blob: 491ce778d9c7353af2af36e58c889657cc2e47a2 [file] [log] [blame]
<!DOCTYPE html>
<!--[if IE 8]><html class="no-js lt-ie9" lang="en" > <![endif]-->
<!--[if gt IE 8]><!--> <html class="no-js" lang="en" > <!--<![endif]-->
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>airflow.contrib.hooks.salesforce_hook &mdash; Airflow Documentation</title>
<script type="text/javascript" src="../../../../_static/js/modernizr.min.js"></script>
<script type="text/javascript" id="documentation_options" data-url_root="../../../../" src="../../../../_static/documentation_options.js"></script>
<script type="text/javascript" src="../../../../_static/jquery.js"></script>
<script type="text/javascript" src="../../../../_static/underscore.js"></script>
<script type="text/javascript" src="../../../../_static/doctools.js"></script>
<script type="text/javascript" src="../../../../_static/language_data.js"></script>
<script type="text/javascript" src="../../../../_static/js/theme.js"></script>
<link rel="stylesheet" href="../../../../_static/css/theme.css" type="text/css" />
<link rel="stylesheet" href="../../../../_static/pygments.css" type="text/css" />
<link rel="index" title="Index" href="../../../../genindex.html" />
<link rel="search" title="Search" href="../../../../search.html" />
<script>
document.addEventListener('DOMContentLoaded', function() {
var el = document.getElementById('changelog');
if (el !== null ) {
// [AIRFLOW-...]
el.innerHTML = el.innerHTML.replace(
/\[(AIRFLOW-[\d]+)\]/g,
`<a href="https://issues.apache.org/jira/browse/$1">[$1]</a>`
);
// (#...)
el.innerHTML = el.innerHTML.replace(
/\(#([\d]+)\)/g,
`<a href="https://github.com/apache/airflow/pull/$1">(#$1)</a>`
);
};
})
</script>
<style>
.example-header {
position: relative;
background: #9AAA7A;
padding: 8px 16px;
margin-bottom: 0;
}
.example-header--with-button {
padding-right: 166px;
}
.example-header:after{
content: '';
display: table;
clear: both;
}
.example-title {
display:block;
padding: 4px;
margin-right: 16px;
color: white;
overflow-x: auto;
}
.example-header-button {
top: 8px;
right: 16px;
position: absolute;
}
.example-header + .highlight-python {
margin-top: 0 !important;
}
.viewcode-button {
display: inline-block;
padding: 8px 16px;
border: 0;
margin: 0;
outline: 0;
border-radius: 2px;
-webkit-box-shadow: 0 3px 5px 0 rgba(0,0,0,.3);
box-shadow: 0 3px 6px 0 rgba(0,0,0,.3);
color: #404040;
background-color: #e7e7e7;
cursor: pointer;
font-size: 16px;
font-weight: 500;
line-height: 1;
text-decoration: none;
text-overflow: ellipsis;
overflow: hidden;
text-transform: uppercase;
-webkit-transition: background-color .2s;
transition: background-color .2s;
vertical-align: middle;
white-space: nowrap;
}
.viewcode-button:visited {
color: #404040;
}
.viewcode-button:hover, .viewcode-button:focus {
color: #404040;
background-color: #d6d6d6;
}
</style>
</head>
<body class="wy-body-for-nav">
<div class="wy-grid-for-nav">
<nav data-toggle="wy-nav-shift" class="wy-nav-side">
<div class="wy-side-scroll">
<div class="wy-side-nav-search" >
<a href="../../../../index.html" class="icon icon-home"> Airflow
</a>
<div class="version">
1.10.3
</div>
<div role="search">
<form id="rtd-search-form" class="wy-form" action="../../../../search.html" method="get">
<input type="text" name="q" placeholder="Search docs" />
<input type="hidden" name="check_keywords" value="yes" />
<input type="hidden" name="area" value="default" />
</form>
</div>
</div>
<div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation">
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../../../project.html">Project</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../license.html">License</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../start.html">Quick Start</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../installation.html">Installation</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../tutorial.html">Tutorial</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../howto/index.html">How-to Guides</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../ui.html">UI / Screenshots</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../concepts.html">Concepts</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../profiling.html">Data Profiling</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../cli.html">Command Line Interface</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../scheduler.html">Scheduling &amp; Triggers</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../plugins.html">Plugins</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../security.html">Security</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../timezone.html">Time zones</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../api.html">Experimental Rest API</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../integration.html">Integration</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../metrics.html">Metrics</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../kubernetes.html">Kubernetes</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../lineage.html">Lineage</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../changelog.html">Changelog</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../faq.html">FAQ</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../macros.html">Macros reference</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../_api/index.html">API Reference</a></li>
</ul>
</div>
</div>
</nav>
<section data-toggle="wy-nav-shift" class="wy-nav-content-wrap">
<nav class="wy-nav-top" aria-label="top navigation">
<i data-toggle="wy-nav-top" class="fa fa-bars"></i>
<a href="../../../../index.html">Airflow</a>
</nav>
<div class="wy-nav-content">
<div class="rst-content">
<div role="navigation" aria-label="breadcrumbs navigation">
<ul class="wy-breadcrumbs">
<li><a href="../../../../index.html">Docs</a> &raquo;</li>
<li><a href="../../../index.html">Module code</a> &raquo;</li>
<li><a href="../hooks.html">airflow.contrib.hooks</a> &raquo;</li>
<li>airflow.contrib.hooks.salesforce_hook</li>
<li class="wy-breadcrumbs-aside">
</li>
</ul>
<hr/>
</div>
<div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
<div itemprop="articleBody">
<h1>Source code for airflow.contrib.hooks.salesforce_hook</h1><div class="highlight"><pre>
<span></span><span class="c1"># -*- coding: utf-8 -*-</span>
<span class="c1">#</span>
<span class="c1"># Licensed to the Apache Software Foundation (ASF) under one</span>
<span class="c1"># or more contributor license agreements. See the NOTICE file</span>
<span class="c1"># distributed with this work for additional information</span>
<span class="c1"># regarding copyright ownership. The ASF licenses this file</span>
<span class="c1"># to you under the Apache License, Version 2.0 (the</span>
<span class="c1"># &quot;License&quot;); you may not use this file except in compliance</span>
<span class="c1"># with the License. You may obtain a copy of the License at</span>
<span class="c1">#</span>
<span class="c1"># http://www.apache.org/licenses/LICENSE-2.0</span>
<span class="c1">#</span>
<span class="c1"># Unless required by applicable law or agreed to in writing,</span>
<span class="c1"># software distributed under the License is distributed on an</span>
<span class="c1"># &quot;AS IS&quot; BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY</span>
<span class="c1"># KIND, either express or implied. See the License for the</span>
<span class="c1"># specific language governing permissions and limitations</span>
<span class="c1"># under the License.</span>
<span class="c1">#</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd">This module contains a Salesforce Hook</span>
<span class="sd">which allows you to connect to your Salesforce instance,</span>
<span class="sd">retrieve data from it, and write that data to a file</span>
<span class="sd">for other uses.</span>
<span class="sd">NOTE: this hook also relies on the simple_salesforce package:</span>
<span class="sd"> https://github.com/simple-salesforce/simple-salesforce</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="kn">from</span> <span class="nn">simple_salesforce</span> <span class="k">import</span> <span class="n">Salesforce</span>
<span class="kn">from</span> <span class="nn">airflow.hooks.base_hook</span> <span class="k">import</span> <span class="n">BaseHook</span>
<span class="kn">import</span> <span class="nn">json</span>
<span class="kn">import</span> <span class="nn">pandas</span> <span class="k">as</span> <span class="nn">pd</span>
<span class="kn">import</span> <span class="nn">time</span>
<span class="kn">from</span> <span class="nn">airflow.utils.log.logging_mixin</span> <span class="k">import</span> <span class="n">LoggingMixin</span>
<div class="viewcode-block" id="SalesforceHook"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/salesforce_hook/index.html#airflow.contrib.hooks.salesforce_hook.SalesforceHook">[docs]</a><span class="k">class</span> <span class="nc">SalesforceHook</span><span class="p">(</span><span class="n">BaseHook</span><span class="p">):</span>
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span>
<span class="bp">self</span><span class="p">,</span>
<span class="n">conn_id</span><span class="p">,</span>
<span class="o">*</span><span class="n">args</span><span class="p">,</span>
<span class="o">**</span><span class="n">kwargs</span>
<span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Create new connection to Salesforce</span>
<span class="sd"> and allows you to pull data out of SFDC and save it to a file.</span>
<span class="sd"> You can then use that file with other</span>
<span class="sd"> Airflow operators to move the data into another data source</span>
<span class="sd"> :param conn_id: the name of the connection that has the parameters</span>
<span class="sd"> we need to connect to Salesforce.</span>
<span class="sd"> The connection should be type `http` and include a</span>
<span class="sd"> user&#39;s security token in the `Extras` field.</span>
<span class="sd"> .. note::</span>
<span class="sd"> For the HTTP connection type, you can include a</span>
<span class="sd"> JSON structure in the `Extras` field.</span>
<span class="sd"> We need a user&#39;s security token to connect to Salesforce.</span>
<span class="sd"> So we define it in the `Extras` field as:</span>
<span class="sd"> `{&quot;security_token&quot;:&quot;YOUR_SECURITY_TOKEN&quot;}`</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="bp">self</span><span class="o">.</span><span class="n">conn_id</span> <span class="o">=</span> <span class="n">conn_id</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_args</span> <span class="o">=</span> <span class="n">args</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_kwargs</span> <span class="o">=</span> <span class="n">kwargs</span>
<span class="c1"># get the connection parameters</span>
<span class="bp">self</span><span class="o">.</span><span class="n">connection</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_connection</span><span class="p">(</span><span class="n">conn_id</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">extras</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">connection</span><span class="o">.</span><span class="n">extra_dejson</span>
<div class="viewcode-block" id="SalesforceHook.sign_in"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/salesforce_hook/index.html#airflow.contrib.hooks.salesforce_hook.SalesforceHook.sign_in">[docs]</a> <span class="k">def</span> <span class="nf">sign_in</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Sign into Salesforce.</span>
<span class="sd"> If we have already signed it, this will just return the original object</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">if</span> <span class="nb">hasattr</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="s1">&#39;sf&#39;</span><span class="p">):</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">sf</span>
<span class="c1"># connect to Salesforce</span>
<span class="n">sf</span> <span class="o">=</span> <span class="n">Salesforce</span><span class="p">(</span>
<span class="n">username</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">connection</span><span class="o">.</span><span class="n">login</span><span class="p">,</span>
<span class="n">password</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">connection</span><span class="o">.</span><span class="n">password</span><span class="p">,</span>
<span class="n">security_token</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">extras</span><span class="p">[</span><span class="s1">&#39;security_token&#39;</span><span class="p">],</span>
<span class="n">instance_url</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">connection</span><span class="o">.</span><span class="n">host</span><span class="p">,</span>
<span class="n">sandbox</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">extras</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">&#39;sandbox&#39;</span><span class="p">,</span> <span class="kc">False</span><span class="p">)</span>
<span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">sf</span> <span class="o">=</span> <span class="n">sf</span>
<span class="k">return</span> <span class="n">sf</span></div>
<div class="viewcode-block" id="SalesforceHook.make_query"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/salesforce_hook/index.html#airflow.contrib.hooks.salesforce_hook.SalesforceHook.make_query">[docs]</a> <span class="k">def</span> <span class="nf">make_query</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">query</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Make a query to Salesforce. Returns result in dictionary</span>
<span class="sd"> :param query: The query to make to Salesforce</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="bp">self</span><span class="o">.</span><span class="n">sign_in</span><span class="p">()</span>
<span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s2">&quot;Querying for all objects&quot;</span><span class="p">)</span>
<span class="n">query</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">sf</span><span class="o">.</span><span class="n">query_all</span><span class="p">(</span><span class="n">query</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">info</span><span class="p">(</span>
<span class="s2">&quot;Received results: Total size: </span><span class="si">%s</span><span class="s2">; Done: </span><span class="si">%s</span><span class="s2">&quot;</span><span class="p">,</span>
<span class="n">query</span><span class="p">[</span><span class="s1">&#39;totalSize&#39;</span><span class="p">],</span> <span class="n">query</span><span class="p">[</span><span class="s1">&#39;done&#39;</span><span class="p">]</span>
<span class="p">)</span>
<span class="n">query</span> <span class="o">=</span> <span class="n">json</span><span class="o">.</span><span class="n">loads</span><span class="p">(</span><span class="n">json</span><span class="o">.</span><span class="n">dumps</span><span class="p">(</span><span class="n">query</span><span class="p">))</span>
<span class="k">return</span> <span class="n">query</span></div>
<div class="viewcode-block" id="SalesforceHook.describe_object"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/salesforce_hook/index.html#airflow.contrib.hooks.salesforce_hook.SalesforceHook.describe_object">[docs]</a> <span class="k">def</span> <span class="nf">describe_object</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">obj</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Get the description of an object from Salesforce.</span>
<span class="sd"> This description is the object&#39;s schema</span>
<span class="sd"> and some extra metadata that Salesforce stores for each object</span>
<span class="sd"> :param obj: Name of the Salesforce object</span>
<span class="sd"> that we are getting a description of.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="bp">self</span><span class="o">.</span><span class="n">sign_in</span><span class="p">()</span>
<span class="k">return</span> <span class="n">json</span><span class="o">.</span><span class="n">loads</span><span class="p">(</span><span class="n">json</span><span class="o">.</span><span class="n">dumps</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">sf</span><span class="o">.</span><span class="fm">__getattr__</span><span class="p">(</span><span class="n">obj</span><span class="p">)</span><span class="o">.</span><span class="n">describe</span><span class="p">()))</span></div>
<div class="viewcode-block" id="SalesforceHook.get_available_fields"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/salesforce_hook/index.html#airflow.contrib.hooks.salesforce_hook.SalesforceHook.get_available_fields">[docs]</a> <span class="k">def</span> <span class="nf">get_available_fields</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">obj</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Get a list of all available fields for an object.</span>
<span class="sd"> This only returns the names of the fields.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="bp">self</span><span class="o">.</span><span class="n">sign_in</span><span class="p">()</span>
<span class="n">desc</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">describe_object</span><span class="p">(</span><span class="n">obj</span><span class="p">)</span>
<span class="k">return</span> <span class="p">[</span><span class="n">f</span><span class="p">[</span><span class="s1">&#39;name&#39;</span><span class="p">]</span> <span class="k">for</span> <span class="n">f</span> <span class="ow">in</span> <span class="n">desc</span><span class="p">[</span><span class="s1">&#39;fields&#39;</span><span class="p">]]</span></div>
<span class="nd">@staticmethod</span>
<div class="viewcode-block" id="SalesforceHook._build_field_list"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/salesforce_hook/index.html#airflow.contrib.hooks.salesforce_hook.SalesforceHook._build_field_list">[docs]</a> <span class="k">def</span> <span class="nf">_build_field_list</span><span class="p">(</span><span class="n">fields</span><span class="p">):</span>
<span class="c1"># join all of the fields in a comma separated list</span>
<span class="k">return</span> <span class="s2">&quot;,&quot;</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">fields</span><span class="p">)</span></div>
<div class="viewcode-block" id="SalesforceHook.get_object_from_salesforce"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/salesforce_hook/index.html#airflow.contrib.hooks.salesforce_hook.SalesforceHook.get_object_from_salesforce">[docs]</a> <span class="k">def</span> <span class="nf">get_object_from_salesforce</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">obj</span><span class="p">,</span> <span class="n">fields</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Get all instances of the `object` from Salesforce.</span>
<span class="sd"> For each model, only get the fields specified in fields.</span>
<span class="sd"> All we really do underneath the hood is run:</span>
<span class="sd"> SELECT &lt;fields&gt; FROM &lt;obj&gt;;</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">field_string</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_build_field_list</span><span class="p">(</span><span class="n">fields</span><span class="p">)</span>
<span class="n">query</span> <span class="o">=</span> <span class="s2">&quot;SELECT </span><span class="si">{0}</span><span class="s2"> FROM </span><span class="si">{1}</span><span class="s2">&quot;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">field_string</span><span class="p">,</span> <span class="n">obj</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">info</span><span class="p">(</span>
<span class="s2">&quot;Making query to Salesforce: </span><span class="si">%s</span><span class="s2">&quot;</span><span class="p">,</span>
<span class="n">query</span> <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">query</span><span class="p">)</span> <span class="o">&lt;</span> <span class="mi">30</span> <span class="k">else</span> <span class="s2">&quot; ... &quot;</span><span class="o">.</span><span class="n">join</span><span class="p">([</span><span class="n">query</span><span class="p">[:</span><span class="mi">15</span><span class="p">],</span> <span class="n">query</span><span class="p">[</span><span class="o">-</span><span class="mi">15</span><span class="p">:]])</span>
<span class="p">)</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">make_query</span><span class="p">(</span><span class="n">query</span><span class="p">)</span></div>
<span class="nd">@classmethod</span>
<div class="viewcode-block" id="SalesforceHook._to_timestamp"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/salesforce_hook/index.html#airflow.contrib.hooks.salesforce_hook.SalesforceHook._to_timestamp">[docs]</a> <span class="k">def</span> <span class="nf">_to_timestamp</span><span class="p">(</span><span class="bp">cls</span><span class="p">,</span> <span class="n">col</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Convert a column of a dataframe to UNIX timestamps if applicable</span>
<span class="sd"> :param col: A Series object representing a column of a dataframe.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="c1"># try and convert the column to datetimes</span>
<span class="c1"># the column MUST have a four digit year somewhere in the string</span>
<span class="c1"># there should be a better way to do this,</span>
<span class="c1"># but just letting pandas try and convert every column without a format</span>
<span class="c1"># caused it to convert floats as well</span>
<span class="c1"># For example, a column of integers</span>
<span class="c1"># between 0 and 10 are turned into timestamps</span>
<span class="c1"># if the column cannot be converted,</span>
<span class="c1"># just return the original column untouched</span>
<span class="k">try</span><span class="p">:</span>
<span class="n">col</span> <span class="o">=</span> <span class="n">pd</span><span class="o">.</span><span class="n">to_datetime</span><span class="p">(</span><span class="n">col</span><span class="p">)</span>
<span class="k">except</span> <span class="ne">ValueError</span><span class="p">:</span>
<span class="n">log</span> <span class="o">=</span> <span class="n">LoggingMixin</span><span class="p">()</span><span class="o">.</span><span class="n">log</span>
<span class="n">log</span><span class="o">.</span><span class="n">warning</span><span class="p">(</span>
<span class="s2">&quot;Could not convert field to timestamps: </span><span class="si">%s</span><span class="s2">&quot;</span><span class="p">,</span> <span class="n">col</span><span class="o">.</span><span class="n">name</span>
<span class="p">)</span>
<span class="k">return</span> <span class="n">col</span>
<span class="c1"># now convert the newly created datetimes into timestamps</span>
<span class="c1"># we have to be careful here</span>
<span class="c1"># because NaT cannot be converted to a timestamp</span>
<span class="c1"># so we have to return NaN</span>
<span class="n">converted</span> <span class="o">=</span> <span class="p">[]</span>
<span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="n">col</span><span class="p">:</span>
<span class="k">try</span><span class="p">:</span>
<span class="n">converted</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">i</span><span class="o">.</span><span class="n">timestamp</span><span class="p">())</span>
<span class="k">except</span> <span class="ne">ValueError</span><span class="p">:</span>
<span class="n">converted</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">pd</span><span class="o">.</span><span class="n">np</span><span class="o">.</span><span class="n">NaN</span><span class="p">)</span>
<span class="k">except</span> <span class="ne">AttributeError</span><span class="p">:</span>
<span class="n">converted</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">pd</span><span class="o">.</span><span class="n">np</span><span class="o">.</span><span class="n">NaN</span><span class="p">)</span>
<span class="c1"># return a new series that maintains the same index as the original</span>
<span class="k">return</span> <span class="n">pd</span><span class="o">.</span><span class="n">Series</span><span class="p">(</span><span class="n">converted</span><span class="p">,</span> <span class="n">index</span><span class="o">=</span><span class="n">col</span><span class="o">.</span><span class="n">index</span><span class="p">)</span></div>
<div class="viewcode-block" id="SalesforceHook.write_object_to_file"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/salesforce_hook/index.html#airflow.contrib.hooks.salesforce_hook.SalesforceHook.write_object_to_file">[docs]</a> <span class="k">def</span> <span class="nf">write_object_to_file</span><span class="p">(</span>
<span class="bp">self</span><span class="p">,</span>
<span class="n">query_results</span><span class="p">,</span>
<span class="n">filename</span><span class="p">,</span>
<span class="n">fmt</span><span class="o">=</span><span class="s2">&quot;csv&quot;</span><span class="p">,</span>
<span class="n">coerce_to_timestamp</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
<span class="n">record_time_added</span><span class="o">=</span><span class="kc">False</span>
<span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Write query results to file.</span>
<span class="sd"> Acceptable formats are:</span>
<span class="sd"> - csv:</span>
<span class="sd"> comma-separated-values file. This is the default format.</span>
<span class="sd"> - json:</span>
<span class="sd"> JSON array. Each element in the array is a different row.</span>
<span class="sd"> - ndjson:</span>
<span class="sd"> JSON array but each element is new-line delimited</span>
<span class="sd"> instead of comma delimited like in `json`</span>
<span class="sd"> This requires a significant amount of cleanup.</span>
<span class="sd"> Pandas doesn&#39;t handle output to CSV and json in a uniform way.</span>
<span class="sd"> This is especially painful for datetime types.</span>
<span class="sd"> Pandas wants to write them as strings in CSV,</span>
<span class="sd"> but as millisecond Unix timestamps.</span>
<span class="sd"> By default, this function will try and leave all values as</span>
<span class="sd"> they are represented in Salesforce.</span>
<span class="sd"> You use the `coerce_to_timestamp` flag to force all datetimes</span>
<span class="sd"> to become Unix timestamps (UTC).</span>
<span class="sd"> This is can be greatly beneficial as it will make all of your</span>
<span class="sd"> datetime fields look the same,</span>
<span class="sd"> and makes it easier to work with in other database environments</span>
<span class="sd"> :param query_results: the results from a SQL query</span>
<span class="sd"> :param filename: the name of the file where the data</span>
<span class="sd"> should be dumped to</span>
<span class="sd"> :param fmt: the format you want the output in.</span>
<span class="sd"> *Default:* csv.</span>
<span class="sd"> :param coerce_to_timestamp: True if you want all datetime fields to be</span>
<span class="sd"> converted into Unix timestamps.</span>
<span class="sd"> False if you want them to be left in the</span>
<span class="sd"> same format as they were in Salesforce.</span>
<span class="sd"> Leaving the value as False will result</span>
<span class="sd"> in datetimes being strings.</span>
<span class="sd"> *Defaults to False*</span>
<span class="sd"> :param record_time_added: *(optional)* True if you want to add a</span>
<span class="sd"> Unix timestamp field to the resulting data</span>
<span class="sd"> that marks when the data</span>
<span class="sd"> was fetched from Salesforce.</span>
<span class="sd"> *Default: False*.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">fmt</span> <span class="o">=</span> <span class="n">fmt</span><span class="o">.</span><span class="n">lower</span><span class="p">()</span>
<span class="k">if</span> <span class="n">fmt</span> <span class="ow">not</span> <span class="ow">in</span> <span class="p">[</span><span class="s1">&#39;csv&#39;</span><span class="p">,</span> <span class="s1">&#39;json&#39;</span><span class="p">,</span> <span class="s1">&#39;ndjson&#39;</span><span class="p">]:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">&quot;Format value is not recognized: </span><span class="si">{0}</span><span class="s2">&quot;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">fmt</span><span class="p">))</span>
<span class="c1"># this line right here will convert all integers to floats if there are</span>
<span class="c1"># any None/np.nan values in the column</span>
<span class="c1"># that&#39;s because None/np.nan cannot exist in an integer column</span>
<span class="c1"># we should write all of our timestamps as FLOATS in our final schema</span>
<span class="n">df</span> <span class="o">=</span> <span class="n">pd</span><span class="o">.</span><span class="n">DataFrame</span><span class="o">.</span><span class="n">from_records</span><span class="p">(</span><span class="n">query_results</span><span class="p">,</span> <span class="n">exclude</span><span class="o">=</span><span class="p">[</span><span class="s2">&quot;attributes&quot;</span><span class="p">])</span>
<span class="n">df</span><span class="o">.</span><span class="n">columns</span> <span class="o">=</span> <span class="p">[</span><span class="n">c</span><span class="o">.</span><span class="n">lower</span><span class="p">()</span> <span class="k">for</span> <span class="n">c</span> <span class="ow">in</span> <span class="n">df</span><span class="o">.</span><span class="n">columns</span><span class="p">]</span>
<span class="c1"># convert columns with datetime strings to datetimes</span>
<span class="c1"># not all strings will be datetimes, so we ignore any errors that occur</span>
<span class="c1"># we get the object&#39;s definition at this point and only consider</span>
<span class="c1"># features that are DATE or DATETIME</span>
<span class="k">if</span> <span class="n">coerce_to_timestamp</span> <span class="ow">and</span> <span class="n">df</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o">&gt;</span> <span class="mi">0</span><span class="p">:</span>
<span class="c1"># get the object name out of the query results</span>
<span class="c1"># it&#39;s stored in the &quot;attributes&quot; dictionary</span>
<span class="c1"># for each returned record</span>
<span class="n">object_name</span> <span class="o">=</span> <span class="n">query_results</span><span class="p">[</span><span class="mi">0</span><span class="p">][</span><span class="s1">&#39;attributes&#39;</span><span class="p">][</span><span class="s1">&#39;type&#39;</span><span class="p">]</span>
<span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s2">&quot;Coercing timestamps for: </span><span class="si">%s</span><span class="s2">&quot;</span><span class="p">,</span> <span class="n">object_name</span><span class="p">)</span>
<span class="n">schema</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">describe_object</span><span class="p">(</span><span class="n">object_name</span><span class="p">)</span>
<span class="c1"># possible columns that can be converted to timestamps</span>
<span class="c1"># are the ones that are either date or datetime types</span>
<span class="c1"># strings are too general and we risk unintentional conversion</span>
<span class="n">possible_timestamp_cols</span> <span class="o">=</span> <span class="p">[</span>
<span class="n">i</span><span class="p">[</span><span class="s1">&#39;name&#39;</span><span class="p">]</span><span class="o">.</span><span class="n">lower</span><span class="p">()</span>
<span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="n">schema</span><span class="p">[</span><span class="s1">&#39;fields&#39;</span><span class="p">]</span>
<span class="k">if</span> <span class="n">i</span><span class="p">[</span><span class="s1">&#39;type&#39;</span><span class="p">]</span> <span class="ow">in</span> <span class="p">[</span><span class="s2">&quot;date&quot;</span><span class="p">,</span> <span class="s2">&quot;datetime&quot;</span><span class="p">]</span> <span class="ow">and</span>
<span class="n">i</span><span class="p">[</span><span class="s1">&#39;name&#39;</span><span class="p">]</span><span class="o">.</span><span class="n">lower</span><span class="p">()</span> <span class="ow">in</span> <span class="n">df</span><span class="o">.</span><span class="n">columns</span>
<span class="p">]</span>
<span class="n">df</span><span class="p">[</span><span class="n">possible_timestamp_cols</span><span class="p">]</span> <span class="o">=</span> <span class="n">df</span><span class="p">[</span><span class="n">possible_timestamp_cols</span><span class="p">]</span><span class="o">.</span><span class="n">apply</span><span class="p">(</span>
<span class="k">lambda</span> <span class="n">x</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">_to_timestamp</span><span class="p">(</span><span class="n">x</span><span class="p">)</span>
<span class="p">)</span>
<span class="k">if</span> <span class="n">record_time_added</span><span class="p">:</span>
<span class="n">fetched_time</span> <span class="o">=</span> <span class="n">time</span><span class="o">.</span><span class="n">time</span><span class="p">()</span>
<span class="n">df</span><span class="p">[</span><span class="s2">&quot;time_fetched_from_salesforce&quot;</span><span class="p">]</span> <span class="o">=</span> <span class="n">fetched_time</span>
<span class="c1"># write the CSV or JSON file depending on the option</span>
<span class="c1"># NOTE:</span>
<span class="c1"># datetimes here are an issue.</span>
<span class="c1"># There is no good way to manage the difference</span>
<span class="c1"># for to_json, the options are an epoch or a ISO string</span>
<span class="c1"># but for to_csv, it will be a string output by datetime</span>
<span class="c1"># For JSON we decided to output the epoch timestamp in seconds</span>
<span class="c1"># (as is fairly standard for JavaScript)</span>
<span class="c1"># And for csv, we do a string</span>
<span class="k">if</span> <span class="n">fmt</span> <span class="o">==</span> <span class="s2">&quot;csv&quot;</span><span class="p">:</span>
<span class="c1"># there are also a ton of newline objects</span>
<span class="c1"># that mess up our ability to write to csv</span>
<span class="c1"># we remove these newlines so that the output is a valid CSV format</span>
<span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s2">&quot;Cleaning data and writing to CSV&quot;</span><span class="p">)</span>
<span class="n">possible_strings</span> <span class="o">=</span> <span class="n">df</span><span class="o">.</span><span class="n">columns</span><span class="p">[</span><span class="n">df</span><span class="o">.</span><span class="n">dtypes</span> <span class="o">==</span> <span class="s2">&quot;object&quot;</span><span class="p">]</span>
<span class="n">df</span><span class="p">[</span><span class="n">possible_strings</span><span class="p">]</span> <span class="o">=</span> <span class="n">df</span><span class="p">[</span><span class="n">possible_strings</span><span class="p">]</span><span class="o">.</span><span class="n">apply</span><span class="p">(</span>
<span class="k">lambda</span> <span class="n">x</span><span class="p">:</span> <span class="n">x</span><span class="o">.</span><span class="n">str</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="s2">&quot;</span><span class="se">\r\n</span><span class="s2">&quot;</span><span class="p">,</span> <span class="s2">&quot;&quot;</span><span class="p">)</span>
<span class="p">)</span>
<span class="n">df</span><span class="p">[</span><span class="n">possible_strings</span><span class="p">]</span> <span class="o">=</span> <span class="n">df</span><span class="p">[</span><span class="n">possible_strings</span><span class="p">]</span><span class="o">.</span><span class="n">apply</span><span class="p">(</span>
<span class="k">lambda</span> <span class="n">x</span><span class="p">:</span> <span class="n">x</span><span class="o">.</span><span class="n">str</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="s2">&quot;</span><span class="se">\n</span><span class="s2">&quot;</span><span class="p">,</span> <span class="s2">&quot;&quot;</span><span class="p">)</span>
<span class="p">)</span>
<span class="c1"># write the dataframe</span>
<span class="n">df</span><span class="o">.</span><span class="n">to_csv</span><span class="p">(</span><span class="n">filename</span><span class="p">,</span> <span class="n">index</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span>
<span class="k">elif</span> <span class="n">fmt</span> <span class="o">==</span> <span class="s2">&quot;json&quot;</span><span class="p">:</span>
<span class="n">df</span><span class="o">.</span><span class="n">to_json</span><span class="p">(</span><span class="n">filename</span><span class="p">,</span> <span class="s2">&quot;records&quot;</span><span class="p">,</span> <span class="n">date_unit</span><span class="o">=</span><span class="s2">&quot;s&quot;</span><span class="p">)</span>
<span class="k">elif</span> <span class="n">fmt</span> <span class="o">==</span> <span class="s2">&quot;ndjson&quot;</span><span class="p">:</span>
<span class="n">df</span><span class="o">.</span><span class="n">to_json</span><span class="p">(</span><span class="n">filename</span><span class="p">,</span> <span class="s2">&quot;records&quot;</span><span class="p">,</span> <span class="n">lines</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">date_unit</span><span class="o">=</span><span class="s2">&quot;s&quot;</span><span class="p">)</span>
<span class="k">return</span> <span class="n">df</span></div></div>
</pre></div>
</div>
</div>
<footer>
<hr/>
<div role="contentinfo">
<p>
</p>
</div>
Built with <a href="http://sphinx-doc.org/">Sphinx</a> using a <a href="https://github.com/rtfd/sphinx_rtd_theme">theme</a> provided by <a href="https://readthedocs.org">Read the Docs</a>.
</footer>
</div>
</div>
</section>
</div>
<script type="text/javascript">
jQuery(function () {
SphinxRtdTheme.Navigation.enable(true);
});
</script>
</body>
</html>