From ed5f81b02e8237c303be48cae1be8aef910156ca Mon Sep 17 00:00:00 2001
From: Kevin Hu <kevinhu.sh@gmail.com>
Date: Mon, 14 Apr 2025 11:00:11 +0800
Subject: [PATCH] Fix: abnormal cell mergeing. (#6991)

### What problem does this PR solve?


### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
---
 deepdoc/vision/table_structure_recognizer.py | 2 +-
 rag/app/manual.py                            | 2 ++
 2 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/deepdoc/vision/table_structure_recognizer.py b/deepdoc/vision/table_structure_recognizer.py
index 64ad8b92..470abc3b 100644
--- a/deepdoc/vision/table_structure_recognizer.py
+++ b/deepdoc/vision/table_structure_recognizer.py
@@ -133,7 +133,7 @@ class TableStructureRecognizer(Recognizer):
         return "Ot"
 
     @staticmethod
-    def construct_table(boxes, is_english=False, html=False, **kwargs):
+    def construct_table(boxes, is_english=False, html=True, **kwargs):
         cap = ""
         i = 0
         while i < len(boxes):
diff --git a/rag/app/manual.py b/rag/app/manual.py
index 5de782d6..a05670a0 100644
--- a/rag/app/manual.py
+++ b/rag/app/manual.py
@@ -162,6 +162,8 @@ class Docx(DocxParser):
                         if c.text == r.cells[j].text:
                             span += 1
                             i = j
+                        else:
+                            break
                     i += 1
                     html += f"<td>{c.text}</td>" if span == 1 else f"<td colspan='{span}'>{c.text}</td>"
                 html += "</tr>"