http://git-wip-us.apache.org/repos/asf/incubator-airflow-site/blob/28a3eb60/_modules/airflow/contrib/hooks/gcp_mlengine_hook.html ---------------------------------------------------------------------- diff --git a/_modules/airflow/contrib/hooks/gcp_mlengine_hook.html b/_modules/airflow/contrib/hooks/gcp_mlengine_hook.html new file mode 100644 index 0000000..82450ae --- /dev/null +++ b/_modules/airflow/contrib/hooks/gcp_mlengine_hook.html @@ -0,0 +1,500 @@ + + +<!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.gcp_mlengine_hook — Airflow Documentation</title> + + + + + + + + + + + + + + + + + + <link rel="stylesheet" href="../../../../_static/css/theme.css" type="text/css" /> + + + + + + <link rel="index" title="Index" + href="../../../../genindex.html"/> + <link rel="search" title="Search" href="../../../../search.html"/> + <link rel="top" title="Airflow Documentation" href="../../../../index.html"/> + <link rel="up" title="Module code" href="../../../index.html"/> + + + <script src="../../../../_static/js/modernizr.min.js"></script> + +</head> + +<body class="wy-body-for-nav" role="document"> + + + <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 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="../../../../configuration.html">Configuration</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 & 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="../../../../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="../../../../faq.html">FAQ</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../../code.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" role="navigation" 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> »</li> + + <li><a href="../../../index.html">Module code</a> »</li> + + <li>airflow.contrib.hooks.gcp_mlengine_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.gcp_mlengine_hook</h1><div class="highlight"><pre> +<span></span><span class="c1">#</span> +<span class="c1"># Licensed to the Apache Software Foundation (ASF) under one or more</span> +<span class="c1"># contributor license agreements. See the NOTICE file distributed with</span> +<span class="c1"># this work for additional information regarding copyright ownership.</span> +<span class="c1"># The ASF licenses this file to You under the Apache License, Version 2.0</span> +<span class="c1"># (the "License"); you may not use this file except in compliance with</span> +<span class="c1"># 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, software</span> +<span class="c1"># distributed under the License is distributed on an "AS IS" BASIS,</span> +<span class="c1"># WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.</span> +<span class="c1"># See the License for the specific language governing permissions and</span> +<span class="c1"># limitations under the License.</span> +<span class="kn">import</span> <span class="nn">random</span> +<span class="kn">import</span> <span class="nn">time</span> +<span class="kn">from</span> <span class="nn">apiclient</span> <span class="k">import</span> <span class="n">errors</span> +<span class="kn">from</span> <span class="nn">apiclient.discovery</span> <span class="k">import</span> <span class="n">build</span> +<span class="kn">from</span> <span class="nn">oauth2client.client</span> <span class="k">import</span> <span class="n">GoogleCredentials</span> + +<span class="kn">from</span> <span class="nn">airflow.contrib.hooks.gcp_api_base_hook</span> <span class="k">import</span> <span class="n">GoogleCloudBaseHook</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> + + +<span class="k">def</span> <span class="nf">_poll_with_exponential_delay</span><span class="p">(</span><span class="n">request</span><span class="p">,</span> <span class="n">max_n</span><span class="p">,</span> <span class="n">is_done_func</span><span class="p">,</span> <span class="n">is_error_func</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="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="n">max_n</span><span class="p">):</span> + <span class="k">try</span><span class="p">:</span> + <span class="n">response</span> <span class="o">=</span> <span class="n">request</span><span class="o">.</span><span class="n">execute</span><span class="p">()</span> + <span class="k">if</span> <span class="n">is_error_func</span><span class="p">(</span><span class="n">response</span><span class="p">):</span> + <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span> + <span class="s1">'The response contained an error: </span><span class="si">{}</span><span class="s1">'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">response</span><span class="p">)</span> + <span class="p">)</span> + <span class="k">elif</span> <span class="n">is_done_func</span><span class="p">(</span><span class="n">response</span><span class="p">):</span> + <span class="n">log</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s1">'Operation is done: </span><span class="si">%s</span><span class="s1">'</span><span class="p">,</span> <span class="n">response</span><span class="p">)</span> + <span class="k">return</span> <span class="n">response</span> + <span class="k">else</span><span class="p">:</span> + <span class="n">time</span><span class="o">.</span><span class="n">sleep</span><span class="p">((</span><span class="mi">2</span><span class="o">**</span><span class="n">i</span><span class="p">)</span> <span class="o">+</span> <span class="p">(</span><span class="n">random</span><span class="o">.</span><span class="n">randint</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="mi">1000</span><span class="p">)</span> <span class="o">/</span> <span class="mi">1000</span><span class="p">))</span> + <span class="k">except</span> <span class="n">errors</span><span class="o">.</span><span class="n">HttpError</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span> + <span class="k">if</span> <span class="n">e</span><span class="o">.</span><span class="n">resp</span><span class="o">.</span><span class="n">status</span> <span class="o">!=</span> <span class="mi">429</span><span class="p">:</span> + <span class="n">log</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s1">'Something went wrong. Not retrying: </span><span class="si">%s</span><span class="s1">'</span><span class="p">,</span> <span class="nb">format</span><span class="p">(</span><span class="n">e</span><span class="p">))</span> + <span class="k">raise</span> + <span class="k">else</span><span class="p">:</span> + <span class="n">time</span><span class="o">.</span><span class="n">sleep</span><span class="p">((</span><span class="mi">2</span><span class="o">**</span><span class="n">i</span><span class="p">)</span> <span class="o">+</span> <span class="p">(</span><span class="n">random</span><span class="o">.</span><span class="n">randint</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="mi">1000</span><span class="p">)</span> <span class="o">/</span> <span class="mi">1000</span><span class="p">))</span> + + +<div class="viewcode-block" id="MLEngineHook"><a class="viewcode-back" href="../../../../integration.html#airflow.contrib.hooks.gcp_mlengine_hook.MLEngineHook">[docs]</a><span class="k">class</span> <span class="nc">MLEngineHook</span><span class="p">(</span><span class="n">GoogleCloudBaseHook</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">gcp_conn_id</span><span class="o">=</span><span class="s1">'google_cloud_default'</span><span class="p">,</span> <span class="n">delegate_to</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> + <span class="nb">super</span><span class="p">(</span><span class="n">MLEngineHook</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">gcp_conn_id</span><span class="p">,</span> <span class="n">delegate_to</span><span class="p">)</span> + <span class="bp">self</span><span class="o">.</span><span class="n">_mlengine</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_conn</span><span class="p">()</span> + +<div class="viewcode-block" id="MLEngineHook.get_conn"><a class="viewcode-back" href="../../../../integration.html#airflow.contrib.hooks.gcp_mlengine_hook.MLEngineHook.get_conn">[docs]</a> <span class="k">def</span> <span class="nf">get_conn</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> + <span class="sd">"""</span> +<span class="sd"> Returns a Google MLEngine service object.</span> +<span class="sd"> """</span> + <span class="n">credentials</span> <span class="o">=</span> <span class="n">GoogleCredentials</span><span class="o">.</span><span class="n">get_application_default</span><span class="p">()</span> + <span class="k">return</span> <span class="n">build</span><span class="p">(</span><span class="s1">'ml'</span><span class="p">,</span> <span class="s1">'v1'</span><span class="p">,</span> <span class="n">credentials</span><span class="o">=</span><span class="n">credentials</span><span class="p">)</span></div> + +<div class="viewcode-block" id="MLEngineHook.create_job"><a class="viewcode-back" href="../../../../integration.html#airflow.contrib.hooks.gcp_mlengine_hook.MLEngineHook.create_job">[docs]</a> <span class="k">def</span> <span class="nf">create_job</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">project_id</span><span class="p">,</span> <span class="n">job</span><span class="p">,</span> <span class="n">use_existing_job_fn</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> + <span class="sd">"""</span> +<span class="sd"> Launches a MLEngine job and wait for it to reach a terminal state.</span> + +<span class="sd"> :param project_id: The Google Cloud project id within which MLEngine</span> +<span class="sd"> job will be launched.</span> +<span class="sd"> :type project_id: string</span> + +<span class="sd"> :param job: MLEngine Job object that should be provided to the MLEngine</span> +<span class="sd"> API, such as:</span> +<span class="sd"> {</span> +<span class="sd"> 'jobId': 'my_job_id',</span> +<span class="sd"> 'trainingInput': {</span> +<span class="sd"> 'scaleTier': 'STANDARD_1',</span> +<span class="sd"> ...</span> +<span class="sd"> }</span> +<span class="sd"> }</span> +<span class="sd"> :type job: dict</span> + +<span class="sd"> :param use_existing_job_fn: In case that a MLEngine job with the same</span> +<span class="sd"> job_id already exist, this method (if provided) will decide whether</span> +<span class="sd"> we should use this existing job, continue waiting for it to finish</span> +<span class="sd"> and returning the job object. It should accepts a MLEngine job</span> +<span class="sd"> object, and returns a boolean value indicating whether it is OK to</span> +<span class="sd"> reuse the existing job. If 'use_existing_job_fn' is not provided,</span> +<span class="sd"> we by default reuse the existing MLEngine job.</span> +<span class="sd"> :type use_existing_job_fn: function</span> + +<span class="sd"> :return: The MLEngine job object if the job successfully reach a</span> +<span class="sd"> terminal state (which might be FAILED or CANCELLED state).</span> +<span class="sd"> :rtype: dict</span> +<span class="sd"> """</span> + <span class="n">request</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_mlengine</span><span class="o">.</span><span class="n">projects</span><span class="p">()</span><span class="o">.</span><span class="n">jobs</span><span class="p">()</span><span class="o">.</span><span class="n">create</span><span class="p">(</span> + <span class="n">parent</span><span class="o">=</span><span class="s1">'projects/</span><span class="si">{}</span><span class="s1">'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">project_id</span><span class="p">),</span> + <span class="n">body</span><span class="o">=</span><span class="n">job</span><span class="p">)</span> + <span class="n">job_id</span> <span class="o">=</span> <span class="n">job</span><span class="p">[</span><span class="s1">'jobId'</span><span class="p">]</span> + + <span class="k">try</span><span class="p">:</span> + <span class="n">request</span><span class="o">.</span><span class="n">execute</span><span class="p">()</span> + <span class="k">except</span> <span class="n">errors</span><span class="o">.</span><span class="n">HttpError</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span> + <span class="c1"># 409 means there is an existing job with the same job ID.</span> + <span class="k">if</span> <span class="n">e</span><span class="o">.</span><span class="n">resp</span><span class="o">.</span><span class="n">status</span> <span class="o">==</span> <span class="mi">409</span><span class="p">:</span> + <span class="k">if</span> <span class="n">use_existing_job_fn</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> + <span class="n">existing_job</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_get_job</span><span class="p">(</span><span class="n">project_id</span><span class="p">,</span> <span class="n">job_id</span><span class="p">)</span> + <span class="k">if</span> <span class="ow">not</span> <span class="n">use_existing_job_fn</span><span class="p">(</span><span class="n">existing_job</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">error</span><span class="p">(</span> + <span class="s1">'Job with job_id </span><span class="si">%s</span><span class="s1"> already exist, but it does '</span> + <span class="s1">'not match our expectation: </span><span class="si">%s</span><span class="s1">'</span><span class="p">,</span> + <span class="n">job_id</span><span class="p">,</span> <span class="n">existing_job</span> + <span class="p">)</span> + <span class="k">raise</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="s1">'Job with job_id </span><span class="si">%s</span><span class="s1"> already exist. Will waiting for it to finish'</span><span class="p">,</span> + <span class="n">job_id</span> + <span class="p">)</span> + <span class="k">else</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">error</span><span class="p">(</span><span class="s1">'Failed to create MLEngine job: </span><span class="si">{}</span><span class="s1">'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">e</span><span class="p">))</span> + <span class="k">raise</span> + + <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_wait_for_job_done</span><span class="p">(</span><span class="n">project_id</span><span class="p">,</span> <span class="n">job_id</span><span class="p">)</span></div> + + <span class="k">def</span> <span class="nf">_get_job</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">project_id</span><span class="p">,</span> <span class="n">job_id</span><span class="p">):</span> + <span class="sd">"""</span> +<span class="sd"> Gets a MLEngine job based on the job name.</span> + +<span class="sd"> :return: MLEngine job object if succeed.</span> +<span class="sd"> :rtype: dict</span> + +<span class="sd"> Raises:</span> +<span class="sd"> apiclient.errors.HttpError: if HTTP error is returned from server</span> +<span class="sd"> """</span> + <span class="n">job_name</span> <span class="o">=</span> <span class="s1">'projects/</span><span class="si">{}</span><span class="s1">/jobs/</span><span class="si">{}</span><span class="s1">'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">project_id</span><span class="p">,</span> <span class="n">job_id</span><span class="p">)</span> + <span class="n">request</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_mlengine</span><span class="o">.</span><span class="n">projects</span><span class="p">()</span><span class="o">.</span><span class="n">jobs</span><span class="p">()</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="n">job_name</span><span class="p">)</span> + <span class="k">while</span> <span class="kc">True</span><span class="p">:</span> + <span class="k">try</span><span class="p">:</span> + <span class="k">return</span> <span class="n">request</span><span class="o">.</span><span class="n">execute</span><span class="p">()</span> + <span class="k">except</span> <span class="n">errors</span><span class="o">.</span><span class="n">HttpError</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span> + <span class="k">if</span> <span class="n">e</span><span class="o">.</span><span class="n">resp</span><span class="o">.</span><span class="n">status</span> <span class="o">==</span> <span class="mi">429</span><span class="p">:</span> + <span class="c1"># polling after 30 seconds when quota failure occurs</span> + <span class="n">time</span><span class="o">.</span><span class="n">sleep</span><span class="p">(</span><span class="mi">30</span><span class="p">)</span> + <span class="k">else</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">error</span><span class="p">(</span><span class="s1">'Failed to get MLEngine job: </span><span class="si">{}</span><span class="s1">'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">e</span><span class="p">))</span> + <span class="k">raise</span> + + <span class="k">def</span> <span class="nf">_wait_for_job_done</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">project_id</span><span class="p">,</span> <span class="n">job_id</span><span class="p">,</span> <span class="n">interval</span><span class="o">=</span><span class="mi">30</span><span class="p">):</span> + <span class="sd">"""</span> +<span class="sd"> Waits for the Job to reach a terminal state.</span> + +<span class="sd"> This method will periodically check the job state until the job reach</span> +<span class="sd"> a terminal state.</span> + +<span class="sd"> Raises:</span> +<span class="sd"> apiclient.errors.HttpError: if HTTP error is returned when getting</span> +<span class="sd"> the job</span> +<span class="sd"> """</span> + <span class="k">assert</span> <span class="n">interval</span> <span class="o">></span> <span class="mi">0</span> + <span class="k">while</span> <span class="kc">True</span><span class="p">:</span> + <span class="n">job</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_get_job</span><span class="p">(</span><span class="n">project_id</span><span class="p">,</span> <span class="n">job_id</span><span class="p">)</span> + <span class="k">if</span> <span class="n">job</span><span class="p">[</span><span class="s1">'state'</span><span class="p">]</span> <span class="ow">in</span> <span class="p">[</span><span class="s1">'SUCCEEDED'</span><span class="p">,</span> <span class="s1">'FAILED'</span><span class="p">,</span> <span class="s1">'CANCELLED'</span><span class="p">]:</span> + <span class="k">return</span> <span class="n">job</span> + <span class="n">time</span><span class="o">.</span><span class="n">sleep</span><span class="p">(</span><span class="n">interval</span><span class="p">)</span> + +<div class="viewcode-block" id="MLEngineHook.create_version"><a class="viewcode-back" href="../../../../integration.html#airflow.contrib.hooks.gcp_mlengine_hook.MLEngineHook.create_version">[docs]</a> <span class="k">def</span> <span class="nf">create_version</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">project_id</span><span class="p">,</span> <span class="n">model_name</span><span class="p">,</span> <span class="n">version_spec</span><span class="p">):</span> + <span class="sd">"""</span> +<span class="sd"> Creates the Version on Google Cloud ML Engine.</span> + +<span class="sd"> Returns the operation if the version was created successfully and</span> +<span class="sd"> raises an error otherwise.</span> +<span class="sd"> """</span> + <span class="n">parent_name</span> <span class="o">=</span> <span class="s1">'projects/</span><span class="si">{}</span><span class="s1">/models/</span><span class="si">{}</span><span class="s1">'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">project_id</span><span class="p">,</span> <span class="n">model_name</span><span class="p">)</span> + <span class="n">create_request</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_mlengine</span><span class="o">.</span><span class="n">projects</span><span class="p">()</span><span class="o">.</span><span class="n">models</span><span class="p">()</span><span class="o">.</span><span class="n">versions</span><span class="p">()</span><span class="o">.</span><span class="n">create</span><span class="p">(</span> + <span class="n">parent</span><span class="o">=</span><span class="n">parent_name</span><span class="p">,</span> <span class="n">body</span><span class="o">=</span><span class="n">version_spec</span><span class="p">)</span> + <span class="n">response</span> <span class="o">=</span> <span class="n">create_request</span><span class="o">.</span><span class="n">execute</span><span class="p">()</span> + <span class="n">get_request</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_mlengine</span><span class="o">.</span><span class="n">projects</span><span class="p">()</span><span class="o">.</span><span class="n">operations</span><span class="p">()</span><span class="o">.</span><span class="n">get</span><span class="p">(</span> + <span class="n">name</span><span class="o">=</span><span class="n">response</span><span class="p">[</span><span class="s1">'name'</span><span class="p">])</span> + + <span class="k">return</span> <span class="n">_poll_with_exponential_delay</span><span class="p">(</span> + <span class="n">request</span><span class="o">=</span><span class="n">get_request</span><span class="p">,</span> + <span class="n">max_n</span><span class="o">=</span><span class="mi">9</span><span class="p">,</span> + <span class="n">is_done_func</span><span class="o">=</span><span class="k">lambda</span> <span class="n">resp</span><span class="p">:</span> <span class="n">resp</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'done'</span><span class="p">,</span> <span class="kc">False</span><span class="p">),</span> + <span class="n">is_error_func</span><span class="o">=</span><span class="k">lambda</span> <span class="n">resp</span><span class="p">:</span> <span class="n">resp</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'error'</span><span class="p">,</span> <span class="kc">None</span><span class="p">)</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">)</span></div> + +<div class="viewcode-block" id="MLEngineHook.set_default_version"><a class="viewcode-back" href="../../../../integration.html#airflow.contrib.hooks.gcp_mlengine_hook.MLEngineHook.set_default_version">[docs]</a> <span class="k">def</span> <span class="nf">set_default_version</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">project_id</span><span class="p">,</span> <span class="n">model_name</span><span class="p">,</span> <span class="n">version_name</span><span class="p">):</span> + <span class="sd">"""</span> +<span class="sd"> Sets a version to be the default. Blocks until finished.</span> +<span class="sd"> """</span> + <span class="n">full_version_name</span> <span class="o">=</span> <span class="s1">'projects/</span><span class="si">{}</span><span class="s1">/models/</span><span class="si">{}</span><span class="s1">/versions/</span><span class="si">{}</span><span class="s1">'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span> + <span class="n">project_id</span><span class="p">,</span> <span class="n">model_name</span><span class="p">,</span> <span class="n">version_name</span><span class="p">)</span> + <span class="n">request</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_mlengine</span><span class="o">.</span><span class="n">projects</span><span class="p">()</span><span class="o">.</span><span class="n">models</span><span class="p">()</span><span class="o">.</span><span class="n">versions</span><span class="p">()</span><span class="o">.</span><span class="n">setDefault</span><span class="p">(</span> + <span class="n">name</span><span class="o">=</span><span class="n">full_version_name</span><span class="p">,</span> <span class="n">body</span><span class="o">=</span><span class="p">{})</span> + + <span class="k">try</span><span class="p">:</span> + <span class="n">response</span> <span class="o">=</span> <span class="n">request</span><span class="o">.</span><span class="n">execute</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="s1">'Successfully set version: </span><span class="si">%s</span><span class="s1"> to default'</span><span class="p">,</span> <span class="n">response</span><span class="p">)</span> + <span class="k">return</span> <span class="n">response</span> + <span class="k">except</span> <span class="n">errors</span><span class="o">.</span><span class="n">HttpError</span> <span class="k">as</span> <span class="n">e</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">error</span><span class="p">(</span><span class="s1">'Something went wrong: </span><span class="si">%s</span><span class="s1">'</span><span class="p">,</span> <span class="n">e</span><span class="p">)</span> + <span class="k">raise</span></div> + +<div class="viewcode-block" id="MLEngineHook.list_versions"><a class="viewcode-back" href="../../../../integration.html#airflow.contrib.hooks.gcp_mlengine_hook.MLEngineHook.list_versions">[docs]</a> <span class="k">def</span> <span class="nf">list_versions</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">project_id</span><span class="p">,</span> <span class="n">model_name</span><span class="p">):</span> + <span class="sd">"""</span> +<span class="sd"> Lists all available versions of a model. Blocks until finished.</span> +<span class="sd"> """</span> + <span class="n">result</span> <span class="o">=</span> <span class="p">[]</span> + <span class="n">full_parent_name</span> <span class="o">=</span> <span class="s1">'projects/</span><span class="si">{}</span><span class="s1">/models/</span><span class="si">{}</span><span class="s1">'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span> + <span class="n">project_id</span><span class="p">,</span> <span class="n">model_name</span><span class="p">)</span> + <span class="n">request</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_mlengine</span><span class="o">.</span><span class="n">projects</span><span class="p">()</span><span class="o">.</span><span class="n">models</span><span class="p">()</span><span class="o">.</span><span class="n">versions</span><span class="p">()</span><span class="o">.</span><span class="n">list</span><span class="p">(</span> + <span class="n">parent</span><span class="o">=</span><span class="n">full_parent_name</span><span class="p">,</span> <span class="n">pageSize</span><span class="o">=</span><span class="mi">100</span><span class="p">)</span> + + <span class="n">response</span> <span class="o">=</span> <span class="n">request</span><span class="o">.</span><span class="n">execute</span><span class="p">()</span> + <span class="n">next_page_token</span> <span class="o">=</span> <span class="n">response</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'nextPageToken'</span><span class="p">,</span> <span class="kc">None</span><span class="p">)</span> + <span class="n">result</span><span class="o">.</span><span class="n">extend</span><span class="p">(</span><span class="n">response</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'versions'</span><span class="p">,</span> <span class="p">[]))</span> + <span class="k">while</span> <span class="n">next_page_token</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> + <span class="n">next_request</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_mlengine</span><span class="o">.</span><span class="n">projects</span><span class="p">()</span><span class="o">.</span><span class="n">models</span><span class="p">()</span><span class="o">.</span><span class="n">versions</span><span class="p">()</span><span class="o">.</span><span class="n">list</span><span class="p">(</span> + <span class="n">parent</span><span class="o">=</span><span class="n">full_parent_name</span><span class="p">,</span> + <span class="n">pageToken</span><span class="o">=</span><span class="n">next_page_token</span><span class="p">,</span> + <span class="n">pageSize</span><span class="o">=</span><span class="mi">100</span><span class="p">)</span> + <span class="n">response</span> <span class="o">=</span> <span class="n">next_request</span><span class="o">.</span><span class="n">execute</span><span class="p">()</span> + <span class="n">next_page_token</span> <span class="o">=</span> <span class="n">response</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'nextPageToken'</span><span class="p">,</span> <span class="kc">None</span><span class="p">)</span> + <span class="n">result</span><span class="o">.</span><span class="n">extend</span><span class="p">(</span><span class="n">response</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'versions'</span><span class="p">,</span> <span class="p">[]))</span> + <span class="n">time</span><span class="o">.</span><span class="n">sleep</span><span class="p">(</span><span class="mi">5</span><span class="p">)</span> + <span class="k">return</span> <span class="n">result</span></div> + +<div class="viewcode-block" id="MLEngineHook.delete_version"><a class="viewcode-back" href="../../../../integration.html#airflow.contrib.hooks.gcp_mlengine_hook.MLEngineHook.delete_version">[docs]</a> <span class="k">def</span> <span class="nf">delete_version</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">project_id</span><span class="p">,</span> <span class="n">model_name</span><span class="p">,</span> <span class="n">version_name</span><span class="p">):</span> + <span class="sd">"""</span> +<span class="sd"> Deletes the given version of a model. Blocks until finished.</span> +<span class="sd"> """</span> + <span class="n">full_name</span> <span class="o">=</span> <span class="s1">'projects/</span><span class="si">{}</span><span class="s1">/models/</span><span class="si">{}</span><span class="s1">/versions/</span><span class="si">{}</span><span class="s1">'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span> + <span class="n">project_id</span><span class="p">,</span> <span class="n">model_name</span><span class="p">,</span> <span class="n">version_name</span><span class="p">)</span> + <span class="n">delete_request</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_mlengine</span><span class="o">.</span><span class="n">projects</span><span class="p">()</span><span class="o">.</span><span class="n">models</span><span class="p">()</span><span class="o">.</span><span class="n">versions</span><span class="p">()</span><span class="o">.</span><span class="n">delete</span><span class="p">(</span> + <span class="n">name</span><span class="o">=</span><span class="n">full_name</span><span class="p">)</span> + <span class="n">response</span> <span class="o">=</span> <span class="n">delete_request</span><span class="o">.</span><span class="n">execute</span><span class="p">()</span> + <span class="n">get_request</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_mlengine</span><span class="o">.</span><span class="n">projects</span><span class="p">()</span><span class="o">.</span><span class="n">operations</span><span class="p">()</span><span class="o">.</span><span class="n">get</span><span class="p">(</span> + <span class="n">name</span><span class="o">=</span><span class="n">response</span><span class="p">[</span><span class="s1">'name'</span><span class="p">])</span> + + <span class="k">return</span> <span class="n">_poll_with_exponential_delay</span><span class="p">(</span> + <span class="n">request</span><span class="o">=</span><span class="n">get_request</span><span class="p">,</span> + <span class="n">max_n</span><span class="o">=</span><span class="mi">9</span><span class="p">,</span> + <span class="n">is_done_func</span><span class="o">=</span><span class="k">lambda</span> <span class="n">resp</span><span class="p">:</span> <span class="n">resp</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'done'</span><span class="p">,</span> <span class="kc">False</span><span class="p">),</span> + <span class="n">is_error_func</span><span class="o">=</span><span class="k">lambda</span> <span class="n">resp</span><span class="p">:</span> <span class="n">resp</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'error'</span><span class="p">,</span> <span class="kc">None</span><span class="p">)</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">)</span></div> + +<div class="viewcode-block" id="MLEngineHook.create_model"><a class="viewcode-back" href="../../../../integration.html#airflow.contrib.hooks.gcp_mlengine_hook.MLEngineHook.create_model">[docs]</a> <span class="k">def</span> <span class="nf">create_model</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">project_id</span><span class="p">,</span> <span class="n">model</span><span class="p">):</span> + <span class="sd">"""</span> +<span class="sd"> Create a Model. Blocks until finished.</span> +<span class="sd"> """</span> + <span class="k">assert</span> <span class="n">model</span><span class="p">[</span><span class="s1">'name'</span><span class="p">]</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> <span class="ow">and</span> <span class="n">model</span><span class="p">[</span><span class="s1">'name'</span><span class="p">]</span> <span class="ow">is</span> <span class="ow">not</span> <span class="s1">''</span> + <span class="n">project</span> <span class="o">=</span> <span class="s1">'projects/</span><span class="si">{}</span><span class="s1">'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">project_id</span><span class="p">)</span> + + <span class="n">request</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_mlengine</span><span class="o">.</span><span class="n">projects</span><span class="p">()</span><span class="o">.</span><span class="n">models</span><span class="p">()</span><span class="o">.</span><span class="n">create</span><span class="p">(</span> + <span class="n">parent</span><span class="o">=</span><span class="n">project</span><span class="p">,</span> <span class="n">body</span><span class="o">=</span><span class="n">model</span><span class="p">)</span> + <span class="k">return</span> <span class="n">request</span><span class="o">.</span><span class="n">execute</span><span class="p">()</span></div> + +<div class="viewcode-block" id="MLEngineHook.get_model"><a class="viewcode-back" href="../../../../integration.html#airflow.contrib.hooks.gcp_mlengine_hook.MLEngineHook.get_model">[docs]</a> <span class="k">def</span> <span class="nf">get_model</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">project_id</span><span class="p">,</span> <span class="n">model_name</span><span class="p">):</span> + <span class="sd">"""</span> +<span class="sd"> Gets a Model. Blocks until finished.</span> +<span class="sd"> """</span> + <span class="k">assert</span> <span class="n">model_name</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> <span class="ow">and</span> <span class="n">model_name</span> <span class="ow">is</span> <span class="ow">not</span> <span class="s1">''</span> + <span class="n">full_model_name</span> <span class="o">=</span> <span class="s1">'projects/</span><span class="si">{}</span><span class="s1">/models/</span><span class="si">{}</span><span class="s1">'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span> + <span class="n">project_id</span><span class="p">,</span> <span class="n">model_name</span><span class="p">)</span> + <span class="n">request</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_mlengine</span><span class="o">.</span><span class="n">projects</span><span class="p">()</span><span class="o">.</span><span class="n">models</span><span class="p">()</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="n">full_model_name</span><span class="p">)</span> + <span class="k">try</span><span class="p">:</span> + <span class="k">return</span> <span class="n">request</span><span class="o">.</span><span class="n">execute</span><span class="p">()</span> + <span class="k">except</span> <span class="n">errors</span><span class="o">.</span><span class="n">HttpError</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span> + <span class="k">if</span> <span class="n">e</span><span class="o">.</span><span class="n">resp</span><span class="o">.</span><span class="n">status</span> <span class="o">==</span> <span class="mi">404</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">error</span><span class="p">(</span><span class="s1">'Model was not found: </span><span class="si">%s</span><span class="s1">'</span><span class="p">,</span> <span class="n">e</span><span class="p">)</span> + <span class="k">return</span> <span class="kc">None</span> + <span class="k">raise</span></div></div> +</pre></div> + + </div> + <div class="articleComments"> + + </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/snide/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"> + var DOCUMENTATION_OPTIONS = { + URL_ROOT:'../../../../', + VERSION:'', + COLLAPSE_INDEX:false, + FILE_SUFFIX:'.html', + HAS_SOURCE: true, + SOURCELINK_SUFFIX: '.txt' + }; + </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/js/theme.js"></script> + + + + + <script type="text/javascript"> + jQuery(function () { + SphinxRtdTheme.StickyNav.enable(); + }); + </script> + + +</body> +</html> \ No newline at end of file
http://git-wip-us.apache.org/repos/asf/incubator-airflow-site/blob/28a3eb60/_modules/airflow/contrib/hooks/gcs_hook.html ---------------------------------------------------------------------- diff --git a/_modules/airflow/contrib/hooks/gcs_hook.html b/_modules/airflow/contrib/hooks/gcs_hook.html index 8edc584..6f3bc49 100644 --- a/_modules/airflow/contrib/hooks/gcs_hook.html +++ b/_modules/airflow/contrib/hooks/gcs_hook.html @@ -13,6 +13,8 @@ + + @@ -30,6 +32,9 @@ + <link rel="index" title="Index" + href="../../../../genindex.html"/> + <link rel="search" title="Search" href="../../../../search.html"/> <link rel="top" title="Airflow Documentation" href="../../../../index.html"/> <link rel="up" title="Module code" href="../../../index.html"/> @@ -40,6 +45,7 @@ <body class="wy-body-for-nav" role="document"> + <div class="wy-grid-for-nav"> @@ -76,7 +82,10 @@ - <ul> + + + + <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> @@ -90,6 +99,8 @@ <li class="toctree-l1"><a class="reference internal" href="../../../../scheduler.html">Scheduling & 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="../../../../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="../../../../faq.html">FAQ</a></li> <li class="toctree-l1"><a class="reference internal" href="../../../../code.html">API Reference</a></li> </ul> @@ -104,8 +115,10 @@ <nav class="wy-nav-top" role="navigation" aria-label="top navigation"> - <i data-toggle="wy-nav-top" class="fa fa-bars"></i> - <a href="../../../../index.html">Airflow</a> + + <i data-toggle="wy-nav-top" class="fa fa-bars"></i> + <a href="../../../../index.html">Airflow</a> + </nav> @@ -118,19 +131,36 @@ + + + + + + + + + + <div role="navigation" aria-label="breadcrumbs navigation"> + <ul class="wy-breadcrumbs"> - <li><a href="../../../../index.html">Docs</a> »</li> - + + <li><a href="../../../../index.html">Docs</a> »</li> + <li><a href="../../../index.html">Module code</a> »</li> - - <li>airflow.contrib.hooks.gcs_hook</li> + + <li>airflow.contrib.hooks.gcs_hook</li> + + <li class="wy-breadcrumbs-aside"> - + </li> + </ul> + + <hr/> </div> <div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article"> @@ -151,17 +181,14 @@ <span class="c1"># See the License for the specific language governing permissions and</span> <span class="c1"># limitations under the License.</span> <span class="c1">#</span> +<span class="kn">from</span> <span class="nn">apiclient.discovery</span> <span class="k">import</span> <span class="n">build</span> +<span class="kn">from</span> <span class="nn">apiclient.http</span> <span class="k">import</span> <span class="n">MediaFileUpload</span> +<span class="kn">from</span> <span class="nn">googleapiclient</span> <span class="k">import</span> <span class="n">errors</span> -<span class="kn">import</span> <span class="nn">logging</span> - -<span class="kn">from</span> <span class="nn">airflow.contrib.hooks.gcp_api_base_hook</span> <span class="kn">import</span> <span class="n">GoogleCloudBaseHook</span> -<span class="kn">from</span> <span class="nn">apiclient.discovery</span> <span class="kn">import</span> <span class="n">build</span> -<span class="kn">from</span> <span class="nn">apiclient.http</span> <span class="kn">import</span> <span class="n">MediaFileUpload</span> - -<span class="n">logging</span><span class="o">.</span><span class="n">getLogger</span><span class="p">(</span><span class="s2">"google_cloud_storage"</span><span class="p">)</span><span class="o">.</span><span class="n">setLevel</span><span class="p">(</span><span class="n">logging</span><span class="o">.</span><span class="n">INFO</span><span class="p">)</span> +<span class="kn">from</span> <span class="nn">airflow.contrib.hooks.gcp_api_base_hook</span> <span class="k">import</span> <span class="n">GoogleCloudBaseHook</span> -<div class="viewcode-block" id="GoogleCloudStorageHook"><a class="viewcode-back" href="../../../../code.html#airflow.contrib.hooks.gcs_hook.GoogleCloudStorageHook">[docs]</a><span class="k">class</span> <span class="nc">GoogleCloudStorageHook</span><span class="p">(</span><span class="n">GoogleCloudBaseHook</span><span class="p">):</span> +<div class="viewcode-block" id="GoogleCloudStorageHook"><a class="viewcode-back" href="../../../../integration.html#airflow.contrib.hooks.gcs_hook.GoogleCloudStorageHook">[docs]</a><span class="k">class</span> <span class="nc">GoogleCloudStorageHook</span><span class="p">(</span><span class="n">GoogleCloudBaseHook</span><span class="p">):</span> <span class="sd">"""</span> <span class="sd"> Interact with Google Cloud Storage. This hook uses the Google Cloud Platform</span> <span class="sd"> connection.</span> @@ -169,17 +196,65 @@ <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">google_cloud_storage_conn_id</span><span class="o">=</span><span class="s1">'google_cloud_storage_default'</span><span class="p">,</span> - <span class="n">delegate_to</span><span class="o">=</span><span class="bp">None</span><span class="p">):</span> - <span class="nb">super</span><span class="p">(</span><span class="n">GoogleCloudStorageHook</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="n">__init__</span><span class="p">(</span><span class="n">google_cloud_storage_conn_id</span><span class="p">,</span> <span class="n">delegate_to</span><span class="p">)</span> + <span class="n">delegate_to</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> + <span class="nb">super</span><span class="p">(</span><span class="n">GoogleCloudStorageHook</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">google_cloud_storage_conn_id</span><span class="p">,</span> + <span class="n">delegate_to</span><span class="p">)</span> - <span class="k">def</span> <span class="nf">get_conn</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> +<div class="viewcode-block" id="GoogleCloudStorageHook.get_conn"><a class="viewcode-back" href="../../../../integration.html#airflow.contrib.hooks.gcs_hook.GoogleCloudStorageHook.get_conn">[docs]</a> <span class="k">def</span> <span class="nf">get_conn</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> <span class="sd">"""</span> <span class="sd"> Returns a Google Cloud Storage service object.</span> <span class="sd"> """</span> <span class="n">http_authorized</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_authorize</span><span class="p">()</span> - <span class="k">return</span> <span class="n">build</span><span class="p">(</span><span class="s1">'storage'</span><span class="p">,</span> <span class="s1">'v1'</span><span class="p">,</span> <span class="n">http</span><span class="o">=</span><span class="n">http_authorized</span><span class="p">)</span> + <span class="k">return</span> <span class="n">build</span><span class="p">(</span><span class="s1">'storage'</span><span class="p">,</span> <span class="s1">'v1'</span><span class="p">,</span> <span class="n">http</span><span class="o">=</span><span class="n">http_authorized</span><span class="p">)</span></div> + + + <span class="c1"># pylint:disable=redefined-builtin</span> +<div class="viewcode-block" id="GoogleCloudStorageHook.copy"><a class="viewcode-back" href="../../../../integration.html#airflow.contrib.hooks.gcs_hook.GoogleCloudStorageHook.copy">[docs]</a> <span class="k">def</span> <span class="nf">copy</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">source_bucket</span><span class="p">,</span> <span class="n">source_object</span><span class="p">,</span> <span class="n">destination_bucket</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> + <span class="n">destination_object</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> + <span class="sd">"""</span> +<span class="sd"> Copies an object from a bucket to another, with renaming if requested.</span> + +<span class="sd"> destination_bucket or destination_object can be omitted, in which case</span> +<span class="sd"> source bucket/object is used, but not both.</span> + +<span class="sd"> :param bucket: The bucket of the object to copy from.</span> +<span class="sd"> :type bucket: string</span> +<span class="sd"> :param object: The object to copy.</span> +<span class="sd"> :type object: string</span> +<span class="sd"> :param destination_bucket: The destination of the object to copied to.</span> +<span class="sd"> Can be omitted; then the same bucket is used.</span> +<span class="sd"> :type destination_bucket: string</span> +<span class="sd"> :param destination_object: The (renamed) path of the object if given.</span> +<span class="sd"> Can be omitted; then the same name is used.</span> +<span class="sd"> """</span> + <span class="n">destination_bucket</span> <span class="o">=</span> <span class="n">destination_bucket</span> <span class="ow">or</span> <span class="n">source_bucket</span> + <span class="n">destination_object</span> <span class="o">=</span> <span class="n">destination_object</span> <span class="ow">or</span> <span class="n">source_object</span> + <span class="k">if</span> <span class="p">(</span><span class="n">source_bucket</span> <span class="o">==</span> <span class="n">destination_bucket</span> <span class="ow">and</span> + <span class="n">source_object</span> <span class="o">==</span> <span class="n">destination_object</span><span class="p">):</span> + <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span> + <span class="s1">'Either source/destination bucket or source/destination object '</span> + <span class="s1">'must be different, not both the same: bucket=</span><span class="si">%s</span><span class="s1">, object=</span><span class="si">%s</span><span class="s1">'</span> <span class="o">%</span> + <span class="p">(</span><span class="n">source_bucket</span><span class="p">,</span> <span class="n">source_object</span><span class="p">))</span> + <span class="k">if</span> <span class="ow">not</span> <span class="n">source_bucket</span> <span class="ow">or</span> <span class="ow">not</span> <span class="n">source_object</span><span class="p">:</span> + <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">'source_bucket and source_object cannot be empty.'</span><span class="p">)</span> - <span class="k">def</span> <span class="nf">download</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">bucket</span><span class="p">,</span> <span class="nb">object</span><span class="p">,</span> <span class="n">filename</span><span class="o">=</span><span class="bp">False</span><span class="p">):</span> + <span class="n">service</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_conn</span><span class="p">()</span> + <span class="k">try</span><span class="p">:</span> + <span class="n">service</span> \ + <span class="o">.</span><span class="n">objects</span><span class="p">()</span> \ + <span class="o">.</span><span class="n">copy</span><span class="p">(</span><span class="n">sourceBucket</span><span class="o">=</span><span class="n">source_bucket</span><span class="p">,</span> <span class="n">sourceObject</span><span class="o">=</span><span class="n">source_object</span><span class="p">,</span> + <span class="n">destinationBucket</span><span class="o">=</span><span class="n">destination_bucket</span><span class="p">,</span> + <span class="n">destinationObject</span><span class="o">=</span><span class="n">destination_object</span><span class="p">,</span> <span class="n">body</span><span class="o">=</span><span class="s1">''</span><span class="p">)</span> \ + <span class="o">.</span><span class="n">execute</span><span class="p">()</span> + <span class="k">return</span> <span class="kc">True</span> + <span class="k">except</span> <span class="n">errors</span><span class="o">.</span><span class="n">HttpError</span> <span class="k">as</span> <span class="n">ex</span><span class="p">:</span> + <span class="k">if</span> <span class="n">ex</span><span class="o">.</span><span class="n">resp</span><span class="p">[</span><span class="s1">'status'</span><span class="p">]</span> <span class="o">==</span> <span class="s1">'404'</span><span class="p">:</span> + <span class="k">return</span> <span class="kc">False</span> + <span class="k">raise</span></div> + + + <span class="c1"># pylint:disable=redefined-builtin</span> +<div class="viewcode-block" id="GoogleCloudStorageHook.download"><a class="viewcode-back" href="../../../../integration.html#airflow.contrib.hooks.gcs_hook.GoogleCloudStorageHook.download">[docs]</a> <span class="k">def</span> <span class="nf">download</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">bucket</span><span class="p">,</span> <span class="nb">object</span><span class="p">,</span> <span class="n">filename</span><span class="o">=</span><span class="kc">False</span><span class="p">):</span> <span class="sd">"""</span> <span class="sd"> Get a file from Google Cloud Storage.</span> @@ -198,12 +273,14 @@ <span class="c1"># Write the file to local file path, if requested.</span> <span class="k">if</span> <span class="n">filename</span><span class="p">:</span> - <span class="k">with</span> <span class="nb">open</span><span class="p">(</span><span class="n">filename</span><span class="p">,</span> <span class="s1">'w'</span><span class="p">)</span> <span class="k">as</span> <span class="n">file_fd</span><span class="p">:</span> + <span class="n">write_argument</span> <span class="o">=</span> <span class="s1">'wb'</span> <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">downloaded_file_bytes</span><span class="p">,</span> <span class="nb">bytes</span><span class="p">)</span> <span class="k">else</span> <span class="s1">'w'</span> + <span class="k">with</span> <span class="nb">open</span><span class="p">(</span><span class="n">filename</span><span class="p">,</span> <span class="n">write_argument</span><span class="p">)</span> <span class="k">as</span> <span class="n">file_fd</span><span class="p">:</span> <span class="n">file_fd</span><span class="o">.</span><span class="n">write</span><span class="p">(</span><span class="n">downloaded_file_bytes</span><span class="p">)</span> - <span class="k">return</span> <span class="n">downloaded_file_bytes</span> + <span class="k">return</span> <span class="n">downloaded_file_bytes</span></div> - <span class="k">def</span> <span class="nf">upload</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">bucket</span><span class="p">,</span> <span class="nb">object</span><span class="p">,</span> <span class="n">filename</span><span class="p">,</span> <span class="n">mime_type</span><span class="o">=</span><span class="s1">'application/octet-stream'</span><span class="p">):</span> + <span class="c1"># pylint:disable=redefined-builtin</span> +<div class="viewcode-block" id="GoogleCloudStorageHook.upload"><a class="viewcode-back" href="../../../../integration.html#airflow.contrib.hooks.gcs_hook.GoogleCloudStorageHook.upload">[docs]</a> <span class="k">def</span> <span class="nf">upload</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">bucket</span><span class="p">,</span> <span class="nb">object</span><span class="p">,</span> <span class="n">filename</span><span class="p">,</span> <span class="n">mime_type</span><span class="o">=</span><span class="s1">'application/octet-stream'</span><span class="p">):</span> <span class="sd">"""</span> <span class="sd"> Uploads a local file to Google Cloud Storage.</span> @@ -222,9 +299,145 @@ <span class="o">.</span><span class="n">objects</span><span class="p">()</span> \ <span class="o">.</span><span class="n">insert</span><span class="p">(</span><span class="n">bucket</span><span class="o">=</span><span class="n">bucket</span><span class="p">,</span> <span class="n">name</span><span class="o">=</span><span class="nb">object</span><span class="p">,</span> <span class="n">media_body</span><span class="o">=</span><span class="n">media</span><span class="p">)</span> \ <span class="o">.</span><span class="n">execute</span><span class="p">()</span></div> + + <span class="c1"># pylint:disable=redefined-builtin</span> +<div class="viewcode-block" id="GoogleCloudStorageHook.exists"><a class="viewcode-back" href="../../../../integration.html#airflow.contrib.hooks.gcs_hook.GoogleCloudStorageHook.exists">[docs]</a> <span class="k">def</span> <span class="nf">exists</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">bucket</span><span class="p">,</span> <span class="nb">object</span><span class="p">):</span> + <span class="sd">"""</span> +<span class="sd"> Checks for the existence of a file in Google Cloud Storage.</span> + +<span class="sd"> :param bucket: The Google cloud storage bucket where the object is.</span> +<span class="sd"> :type bucket: string</span> +<span class="sd"> :param object: The name of the object to check in the Google cloud</span> +<span class="sd"> storage bucket.</span> +<span class="sd"> :type object: string</span> +<span class="sd"> """</span> + <span class="n">service</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_conn</span><span class="p">()</span> + <span class="k">try</span><span class="p">:</span> + <span class="n">service</span> \ + <span class="o">.</span><span class="n">objects</span><span class="p">()</span> \ + <span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">bucket</span><span class="o">=</span><span class="n">bucket</span><span class="p">,</span> <span class="nb">object</span><span class="o">=</span><span class="nb">object</span><span class="p">)</span> \ + <span class="o">.</span><span class="n">execute</span><span class="p">()</span> + <span class="k">return</span> <span class="kc">True</span> + <span class="k">except</span> <span class="n">errors</span><span class="o">.</span><span class="n">HttpError</span> <span class="k">as</span> <span class="n">ex</span><span class="p">:</span> + <span class="k">if</span> <span class="n">ex</span><span class="o">.</span><span class="n">resp</span><span class="p">[</span><span class="s1">'status'</span><span class="p">]</span> <span class="o">==</span> <span class="s1">'404'</span><span class="p">:</span> + <span class="k">return</span> <span class="kc">False</span> + <span class="k">raise</span></div> + + <span class="c1"># pylint:disable=redefined-builtin</span> +<div class="viewcode-block" id="GoogleCloudStorageHook.is_updated_after"><a class="viewcode-back" href="../../../../integration.html#airflow.contrib.hooks.gcs_hook.GoogleCloudStorageHook.is_updated_after">[docs]</a> <span class="k">def</span> <span class="nf">is_updated_after</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">bucket</span><span class="p">,</span> <span class="nb">object</span><span class="p">,</span> <span class="n">ts</span><span class="p">):</span> + <span class="sd">"""</span> +<span class="sd"> Checks if an object is updated in Google Cloud Storage.</span> + +<span class="sd"> :param bucket: The Google cloud storage bucket where the object is.</span> +<span class="sd"> :type bucket: string</span> +<span class="sd"> :param object: The name of the object to check in the Google cloud</span> +<span class="sd"> storage bucket.</span> +<span class="sd"> :type object: string</span> +<span class="sd"> :param ts: The timestamp to check against.</span> +<span class="sd"> :type ts: datetime</span> +<span class="sd"> """</span> + <span class="n">service</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_conn</span><span class="p">()</span> + <span class="k">try</span><span class="p">:</span> + <span class="n">response</span> <span class="o">=</span> <span class="p">(</span><span class="n">service</span> + <span class="o">.</span><span class="n">objects</span><span class="p">()</span> + <span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">bucket</span><span class="o">=</span><span class="n">bucket</span><span class="p">,</span> <span class="nb">object</span><span class="o">=</span><span class="nb">object</span><span class="p">)</span> + <span class="o">.</span><span class="n">execute</span><span class="p">())</span> + + <span class="k">if</span> <span class="s1">'updated'</span> <span class="ow">in</span> <span class="n">response</span><span class="p">:</span> + <span class="kn">import</span> <span class="nn">dateutil.parser</span> + <span class="kn">import</span> <span class="nn">dateutil.tz</span> + + <span class="k">if</span> <span class="ow">not</span> <span class="n">ts</span><span class="o">.</span><span class="n">tzinfo</span><span class="p">:</span> + <span class="n">ts</span> <span class="o">=</span> <span class="n">ts</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="n">tzinfo</span><span class="o">=</span><span class="n">dateutil</span><span class="o">.</span><span class="n">tz</span><span class="o">.</span><span class="n">tzutc</span><span class="p">())</span> + + <span class="n">updated</span> <span class="o">=</span> <span class="n">dateutil</span><span class="o">.</span><span class="n">parser</span><span class="o">.</span><span class="n">parse</span><span class="p">(</span><span class="n">response</span><span class="p">[</span><span class="s1">'updated'</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">"Verify object date: </span><span class="si">%s</span><span class="s2"> > </span><span class="si">%s</span><span class="s2">"</span><span class="p">,</span> <span class="n">updated</span><span class="p">,</span> <span class="n">ts</span><span class="p">)</span> + + <span class="k">if</span> <span class="n">updated</span> <span class="o">></span> <span class="n">ts</span><span class="p">:</span> + <span class="k">return</span> <span class="kc">True</span> + + <span class="k">except</span> <span class="n">errors</span><span class="o">.</span><span class="n">HttpError</span> <span class="k">as</span> <span class="n">ex</span><span class="p">:</span> + <span class="k">if</span> <span class="n">ex</span><span class="o">.</span><span class="n">resp</span><span class="p">[</span><span class="s1">'status'</span><span class="p">]</span> <span class="o">!=</span> <span class="s1">'404'</span><span class="p">:</span> + <span class="k">raise</span> + + <span class="k">return</span> <span class="kc">False</span></div> + +<div class="viewcode-block" id="GoogleCloudStorageHook.delete"><a class="viewcode-back" href="../../../../integration.html#airflow.contrib.hooks.gcs_hook.GoogleCloudStorageHook.delete">[docs]</a> <span class="k">def</span> <span class="nf">delete</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">bucket</span><span class="p">,</span> <span class="nb">object</span><span class="p">,</span> <span class="n">generation</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> + <span class="sd">"""</span> +<span class="sd"> Delete an object if versioning is not enabled for the bucket, or if generation</span> +<span class="sd"> parameter is used.</span> + +<span class="sd"> :param bucket: name of the bucket, where the object resides</span> +<span class="sd"> :type bucket: string</span> +<span class="sd"> :param object: name of the object to delete</span> +<span class="sd"> :type object: string</span> +<span class="sd"> :param generation: if present, permanently delete the object of this generation</span> +<span class="sd"> :type generation: string</span> +<span class="sd"> :return: True if succeeded</span> +<span class="sd"> """</span> + <span class="n">service</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_conn</span><span class="p">()</span> + + <span class="k">try</span><span class="p">:</span> + <span class="n">service</span> \ + <span class="o">.</span><span class="n">objects</span><span class="p">()</span> \ + <span class="o">.</span><span class="n">delete</span><span class="p">(</span><span class="n">bucket</span><span class="o">=</span><span class="n">bucket</span><span class="p">,</span> <span class="nb">object</span><span class="o">=</span><span class="nb">object</span><span class="p">,</span> <span class="n">generation</span><span class="o">=</span><span class="n">generation</span><span class="p">)</span> \ + <span class="o">.</span><span class="n">execute</span><span class="p">()</span> + <span class="k">return</span> <span class="kc">True</span> + <span class="k">except</span> <span class="n">errors</span><span class="o">.</span><span class="n">HttpError</span> <span class="k">as</span> <span class="n">ex</span><span class="p">:</span> + <span class="k">if</span> <span class="n">ex</span><span class="o">.</span><span class="n">resp</span><span class="p">[</span><span class="s1">'status'</span><span class="p">]</span> <span class="o">==</span> <span class="s1">'404'</span><span class="p">:</span> + <span class="k">return</span> <span class="kc">False</span> + <span class="k">raise</span></div> + +<div class="viewcode-block" id="GoogleCloudStorageHook.list"><a class="viewcode-back" href="../../../../integration.html#airflow.contrib.hooks.gcs_hook.GoogleCloudStorageHook.list">[docs]</a> <span class="k">def</span> <span class="nf">list</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">bucket</span><span class="p">,</span> <span class="n">versions</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">maxResults</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">prefix</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> + <span class="sd">"""</span> +<span class="sd"> List all objects from the bucket with the give string prefix in name</span> + +<span class="sd"> :param bucket: bucket name</span> +<span class="sd"> :type bucket: string</span> +<span class="sd"> :param versions: if true, list all versions of the objects</span> +<span class="sd"> :type versions: boolean</span> +<span class="sd"> :param maxResults: max count of items to return in a single page of responses</span> +<span class="sd"> :type maxResults: integer</span> +<span class="sd"> :param prefix: prefix string which filters objects whose name begin with this prefix</span> +<span class="sd"> :type prefix: string</span> +<span class="sd"> :return: a stream of object names matching the filtering criteria</span> +<span class="sd"> """</span> + <span class="n">service</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_conn</span><span class="p">()</span> + + <span class="n">ids</span> <span class="o">=</span> <span class="nb">list</span><span class="p">()</span> + <span class="n">pageToken</span> <span class="o">=</span> <span class="kc">None</span> + <span class="k">while</span><span class="p">(</span><span class="kc">True</span><span class="p">):</span> + <span class="n">response</span> <span class="o">=</span> <span class="n">service</span><span class="o">.</span><span class="n">objects</span><span class="p">()</span><span class="o">.</span><span class="n">list</span><span class="p">(</span> + <span class="n">bucket</span><span class="o">=</span><span class="n">bucket</span><span class="p">,</span> + <span class="n">versions</span><span class="o">=</span><span class="n">versions</span><span class="p">,</span> + <span class="n">maxResults</span><span class="o">=</span><span class="n">maxResults</span><span class="p">,</span> + <span class="n">pageToken</span><span class="o">=</span><span class="n">pageToken</span><span class="p">,</span> + <span class="n">prefix</span><span class="o">=</span><span class="n">prefix</span> + <span class="p">)</span><span class="o">.</span><span class="n">execute</span><span class="p">()</span> + + <span class="k">if</span> <span class="s1">'items'</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">response</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">"No items found for prefix: </span><span class="si">%s</span><span class="s2">"</span><span class="p">,</span> <span class="n">prefix</span><span class="p">)</span> + <span class="k">break</span> + + <span class="k">for</span> <span class="n">item</span> <span class="ow">in</span> <span class="n">response</span><span class="p">[</span><span class="s1">'items'</span><span class="p">]:</span> + <span class="k">if</span> <span class="n">item</span> <span class="ow">and</span> <span class="s1">'name'</span> <span class="ow">in</span> <span class="n">item</span><span class="p">:</span> + <span class="n">ids</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">item</span><span class="p">[</span><span class="s1">'name'</span><span class="p">])</span> + + <span class="k">if</span> <span class="s1">'nextPageToken'</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">response</span><span class="p">:</span> + <span class="c1"># no further pages of results, so stop the loop</span> + <span class="k">break</span> + + <span class="n">pageToken</span> <span class="o">=</span> <span class="n">response</span><span class="p">[</span><span class="s1">'nextPageToken'</span><span class="p">]</span> + <span class="k">if</span> <span class="ow">not</span> <span class="n">pageToken</span><span class="p">:</span> + <span class="c1"># empty next page token</span> + <span class="k">break</span> + <span class="k">return</span> <span class="n">ids</span></div></div> </pre></div> </div> + <div class="articleComments"> + + </div> </div> <footer> @@ -257,7 +470,8 @@ VERSION:'', COLLAPSE_INDEX:false, FILE_SUFFIX:'.html', - HAS_SOURCE: true + HAS_SOURCE: true, + SOURCELINK_SUFFIX: '.txt' }; </script> <script type="text/javascript" src="../../../../_static/jquery.js"></script>
