{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Counting lines of code in a git repo."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "    import importnb\n",
    "    from pathlib import Path\n",
    "    from pandas import *\n",
    "    import mimetypes\n",
    "    from toolz.curried import *\n",
    "    from poser import *\n",
    "    from toolz.curried import *"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "    mimetypes.add_type('application/x-ipynb+json', '.ipynb')\n",
    "    mimetypes.add_type('text/markdown', '.md')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "def files_by_type():\n",
    "    contents = list(filter(\n",
    "        compose(all, juxt(\n",
    "            Path.is_file, \n",
    "            lambda x: all(\n",
    "                s not in str(x)for s in ('__pycache__', 'checkpoint')\n",
    "            ))), \n",
    "        Path(importnb.__file__).parent.parent.rglob('*')))\n",
    "    return Series(pipe(\n",
    "        contents, map(compose(first, mimetypes.guess_type, str))\n",
    "    ), index=contents, name='mime').to_frame().reset_index().set_index('mime').pipe(\n",
    "        lambda df: df.groupby(df.index).agg(compose(list, unique))\n",
    "    )['index'].apply(Series)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "    def count_lines(str):\n",
    "        significant, empty, comment = 0, 0, 0\n",
    "        for line in str.splitlines():\n",
    "            if line.strip():\n",
    "                if line.lstrip().startswith('#'): comment +=1 \n",
    "                else: significant += 1\n",
    "            else: empty += 1\n",
    "        return Series(dict(zip(('significant', 'empty', 'comment'), (significant, empty, comment))))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "    import json\n",
    "    from pandas import concat as Concat\n",
    "    from IPython.utils.capture import capture_output"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "    def nb_info(df):\n",
    "        \"\"\"Number of cells maybe\"\"\"\n",
    "        notebooks = df.loc['application/x-ipynb+json'].dropna().apply(compose(\n",
    "            Series, get('cells'), json.loads, Path.read_text\n",
    "        )).set_index(df.loc['application/x-ipynb+json'].dropna().values).stack().apply(\n",
    "            lambda x: Series({'cell_type': x['cell_type'], 'source': '\\n'.join(x.get('source'))})\n",
    "        ).set_index('cell_type', append=True).reorder_levels((2,0,1))\n",
    "        notebooks = notebooks.reset_index(0, drop=True).join(\n",
    "            notebooks.loc['code']['source'].apply(count_lines)\n",
    "        ).set_index(notebooks.index).unstack(-1)\n",
    "        return notebooks['significant'].sum(axis=1).unstack(0).fillna(0)['code']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "    from IPython import get_ipython"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "    def iterate_over_the_project(project, max=10, iter=20, **loc):\n",
    "        repo, project = project\n",
    "        if not Path(project).exists():\n",
    "            !git clone $repo\n",
    "        !cd $project && git pull  \n",
    "        for i in range(max):\n",
    "            with capture_output() as time:\n",
    "                !cd $project && git log -1 --format=%cd --date=local        \n",
    "            loc[to_datetime(time.stdout)] = compose(nb_info, files_by_type)()\n",
    "            !cd $project && git reset --hard HEAD~$iter\n",
    "        !cd $project && git pull  \n",
    "        return loc"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "fatal: repository 'None' does not exist\n",
      "The system cannot find the path specified.\n"
     ]
    },
    {
     "ename": "TypeError",
     "evalue": "'builtin_function_or_method' object cannot be interpreted as an integer",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mTypeError\u001b[0m                                 Traceback (most recent call last)",
      "\u001b[1;32m<ipython-input-11-77f619f20ded>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m()\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[0miterate_over_the_project\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;32mNone\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;34m'importnb'\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m",
      "\u001b[1;32m<ipython-input-10-ca5d7888dc97>\u001b[0m in \u001b[0;36miterate_over_the_project\u001b[1;34m(project, **loc)\u001b[0m\n\u001b[0;32m      4\u001b[0m         \u001b[0mget_ipython\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0msystem\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m'git clone $repo'\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m      5\u001b[0m     \u001b[0mget_ipython\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0msystem\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m'cd $project && git pull  '\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m----> 6\u001b[1;33m     \u001b[1;32mfor\u001b[0m \u001b[0mi\u001b[0m \u001b[1;32min\u001b[0m \u001b[0mrange\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mmax\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m      7\u001b[0m         \u001b[1;32mwith\u001b[0m \u001b[0mcapture_output\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;32mas\u001b[0m \u001b[0mtime\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m      8\u001b[0m             \u001b[0mget_ipython\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0msystem\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m'cd $project && git log -1 --format=%cd --date=local        '\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;31mTypeError\u001b[0m: 'builtin_function_or_method' object cannot be interpreted as an integer"
     ]
    }
   ],
   "source": [
    "    def _test_with_importnb():\n",
    "        assert iterate_over_the_project(('https://github.com/deathbeds/importnb', 'importnb'))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [],
   "source": [
    "if __name__ == '__main__':\n",
    "    %matplotlib inline\n",
    "    Concat(loc).unstack(-1).fillna(0).sum(axis=1).plot()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.6.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}