refactor(workers): extract parseTableRow to shared markdown-utils

Author: cursoragent

workers/src/index.ts

@@ -22,14 +22,15 @@ import { ZipBaselineFetcher } from "./zip-baseline-fetcher";
 import { RequestTracer } from "./tracing";
 import { parseConsumerLabel } from "./telemetry";
 import { renderNotFoundPage } from "./not-found-ui";
+import { parseTableRow } from "./markdown-utils";
 import pkg from "../package.json";
 
 export type { Env };
 
 const BUILD_VERSION = pkg.version;
 
 // ──────────────────────────────────────────────────────────────────────────────
-// Canon-table parsing helper (local copy — mirrors orchestrate.ts parseTableRow).
+// Canon-table parsing helper.
 //
 // parseSelfReportHeadersTable extracts the self-report header contract from
 // canon/constraints/telemetry-governance.md. The table format is governed by
@@ -38,13 +39,6 @@ const BUILD_VERSION = pkg.version;
 // fall back to the minimal baseline without hiding the degradation.
 // ──────────────────────────────────────────────────────────────────────────────
 
-function parseTableRow(row: string): string[] {
-  const parts = row.split("|");
-  if (parts.length > 0 && parts[0].trim() === "") parts.shift();
-  if (parts.length > 0 && parts[parts.length - 1].trim() === "") parts.pop();
-  return parts.map((c) => c.trim());
-}
-
 function parseSelfReportHeadersTable(markdown: string): Record<string, string> | null {
   // Target section: "### Self-Report Fields" — grab the table that follows.
   // Stop at the next `###` or `##` heading, whichever comes first.

workers/src/markdown-utils.ts

@@ -0,0 +1,24 @@
+/**
+ * Shared markdown parsing helpers.
+ *
+ * Keep this module dependency-free so it can be imported from any code path
+ * (orchestrate, index, future canon readers) without pulling in unrelated
+ * state. Every helper here must be pure and stateless.
+ */
+
+/**
+ * Parse a single markdown table row into trimmed cell values, preserving
+ * legitimately-empty middle cells. Only the leading and trailing empty strings
+ * produced by splitting a `| a | b |`-style row are stripped — a prior
+ * `.filter(c => c.length > 0)` approach also dropped empty interior cells,
+ * which silently collapsed the column count and caused `cols.length >= N`
+ * guards to misfire (e.g. a voice-dump row with an empty tiers cell).
+ */
+export function parseTableRow(row: string): string[] {
+  const parts = row.split("|");
+  // Strip the leading empty produced by a leading `|`, if present
+  if (parts.length > 0 && parts[0].trim() === "") parts.shift();
+  // Strip the trailing empty produced by a trailing `|`, if present
+  if (parts.length > 0 && parts[parts.length - 1].trim() === "") parts.pop();
+  return parts.map((c) => c.trim());
+}

workers/src/orchestrate.ts

@@ -18,6 +18,7 @@ import {
   type SectionResult,
 } from "./zip-baseline-fetcher";
 import { buildBM25Index, searchBM25, type BM25Index } from "./bm25";
+import { parseTableRow } from "./markdown-utils";
 import type { RequestTracer } from "./tracing";
 import pkg from "../package.json";
 
@@ -154,27 +155,6 @@ export interface OrchestrateOptions {
   canonUrl?: string;
 }
 
-// ──────────────────────────────────────────────────────────────────────────────
-// Markdown table helpers
-// ──────────────────────────────────────────────────────────────────────────────
-
-/**
- * Parse a single markdown table row into trimmed cell values, preserving
- * legitimately-empty middle cells. Only the leading and trailing empty strings
- * produced by splitting a `| a | b |`-style row are stripped — a prior
- * `.filter(c => c.length > 0)` approach also dropped empty interior cells,
- * which silently collapsed the column count and caused `cols.length >= N`
- * guards to misfire (e.g. a voice-dump row with an empty tiers cell).
- */
-function parseTableRow(row: string): string[] {
-  const parts = row.split("|");
-  // Strip the leading empty produced by a leading `|`, if present
-  if (parts.length > 0 && parts[0].trim() === "") parts.shift();
-  // Strip the trailing empty produced by a trailing `|`, if present
-  if (parts.length > 0 && parts[parts.length - 1].trim() === "") parts.pop();
-  return parts.map((c) => c.trim());
-}
-
 // ──────────────────────────────────────────────────────────────────────────────
 // BM25 Index Cache (per-request, lazy)
 // ──────────────────────────────────────────────────────────────────────────────