Japanese Text Analyzer

🚀 Japanese Language and Text Analysis Tool

This tool uses "kuromoji.js" to count Japanese words. It follows the basic process of natural language processing to perform word segmentation on the text, breaking it down into the smallest meaningful units (morphemes). The first time you run it, it may take some time to load the dictionary data. To avoid delays during tool execution, the tokenizer is pre - initialized when the server starts.

✨ Features

Japanese Text Analysis Function Description

Analysis Metrics

• Average Sentence Length: The average number of characters per sentence. A higher value indicates that the text is more difficult to read.
• Number of Morphemes per Sentence: The average number of segmented words per sentence, reflecting the sentence density and grammatical complexity.
• Part - of - Speech Ratio: The usage frequency of parts of speech such as nouns, verbs, and adjectives.
• Particle Usage Rate: The usage frequency of specific particles, used to analyze sentence structure and word order.
• Character Type Ratio: The ratio of katakana, hiragana, Chinese characters, and alphanumeric characters.
• Lexical Diversity: The ratio of the number of different words to the total number of words (type - token ratio), reflecting the richness of the vocabulary.
• Katakana Word Rate: The usage frequency of katakana words, indicating the amount of foreign words or technical terms and the informality of the style.
• Polite Language Usage Frequency: The usage frequency of polite expressions, measuring the politeness and formality of the text.
• Average Punctuation Mark Count: The average number of punctuation marks per sentence, providing an indicator of sentence separation and readability.

File Path Resolution Function

1. Use absolute paths directly:
   • Windows - style absolute paths (e.g., C:\Users\username\Documents\file.txt).
   • Automatically detect and convert WSL/Linux - style absolute paths (e.g., /c/Users/username/Documents/file.txt).
2. Resolve relative paths based on the current directory.
3. Search starting from the user's home directory (%USERPROFILE% or $HOME).
4. Search starting from the desktop directory.
5. Search starting from the documents directory.

With this flexible file search function, the tool can automatically search for files in multiple common directories even if only a file name like "README.md" is specified. Additionally, paths obtained in the WSL environment (e.g., in the /c/Users/... format) can be directly used in the Windows environment.

📄 License

This MCP server is provided under the MIT License. This means you are free to use, modify, and distribute this software in compliance with the terms of the MIT License. For more details, please refer to the LICENSE file in the project repository.