{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Кодировки"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import sys\n",
    "import chardet"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "28"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "x = 10\n",
    "sys.getsizeof(x)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "def f():\n",
    "    \"\"\"\n",
    "    docs\n",
    "    \"\"\"\n",
    "    pass"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'\\n    docs\\n    '"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "f.__doc__"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[49, 80, 84, 88, 92, 96, 100]"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "beer = \"🍺 some\"\n",
    "[sys.getsizeof(beer[:index]) for index in range(len(beer) + 1)]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "easy = \"easy\"\n",
    "изич = \"изич\"\n",
    "易易易易 = \"易易易易\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[49, 50, 51, 52, 53]"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "[sys.getsizeof(easy[:index]) for index in range(len(easy) + 1)]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[49, 76, 78, 80, 82]"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "[sys.getsizeof(изич[:index]) for index in range(len(изич) + 1)]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[49, 76, 78, 80, 82]"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "[sys.getsizeof(易易易易[:index]) for index in range(len(易易易易) + 1)]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(90, 98)"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sys.getsizeof(изич + easy), sys.getsizeof(易易易易 + изич + easy)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "({'confidence': 1.0, 'encoding': 'ascii', 'language': ''},\n",
       " {'confidence': 0.938125, 'encoding': 'utf-8', 'language': ''},\n",
       " {'confidence': 0.938125, 'encoding': 'utf-8', 'language': ''})"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "chardet.detect(easy.encode()), chardet.detect(изич.encode()), chardet.detect(易易易易.encode())"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Задание строк"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "str1 = \"think about 'it'\"\n",
    "\n",
    "str2 = 'синк эбаут \"ит\"'\n",
    "\n",
    "str3 = \"\"\"想想吧 想想吧 想想吧\n",
    "想想吧\n",
    "\"\"\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "think about 'it'\n",
      "синк эбаут \"ит\" \t \" '\n"
     ]
    }
   ],
   "source": [
    "str_escape = str1 + \"\\n\" + str2 + \" \\t \\\" \\'\"\n",
    "print(str_escape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\\n \\t \\\" \\'\n"
     ]
    }
   ],
   "source": [
    "raw_str = r\"\\n \\t \\\" \\'\"\n",
    "print(raw_str)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Строки и Unicode"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import codecs"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "EASY\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "b'EASY'"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "u_str = \"\\u0045\\u0041\\u0053\\u0059\"\n",
    "print(u_str)\n",
    "codecs.encode(u_str)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "('A', 48)"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "chr(65), ord('0')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Функции строк стандартной библиотеки str"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "text = \"\"\"Given a string representing one Unicode character,\n",
    "return an integer representing the Unicode code point of that character.\n",
    "For example, ord('a') returns the integer 97 and ord('€') (Euro sign) returns 8364.\n",
    "This is the inverse of chr().\"\"\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(-1, 78, 10)"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "text.find(\"€\", 180), text.index(\"ing\", 70, 100), text.count(\"a\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Given a string representing one UniEASYode EASYharaEASYter,\n",
      "return an integer representing the UniEASYode EASYode point of that EASYharaEASYter.\n",
      "For example, ord('a') returns the integer 97 and ord('€') (Euro sign) returns 8364.\n",
      "This is the inverse of EASYhr().\n"
     ]
    }
   ],
   "source": [
    "print(text.replace(\"c\", \"EASY\"))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(False, True)"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "text.startswith(\"Givens\"), text.endswith(\".\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(True, True, True, False, True, False)"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "\"easy100500\".isalnum(), \"想想吧\".isalpha(), \"1000\".isdigit(), \"AbCd\".islower(), \"   \".isspace(), \"Sad sad\".istitle()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "('test test', 'TEST TEST', 'Test test', 'Test Test', 'Test Test')"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "\"tEST tEST\".lower(), \"tEST tEST\".upper(), \"tEST tEST\".capitalize(), \"tEST tEST\".title(), \"tEST tEST\".swapcase()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "\"Given a string representing one Unicode character,\\nreturn an integer representing the Unicode code point of that character.\\nFor example, ord('a') returns the integer 97 and ord('€') (Euro sign) returns 8364.\\nThis is the inverse of chr().\""
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "(\"\\n\" + text).strip()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "\"Given a string representing one Unicode character, return an integer representing the Unicode code point of that character. For example, ord('a') returns the integer 97 and ord('€') (Euro sign) returns 8364. This is the inverse of chr().\""
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "' '.join(text.split())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "('Given a string representing one Unicode character,\\nreturn an ',\n",
       " 'integer',\n",
       " \" representing the Unicode code point of that character.\\nFor example, ord('a') returns the integer 97 and ord('€') (Euro sign) returns 8364.\\nThis is the inverse of chr().\")"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "text.partition(\"integer\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "('100       ', '       100', '   100    ')"
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "str(100).ljust(10), str(100).rjust(10), str(100).center(10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'some text 10'"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "x = 10\n",
    "f\"some text {x}\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(True, True)"
      ]
     },
     "execution_count": 31,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "\"integer\" in text, \"Gives\" not in text"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(158, 158)"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "text.rfind(\"int\"), text.rindex(\"int\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(\"Given a string representing one Unicode character,\\nreturn an integer representing the Unicode code point of that character.\\nFor example, ord('a') returns the \",\n",
       " 'int',\n",
       " \"eger 97 and ord('€') (Euro sign) returns 8364.\\nThis is the inverse of chr().\")"
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "text.rpartition(\"int\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import chardet"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "True"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "\"test\".encode(\"utf-8\") in \"some test\".encode(\"utf-8\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Форматирование строк"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Новый стиль"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "fn: Anton, sn: Emelianov\n"
     ]
    }
   ],
   "source": [
    "name = \"Anton\"\n",
    "second_name = \"Emelianov\"\n",
    "print(\"fn: {}, sn: {}\".format(name, second_name))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "fn: Anton, sn: Emelianov\n"
     ]
    }
   ],
   "source": [
    "print(\"fn: {1}, sn: {0}\".format(second_name, name))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "fn: Anton, sn: Emelianov\n"
     ]
    }
   ],
   "source": [
    "print(\"fn: {name}, sn: {second_name}\".format(second_name=second_name, name=name))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "left        10\n",
      "10        right\n",
      "left    10    right\n"
     ]
    }
   ],
   "source": [
    "print(\"left{:>10}\".format(10))\n",
    "print(\"{:<10}right\".format(10))\n",
    "print(\"left{:^10}right\".format(10))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Старый стиль"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "old school 1900 year in town Moscow\n"
     ]
    }
   ],
   "source": [
    "print(\"old school %d year in town %s\" % (1900, \"Moscow\"))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "old school in town Moscow\n"
     ]
    }
   ],
   "source": [
    "print(\"old school in town %s\" % (\"Moscow\"))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Модуль string"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "from string import ascii_lowercase, ascii_uppercase, digits, ascii_letters, punctuation, whitespace"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "('abcdefghijklmnopqrstuvwxyz',\n",
       " 'ABCDEFGHIJKLMNOPQRSTUVWXYZ',\n",
       " '0123456789',\n",
       " 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ',\n",
       " '!\"#$%&\\'()*+,-./:;<=>?@[\\\\]^_`{|}~',\n",
       " ' \\t\\n\\r\\x0b\\x0c')"
      ]
     },
     "execution_count": 41,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ascii_lowercase, ascii_uppercase, digits, ascii_letters, punctuation, whitespace"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Тип bytes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "byte_str = b\"\\xd0\\xbb\\xd0\\xb5\\xd0\\xb3\\xd0\\xba\\xd0\\xbe\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "\"легко\".encode(\"utf-8\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Файлы"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "fin = open(\"buckets.py\", \"r\", encoding=\"utf-8\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "type(fin)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "fout = open(\"buckets_copy.py\", \"w\")\n",
    "for line in fin.readlines():\n",
    "    print(line)\n",
    "    fout.write(line)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "fin.close()\n",
    "fout.close()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "fin.closed, fout.closed"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "with open(\"buckets.py\", \"r\", encoding=\"utf-8\") as fin:\n",
    "    ff = fin.read()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'class Buckets(object):\\n    def __init__(self, length, default):\\n        self.default = default\\n        self.buckets = [default] * length\\n\\n    def add(self, index, element):\\n        self.buckets[index].append(element)\\n\\n    def find(self, index, element):\\n        return element in self.buckets[index]\\n\\n    def clear(self, index):\\n        self.buckets[index] = self.default\\n'"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": []
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Потоки ввода-вывода"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "stdin = sys.stdin.readline()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "sys.stdout.write(\"End of lecture! Yeah!\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "sys.stderr.write(\"Dead\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "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": "3.6.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}