{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Practice - read last line from external file   \n",
    "Python Workbook, chp5  \n",
    "August 7, 2020  (past several days, internet lookup has better solutions)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 0. Check python version, active conda env  "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Python 3.8.2\r\n"
     ]
    }
   ],
   "source": [
    "!python --version"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "# conda environments:\r\n",
      "#\r\n",
      "base                     /home/jyoon/conda3\r\n",
      "dlpy                  *  /home/jyoon/conda3/envs/dlpy\r\n",
      "fluentpy                 /home/jyoon/conda3/envs/fluentpy\r\n",
      "\r\n"
     ]
    }
   ],
   "source": [
    "!conda env list  \n",
    "# * is next to active conda env.  "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 1. Start practice"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Hello! Welcome to demofile.txt\n",
      "This file is for testing purposes.\n",
      "Good Luck!\n",
      "\n"
     ]
    }
   ],
   "source": [
    "f = open('demofile.txt', 'rt')\n",
    "blob = f.read()  # read all \n",
    "print(blob)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "False\n"
     ]
    }
   ],
   "source": [
    "print(f.closed)  # check if f is closed at this point."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Hello! Welcome to demofile.txt\n",
      "\n"
     ]
    }
   ],
   "source": [
    "f = open('demofile.txt')  # Open again to go back to file start point.  \n",
    "line = f.readline()  # read first line, no S\n",
    "print(line)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Good Luck!\n",
      "\n"
     ]
    }
   ],
   "source": [
    "f = open('demofile.txt')\n",
    "lines = f.readlines()  # read all lines, iterable list. With S\n",
    "print(lines[-1])  # print last line\n",
    "f.close()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 2. Binary format reads 'rb'  "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "b'Hello! Welcome to demofile.txt\\n' b'uck!\\n'\n"
     ]
    }
   ],
   "source": [
    "# Try binary format reading.  \n",
    "with open('demofile.txt', 'rb') as f:  # binary format\n",
    "    first = f.readline()\n",
    "    f.seek(-5, 2)  # Go to pointer 5th bytes from end of file \n",
    "    #last = f.read()  # does readline work?  May not read all of the last line.  \n",
    "    last = f.readline()  # readline does work.  Still not all of the line.  \n",
    "    print(first, last)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "b'Hello! Welcome to demofile.txt\\n'\n",
      " b'Good Luck!\\n'\n"
     ]
    }
   ],
   "source": [
    "# Seek from end of file needs a loop.  \n",
    "with open('demofile.txt', 'rb') as f:  # binary format\n",
    "    first = f.readline()\n",
    "    \n",
    "    f.seek(-2, 2)  # Go to pointer 2 bytes relative to end   \n",
    "    while f.read(1) != b\"\\n\":   # while read one byte is not equal to binary '\\n'\n",
    "        f.seek(-2, 1)   # go back 1 byte.  \n",
    "    # after while loop, this is beginning of last line    \n",
    "    last = f.read()  # read all bytes from here.   \n",
    "    # last = f.readline() gives same output.  \n",
    "    \n",
    "    print(str(first)+\"\\n\", str(last))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 3. Good for short files, readlines() all at once, save, index [ ] into each line"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Hello! Welcome to demofile.txt\n",
      " Good Luck!\n",
      "\n",
      "True\n"
     ]
    }
   ],
   "source": [
    "# Good for short text files.  \n",
    "with open('demofile.txt', 'rt') as f:  \n",
    "    lines = f.readlines()\n",
    "    first = lines[0]\n",
    "    last = lines[-1]\n",
    "    print(first, last)\n",
    "\n",
    "print(f.closed)  # check file is cloased after \"with\" block end.  "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 4. seek(0) to go back to start, works with 'rt' "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "lines:  ['Hello! Welcome to demofile.txt\\n', 'This file is for testing purposes.\\n', 'Good Luck!\\n']\n",
      "blob:  Hello! Welcome to demofile.txt\n",
      "This file is for testing purposes.\n",
      "Good Luck!\n",
      "\n",
      "one:  ['Hello! Welcome to demofile.txt\\n']\n",
      "two:  This file is for testing purposes.\n",
      "\n"
     ]
    }
   ],
   "source": [
    "f2 = open('demofile.txt')  \n",
    "lines = f2.readlines()\n",
    "print(\"lines: \", lines)\n",
    "\n",
    "f2.seek(0)  # Goto beginning of file\n",
    "blob= f2.read()\n",
    "print(\"blob: \", blob)\n",
    "\n",
    "f2.seek(0)\n",
    "one = f2.readlines(1)\n",
    "print(\"one: \", one)\n",
    "\n",
    "f2.seek(0)\n",
    "two = f2.readlines()[1]  # Works!  prints 2nd item. nifty. \n",
    "print(\"two: \", two)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 5. Only binary read 'rb' can use relative indexing  "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "b'Hello! Welcome to demofile.txt\\n'\n",
      "b'Good Luck!\\n'\n",
      "77\n",
      "66\n",
      "b'Good Luck!\\n'\n"
     ]
    }
   ],
   "source": [
    "# seek can be used with text format?  \n",
    "# Yes, but can't do relative location other than 0, current point. \n",
    "# If the file is opened in text mode (without ‘b’), only offsets returned by tell() are legal. \n",
    "# none of the relative indexing from back/current location works without 'b' binary format.  \n",
    "\n",
    "with open('demofile.txt', 'rb') as f:  # need to be in binary format\n",
    "    first = f.readline()\n",
    "    print(first)\n",
    "    \n",
    "    f.seek(0, 0)  \n",
    "    last = f.readlines()[2]\n",
    "    print(last)\n",
    " \n",
    "    #f.seek(-2, 2)  # not work, only 0 offset works with 2, 1 mode.  \n",
    "    f.seek(0, 2)  # end of file work with text format file.  \n",
    "    print(f.tell())\n",
    "    f.seek(-11, 1)\n",
    "    print(f.tell())\n",
    "    last = f.read()\n",
    "    print(last) \n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "77\n",
      "0\n",
      "Hello! Welcome to demofile.txt\n",
      " 31\n",
      "Good Luck!\n",
      " 77\n",
      "['This file is for testing purposes.\\n', 'Good Luck!\\n'] 77\n",
      "This file is for testing purposes.\n",
      " 66\n",
      "Good Luck!\n",
      "\n"
     ]
    }
   ],
   "source": [
    "with open('demofile.txt') as f:  # text format again\n",
    "    f.seek(0, 2)  # end of file  \n",
    "    loc = f.tell(); print(loc)\n",
    "    \n",
    "    f.seek(0, 0)  # go back to beginning of tile \n",
    "    print(f.tell())\n",
    "    first = f.readline()\n",
    "    print(first, f.tell())\n",
    "    \n",
    "    last = f.readlines()[-1]\n",
    "    print(last, f.tell())\n",
    "    \n",
    "    f.seek(31, 0)\n",
    "    two = f.readlines()\n",
    "    print(two, f.tell())\n",
    "    \n",
    "    f.seek(31, 0)\n",
    "    second = f.readline()\n",
    "    print(second, f.tell())\n",
    "    \n",
    "    third = f.readline()\n",
    "    print(third)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 6. Doen't solve large file last line problem, but another way to move around 'rt' format."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "77\n",
      "11\n",
      "66\n",
      "Good Luck!\n",
      "\n"
     ]
    }
   ],
   "source": [
    "with open('demofile.txt') as f:  # text format again\n",
    "    \n",
    "    # num_ln = len(f.readlines()); print(num_ln)\n",
    "    \n",
    "    num_ch_all = len(f.read())\n",
    "    print(num_ch_all)\n",
    "    \n",
    "    f.seek(0)  # back to beginning\n",
    "    num_ch_last = len(f.readlines()[-1]); \n",
    "    print(num_ch_last)\n",
    "    \n",
    "    offset = num_ch_all - num_ch_last  # offset from file beginning\n",
    "    f.seek(offset, 0)\n",
    "    print(f.tell())\n",
    "    print(f.read())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3.8.2 64-bit ('dlpy': conda)",
   "language": "python",
   "name": "python38264bitdlpycondaee83557e2f484524a67e008c475209c4"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.8.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}