Milestone 2’s core deterministic scanner path

src/repo_registry/core/models.py

@@ -1,6 +1,7 @@
 from __future__ import annotations
 
 from dataclasses import dataclass, field
+from typing import Any
 
 
 @dataclass(frozen=True)
@@ -13,6 +14,48 @@ class Repository:
     status: str
 
 
+@dataclass(frozen=True)
+class RepositorySnapshot:
+    id: int
+    repository_id: int
+    commit_hash: str
+    branch: str
+    source_path: str
+    file_count: int
+
+
+@dataclass(frozen=True)
+class AnalysisRun:
+    id: int
+    repository_id: int
+    snapshot_id: int | None
+    status: str
+    started_at: str
+    completed_at: str | None
+    error_message: str | None
+    scanner_version: str
+
+
+@dataclass(frozen=True)
+class ObservedFact:
+    id: int
+    repository_id: int
+    analysis_run_id: int
+    snapshot_id: int | None
+    kind: str
+    path: str
+    name: str
+    value: str
+    metadata: dict[str, Any]
+
+
+@dataclass(frozen=True)
+class ScanSummary:
+    analysis_run: AnalysisRun
+    snapshot: RepositorySnapshot | None
+    facts: list[ObservedFact]
+
+
 @dataclass(frozen=True)
 class Evidence:
     id: int

src/repo_registry/core/service.py

@@ -2,7 +2,15 @@ from __future__ import annotations
 
 from collections.abc import Sequence
 
-from repo_registry.core.models import Repository, RepositoryAbilityMap, SearchResult
+from repo_registry.core.models import (
+    AnalysisRun,
+    ObservedFact,
+    Repository,
+    RepositoryAbilityMap,
+    ScanSummary,
+    SearchResult,
+)
+from repo_registry.repo_scanning.scanner import DeterministicScanner
 from repo_registry.storage.sqlite import RegistryStore
 
 
@@ -11,6 +19,7 @@ class RegistryService:
 
     def __init__(self, store: RegistryStore) -> None:
         self.store = store
+        self.scanner = DeterministicScanner()
 
     def register_repository(
         self,
@@ -33,6 +42,48 @@ class RegistryService:
     def get_repository(self, repository_id: int) -> Repository:
         return self.store.get_repository(repository_id)
 
+    def analyze_repository(
+        self,
+        repository_id: int,
+        *,
+        source_path: str | None = None,
+    ) -> ScanSummary:
+        repository = self.store.get_repository(repository_id)
+        run = self.store.create_analysis_run(repository_id)
+        self.store.update_repository_status(repository_id, "analyzing")
+        try:
+            scan_result = self.scanner.scan(source_path or repository.url)
+        except Exception as exc:
+            failed_run = self.store.fail_analysis_run(repository_id, run.id, str(exc))
+            return ScanSummary(analysis_run=failed_run, snapshot=None, facts=[])
+
+        completed_run = self.store.complete_analysis_run(
+            repository_id,
+            run.id,
+            scan_result,
+        )
+        snapshot = (
+            self.store.get_snapshot(completed_run.snapshot_id)
+            if completed_run.snapshot_id is not None
+            else None
+        )
+        facts = self.store.list_observed_facts(repository_id, completed_run.id)
+        return ScanSummary(
+            analysis_run=completed_run,
+            snapshot=snapshot,
+            facts=facts,
+        )
+
+    def list_analysis_runs(self, repository_id: int) -> list[AnalysisRun]:
+        return self.store.list_analysis_runs(repository_id)
+
+    def list_observed_facts(
+        self,
+        repository_id: int,
+        analysis_run_id: int | None = None,
+    ) -> list[ObservedFact]:
+        return self.store.list_observed_facts(repository_id, analysis_run_id)
+
     def add_ability(
         self,
         repository_id: int,