first content-indexing slice

src/repo_registry/core/models.py

@@ -59,6 +59,19 @@ class ObservedFact:
     metadata: dict[str, Any]
 
 
+@dataclass(frozen=True)
+class ContentChunk:
+    id: int
+    repository_id: int
+    analysis_run_id: int
+    snapshot_id: int | None
+    path: str
+    kind: str
+    start_line: int
+    end_line: int
+    text: str
+
+
 @dataclass(frozen=True)
 class ScanSummary:
     analysis_run: AnalysisRun

src/repo_registry/core/service.py

@@ -7,6 +7,7 @@ from repo_registry.core.models import (
     AnalysisRun,
     CapabilitySummary,
     CandidateGraph,
+    ContentChunk,
     ObservedFact,
     Repository,
     RepositoryAbilityMap,
@@ -15,6 +16,7 @@ from repo_registry.core.models import (
     SearchResult,
 )
 from repo_registry.candidate_graph.generator import CandidateGraphGenerator
+from repo_registry.content_indexing.extractor import ContentExtractor
 from repo_registry.repo_ingestion.git import GitIngestionService
 from repo_registry.repo_ingestion.metadata import RepositoryMetadataExtractor
 from repo_registry.repo_scanning.scanner import DeterministicScanner
@@ -34,6 +36,7 @@ class RegistryService:
         self.ingestion = ingestion or GitIngestionService()
         self.metadata_extractor = RepositoryMetadataExtractor()
         self.candidate_generator = CandidateGraphGenerator()
+        self.content_extractor = ContentExtractor()
 
     def register_repository(
         self,
@@ -111,6 +114,13 @@ class RegistryService:
             else None
         )
         facts = self.store.list_observed_facts(repository_id, completed_run.id)
+        chunks = self.content_extractor.extract(scan_result.source_path, facts)
+        self.store.replace_content_chunks(
+            repository_id,
+            completed_run.id,
+            completed_run.snapshot_id,
+            chunks,
+        )
         candidates = self.candidate_generator.generate(repository, facts)
         self.store.replace_candidate_graph(repository_id, completed_run.id, candidates)
         return ScanSummary(
@@ -145,6 +155,13 @@ class RegistryService:
     ) -> list[ObservedFact]:
         return self.store.list_observed_facts(repository_id, analysis_run_id)
 
+    def list_content_chunks(
+        self,
+        repository_id: int,
+        analysis_run_id: int | None = None,
+    ) -> list[ContentChunk]:
+        return self.store.list_content_chunks(repository_id, analysis_run_id)
+
     def candidate_graph(self, repository_id: int, analysis_run_id: int) -> CandidateGraph:
         return self.store.get_candidate_graph(repository_id, analysis_run_id)