fullwidth_halfwidth_normalizer

Official

Standardize text in Chinese documents by converting full-width characters to half-width.

Authorcas-bigdatalab
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill addresses the challenge of inconsistent character width in Chinese documents, ensuring uniformity and compatibility.

Core Features & Use Cases

  • Full-width to Half-width Conversion: Transforms full-width ASCII characters and spaces into their half-width equivalents.
  • Unicode Normalization: Optional normalization of Unicode characters to standardize their representation.
  • Use Case: Ideal for processing Japanese-Korean-Chinese mixed text where a consistent character width is required, without altering Chinese punctuation or formatting.

Quick Start

Normalize the full-width characters in your dataset by running the skill with the following command: python scripts/fullwidth_halfwidth_normalizer.py --input_path input.csv --output_path output.csv.

Dependency Matrix

Required Modules

pandasdata_io

Components

scripts

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: fullwidth_halfwidth_normalizer
Download link: https://github.com/cas-bigdatalab/piflow/archive/main.zip#fullwidth-halfwidth-normalizer

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 620,000+ vetted skills library on demand.