magic-pdf 0.9.1__py3-none-any.whl → 0.9.3__py3-none-any.whl

magic_pdf/pdf_parse_union_core_v2.py

@@ -30,8 +30,8 @@ from magic_pdf.pre_proc.equations_replace import (
 from magic_pdf.pre_proc.ocr_detect_all_bboxes import \
     ocr_prepare_bboxes_for_layout_split_v2
 from magic_pdf.pre_proc.ocr_dict_merge import (fill_spans_in_blocks,
-                                               fix_block_spans,
-                                               fix_discarded_block, fix_block_spans_v2)
+                                               fix_discarded_block,
+                                               fix_block_spans_v2)
 from magic_pdf.pre_proc.ocr_span_list_modify import (
     get_qa_need_list_v2, remove_overlaps_low_confidence_spans,
     remove_overlaps_min_spans)
@@ -164,8 +164,8 @@ class ModelSingleton:
 
 
 def do_predict(boxes: List[List[int]], model) -> List[int]:
-    from magic_pdf.model.v3.helpers import (boxes2inputs, parse_logits,
-                                            prepare_inputs)
+    from magic_pdf.model.sub_modules.reading_oreder.layoutreader.helpers import (boxes2inputs, parse_logits,
+                                                                                 prepare_inputs)
 
     inputs = boxes2inputs(boxes)
     inputs = prepare_inputs(inputs, model)
@@ -174,23 +174,57 @@ def do_predict(boxes: List[List[int]], model) -> List[int]:
 
 
 def cal_block_index(fix_blocks, sorted_bboxes):
-    for block in fix_blocks:
 
-        line_index_list = []
-        if len(block['lines']) == 0:
-            block['index'] = sorted_bboxes.index(block['bbox'])
-        else:
+    if sorted_bboxes is not None:
+        # 使用layoutreader排序
+        for block in fix_blocks:
+            line_index_list = []
+            if len(block['lines']) == 0:
+                block['index'] = sorted_bboxes.index(block['bbox'])
+            else:
+                for line in block['lines']:
+                    line['index'] = sorted_bboxes.index(line['bbox'])
+                    line_index_list.append(line['index'])
+                median_value = statistics.median(line_index_list)
+                block['index'] = median_value
+
+            # 删除图表body block中的虚拟line信息, 并用real_lines信息回填
+            if block['type'] in [BlockType.ImageBody, BlockType.TableBody]:
+                block['virtual_lines'] = copy.deepcopy(block['lines'])
+                block['lines'] = copy.deepcopy(block['real_lines'])
+                del block['real_lines']
+    else:
+        # 使用xycut排序
+        block_bboxes = []
+        for block in fix_blocks:
+            block_bboxes.append(block['bbox'])
+
+            # 删除图表body block中的虚拟line信息, 并用real_lines信息回填
+            if block['type'] in [BlockType.ImageBody, BlockType.TableBody]:
+                block['virtual_lines'] = copy.deepcopy(block['lines'])
+                block['lines'] = copy.deepcopy(block['real_lines'])
+                del block['real_lines']
+
+        import numpy as np
+        from magic_pdf.model.sub_modules.reading_oreder.layoutreader.xycut import recursive_xy_cut
+
+        random_boxes = np.array(block_bboxes)
+        np.random.shuffle(random_boxes)
+        res = []
+        recursive_xy_cut(np.asarray(random_boxes).astype(int), np.arange(len(block_bboxes)), res)
+        assert len(res) == len(block_bboxes)
+        sorted_boxes = random_boxes[np.array(res)].tolist()
+
+        for i, block in enumerate(fix_blocks):
+            block['index'] = sorted_boxes.index(block['bbox'])
+
+        # 生成line index
+        sorted_blocks = sorted(fix_blocks, key=lambda b: b['index'])
+        line_inedx = 1
+        for block in sorted_blocks:
             for line in block['lines']:
-                line['index'] = sorted_bboxes.index(line['bbox'])
-                line_index_list.append(line['index'])
-            median_value = statistics.median(line_index_list)
-            block['index'] = median_value
-
-        # 删除图表body block中的虚拟line信息, 并用real_lines信息回填
-        if block['type'] in [BlockType.ImageBody, BlockType.TableBody]:
-            block['virtual_lines'] = copy.deepcopy(block['lines'])
-            block['lines'] = copy.deepcopy(block['real_lines'])
-            del block['real_lines']
+                line['index'] = line_inedx
+                line_inedx += 1
 
     return fix_blocks
 
@@ -264,6 +298,9 @@ def sort_lines_by_model(fix_blocks, page_w, page_h, line_height):
                 block['lines'].append({'bbox': line, 'spans': []})
             page_line_list.extend(lines)
 
+    if len(page_line_list) > 200:  # layoutreader最高支持512line
+        return None
+
     # 使用layoutreader排序
     x_scale = 1000.0 / page_w
     y_scale = 1000.0 / page_h

magic_pdf/resources/model_config/model_configs.yaml

@@ -4,4 +4,5 @@ weights:
   yolo_v8_mfd: MFD/YOLO/yolo_v8_ft.pt
   unimernet_small: MFR/unimernet_small
   struct_eqtable: TabRec/StructEqTable
-  tablemaster: TabRec/TableMaster
+  tablemaster: TabRec/TableMaster
+  rapid_table: TabRec/RapidTable

magic_pdf/tools/common.py

@@ -14,6 +14,9 @@ from magic_pdf.pipe.TXTPipe import TXTPipe
 from magic_pdf.pipe.UNIPipe import UNIPipe
 from magic_pdf.rw.AbsReaderWriter import AbsReaderWriter
 from magic_pdf.rw.DiskReaderWriter import DiskReaderWriter
+import fitz
+# from io import BytesIO
+# from pypdf import PdfReader, PdfWriter
 
 
 def prepare_env(output_dir, pdf_file_name, method):
@@ -26,6 +29,42 @@ def prepare_env(output_dir, pdf_file_name, method):
     return local_image_dir, local_md_dir
 
 
+# def convert_pdf_bytes_to_bytes_by_pypdf(pdf_bytes, start_page_id=0, end_page_id=None):
+#     # 将字节数据包装在 BytesIO 对象中
+#     pdf_file = BytesIO(pdf_bytes)
+#     # 读取 PDF 的字节数据
+#     reader = PdfReader(pdf_file)
+#     # 创建一个新的 PDF 写入器
+#     writer = PdfWriter()
+#     # 将所有页面添加到新的 PDF 写入器中
+#     end_page_id = end_page_id if end_page_id is not None and end_page_id >= 0 else len(reader.pages) - 1
+#     if end_page_id > len(reader.pages) - 1:
+#         logger.warning("end_page_id is out of range, use pdf_docs length")
+#         end_page_id = len(reader.pages) - 1
+#     for i, page in enumerate(reader.pages):
+#         if start_page_id <= i <= end_page_id:
+#             writer.add_page(page)
+#     # 创建一个字节缓冲区来存储输出的 PDF 数据
+#     output_buffer = BytesIO()
+#     # 将 PDF 写入字节缓冲区
+#     writer.write(output_buffer)
+#     # 获取字节缓冲区的内容
+#     converted_pdf_bytes = output_buffer.getvalue()
+#     return converted_pdf_bytes
+
+
+def convert_pdf_bytes_to_bytes_by_pymupdf(pdf_bytes, start_page_id=0, end_page_id=None):
+    document = fitz.open("pdf", pdf_bytes)
+    output_document = fitz.open()
+    end_page_id = end_page_id if end_page_id is not None and end_page_id >= 0 else len(document) - 1
+    if end_page_id > len(document) - 1:
+        logger.warning("end_page_id is out of range, use pdf_docs length")
+        end_page_id = len(document) - 1
+    output_document.insert_pdf(document, from_page=start_page_id, to_page=end_page_id)
+    output_bytes = output_document.tobytes()
+    return output_bytes
+
+
 def do_parse(
     output_dir,
     pdf_file_name,
@@ -55,6 +94,8 @@ def do_parse(
         f_draw_model_bbox = True
         f_draw_line_sort_bbox = True
 
+    pdf_bytes = convert_pdf_bytes_to_bytes_by_pymupdf(pdf_bytes, start_page_id, end_page_id)
+
     orig_model_list = copy.deepcopy(model_list)
     local_image_dir, local_md_dir = prepare_env(output_dir, pdf_file_name,
                                                 parse_method)
@@ -66,15 +107,18 @@ def do_parse(
     if parse_method == 'auto':
         jso_useful_key = {'_pdf_type': '', 'model_list': model_list}
         pipe = UNIPipe(pdf_bytes, jso_useful_key, image_writer, is_debug=True,
-                       start_page_id=start_page_id, end_page_id=end_page_id, lang=lang,
+                       # start_page_id=start_page_id, end_page_id=end_page_id,
+                       lang=lang,
                        layout_model=layout_model, formula_enable=formula_enable, table_enable=table_enable)
     elif parse_method == 'txt':
         pipe = TXTPipe(pdf_bytes, model_list, image_writer, is_debug=True,
-                       start_page_id=start_page_id, end_page_id=end_page_id, lang=lang,
+                       # start_page_id=start_page_id, end_page_id=end_page_id,
+                       lang=lang,
                        layout_model=layout_model, formula_enable=formula_enable, table_enable=table_enable)
     elif parse_method == 'ocr':
         pipe = OCRPipe(pdf_bytes, model_list, image_writer, is_debug=True,
-                       start_page_id=start_page_id, end_page_id=end_page_id, lang=lang,
+                       # start_page_id=start_page_id, end_page_id=end_page_id,
+                       lang=lang,
                        layout_model=layout_model, formula_enable=formula_enable, table_enable=table_enable)
     else:
         logger.error('unknown parse method')

{magic_pdf-0.9.1.dist-info → magic_pdf-0.9.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: magic-pdf
-Version: 0.9.1
+Version: 0.9.3
 Summary: A practical tool for converting PDF to Markdown
 Home-page: https://github.com/opendatalab/MinerU
 Requires-Python: >=3.9
@@ -26,6 +26,9 @@ Requires-Dist: struct-eqtable==0.3.2; extra == "full"
 Requires-Dist: einops; extra == "full"
 Requires-Dist: accelerate; extra == "full"
 Requires-Dist: doclayout-yolo==0.0.2; extra == "full"
+Requires-Dist: rapidocr-paddle; extra == "full"
+Requires-Dist: rapid-table; extra == "full"
+Requires-Dist: PyYAML; extra == "full"
 Requires-Dist: detectron2; extra == "full"
 Requires-Dist: paddlepaddle==3.0.0b1; platform_system == "Linux" and extra == "full"
 Requires-Dist: matplotlib; (platform_system == "Linux" or platform_system == "Darwin") and extra == "full"
@@ -80,7 +83,8 @@ Requires-Dist: paddlepaddle==2.6.1; (platform_system == "Windows" or platform_sy
 </div>
 
 # Changelog
-- 2024/11/06 0.9.1 released. Integrated the [StructTable-InternVL2-1B](https://huggingface.co/U4R/StructTable-InternVL2-1B) model for table recognition functionality.
+- 2024/11/15 0.9.3 released. Integrated [RapidTable](https://github.com/RapidAI/RapidTable) for table recognition, improving single-table parsing speed by more than 10 times, with higher accuracy and lower GPU memory usage.
+- 2024/11/06 0.9.2 released. Integrated the [StructTable-InternVL2-1B](https://huggingface.co/U4R/StructTable-InternVL2-1B) model for table recognition functionality.
 - 2024/10/31 0.9.0 released. This is a major new version with extensive code refactoring, addressing numerous issues, improving performance, reducing hardware requirements, and enhancing usability:
   - Refactored the sorting module code to use [layoutreader](https://github.com/ppaanngggg/layoutreader) for reading order sorting, ensuring high accuracy in various layouts.
   - Refactored the paragraph concatenation module to achieve good results in cross-column, cross-page, cross-figure, and cross-table scenarios.
@@ -176,13 +180,14 @@ There are three different ways to experience MinerU:
 - [Quick CPU Demo (Windows, Linux, Mac)](#quick-cpu-demo)
 - [Linux/Windows + CUDA](#Using-GPU)
 
-**⚠️ Pre-installation Notice—Hardware and Software Environment Support**
-
-To ensure the stability and reliability of the project, we only optimize and test for specific hardware and software environments during development. This ensures that users deploying and running the project on recommended system configurations will get the best performance with the fewest compatibility issues.
-
-By focusing resources on the mainline environment, our team can more efficiently resolve potential bugs and develop new features.
-
-In non-mainline environments, due to the diversity of hardware and software configurations, as well as third-party dependency compatibility issues, we cannot guarantee 100% project availability. Therefore, for users who wish to use this project in non-recommended environments, we suggest carefully reading the documentation and FAQ first. Most issues already have corresponding solutions in the FAQ. We also encourage community feedback to help us gradually expand support.
+> [!WARNING]
+> **Pre-installation Notice—Hardware and Software Environment Support**
+>
+> To ensure the stability and reliability of the project, we only optimize and test for specific hardware and software environments during development. This ensures that users deploying and running the project on recommended system configurations will get the best performance with the fewest compatibility issues.
+>
+> By focusing resources on the mainline environment, our team can more efficiently resolve potential bugs and develop new features.
+>
+> In non-mainline environments, due to the diversity of hardware and software configurations, as well as third-party dependency compatibility issues, we cannot guarantee 100% project availability. Therefore, for users who wish to use this project in non-recommended environments, we suggest carefully reading the documentation and FAQ first. Most issues already have corresponding solutions in the FAQ. We also encourage community feedback to help us gradually expand support.
 
 <table>
     <tr>
@@ -262,11 +267,13 @@ Refer to [How to Download Model Files](docs/how_to_download_models_en.md) for de
 After completing the [2. Download model weight files](#2-download-model-weight-files) step, the script will automatically generate a `magic-pdf.json` file in the user directory and configure the default model path.
 You can find the `magic-pdf.json` file in your 【user directory】.
 
+> [!TIP]
 > The user directory for Windows is "C:\\Users\\username", for Linux it is "/home/username", and for macOS it is "/Users/username".
 
 You can modify certain configurations in this file to enable or disable features, such as table recognition:
 
 
+> [!NOTE]
 > If the following items are not present in the JSON, please manually add the required items and remove the comment content (standard JSON does not support comments).
 
 ```json
@@ -281,7 +288,7 @@ You can modify certain configurations in this file to enable or disable features
         "enable": true  // The formula recognition feature is enabled by default. If you need to disable it, please change the value here to "false".
     },
     "table-config": {
-        "model": "tablemaster",  // When using structEqTable, please change to "struct_eqtable".
+        "model": "rapid_table",  // When using structEqTable, please change to "struct_eqtable".
         "enable": false, // The table recognition feature is disabled by default. If you need to enable it, please change the value here to "true".
         "max_time": 400
     }
@@ -295,13 +302,14 @@ If your device supports CUDA and meets the GPU requirements of the mainline envi
 - [Ubuntu 22.04 LTS + GPU](docs/README_Ubuntu_CUDA_Acceleration_en_US.md)
 - [Windows 10/11 + GPU](docs/README_Windows_CUDA_Acceleration_en_US.md)
 - Quick Deployment with Docker
-    > Docker requires a GPU with at least 16GB of VRAM, and all acceleration features are enabled by default.
-    >
-    > Before running this Docker, you can use the following command to check if your device supports CUDA acceleration on Docker.
-    > 
-    > ```bash
-    > docker run --rm --gpus=all nvidia/cuda:12.1.0-base-ubuntu22.04 nvidia-smi
-    > ```
+> [!IMPORTANT]
+> Docker requires a GPU with at least 8GB of VRAM, and all acceleration features are enabled by default.
+>
+> Before running this Docker, you can use the following command to check if your device supports CUDA acceleration on Docker.
+> 
+> ```bash
+> docker run --rm --gpus=all nvidia/cuda:12.1.0-base-ubuntu22.04 nvidia-smi
+> ```
   ```bash
   wget https://github.com/opendatalab/MinerU/raw/master/Dockerfile
   docker build -t mineru:latest .
@@ -363,8 +371,8 @@ The results will be saved in the `{some_output_dir}` directory. The output file
 ├── some_pdf_spans.pdf                   # smallest granularity bbox position information diagram
 └── some_pdf_content_list.json           # Rich text JSON arranged in reading order
 ```
-
-For more information about the output files, please refer to the [Output File Description](docs/output_file_en_us.md).
+> [!TIP]
+> For more information about the output files, please refer to the [Output File Description](docs/output_file_en_us.md).
 
 ### API
 
@@ -415,12 +423,12 @@ TODO
 
 # TODO
 
-- 🗹 Reading order based on the model  
-- 🗹 Recognition of `index` and `list` in the main text  
-- 🗹 Table recognition
-- ☐ Code block recognition in the main text
-- ☐ [Chemical formula recognition](docs/chemical_knowledge_introduction/introduction.pdf)
-- ☐ Geometric shape recognition
+- [x] Reading order based on the model  
+- [x] Recognition of `index` and `list` in the main text  
+- [x] Table recognition
+- [ ] Code block recognition in the main text
+- [ ] [Chemical formula recognition](docs/chemical_knowledge_introduction/introduction.pdf)
+- [ ] Geometric shape recognition
 
 # Known Issues
 
@@ -455,7 +463,9 @@ This project currently uses PyMuPDF to achieve advanced functionality. However,
 # Acknowledgments
 
 - [PDF-Extract-Kit](https://github.com/opendatalab/PDF-Extract-Kit)
+- [DocLayout-YOLO](https://github.com/opendatalab/DocLayout-YOLO)
 - [StructEqTable](https://github.com/UniModal4Reasoning/StructEqTable-Deploy)
+- [RapidTable](https://github.com/RapidAI/RapidTable)
 - [PaddleOCR](https://github.com/PaddlePaddle/PaddleOCR)
 - [PyMuPDF](https://github.com/pymupdf/PyMuPDF)
 - [layoutreader](https://github.com/ppaanngggg/layoutreader)

{magic_pdf-0.9.1.dist-info → magic_pdf-0.9.3.dist-info}/RECORD

@@ -2,7 +2,7 @@ magic_pdf/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 magic_pdf/pdf_parse_by_ocr.py,sha256=E-AYHUXjzorFli0CEtmnAi09SI2STJ7FX58yjU0c9PI,810
 magic_pdf/pdf_parse_by_txt.py,sha256=YeFYVAdfwF1CXOHq0LVE5131nqPHA14nt5t_sb-CMMk,709
 magic_pdf/pdf_parse_union_core.py,sha256=AGIrP7ahc6Ycku0PxAlbjZhwqsdJ8iuRPIn-PFASKWY,11772
-magic_pdf/pdf_parse_union_core_v2.py,sha256=18V8aYLz0gLQSMxGJDgUCWSltr15L8s8ClNqB17DNvw,23647
+magic_pdf/pdf_parse_union_core_v2.py,sha256=GAgSP0PqbPg4U_nJXUztr-uBmakIK5rKwuxv0o9nMK0,25228
 magic_pdf/user_api.py,sha256=gM-3RQYc6pMEsVvEPFXfWf5RBjAvHcUccugL6fXpP_U,3991
 magic_pdf/config/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 magic_pdf/config/enums.py,sha256=CImYuw4sbKpq9zrj6zrrEvtdoGkjxDt8S8ByNVDpypU,89
@@ -23,7 +23,7 @@ magic_pdf/data/io/http.py,sha256=XlKB0DNf4a_uUnfgcclvaaOtmE7lmddx0DnK8A-emAM,958
 magic_pdf/data/io/s3.py,sha256=hyA7sbNriQy64xd_uyJ7acN_oneQ1Pdmoc7_xcvkue8,3606
 magic_pdf/dict2md/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 magic_pdf/dict2md/mkcontent.py,sha256=rWUY-2opd0jeowEUEVOV_uWcKum1Q7ng4nOoT6-ka_s,17459
-magic_pdf/dict2md/ocr_mkcontent.py,sha256=ClxKUwrK7wlXKCcDfuTryztKl5e8pzcnh5x_fODFm2U,12928
+magic_pdf/dict2md/ocr_mkcontent.py,sha256=lM5UBDueiZcm4_z-jtmcgbJH2jhaXhMVY5ubggaKqHU,12954
 magic_pdf/filter/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 magic_pdf/filter/pdf_classify_by_type.py,sha256=spmDO-f2ihAl1d6-EP-j271Yi50oyu6mw4X2kRd_m0s,42320
 magic_pdf/filter/pdf_meta_scan.py,sha256=5R2XDiBZw0xd4ugbDxuyk6fztGlT5jFsGN85hLvo-hQ,17390
@@ -38,7 +38,7 @@ magic_pdf/layout/layout_det_utils.py,sha256=NCYBTvsrULE3Cue53aMD1MfXTmOL9Xy0nivl
 magic_pdf/layout/layout_sort.py,sha256=jtacQVcxnuYAksvEqtS0DH-v6U8qyjX-jmyZgDJ-egA,37005
 magic_pdf/layout/layout_spiler_recog.py,sha256=QjBSgB-a7J2yjUR1eaCs9ZD7URtiRnV6W934hpAeuC4,3067
 magic_pdf/layout/mcol_sort.py,sha256=ADnLisBJBHXDKYChcf2lzTb_TC_vZ4q89_CSN8mwEJc,11331
-magic_pdf/libs/Constants.py,sha256=u9i-ivxxcGp7Hu_zvrLA1jdPcEnYhPb7wXOSUaOSwGQ,1140
+magic_pdf/libs/Constants.py,sha256=ptiwMvWDUmzRZ0IbP1bM3PjGJ24BQVQQHO4sCeioPv8,1173
 magic_pdf/libs/MakeContentConfig.py,sha256=Do5VKNQp3gfUKyhrZStfzfBj7l-vbsYpsJFF1SsmEc0,248
 magic_pdf/libs/ModelBlockTypeEnum.py,sha256=kalXPbo5ya6hKhhBHPGlHl1yjWOURoXZWQM3rVUyPsY,164
 magic_pdf/libs/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -46,11 +46,11 @@ magic_pdf/libs/boxbase.py,sha256=ELMHWolgWROxOAQDgwmL7VS5kveZp4ifvEzRmPul2Ws,169
 magic_pdf/libs/calc_span_stats.py,sha256=5vnU27DcbkFDRSAoLqAmX0KQ3I9ehWkEgh_t9hxg_zI,10147
 magic_pdf/libs/clean_memory.py,sha256=BIOmEWuwR7c_p4OwTSW2muE3PRaGhmOplS-wTXt_EXk,211
 magic_pdf/libs/commons.py,sha256=6Zu9-OyamyCNDY7qj0SxR-rux-ggj9im3CVPtC4ubB8,7108
-magic_pdf/libs/config_reader.py,sha256=0uMOTSZE2crvqdGj2j21tlwV0nNRZha44Y9X98gQ3AQ,4067
+magic_pdf/libs/config_reader.py,sha256=7QIeUPLb8CNa7E3n8TT3MN61lZdYVTylxn5cyXPsPfA,4066
 magic_pdf/libs/convert_utils.py,sha256=Ov-lsfCLBPz_15iSJXIslBNmrSf_E_1g_XDWJy8NgO8,143
 magic_pdf/libs/coordinate_transform.py,sha256=Bbop2cP2uz2ZG0U0gwd7J6EKkgABq5Rv03qf2LMPw80,429
 magic_pdf/libs/detect_language_from_model.py,sha256=Uln8F9qs8EJOw4EgI7KRlaU3lD_mK8KMTlADLFtz8fk,816
-magic_pdf/libs/draw_bbox.py,sha256=J_RaG6sRkqNyUd75NiWbDk-3LIE8es-zNIbcwR9myvo,17196
+magic_pdf/libs/draw_bbox.py,sha256=Ri_jbOv3Tgnx6s1IscRIWiIKNfUHPkGW8v4q4jPtgo8,17623
 magic_pdf/libs/drop_reason.py,sha256=IfjPSrPLMmVziqjOXPep7r_ioQKFRahDgbOW1SD-Tuw,2148
 magic_pdf/libs/drop_tag.py,sha256=bZDg3bIVWvBT1Ec1icwj5WLOkt5-hI6eRYZ2tX9_a74,673
 magic_pdf/libs/hash_utils.py,sha256=VEKK9WfFoZgrPfi8kfITjLpr8Ahufs8tXh9R1Y5lAL8,404
@@ -65,42 +65,63 @@ magic_pdf/libs/pdf_check.py,sha256=MAe8wzwT0qvPf_I72wEZG7k1g4haNHS7oUtLqkB5rlE,2
 magic_pdf/libs/pdf_image_tools.py,sha256=CAd01giTKr_UJz1_QtDOARG9G9z69GFpzRZwcWSfLtE,1282
 magic_pdf/libs/safe_filename.py,sha256=ckwcM_eqoysTb5id8czp-tXq2G9da0-l3pshZDCHQtE,236
 magic_pdf/libs/textbase.py,sha256=SC1Frhz3Fb7V7n2SFRBsl7Bmg0JZdlvZskq0lfW1vIk,732
-magic_pdf/libs/version.py,sha256=UwJXM8JY2T3tE2id0K2k_lEaVThbRTrGO1mNibyzIz8,22
+magic_pdf/libs/version.py,sha256=xKd3pzbczuMsdB08eLAOqZDUd_q1IRxwZ_ccAFL4c4A,22
 magic_pdf/libs/vis_utils.py,sha256=hTOTEakKV0pGMbk0tbRkVI_tku7A3dGc96ynObZ4kwI,10207
 magic_pdf/model/__init__.py,sha256=1QcfMKET0xQhSaZMjNQHi_TjzSSDR6PI5mjkmaXHPe8,52
 magic_pdf/model/doc_analyze_by_custom_model.py,sha256=eYrtOIlFqw8O95ShoCTaAhLBHk7TXc5DGif93VikW4s,6977
 magic_pdf/model/magic_model.py,sha256=RKJOruUGAV1lHcGqSlCDbkJn5kutb3fphDreOHASPQg,43505
 magic_pdf/model/model_list.py,sha256=tJ9jtMB93HGx8Rmt8wmQSDFXZBUIPQrwaaYsep4luTM,183
-magic_pdf/model/pdf_extract_kit.py,sha256=7BVcVkrIAI2aTAUHD_Xrq0yAuy4BEAAJEicOM8Hr0Xw,21593
-magic_pdf/model/ppTableModel.py,sha256=fqMuMahN2BW4sKGCgFLsi1X1OFaIG8Dab_eHUhKPcH4,2692
+magic_pdf/model/pdf_extract_kit.py,sha256=6y8tQSwse8cAgqjDoJvJ-uSPdT8FYzyUeCW5g7j1Tyw,10126
 magic_pdf/model/pp_structure_v2.py,sha256=BKPN7W4BjG0eWPAPjPEac1RMnb5eIzmAz4E4Rq-9b1U,3019
-magic_pdf/model/pek_sub_modules/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-magic_pdf/model/pek_sub_modules/post_process.py,sha256=HzRxV2sVR3Qo8XKYEHhT6tae-bYTb6dnAfGP6gfVNaM,1135
-magic_pdf/model/pek_sub_modules/self_modify.py,sha256=NGUr8t4bXSeh38hwrfs6qxhf0IW-f3J96bnrg1xw8BA,14281
-magic_pdf/model/pek_sub_modules/layoutlmv3/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-magic_pdf/model/pek_sub_modules/layoutlmv3/backbone.py,sha256=1cvSCczgvwOLdvzWyqttoYPMHsXmnzI3w9abJ1bAXoM,7106
-magic_pdf/model/pek_sub_modules/layoutlmv3/beit.py,sha256=e-INve6bpEx_0FM5wYbQcEcelc79tzDlCljTVHaGt1w,30450
-magic_pdf/model/pek_sub_modules/layoutlmv3/deit.py,sha256=Qyn5UWutZ-0GJczexCh-oMMSXtav_g3ovumMFJp8Om4,17000
-magic_pdf/model/pek_sub_modules/layoutlmv3/model_init.py,sha256=PhWqqRwgSSmXTaUlLIjGqnBUNjzxwYDKgMzKjnxNy1k,4528
-magic_pdf/model/pek_sub_modules/layoutlmv3/rcnn_vl.py,sha256=nI4G6AeLRmjavNhs5S2USKh0ozn-ftMuW0F0m_eVy3c,6649
-magic_pdf/model/pek_sub_modules/layoutlmv3/visualizer.py,sha256=H6UYeCCbaN2gbDjGthTkKkPoyWxfE3azRjsR7fVBwnw,49797
-magic_pdf/model/pek_sub_modules/layoutlmv3/layoutlmft/__init__.py,sha256=C4N9gXJr7is7uznvQefQ7dOhlzEhdp86Lgh-7p0Y-08,186
-magic_pdf/model/pek_sub_modules/layoutlmv3/layoutlmft/data/__init__.py,sha256=W7V62JOh12NdMZj2H1sde3Il0AqW2VKplmHEsLle6tg,76
-magic_pdf/model/pek_sub_modules/layoutlmv3/layoutlmft/data/cord.py,sha256=jR_lRZxy8SeEvTK3FdlXmQHF0kefJf7ZqwM_8pvyI5E,8153
-magic_pdf/model/pek_sub_modules/layoutlmv3/layoutlmft/data/data_collator.py,sha256=M2TE47BprHSuQJYcoMeWOSpqkr_nh8VK6t2l26XWmxg,6279
-magic_pdf/model/pek_sub_modules/layoutlmv3/layoutlmft/data/funsd.py,sha256=Ez9tMeruHncJlkKQ7iRGBB9Pk1uWtgxlGeqs-sOmIG0,5214
-magic_pdf/model/pek_sub_modules/layoutlmv3/layoutlmft/data/image_utils.py,sha256=vuNOMzYw_h7jmaD2XUqkGlrjDEPB7XUts16GRICBmG4,10334
-magic_pdf/model/pek_sub_modules/layoutlmv3/layoutlmft/data/xfund.py,sha256=6jLKyc_4VhbHY4YEzBXm5RkPdsd9ldnUGXFZBLiJ-_s,8270
-magic_pdf/model/pek_sub_modules/layoutlmv3/layoutlmft/models/__init__.py,sha256=d5bm3Rx-jTrgfJDWrzD7t5R5CdHfug9dCNvUEneIYW4,190
-magic_pdf/model/pek_sub_modules/layoutlmv3/layoutlmft/models/layoutlmv3/__init__.py,sha256=a04w_C0B4P9jF-3I_tXCj3fLmfFQR5XSKGbhgGm--pM,1216
-magic_pdf/model/pek_sub_modules/layoutlmv3/layoutlmft/models/layoutlmv3/configuration_layoutlmv3.py,sha256=CJBcAmmLeRFVMN1YjWefoUW7hk0KXek0Eb_tergKl4Y,2150
-magic_pdf/model/pek_sub_modules/layoutlmv3/layoutlmft/models/layoutlmv3/modeling_layoutlmv3.py,sha256=mdo8tO-DrJcv0Lbk9Pp98n3NQXYOnFFyXQWjU7t35kA,54633
-magic_pdf/model/pek_sub_modules/layoutlmv3/layoutlmft/models/layoutlmv3/tokenization_layoutlmv3.py,sha256=diKlrfxYjKAmYrUgjYdx-FXLh-swShC3tl-EBX1b3oI,1197
-magic_pdf/model/pek_sub_modules/layoutlmv3/layoutlmft/models/layoutlmv3/tokenization_layoutlmv3_fast.py,sha256=0lxiG69_fGpSSBYA9CBLnDa_qqa1rInZ0pJpqBwZ0Yw,1372
-magic_pdf/model/pek_sub_modules/structeqtable/StructTableModel.py,sha256=qQthlYDvDPah1mzzrnKXU4fYqlJdXOPBnJ8tYf-o_0k,1384
-magic_pdf/model/pek_sub_modules/structeqtable/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-magic_pdf/model/v3/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-magic_pdf/model/v3/helpers.py,sha256=IVUFcNMDF3-kio-BIxjppHnWS3eHPqvvNihIw2fbIFM,4372
+magic_pdf/model/sub_modules/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+magic_pdf/model/sub_modules/model_init.py,sha256=iFugp79H_QLi-P7t_6Ug0qIs2oOc4zSnf-8hhZhezHA,5021
+magic_pdf/model/sub_modules/model_utils.py,sha256=ToiuwXbrvH_CPIwW2AXzz9miadUN5FA7lthwBljtIco,2118
+magic_pdf/model/sub_modules/layout/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+magic_pdf/model/sub_modules/layout/doclayout_yolo/DocLayoutYOLO.py,sha256=roe6Rth6cvBrCw0MWXcj1CBjvK3S_Ni7GC4DxY4-yBQ,886
+magic_pdf/model/sub_modules/layout/doclayout_yolo/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+magic_pdf/model/sub_modules/layout/layoutlmv3/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+magic_pdf/model/sub_modules/layout/layoutlmv3/backbone.py,sha256=1cvSCczgvwOLdvzWyqttoYPMHsXmnzI3w9abJ1bAXoM,7106
+magic_pdf/model/sub_modules/layout/layoutlmv3/beit.py,sha256=e-INve6bpEx_0FM5wYbQcEcelc79tzDlCljTVHaGt1w,30450
+magic_pdf/model/sub_modules/layout/layoutlmv3/deit.py,sha256=Qyn5UWutZ-0GJczexCh-oMMSXtav_g3ovumMFJp8Om4,17000
+magic_pdf/model/sub_modules/layout/layoutlmv3/model_init.py,sha256=PhWqqRwgSSmXTaUlLIjGqnBUNjzxwYDKgMzKjnxNy1k,4528
+magic_pdf/model/sub_modules/layout/layoutlmv3/rcnn_vl.py,sha256=nI4G6AeLRmjavNhs5S2USKh0ozn-ftMuW0F0m_eVy3c,6649
+magic_pdf/model/sub_modules/layout/layoutlmv3/visualizer.py,sha256=H6UYeCCbaN2gbDjGthTkKkPoyWxfE3azRjsR7fVBwnw,49797
+magic_pdf/model/sub_modules/layout/layoutlmv3/layoutlmft/__init__.py,sha256=C4N9gXJr7is7uznvQefQ7dOhlzEhdp86Lgh-7p0Y-08,186
+magic_pdf/model/sub_modules/layout/layoutlmv3/layoutlmft/data/__init__.py,sha256=W7V62JOh12NdMZj2H1sde3Il0AqW2VKplmHEsLle6tg,76
+magic_pdf/model/sub_modules/layout/layoutlmv3/layoutlmft/data/cord.py,sha256=jR_lRZxy8SeEvTK3FdlXmQHF0kefJf7ZqwM_8pvyI5E,8153
+magic_pdf/model/sub_modules/layout/layoutlmv3/layoutlmft/data/data_collator.py,sha256=M2TE47BprHSuQJYcoMeWOSpqkr_nh8VK6t2l26XWmxg,6279
+magic_pdf/model/sub_modules/layout/layoutlmv3/layoutlmft/data/funsd.py,sha256=Ez9tMeruHncJlkKQ7iRGBB9Pk1uWtgxlGeqs-sOmIG0,5214
+magic_pdf/model/sub_modules/layout/layoutlmv3/layoutlmft/data/image_utils.py,sha256=vuNOMzYw_h7jmaD2XUqkGlrjDEPB7XUts16GRICBmG4,10334
+magic_pdf/model/sub_modules/layout/layoutlmv3/layoutlmft/data/xfund.py,sha256=6jLKyc_4VhbHY4YEzBXm5RkPdsd9ldnUGXFZBLiJ-_s,8270
+magic_pdf/model/sub_modules/layout/layoutlmv3/layoutlmft/models/__init__.py,sha256=d5bm3Rx-jTrgfJDWrzD7t5R5CdHfug9dCNvUEneIYW4,190
+magic_pdf/model/sub_modules/layout/layoutlmv3/layoutlmft/models/layoutlmv3/__init__.py,sha256=a04w_C0B4P9jF-3I_tXCj3fLmfFQR5XSKGbhgGm--pM,1216
+magic_pdf/model/sub_modules/layout/layoutlmv3/layoutlmft/models/layoutlmv3/configuration_layoutlmv3.py,sha256=CJBcAmmLeRFVMN1YjWefoUW7hk0KXek0Eb_tergKl4Y,2150
+magic_pdf/model/sub_modules/layout/layoutlmv3/layoutlmft/models/layoutlmv3/modeling_layoutlmv3.py,sha256=mdo8tO-DrJcv0Lbk9Pp98n3NQXYOnFFyXQWjU7t35kA,54633
+magic_pdf/model/sub_modules/layout/layoutlmv3/layoutlmft/models/layoutlmv3/tokenization_layoutlmv3.py,sha256=diKlrfxYjKAmYrUgjYdx-FXLh-swShC3tl-EBX1b3oI,1197
+magic_pdf/model/sub_modules/layout/layoutlmv3/layoutlmft/models/layoutlmv3/tokenization_layoutlmv3_fast.py,sha256=0lxiG69_fGpSSBYA9CBLnDa_qqa1rInZ0pJpqBwZ0Yw,1372
+magic_pdf/model/sub_modules/mfd/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+magic_pdf/model/sub_modules/mfd/yolov8/YOLOv8.py,sha256=A0eABWvJLyRH6kENWU31g66D2QQos12S0hEmbOuoB0g,347
+magic_pdf/model/sub_modules/mfd/yolov8/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+magic_pdf/model/sub_modules/mfr/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+magic_pdf/model/sub_modules/mfr/unimernet/Unimernet.py,sha256=jeJkqID6L1ZivPMdK1PgpFrE0RcmCRl19oXbudxwgXc,3528
+magic_pdf/model/sub_modules/mfr/unimernet/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+magic_pdf/model/sub_modules/ocr/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+magic_pdf/model/sub_modules/ocr/paddleocr/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+magic_pdf/model/sub_modules/ocr/paddleocr/ocr_utils.py,sha256=2QAxxs0awZ_osLMiL-oP8Ik6VQ3f2C4dgJ0EV93bxlQ,9202
+magic_pdf/model/sub_modules/ocr/paddleocr/ppocr_273_mod.py,sha256=BZ7wtkYvvcKtv8jUOI1n6wsSramt-Ob5faP7UeqrfCU,6710
+magic_pdf/model/sub_modules/ocr/paddleocr/ppocr_291_mod.py,sha256=VouMTvi6M5TV6pQdlpusgfyZapxiZ_Wi7Ff53eMC3rE,8996
+magic_pdf/model/sub_modules/reading_oreder/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+magic_pdf/model/sub_modules/reading_oreder/layoutreader/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+magic_pdf/model/sub_modules/reading_oreder/layoutreader/helpers.py,sha256=IVUFcNMDF3-kio-BIxjppHnWS3eHPqvvNihIw2fbIFM,4372
+magic_pdf/model/sub_modules/reading_oreder/layoutreader/xycut.py,sha256=ezNSq_Y4UXiztB58hbXJsjTJlOBqWIjuW5A2uLSaZSo,7349
+magic_pdf/model/sub_modules/table/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+magic_pdf/model/sub_modules/table/table_utils.py,sha256=B9BC4f5EEjlt2ldYxrIC8Wic2Tz3t3gTJeEyK3ggrOU,282
+magic_pdf/model/sub_modules/table/rapidtable/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+magic_pdf/model/sub_modules/table/rapidtable/rapid_table.py,sha256=UT__wzKQ4tVxlxgFacDqJfTyBU911CTJXD_6CTw6iS8,516
+magic_pdf/model/sub_modules/table/structeqtable/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+magic_pdf/model/sub_modules/table/structeqtable/struct_eqtable.py,sha256=SrNPm-uOFEvN5muFGbXTAuwzXm-rCiaihVdqbydIBIA,1131
+magic_pdf/model/sub_modules/table/tablemaster/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+magic_pdf/model/sub_modules/table/tablemaster/tablemaster_paddle.py,sha256=keSvrxuTVqc8PbNenwb43VDhJqqzp0ayxK691kxClac,2702
 magic_pdf/para/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 magic_pdf/para/block_continuation_processor.py,sha256=IkReB5hirjm0OAirNzQQpnWe2f2bdP3Hug3Ef8qTRDA,22749
 magic_pdf/para/block_termination_processor.py,sha256=YU3ZYqJy9e3OQmOuQYZrR6AUpmAlQ0mhj0PgZZPZ_fM,17957
@@ -112,7 +133,7 @@ magic_pdf/para/layout_match_processor.py,sha256=yr4FEO7GJ502udShqGRqIJQ_FQxoa0aG
 magic_pdf/para/para_pipeline.py,sha256=zLaCHI9jLi1UPzh0lHP44mUjpKVTHS0gE_5YrkjVqEY,11796
 magic_pdf/para/para_split.py,sha256=-UJM2jREW_2h3ZlJAU7dRD8bK3CMGKuhJrfgqv3Auvk,31310
 magic_pdf/para/para_split_v2.py,sha256=ZIiLzpvVL364x1zcEG9IbT6ARJ-6JnWLIVrsDmf4w1M,36878
-magic_pdf/para/para_split_v3.py,sha256=k02I9Rdc8jfYr3bMT_Gm38b5ginkl-ZIU5C_XcfAcs8,14704
+magic_pdf/para/para_split_v3.py,sha256=vSJ5_QqGKP1rbTbGQg5ONNpybidpTdbgXZgTGd2bGsw,14539
 magic_pdf/para/raw_processor.py,sha256=mHxD9FrdOSXH7NqM41s55URyCyuyACvm9kKtowkIb3k,6317
 magic_pdf/para/stats.py,sha256=-6Pf9Y8jkP1uJOYWiHUjw9Lb-Fb9GY7MHr_ok7x2GX0,9731
 magic_pdf/para/title_processor.py,sha256=pYZv9vEkIjAtCz8jIUtl9AVUy_ib5SdAZmMVoZtsMRI,38593
@@ -155,7 +176,7 @@ magic_pdf/pre_proc/resolve_bbox_conflict.py,sha256=bJiegofPUeDyi--oZjfipQ5Q5RLm6
 magic_pdf/pre_proc/solve_line_alien.py,sha256=aNoQptPcC38Sm1I2ABhgw8jeH_5kjsRHx3VYlFFtm1g,853
 magic_pdf/pre_proc/statistics.py,sha256=_9jGlXq0iXd03UMxB92ZqCiu7cjNkG5vHvFlTF_9ytA,220
 magic_pdf/resources/fasttext-langdetect/lid.176.ftz,sha256=jzRyz-hzintgmejpmcPL-uDc0VaWqsfXc4qAOdtgPoM,938013
-magic_pdf/resources/model_config/model_configs.yaml,sha256=muwPuO6C8Z5oEStE-wWEt7vmkenmJiqTbkRfUfle_vU,257
+magic_pdf/resources/model_config/model_configs.yaml,sha256=S2BnVQxPd0xsZswn9WqJKTfnqd7ayY5lRwDVifTEAfw,290
 magic_pdf/resources/model_config/UniMERNet/demo.yaml,sha256=Jdaim2D2lAYrV9rhc1X5Sy2_IacGOrfysJhxEUgSElo,827
 magic_pdf/resources/model_config/layoutlmv3/layoutlmv3_base_inference.yaml,sha256=9aNAEYgpHTAWpcUrDvuPG2y4V-Qw8QdcJefi96y8yDU,6109
 magic_pdf/rw/AbsReaderWriter.py,sha256=2H5SDJfAAOX9kPfel06a8VRCHxD1Y8aPbWEkQDdn9JM,452
@@ -167,12 +188,12 @@ magic_pdf/spark/spark_api.py,sha256=eSLXTjMYW5Ya41VMIApRVfji1ZxEZXdH9ZdsL6fy5Kw,
 magic_pdf/tools/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 magic_pdf/tools/cli.py,sha256=yl2E-DYxBN3XF7bWOBseYxptbmeE7tXWpwV-sp2aGIE,3140
 magic_pdf/tools/cli_dev.py,sha256=3e5eyCQEt_EujXZu5fUAWr_W-YQQVqS9pB0Qgw7t1D8,4122
-magic_pdf/tools/common.py,sha256=2S8N60pcA6bFqAmdchoEmn22l9ntQxEfyaKpxfCKJ-Y,5465
+magic_pdf/tools/common.py,sha256=oo6DsbriyQv0azRNZSt4B-13eXvsMsPgE_kwgO0-aM8,7364
 magic_pdf/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 magic_pdf/utils/annotations.py,sha256=82ou3uELNbQWa9hOFFkVt0gsIskAKf5msCv5J2IJ5V0,211
-magic_pdf-0.9.1.dist-info/LICENSE.md,sha256=jVa0BUaKrRH4erV2P5AeJ24I2WRv9chIGxditreJ6e0,34524
-magic_pdf-0.9.1.dist-info/METADATA,sha256=2NLbuQt-GzeMws3412i4A8XaDr8xuMZBymu7n3XY7S0,39624
-magic_pdf-0.9.1.dist-info/WHEEL,sha256=eOLhNAGa2EW3wWl_TU484h7q1UNgy0JXjjoqKoxAAQc,92
-magic_pdf-0.9.1.dist-info/entry_points.txt,sha256=wXwYke3j8fqDQTocUspL-CqDUEv3Tfcwp09fM8dZAhA,98
-magic_pdf-0.9.1.dist-info/top_level.txt,sha256=J9I0AzmHWGkp9c6DL8Oe4mEx3yYphLzkRn4H25Lg1rE,10
-magic_pdf-0.9.1.dist-info/RECORD,,
+magic_pdf-0.9.3.dist-info/LICENSE.md,sha256=jVa0BUaKrRH4erV2P5AeJ24I2WRv9chIGxditreJ6e0,34524
+magic_pdf-0.9.3.dist-info/METADATA,sha256=IpWvg-cnoZ9euLIh_3PYmPGh-DCQ8n8Lp2Ar4oyUfuc,40128
+magic_pdf-0.9.3.dist-info/WHEEL,sha256=bFJAMchF8aTQGUgMZzHJyDDMPTO3ToJ7x23SLJa1SVo,92
+magic_pdf-0.9.3.dist-info/entry_points.txt,sha256=wXwYke3j8fqDQTocUspL-CqDUEv3Tfcwp09fM8dZAhA,98
+magic_pdf-0.9.3.dist-info/top_level.txt,sha256=J9I0AzmHWGkp9c6DL8Oe4mEx3yYphLzkRn4H25Lg1rE,10
+magic_pdf-0.9.3.dist-info/RECORD,,

{magic_pdf-0.9.1.dist-info → magic_pdf-0.9.3.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: bdist_wheel (0.44.0)
+Generator: bdist_wheel (0.45.0)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

magic_pdf/model/pek_sub_modules/post_process.py

@@ -1,36 +0,0 @@
-import re
-
-def layout_rm_equation(layout_res):
-    rm_idxs = []
-    for idx, ele in enumerate(layout_res['layout_dets']):
-        if ele['category_id'] == 10:
-            rm_idxs.append(idx)
-    
-    for idx in rm_idxs[::-1]:
-        del layout_res['layout_dets'][idx]
-    return layout_res
-
-
-def get_croped_image(image_pil, bbox):
-    x_min, y_min, x_max, y_max = bbox
-    croped_img = image_pil.crop((x_min, y_min, x_max, y_max))
-    return croped_img
-
-
-def latex_rm_whitespace(s: str):
-    """Remove unnecessary whitespace from LaTeX code.
-    """
-    text_reg = r'(\\(operatorname|mathrm|text|mathbf)\s?\*? {.*?})'
-    letter = '[a-zA-Z]'
-    noletter = '[\W_^\d]'
-    names = [x[0].replace(' ', '') for x in re.findall(text_reg, s)]
-    s = re.sub(text_reg, lambda match: str(names.pop(0)), s)
-    news = s
-    while True:
-        s = news
-        news = re.sub(r'(?!\\ )(%s)\s+?(%s)' % (noletter, noletter), r'\1\2', s)
-        news = re.sub(r'(?!\\ )(%s)\s+?(%s)' % (noletter, letter), r'\1\2', news)
-        news = re.sub(r'(%s)\s+?(%s)' % (letter, noletter), r'\1\2', news)
-        if news == s:
-            break
-    return s