From 6d15f1f247c41af22b8f7fc99631a3a18950ff37 Mon Sep 17 00:00:00 2001
From: Yiorgis Gozadinos <ggozadinos@gmail.com>
Date: Fri, 22 May 2026 13:45:55 +0300
Subject: [PATCH] fix URL-decode file:// paths before stat/exists checks

---
 haiku_rag_slim/haiku/rag/client/documents.py | 21 ++++----
 tests/ingester/test_serve_integration.py     | 56 ++++++++++++++++++++
 2 files changed, 67 insertions(+), 10 deletions(-)

diff --git a/haiku_rag_slim/haiku/rag/client/documents.py b/haiku_rag_slim/haiku/rag/client/documents.py
index f8b17ea3..973e123f 100644
--- a/haiku_rag_slim/haiku/rag/client/documents.py
+++ b/haiku_rag_slim/haiku/rag/client/documents.py
@@ -1,7 +1,7 @@
 import tempfile
 from pathlib import Path
 from typing import TYPE_CHECKING
-from urllib.parse import urlparse
+from urllib.parse import unquote, urlparse
 
 from haiku.rag.client.processing import (
     ensure_chunks_embedded,
@@ -315,8 +315,10 @@ async def create_document_from_source(
     # Directory case: recurse with the existing FS filter and produce one
     # document per file. Remote schemes (http/s3) never hit this branch.
     if parsed_url.scheme in ("", "file"):
+        # file:// URIs URL-encode special characters ([, ], spaces, etc.);
+        # unquote to get the real filesystem path before any stat/rglob.
         local_path = (
-            Path(parsed_url.path)
+            Path(unquote(parsed_url.path))
             if parsed_url.scheme == "file"
             else (Path(source) if isinstance(source, str) else source)
         )
@@ -355,16 +357,15 @@ async def create_document_from_source(
     fetcher = resolve_fetcher(source_str, storage_options=storage_options)
 
     # The stored URI is what we look up + persist by. For an explicit uri
-    # override, use it as-is. Otherwise canonicalize local paths to file://
-    # and leave remote URIs alone.
+    # override, use it as-is. For a file:// input the source string is
+    # already canonical (URL-encoded); round-tripping via Path.as_uri()
+    # would double-encode any escapes like %5B. For bare paths, canonicalize.
     if uri is not None:
         stored_uri = uri
-    elif parsed_url.scheme in ("", "file"):
-        stored_uri = (
-            (Path(parsed_url.path) if parsed_url.scheme == "file" else Path(source_str))
-            .absolute()
-            .as_uri()
-        )
+    elif parsed_url.scheme == "file":
+        stored_uri = source_str
+    elif parsed_url.scheme == "":
+        stored_uri = Path(source_str).absolute().as_uri()
     else:
         stored_uri = source_str
 
diff --git a/tests/ingester/test_serve_integration.py b/tests/ingester/test_serve_integration.py
index 87d5f439..7a2c5737 100644
--- a/tests/ingester/test_serve_integration.py
+++ b/tests/ingester/test_serve_integration.py
@@ -135,6 +135,62 @@ async def test_e2e_initial_sweep_lands_succeeded_jobs(tmp_path, jobs, sync):
     assert row_b is not None and row_b.content_hash and row_b.last_ingested_at
 
 
+@pytest.mark.asyncio
+async def test_e2e_handles_url_encoded_special_chars_in_path(tmp_path, jobs, sync):
+    """File names containing characters that path.as_uri() URL-encodes (e.g.
+    Next.js dynamic-route brackets like `[chunk_id]`) must survive the
+    round-trip through the job queue without tripping the existence check
+    inside create_document_from_source."""
+    bracketed_dir = tmp_path / "[chunk_id]"
+    bracketed_dir.mkdir()
+    target = bracketed_dir / "route.ts"
+    target.write_text("export default {};")
+
+    client = _mock_client(tmp_path)
+    cfg = FSSourceConfig(
+        type="fs",
+        id="local",
+        root=tmp_path,
+        poll_interval_s=60.0,
+    )
+
+    manager = PollerManager(
+        configs=[cfg],
+        job_repo=jobs,
+        sync_repo=sync,
+        supported_extensions=[".ts"],
+    )
+    pool = WorkerPool(
+        client=client,
+        job_repo=jobs,
+        sync_repo=sync,
+        worker_count=1,
+        max_concurrent=1,
+        poll_idle_interval_s=0.05,
+    )
+
+    await pool.start()
+    await manager.start()
+    try:
+
+        async def _one_succeeded() -> bool:
+            counts = await jobs.counts_by_status()
+            return counts.get("succeeded", 0) == 1
+
+        await _wait_for(_one_succeeded, timeout=5.0)
+    finally:
+        await manager.stop()
+        await pool.stop()
+
+    counts = await jobs.counts_by_status()
+    assert counts.get("succeeded", 0) == 1
+    assert counts.get("dead", 0) == 0  # no PermanentError("File does not exist")
+
+    # The URI in the queue is URL-encoded; the worker still finds the file.
+    [call] = client.create_document_from_source.await_args_list
+    assert "%5Bchunk_id%5D" in call.args[0]
+
+
 @pytest.mark.asyncio
 async def test_e2e_watchfiles_push_event_lands_as_job(tmp_path, jobs, sync):
     """FSPoller's watchfiles loop: a file *added* after startup should land