@c4a/extract 0.6.0-beta.5 → 0.6.0-beta.7

package/README.md

@@ -131,7 +131,7 @@ When `snapshot` input is provided, the runner builds these files:
 During projection, code-owned Sections receive code `source_ref` values derived from these rows:
 
 - package rows: `src-N#package:<package>@<hash>`
-- symbol rows: `src-N#symbol:<locator>:<kind>@<hash>`
+- symbol rows: `src-N#symbol:<file>:<symbol>:<kind>@<hash>`
 
 These refs are verified against the raw code snapshot JSONL indexes. They are
 separate from prose evidence refs, because code snapshots use
@@ -212,6 +212,11 @@ project flow: better symbols/relations produce better draft candidates, stable
 `repo:<source>#symbol:...` source refs, review evidence, approved Markdown, and
 package output.
 
+Approved codegraph Markdown localizes canonical refs as
+`src-N#symbol:<file>:<symbol>:<kind>@<digest>`. The file segment is part of the
+deterministic evidence identity used by verification; agents copy the complete
+ref as an opaque token.
+
 ## Development
 
 ```bash

package/index.js

@@ -15474,7 +15474,8 @@ var DEFAULT_SOURCE_SPAN_HASH_LENGTH = 12;
 var BOM = "\uFEFF";
 var HASH_ID_RE = /^(?:sha256:)?[a-f0-9]{64}$/u;
 var SOURCE_SPAN_HASH_RE = /^[a-f0-9]{8,64}$/u;
-var DOCUMENT_SOURCE_NAME_RE = /^[a-z0-9][a-z0-9._-]*$/u;
+var DOCUMENT_SOURCE_SLUG_RE = /^[a-z0-9][a-z0-9._-]*$/u;
+var DOCUMENT_SOURCE_BATCH_RE = /^\d{8}\/[a-z0-9][a-z0-9._-]*$/u;
 function isRecord(value) {
   return value !== null && typeof value === "object" && !Array.isArray(value);
 }
@@ -15499,8 +15500,20 @@ function assertDocumentSourceType(value) {
 }
 function normalizeDocumentSourceName(name) {
   const value = name.trim();
-  if (!DOCUMENT_SOURCE_NAME_RE.test(value)) {
-    throw new TypeError(`document source name must be a lowercase path-safe slug: ${name}`);
+  if (!DOCUMENT_SOURCE_SLUG_RE.test(value) && !DOCUMENT_SOURCE_BATCH_RE.test(value)) {
+    throw new TypeError(`document source name must be a lowercase path-safe slug or YYYYMMDD/module identity: ${name}`);
+  }
+  if (DOCUMENT_SOURCE_BATCH_RE.test(value)) {
+    const dateName = value.slice(0, 8);
+    const year = Number(dateName.slice(0, 4));
+    const month = Number(dateName.slice(4, 6));
+    const day = Number(dateName.slice(6, 8));
+    const date = new Date(0);
+    date.setUTCHours(0, 0, 0, 0);
+    date.setUTCFullYear(year, month - 1, day);
+    if (date.getUTCFullYear() !== year || date.getUTCMonth() !== month - 1 || date.getUTCDate() !== day) {
+      throw new TypeError(`document source batch must be a valid calendar date: ${name}`);
+    }
   }
   return value;
 }
@@ -15530,14 +15543,20 @@ function decodeSnapshotLocatorPath(path2) {
   }
 }
 function parseDocumentSourceLocator(source2) {
-  const match = /^(file|lark):([^/]+)\/(.+)$/u.exec(source2);
-  if (match?.[1] === undefined || match[2] === undefined || match[3] === undefined)
+  const match = /^(file|lark):(.+)$/u.exec(source2);
+  if (match?.[1] === undefined || match[2] === undefined)
+    return null;
+  const segments = match[2].split("/");
+  const batched = /^\d{8}$/u.test(segments[0] ?? "") && segments.length >= 3;
+  const sourceName = batched ? `${segments[0]}/${segments[1]}` : segments[0];
+  const documentPath = segments.slice(batched ? 2 : 1).join("/");
+  if (sourceName === undefined || documentPath.length === 0)
     return null;
   try {
     return {
       sourceType: match[1],
-      sourceName: normalizeDocumentSourceName(match[2]),
-      documentPath: decodeSnapshotLocatorPath(match[3])
+      sourceName: normalizeDocumentSourceName(sourceName),
+      documentPath: decodeSnapshotLocatorPath(documentPath)
     };
   } catch {
     return null;

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@c4a/extract",
-  "version": "0.6.0-beta.5",
+  "version": "0.6.0-beta.7",
   "type": "module",
   "bin": {
     "c4a-extract-code": "./bin/c4a-extract-code.js"