{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "This is a work-in-progress for some future cohpy meeting."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Lastly, uses names to refer to parts of a string that match a regular expression is fantastic!  It makes the code much more readable than using meaningless numerical indexes.\n",
    "\n",
    "This was new to a Python expert who now loves it,\n",
    "although his still prefers to eschew regular expressions\n",
    "because they are hard to read.\n",
    "\n",
    "Imagine the following contrived example,\n",
    "where I want to get the hash of an git object from its filepath."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "s = '.git/objects/8e/28241360c472576e8caa944253d4af368d9081'\n",
    "\n",
    "import re\n",
    "git_pattern = re.compile(r'''\n",
    "    .*/                      # anything and a slash\n",
    "    (\n",
    "        ([0-9a-fA-F]{2})     # 2 hexadecimal digits\n",
    "        /                    # separated by a slash\n",
    "        ([0-9a-fA-F]{38})    # 38 hexadecimal digits\n",
    "    )$''', flags=re.VERBOSE)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<_sre.SRE_Match object; span=(0, 54), match='.git/objects/8e/28241360c472576e8caa944253d4af368>"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "m = git_pattern.match(s)\n",
    "m"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'.git/objects/8e/28241360c472576e8caa944253d4af368d9081'"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "m.group(0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'8e/28241360c472576e8caa944253d4af368d9081'"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "m.group(1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'8e'"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "m.group(2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'28241360c472576e8caa944253d4af368d9081'"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "m.group(3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Help on function compile in module re:\n",
      "\n",
      "compile(pattern, flags=0)\n",
      "    Compile a regular expression pattern, returning a pattern object.\n",
      "\n"
     ]
    }
   ],
   "source": [
    "help(re.compile)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "s = '.git/objects/8e/28241360c472576e8caa944253d4af368d9081'\n",
    "\n",
    "import re\n",
    "git_pattern = re.compile(r'''\n",
    "    .*/                      # anything and a slash\n",
    "    (?P<hash_with_slash>\n",
    "        (?P<hash_directory> [0-9a-fA-F]{2})     # 2 hexadecimal digits\n",
    "        /                    # separated by a slash\n",
    "        (?P<hash_filename> [0-9a-fA-F]{38})    # 38 hexadecimal digits\n",
    "    )$''', flags=re.VERBOSE)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<_sre.SRE_Match object; span=(0, 54), match='.git/objects/8e/28241360c472576e8caa944253d4af368>"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "m = git_pattern.match(s)\n",
    "m"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'8e'"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "m.group(2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'8e'"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "m.group('hash_directory')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'28241360c472576e8caa944253d4af368d9081'"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "m.group(3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'28241360c472576e8caa944253d4af368d9081'"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "m.group('hash_filename')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'8e28241360c472576e8caa944253d4af368d9081'"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "hash = m.group('hash_directory') + m.group('hash_filename')\n",
    "hash"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'8e28241360c472576e8caa944253d4af368d9081'"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "hash = ''.join(map(m.group, ('hash_directory', 'hash_filename')))\n",
    "hash"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'8e28241360c472576e8caa944253d4af368d9081'"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "hash = ''.join(map(lambda s: m.group('hash_%s' % s), ('directory', 'filename')))\n",
    "hash"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'8e/28241360c472576e8caa944253d4af368d9081'"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "m.group(1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'8e/28241360c472576e8caa944253d4af368d9081'"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "m.group('hash_with_slash')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'8e28241360c472576e8caa944253d4af368d9081'"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "hash = ''.join(c for c in m.group('hash_with_slash') if c != '/')\n",
    "hash"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'.git/objects/8e/28241360c472576e8caa944253d4af368d9081'"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "s"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "s = '8e/28241360c472576e8caa944253d4af368d9081'\n",
    "m = git_pattern.match(s)\n",
    "m"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'None'"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "repr(m)"
   ]
  }
 ],
 "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": "3.5.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}