{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "c350765d",
   "metadata": {},
   "source": [
    "# Python Code Text Splitter\n",
    "\n",
    "PythonCodeTextSplitter splits text along python class and method definitions. It's implemented as a simple subclass of RecursiveCharacterSplitter with Python-specific separators. See the source code to see the Python syntax expected by default.\n",
    "\n",
    "1. How the text is split: by list of python specific characters\n",
    "2. How the chunk size is measured: by length function passed in (defaults to number of characters)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "1703463f",
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.text_splitter import PythonCodeTextSplitter"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "f17a1854",
   "metadata": {},
   "outputs": [],
   "source": [
    "python_text = \"\"\"\n",
    "class Foo:\n",
    "\n",
    "    def bar():\n",
    "    \n",
    "    \n",
    "def foo():\n",
    "\n",
    "def testing_func():\n",
    "\n",
    "def bar():\n",
    "\"\"\"\n",
    "python_splitter = PythonCodeTextSplitter(chunk_size=30, chunk_overlap=0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "6cdc55f3",
   "metadata": {},
   "outputs": [],
   "source": [
    "docs = python_splitter.create_documents([python_text])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "8cc33770",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[Document(page_content='Foo:\\n\\n    def bar():', lookup_str='', metadata={}, lookup_index=0),\n",
       " Document(page_content='foo():\\n\\ndef testing_func():', lookup_str='', metadata={}, lookup_index=0),\n",
       " Document(page_content='bar():', lookup_str='', metadata={}, lookup_index=0)]"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "docs"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.9.1"
  },
  "vscode": {
   "interpreter": {
    "hash": "aee8b7b246df8f9039afb4144a1f6fd8d2ca17a180786b69acc140d282b71a49"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}