diff --git a/file2text/loader.py b/file2text/loader.py index 59d8047..2c15753 100644 --- a/file2text/loader.py +++ b/file2text/loader.py @@ -169,9 +169,12 @@ def fileloader(file_path): if __name__ == '__main__': import sys + from appPublic.textsplit import split_text_with_dialog_preserved if len(sys.argv) < 2: print(f'{sys.argv[0]} file\nload a file and get its text') sys.exit(1) text = fileloader(sys.argv[1]) - print(f'{text}') + txtlst = split_text_with_dialog_preserved(text) + for txt in txtlst: + print(f'{txt}') diff --git a/pyproject.toml b/pyproject.toml new file mode 100644 index 0000000..7205f31 --- /dev/null +++ b/pyproject.toml @@ -0,0 +1,28 @@ +[project] +name="file2text" +version = "0.0.1" +description = "load documents from file and get it's text" +authors = [{ name = "yu moqing", email = "yumoqing@gmail.com" }] +readme = "README.md" +requires-python = ">=3.8" +license = {text = "MIT"} +dependencies = [ + "langchain_community", + "pillow", + "mobi", + "html2text", + "python-docx", + "python-pptx", + "openpyxl", + "pypdf", + "ebooklib ", + "beautifulsoup4", +] + +[project.optional-dependencies] +dev = ["pytest", "black", "mypy"] + +[build-system] +requires = ["setuptools>=61", "wheel"] +build-backend = "setuptools.build_meta" + diff --git a/requirements.txt b/requirements.txt deleted file mode 100644 index 8cc1e09..0000000 --- a/requirements.txt +++ /dev/null @@ -1,12 +0,0 @@ -langchain_community -unstructured -pillow -mobi -html2text -python-docx -python-pptx -openpyxl -pypdf -ebooklib -beautifulsoup4 - diff --git a/setup.py b/setup.py deleted file mode 100755 index d7ae90c..0000000 --- a/setup.py +++ /dev/null @@ -1,52 +0,0 @@ -# -*- coding: utf-8 -*- - -from file2text.version import __version__ -try: - from setuptools import setup -except ImportError: - from distutils.core import setup -required = [] -with open('requirements.txt', 'r') as f: - ls = f.read() - required = ls.split('\n') - -with open('file2text/version.py', 'r') as f: - x = f.read() - y = x[x.index("'")+1:] - z = y[:y.index("'")] - version = z -with open("README.md", "r") as fh: - long_description = fh.read() - -name = "file2text" -description = "file2text" -author = "yumoqing" -email = "yumoqing@gmail.com" - -package_data = {} - -setup( - name="file2text", - version=version, - - # uncomment the following lines if you fill them out in release.py - description=description, - author=author, - author_email=email, - platforms='any', - install_requires=required , - packages=[ - "file2text" - ], - package_data=package_data, - keywords = [ - ], - url="https://github.com/yumoqing/file2text", - long_description=long_description, - long_description_content_type="text/markdown", - classifiers = [ - 'Operating System :: OS Independent', - 'Programming Language :: Python :: 3', - 'License :: OSI Approved :: MIT License', - ], -)