From 87bb8a023bdfa8cb6f9f1e3ebc381b2a04c2a6d8 Mon Sep 17 00:00:00 2001
From: yangdx <gzdaniel@me.com>
Date: Sun, 14 Sep 2025 17:29:27 +0800
Subject: [PATCH] Fix tuple delimiter regex patterns and add debug logging

- Add debug logs for malformed records
- Fix regex for consecutive delimiters
- Handle missing closing brackets
---
 lightrag/operate.py |  2 ++
 lightrag/utils.py   | 13 +++++++------
 2 files changed, 9 insertions(+), 6 deletions(-)

diff --git a/lightrag/operate.py b/lightrag/operate.py
index 4cdc1c19..7821ae38 100644
--- a/lightrag/operate.py
+++ b/lightrag/operate.py
@@ -326,6 +326,7 @@ async def _handle_single_entity_extraction(
             logger.warning(
                 f"{chunk_key}: LLM output format error; found {len(record_attributes)}/4 feilds on ENTITY `{record_attributes[1]}` @ `{record_attributes[2] if len(record_attributes) > 2 else 'N/A'}`"
             )
+            logger.debug(record_attributes)
         return None
 
     try:
@@ -399,6 +400,7 @@ async def _handle_single_relationship_extraction(
             logger.warning(
                 f"{chunk_key}: LLM output format error; found {len(record_attributes)}/5 fields on REALTION `{record_attributes[1]}`~`{record_attributes[2] if len(record_attributes) >2 else 'N/A'}`"
             )
+            logger.debug(record_attributes)
         return None
 
     try:
diff --git a/lightrag/utils.py b/lightrag/utils.py
index 177d3fbf..77bd9c47 100644
--- a/lightrag/utils.py
+++ b/lightrag/utils.py
@@ -2583,9 +2583,9 @@ def fix_tuple_delimiter_corruption(
     # Escape the delimiter core for regex use
     escaped_delimiter_core = re.escape(delimiter_core)
 
-    # Fix: <|#||#|> -> <|#|>, <|#|||#|> -> <|#|>
+    # Fix: <|##|> -> <|#|>, <|#||#|> -> <|#|>, <|#|||#|> -> <|#|>
     record = re.sub(
-        rf"<\|{escaped_delimiter_core}\|+{escaped_delimiter_core}\|>",
+        rf"<\|{escaped_delimiter_core}\|*?{escaped_delimiter_core}\|>",
         tuple_delimiter,
         record,
     )
@@ -2604,9 +2604,9 @@ def fix_tuple_delimiter_corruption(
         record,
     )
 
-    # Fix: <X|#|> -> <|#|>, <|#|Y> -> <|#|>, <X|#|Y> -> <|#|>, <||#||> -> <|#|> (one extra characters outside pipes)
+    # Fix: <X|#|> -> <|#|>, <|#|Y> -> <|#|>, <X|#|Y> -> <|#|>, <||#||> -> <|#|>, <||#> -> <|#|> (one extra characters outside pipes)
     record = re.sub(
-        rf"<.?\|{escaped_delimiter_core}\|.?>",
+        rf"<.?\|{escaped_delimiter_core}\|*?>",
         tuple_delimiter,
         record,
     )
@@ -2625,9 +2625,10 @@ def fix_tuple_delimiter_corruption(
         record,
     )
 
-    # Fix: <|#| -> <|#|> (missing closing >)
+    # Fix: <|#| -> <|#|>, <|#|| -> <|#|> (missing closing >)
+    # 
     record = re.sub(
-        rf"<\|{escaped_delimiter_core}\|(?!>)",
+        rf"<\|{escaped_delimiter_core}\|+(?!>)",
         tuple_delimiter,
         record,
     )