validate-desktop-date-header

validate-desktop-date-header.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## [Bug 1144778](https://bugzilla.mozilla.org/show_bug.cgi?id=1144778) - Validate the Date header submissions"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "import ujson as json\n",
    "import matplotlib.pyplot as plt\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "import plotly.plotly as py\n",
    "from plotly.graph_objs import *\n",
    "import re\n",
    "import email.utils as eut\n",
    "import datetime\n",
    "import time\n",
    "\n",
    "from moztelemetry import get_pings, get_pings_properties, get_one_ping_per_client, get_clients_history, get_records"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "pings = get_pings(sc,\n",
    "                  app=\"Firefox\",\n",
    "                  channel=\"nightly\",\n",
    "                  build_id=(\"20160520000000\", \"20160524999999\"),\n",
    "                  fraction=0.1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "properties = [\n",
    "    'meta/Date',\n",
    "    'meta/submissionDate',\n",
    "    'clientId'\n",
    "]\n",
    "pings = get_pings_properties(pings, properties)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'clientId': u'95c6432b-1cd8-46ad-86a5-5386e5023a7b',\n",
       " 'meta/Date': u'Tue, 24 May 2016 02:27:45 GMT',\n",
       " 'meta/submissionDate': u'20160524'}"
      ]
     },
     "execution_count": 41,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pings.first()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Validate the expected ping contents."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "def valid_date_header(s):\n",
    "    date_pattern = '^\\D+, \\d{1,2} \\D+ \\d{4,4} \\d\\d:\\d\\d:\\d\\d GMT(\\\\+00:00)?$'\n",
    "    return re.match(date_pattern, s) != None"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "def ping_check(ping):\n",
    "    props = {\n",
    "        'meta/Date': [unicode],\n",
    "        'meta/submissionDate': [unicode],\n",
    "        'clientId': [unicode],\n",
    "    }\n",
    "\n",
    "    for k,types in props.iteritems():\n",
    "        if not k in ping:\n",
    "            return 'missing field: ' + prop\n",
    "        if type(ping[k]) not in types:\n",
    "            return 'wrong type for ' + k\n",
    "    \n",
    "    if not valid_date_header(ping['meta/Date']):\n",
    "        return 'invalid date header'\n",
    "\n",
    "    return 'valid'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "defaultdict(int, {'valid': 18505, 'wrong type for meta/Date': 381})"
      ]
     },
     "execution_count": 44,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "results = pings.map(lambda p: (ping_check(p), p))\n",
    "results.countByKey()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "So a subset of the pings are missing the meta/Date field.\n",
    "This might be local developer builds with \"official\" build flags that don't have the Date header changes yet but submit on up-to-date build ids."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Lets show examples for each result group."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[('wrong type for meta/Date',\n",
       "  {'clientId': '...', 'meta/Date': None, 'meta/submissionDate': u'20160524'}),\n",
       " ('valid',\n",
       "  {'clientId': '...',\n",
       "   'meta/Date': u'Tue, 24 May 2016 15:48:15 GMT',\n",
       "   'meta/submissionDate': u'20160524'})]"
      ]
     },
     "execution_count": 45,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ps = results.groupByKey().map(lambda t: (t[0], list(t[1])[0])).collect()\n",
    "for k,p in ps:\n",
    "    p['clientId'] = '...'\n",
    "ps"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  }
 ],
 "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
}

validate-desktop-date-header.py

# coding: utf-8

# ## [Bug 1144778](https://bugzilla.mozilla.org/show_bug.cgi?id=1144778) - Validate the Date header submissions

# In[38]:

import ujson as json
import matplotlib.pyplot as plt
import pandas as pd
import numpy as np
import plotly.plotly as py
from plotly.graph_objs import *
import re
import email.utils as eut
import datetime
import time

from moztelemetry import get_pings, get_pings_properties, get_one_ping_per_client, get_clients_history, get_records


# In[39]:

pings = get_pings(sc,
                  app="Firefox",
                  channel="nightly",
                  build_id=("20160520000000", "20160524999999"),
                  fraction=0.1)


# In[40]:

properties = [
    'meta/Date',
    'meta/submissionDate',
    'clientId'
]
pings = get_pings_properties(pings, properties)


# In[41]:

pings.first()


# ### Validate the expected ping contents.

# In[42]:

def valid_date_header(s):
    date_pattern = '^\D+, \d{1,2} \D+ \d{4,4} \d\d:\d\d:\d\d GMT(\\+00:00)?$'
    return re.match(date_pattern, s) != None


# In[43]:

def ping_check(ping):
    props = {
        'meta/Date': [unicode],
        'meta/submissionDate': [unicode],
        'clientId': [unicode],
    }

    for k,types in props.iteritems():
        if not k in ping:
            return 'missing field: ' + prop
        if type(ping[k]) not in types:
            return 'wrong type for ' + k
    
    if not valid_date_header(ping['meta/Date']):
        return 'invalid date header'

    return 'valid'


# In[44]:

results = pings.map(lambda p: (ping_check(p), p))
results.countByKey()


# So a subset of the pings are missing the meta/Date field.
# This might be local developer builds with "official" build flags that don't have the Date header changes yet but submit on up-to-date build ids.

# Lets show examples for each result group.

# In[45]:

ps = results.groupByKey().map(lambda t: (t[0], list(t[1])[0])).collect()
for k,p in ps:
    p['clientId'] = '...'
ps


# In[ ]: