From 36f2d7b7977774893dda3c79f172a28d62756ac0 Mon Sep 17 00:00:00 2001
From: KevinHuSh <kevinhu.sh@gmail.com>
Date: Tue, 2 Apr 2024 10:51:21 +0800
Subject: [PATCH] To avoid assertion while no rows in excel (#197)

### What problem does this PR solve?

_Briefly describe what this PR aims to solve. Include background context
that will help reviewers understand the purpose of the PR._

Issue link:#[[Link the issue
here](https://github.com/infiniflow/ragflow/issues/196)]

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
- [ ] New Feature (non-breaking change which adds functionality)
- [ ] Breaking Change (fix or feature that could cause existing
functionality not to work as expected)
- [ ] Documentation Update
- [ ] Refactoring
- [ ] Performance Improvement
- [ ] Test cases
- [ ] Python SDK impacted, Need to update PyPI
- [ ] Other (please describe):
---
 deepdoc/parser/excel_parser.py | 2 ++
 rag/app/manual.py              | 1 +
 rag/app/one.py                 | 1 +
 rag/app/table.py               | 1 +
 4 files changed, 5 insertions(+)

diff --git a/deepdoc/parser/excel_parser.py b/deepdoc/parser/excel_parser.py
index 7d470f3c..89cabb5d 100644
--- a/deepdoc/parser/excel_parser.py
+++ b/deepdoc/parser/excel_parser.py
@@ -14,6 +14,7 @@ class HuExcelParser:
         for sheetname in wb.sheetnames:
             ws = wb[sheetname]
             rows = list(ws.rows)
+            if not rows:continue
             tb += f"<table><caption>{sheetname}</caption><tr>"
             for t in list(rows[0]):
                 tb += f"<th>{t.value}</th>"
@@ -38,6 +39,7 @@ class HuExcelParser:
         for sheetname in wb.sheetnames:
             ws = wb[sheetname]
             rows = list(ws.rows)
+            if not rows:continue
             ti = list(rows[0])
             for r in list(rows[1:]):
                 l = []
diff --git a/rag/app/manual.py b/rag/app/manual.py
index 234ff9c0..284e3d6e 100644
--- a/rag/app/manual.py
+++ b/rag/app/manual.py
@@ -109,6 +109,7 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
     sections = [(txt, sec_ids[i], poss)
                 for i, (txt, _, poss) in enumerate(sections)]
     for (img, rows), poss in tbls:
+        if not rows:continue
         sections.append((rows if isinstance(rows, str) else rows[0], -1,
                          [(p[0] + 1 - from_page, p[1], p[2], p[3], p[4]) for p in poss]))
 
diff --git a/rag/app/one.py b/rag/app/one.py
index bd904610..8c08e6ac 100644
--- a/rag/app/one.py
+++ b/rag/app/one.py
@@ -44,6 +44,7 @@ class Pdf(PdfParser):
         sections = [(b["text"], self.get_position(b, zoomin))
                     for i, b in enumerate(self.boxes)]
         for (img, rows), poss in tbls:
+            if not rows:continue
             sections.append((rows if isinstance(rows, str) else rows[0],
                              [(p[0] + 1 - from_page, p[1], p[2], p[3], p[4]) for p in poss]))
         return [(txt, "") for txt, _ in sorted(sections, key=lambda x: (
diff --git a/rag/app/table.py b/rag/app/table.py
index 3d105270..29fa2546 100644
--- a/rag/app/table.py
+++ b/rag/app/table.py
@@ -40,6 +40,7 @@ class Excel(ExcelParser):
         for sheetname in wb.sheetnames:
             ws = wb[sheetname]
             rows = list(ws.rows)
+            if not rows:continue
             headers = [cell.value for cell in rows[0]]
             missed = set([i for i, h in enumerate(headers) if h is None])
             headers = [