magic-pdf 0.9.2__py3-none-any.whl → 0.10.0__py3-none-any.whl

magic_pdf/tools/common.py

@@ -3,17 +3,20 @@ import json as json_parse
 import os
 
 import click
+import fitz
 from loguru import logger
 
 import magic_pdf.model as model_config
+from magic_pdf.config.make_content_config import DropMode, MakeMode
+from magic_pdf.data.data_reader_writer import FileBasedDataWriter
 from magic_pdf.libs.draw_bbox import (draw_layout_bbox, draw_line_sort_bbox,
                                       draw_model_bbox, draw_span_bbox)
-from magic_pdf.libs.MakeContentConfig import DropMode, MakeMode
 from magic_pdf.pipe.OCRPipe import OCRPipe
 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
+
+# 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,
@@ -55,26 +94,34 @@ def do_parse(
         f_draw_model_bbox = True
         f_draw_line_sort_bbox = True
 
+    if lang == "":
+        lang = None
+
+    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)
 
-    image_writer, md_writer = DiskReaderWriter(
-        local_image_dir), DiskReaderWriter(local_md_dir)
+    image_writer, md_writer = FileBasedDataWriter(
+        local_image_dir), FileBasedDataWriter(local_md_dir)
     image_dir = str(os.path.basename(local_image_dir))
 
     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')
@@ -101,49 +148,36 @@ def do_parse(
     if f_draw_line_sort_bbox:
         draw_line_sort_bbox(pdf_info, pdf_bytes, local_md_dir, pdf_file_name)
 
-    md_content = pipe.pipe_mk_markdown(image_dir,
-                                       drop_mode=DropMode.NONE,
-                                       md_make_mode=f_make_md_mode)
+    md_content = pipe.pipe_mk_markdown(image_dir, drop_mode=DropMode.NONE, md_make_mode=f_make_md_mode)
     if f_dump_md:
-        md_writer.write(
-            content=md_content,
-            path=f'{pdf_file_name}.md',
-            mode=AbsReaderWriter.MODE_TXT,
+        md_writer.write_string(
+            f'{pdf_file_name}.md',
+            md_content
         )
 
     if f_dump_middle_json:
-        md_writer.write(
-            content=json_parse.dumps(pipe.pdf_mid_data,
-                                     ensure_ascii=False,
-                                     indent=4),
-            path=f'{pdf_file_name}_middle.json',
-            mode=AbsReaderWriter.MODE_TXT,
+        md_writer.write_string(
+            f'{pdf_file_name}_middle.json',
+            json_parse.dumps(pipe.pdf_mid_data, ensure_ascii=False, indent=4)
         )
 
     if f_dump_model_json:
-        md_writer.write(
-            content=json_parse.dumps(orig_model_list,
-                                     ensure_ascii=False,
-                                     indent=4),
-            path=f'{pdf_file_name}_model.json',
-            mode=AbsReaderWriter.MODE_TXT,
+        md_writer.write_string(
+            f'{pdf_file_name}_model.json',
+            json_parse.dumps(orig_model_list, ensure_ascii=False, indent=4)
         )
 
     if f_dump_orig_pdf:
         md_writer.write(
-            content=pdf_bytes,
-            path=f'{pdf_file_name}_origin.pdf',
-            mode=AbsReaderWriter.MODE_BIN,
+            f'{pdf_file_name}_origin.pdf',
+            pdf_bytes,
         )
 
     content_list = pipe.pipe_mk_uni_format(image_dir, drop_mode=DropMode.NONE)
     if f_dump_content_list:
-        md_writer.write(
-            content=json_parse.dumps(content_list,
-                                     ensure_ascii=False,
-                                     indent=4),
-            path=f'{pdf_file_name}_content_list.json',
-            mode=AbsReaderWriter.MODE_TXT,
+        md_writer.write_string(
+            f'{pdf_file_name}_content_list.json',
+            json_parse.dumps(content_list, ensure_ascii=False, indent=4)
         )
 
     logger.info(f'local output dir is {local_md_dir}')

magic_pdf/user_api.py

@@ -1,36 +1,28 @@
-"""
-用户输入：
-    model数组，每个元素代表一个页面
-    pdf在s3的路径
-    截图保存的s3位置
+"""用户输入： model数组，每个元素代表一个页面 pdf在s3的路径 截图保存的s3位置.
 
 然后：
     1）根据s3路径，调用spark集群的api,拿到ak,sk,endpoint，构造出s3PDFReader
     2）根据用户输入的s3地址，调用spark集群的api,拿到ak,sk,endpoint，构造出s3ImageWriter
 
 其余部分至于构造s3cli, 获取ak,sk都在code-clean里写代码完成。不要反向依赖！！！
-
 """
-import re
 
 from loguru import logger
 
+from magic_pdf.data.data_reader_writer import DataWriter
 from magic_pdf.libs.version import __version__
 from magic_pdf.model.doc_analyze_by_custom_model import doc_analyze
-from magic_pdf.rw import AbsReaderWriter
 from magic_pdf.pdf_parse_by_ocr import parse_pdf_by_ocr
 from magic_pdf.pdf_parse_by_txt import parse_pdf_by_txt
 
-PARSE_TYPE_TXT = "txt"
-PARSE_TYPE_OCR = "ocr"
+PARSE_TYPE_TXT = 'txt'
+PARSE_TYPE_OCR = 'ocr'
 
 
-def parse_txt_pdf(pdf_bytes: bytes, pdf_models: list, imageWriter: AbsReaderWriter, is_debug=False,
+def parse_txt_pdf(pdf_bytes: bytes, pdf_models: list, imageWriter: DataWriter, is_debug=False,
                   start_page_id=0, end_page_id=None, lang=None,
                   *args, **kwargs):
-    """
-    解析文本类pdf
-    """
+    """解析文本类pdf."""
     pdf_info_dict = parse_pdf_by_txt(
         pdf_bytes,
         pdf_models,
@@ -38,24 +30,23 @@ def parse_txt_pdf(pdf_bytes: bytes, pdf_models: list, imageWriter: AbsReaderWrit
         start_page_id=start_page_id,
         end_page_id=end_page_id,
         debug_mode=is_debug,
+        lang=lang,
     )
 
-    pdf_info_dict["_parse_type"] = PARSE_TYPE_TXT
+    pdf_info_dict['_parse_type'] = PARSE_TYPE_TXT
 
-    pdf_info_dict["_version_name"] = __version__
+    pdf_info_dict['_version_name'] = __version__
 
     if lang is not None:
-        pdf_info_dict["_lang"] = lang
+        pdf_info_dict['_lang'] = lang
 
     return pdf_info_dict
 
 
-def parse_ocr_pdf(pdf_bytes: bytes, pdf_models: list, imageWriter: AbsReaderWriter, is_debug=False,
+def parse_ocr_pdf(pdf_bytes: bytes, pdf_models: list, imageWriter: DataWriter, is_debug=False,
                   start_page_id=0, end_page_id=None, lang=None,
                   *args, **kwargs):
-    """
-    解析ocr类pdf
-    """
+    """解析ocr类pdf."""
     pdf_info_dict = parse_pdf_by_ocr(
         pdf_bytes,
         pdf_models,
@@ -63,25 +54,24 @@ def parse_ocr_pdf(pdf_bytes: bytes, pdf_models: list, imageWriter: AbsReaderWrit
         start_page_id=start_page_id,
         end_page_id=end_page_id,
         debug_mode=is_debug,
+        lang=lang,
     )
 
-    pdf_info_dict["_parse_type"] = PARSE_TYPE_OCR
+    pdf_info_dict['_parse_type'] = PARSE_TYPE_OCR
 
-    pdf_info_dict["_version_name"] = __version__
+    pdf_info_dict['_version_name'] = __version__
 
     if lang is not None:
-        pdf_info_dict["_lang"] = lang
+        pdf_info_dict['_lang'] = lang
 
     return pdf_info_dict
 
 
-def parse_union_pdf(pdf_bytes: bytes, pdf_models: list, imageWriter: AbsReaderWriter, is_debug=False,
+def parse_union_pdf(pdf_bytes: bytes, pdf_models: list, imageWriter: DataWriter, is_debug=False,
                     input_model_is_empty: bool = False,
                     start_page_id=0, end_page_id=None, lang=None,
                     *args, **kwargs):
-    """
-    ocr和文本混合的pdf，全部解析出来
-    """
+    """ocr和文本混合的pdf，全部解析出来."""
 
     def parse_pdf(method):
         try:
@@ -92,18 +82,19 @@ def parse_union_pdf(pdf_bytes: bytes, pdf_models: list, imageWriter: AbsReaderWr
                 start_page_id=start_page_id,
                 end_page_id=end_page_id,
                 debug_mode=is_debug,
+                lang=lang,
             )
         except Exception as e:
             logger.exception(e)
             return None
 
     pdf_info_dict = parse_pdf(parse_pdf_by_txt)
-    if pdf_info_dict is None or pdf_info_dict.get("_need_drop", False):
-        logger.warning(f"parse_pdf_by_txt drop or error, switch to parse_pdf_by_ocr")
+    if pdf_info_dict is None or pdf_info_dict.get('_need_drop', False):
+        logger.warning('parse_pdf_by_txt drop or error, switch to parse_pdf_by_ocr')
         if input_model_is_empty:
-            layout_model = kwargs.get("layout_model", None)
-            formula_enable = kwargs.get("formula_enable", None)
-            table_enable = kwargs.get("table_enable", None)
+            layout_model = kwargs.get('layout_model', None)
+            formula_enable = kwargs.get('formula_enable', None)
+            table_enable = kwargs.get('table_enable', None)
             pdf_models = doc_analyze(
                 pdf_bytes,
                 ocr=True,
@@ -116,15 +107,15 @@ def parse_union_pdf(pdf_bytes: bytes, pdf_models: list, imageWriter: AbsReaderWr
             )
         pdf_info_dict = parse_pdf(parse_pdf_by_ocr)
         if pdf_info_dict is None:
-            raise Exception("Both parse_pdf_by_txt and parse_pdf_by_ocr failed.")
+            raise Exception('Both parse_pdf_by_txt and parse_pdf_by_ocr failed.')
         else:
-            pdf_info_dict["_parse_type"] = PARSE_TYPE_OCR
+            pdf_info_dict['_parse_type'] = PARSE_TYPE_OCR
     else:
-        pdf_info_dict["_parse_type"] = PARSE_TYPE_TXT
+        pdf_info_dict['_parse_type'] = PARSE_TYPE_TXT
 
-    pdf_info_dict["_version_name"] = __version__
+    pdf_info_dict['_version_name'] = __version__
 
     if lang is not None:
-        pdf_info_dict["_lang"] = lang
+        pdf_info_dict['_lang'] = lang
 
     return pdf_info_dict

{magic_pdf-0.9.2.dist-info → magic_pdf-0.10.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: magic-pdf
-Version: 0.9.2
+Version: 0.10.0
 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"
@@ -35,6 +38,8 @@ Provides-Extra: lite
 Requires-Dist: paddleocr==2.7.3; extra == "lite"
 Requires-Dist: paddlepaddle==3.0.0b1; platform_system == "Linux" and extra == "lite"
 Requires-Dist: paddlepaddle==2.6.1; (platform_system == "Windows" or platform_system == "Darwin") and extra == "lite"
+Provides-Extra: old_linux
+Requires-Dist: albumentations<=1.4.20; extra == "old-linux"
 
 <div align="center" xmlns="http://www.w3.org/1999/html">
 <!-- logo -->
@@ -80,6 +85,10 @@ Requires-Dist: paddlepaddle==2.6.1; (platform_system == "Windows" or platform_sy
 </div>
 
 # Changelog
+- 2024/11/22 0.10.0 released. Introducing hybrid OCR text extraction capabilities,
+  - Significantly improved parsing performance in complex text distribution scenarios such as dense formulas, irregular span regions, and text represented by images.
+  - Combines the dual advantages of accurate content extraction and faster speed in text mode, and more precise span/line region recognition in OCR mode.
+- 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.
@@ -158,7 +167,7 @@ https://github.com/user-attachments/assets/4bea02c9-6d54-4cd6-97ed-dff14340982c
 - Preserve the structure of the original document, including headings, paragraphs, lists, etc.
 - Extract images, image descriptions, tables, table titles, and footnotes.
 - Automatically recognize and convert formulas in the document to LaTeX format.
-- Automatically recognize and convert tables in the document to LaTeX or HTML format.
+- Automatically recognize and convert tables in the document to HTML format.
 - Automatically detect scanned PDFs and garbled PDFs and enable OCR functionality.
 - OCR supports detection and recognition of 84 languages.
 - Supports multiple output formats, such as multimodal and NLP Markdown, JSON sorted by reading order, and rich intermediate formats.
@@ -222,17 +231,11 @@ There are three different ways to experience MinerU:
     </tr>
     <tr>
         <td rowspan="2">GPU Hardware Support List</td>
-        <td colspan="2">Minimum Requirement 8G+ VRAM</td>
-        <td colspan="2">3060ti/3070/4060<br>
-        8G VRAM enables layout, formula recognition acceleration and OCR acceleration</td>
+        <td colspan="2">GPU VRAM 8GB or more</td>
+        <td colspan="2">2080~2080Ti / 3060Ti~3090Ti / 4060~4090<br>
+        8G VRAM can enable all acceleration features</td>
         <td rowspan="2">None</td>
     </tr>
-    <tr>
-        <td colspan="2">Recommended Configuration 10G+ VRAM</td>
-        <td colspan="2">3080/3080ti/3090/3090ti/4070/4070ti/4070tisuper/4080/4090<br>
-        10G VRAM or more can enable layout, formula recognition, OCR acceleration and table recognition acceleration simultaneously
-        </td>
-    </tr>
 </table>
 
 ### Online Demo
@@ -284,7 +287,7 @@ 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",  // Default to using "rapid_table", can be switched to "tablemaster" or "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
     }
@@ -299,7 +302,7 @@ If your device supports CUDA and meets the GPU requirements of the mainline envi
 - [Windows 10/11 + GPU](docs/README_Windows_CUDA_Acceleration_en_US.md)
 - Quick Deployment with Docker
 > [!IMPORTANT]
-> Docker requires a GPU with at least 16GB of VRAM, and all acceleration features are enabled by default.
+> 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.
 > 
@@ -459,7 +462,9 @@ 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-0.10.0.dist-info/RECORD

@@ -0,0 +1,198 @@
+magic_pdf/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+magic_pdf/pdf_parse_by_ocr.py,sha256=WTaLVSU2wRpgtldasnqbrw1B0OvVi8VvcB_t-dAIfmw,880
+magic_pdf/pdf_parse_by_txt.py,sha256=dh3ZM6BVrFzwbH4137BPUdKhgacGlpS2N4mn74_-UaA,762
+magic_pdf/pdf_parse_union_core.py,sha256=w90lFIMOYUMAq4iv8bpsbBtLXFphPV4HyYeqbOTYQUI,12420
+magic_pdf/pdf_parse_union_core_v2.py,sha256=EqEi9AahBBh2JbXoY8uOCmClvi9W_H_26U4jK8RwPwU,31308
+magic_pdf/user_api.py,sha256=Sh6U7iD5VsH7Qkav_0o5GTx-Rlj7vhmhHQHZSBKR5T8,4006
+magic_pdf/config/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+magic_pdf/config/constants.py,sha256=gqhUEtso7rCop-k-VvEPAMW_6pA6Tv2Y9smrr_0Iajo,1173
+magic_pdf/config/drop_reason.py,sha256=CqjMzBE96Qo8OeFvhhhItY8WhyqsKhE3DmyJLoQZNCc,2248
+magic_pdf/config/drop_tag.py,sha256=CjveyzhAsHm_bfXB7ZZNKruw1NR-WdKD8Hz6OhQdG0A,680
+magic_pdf/config/enums.py,sha256=CImYuw4sbKpq9zrj6zrrEvtdoGkjxDt8S8ByNVDpypU,89
+magic_pdf/config/exceptions.py,sha256=87UX7gyUpj4HqjPcz2hLqdnYeImtDQAxOxj8oXZ_zkE,622
+magic_pdf/config/make_content_config.py,sha256=J2eJIhVHBPGwX18zVQomQUOxs8LcfeGLxLgdBEeRvLg,248
+magic_pdf/config/model_block_type.py,sha256=y5ie2ZLvo-h8OdVk8HOEha6qK0OJFtLmtOhYjrV680g,166
+magic_pdf/config/ocr_content_type.py,sha256=e_7RBTdShaWvWhMO2SFou7GM521elMH_Jtn5usbHWdY,890
+magic_pdf/data/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+magic_pdf/data/dataset.py,sha256=n8rGw1-wizABR8giSk_XWPCXzx3478u5DK2Z0wOCOeI,5089
+magic_pdf/data/read_api.py,sha256=hGpSVg9EcyM2mIlOsDIwsl7Y_ybWf9kkoxRumIXSzQQ,3566
+magic_pdf/data/schemas.py,sha256=oIUTBzK8Wq8Wuy8A_uilWAbVhucRvOs9_f3lSKYgcmQ,664
+magic_pdf/data/utils.py,sha256=dJZiqygwNier0UG5tbt5jAPjgwcnfsAN6-m-G1kVPLQ,917
+magic_pdf/data/data_reader_writer/__init__.py,sha256=QtevUaeSivv9dQKi3Tomfn4Z0E4To0cB8qXTnglxaHc,705
+magic_pdf/data/data_reader_writer/base.py,sha256=gUrHCMTHYBrWpqgHdIc-hN7HHwUC2ApK_VXrDUrnfdg,1320
+magic_pdf/data/data_reader_writer/filebase.py,sha256=21RYy4m9MqJGqwd2HWICQJHM-PZXp7UYETCQQK390Kk,1988
+magic_pdf/data/data_reader_writer/multi_bucket_s3.py,sha256=_HA8NJO1Be7KwozlwOJ90o8Ik2vfjlvlDPXppESeIfk,5885
+magic_pdf/data/data_reader_writer/s3.py,sha256=9Oy1cNuXMwG1e8PgZ7AR-pn_MqHAhkgAGnyEZCYoYAA,2408
+magic_pdf/data/io/__init__.py,sha256=WKaIlu8i5AWYxFCGNJcorAfMnlUQDOF8CX07Ycfnu2c,294
+magic_pdf/data/io/base.py,sha256=SqNQqe30ZvoVvg7GVv-hLMCjN6yBgDyQQWeLgGsTfhQ,1118
+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=bMQK7uiay76YaWA92VIK57YajINV20SnOs65wOEXyKE,18667
+magic_pdf/dict2md/ocr_mkcontent.py,sha256=ohjhEFS9YFrzTCC9c9yrvi4QuZe9iZm1qlkQWB6xxIw,13038
+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=h4D4O0OeAlEy2A8mJ6E0aQ8wIizIfsIxEagbjaomnAo,17823
+magic_pdf/integrations/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+magic_pdf/integrations/rag/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+magic_pdf/integrations/rag/api.py,sha256=t38wvIBzLje4_JzTP3dewMLqV-tQJ-A3B92Sj2oyrfs,2507
+magic_pdf/integrations/rag/type.py,sha256=Z_1g_ZIOCsb7-FmZBudReIXj8nzGrgj_BygCalhJdmk,3193
+magic_pdf/integrations/rag/utils.py,sha256=DCb-UhC8TElb6Eq7_6NmmETreKEk5DVE18hNL8sTEBk,11762
+magic_pdf/layout/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+magic_pdf/layout/bbox_sort.py,sha256=PzzaBf6MC_AZ-ZWGU0Kg-KIsw874l_gML73mM3hE4Ps,30807
+magic_pdf/layout/layout_det_utils.py,sha256=NCYBTvsrULE3Cue53aMD1MfXTmOL9Xy0nivl6ku2cls,9137
+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/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+magic_pdf/libs/boxbase.py,sha256=ELMHWolgWROxOAQDgwmL7VS5kveZp4ifvEzRmPul2Ws,16925
+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=vDsxw2xbW7Gb1mKqERTSlttbXFNtVU0BDdae2dG7wEI,4068
+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=NhAfqib5HYuGjjrAG_SvJR-yOHZTy6tzDxLXdxKlULQ,17676
+magic_pdf/libs/hash_utils.py,sha256=VEKK9WfFoZgrPfi8kfITjLpr8Ahufs8tXh9R1Y5lAL8,404
+magic_pdf/libs/json_compressor.py,sha256=6-KCu0lb5ksmyqWtQGb4QqmP-FjRb5dP7P-Hevcn68g,875
+magic_pdf/libs/language.py,sha256=Hj5-lrGoNExxdHLbkcNG-c27U4AjJ9AZPdZblaNSehU,1099
+magic_pdf/libs/local_math.py,sha256=tqljQOgqh3fZc146HYhO88JXJaiXMVwArBkk_CSGICc,177
+magic_pdf/libs/markdown_utils.py,sha256=cLxLXjRhrNp_wCHvtglrGA_FVdrvfd1KULeTtj1p18w,944
+magic_pdf/libs/nlp_utils.py,sha256=-X9W3-Ns5ZdDYFvyyEq6i6P2b5hCATaFEZeOjwNOH9M,6901
+magic_pdf/libs/path_utils.py,sha256=Hykw_l5CU736b2egHV9P7B-qh3QNKO4nZSGCbsi0Z8E,1043
+magic_pdf/libs/pdf_check.py,sha256=MAe8wzwT0qvPf_I72wEZG7k1g4haNHS7oUtLqkB5rlE,2145
+magic_pdf/libs/pdf_image_tools.py,sha256=sh8hgBQu_83R71qBLodOFdByBUuQujsOMfgpSD9mrhE,1981
+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=v4zmKjsKOPZbp6BrWoz7iK4ST0sdZdUh9bQSJmluZ5o,23
+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=HOT6chGx2VPyH6O9WB0c6xGPeDs9m_6oZn3iOa745yw,7125
+magic_pdf/model/magic_model.py,sha256=8nJLzNCa0Ag4JhMAQbjj5qrkj617qKPCXVJAiT9DnaA,43472
+magic_pdf/model/model_list.py,sha256=tJ9jtMB93HGx8Rmt8wmQSDFXZBUIPQrwaaYsep4luTM,183
+magic_pdf/model/pdf_extract_kit.py,sha256=ceYWlSU1BhakfsHPVM9SrUx35EvCBa20uJmgDO5PAtE,10933
+magic_pdf/model/pp_structure_v2.py,sha256=BKPN7W4BjG0eWPAPjPEac1RMnb5eIzmAz4E4Rq-9b1U,3019
+magic_pdf/model/sub_modules/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+magic_pdf/model/sub_modules/model_init.py,sha256=CnlZLsiSOmGJXQRASH-hMmuPiF6hYKCNfmzDTjQqy5g,5073
+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=UP7fADPGoxAMj2SUKmeW-fe_AcAQxlT9Mfy4WF6vHmU,9796
+magic_pdf/model/sub_modules/ocr/paddleocr/ppocr_273_mod.py,sha256=a6xkQHqLMUL4NCaORp8oo4Tfa8GB8PN9MVvG7Pj6jIE,7316
+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=_FKKOSKeceusx6DCnhqYzP-4b1zSWptrefimxFTmy8Q,583
+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=AdH3UGu4BEoII0uFjPKUf61W7HmG4fDlWgR1xxMeFlE,2775
+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
+magic_pdf/para/commons.py,sha256=VdJ8SY9qJTtcRyx8HH-PFeZSJwL4Tsf50197RD_-dwc,5414
+magic_pdf/para/denoise.py,sha256=J7dM2KNnbdzAd2A3agB04U6L1GL9RrhAs-MLrq-_Ftg,10443
+magic_pdf/para/draw.py,sha256=KyWc03do_WuBKQ028HYzepYwbIkel9ID0uqRhuPVOHc,5643
+magic_pdf/para/exceptions.py,sha256=kpjGxrSZ-drNmoKlmuQ0asTjI8cKKKWsdDDBoDHQP9M,4978
+magic_pdf/para/layout_match_processor.py,sha256=yr4FEO7GJ502udShqGRqIJQ_FQxoa0aG_mhmWd8nLwI,1554
+magic_pdf/para/para_split.py,sha256=z7nYeg86BjZOAdJNMwYKSu51W9evurtl3cy1ZUcQLlw,33222
+magic_pdf/para/para_split_v2.py,sha256=vJJqqMMKbv8D702nODThL-5hjkgZ7Vl2BTmEIdwmmDw,39051
+magic_pdf/para/para_split_v3.py,sha256=atfELVRx-90paAS3nZptgP0qG8UpTTaj3LG_2x3NAlQ,15977
+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
+magic_pdf/pipe/AbsPipe.py,sha256=jPtAa0pz_vPddya3ZpUk6UrGqp8PcBdLONO1spzavQo,4371
+magic_pdf/pipe/OCRPipe.py,sha256=nuN-zpUzu--gyrC0_vsvvilAyK7Mp3Tom_UOnsur1ps,2158
+magic_pdf/pipe/TXTPipe.py,sha256=5OFo2e8U5Y24wJrFDEJghBDpklnKFEnzKTYVnnhQssE,2159
+magic_pdf/pipe/UNIPipe.py,sha256=ik0xXPdsHo7Un0gFpLC5ul04BP3Omd2mp5gqem40deE,4807
+magic_pdf/pipe/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+magic_pdf/post_proc/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+magic_pdf/post_proc/detect_para.py,sha256=5LX86ueHQGOV9CNimAxqZH4R3KTi78leum1de_Na0pw,126181
+magic_pdf/post_proc/pdf_post_filter.py,sha256=3EJDovQPckPKJaBY1wvAty-LGKyRG63WICY_bA_Kfbs,2501
+magic_pdf/post_proc/remove_footnote.py,sha256=701P7xRu6gzLaEHfb2xkYpLZI4CwK2FAo7Ggho4bOTI,7596
+magic_pdf/pre_proc/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+magic_pdf/pre_proc/citationmarker_remove.py,sha256=IitOERaK9fGaktsYMyiaaL_71uMIrlG5ZdmpZaR6dsA,6640
+magic_pdf/pre_proc/construct_page_dict.py,sha256=lp3zBmInlWYYIcGC1-NSqT9s44AjDvlnWxDPeZoBVSY,3043
+magic_pdf/pre_proc/cut_image.py,sha256=TghshkDTgdUbyLSbKZoFI9-n-xaFub02IYPyu0IAnRY,2761
+magic_pdf/pre_proc/detect_equation.py,sha256=9omDHKTI8QO9Qd46eVFHWhZeMmTNx7XDuWRgjXI-KFA,6627
+magic_pdf/pre_proc/detect_footer_by_model.py,sha256=_EghAM_zWBcqVY8XBkbSoprKqKUa0mlN1U8YNWxNNLI,2848
+magic_pdf/pre_proc/detect_footer_header_by_statistics.py,sha256=924soXZ51QVpitPgVgnwbC7BqOZI30j5hGW5zP86y-w,11250
+magic_pdf/pre_proc/detect_footnote.py,sha256=UxFuTCRwXdAv3wKCgRQJJVt12hM9O9oPTwzPAChQXoM,8309
+magic_pdf/pre_proc/detect_header.py,sha256=KOmRehgKMuMqNa_2weXkdNSiRVWMFgLMQE4e1itbY7g,2848
+magic_pdf/pre_proc/detect_images.py,sha256=8DwGGTb5IjxqADZDTc_ngwJrTYXxK2qpRqI2FBoPr00,30432
+magic_pdf/pre_proc/detect_page_number.py,sha256=qvYrBbCtBbREvw-MySL_p7byCRvcm1fkLJ5ZB4TP8OM,2848
+magic_pdf/pre_proc/detect_tables.py,sha256=srJzgLVeVuOsqnESqfdJfVukTF84K8qmI5mgFX_BZGs,2800
+magic_pdf/pre_proc/equations_replace.py,sha256=7mexRPwD9C_UJ-SbvO_-XnpcnN7YtGUUznmPjHbjhnw,20526
+magic_pdf/pre_proc/fix_image.py,sha256=5MOfkXc8abfIp49g-68vll40wwTUZ5tcQ2gtsJuFmvs,11486
+magic_pdf/pre_proc/fix_table.py,sha256=20sqJe27fAXcL7_C0qQ9mpsggmH37WuX-wPYWyRgACA,13227
+magic_pdf/pre_proc/main_text_font.py,sha256=1gkjvPuBdKC4oVFkLvnRm2zghsLtVlfAEMKXouyVonM,1048
+magic_pdf/pre_proc/ocr_detect_all_bboxes.py,sha256=DMc2H2xGqVePBReZu5AQbPdvDw3sxOssmujCLlNW3Vs,14143
+magic_pdf/pre_proc/ocr_detect_layout.py,sha256=DW0_HXzmcbW22cXKIYFsyZNFh8mEjSHXIFVjXndJsvQ,5878
+magic_pdf/pre_proc/ocr_dict_merge.py,sha256=Au8y1NBhbWpq_VuPLg3b9dAMUhyPS71xtTghtd21K5M,14273
+magic_pdf/pre_proc/ocr_span_list_modify.py,sha256=9DxEyy1pH87g4T_JEgI3cTVCL2TVrEBl38wsmqhQM4k,12758
+magic_pdf/pre_proc/pdf_pre_filter.py,sha256=qvNlNyj4Mc3qa73mgfkp0PMR-ucABbx3mMcyVipaEpQ,2776
+magic_pdf/pre_proc/post_layout_split.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+magic_pdf/pre_proc/remove_bbox_overlap.py,sha256=8eXNdsz9s06LX0kS0AxYSkaY1tWQQMkJfVtVSdjTQNE,3090
+magic_pdf/pre_proc/remove_colored_strip_bbox.py,sha256=WVKhgeWifRdO-u2ETYffkcMOFVYIbiaZu5pMr1RpEdA,4090
+magic_pdf/pre_proc/remove_footer_header.py,sha256=Igdr4jH7BUGuTcapWPiKEGKxhWH12c3VVmX5xwUVn7w,5680
+magic_pdf/pre_proc/remove_rotate_bbox.py,sha256=di7geS7AFhSaAvkWZHT6J3dlXEq8uu9Z4oBYtolQjl0,8803
+magic_pdf/pre_proc/resolve_bbox_conflict.py,sha256=ABl0vo8kkcCPSTI8dpXQTOH1b9R-lbzsJDDFONU6ELk,7313
+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=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
+magic_pdf/rw/DiskReaderWriter.py,sha256=7ZAekH8V6xlBo_1WeSZ6sNwAj2WGPtjNl50zq1CoMDY,2614
+magic_pdf/rw/S3ReaderWriter.py,sha256=_DmL45Ubio-_VsKD84KrqOQ-VNDUTzcXSrXfNMb5vww,5310
+magic_pdf/rw/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+magic_pdf/spark/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+magic_pdf/spark/spark_api.py,sha256=BYO6zlRW0cEnIUB3ZzNQTu_LsPHEVitqiUN7gy3x_wo,1124
+magic_pdf/tools/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+magic_pdf/tools/cli.py,sha256=83a8p4_DvVdDOTuviE6WqexSXsDE_MUY-af3QDxXeoU,3067
+magic_pdf/tools/cli_dev.py,sha256=3RbubfTIagWoFYdu8wSDanr-BJDjFGeDet55jTy7He0,3948
+magic_pdf/tools/common.py,sha256=ILTv8YjnK-XTVV5nzak3Sm-EJJXjG1hJJghlYKgYVBQ,6809
+magic_pdf/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+magic_pdf/utils/annotations.py,sha256=82ou3uELNbQWa9hOFFkVt0gsIskAKf5msCv5J2IJ5V0,211
+magic_pdf-0.10.0.dist-info/LICENSE.md,sha256=jVa0BUaKrRH4erV2P5AeJ24I2WRv9chIGxditreJ6e0,34524
+magic_pdf-0.10.0.dist-info/METADATA,sha256=U_TtQjdODFjAADoZro_ipfGiasBCVq2_zZlF2DFyNpM,40300
+magic_pdf-0.10.0.dist-info/WHEEL,sha256=bFJAMchF8aTQGUgMZzHJyDDMPTO3ToJ7x23SLJa1SVo,92
+magic_pdf-0.10.0.dist-info/entry_points.txt,sha256=wXwYke3j8fqDQTocUspL-CqDUEv3Tfcwp09fM8dZAhA,98
+magic_pdf-0.10.0.dist-info/top_level.txt,sha256=J9I0AzmHWGkp9c6DL8Oe4mEx3yYphLzkRn4H25Lg1rE,10
+magic_pdf-0.10.0.dist-info/RECORD,,

{magic_pdf-0.9.2.dist-info → magic_pdf-0.10.0.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