From f776db07799abc4897e2c7122dcc67c6aaf67e0f Mon Sep 17 00:00:00 2001
From: yangdx <yangdx@znipower.com>
Date: Thu, 20 Feb 2025 04:09:02 +0800
Subject: [PATCH] Improved document status retrieval with content fallback.

- Added content fallback to content_summary
- Handled missing fields gracefully
- Made data copy to avoid modification
- Added error logging for missing fields
- Improved code readability and robustness
---
 lightrag/kg/json_doc_status_impl.py | 19 ++++++++++++++-----
 1 file changed, 14 insertions(+), 5 deletions(-)

diff --git a/lightrag/kg/json_doc_status_impl.py b/lightrag/kg/json_doc_status_impl.py
index 1a05abc2..76b7158b 100644
--- a/lightrag/kg/json_doc_status_impl.py
+++ b/lightrag/kg/json_doc_status_impl.py
@@ -48,11 +48,20 @@ class JsonDocStatusStorage(DocStatusStorage):
         self, status: DocStatus
     ) -> dict[str, DocProcessingStatus]:
         """Get all documents with a specific status"""
-        return {
-            k: DocProcessingStatus(**v)
-            for k, v in self._data.items()
-            if v["status"] == status.value
-        }
+        result = {}
+        for k, v in self._data.items():
+            if v["status"] == status.value:
+                try:
+                    # Make a copy of the data to avoid modifying the original
+                    data = v.copy()
+                    # If content is missing, use content_summary as content
+                    if "content" not in data and "content_summary" in data:
+                        data["content"] = data["content_summary"]
+                    result[k] = DocProcessingStatus(**data)
+                except KeyError as e:
+                    logger.error(f"Missing required field for document {k}: {e}")
+                    continue
+        return result
 
     async def index_done_callback(self) -> None:
         write_json(self._data, self._file_name)