From 72bf34f858747162799d59b2bc076ea74254f75e Mon Sep 17 00:00:00 2001
From: BotAndyGao <gaoxu@botsmart.cn>
Date: Tue, 26 Nov 2024 18:20:50 +0800
Subject: [PATCH 1/3] fix issues with exporting tables containing cells that
 span multiple rows and columns (#119)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

* 1、解决导出表格标注时添加colspan和rowspan时的异常
2、解决导出的gt文件中gt属性中html标签合规的问题

* fix code style

* 修复单元格占多行又占多列导出报错的问题。issues：导出表格标注报错 #113
---
 PPOCRLabel.py |  1 -
 libs/utils.py | 18 ++++++++++--------
 2 files changed, 10 insertions(+), 9 deletions(-)

diff --git a/PPOCRLabel.py b/PPOCRLabel.py
index 64a324d..c806355 100644
--- a/PPOCRLabel.py
+++ b/PPOCRLabel.py
@@ -3181,7 +3181,6 @@ def exportJSON(self):
         """
         export PPLabel and CSV to JSON (PubTabNet)
         """
-        import pandas as pd
 
         # automatically save annotations
         self.saveFilestate()
diff --git a/libs/utils.py b/libs/utils.py
index a11d7a6..8ad0c9e 100644
--- a/libs/utils.py
+++ b/libs/utils.py
@@ -232,14 +232,16 @@ def convert_token(html_list):
             elif col == "td":
                 token_list.extend(["<td>", "</td>"])
             else:
-                token_list.append("<td")
-                if "colspan" in col:
-                    _, n = col.split("colspan=")
-                    token_list.append(' colspan="{}"'.format(int(n)))
-                if "rowspan" in col:
-                    _, n = col.split("rowspan=")
-                    token_list.append(' rowspan="{}"'.format(int(n)))
-                token_list.extend([">", "</td>"])
+                token_list.append("<td")  # Start the td tag
+                # Use regex to match "colspan" and "rowspan" attributes and their values
+                colspan_match = re.search(r"colspan=(\d+)", col)
+                rowspan_match = re.search(r"rowspan=(\d+)", col)
+                if colspan_match:
+                    token_list.append(f' colspan="{colspan_match.group(1)}"')
+                if rowspan_match:
+                    token_list.append(f' rowspan="{rowspan_match.group(1)}"')
+                token_list.append(">")  # End the opening td tag
+                token_list.append("</td>")  # Close the td tag
         token_list.append("</tr>")
     token_list.append("</tbody>")
 

From d9cc4554e3081c78efea1d5a2cb6d439b5b6d251 Mon Sep 17 00:00:00 2001
From: Wang Xin <xinwang614@gmail.com>
Date: Thu, 28 Nov 2024 15:44:37 +0800
Subject: [PATCH 2/3] Update deploy.yml (#120)

---
 .github/workflows/deploy.yml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/.github/workflows/deploy.yml b/.github/workflows/deploy.yml
index 492da1d..76cfbd8 100644
--- a/.github/workflows/deploy.yml
+++ b/.github/workflows/deploy.yml
@@ -71,7 +71,7 @@ jobs:
         name: python-package-distributions
         path: dist/
     - name: Sign the dists with Sigstore
-      uses: sigstore/gh-action-sigstore-python@v2.1.1
+      uses: sigstore/gh-action-sigstore-python@v3.0.0
       with:
         inputs: >-
           ./dist/*.tar.gz

From 10a68bf0e0526dacb7e72da23d1b9d978762f190 Mon Sep 17 00:00:00 2001
From: Wang Xin <xinwang614@gmail.com>
Date: Thu, 28 Nov 2024 16:13:03 +0800
Subject: [PATCH 3/3] rename deploy workflow (#121)

---
 .github/workflows/{deploy.yml => publish.yml} | 0
 1 file changed, 0 insertions(+), 0 deletions(-)
 rename .github/workflows/{deploy.yml => publish.yml} (100%)

diff --git a/.github/workflows/deploy.yml b/.github/workflows/publish.yml
similarity index 100%
rename from .github/workflows/deploy.yml
rename to .github/workflows/publish.yml