+        return [
+            {
+                "DOI": "10.1000/wrong-year",
+                "title": ["Induction of Pluripotent Stem Cells from Adult Human Fibroblasts"],
+                "issued": {"date-parts": [[2014]]},
+                "author": [{"family": "Yamanaka"}],
+            }
+        ]
+
+    monkeypatch.setattr(crossref_app, "_fetch_items", _fake_fetch_items)
+    doi = await crossref_app.discover_doi_for_publication(
+        item=_item(
+            title="Induction of Pluripotent Stem Cells from Adult Human Fibroblasts",
+            year=2007,
+        ),
+        max_rows=10,
+        email=None,
+    )
+    assert doi is None

tests/unit/test_doi_normalize.py

@@ -0,0 +1,17 @@
+from __future__ import annotations
+
+from app.services.domains.doi.normalize import first_doi_from_texts, normalize_doi
+
+
+def test_normalize_doi_extracts_and_lowercases() -> None:
+    value = "https://doi.org/10.48550/ARXIV.1412.6980"
+    assert normalize_doi(value) == "10.48550/arxiv.1412.6980"
+
+
+def test_first_doi_from_texts_prefers_first_match() -> None:
+    result = first_doi_from_texts(
+        "no doi here",
+        "venue text 10.1000/ABC-123",
+        "title with 10.9999/ignored",
+    )
+    assert result == "10.1000/abc-123"

tests/unit/test_run_safety.py

@@ -3,7 +3,7 @@ from __future__ import annotations
 from datetime import datetime, timedelta, timezone
 
 from app.db.models import UserSetting
-from app.services import run_safety
+from app.services.domains.ingestion import safety as run_safety
 
 
 def test_apply_run_safety_outcome_triggers_blocked_cooldown() -> None:

tests/unit/test_runs_summary.py

@@ -1,6 +1,6 @@
 from __future__ import annotations
 
-from app.services.runs import extract_run_summary
+from app.services.domains.runs.application import extract_run_summary
 
 
 def test_extract_run_summary_includes_extended_metrics() -> None:

tests/unit/test_scholar_parser.py

@@ -2,12 +2,15 @@ from __future__ import annotations
 
 from pathlib import Path
 
-from app.services.scholar_parser import (
+import pytest
+
+from app.services.domains.scholar.parser import (
     ParseState,
+    ScholarDomInvariantError,
     parse_author_search_page,
     parse_profile_page,
 )
-from app.services.scholar_source import FetchResult
+from app.services.domains.scholar.source import FetchResult
 
 
 def _fixture(name: str) -> str:
@@ -98,7 +101,7 @@ def test_parse_profile_page_handles_missing_optional_metadata() -> None:
     assert publication.venue_text is None
 
 
-def test_parse_profile_page_extracts_direct_pdf_link() -> None:
+def test_parse_profile_page_ignores_direct_pdf_link_markup() -> None:
     html = """
     <html>
       <div id="gsc_prf_in">Direct PDF Test</div>
@@ -131,7 +134,7 @@ def test_parse_profile_page_extracts_direct_pdf_link() -> None:
 
     assert parsed.state == ParseState.OK
     assert len(parsed.publications) == 1
-    assert parsed.publications[0].pdf_url == "https://example.org/paper.pdf"
+    assert parsed.publications[0].pdf_url is None
 
 
 def test_parse_profile_page_fails_fast_when_citation_markup_is_unparseable() -> None:
@@ -160,10 +163,9 @@ def test_parse_profile_page_fails_fast_when_citation_markup_is_unparseable() ->
         error=None,
     )
 
-    parsed = parse_profile_page(fetch_result)
-
-    assert parsed.state == ParseState.LAYOUT_CHANGED
-    assert parsed.state_reason == "layout_row_citation_unparseable"
+    with pytest.raises(ScholarDomInvariantError) as exc:
+        parse_profile_page(fetch_result)
+    assert exc.value.code == "layout_row_citation_unparseable"
 
 
 def test_parse_profile_page_detects_layout_change_when_markers_absent() -> None:
@@ -175,11 +177,9 @@ def test_parse_profile_page_detects_layout_change_when_markers_absent() -> None:
         error=None,
     )
 
-    parsed = parse_profile_page(fetch_result)
-
-    assert parsed.state == ParseState.LAYOUT_CHANGED
-    assert parsed.state_reason == "layout_markers_missing"
-    assert "no_rows_detected" in parsed.warnings
+    with pytest.raises(ScholarDomInvariantError) as exc:
+        parse_profile_page(fetch_result)
+    assert exc.value.code == "layout_markers_missing"
 
 
 def test_parse_profile_page_reports_network_reason_when_status_missing() -> None:

tests/unit/test_scholar_search_safety.py

@@ -3,9 +3,9 @@ from __future__ import annotations
 import pytest
 from sqlalchemy.ext.asyncio import AsyncSession
 
-from app.services import scholars as scholar_service
-from app.services.scholar_parser import ParseState
-from app.services.scholar_source import FetchResult
+from app.services.domains.scholars import application as scholar_service
+from app.services.domains.scholar.parser import ParseState
+from app.services.domains.scholar.source import FetchResult
 
 pytestmark = [pytest.mark.integration, pytest.mark.db]
 

tests/unit/test_scholar_source.py

@@ -1,4 +1,4 @@
-from app.services.scholar_source import _build_profile_url
+from app.services.domains.scholar.source import _build_profile_url
 
 
 def test_build_profile_url_includes_pagesize_for_initial_page() -> None:

tests/unit/test_user_settings.py

@@ -2,7 +2,7 @@ from __future__ import annotations
 
 import pytest
 
-from app.services.user_settings import (
+from app.services.domains.settings.application import (
     DEFAULT_NAV_VISIBLE_PAGES,
     HARD_MIN_REQUEST_DELAY_SECONDS,
     HARD_MIN_RUN_INTERVAL_MINUTES,