fix(loaders): accumulate all pages in CustomDocLoader (#376)

openrag/components/indexer/loaders/CustomDocLoader.py

@@ -34,6 +34,6 @@ async def aload_document(self, file_path, metadata: dict = None):
 
         s = ""
         for page_num, p in enumerate(pages, start=1):
-            s = p.page_content.strip() + f"\n[PAGE_{page_num}]\n"
+            s += p.page_content.strip() + f"\n[PAGE_{page_num}]\n"
 
         return Document(page_content=s, metadata=metadata)

openrag/components/indexer/loaders/test_customdocloader.py

@@ -0,0 +1,40 @@
+"""Regression test for CustomDocLoader page accumulation (#376).
+
+The previous loop body used ``s = ...`` instead of ``s += ...``, so only
+the final page survived. This test confirms every page's content is now
+in the returned ``Document``.
+"""
+
+from unittest.mock import AsyncMock, MagicMock, patch
+
+import pytest
+from langchain_core.documents.base import Document as LCDocument
+
+
+@pytest.mark.asyncio
+async def test_customdocloader_accumulates_all_pages(tmp_path):
+    from components.indexer.loaders.CustomDocLoader import CustomDocLoader
+
+    fake_pages = [
+        LCDocument(page_content="page-one"),
+        LCDocument(page_content="page-two"),
+        LCDocument(page_content="page-three"),
+    ]
+    fake_loader_instance = MagicMock()
+    fake_loader_instance.aload = AsyncMock(return_value=fake_pages)
+    fake_loader_cls = MagicMock(return_value=fake_loader_instance)
+
+    file_path = tmp_path / "stub.docx"
+    file_path.write_text("ignored")
+
+    with patch.dict(CustomDocLoader.doc_loaders, {".docx": fake_loader_cls}, clear=True):
+        # BaseLoader.__init__ pulls a config; we bypass it with object.__new__
+        loader = object.__new__(CustomDocLoader)
+        result = await loader.aload_document(str(file_path), metadata={"src": "x"})
+
+    assert "page-one" in result.page_content
+    assert "page-two" in result.page_content
+    assert "page-three" in result.page_content
+    assert "[PAGE_1]" in result.page_content
+    assert "[PAGE_2]" in result.page_content
+    assert "[PAGE_3]" in result.page_content