{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Data handling Demo"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Switch to Jupyter\n",
    "### Setup Files and Directories"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "RAWDATA_DIR=/tmp/rr_demo\n",
    "DATA1=\"${RAWDATA_DIR}/data1.csv\"\n",
    "DATA2=\"${RAWDATA_DIR}/data2.csv\"\n",
    "mkdir -p $RAWDATA_DIR\n",
    "\n",
    "printf \"1\\n2\\n3\\n4\" > $DATA1\n",
    "printf \"5\\n6\\n7\\n8\" > $DATA2"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Checksums"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "==> data1.csv <==\n",
      "1\n",
      "2\n",
      "3\n",
      "4\n",
      "==> data2.csv <==\n",
      "5\n",
      "6\n",
      "7\n",
      "8"
     ]
    }
   ],
   "source": [
    "cd $RAWDATA_DIR\n",
    "head *.csv"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "257cde944bf50d4fe05001bc33dd0ca4  data1.csv\n",
      "347f3f3465f592fd05200c622045948f  data2.csv\n"
     ]
    }
   ],
   "source": [
    "md5sum *.csv"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "  \n",
    "## Checksums File"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "data1.csv: OK\n",
      "data2.csv: OK\n"
     ]
    }
   ],
   "source": [
    "md5sum *.csv > mydata_md5.txt\n",
    "md5sum -c mydata_md5.txt"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Catching Changes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "5\n",
      "6\n",
      "3\n",
      "8"
     ]
    }
   ],
   "source": [
    "sed -i s/7/3/ $DATA2\n",
    "cat $DATA2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "tags": [
     "raises-exception"
    ]
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "data1.csv: OK\n",
      "data2.csv: FAILED\n",
      "md5sum: WARNING: 1 computed checksum did NOT match\n"
     ]
    },
    {
     "ename": "",
     "evalue": "1",
     "output_type": "error",
     "traceback": []
    }
   ],
   "source": [
    "md5sum -c mydata_md5.txt"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## READ-ONLY"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "drwxr-xr-x 2 jovyan users 4096 Jun 25 17:10 \u001b[0m\u001b[01;34m/tmp/rr_demo\u001b[0m\n",
      "total 12\n",
      "-rw-r--r-- 1 jovyan users  7 Jun 25 17:10 data1.csv\n",
      "-rw-r--r-- 1 jovyan users 88 Jun 25 17:10 mydata_md5.txt\n",
      "-rw-r--r-- 1 jovyan users  7 Jun 25 17:10 data2.csv\n"
     ]
    }
   ],
   "source": [
    "ls -ld $RAWDATA_DIR\n",
    "ls -ltr $RAWDATA_DIR"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "dr-xr-xr-x 2 jovyan users 4096 Jun 25 17:10 \u001b[0m\u001b[01;34m/tmp/rr_demo\u001b[0m\n",
      "total 12\n",
      "-r--r--r-- 1 jovyan users  7 Jun 25 17:10 data1.csv\n",
      "-r--r--r-- 1 jovyan users 88 Jun 25 17:10 mydata_md5.txt\n",
      "-r--r--r-- 1 jovyan users  7 Jun 25 17:10 data2.csv\n"
     ]
    }
   ],
   "source": [
    "chmod -R a-w $RAWDATA_DIR\n",
    "ls -ld $RAWDATA_DIR\n",
    "ls -ltr $RAWDATA_DIR"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Preventing Modification"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "tags": [
     "raises-exception"
    ]
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "bash: /tmp/rr_demo/data2.csv: Permission denied\n"
     ]
    },
    {
     "ename": "",
     "evalue": "1",
     "output_type": "error",
     "traceback": []
    }
   ],
   "source": [
    "echo \"This is not the data you are looking for\" > $DATA2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "tags": [
     "raises-exception"
    ]
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "sed: couldn't open temporary file /tmp/rr_demo/sedzRnyBp: Permission denied\n"
     ]
    },
    {
     "ename": "",
     "evalue": "4",
     "output_type": "error",
     "traceback": []
    }
   ],
   "source": [
    "sed s/7/3/ -i $DATA2"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Preventing Deletion"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "tags": [
     "raises-exception"
    ]
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "rm: cannot remove '/tmp/rr_demo/data1.csv': Permission denied\n",
      "rm: cannot remove '/tmp/rr_demo/data2.csv': Permission denied\n",
      "rm: cannot remove '/tmp/rr_demo/mydata_md5.txt': Permission denied\n"
     ]
    },
    {
     "ename": "",
     "evalue": "1",
     "output_type": "error",
     "traceback": []
    }
   ],
   "source": [
    "rm -rf $RAWDATA_DIR"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Clean up\n",
    "Let's clean up the directory we made.  To do this we need to reset permissions to allow write, otherwise we will get an error again"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "chmod -R a+w $RAWDATA_DIR\n",
    "rm -rf $RAWDATA_DIR"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Bash",
   "language": "bash",
   "name": "bash"
  },
  "language_info": {
   "codemirror_mode": "shell",
   "file_extension": ".sh",
   "mimetype": "text/x-sh",
   "name": "bash"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}