From 843720f958038d7ceb9482b849b9142acb8c3478 Mon Sep 17 00:00:00 2001
From: KevinHuSh <kevinhu.sh@gmail.com>
Date: Thu, 30 May 2024 11:47:36 +0800
Subject: [PATCH] fix bug in pdf parser (#986)

### What problem does this PR solve?

#963

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
---
 deepdoc/parser/pdf_parser.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/deepdoc/parser/pdf_parser.py b/deepdoc/parser/pdf_parser.py
index 4e43df7a3..2971858c0 100644
--- a/deepdoc/parser/pdf_parser.py
+++ b/deepdoc/parser/pdf_parser.py
@@ -392,7 +392,7 @@ class RAGFlowPdfParser:
                 b["text"].strip()[-1] in ",;:'\"，、‘“；：-",
                 len(b["text"].strip()) > 1 and b["text"].strip(
                 )[-2] in ",;:'\"，‘“、；：",
-                b_["text"].strip()[0] in "。；？！?”）),，、：",
+                b_["text"].strip() and b_["text"].strip()[0] in "。；？！?”）),，、：",
             ]
             # features for not concating
             feats = [