merge: sync from master branch

docs/download_models.py

+# use modelscope sdk download models
+from modelscope import snapshot_download
+model_dir = snapshot_download('opendatalab/PDF-Extract-Kit')
+print(f"model dir is: {model_dir}/models")

docs/how_to_download_models_en.md

@@ -9,7 +9,7 @@ git lfs install
 To download the `PDF-Extract-Kit` model from Hugging Face, use the following command:
 
 ```bash
-git lfs clone https://huggingface.co/wanderkid/PDF-Extract-Kit
+git lfs clone https://huggingface.co/opendatalab/PDF-Extract-Kit
 ```
 
 Ensure that Git LFS is enabled during the clone to properly download all large files.

docs/how_to_download_models_zh_cn.md

@@ -13,7 +13,7 @@
 
 ```bash
 git lfs install # 安装 Git 大文件存储插件 (Git LFS) 
-git lfs clone https://huggingface.co/wanderkid/PDF-Extract-Kit # 从 Hugging Face 下载 PDF-Extract-Kit 模型
+git lfs clone https://huggingface.co/opendatalab/PDF-Extract-Kit # 从 Hugging Face 下载 PDF-Extract-Kit 模型
 ```
 
 
@@ -28,7 +28,7 @@ ModelScope 支持SDK或模型下载，任选一个即可。
 
 ```bash
 git lfs install
-git lfs clone https://www.modelscope.cn/wanderkid/PDF-Extract-Kit.git
+git lfs clone https://www.modelscope.cn/opendatalab/PDF-Extract-Kit.git
 ```
 
 ### 2）利用SDK下载
@@ -41,7 +41,7 @@ pip install modelscope
 ```python
 # 使用modelscope sdk下载模型
 from modelscope import snapshot_download
-model_dir = snapshot_download('wanderkid/PDF-Extract-Kit')
+model_dir = snapshot_download('opendatalab/PDF-Extract-Kit')
 print(f"模型文件下载路径为：{model_dir}/models")
 ```
 

magic_pdf/para/para_split_v2.py

@@ -100,7 +100,7 @@ def __detect_list_lines(lines, new_layout_bboxes, lang):
 
     if lang != 'en':
         return lines, None
-    else:
+
     total_lines = len(lines)
     line_fea_encode = []
     """
@@ -114,6 +114,9 @@ def __detect_list_lines(lines, new_layout_bboxes, lang):
         x_map_tag_dict, min_x_tag = cluster_line_x(lines)
     for l in lines:
         span_text = __get_span_text(l['spans'][0])
+        if not span_text:
+            line_fea_encode.append(0)
+            continue
         first_char = span_text[0]
         layout = __find_layout_bbox_by_line(l['bbox'], new_layout_bboxes)
         if not layout:

signatures/version1/cla.json

@@ -31,6 +31,22 @@
       "created_at": "2024-08-13T12:23:16Z",
       "repoId": 765083837,
       "pullRequestNo": 418
+    },
+    {
+      "name": "Matthijz98",
+      "id": 17087153,
+      "comment_id": 2298912989,
+      "created_at": "2024-08-20T13:49:50Z",
+      "repoId": 765083837,
+      "pullRequestNo": 467
+    },
+    {
+      "name": "strongerfly",
+      "id": 11643869,
+      "comment_id": 2309481561,
+      "created_at": "2024-08-26T07:01:49Z",
+      "repoId": 765083837,
+      "pullRequestNo": 487
     }
   ]
 }
\ No newline at end of file