Perform a search for a file on libcfgraph!

filesearch.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "import glob\n",
    "import os\n",
    "import json"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "from pandas.io import json"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# There is a crazy repo here\n",
    "\n",
    "### https://github.com/regro/libcfgraph\n",
    "\n",
    "We're going to use it to find which conda-forge package on `win-64` contains `'sed.exe'`"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Already up to date.\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "fatal: destination path '/home/jovyan/libcfgraph' already exists and is not an empty directory.\n"
     ]
    }
   ],
   "source": [
    "%%bash\n",
    "git clone https://github.com/regro/libcfgraph ~/libcfgraph\n",
    "cd ~/libcfgraph\n",
    "git pull"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [],
   "source": [
    "PLATFORM = 'win-64'\n",
    "SUFFIX = '/sed.exe'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [],
   "source": [
    "x = glob.glob(os.path.expanduser(f'~/libcfgraph/artifacts/*/*/{PLATFORM}/*.json'))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Requirement already satisfied: tqdm in /opt/conda/lib/python3.6/site-packages (4.28.1)\n",
      "\u001b[33mYou are using pip version 18.0, however version 18.1 is available.\n",
      "You should consider upgrading via the 'pip install --upgrade pip' command.\u001b[0m\n"
     ]
    }
   ],
   "source": [
    "!pip install tqdm"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "import tqdm"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [],
   "source": [
    "results = set()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "def search_files(data, package, suffix, filename):\n",
    "    for fn in data['files']:\n",
    "        if fn.endswith(suffix):\n",
    "            results.add((package, filename))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 40685/40685 [00:08<00:00, 5071.51it/s]\n"
     ]
    }
   ],
   "source": [
    "compiled_things = set()\n",
    "migrated_things = set()\n",
    "for metadata in tqdm.tqdm(x):\n",
    "    *_, package, channel, arch, fn = metadata.split(os.path.sep)\n",
    "    with open(metadata, 'r') as fo:\n",
    "        data = json.loads(fo.read())\n",
    "    search_files(data, package=package, filename=fn, suffix='/sed.exe')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{('git', 'git-2.12.2-4.json'),\n",
       " ('git', 'git-2.13.3-0.json'),\n",
       " ('git', 'git-2.14.1-0.json'),\n",
       " ('git', 'git-2.14.1-1.json'),\n",
       " ('git', 'git-2.14.2-0.json'),\n",
       " ('git', 'git-2.14.2-1.json'),\n",
       " ('git', 'git-2.14.2-2.json'),\n",
       " ('git', 'git-2.14.2-3.json'),\n",
       " ('git', 'git-2.18.0-ha0abe07_1.json'),\n",
       " ('git', 'git-2.19.0-h21ff451_0.json'),\n",
       " ('git', 'git-2.19.1-h21ff451_0.json'),\n",
       " ('git', 'git-2.19.1-h21ff451_1000.json'),\n",
       " ('git', 'git-2.8.2-2.json'),\n",
       " ('git', 'git-2.8.2-3.json'),\n",
       " ('git', 'git-2.8.2-4.json')}"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "results"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python [default]",
   "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": "3.6.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}