phrasplit 0.1.0__tar.gz

phrasplit-0.1.0/.github/pytest.ini

@@ -0,0 +1,3 @@
+[pytest]
+norecursedirs = .git .* *.egg* old dist build
+addopts = -rw

phrasplit-0.1.0/.github/workflows/codecov.yml

@@ -0,0 +1,29 @@
+name: CodeCov
+on: push
+jobs:
+  run:
+    runs-on: ubuntu-latest
+    env:
+      OS: ubuntu-latest
+    steps:
+    - uses: actions/checkout@master
+    - name: Setup Python
+      uses: actions/setup-python@master
+    - name: 'generate report'
+      run: |
+        pip install coverage click pytest pytest-cov
+        pip install -r requirements-test.txt
+        pip install spacy
+        python -m spacy download en_core_web_sm
+        pip install -e .
+        pytest --cov --junitxml=junit.xml 
+    - name: Upload coverage to Codecov
+      uses: codecov/codecov-action@v5
+      with:
+        token: ${{ secrets.CODECOV_TOKEN }} # required
+    - name: Upload test results to Codecov
+      if: ${{ !cancelled() }}
+      uses: codecov/test-results-action@v1
+      with:
+        token: ${{ secrets.CODECOV_TOKEN }}
+ 

phrasplit-0.1.0/.github/workflows/pre-commit.yml

@@ -0,0 +1,13 @@
+name: pre-commit
+
+on:
+  pull_request:
+  push:
+
+jobs:
+  pre-commit:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v3
+    - uses: actions/setup-python@v3
+    - uses: pre-commit/action@v3.0.1

phrasplit-0.1.0/.github/workflows/python-publish.yml

@@ -0,0 +1,39 @@
+# This workflow will upload a Python Package using Twine when a release is created
+# For more information see: https://docs.github.com/en/actions/automating-builds-and-tests/building-and-testing-python#publishing-to-package-registries
+
+# This workflow uses actions that are not certified by GitHub.
+# They are provided by a third-party and are governed by
+# separate terms of service, privacy policy, and support
+# documentation.
+
+name: Upload Python Package
+
+on:
+  release:
+    types: [published]
+
+permissions:
+  contents: read
+
+jobs:
+  deploy:
+
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v3
+    - name: Set up Python
+      uses: actions/setup-python@v3
+      with:
+        python-version: '3.x'
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install build
+    - name: Build package
+      run: python -m build
+    - name: Publish package
+      uses: pypa/gh-action-pypi-publish@27b31702a0e7fc50959f5ad993c78deac1bdfc29
+      with:
+        user: __token__
+        password: ${{ secrets.PYPI_API_TOKEN }}

phrasplit-0.1.0/.github/workflows/tests.yml

@@ -0,0 +1,23 @@
+name: Run tests
+on: [push]
+jobs:
+  run:
+    runs-on: ${{ matrix.os }}
+    strategy:
+      matrix:
+        os: [ubuntu-latest, windows-latest, macos-latest]
+        python-version: ["3.10", "3.11", "3.12", "3.13"]
+    steps:
+    - uses: actions/checkout@master
+    - name: Setup Python
+      uses: actions/setup-python@master
+      with:
+        python-version: ${{ matrix.python-version }}
+    - name: Install packages
+      run: |
+        pip install pytest
+        pip install -e .
+        pip install -r requirements-test.txt
+        pip install spacy
+        python -m spacy download en_core_web_sm
+        pytest

phrasplit-0.1.0/.gitignore

@@ -0,0 +1,208 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py.cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+#poetry.toml
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
+#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
+#pdm.lock
+#pdm.toml
+.pdm-python
+.pdm-build/
+
+# pixi
+#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
+#pixi.lock
+#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
+#   in the .venv directory. It is recommended not to include this directory in version control.
+.pixi
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.envrc
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+# Abstra
+# Abstra is an AI-powered process automation framework.
+# Ignore directories containing user credentials, local state, and settings.
+# Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#  Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore
+#  that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#  and can be added to the global gitignore or merged into this file. However, if you prefer,
+#  you could uncomment the following to ignore the entire vscode folder
+# .vscode/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Cursor
+#  Cursor is an AI-powered code editor. `.cursorignore` specifies files/directories to
+#  exclude from AI features like autocomplete and code analysis. Recommended for sensitive data
+#  refer to https://docs.cursor.com/context/ignore-files
+.cursorignore
+.cursorindexingignore
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/
+phrasplit/_version.py

phrasplit-0.1.0/.pre-commit-config.yaml

@@ -0,0 +1,66 @@
+exclude: |
+  # NOT INSTALLABLE ADDONS
+  # END NOT INSTALLABLE ADDONS
+  # Files and folders generated by bots, to avoid loops
+  ^setup/|/static/description/index\.html$|
+  # We don't want to mess with tool-generated files
+  .svg$|/tests/([^/]+/)?cassettes/|^.copier-answers.yml$|^.github/|
+  # Maybe reactivate this when all README files include prettier ignore tags?
+  ^README\.md$|
+  # Repos using Sphinx to generate docs don't need prettying
+  ^docs/_templates/.*\.html$|
+  # Don't bother non-technical authors with formatting issues in docs
+  readme/.*\.(rst|md)$|
+  # Ignore build and dist directories in addons
+  /build/|/dist/|/dev/|/notebooks/
+  # You don't usually want a bot to modify your legal texts
+  (LICENSE.*|COPYING.*)|
+default_language_version:
+  python: python3
+  node: "16.17.0"
+repos:
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.6.8
+    hooks:
+      - id: ruff
+        args: [--fix, --exit-non-zero-on-fix, --config=.ruff.toml]
+      - id: ruff-format
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.6.0
+    hooks:
+      - id: check-toml
+      - id: check-yaml
+      - id: end-of-file-fixer
+      - id: trailing-whitespace
+      - id: check-symlinks
+      - id: check-xml
+      - id: mixed-line-ending
+        args: ["--fix=lf"]
+      - id: debug-statements
+      - id: fix-encoding-pragma
+        args: ["--remove"]
+      - id: check-case-conflict
+      - id: check-docstring-first
+      - id: check-executables-have-shebangs
+      - id: check-merge-conflict
+        # exclude files where underlines are not distinguishable from merge conflicts
+        exclude: /README\.rst$|^docs/.*\.rst$
+  - repo: https://github.com/pre-commit/mirrors-prettier
+    rev: v2.7.1
+    hooks:
+      - id: prettier
+        name: prettier (with plugin-xml)
+        additional_dependencies:
+          - "prettier@2.7.1"
+          - "@prettier/plugin-xml@2.2.0"
+        args:
+          - --plugin=@prettier/plugin-xml
+        files: \.(css|htm|html|js|json|jsx|less|md|scss|toml|ts|xml|yaml|yml)$
+  - repo: https://github.com/pre-commit/mirrors-eslint
+    rev: v8.24.0
+    hooks:
+      - id: eslint
+        verbose: true
+        args:
+          - --color
+          - --fix

phrasplit-0.1.0/.prettierrc.yml

@@ -0,0 +1,8 @@
+# Defaults for all prettier-supported languages.
+# Prettier will complete this with settings from .editorconfig file.
+bracketSpacing: false
+printWidth: 88
+proseWrap: always
+semi: true
+trailingComma: "es5"
+xmlWhitespaceSensitivity: "strict"

phrasplit-0.1.0/.readthedocs.yaml

@@ -0,0 +1,22 @@
+# Read the Docs configuration file
+# See https://docs.readthedocs.io/en/stable/config-file/v2.html for details
+
+# Required
+version: 2
+
+# Set the OS, Python version, and other tools you might need
+build:
+  os: ubuntu-24.04
+  tools:
+    python: "3.13"
+
+# Build documentation in the "docs/" directory with Sphinx
+sphinx:
+  configuration: docs/conf.py
+
+# Optionally, but recommended,
+# declare the Python requirements required to build your documentation
+# See https://docs.readthedocs.io/en/stable/guides/reproducible-builds.html
+python:
+  install:
+    - requirements: docs/requirements.txt

phrasplit-0.1.0/.ruff.toml

@@ -0,0 +1,29 @@
+
+target-version = "py39"
+fix = true
+
+[lint]
+extend-select = [
+    "B",
+    "C90",
+    "E501",  # line too long (default 88)
+    "I",  # isort
+    "UP",  # pyupgrade
+]
+exclude = ["setup/*", "notebooks/*"]
+
+[format]
+exclude = ["setup/*", "notebooks/*"]
+
+[lint.per-file-ignores]
+"__init__.py" = ["F401", "I001"]  # ignore unused and unsorted imports in __init__.py
+"__manifest__.py" = ["B018"]  # useless expression
+"cli.py" = ["C901"]  # Allow higher complexity for CLI commands with recursive logic
+"pydrime/cli/*.py" = ["C901"]  # Allow higher complexity for CLI command modules
+"test_webdav_provider.py" = ["I001"]  # wsgidav requires specific import order to avoid circular import
+
+[lint.isort]
+section-order = ["future", "standard-library", "third-party", "first-party", "local-folder"]
+
+[lint.mccabe]
+max-complexity = 22

phrasplit-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 Holger Nahrstaedt
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

phrasplit-0.1.0/PKG-INFO

@@ -0,0 +1,227 @@
+Metadata-Version: 2.4
+Name: phrasplit
+Version: 0.1.0
+Summary: A simple tool to split text.
+Author-email: Holger Nahrstaedt <nahrstaedt@gmail.com>
+License: MIT License
+        
+        Copyright (c) 2025 Holger Nahrstaedt
+        
+        Permission is hereby granted, free of charge, to any person obtaining a copy
+        of this software and associated documentation files (the "Software"), to deal
+        in the Software without restriction, including without limitation the rights
+        to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+        copies of the Software, and to permit persons to whom the Software is
+        furnished to do so, subject to the following conditions:
+        
+        The above copyright notice and this permission notice shall be included in all
+        copies or substantial portions of the Software.
+        
+        THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+        IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+        FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+        AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+        LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+        OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+        SOFTWARE.
+        
+Project-URL: Homepage, https://github.com/holgern/phrasplit
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+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: Programming Language :: Python :: 3.14
+Classifier: Topic :: Software Development :: Libraries
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: click>=8.0.0
+Requires-Dist: rich>=13.0.0
+Requires-Dist: spacy>=3.5.0
+Provides-Extra: dev
+Requires-Dist: pytest>=7.0.0; extra == "dev"
+Requires-Dist: ruff>=0.1.0; extra == "dev"
+Dynamic: license-file
+
+# phrasplit
+
+A Python library for splitting text into sentences, clauses, or paragraphs using spaCy
+NLP. Designed for audiobook creation and text-to-speech processing.
+
+## Features
+
+- **Sentence splitting**: Intelligent sentence boundary detection using spaCy
+- **Clause splitting**: Split sentences at commas for natural pause points
+- **Paragraph splitting**: Split text at double newlines
+- **Long line splitting**: Break long lines at sentence/clause boundaries
+- **Abbreviation handling**: Correctly handles Mr., Dr., U.S.A., etc.
+- **Ellipsis support**: Preserves ellipses without incorrect splitting
+
+## Installation
+
+```bash
+pip install phrasplit
+```
+
+You'll also need to download a spaCy language model:
+
+```bash
+python -m spacy download en_core_web_sm
+```
+
+## Quick Start
+
+### Python API
+
+```python
+from phrasplit import split_sentences, split_clauses, split_paragraphs, split_long_lines
+
+# Split text into sentences
+text = "Dr. Smith is here. She has a Ph.D. in Chemistry."
+sentences = split_sentences(text)
+# ['Dr. Smith is here.', 'She has a Ph.D. in Chemistry.']
+
+# Split sentences into comma-separated parts (for audiobook pauses)
+text = "I like coffee, and I like tea."
+clauses = split_clauses(text)
+# ['I like coffee,', 'and I like tea.']
+
+# Split text into paragraphs
+text = "First paragraph.\n\nSecond paragraph."
+paragraphs = split_paragraphs(text)
+# ['First paragraph.', 'Second paragraph.']
+
+# Split long lines at natural boundaries
+text = "This is a very long sentence that needs to be split."
+lines = split_long_lines(text, max_length=30)
+```
+
+### Command Line Interface
+
+```bash
+# Split into sentences
+phrasplit sentences input.txt -o output.txt
+
+# Split into clauses
+phrasplit clauses input.txt -o output.txt
+
+# Split into paragraphs
+phrasplit paragraphs input.txt -o output.txt
+
+# Split long lines (default max 80 characters)
+phrasplit longlines input.txt -o output.txt --max-length 60
+
+# Use a different spaCy model
+phrasplit sentences input.txt --model en_core_web_lg
+
+# Read from stdin (pipe or redirect)
+echo "Hello world. This is a test." | phrasplit sentences
+cat input.txt | phrasplit clauses -o output.txt
+
+# Explicit stdin with dash
+phrasplit sentences - < input.txt
+```
+
+## API Reference
+
+### `split_sentences(text, language_model="en_core_web_sm")`
+
+Split text into sentences using spaCy's sentence boundary detection.
+
+**Parameters:**
+
+- `text`: Input text string
+- `language_model`: spaCy model to use (default: "en_core_web_sm")
+
+**Returns:** List of sentences
+
+### `split_clauses(text, language_model="en_core_web_sm")`
+
+Split text into comma-separated parts. Useful for creating natural pause points in
+audiobook/TTS applications.
+
+**Parameters:**
+
+- `text`: Input text string
+- `language_model`: spaCy model to use (default: "en_core_web_sm")
+
+**Returns:** List of clauses (comma stays at end of each part)
+
+### `split_paragraphs(text)`
+
+Split text into paragraphs at double newlines.
+
+**Parameters:**
+
+- `text`: Input text string
+
+**Returns:** List of paragraphs
+
+### `split_long_lines(text, max_length, language_model="en_core_web_sm")`
+
+Split lines exceeding max_length at sentence/clause boundaries.
+
+**Parameters:**
+
+- `text`: Input text string
+- `max_length`: Maximum line length in characters
+- `language_model`: spaCy model to use (default: "en_core_web_sm")
+
+**Returns:** List of lines, each within max_length
+
+## Use Cases
+
+### Audiobook Creation
+
+Split text at commas to create natural pause points for text-to-speech:
+
+```python
+from phrasplit import split_clauses
+
+text = "When the sun rose, the birds began to sing, and the day started."
+parts = split_clauses(text)
+# ['When the sun rose,', 'the birds began to sing,', 'and the day started.']
+```
+
+### Subtitle Generation
+
+Split long lines to fit subtitle constraints:
+
+```python
+from phrasplit import split_long_lines
+
+text = "This is a very long sentence that would not fit on a single subtitle line."
+lines = split_long_lines(text, max_length=42)
+```
+
+### Text Processing Pipelines
+
+```python
+from phrasplit import split_paragraphs, split_sentences
+
+text = open("book.txt").read()
+
+for paragraph in split_paragraphs(text):
+    for sentence in split_sentences(paragraph):
+        process(sentence)
+```
+
+## Requirements
+
+- Python 3.9+
+- spaCy 3.5+
+- click 8.0+
+- rich 13.0+
+
+## License
+
+MIT License - see [LICENSE](LICENSE) for details.
+
+## Contributing
+
+Contributions are welcome! Please feel free to submit a Pull Request.