Merge pull request #1490 from opendatalab/master

master->dev

magic_pdf/libs/version.py

-__version__ = "0.10.6"
+__version__ = "1.0.0"

next_docs/zh_cn/user_guide/quick_start/to_markdown.rst

@@ -12,6 +12,7 @@
     from magic_pdf.data.data_reader_writer import FileBasedDataWriter, FileBasedDataReader
     from magic_pdf.data.dataset import PymuDocDataset
     from magic_pdf.model.doc_analyze_by_custom_model import doc_analyze
+    from magic_pdf.config.enums import SupportedPdfParseMethod
 
     # args
     pdf_file_name = "abc.pdf"  # replace with the real pdf path
@@ -37,14 +38,21 @@
     ds = PymuDocDataset(pdf_bytes)
 
     ## inference
+    if ds.classify() == SupportedPdfParseMethod.OCR:
         infer_result = ds.apply(doc_analyze, ocr=True)
 
-    ### draw model result on each page
-    infer_result.draw_model(os.path.join(local_md_dir, f"{name_without_suff}_model.pdf"))
-
         ## pipeline
         pipe_result = infer_result.pipe_ocr_mode(image_writer)
 
+    else:
+        infer_result = ds.apply(doc_analyze, ocr=False)
+
+        ## pipeline
+        pipe_result = infer_result.pipe_txt_mode(image_writer)
+
+    ### draw model result on each page
+    infer_result.draw_model(os.path.join(local_md_dir, f"{name_without_suff}_model.pdf"))
+
     ### draw layout result on each page
     pipe_result.draw_layout(os.path.join(local_md_dir, f"{name_without_suff}_layout.pdf"))
 
@@ -54,6 +62,9 @@
     ### dump markdown
     pipe_result.dump_md(md_writer, f"{name_without_suff}.md", image_dir)
 
+    ### dump content list
+    pipe_result.dump_content_list(md_writer, f"{name_without_suff}_content_list.json", image_dir)
+
 
 对象存储文件示例
 ^^^^^^^^^^^^^^^^
@@ -93,14 +104,21 @@
     ds = PymuDocDataset(pdf_bytes)
 
     ## inference
+    if ds.classify() == SupportedPdfParseMethod.OCR:
         infer_result = ds.apply(doc_analyze, ocr=True)
 
-    ### draw model result on each page
-    infer_result.draw_model(os.path.join(local_dir, f'{name_without_suff}_model.pdf'))  # dump to local
-
         ## pipeline
         pipe_result = infer_result.pipe_ocr_mode(image_writer)
 
+    else:
+        infer_result = ds.apply(doc_analyze, ocr=False)
+
+        ## pipeline
+        pipe_result = infer_result.pipe_txt_mode(image_writer)
+
+    ### draw model result on each page
+    infer_result.draw_model(os.path.join(local_dir, f'{name_without_suff}_model.pdf'))  # dump to local
+
     ### draw layout result on each page
     pipe_result.draw_layout(os.path.join(local_dir, f'{name_without_suff}_layout.pdf'))  # dump to local
 
@@ -110,5 +128,7 @@
     ### dump markdown
     pipe_result.dump_md(writer, f'{name_without_suff}.md', "unittest/tmp/images")  # dump to remote s3
 
+    ### dump content list
+    pipe_result.dump_content_list(md_writer, f"{name_without_suff}_content_list.json", image_dir)
 
 前去 :doc:`../data/data_reader_writer` 获取更多有关 **读写** 示例

signatures/version1/cla.json

@@ -103,6 +103,38 @@
       "created_at": "2024-11-19T07:28:12Z",
       "repoId": 765083837,
       "pullRequestNo": 1024
+    },
+    {
+      "name": "MatthewZMD",
+      "id": 12422335,
+      "comment_id": 2565021810,
+      "created_at": "2024-12-30T04:46:33Z",
+      "repoId": 765083837,
+      "pullRequestNo": 1379
+    },
+    {
+      "name": "yzztin",
+      "id": 99233593,
+      "comment_id": 2568773016,
+      "created_at": "2025-01-03T07:02:55Z",
+      "repoId": 765083837,
+      "pullRequestNo": 1397
+    },
+    {
+      "name": "utopia2077",
+      "id": 78017255,
+      "comment_id": 2571704177,
+      "created_at": "2025-01-05T17:57:17Z",
+      "repoId": 765083837,
+      "pullRequestNo": 1412
+    },
+    {
+      "name": "beholder91",
+      "id": 113708464,
+      "comment_id": 2581919559,
+      "created_at": "2025-01-10T06:58:05Z",
+      "repoId": 765083837,
+      "pullRequestNo": 1479
     }
   ]
 }
\ No newline at end of file