kreuzberg 3.2.0__py3-none-any.whl → 3.4.0__py3-none-any.whl

kreuzberg-3.4.0.dist-info/RECORD

@@ -0,0 +1,50 @@
+kreuzberg/__init__.py,sha256=jRm2U-loiKWwJpgOFgZ8Ev2mfz9sI1qJOZ2V3OoJUlg,1258
+kreuzberg/__main__.py,sha256=s2qM1nPEkRHAQP-G3P7sf5l6qA_KJeIEHS5LpPz04lg,183
+kreuzberg/_chunker.py,sha256=2eHSRHcZdJ2ZjR3in49y3o9tPl5HMO3vkbnMqaVCbHI,1887
+kreuzberg/_cli_config.py,sha256=WD_seFjbuay_NJv77vGLBW6BVV9WZNujdzf3zQkhzPc,5691
+kreuzberg/_constants.py,sha256=Bxc8oiN-wHwnWXT9bEiJhTUcu1ygPpra5qHirAif3b4,191
+kreuzberg/_gmft.py,sha256=6liCjedPxH5Xbe7V-AmrZIq5Y9Dejn7D-LSCbgYs2Sg,14762
+kreuzberg/_mime_types.py,sha256=QgX-k8aI4lTKArObDM0TFPt7DUjUVwWrdIaIZDh_XQY,7815
+kreuzberg/_playa.py,sha256=rU6ii2Qnrj8tkDYlSiab5h-BCYLJnUg4QwSLVDEXF5g,11883
+kreuzberg/_registry.py,sha256=c2B_PJbaL0q3ab2eNmj_0jldeyMaqgvRwkZqUU4MM5Q,3290
+kreuzberg/_types.py,sha256=8kwDjQjBdiTbNcRwJmH4vijNpf9Ml9WNW85Uxv2alDw,7634
+kreuzberg/cli.py,sha256=S0w2nGXBWPFn1NhxppW7dpUwB9f_3ymFuWSAB2aRu9g,12465
+kreuzberg/exceptions.py,sha256=xRaiJh11i8E6Nc-gAQPgNW5xvhiiFBhRS-CBbCEbHQM,2881
+kreuzberg/extraction.py,sha256=z8sht8Yw9v6bE_WgLdWx-phu4T58eExME296DV_41VU,16551
+kreuzberg/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+kreuzberg/_api/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+kreuzberg/_api/main.py,sha256=kZCMPPzP4BGzEege9pdhQTJPKKVjCaC6kZdMMeaqP2M,2599
+kreuzberg/_extractors/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+kreuzberg/_extractors/_base.py,sha256=YUr6A2n34LlFzbYQkiKqhXAphL9RYrvAls5SlkoQqNg,3028
+kreuzberg/_extractors/_html.py,sha256=L_vcKyv1ObI6irPaD3-WTKqxeRfZA4Rhsl3zUiAe_ws,1312
+kreuzberg/_extractors/_image.py,sha256=Vks6WEDoW5AlGqIGVSeuhZzvJNwS8V6wxeD46Fxxogw,3947
+kreuzberg/_extractors/_pandoc.py,sha256=oQ4DgQSPoX1LXjGAKh_A40JHqiKWb91LeRBYSS_6EUA,26750
+kreuzberg/_extractors/_pdf.py,sha256=qgYwGvAlvyZzb94lXGcKGIhzmSFpP6YGzYc7fs8b-yw,13432
+kreuzberg/_extractors/_presentation.py,sha256=ZX-EKQppHwvKtyKk0-IQVF6QAqJi0SfGgCiiyqMQh0w,8701
+kreuzberg/_extractors/_spread_sheet.py,sha256=ToLZIK_PO72IYbsdtSQkHOwTUhDwptjOfSX--e1UdSM,6487
+kreuzberg/_multiprocessing/__init__.py,sha256=nwYQpKH7ixHwzkQbTMFCstOCBKktmbNq5dTrwI2Mn94,203
+kreuzberg/_multiprocessing/gmft_isolated.py,sha256=wpZ5br5dL9P6hhGjAYckHbz8IvXrDdEvajJ7fxbFmAU,11199
+kreuzberg/_multiprocessing/process_manager.py,sha256=dvO9JBWYnH1KCpzwn9h3Tz-wAoihMwTLE6OS-DF_sK0,6030
+kreuzberg/_multiprocessing/sync_tesseract.py,sha256=Ck1PvHGWOMQWUcC7RyVrBt8K9VDFQ0lQcwFkwYzl3rE,8240
+kreuzberg/_multiprocessing/tesseract_pool.py,sha256=UN7BtS_ib1ux9xuR6d6AB3PY7UEUhd-5Ti1n1H0UnYw,10945
+kreuzberg/_ocr/__init__.py,sha256=VTqwKDlIRbjve71Y11Ztygyhv5aWG9LWTj8iX66ANxE,533
+kreuzberg/_ocr/_base.py,sha256=lNT0Tin4hzbmaamqqySxvYEwNtrJB5gGlStrANQQcyc,1637
+kreuzberg/_ocr/_easyocr.py,sha256=QSd6Bw7RBsOyL5ry-6lFLD7gJxcpK1P3AD_RRK4TPWs,13734
+kreuzberg/_ocr/_paddleocr.py,sha256=UvugDdZd7RojHUiFeBaI8aqz36ecegPLj2v6oT6c42g,13776
+kreuzberg/_ocr/_tesseract.py,sha256=NAHklkHvDKMgHVqjhgYfxC3DIJuQn8fXPkvnmQxUiV8,12784
+kreuzberg/_utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+kreuzberg/_utils/_cache.py,sha256=JGiwwcNBoD950IbsPUUAD5gAGS7byUuz0BqYSneVakc,13088
+kreuzberg/_utils/_device.py,sha256=Dk4g-LzUMJ-WMM-9czNQJj3mUI43l2w7t6MJcERYb2U,10264
+kreuzberg/_utils/_document_cache.py,sha256=z8irioKsOu8xve1YgHatm__wIFvs9I1gDK3tLNsNyqM,6926
+kreuzberg/_utils/_errors.py,sha256=AV3oaRQDgJxe1YUZd9pCQUysUv9KW8Ib37MvnyFOZ4o,6386
+kreuzberg/_utils/_pdf_lock.py,sha256=nqxAYCNlfWDrJtP4ZNu57st1YnkDl-gYXdr0q8nv0kA,1961
+kreuzberg/_utils/_process_pool.py,sha256=7n5UN3d-xeYHU5TiRI62u-JenERPinJzFhbRUq-zL9k,2895
+kreuzberg/_utils/_serialization.py,sha256=AhZvyAu4KsjAqyZDh--Kn2kSWGgCuH7udio8lTklO0g,2132
+kreuzberg/_utils/_string.py,sha256=owIVkUtP0__GiJD9RIJzPdvyIigT5sQho3mOXPbsnW0,958
+kreuzberg/_utils/_sync.py,sha256=IsKkR_YmseZKY6Asz6w3k-dgMXcrVaI06jWfDY7Bol4,4842
+kreuzberg/_utils/_tmp.py,sha256=5rqG_Nlb9xweaLqJA8Kc5csHDase9_eY_Fq93rNQGWc,1044
+kreuzberg-3.4.0.dist-info/METADATA,sha256=Rg939xe9b-H0TExRcJKkf9MFg7-kWM_fvzGvV6VDG0Q,11215
+kreuzberg-3.4.0.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+kreuzberg-3.4.0.dist-info/entry_points.txt,sha256=VdoFaTl3QSvVWOZcIlPpDd47o6kn7EvmXSs8FI0ExLc,48
+kreuzberg-3.4.0.dist-info/licenses/LICENSE,sha256=-8caMvpCK8SgZ5LlRKhGCMtYDEXqTKH9X8pFEhl91_4,1066
+kreuzberg-3.4.0.dist-info/RECORD,,

{kreuzberg-3.2.0.dist-info → kreuzberg-3.4.0.dist-info}/WHEEL

@@ -1,5 +1,4 @@
 Wheel-Version: 1.0
-Generator: setuptools (80.9.0)
+Generator: hatchling 1.27.0
 Root-Is-Purelib: true
 Tag: py3-none-any
-

kreuzberg-3.4.0.dist-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+kreuzberg = kreuzberg.cli:cli

kreuzberg-3.2.0.dist-info/METADATA

@@ -1,166 +0,0 @@
-Metadata-Version: 2.4
-Name: kreuzberg
-Version: 3.2.0
-Summary: A text extraction library supporting PDFs, images, office documents and more
-Author-email: Na'aman Hirschfeld <nhirschfed@gmail.com>
-License: MIT
-Project-URL: homepage, https://github.com/Goldziher/kreuzberg
-Keywords: document-processing,image-to-text,ocr,pandoc,pdf-extraction,rag,table-extraction,tesseract,text-extraction,text-processing
-Classifier: Development Status :: 4 - Beta
-Classifier: Intended Audience :: Developers
-Classifier: License :: OSI Approved :: MIT License
-Classifier: Operating System :: OS Independent
-Classifier: Programming Language :: Python :: 3 :: Only
-Classifier: Programming Language :: Python :: 3.9
-Classifier: Programming Language :: Python :: 3.10
-Classifier: Programming Language :: Python :: 3.11
-Classifier: Programming Language :: Python :: 3.12
-Classifier: Programming Language :: Python :: 3.13
-Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
-Classifier: Topic :: Software Development :: Libraries :: Python Modules
-Classifier: Topic :: Text Processing :: General
-Classifier: Topic :: Utilities
-Classifier: Typing :: Typed
-Requires-Python: >=3.9
-Description-Content-Type: text/markdown
-License-File: LICENSE
-Requires-Dist: anyio>=4.9.0
-Requires-Dist: charset-normalizer>=3.4.2
-Requires-Dist: exceptiongroup>=1.2.2; python_version < "3.11"
-Requires-Dist: html-to-markdown>=1.4.0
-Requires-Dist: playa-pdf>=0.6.1
-Requires-Dist: pypdfium2==4.30.0
-Requires-Dist: python-calamine>=0.3.2
-Requires-Dist: python-pptx>=1.0.2
-Requires-Dist: typing-extensions>=4.14.0; python_version < "3.12"
-Provides-Extra: all
-Requires-Dist: easyocr>=1.7.2; extra == "all"
-Requires-Dist: gmft>=0.4.1; extra == "all"
-Requires-Dist: paddleocr>=3.0.2; extra == "all"
-Requires-Dist: paddlepaddle>=3.0.0; extra == "all"
-Requires-Dist: semantic-text-splitter>=0.27.0; extra == "all"
-Requires-Dist: setuptools>=80.9.0; extra == "all"
-Provides-Extra: chunking
-Requires-Dist: semantic-text-splitter>=0.27.0; extra == "chunking"
-Provides-Extra: easyocr
-Requires-Dist: easyocr>=1.7.2; extra == "easyocr"
-Provides-Extra: gmft
-Requires-Dist: gmft>=0.4.1; extra == "gmft"
-Provides-Extra: paddleocr
-Requires-Dist: paddleocr>=3.0.2; extra == "paddleocr"
-Requires-Dist: paddlepaddle>=3.0.0; extra == "paddleocr"
-Requires-Dist: setuptools>=80.9.0; extra == "paddleocr"
-Dynamic: license-file
-
-# Kreuzberg
-
-[![Discord](https://img.shields.io/badge/Discord-Join%20our%20community-7289da)](https://discord.gg/pXxagNK2zN)
-[![PyPI version](https://badge.fury.io/py/kreuzberg.svg)](https://badge.fury.io/py/kreuzberg)
-[![Documentation](https://img.shields.io/badge/docs-GitHub_Pages-blue)](https://goldziher.github.io/kreuzberg/)
-[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
-
-Kreuzberg is a Python library for text extraction from documents. It provides a unified interface for extracting text from PDFs, images, office documents, and more, with both async and sync APIs.
-
-## Why Kreuzberg?
-
-- **Simple and Hassle-Free**: Clean API that just works, without complex configuration
-- **Local Processing**: No external API calls or cloud dependencies required
-- **Resource Efficient**: Lightweight processing without GPU requirements
-- **Format Support**: Comprehensive support for documents, images, and text formats
-- **Multiple OCR Engines**: Support for Tesseract, EasyOCR, and PaddleOCR
-- **Metadata Extraction**: Get document metadata alongside text content
-- **Table Extraction**: Extract tables from documents using the excellent GMFT library
-- **Modern Python**: Built with async/await, type hints, and a functional-first approach
-- **Permissive OSS**: MIT licensed with permissively licensed dependencies
-
-## Quick Start
-
-```bash
-pip install kreuzberg
-```
-
-Install pandoc:
-
-```bash
-# Ubuntu/Debian
-sudo apt-get install tesseract-ocr pandoc
-
-# macOS
-brew install tesseract pandoc
-
-# Windows
-choco install -y tesseract pandoc
-```
-
-The tesseract OCR engine is the default OCR engine. You can decide not to use it - and then either use one of the two alternative OCR engines, or have no OCR at all.
-
-### Alternative OCR engines
-
-```bash
-# Install with EasyOCR support
-pip install "kreuzberg[easyocr]"
-
-# Install with PaddleOCR support
-pip install "kreuzberg[paddleocr]"
-```
-
-## Quick Example
-
-```python
-import asyncio
-from kreuzberg import extract_file
-
-async def main():
-    # Extract text from a PDF
-    result = await extract_file("document.pdf")
-    print(result.content)
-
-    # Extract text from an image
-    result = await extract_file("scan.jpg")
-    print(result.content)
-
-    # Extract text from a Word document
-    result = await extract_file("report.docx")
-    print(result.content)
-
-asyncio.run(main())
-```
-
-## Documentation
-
-For comprehensive documentation, visit our [GitHub Pages](https://goldziher.github.io/kreuzberg/):
-
-- [Getting Started](https://goldziher.github.io/kreuzberg/getting-started/) - Installation and basic usage
-- [User Guide](https://goldziher.github.io/kreuzberg/user-guide/) - In-depth usage information
-- [API Reference](https://goldziher.github.io/kreuzberg/api-reference/) - Detailed API documentation
-- [Examples](https://goldziher.github.io/kreuzberg/examples/) - Code examples for common use cases
-- [OCR Configuration](https://goldziher.github.io/kreuzberg/user-guide/ocr-configuration/) - Configure OCR engines
-- [OCR Backends](https://goldziher.github.io/kreuzberg/user-guide/ocr-backends/) - Choose the right OCR engine
-
-## Supported Formats
-
-Kreuzberg supports a wide range of document formats:
-
-- **Documents**: PDF, DOCX, RTF, TXT, EPUB, etc.
-- **Images**: JPG, PNG, TIFF, BMP, GIF, etc.
-- **Spreadsheets**: XLSX, XLS, CSV, etc.
-- **Presentations**: PPTX, PPT, etc.
-- **Web Content**: HTML, XML, etc.
-
-## OCR Engines
-
-Kreuzberg supports multiple OCR engines:
-
-- **Tesseract** (Default): Lightweight, fast startup, requires system installation
-- **EasyOCR**: Good for many languages, pure Python, but downloads models on first use
-- **PaddleOCR**: Excellent for Asian languages, pure Python, but downloads models on first use
-
-For comparison and selection guidance, see the [OCR Backends](https://goldziher.github.io/kreuzberg/user-guide/ocr-backends/) documentation.
-
-## Contributing
-
-We welcome contributions! Please see our [Contributing Guide](docs/contributing.md) for details on setting up your development environment and submitting pull requests.
-
-## License
-
-This library is released under the MIT license.

kreuzberg-3.2.0.dist-info/RECORD

@@ -1,34 +0,0 @@
-kreuzberg/__init__.py,sha256=lT9OwIdf5CEhSX7IVmtSFPgRhz6B2z2A-RE8Zdm0PH4,1216
-kreuzberg/_chunker.py,sha256=2eHSRHcZdJ2ZjR3in49y3o9tPl5HMO3vkbnMqaVCbHI,1887
-kreuzberg/_constants.py,sha256=Bxc8oiN-wHwnWXT9bEiJhTUcu1ygPpra5qHirAif3b4,191
-kreuzberg/_gmft.py,sha256=qLhfepQuaROjPOdI-tDRqqqnOcqDY1D411ZXzoywnpg,7229
-kreuzberg/_mime_types.py,sha256=pKtxBPDoye2knyou_VODDMPIt3eXotP-ak4MAKFI2SU,6310
-kreuzberg/_playa.py,sha256=agHdhKfKLNtiP37XdNncbCP65v3Qv3m1Gn2KTRUkVx8,10396
-kreuzberg/_registry.py,sha256=c2B_PJbaL0q3ab2eNmj_0jldeyMaqgvRwkZqUU4MM5Q,3290
-kreuzberg/_types.py,sha256=G7UQ5ZUWcpgwHoasexW7f2te3gKe3PHHi_3Fm1cju-w,7503
-kreuzberg/exceptions.py,sha256=xRaiJh11i8E6Nc-gAQPgNW5xvhiiFBhRS-CBbCEbHQM,2881
-kreuzberg/extraction.py,sha256=0sjvbunx5srbR5lzjOAQjGK5JY3bCUHw-dRFmHjFz7o,8671
-kreuzberg/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-kreuzberg/_extractors/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-kreuzberg/_extractors/_base.py,sha256=YUr6A2n34LlFzbYQkiKqhXAphL9RYrvAls5SlkoQqNg,3028
-kreuzberg/_extractors/_html.py,sha256=L_vcKyv1ObI6irPaD3-WTKqxeRfZA4Rhsl3zUiAe_ws,1312
-kreuzberg/_extractors/_image.py,sha256=VQgSFSzXIMX3A52-DyvuKgfTRXUJIjYn6IX4-sQWWdg,2626
-kreuzberg/_extractors/_pandoc.py,sha256=OAbWvfzEx3rjim9uNMS9yBRnvkI71rYJKlgVzndsvyc,22157
-kreuzberg/_extractors/_pdf.py,sha256=eNFws_UxLgWSTC_VC_zJmVojpyQvioOXgNjSHQzBq5c,6607
-kreuzberg/_extractors/_presentation.py,sha256=7W6RHTk-zksuHoSk0i6UaSBf5NatnPo17MxepQoI6XI,8758
-kreuzberg/_extractors/_spread_sheet.py,sha256=1ejRZk8AE1dXS1tRIdg2S0J9Vo0wG81iKkW2IF6PjlE,4445
-kreuzberg/_ocr/__init__.py,sha256=VTqwKDlIRbjve71Y11Ztygyhv5aWG9LWTj8iX66ANxE,533
-kreuzberg/_ocr/_base.py,sha256=lNT0Tin4hzbmaamqqySxvYEwNtrJB5gGlStrANQQcyc,1637
-kreuzberg/_ocr/_easyocr.py,sha256=1OG2IbLdg4cXouV0FVzMnCkYYh6GN1pvXqXWw40PUz8,14054
-kreuzberg/_ocr/_paddleocr.py,sha256=K6D3B2cn-JIhipI5UHMa0Kn2M-GKtyUFCahs8wJQZcA,13855
-kreuzberg/_ocr/_tesseract.py,sha256=KcJMK4o__2H2ftibk1lC7HVqEfpaE_jVZgLhUXkxTvk,9773
-kreuzberg/_utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-kreuzberg/_utils/_device.py,sha256=Ja28S2psgEwWzjdO05ZI11RFb3MSlUZDT19sC4SAyVE,10955
-kreuzberg/_utils/_string.py,sha256=oNO0cmwjVNG0jAzaqNCjYtzvM_nxH5TW2KV-Uh3oEUU,978
-kreuzberg/_utils/_sync.py,sha256=lycobEMXk0tBMWLwkuMdOuNMStDwPKMC0V1Qgp_oi6k,4071
-kreuzberg/_utils/_tmp.py,sha256=5rqG_Nlb9xweaLqJA8Kc5csHDase9_eY_Fq93rNQGWc,1044
-kreuzberg-3.2.0.dist-info/licenses/LICENSE,sha256=-8caMvpCK8SgZ5LlRKhGCMtYDEXqTKH9X8pFEhl91_4,1066
-kreuzberg-3.2.0.dist-info/METADATA,sha256=xffQAGQur7sCgUT9RDqZpfkYTdthsuYIhCvbUDKFnmA,6504
-kreuzberg-3.2.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-kreuzberg-3.2.0.dist-info/top_level.txt,sha256=rbGkygffkZiyKhL8UN41ZOjLfem0jJPA1Whtndne0rE,10
-kreuzberg-3.2.0.dist-info/RECORD,,

kreuzberg-3.2.0.dist-info/top_level.txt

@@ -1 +0,0 @@
-kreuzberg