fss-polish/README.md
FSSCoding 9316bc50f1 Initial commit: FSS-Polish v1.0.0
Complete implementation of Fast Spelling and Style Polish tool with:
- Australian English spelling conversion (7 patterns + case preservation)
- CLI support with text input or clipboard mode
- Daemon mode with configurable hotkey
- MIN_LENGTH, AGGRESSION, and CUSTOM_DICTIONARY config options
- Comprehensive diff logging
- 12 passing tests (100% test coverage for AU spelling)
- Wheel package built and ready for deployment
- Agent-friendly CLI with stdin/stdout support

Features:
- Text correction using t5-small-spoken-typo model
- Australian/American spelling conversion
- Configurable correction aggression levels
- Custom dictionary whitelist support
- Background daemon with hotkey trigger
- CLI tool for direct text polishing
- Preserves clipboard history (adds new item vs replace)

Ready for deployment to /opt and Gitea repository.
2025-10-25 23:59:34 +11:00

66 lines
1.8 KiB
Markdown

# Clipboard Polisher
A lightweight, resident clipboard-based text polishing tool powered by a ~50 M parameter text-correction model designed for speed, minimal interference, and easy integration into your everyday workflows.
## Project Overview
This project aims to build a standalone text polishing utility that runs in the background and corrects typos, spacing errors, and obvious mis-words in any text copied to the clipboard. Unlike LLM-based rewriting tools, it will:
* Not rewrite sentences or alter meaning
* Be extremely lightweight (~50 M parameters)
* Be hotkey-triggered for instant use
* Keep the model pre-loaded in memory for speed
* Act as a conditioning pass for copied or transcribed text, markdown fragments, and notes
## Features
* Lightweight Model Inference
* Global Hotkey Integration
* Resident Background Service
* Custom Post-Processing Hooks
* Configurable Aggression
## Installation
```bash
pip install -e .
```
## Usage
Run the daemon with:
```bash
clipboard-polisher
```
## Configuration
The tool uses a configuration file `config.py` that sets up model name, hotkey, and other settings.
## Development
This project is designed to be easily expandable with agent APIs, dictionaries, multi-profile modes, and more.
## License
MIT License
## File & Folder Structure (Proposed)
```
clipboard-polisher/
├── src/
│ ├── main.py # Entry point
│ ├── model_loader.py # Load and cache model
│ ├── hotkey.py # Hotkey + clipboard handler
│ ├── config.py # Settings, profiles
│ └── utils.py # Diff, logging, helpers
├── requirements.txt
├── README.md
├── setup.py
├── service/
│ └── clipboard-polisher.service # systemd unit
└── tests/
└── test_polish.py
```