magic-pdf 0.5.12__py3-none-any.whl → 0.5.13__py3-none-any.whl

magic_pdf/cli/magicpdf.py

@@ -290,7 +290,11 @@ def pdf_command(pdf, model, method, inside_model):
     def get_model_json(model_path):
         # 这里处理pdf和模型相关的逻辑
         if model_path is None:
-            model_path = pdf.replace(".pdf", ".json")
+            file_name_without_extension, extension = os.path.splitext(pdf)
+            if extension == ".pdf":
+                model_path = file_name_without_extension + ".json"
+            else:
+                raise Exception("pdf_path input error")
             if not os.path.exists(model_path):
                 logger.warning(
                     f"not found json {model_path} existed"

magic_pdf/libs/language.py

@@ -1,15 +1,15 @@
 import unicodedata
-from fast_langdetect import detect_langs
+from fast_langdetect import detect_language
 
 
 def detect_lang(text: str) -> str:
     if len(text) == 0:
         return ""
     try:
-        lang_upper = detect_langs(text)
+        lang_upper = detect_language(text)
     except:
         html_no_ctrl_chars = ''.join([l for l in text if unicodedata.category(l)[0] not in ['C', ]])
-        lang_upper = detect_langs(html_no_ctrl_chars)
+        lang_upper = detect_language(html_no_ctrl_chars)
     try:
         lang = lang_upper.lower()
     except:

magic_pdf/libs/version.py

@@ -1 +1 @@
-__version__ = "0.5.12"
+__version__ = "0.5.13"

{magic_pdf-0.5.12.dist-info → magic_pdf-0.5.13.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: magic-pdf
-Version: 0.5.12
+Version: 0.5.13
 Summary: A practical tool for converting PDF to Markdown
 Home-page: https://github.com/magicpdf/Magic-PDF
 Requires-Python: >=3.9
@@ -16,6 +16,7 @@ Requires-Dist: fast-langdetect >=0.1.1
 Requires-Dist: wordninja >=2.0.0
 Requires-Dist: scikit-learn >=1.0.2
 Requires-Dist: pdfminer.six >=20231228
+Requires-Dist: numpy <2.0.0
 Provides-Extra: cpu
 Requires-Dist: paddleocr ; extra == 'cpu'
 Requires-Dist: paddlepaddle ; extra == 'cpu'
@@ -45,7 +46,7 @@ Requires-Dist: paddlepaddle-gpu ; extra == 'gpu'
 
 ## Introduction
 
-MinerU is a one-stop, open-source data extraction tool, primarily includes the following features:
+MinerU is a one-stop, open-source, high-quality data extraction tool, includes the following primary features:
 
 - [Magic-PDF](#Magic-PDF)  PDF Document Extraction  
 - [Magic-Doc](#Magic-Doc)  Webpage & E-book Extraction
@@ -71,7 +72,7 @@ Key features include:
 - Available for Windows, Linux, and macOS platforms
 
 
-https://github.com/magicpdf/Magic-PDF/assets/11393164/618937cb-dc6a-4646-b433-e3131a5f4070
+https://github.com/opendatalab/MinerU/assets/11393164/618937cb-dc6a-4646-b433-e3131a5f4070
 
 
 
@@ -88,9 +89,6 @@ https://github.com/magicpdf/Magic-PDF/assets/11393164/618937cb-dc6a-4646-b433-e3
 
 - [PDF-Extract-Kit](https://github.com/opendatalab/PDF-Extract-Kit)
   - A Comprehensive Toolkit for High-Quality PDF Content Extraction
-- [Miner-PDF-Benchmark](https://github.com/opendatalab/Miner-PDF-Benchmark)
-  - An end-to-end PDF document comprehension evaluation suite designed for large-scale model data scenarios
-
 
 ## Getting Started
 
@@ -111,9 +109,10 @@ pip install magic-pdf
 ###### simple
 
 ```bash
-cp magic-pdf.template.json to ~/magic-pdf.json
+cp magic-pdf.template.json ~/magic-pdf.json
 magic-pdf pdf-command --pdf "pdf_path" --model "model_json_path"
 ```
+After the program has finished, you can find the generated markdown files under the directory "/tmp/magic-pdf".
 
 ###### more 
 
@@ -150,26 +149,6 @@ md_content = pipe.pipe_mk_markdown(image_dir, drop_mode="none")
 Demo can be referred to [demo.py](demo/demo.py)
 
 
-## All Thanks To Our Contributors
-
-<a href="https://github.com/magicpdf/Magic-PDF/graphs/contributors">
-  <img src="https://contrib.rocks/image?repo=opendatalab/MinerU" />
-</a>
-
-
-## License Information
-
-[LICENSE.md](LICENSE.md)
-
-The project currently leverages PyMuPDF to deliver advanced functionalities; however, its adherence to the AGPL license may impose limitations on certain use cases. In upcoming iterations, we intend to explore and transition to a more permissively licensed PDF processing library to enhance user-friendliness and flexibility.
-
-
-## Acknowledgments
-
-- [PaddleOCR](https://github.com/PaddlePaddle/PaddleOCR)
-- [PyMuPDF](https://github.com/pymupdf/PyMuPDF)
-
-
 # Magic-Doc
 
 
@@ -203,5 +182,50 @@ https://github.com/opendatalab/MinerU/assets/11393164/20438a02-ce6c-4af8-9dde-d7
 
 ## Project Repository
 
-- [Magic-Doc](https://github.com/magicpdf/Magic-Doc)
+- [Magic-Doc](https://github.com/InternLM/magic-doc)
   Outstanding Webpage and E-book Extraction Tool
+
+
+# All Thanks To Our Contributors
+
+<a href="https://github.com/magicpdf/Magic-PDF/graphs/contributors">
+  <img src="https://contrib.rocks/image?repo=opendatalab/MinerU" />
+</a>
+
+
+# License Information
+
+[LICENSE.md](LICENSE.md)
+
+The project currently leverages PyMuPDF to deliver advanced functionalities; however, its adherence to the AGPL license may impose limitations on certain use cases. In upcoming iterations, we intend to explore and transition to a more permissively licensed PDF processing library to enhance user-friendliness and flexibility.
+
+
+# Acknowledgments
+
+- [PaddleOCR](https://github.com/PaddlePaddle/PaddleOCR)
+- [PyMuPDF](https://github.com/pymupdf/PyMuPDF)
+- [fast-langdetect](https://github.com/LlmKira/fast-langdetect)
+- [pdfminer.six](https://github.com/pdfminer/pdfminer.six)
+
+
+# Citation
+
+```bibtex
+@misc{2024mineru,
+    title={MinerU: A One-stop, Open-source, High-quality Data Extraction Tool},
+    author={MinerU Contributors},
+    howpublished = {\url{https://github.com/opendatalab/MinerU}},
+    year={2024}
+}
+```
+
+
+# Star History
+
+<a>
+ <picture>
+   <source media="(prefers-color-scheme: dark)" srcset="https://api.star-history.com/svg?repos=opendatalab/MinerU&type=Date&theme=dark" />
+   <source media="(prefers-color-scheme: light)" srcset="https://api.star-history.com/svg?repos=opendatalab/MinerU&type=Date" />
+   <img alt="Star History Chart" src="https://api.star-history.com/svg?repos=opendatalab/MinerU&type=Date" />
+ </picture>
+</a>

{magic_pdf-0.5.12.dist-info → magic_pdf-0.5.13.dist-info}/RECORD

@@ -5,7 +5,7 @@ magic_pdf/pdf_parse_for_train.py,sha256=Oby61DMjJ716Jj_ri7lwXfv2Chus0pbBR2RPXrmB
 magic_pdf/pdf_parse_union_core.py,sha256=a67iQuEfuslAEF-wQplGZKXUuz5mT3HiCyvuR52E6Gw,10584
 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=BA6lPjBhurXAnfmvdbQiS_atEFq3PVdNYDPkvxs1N0M,11654
+magic_pdf/cli/magicpdf.py,sha256=d4Wy2g7t_GsclV4r0vQR0enIh08-Ml2n1jf1zdrq4LE,11852
 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=RyxebPtvFfNce_HCa-_YGxwFx_srzL-BfMKc85V9JG0,15442
@@ -34,7 +34,7 @@ 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=U8bOttqtJiBvqOFUksiHeeC3vgjzJIWTLqQrmorg7T0,683
+magic_pdf/libs/language.py,sha256=l0LGIz-dlerU9Xct-7ypNKGNEI_q-CTadsJAnVTF9VY,692
 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
@@ -44,7 +44,7 @@ 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=LznNzk7nDbJCv7NVxCOu958-1uT_nFJ79_3vJt7WPDc,23
+magic_pdf/libs/version.py,sha256=jEM-pQV3SLNuNue5fxlBM8hWNuJydsyqi_WBzC1VQaM,23
 magic_pdf/libs/vis_utils.py,sha256=hTOTEakKV0pGMbk0tbRkVI_tku7A3dGc96ynObZ4kwI,10207
 magic_pdf/model/360_layout_analysis.py,sha256=GbchKPJRVcrxvwNXMnR4vt8lOLPauTWMl-43ayyhX7U,221
 magic_pdf/model/__init__.py,sha256=X6t9kPDqM8hDCbq8fQc_8jILtG6mepDjN_kadUo39Sk,29
@@ -115,9 +115,9 @@ magic_pdf/train_utils/convert_to_train_format.py,sha256=ifo2FAoBMa_etCvz0O4v03xO
 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-0.5.12.dist-info/LICENSE.md,sha256=hIahDEOTzuHCU5J2nd07LWwkLW7Hko4UFO__ffsvB-8,34523
-magic_pdf-0.5.12.dist-info/METADATA,sha256=iNTDKGkj4D77ErkS0P1dNZ4ttFriYHbTSjsEE3f8MP0,5917
-magic_pdf-0.5.12.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
-magic_pdf-0.5.12.dist-info/entry_points.txt,sha256=NbSkSmE08UuTwdoJD8Uofq8iyufySA4x7jmIIk4YCzI,57
-magic_pdf-0.5.12.dist-info/top_level.txt,sha256=J9I0AzmHWGkp9c6DL8Oe4mEx3yYphLzkRn4H25Lg1rE,10
-magic_pdf-0.5.12.dist-info/RECORD,,
+magic_pdf-0.5.13.dist-info/LICENSE.md,sha256=hIahDEOTzuHCU5J2nd07LWwkLW7Hko4UFO__ffsvB-8,34523
+magic_pdf-0.5.13.dist-info/METADATA,sha256=g5VqQbFmBpLwZyVNivClRek2vVoBAGwhjuT8Tnq3Wtc,6673
+magic_pdf-0.5.13.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
+magic_pdf-0.5.13.dist-info/entry_points.txt,sha256=NbSkSmE08UuTwdoJD8Uofq8iyufySA4x7jmIIk4YCzI,57
+magic_pdf-0.5.13.dist-info/top_level.txt,sha256=J9I0AzmHWGkp9c6DL8Oe4mEx3yYphLzkRn4H25Lg1rE,10
+magic_pdf-0.5.13.dist-info/RECORD,,