Recipe for creating iris-grib

make-iris-grib.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Recipe to initialise iris-grib repo"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Cloning into 'iris-grib'...\n",
      "remote: Counting objects: 37557, done.\u001b[K\n",
      "remote: Compressing objects: 100% (5/5), done.\u001b[K\n",
      "remote: Total 37557 (delta 1), reused 0 (delta 0), pack-reused 37551\u001b[K\n",
      "Receiving objects: 100% (37557/37557), 97.80 MiB | 1.15 MiB/s, done.\n",
      "Resolving deltas: 100% (26013/26013), done.\n",
      "Checking connectivity... done.\n"
     ]
    }
   ],
   "source": [
    "!git clone git@github.com:SciTools/iris.git iris-grib"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "/home/richard/git/iris-grib\n"
     ]
    }
   ],
   "source": [
    "cd iris-grib"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Remove all the files that don't contain \"grib\"\n",
    "\n",
    "Also keep the licence definition files."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1595\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "['test_um_to_pp.py',\n",
       " 'PuRd_09.txt',\n",
       " '_constraints.py',\n",
       " 'test_std_names.py',\n",
       " 'simple5_midpoint.cml']"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "grib_names = !git ls-files | grep grib | xargs -n 1 basename\n",
    "all_names = !git ls-files | xargs -n 1 basename\n",
    "dross_names = set(all_names) - set(grib_names) - set(['COPYING', 'COPYING.LESSER'])\n",
    "\n",
    "print len(dross_names)\n",
    "list(dross_names)[:5]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import subprocess\n",
    "BFG_PATH = '/home/richard/Downloads/bfg-1.12.12.jar'\n",
    "dross = ','.join(list(dross_names)[:])\n",
    "arg = '{' + dross + '}'\n",
    "subprocess.check_call(['java', '-jar', BFG_PATH, '--no-blob-protection', '--delete-files', arg])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Remove irrelevant directories"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dir_names = ['tools', 'docs', 'analysis', 'experimental', 'io', 'runner',\n",
    "             'concatenate', 'plot', 'format_interop', '_pyke_rules', 'um',\n",
    "             'cf', 'pp', 'ff', 'quickplot', 'aux_factory', 'netcdf',\n",
    "             'name_loaders', 'abf', 'pp_rules', 'nimrod_load_rules',\n",
    "             'pyke_rules', 'coords', 'cube', 'coord_systems', 'util'\n",
    "             'coord_categorisation', 'merge', 'system', 'name_grib',\n",
    "             'cdm', 'COLPEX', 'coord_api', 'FF', 'regrid', 'trajectory',\n",
    "             'trui', 'usecases', 'xml']\n",
    "arg = '{' + ','.join(dir_names) + '}'\n",
    "subprocess.check_call(['java', '-jar', BFG_PATH, '--no-blob-protection', '--delete-folders', arg])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Clean out redundant commits"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Writing rewrite_parents.rb\n"
     ]
    }
   ],
   "source": [
    "%%writefile rewrite_parents.rb\n",
    "#!/usr/bin/ruby \n",
    "old_parents = gets.chomp.gsub('-p ', ' ') \n",
    "\n",
    "if old_parents.empty? then \n",
    "    new_parents = [] \n",
    "else \n",
    "    new_parents = `git show-branch --independent #{old_parents}`.split \n",
    "end \n",
    "\n",
    "puts new_parents.map{|p| '-p ' + p}.join(' ')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "!chmod u+x rewrite_parents.rb"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "!git reset HEAD\n",
    "pruned = !git filter-branch -f --prune-empty --parent-filter `readlink -f rewrite_parents.rb` -- --all"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Tidy up"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "!git reflog expire --expire=now --all"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Counting objects: 10922, done.\n",
      "Delta compression using up to 2 threads.\n",
      "Compressing objects: 100% (9823/9823), done.\n",
      "Writing objects: 100% (10922/10922), done.\n",
      "Total 10922 (delta 5685), reused 521 (delta 0)\n"
     ]
    }
   ],
   "source": [
    "!git gc --prune=now --aggressive"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "cleaned = !git clean -fdx"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 2",
   "language": "python",
   "name": "python2"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.11"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}