From 8ea1f46ae51f29dce7908a1bde77fee22e6c2e3f Mon Sep 17 00:00:00 2001
From: Roger Parkinson <77937569+Roger-Parkinson-EHP@users.noreply.github.com>
Date: Sat, 21 Mar 2026 23:19:31 -0400
Subject: [PATCH] fix: handle CRLF line endings in markdown heading regex

The HEADING_RE regex used `$` to anchor the end of heading lines,
but on Windows, `String.split('\n')` leaves `\r` at the end of each
line. The `$` anchor does not match before `\r` in JavaScript's
non-multiline mode, causing the regex to silently skip every heading
in CRLF-encoded files.

This resulted in 0 Section nodes being created for markdown files
on Windows, while the same files indexed correctly on macOS/Linux.

Fix: replace `.+$` with `.+?[\r\t ]*$` to consume optional trailing
whitespace and carriage returns before the anchor.

Tested on a 424-file markdown-heavy repo on Windows:
  Before: 22 sections (only from LF-encoded files)
  After:  8,072 sections (all files)
---
 gitnexus/src/core/ingestion/markdown-processor.ts | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/gitnexus/src/core/ingestion/markdown-processor.ts b/gitnexus/src/core/ingestion/markdown-processor.ts
index d894cee43..196c0e1e1 100644
--- a/gitnexus/src/core/ingestion/markdown-processor.ts
+++ b/gitnexus/src/core/ingestion/markdown-processor.ts
@@ -10,7 +10,7 @@ import path from 'node:path';
 import { generateId } from '../../lib/utils.js';
 import { KnowledgeGraph, GraphNode, GraphRelationship } from '../graph/types.js';
 
-const HEADING_RE = /^(#{1,6})\s+(.+)$/;
+const HEADING_RE = /^(#{1,6})\s+(.+?)[\r\t ]*$/;
 const LINK_RE = /\[([^\]]*)\]\(([^)]+)\)/g;
 const MD_EXTENSIONS = new Set(['.md', '.mdx']);