From d8192f8f1736e2a01db50e68d947a1f3b74e4a1c Mon Sep 17 00:00:00 2001
From: Pegasus <42954461+leonace924@users.noreply.github.com>
Date: Thu, 15 Jan 2026 01:24:51 -0500
Subject: [PATCH] Fix: validate regex pattern in split_with_pattern to prevent
 crash (#12633)

### What problem does this PR solve?

Fix regex pattern validation in split_with_pattern (#12605)

- Add try-except block to validate user-provided regex patterns before
use
- Gracefully fallback to single chunk when invalid regex is provided
- Prevent server crash during DOCX parsing with malformed delimiters

## Problem

Parsing DOCX files with custom regex delimiters crashes with `re.error:
nothing to repeat at position 9` when users provide invalid regex
patterns.

Closes #12605

## Solution

Validate and compile regex pattern before use. On invalid pattern, log
warning and return content as single chunk instead of crashing.

## Changes

- `rag/nlp/__init__.py`: Add regex validation in `split_with_pattern()`
function

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)

Contribution by Gittensor, see my contribution statistics at
https://gittensor.io/miners/details?githubId=42954461
---
 rag/nlp/__init__.py | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/rag/nlp/__init__.py b/rag/nlp/__init__.py
index e4cefd993..bc033dac4 100644
--- a/rag/nlp/__init__.py
+++ b/rag/nlp/__init__.py
@@ -275,7 +275,18 @@ def tokenize(d, txt, eng):
 
 def split_with_pattern(d, pattern: str, content: str, eng) -> list:
     docs = []
-    txts = [txt for txt in re.split(r"(%s)" % pattern, content, flags=re.DOTALL)]
+
+    # Validate and compile regex pattern before use
+    try:
+        compiled_pattern = re.compile(r"(%s)" % pattern, flags=re.DOTALL)
+    except re.error as e:
+        logging.warning(f"Invalid delimiter regex pattern '{pattern}': {e}. Falling back to no split.")
+        # Fallback: return content as single chunk
+        dd = copy.deepcopy(d)
+        tokenize(dd, content, eng)
+        return [dd]
+
+    txts = [txt for txt in compiled_pattern.split(content)]
     for j in range(0, len(txts), 2):
         txt = txts[j]
         if not txt: