magic-pdf 0.6.1__py3-none-any.whl → 0.7.0a1__py3-none-any.whl

magic_pdf/tools/common.py

@@ -0,0 +1,119 @@
+import os
+import json as json_parse
+import copy
+import click
+from loguru import logger
+from magic_pdf.libs.MakeContentConfig import DropMode, MakeMode
+from magic_pdf.libs.draw_bbox import draw_layout_bbox, draw_span_bbox
+from magic_pdf.pipe.UNIPipe import UNIPipe
+from magic_pdf.pipe.OCRPipe import OCRPipe
+from magic_pdf.pipe.TXTPipe import TXTPipe
+from magic_pdf.rw.DiskReaderWriter import DiskReaderWriter
+from magic_pdf.rw.AbsReaderWriter import AbsReaderWriter
+import magic_pdf.model as model_config
+
+
+def prepare_env(output_dir, pdf_file_name, method):
+    local_parent_dir = os.path.join(output_dir, pdf_file_name, method)
+
+    local_image_dir = os.path.join(str(local_parent_dir), "images")
+    local_md_dir = local_parent_dir
+    os.makedirs(local_image_dir, exist_ok=True)
+    os.makedirs(local_md_dir, exist_ok=True)
+    return local_image_dir, local_md_dir
+
+
+def do_parse(
+    output_dir,
+    pdf_file_name,
+    pdf_bytes,
+    model_list,
+    parse_method,
+    f_draw_span_bbox=True,
+    f_draw_layout_bbox=True,
+    f_dump_md=True,
+    f_dump_middle_json=True,
+    f_dump_model_json=True,
+    f_dump_orig_pdf=True,
+    f_dump_content_list=False,
+    f_make_md_mode=MakeMode.MM_MD,
+):
+    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_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)
+    elif parse_method == "txt":
+        pipe = TXTPipe(pdf_bytes, model_list, image_writer, is_debug=True)
+    elif parse_method == "ocr":
+        pipe = OCRPipe(pdf_bytes, model_list, image_writer, is_debug=True)
+    else:
+        logger.error("unknown parse method")
+        exit(1)
+
+    pipe.pipe_classify()
+
+    if len(model_list) == 0:
+        if model_config.__use_inside_model__:
+            pipe.pipe_analyze()
+            orig_model_list = copy.deepcopy(pipe.model_list)
+        else:
+            logger.error("need model list input")
+            exit(2)
+
+    pipe.pipe_parse()
+    pdf_info = pipe.pdf_mid_data["pdf_info"]
+    if f_draw_layout_bbox:
+        draw_layout_bbox(pdf_info, pdf_bytes, local_md_dir)
+    if f_draw_span_bbox:
+        draw_span_bbox(pdf_info, pdf_bytes, local_md_dir)
+
+    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,
+        )
+
+    if f_dump_middle_json:
+        md_writer.write(
+            content=json_parse.dumps(pipe.pdf_mid_data, ensure_ascii=False, indent=4),
+            path="middle.json",
+            mode=AbsReaderWriter.MODE_TXT,
+        )
+
+    if f_dump_model_json:
+        md_writer.write(
+            content=json_parse.dumps(orig_model_list, ensure_ascii=False, indent=4),
+            path="model.json",
+            mode=AbsReaderWriter.MODE_TXT,
+        )
+
+    if f_dump_orig_pdf:
+        md_writer.write(
+            content=pdf_bytes,
+            path="origin.pdf",
+            mode=AbsReaderWriter.MODE_BIN,
+        )
+
+    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="content_list.json",
+            mode=AbsReaderWriter.MODE_TXT,
+        )
+
+    logger.info(f"local output dir is {local_md_dir}")
+
+
+parse_pdf_methods = click.Choice(["ocr", "txt", "auto"])

{magic_pdf-0.6.1.dist-info → magic_pdf-0.7.0a1.dist-info}/METADATA

@@ -1,35 +1,44 @@
 Metadata-Version: 2.1
 Name: magic-pdf
-Version: 0.6.1
+Version: 0.7.0a1
 Summary: A practical tool for converting PDF to Markdown
 Home-page: https://github.com/opendatalab/MinerU
 Requires-Python: >=3.9
 Description-Content-Type: text/markdown
 License-File: LICENSE.md
-Requires-Dist: boto3 >=1.28.43
-Requires-Dist: Brotli >=1.1.0
-Requires-Dist: click >=8.1.7
-Requires-Dist: PyMuPDF >=1.24.7
-Requires-Dist: loguru >=0.6.0
-Requires-Dist: numpy >=1.21.6
-Requires-Dist: fast-langdetect >=0.2.1
-Requires-Dist: wordninja >=2.0.0
-Requires-Dist: scikit-learn >=1.0.2
-Requires-Dist: pdfminer.six >=20231228
-Provides-Extra: cpu
-Requires-Dist: paddleocr ==2.7.3 ; extra == 'cpu'
-Requires-Dist: paddlepaddle ; extra == 'cpu'
-Provides-Extra: full-cpu
-Requires-Dist: unimernet ; extra == 'full-cpu'
-Requires-Dist: matplotlib ; extra == 'full-cpu'
-Requires-Dist: ultralytics ; extra == 'full-cpu'
-Requires-Dist: paddleocr ==2.7.3 ; extra == 'full-cpu'
-Requires-Dist: paddlepaddle ; extra == 'full-cpu'
-Provides-Extra: gpu
-Requires-Dist: paddleocr ==2.7.3 ; extra == 'gpu'
-Requires-Dist: paddlepaddle-gpu ; extra == 'gpu'
-
-<div id="top"></div>
+Requires-Dist: boto3>=1.28.43
+Requires-Dist: Brotli>=1.1.0
+Requires-Dist: click>=8.1.7
+Requires-Dist: PyMuPDF>=1.24.9
+Requires-Dist: loguru>=0.6.0
+Requires-Dist: numpy<2.0.0,>=1.21.6
+Requires-Dist: fast-langdetect==0.2.0
+Requires-Dist: wordninja>=2.0.0
+Requires-Dist: scikit-learn>=1.0.2
+Requires-Dist: pdfminer.six==20231228
+Provides-Extra: full
+Requires-Dist: unimernet==0.1.6; extra == "full"
+Requires-Dist: ultralytics; extra == "full"
+Requires-Dist: paddleocr==2.7.3; extra == "full"
+Requires-Dist: pypandoc; extra == "full"
+Requires-Dist: struct-eqtable==0.1.0; 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"
+Requires-Dist: matplotlib<=3.9.0; platform_system == "Windows" and extra == "full"
+Requires-Dist: paddlepaddle==2.6.1; (platform_system == "Windows" or platform_system == "Darwin") and extra == "full"
+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"
+
+<div id="top">
+
+<p align="center">
+  <img src="docs/images/MinerU-logo.png" width="300px" style="vertical-align:middle;">
+</p>
+
+</div>
 <div align="center">
 
 [![stars](https://img.shields.io/github/stars/opendatalab/MinerU.svg)](https://github.com/opendatalab/MinerU)
@@ -40,15 +49,24 @@ Requires-Dist: paddlepaddle-gpu ; extra == 'gpu'
 [![Downloads](https://static.pepy.tech/badge/magic-pdf)](https://pepy.tech/project/magic-pdf)
 [![Downloads](https://static.pepy.tech/badge/magic-pdf/month)](https://pepy.tech/project/magic-pdf)
 
+<a href="https://trendshift.io/repositories/11174" target="_blank"><img src="https://trendshift.io/api/badge/repositories/11174" alt="opendatalab%2FMinerU | Trendshift" style="width: 200px; height: 55px;"/></a>
 
 
 
-[English](README.md) | [简体中文](README_zh-CN.md)
+
+[English](README.md) | [简体中文](README_zh-CN.md) | [日本語](README_ja-JP.md)
 
 </div>
 
 <div align="center">
-
+<p align="center">
+<a href="https://github.com/opendatalab/MinerU">MinerU: An end-to-end PDF parsing tool based on PDF-Extract-Kit, supporting conversion from PDF to Markdown.</a>🚀🚀🚀<br>
+<a href="https://github.com/opendatalab/PDF-Extract-Kit">PDF-Extract-Kit: A Comprehensive Toolkit for High-Quality PDF Content Extraction</a>🔥🔥🔥
+</p>
+
+<p align="center">
+    👋 join us on <a href="https://discord.gg/gPxmVeGC" target="_blank">Discord</a> and <a href="https://cdn.vansin.top/internlm/mineru.jpg" target="_blank">WeChat</a>
+</p>
 </div>
 
 # MinerU 
@@ -82,7 +100,7 @@ Key features include:
 - Available for Windows, Linux, and macOS platforms
 
 
-https://github.com/opendatalab/MinerU/assets/11393164/618937cb-dc6a-4646-b433-e3131a5f4070
+https://github.com/user-attachments/assets/4bea02c9-6d54-4cd6-97ed-dff14340982c
 
 
 
@@ -95,10 +113,9 @@ https://github.com/opendatalab/MinerU/assets/11393164/618937cb-dc6a-4646-b433-e3
 
 ![Flowchart](docs/images/flowchart_en.png)
 
-### Submodule Repositories
+### Dependency repositorys
 
-- [PDF-Extract-Kit](https://github.com/opendatalab/PDF-Extract-Kit)
-  - A Comprehensive Toolkit for High-Quality PDF Content Extraction
+- [PDF-Extract-Kit : A Comprehensive Toolkit for High-Quality PDF Content Extraction](https://github.com/opendatalab/PDF-Extract-Kit) 🚀🚀🚀
 
 ## Getting Started
 
@@ -113,24 +130,34 @@ conda create -n MinerU python=3.10
 conda activate MinerU
 ```
 
-### Usage Instructions
+### Installation and Configuration
 
 #### 1. Install Magic-PDF
 
-Install using pip:
-```bash
-pip install magic-pdf
-```
-Alternatively, for built-in high-precision model parsing capabilities, use:
+**1.Install dependencies**
+
+The full-feature package depends on detectron2, which requires a compilation installation.   
+If you need to compile it yourself, please refer to https://github.com/facebookresearch/detectron2/issues/5114  
+Alternatively, you can directly use our precompiled whl package (limited to Python 3.10):
+
 ```bash
-pip install magic-pdf[full-cpu]
+pip install detectron2 --extra-index-url https://wheels.myhloli.com
 ```
-The high-precision models depend on detectron2, which requires a compiled installation.  
-If you need to compile it yourself, refer to https://github.com/facebookresearch/detectron2/issues/5114  
-Or directly use our pre-compiled wheel packages (limited to python 3.10):  
+
+**2.Install the full-feature package with pip**
+>Note: The pip-installed package supports CPU-only and is ideal for quick tests.
+>
+>For CUDA/MPS acceleration in production, see [Acceleration Using CUDA or MPS](#4-Acceleration-Using-CUDA-or-MPS).
+
 ```bash
-pip install detectron2 --extra-index-url https://myhloli.github.io/wheels/
+pip install magic-pdf[full]==0.6.2b1
 ```
+> ❗️❗️❗️
+> We have pre-released the 0.6.2 beta version, addressing numerous issues mentioned in our logs. However, this build has not undergone full QA testing and does not represent the final release quality. Should you encounter any problems, please promptly report them to us via issues or revert to using version 0.6.1.
+> ```bash
+> pip install magic-pdf[full-cpu]==0.6.1
+> ```
+
 
 
 #### 2. Downloading model weights files
@@ -154,38 +181,21 @@ In magic-pdf.json, configure "models-dir" to point to the directory where the mo
 ```
 
 
-#### 4. Usage via Command Line
-
-###### simple
-
-```bash
-magic-pdf pdf-command --pdf "pdf_path" --inside_model true
-```
-After the program has finished, you can find the generated markdown files under the directory "/tmp/magic-pdf".  
-You can find the corresponding xxx_model.json file in the markdown directory.   
-If you intend to do secondary development on the post-processing pipeline, you can use the command:  
-```bash
-magic-pdf pdf-command --pdf "pdf_path" --model "model_json_path"
-```
-In this way, you won't need to re-run the model data, making debugging more convenient.
-
-
-###### more 
-
-```bash
-magic-pdf --help
-```
-
-
-#### 5. Acceleration Using CUDA or MPS
-
+#### 4. Acceleration Using CUDA or MPS
+If you have an available Nvidia GPU or are using a Mac with Apple Silicon, you can leverage acceleration with CUDA or MPS respectively.
 ##### CUDA
 
 You need to install the corresponding PyTorch version according to your CUDA version.  
-This example installs the CUDA 11.8 version.More information https://pytorch.org/get-started/locally/  
+This example installs the CUDA 11.8 version.More information https://pytorch.org/get-started/locally/
 ```bash
 pip install --force-reinstall torch==2.3.1 torchvision==0.18.1 --index-url https://download.pytorch.org/whl/cu118
 ```
+> ❗ ️Make sure to specify version
+> ```bash
+> torch==2.3.1 torchvision==0.18.1
+> ```
+>  in the command, as these are the highest versions we support. Failing to specify the versions may result in automatically installing higher versions which can cause the program to fail.
+
 Also, you need to modify the value of "device-mode" in the configuration file magic-pdf.json.  
 ```json
 {
@@ -203,13 +213,39 @@ You also need to modify the value of "device-mode" in the configuration file mag
 }
 ```
 
-#### 6. Usage via Api
+
+### Usage
+
+#### 1.Usage via Command Line
+
+###### simple
+
+```bash
+magic-pdf pdf-command --pdf "pdf_path" --inside_model true
+```
+After the program has finished, you can find the generated markdown files under the directory "/tmp/magic-pdf".  
+You can find the corresponding xxx_model.json file in the markdown directory.   
+If you intend to do secondary development on the post-processing pipeline, you can use the command:  
+```bash
+magic-pdf pdf-command --pdf "pdf_path" --model "model_json_path"
+```
+In this way, you won't need to re-run the model data, making debugging more convenient.
+
+
+###### more 
+
+```bash
+magic-pdf --help
+```
+
+
+#### 2. Usage via Api
 
 ###### Local
 ```python
 image_writer = DiskReaderWriter(local_image_dir)
 image_dir = str(os.path.basename(local_image_dir))
-jso_useful_key = {"_pdf_type": "", "model_list": model_json}
+jso_useful_key = {"_pdf_type": "", "model_list": []}
 pipe = UNIPipe(pdf_bytes, jso_useful_key, image_writer)
 pipe.pipe_classify()
 pipe.pipe_parse()
@@ -222,7 +258,7 @@ s3pdf_cli = S3ReaderWriter(pdf_ak, pdf_sk, pdf_endpoint)
 image_dir = "s3://img_bucket/"
 s3image_cli = S3ReaderWriter(img_ak, img_sk, img_endpoint, parent_path=image_dir)
 pdf_bytes = s3pdf_cli.read(s3_pdf_path, mode=s3pdf_cli.MODE_BIN)
-jso_useful_key = {"_pdf_type": "", "model_list": model_json}
+jso_useful_key = {"_pdf_type": "", "model_list": []}
 pipe = UNIPipe(pdf_bytes, jso_useful_key, s3image_cli)
 pipe.pipe_classify()
 pipe.pipe_parse()
@@ -271,7 +307,7 @@ https://github.com/opendatalab/MinerU/assets/11393164/20438a02-ce6c-4af8-9dde-d7
 
 # All Thanks To Our Contributors
 
-<a href="https://github.com/magicpdf/Magic-PDF/graphs/contributors">
+<a href="https://github.com/opendatalab/MinerU/graphs/contributors">
   <img src="https://contrib.rocks/image?repo=opendatalab/MinerU" />
 </a>
 
@@ -294,6 +330,13 @@ The project currently leverages PyMuPDF to deliver advanced functionalities; how
 # Citation
 
 ```bibtex
+@article{he2024opendatalab,
+  title={Opendatalab: Empowering general artificial intelligence with open datasets},
+  author={He, Conghui and Li, Wei and Jin, Zhenjiang and Xu, Chao and Wang, Bin and Lin, Dahua},
+  journal={arXiv preprint arXiv:2407.13773},
+  year={2024}
+}
+
 @misc{2024mineru,
     title={MinerU: A One-stop, Open-source, High-quality Data Extraction Tool},
     author={MinerU Contributors},
@@ -312,3 +355,8 @@ The project currently leverages PyMuPDF to deliver advanced functionalities; how
    <img alt="Star History Chart" src="https://api.star-history.com/svg?repos=opendatalab/MinerU&type=Date" />
  </picture>
 </a>
+
+# Links
+- [LabelU (A Lightweight Multi-modal Data Annotation Tool)](https://github.com/opendatalab/labelU)
+- [LabelLLM (An Open-source LLM Dialogue Annotation Platform)](https://github.com/opendatalab/LabelLLM)
+- [PDF-Extract-Kit (A Comprehensive Toolkit for High-Quality PDF Content Extraction)](https://github.com/opendatalab/PDF-Extract-Kit)

{magic_pdf-0.6.1.dist-info → magic_pdf-0.7.0a1.dist-info}/RECORD

@@ -1,14 +1,11 @@
 magic_pdf/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 magic_pdf/pdf_parse_by_ocr.py,sha256=IWnSWt1Z-d35xRqspzdLR2iUtma_SAu4W7K4kEk8SHc,638
 magic_pdf/pdf_parse_by_txt.py,sha256=KUSH7Gh83CZmdyWw59pqDskwyJ2Kg-jU-9fnQGJQEs4,537
-magic_pdf/pdf_parse_for_train.py,sha256=Oby61DMjJ716Jj_ri7lwXfv2Chus0pbBR2RPXrmBW08,28661
-magic_pdf/pdf_parse_union_core.py,sha256=a67iQuEfuslAEF-wQplGZKXUuz5mT3HiCyvuR52E6Gw,10584
+magic_pdf/pdf_parse_union_core.py,sha256=jNly6l9pGcCf7wr6s6PgQhITJZ1m9PaI32Q26zxFngs,10620
 magic_pdf/user_api.py,sha256=CVQH-VSiZpz0bSkyMT4czk1epZriIPSJsLsPbluPa9Q,3054
-magic_pdf/cli/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-magic_pdf/cli/magicpdf.py,sha256=EcTiX-MaiDc4Fv9qZ_UdjHt5tYnBEu6vlbp0w030sA0,12691
 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=oV1x1N6AoVkRcQEdrCQ5uaFwOrmirosnGgTeqLzbJCA,15446
+magic_pdf/dict2md/ocr_mkcontent.py,sha256=mq6tACGkL383bdUla7xOkRXRTBBydRtdbgIHwkk_daM,16169
 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
@@ -25,7 +22,7 @@ magic_pdf/libs/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 magic_pdf/libs/boxbase.py,sha256=MvD0DypR4sTEF3T2RrI_yJ8mPDUBYHAqAaau2mnBSxY,15343
 magic_pdf/libs/calc_span_stats.py,sha256=5vnU27DcbkFDRSAoLqAmX0KQ3I9ehWkEgh_t9hxg_zI,10147
 magic_pdf/libs/commons.py,sha256=6Zu9-OyamyCNDY7qj0SxR-rux-ggj9im3CVPtC4ubB8,7108
-magic_pdf/libs/config_reader.py,sha256=wB0Zn6qEwuAWmv2Icz9owPIqxrhFEH5i6sUr8Nt5ULo,1806
+magic_pdf/libs/config_reader.py,sha256=dPx6JJJuCw9AzNgKtrTG1elmfdeN6gDhgFK9r15-NsE,2505
 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
@@ -34,9 +31,9 @@ magic_pdf/libs/drop_reason.py,sha256=IfjPSrPLMmVziqjOXPep7r_ioQKFRahDgbOW1SD-Tuw
 magic_pdf/libs/drop_tag.py,sha256=bZDg3bIVWvBT1Ec1icwj5WLOkt5-hI6eRYZ2tX9_a74,673
 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=l0LGIz-dlerU9Xct-7ypNKGNEI_q-CTadsJAnVTF9VY,692
+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/math.py,sha256=tqljQOgqh3fZc146HYhO88JXJaiXMVwArBkk_CSGICc,177
 magic_pdf/libs/nlp_utils.py,sha256=-X9W3-Ns5ZdDYFvyyEq6i6P2b5hCATaFEZeOjwNOH9M,6901
 magic_pdf/libs/ocr_content_type.py,sha256=DiGTYppd6WlibwCAeVpIy3NHCQkglfIAQsJ_ffu5BPw,526
 magic_pdf/libs/path_utils.py,sha256=Hykw_l5CU736b2egHV9P7B-qh3QNKO4nZSGCbsi0Z8E,1043
@@ -44,22 +41,22 @@ 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=baAcEjLSYFIeNZF51tOMmA_zAMhN8HvKael-UU-Ruec,22
+magic_pdf/libs/version.py,sha256=iEqOsQ5JUsdTQDAPqryKypkJMTOXXBl71cd4Drh5pDs,24
 magic_pdf/libs/vis_utils.py,sha256=hTOTEakKV0pGMbk0tbRkVI_tku7A3dGc96ynObZ4kwI,10207
-magic_pdf/model/__init__.py,sha256=XeYcF4RMZ3DosyLqiz0_n1JVa2k5RhTwUXwKt5sAjEQ,53
-magic_pdf/model/doc_analyze_by_custom_model.py,sha256=kssz_Nn6zTYED_iEgGuFRjus947xoK5dTqj88FOehE0,3256
-magic_pdf/model/magic_model.py,sha256=2H6Gz1mg0f0YCvz-TLIWrAWXCQLgZftBXJNRPlSIjwc,25077
+magic_pdf/model/__init__.py,sha256=1QcfMKET0xQhSaZMjNQHi_TjzSSDR6PI5mjkmaXHPe8,52
+magic_pdf/model/doc_analyze_by_custom_model.py,sha256=cSmh27RG1cvY0pd98T82rq0pANBwkYN0siZIN6oPNI8,4332
+magic_pdf/model/magic_model.py,sha256=xwKV9BrdjOJecJSzbErT54N6qeJu0tvFuJg2S1z_2kU,25413
 magic_pdf/model/model_list.py,sha256=AqxAtKGLDn7VVXWYwk0l9LnACxDLyU2jwOJ7vjPZj04,72
-magic_pdf/model/pdf_extract_kit.py,sha256=yuhelZaVq2NzuL0hygX61i0OmxfD1BIYhtZ0nFHwitw,8651
-magic_pdf/model/pp_structure_v2.py,sha256=apYWwWiCjlks5CLXolcynnuPV7llCm2PdP-6tg0-Kt0,2903
+magic_pdf/model/pdf_extract_kit.py,sha256=I3pZBWQu8y5YVjURTUJnsIySjeSGK-Yefit9PiqN9VE,12952
+magic_pdf/model/pp_structure_v2.py,sha256=1sn8IJK0d5ZmqJ2XFt9FdaSdI0RQf-iwNAWBrVrIeuc,2872
 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=XiwLUCiY_E0JkaIQr5m1hOD75-iGrgkMVe-1bzeF_Go,10522
+magic_pdf/model/pek_sub_modules/self_modify.py,sha256=wl7HPzfUyKrjsSRp_iMXlbM2q1brVk5TD9NbgyY6UWU,11397
 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=POs5s4_9rS-GlE7f_iHBuZpTwOuyfI6VE3DUb37fgxA,4483
+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
@@ -75,6 +72,8 @@ magic_pdf/model/pek_sub_modules/layoutlmv3/layoutlmft/models/layoutlmv3/configur
 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=BdrBZ_2B2jgF0vzn_ted8bE9Te-DC1Ea2UijqULNKjg,928
+magic_pdf/model/pek_sub_modules/structeqtable/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 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
@@ -99,7 +98,7 @@ magic_pdf/post_proc/detect_para.py,sha256=5LX86ueHQGOV9CNimAxqZH4R3KTi78leum1de_
 magic_pdf/post_proc/pdf_post_filter.py,sha256=FeZceyjGG_UvBrBoa51Ohge5edQzCoJtZTaocidKCHg,2530
 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=81iFoNLhZ2vOZi1g2zBH0S2UEfyZdhBY43qKKdxr6mo,6521
+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=bbeELTg2-SFyHkVEnGAL_7S6k8hyy1xtDSoFmXDQDOA,2768
 magic_pdf/pre_proc/detect_equation.py,sha256=9omDHKTI8QO9Qd46eVFHWhZeMmTNx7XDuWRgjXI-KFA,6627
@@ -114,10 +113,10 @@ magic_pdf/pre_proc/equations_replace.py,sha256=fXj7ZV7F3YtkDYrAhE9g5tHk4_3pVUyLb
 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=K5VHG_hNzqR6va0TB24SONMS7NGYBrbY4pxgEijLNlk,5305
+magic_pdf/pre_proc/ocr_detect_all_bboxes.py,sha256=aM_RZWg-2nPBQtqOVoMuvexmP5g1CuP94WxKxXuqnW4,6574
 magic_pdf/pre_proc/ocr_detect_layout.py,sha256=DW0_HXzmcbW22cXKIYFsyZNFh8mEjSHXIFVjXndJsvQ,5878
 magic_pdf/pre_proc/ocr_dict_merge.py,sha256=lz1viJJkjZAklKZYmkWP39YBnv5BoWVr3fv6mmNr33E,12620
-magic_pdf/pre_proc/ocr_span_list_modify.py,sha256=nIkbEcV0EBBQbwzvfnjDPseHxVzYxFRQmtel3GnXdPo,11290
+magic_pdf/pre_proc/ocr_span_list_modify.py,sha256=jqBheXF8EuYCfS9tn6typr-aE57nfMoeBC36J5GjpbQ,11519
 magic_pdf/pre_proc/pdf_pre_filter.py,sha256=FIMwe8Lei9LI2RmkqiaSyTHV5b7ViADbpyBwgVwZH-c,2687
 magic_pdf/pre_proc/post_layout_split.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 magic_pdf/pre_proc/remove_bbox_overlap.py,sha256=u_ObNLkZ8pPDNBUkSMpA9ffiSpfz42B4807cdBPZmLU,3085
@@ -127,23 +126,23 @@ magic_pdf/pre_proc/remove_rotate_bbox.py,sha256=0FlBXeiEwjZAGAWo-DiMptclFOj04POu
 magic_pdf/pre_proc/resolve_bbox_conflict.py,sha256=bJiegofPUeDyi--oZjfipQ5Q5RLm6TOCW0TLXbPii_Q,7307
 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/model_config/model_configs.yaml,sha256=C_9UfFMlHOX-iSgcwCHjyHKazKKuwpy1RcGHeTQD1kY,139
+magic_pdf/resources/fasttext-langdetect/lid.176.ftz,sha256=jzRyz-hzintgmejpmcPL-uDc0VaWqsfXc4qAOdtgPoM,938013
+magic_pdf/resources/model_config/model_configs.yaml,sha256=2MxCOJ5yNUupQqvrAvEuJKlygjxxV_o1qE64K_4NWKA,235
 magic_pdf/resources/model_config/UniMERNet/demo.yaml,sha256=al9_--m3n2j9zEn9OjlmmpfQbqVBAYFakXc_hY4vDXo,807
-magic_pdf/resources/model_config/layoutlmv3/layoutlmv3_base_inference.yaml,sha256=noqVE3GmZUG86NYDfs9DiFgdQFjXaICyCU7KPzgR3II,6174
-magic_pdf/rw/AbsReaderWriter.py,sha256=1Hd6Xo2g12CaRAo5Sze-R_GSQA6GQ0rQwSmgQvw4V_c,1297
-magic_pdf/rw/DiskReaderWriter.py,sha256=0tt8lbRyqrOfFgGlhjt24YMdj2xN7QUIVysfhFIxPgo,2113
-magic_pdf/rw/S3ReaderWriter.py,sha256=O7Quf3CUqXBjMz4sIE7kNVI3TIQROeg5PuXneAacieY,4474
+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=eSLXTjMYW5Ya41VMIApRVfji1ZxEZXdH9ZdsL6fy5Kw,1131
-magic_pdf/train_utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-magic_pdf/train_utils/convert_to_train_format.py,sha256=ifo2FAoBMa_etCvz0O4v03xO6mHV8IPXYxHH7-OcHfk,2443
-magic_pdf/train_utils/extract_caption.py,sha256=gommEqIEWLplSDEJWD7_66daqlOBsWhpRBW1DHpkny4,1825
-magic_pdf/train_utils/remove_footer_header.py,sha256=pyeNNdJ-th3wl5Xwb10ZLYNaFN4-6BmahoMFE8VTNNs,5978
-magic_pdf/train_utils/vis_utils.py,sha256=MV9N9cT3ifJ35u7LFKGF9I_bOIQrtU1zcsxu2hj3aqM,10111
-magic_pdf-0.6.1.dist-info/LICENSE.md,sha256=hIahDEOTzuHCU5J2nd07LWwkLW7Hko4UFO__ffsvB-8,34523
-magic_pdf-0.6.1.dist-info/METADATA,sha256=uu10UAPzDB8N0AMZGaftgw-OEVpbgOrxVgm5EykcC8w,9488
-magic_pdf-0.6.1.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
-magic_pdf-0.6.1.dist-info/entry_points.txt,sha256=NbSkSmE08UuTwdoJD8Uofq8iyufySA4x7jmIIk4YCzI,57
-magic_pdf-0.6.1.dist-info/top_level.txt,sha256=J9I0AzmHWGkp9c6DL8Oe4mEx3yYphLzkRn4H25Lg1rE,10
-magic_pdf-0.6.1.dist-info/RECORD,,
+magic_pdf/tools/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+magic_pdf/tools/cli.py,sha256=aVmurGAEyWT-MOv0MOaCRrfef1-jkRTpeVVWUsEVyeY,2157
+magic_pdf/tools/cli_dev.py,sha256=uDc4fDxVuOIrkaKRdjNAqyh9htyLd-fYDEfJBNFUYao,4149
+magic_pdf/tools/common.py,sha256=x4W-Tyo0A-TGsOjzlUGAhxiU2AisU3nBE3_2H_RLUO4,3801
+magic_pdf-0.7.0a1.dist-info/LICENSE.md,sha256=hIahDEOTzuHCU5J2nd07LWwkLW7Hko4UFO__ffsvB-8,34523
+magic_pdf-0.7.0a1.dist-info/METADATA,sha256=NBLsixinI-5iHwdweKr13SM5qg6Jf-fWCwg5ihavlpY,12455
+magic_pdf-0.7.0a1.dist-info/WHEEL,sha256=eOLhNAGa2EW3wWl_TU484h7q1UNgy0JXjjoqKoxAAQc,92
+magic_pdf-0.7.0a1.dist-info/entry_points.txt,sha256=wXwYke3j8fqDQTocUspL-CqDUEv3Tfcwp09fM8dZAhA,98
+magic_pdf-0.7.0a1.dist-info/top_level.txt,sha256=J9I0AzmHWGkp9c6DL8Oe4mEx3yYphLzkRn4H25Lg1rE,10
+magic_pdf-0.7.0a1.dist-info/RECORD,,

{magic_pdf-0.6.1.dist-info → magic_pdf-0.7.0a1.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: bdist_wheel (0.43.0)
+Generator: bdist_wheel (0.44.0)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

magic_pdf-0.7.0a1.dist-info/entry_points.txt

@@ -0,0 +1,3 @@
+[console_scripts]
+magic-pdf = magic_pdf.tools.cli:cli
+magic-pdf-dev = magic_pdf.tools.cli_dev:cli