refactor(reference): share graph index projections

src/application/ReferenceSourceImport.ts

@@ -2,6 +2,8 @@ import { compareUnicodeCodePoints } from "../domain/unicodeCodePointOrder.js";
 import { isSecretLikePath } from "../domain/referenceSourceClassification.js";
 import {
   createHistoricalSourceGraph,
+  historicalSourceLanguages,
+  historicalSourceManifests,
   historicalSourceParseFailureKey,
   type HistoricalSourceGraph,
   type HistoricalSourceGraphInput,
@@ -83,30 +85,6 @@ const buildProvenance = (
   caller: options.caller,
 });
 
-const deriveLanguages = (
-  entries: HistoricalSourceGraphInput["entries"],
-): string[] =>
-  [
-    ...new Set(
-      entries.flatMap((entry) =>
-        entry.kind === "file" && entry.language !== null
-          ? [entry.language]
-          : [],
-      ),
-    ),
-  ].sort(compareUnicodeCodePoints);
-
-const deriveManifests = (
-  entries: HistoricalSourceGraphInput["entries"],
-): string[] =>
-  entries
-    .flatMap((entry) =>
-      entry.kind === "file" && entry.classifications.includes("manifest")
-        ? [entry.path]
-        : [],
-    )
-    .sort(compareUnicodeCodePoints);
-
 const deriveInventoryState = (
   input: Pick<
     HistoricalSourceGraphInput,
@@ -229,8 +207,8 @@ export const importReferenceSource = async (
     ),
     parse_failures: uniqueFailures,
     exclusions: sortedExclusions,
-    languages: deriveLanguages(sortedEntries),
-    manifests: deriveManifests(sortedEntries),
+    languages: historicalSourceLanguages(sortedEntries),
+    manifests: historicalSourceManifests(sortedEntries),
     vcs,
     provenance: buildProvenance(options),
     limitations: sortedLimitations,

src/domain/referenceSourceGraph.ts

@@ -255,7 +255,8 @@ const checkSortedUnique = (
     }
 };
 
-const expectedLanguages = (
+/** Derive the canonical language index from inventoried source files. */
+export const historicalSourceLanguages = (
   entries: readonly z.infer<typeof sourceEntrySchema>[],
 ): string[] =>
   [
@@ -268,7 +269,8 @@ const expectedLanguages = (
     ),
   ].sort(compareUnicodeCodePoints);
 
-const expectedManifests = (
+/** Derive the canonical manifest path index from inventoried source files. */
+export const historicalSourceManifests = (
   entries: readonly z.infer<typeof sourceEntrySchema>[],
 ): string[] =>
   entries
@@ -408,7 +410,7 @@ function checkGraphInvariants(
 
   if (
     canonicalJson(graph.languages) !==
-    canonicalJson(expectedLanguages(graph.entries))
+    canonicalJson(historicalSourceLanguages(graph.entries))
   )
     context.addIssue({
       code: "custom",
@@ -417,7 +419,7 @@ function checkGraphInvariants(
     });
   if (
     canonicalJson(graph.manifests) !==
-    canonicalJson(expectedManifests(graph.entries))
+    canonicalJson(historicalSourceManifests(graph.entries))
   )
     context.addIssue({
       code: "custom",