Convert file extensions to Langchain programming language

file_extension_language_map.json

{
  "cpp": "cpp",
  "c++": "cpp",
  "cc": "cpp",
  "cp": "cpp",
  "cxx": "cpp",
  "h": "cpp",
  "h++": "cpp",
  "hh": "cpp",
  "hpp": "cpp",
  "hxx": "cpp",
  "inc": "html",
  "inl": "cpp",
  "ipp": "cpp",
  "tcc": "cpp",
  "tpp": "cpp",
  "go": "go",
  "java": "java",
  "js": "js",
  "_js": "js",
  "bones": "js",
  "es": "js",
  "es6": "js",
  "frag": "js",
  "gs": "js",
  "jake": "js",
  "jsb": "js",
  "jscad": "js",
  "jsfl": "js",
  "jsm": "js",
  "jss": "js",
  "njs": "js",
  "pac": "js",
  "sjs": "js",
  "ssjs": "js",
  "sublime-build": "js",
  "sublime-commands": "js",
  "sublime-completions": "js",
  "sublime-keymap": "js",
  "sublime-macro": "js",
  "sublime-menu": "js",
  "sublime-mousemap": "js",
  "sublime-project": "js",
  "sublime-settings": "js",
  "sublime-theme": "js",
  "sublime-workspace": "js",
  "sublime_metrics": "js",
  "sublime_session": "js",
  "xsjs": "js",
  "xsjslib": "js",
  "php": "php",
  "aw": "php",
  "ctp": "php",
  "fcgi": "ruby",
  "php3": "php",
  "php4": "php",
  "php5": "php",
  "phps": "php",
  "phpt": "php",
  "proto": "proto",
  "py": "python",
  "bzl": "python",
  "cgi": "python",
  "gyp": "python",
  "lmi": "python",
  "pyde": "python",
  "pyp": "python",
  "pyt": "python",
  "pyw": "python",
  "rpy": "python",
  "tac": "python",
  "wsgi": "python",
  "xpy": "python",
  "rst": "rst",
  "rest": "rst",
  "rest.txt": "rst",
  "rst.txt": "rst",
  "rb": "ruby",
  "builder": "ruby",
  "gemspec": "ruby",
  "god": "ruby",
  "irbrc": "ruby",
  "jbuilder": "ruby",
  "mspec": "ruby",
  "pluginspec": "ruby",
  "podspec": "ruby",
  "rabl": "ruby",
  "rake": "ruby",
  "rbuild": "ruby",
  "rbw": "ruby",
  "rbx": "ruby",
  "ru": "ruby",
  "ruby": "ruby",
  "thor": "ruby",
  "watchr": "ruby",
  "rs": "rust",
  "rs.in": "rust",
  "scala": "scala",
  "sbt": "scala",
  "sc": "scala",
  "swift": "swift",
  "md": "markdown",
  "markdown": "markdown",
  "mkd": "markdown",
  "mkdn": "markdown",
  "mkdown": "markdown",
  "ron": "markdown",
  "tex": "latex",
  "html": "html",
  "htm": "html",
  "html.hl": "html",
  "st": "html",
  "xht": "html",
  "xhtml": "html",
  "sol": "sol"
}

LangChainLanguageFileExtensions.md

A JSON object where the keys are file extensions and the value is the language used by Langchain.

Use this JSON map to leverage the RecursiveCharacterTextSplitter.fromLanguage method to properly split programming files when creating embeddings on a code base.

https://api.js.langchain.com/classes/langchain_text_splitter.RecursiveCharacterTextSplitter.html#fromLanguage