Merge pull request #693 from myhloli/dev

feat: add arXiv paper link to header and adjust PDF parsing logic

magic_pdf/pdf_parse_union_core_v2.py

@@ -191,7 +191,7 @@ def insert_lines_into_block(block_bbox, line_height, page_w, page_h):
     # 如果block高度小于n行正文，则直接返回block的bbox
     if line_height*3 < block_height:
         if block_height > page_h*0.25 and page_w*0.5 > block_weight > page_w*0.25:  # 可能是双列结构，可以切细点
-            lines = int(block_height/line_height)
+            lines = int(block_height/line_height)+1
         else:
             # 如果block的宽度超过0.4页面宽度，则将block分成3行
             if block_weight > page_w*0.4:

projects/gradio_app/header.html

@@ -90,6 +90,16 @@
           </a>
         </span>
 
+        <!-- arXiv Link. -->
+        <span class="link-block">
+          <a href="https://arxiv.org/abs/2409.18839" class="external-link button is-normal is-rounded is-dark" style="text-decoration: none; cursor: pointer">
+            <span class="icon" style="margin-right: 8px">
+              <i class="fas fa-file" style="color: white"></i>
+            </span>
+            <span style="color: white">Paper</span>
+          </a>
+        </span>
+
         <!-- Homepage Link. -->
         <span class="link-block">
           <a href="https://opendatalab.com/" class="external-link button is-normal is-rounded is-dark" style="text-decoration: none; cursor: pointer">