http://git-wip-us.apache.org/repos/asf/incubator-airflow-site/blob/1f06fa0e/_modules/airflow/contrib/hooks/gcp_dataflow_hook.html ---------------------------------------------------------------------- diff --git a/_modules/airflow/contrib/hooks/gcp_dataflow_hook.html b/_modules/airflow/contrib/hooks/gcp_dataflow_hook.html index 808d22f..cf99744 100644 --- a/_modules/airflow/contrib/hooks/gcp_dataflow_hook.html +++ b/_modules/airflow/contrib/hooks/gcp_dataflow_hook.html @@ -178,6 +178,7 @@ <span class="c1"># specific language governing permissions and limitations</span> <span class="c1"># under the License.</span> <span class="kn">import</span> <span class="nn">json</span> +<span class="kn">import</span> <span class="nn">re</span> <span class="kn">import</span> <span class="nn">select</span> <span class="kn">import</span> <span class="nn">subprocess</span> <span class="kn">import</span> <span class="nn">time</span> @@ -194,12 +195,13 @@ <span class="k">class</span> <span class="nc">_DataflowJob</span><span class="p">(</span><span class="n">LoggingMixin</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">dataflow</span><span class="p">,</span> <span class="n">project_number</span><span class="p">,</span> <span class="n">name</span><span class="p">,</span> <span class="n">location</span><span class="p">,</span> <span class="n">poll_sleep</span><span class="o">=</span><span class="mi">10</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">dataflow</span><span class="p">,</span> <span class="n">project_number</span><span class="p">,</span> <span class="n">name</span><span class="p">,</span> <span class="n">location</span><span class="p">,</span> <span class="n">poll_sleep</span><span class="o">=</span><span class="mi">10</span><span class="p">,</span> + <span class="n">job_id</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> <span class="bp">self</span><span class="o">.</span><span class="n">_dataflow</span> <span class="o">=</span> <span class="n">dataflow</span> <span class="bp">self</span><span class="o">.</span><span class="n">_project_number</span> <span class="o">=</span> <span class="n">project_number</span> <span class="bp">self</span><span class="o">.</span><span class="n">_job_name</span> <span class="o">=</span> <span class="n">name</span> <span class="bp">self</span><span class="o">.</span><span class="n">_job_location</span> <span class="o">=</span> <span class="n">location</span> - <span class="bp">self</span><span class="o">.</span><span class="n">_job_id</span> <span class="o">=</span> <span class="kc">None</span> + <span class="bp">self</span><span class="o">.</span><span class="n">_job_id</span> <span class="o">=</span> <span class="n">job_id</span> <span class="bp">self</span><span class="o">.</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="bp">self</span><span class="o">.</span><span class="n">_poll_sleep</span> <span class="o">=</span> <span class="n">poll_sleep</span> @@ -207,7 +209,7 @@ <span class="n">jobs</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_dataflow</span><span class="o">.</span><span class="n">projects</span><span class="p">()</span><span class="o">.</span><span class="n">locations</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">list</span><span class="p">(</span> <span class="n">projectId</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_project_number</span><span class="p">,</span> <span class="n">location</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_job_location</span> - <span class="p">)</span><span class="o">.</span><span class="n">execute</span><span class="p">()</span> + <span class="p">)</span><span class="o">.</span><span class="n">execute</span><span class="p">(</span><span class="n">num_retries</span><span class="o">=</span><span class="mi">5</span><span class="p">)</span> <span class="k">for</span> <span class="n">job</span> <span class="ow">in</span> <span class="n">jobs</span><span class="p">[</span><span class="s1">'jobs'</span><span class="p">]:</span> <span class="k">if</span> <span class="n">job</span><span class="p">[</span><span class="s1">'name'</span><span class="p">]</span> <span class="o">==</span> <span class="bp">self</span><span class="o">.</span><span class="n">_job_name</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">_job_id</span> <span class="o">=</span> <span class="n">job</span><span class="p">[</span><span class="s1">'id'</span><span class="p">]</span> @@ -215,13 +217,15 @@ <span class="k">return</span> <span class="kc">None</span> <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="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_job_name</span><span class="p">:</span> + <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_job_id</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">_dataflow</span><span class="o">.</span><span class="n">projects</span><span class="p">()</span><span class="o">.</span><span class="n">locations</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">projectId</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_project_number</span><span class="p">,</span> + <span class="n">location</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_job_location</span><span class="p">,</span> + <span class="n">jobId</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_job_id</span><span class="p">)</span><span class="o">.</span><span class="n">execute</span><span class="p">(</span><span class="n">num_retries</span><span class="o">=</span><span class="mi">5</span><span class="p">)</span> + <span class="k">elif</span> <span class="bp">self</span><span class="o">.</span><span class="n">_job_name</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_id_from_name</span><span class="p">()</span> <span class="k">else</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">_dataflow</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">projectId</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_project_number</span><span class="p">,</span> - <span class="n">jobId</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_job_id</span> - <span class="p">)</span><span class="o">.</span><span class="n">execute</span><span class="p">()</span> + <span class="k">raise</span> <span class="ne">Exception</span><span class="p">(</span><span class="s1">'Missing both dataflow job ID and name.'</span><span class="p">)</span> <span class="k">if</span> <span class="n">job</span> <span class="ow">and</span> <span class="s1">'currentState'</span> <span class="ow">in</span> <span class="n">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">info</span><span class="p">(</span> @@ -284,36 +288,50 @@ <span class="k">def</span> <span class="nf">_line</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">fd</span><span class="p">):</span> <span class="k">if</span> <span class="n">fd</span> <span class="o">==</span> <span class="bp">self</span><span class="o">.</span><span class="n">_proc</span><span class="o">.</span><span class="n">stderr</span><span class="o">.</span><span class="n">fileno</span><span class="p">():</span> - <span class="n">lines</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_proc</span><span class="o">.</span><span class="n">stderr</span><span class="o">.</span><span class="n">readlines</span><span class="p">()</span> - <span class="k">for</span> <span class="n">line</span> <span class="ow">in</span> <span class="n">lines</span><span class="p">:</span> + <span class="n">line</span> <span class="o">=</span> <span class="sa">b</span><span class="s1">''</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_proc</span><span class="o">.</span><span class="n">stderr</span><span class="o">.</span><span class="n">readlines</span><span class="p">())</span> + <span class="k">if</span> <span class="n">line</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">warning</span><span class="p">(</span><span class="n">line</span><span class="p">[:</span><span class="o">-</span><span class="mi">1</span><span class="p">])</span> - <span class="k">if</span> <span class="n">lines</span><span class="p">:</span> - <span class="k">return</span> <span class="n">lines</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span> + <span class="k">return</span> <span class="n">line</span> <span class="k">if</span> <span class="n">fd</span> <span class="o">==</span> <span class="bp">self</span><span class="o">.</span><span class="n">_proc</span><span class="o">.</span><span class="n">stdout</span><span class="o">.</span><span class="n">fileno</span><span class="p">():</span> - <span class="n">line</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_proc</span><span class="o">.</span><span class="n">stdout</span><span class="o">.</span><span class="n">readline</span><span class="p">()</span> + <span class="n">line</span> <span class="o">=</span> <span class="sa">b</span><span class="s1">''</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_proc</span><span class="o">.</span><span class="n">stdout</span><span class="o">.</span><span class="n">readlines</span><span class="p">())</span> + <span class="k">if</span> <span class="n">line</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="n">line</span><span class="p">[:</span><span class="o">-</span><span class="mi">1</span><span class="p">])</span> <span class="k">return</span> <span class="n">line</span> <span class="nd">@staticmethod</span> <span class="k">def</span> <span class="nf">_extract_job</span><span class="p">(</span><span class="n">line</span><span class="p">):</span> - <span class="k">if</span> <span class="n">line</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> - <span class="k">if</span> <span class="n">line</span><span class="o">.</span><span class="n">startswith</span><span class="p">(</span><span class="s2">"Submitted job: "</span><span class="p">):</span> - <span class="k">return</span> <span class="n">line</span><span class="p">[</span><span class="mi">15</span><span class="p">:</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span> + <span class="c1"># Job id info: https://goo.gl/SE29y9.</span> + <span class="n">job_id_pattern</span> <span class="o">=</span> <span class="n">re</span><span class="o">.</span><span class="n">compile</span><span class="p">(</span> + <span class="sa">b</span><span class="s1">'.*console.cloud.google.com/dataflow.*/jobs/([a-z|0-9|A-Z|\-|\_]+).*'</span><span class="p">)</span> + <span class="n">matched_job</span> <span class="o">=</span> <span class="n">job_id_pattern</span><span class="o">.</span><span class="n">search</span><span class="p">(</span><span class="n">line</span> <span class="ow">or</span> <span class="s1">''</span><span class="p">)</span> + <span class="k">if</span> <span class="n">matched_job</span><span class="p">:</span> + <span class="k">return</span> <span class="n">matched_job</span><span class="o">.</span><span class="n">group</span><span class="p">(</span><span class="mi">1</span><span class="p">)</span><span class="o">.</span><span class="n">decode</span><span class="p">()</span> <span class="k">def</span> <span class="nf">wait_for_done</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> <span class="n">reads</span> <span class="o">=</span> <span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">_proc</span><span class="o">.</span><span class="n">stderr</span><span class="o">.</span><span class="n">fileno</span><span class="p">(),</span> <span class="bp">self</span><span class="o">.</span><span class="n">_proc</span><span class="o">.</span><span class="n">stdout</span><span class="o">.</span><span class="n">fileno</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">"Start waiting for DataFlow process to complete."</span><span class="p">)</span> - <span class="k">while</span> <span class="bp">self</span><span class="o">.</span><span class="n">_proc</span><span class="o">.</span><span class="n">poll</span><span class="p">()</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> + <span class="n">job_id</span> <span class="o">=</span> <span class="kc">None</span> + <span class="c1"># Make sure logs are processed regardless whether the subprocess is</span> + <span class="c1"># terminated.</span> + <span class="n">process_ends</span> <span class="o">=</span> <span class="kc">False</span> + <span class="k">while</span> <span class="kc">True</span><span class="p">:</span> <span class="n">ret</span> <span class="o">=</span> <span class="n">select</span><span class="o">.</span><span class="n">select</span><span class="p">(</span><span class="n">reads</span><span class="p">,</span> <span class="p">[],</span> <span class="p">[],</span> <span class="mi">5</span><span class="p">)</span> <span class="k">if</span> <span class="n">ret</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> <span class="k">for</span> <span class="n">fd</span> <span class="ow">in</span> <span class="n">ret</span><span class="p">[</span><span class="mi">0</span><span class="p">]:</span> <span class="n">line</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_line</span><span class="p">(</span><span class="n">fd</span><span class="p">)</span> <span class="k">if</span> <span class="n">line</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">debug</span><span class="p">(</span><span class="n">line</span><span class="p">[:</span><span class="o">-</span><span class="mi">1</span><span class="p">])</span> + <span class="n">job_id</span> <span class="o">=</span> <span class="n">job_id</span> <span class="ow">or</span> <span class="bp">self</span><span class="o">.</span><span class="n">_extract_job</span><span class="p">(</span><span class="n">line</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">info</span><span class="p">(</span><span class="s2">"Waiting for DataFlow process to complete."</span><span class="p">)</span> + <span class="k">if</span> <span class="n">process_ends</span><span class="p">:</span> + <span class="k">break</span> + <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_proc</span><span class="o">.</span><span class="n">poll</span><span class="p">()</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> + <span class="c1"># Mark process completion but allows its outputs to be consumed.</span> + <span class="n">process_ends</span> <span class="o">=</span> <span class="kc">True</span> <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_proc</span><span class="o">.</span><span class="n">returncode</span> <span class="ow">is</span> <span class="ow">not</span> <span class="mi">0</span><span class="p">:</span> <span class="k">raise</span> <span class="ne">Exception</span><span class="p">(</span><span class="s2">"DataFlow failed with return code </span><span class="si">{}</span><span class="s2">"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span> <span class="bp">self</span><span class="o">.</span><span class="n">_proc</span><span class="o">.</span><span class="n">returncode</span><span class="p">))</span> + <span class="k">return</span> <span class="n">job_id</span> <div class="viewcode-block" id="DataFlowHook"><a class="viewcode-back" href="../../../../integration.html#airflow.contrib.hooks.gcp_dataflow_hook.DataFlowHook">[docs]</a><span class="k">class</span> <span class="nc">DataFlowHook</span><span class="p">(</span><span class="n">GoogleCloudBaseHook</span><span class="p">):</span> @@ -327,7 +345,7 @@ <div class="viewcode-block" id="DataFlowHook.get_conn"><a class="viewcode-back" href="../../../../integration.html#airflow.contrib.hooks.gcp_dataflow_hook.DataFlowHook.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"> Returns a Google Cloud Dataflow 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> @@ -338,9 +356,10 @@ <span class="n">variables</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set_variables</span><span class="p">(</span><span class="n">variables</span><span class="p">)</span> <span class="n">cmd</span> <span class="o">=</span> <span class="n">command_prefix</span> <span class="o">+</span> <span class="bp">self</span><span class="o">.</span><span class="n">_build_cmd</span><span class="p">(</span><span class="n">task_id</span><span class="p">,</span> <span class="n">variables</span><span class="p">,</span> <span class="n">label_formatter</span><span class="p">)</span> - <span class="n">_Dataflow</span><span class="p">(</span><span class="n">cmd</span><span class="p">)</span><span class="o">.</span><span class="n">wait_for_done</span><span class="p">()</span> + <span class="n">job_id</span> <span class="o">=</span> <span class="n">_Dataflow</span><span class="p">(</span><span class="n">cmd</span><span class="p">)</span><span class="o">.</span><span class="n">wait_for_done</span><span class="p">()</span> <span class="n">_DataflowJob</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">get_conn</span><span class="p">(),</span> <span class="n">variables</span><span class="p">[</span><span class="s1">'project'</span><span class="p">],</span> <span class="n">name</span><span class="p">,</span> - <span class="n">variables</span><span class="p">[</span><span class="s1">'region'</span><span class="p">],</span> <span class="bp">self</span><span class="o">.</span><span class="n">poll_sleep</span><span class="p">)</span><span class="o">.</span><span class="n">wait_for_done</span><span class="p">()</span> + <span class="n">variables</span><span class="p">[</span><span class="s1">'region'</span><span class="p">],</span> + <span class="bp">self</span><span class="o">.</span><span class="n">poll_sleep</span><span class="p">,</span> <span class="n">job_id</span><span class="p">)</span><span class="o">.</span><span class="n">wait_for_done</span><span class="p">()</span> <span class="nd">@staticmethod</span> <span class="k">def</span> <span class="nf">_set_variables</span><span class="p">(</span><span class="n">variables</span><span class="p">):</span> @@ -352,10 +371,7 @@ <span class="k">def</span> <span class="nf">start_java_dataflow</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">task_id</span><span class="p">,</span> <span class="n">variables</span><span class="p">,</span> <span class="n">dataflow</span><span class="p">,</span> <span class="n">job_class</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">append_job_name</span><span class="o">=</span><span class="kc">True</span><span class="p">):</span> - <span class="k">if</span> <span class="n">append_job_name</span><span class="p">:</span> - <span class="n">name</span> <span class="o">=</span> <span class="n">task_id</span> <span class="o">+</span> <span class="s2">"-"</span> <span class="o">+</span> <span class="nb">str</span><span class="p">(</span><span class="n">uuid</span><span class="o">.</span><span class="n">uuid1</span><span class="p">())[:</span><span class="mi">8</span><span class="p">]</span> - <span class="k">else</span><span class="p">:</span> - <span class="n">name</span> <span class="o">=</span> <span class="n">task_id</span> + <span class="n">name</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_build_dataflow_job_name</span><span class="p">(</span><span class="n">task_id</span><span class="p">,</span> <span class="n">append_job_name</span><span class="p">)</span> <span class="n">variables</span><span class="p">[</span><span class="s1">'jobName'</span><span class="p">]</span> <span class="o">=</span> <span class="n">name</span> <span class="k">def</span> <span class="nf">label_formatter</span><span class="p">(</span><span class="n">labels_dict</span><span class="p">):</span> @@ -368,19 +384,13 @@ <span class="k">def</span> <span class="nf">start_template_dataflow</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">task_id</span><span class="p">,</span> <span class="n">variables</span><span class="p">,</span> <span class="n">parameters</span><span class="p">,</span> <span class="n">dataflow_template</span><span class="p">,</span> <span class="n">append_job_name</span><span class="o">=</span><span class="kc">True</span><span class="p">):</span> - <span class="k">if</span> <span class="n">append_job_name</span><span class="p">:</span> - <span class="n">name</span> <span class="o">=</span> <span class="n">task_id</span> <span class="o">+</span> <span class="s2">"-"</span> <span class="o">+</span> <span class="nb">str</span><span class="p">(</span><span class="n">uuid</span><span class="o">.</span><span class="n">uuid1</span><span class="p">())[:</span><span class="mi">8</span><span class="p">]</span> - <span class="k">else</span><span class="p">:</span> - <span class="n">name</span> <span class="o">=</span> <span class="n">task_id</span> + <span class="n">name</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_build_dataflow_job_name</span><span class="p">(</span><span class="n">task_id</span><span class="p">,</span> <span class="n">append_job_name</span><span class="p">)</span> <span class="bp">self</span><span class="o">.</span><span class="n">_start_template_dataflow</span><span class="p">(</span> <span class="n">name</span><span class="p">,</span> <span class="n">variables</span><span class="p">,</span> <span class="n">parameters</span><span class="p">,</span> <span class="n">dataflow_template</span><span class="p">)</span> <span class="k">def</span> <span class="nf">start_python_dataflow</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">task_id</span><span class="p">,</span> <span class="n">variables</span><span class="p">,</span> <span class="n">dataflow</span><span class="p">,</span> <span class="n">py_options</span><span class="p">,</span> <span class="n">append_job_name</span><span class="o">=</span><span class="kc">True</span><span class="p">):</span> - <span class="k">if</span> <span class="n">append_job_name</span><span class="p">:</span> - <span class="n">name</span> <span class="o">=</span> <span class="n">task_id</span> <span class="o">+</span> <span class="s2">"-"</span> <span class="o">+</span> <span class="nb">str</span><span class="p">(</span><span class="n">uuid</span><span class="o">.</span><span class="n">uuid1</span><span class="p">())[:</span><span class="mi">8</span><span class="p">]</span> - <span class="k">else</span><span class="p">:</span> - <span class="n">name</span> <span class="o">=</span> <span class="n">task_id</span> + <span class="n">name</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_build_dataflow_job_name</span><span class="p">(</span><span class="n">task_id</span><span class="p">,</span> <span class="n">append_job_name</span><span class="p">)</span> <span class="n">variables</span><span class="p">[</span><span class="s1">'job_name'</span><span class="p">]</span> <span class="o">=</span> <span class="n">name</span> <span class="k">def</span> <span class="nf">label_formatter</span><span class="p">(</span><span class="n">labels_dict</span><span class="p">):</span> @@ -390,7 +400,25 @@ <span class="p">[</span><span class="s2">"python"</span><span class="p">]</span> <span class="o">+</span> <span class="n">py_options</span> <span class="o">+</span> <span class="p">[</span><span class="n">dataflow</span><span class="p">],</span> <span class="n">label_formatter</span><span class="p">)</span> - <span class="k">def</span> <span class="nf">_build_cmd</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">task_id</span><span class="p">,</span> <span class="n">variables</span><span class="p">,</span> <span class="n">label_formatter</span><span class="p">):</span> + <span class="nd">@staticmethod</span> + <span class="k">def</span> <span class="nf">_build_dataflow_job_name</span><span class="p">(</span><span class="n">task_id</span><span class="p">,</span> <span class="n">append_job_name</span><span class="o">=</span><span class="kc">True</span><span class="p">):</span> + <span class="n">task_id</span> <span class="o">=</span> <span class="nb">str</span><span class="p">(</span><span class="n">task_id</span><span class="p">)</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="s1">'_'</span><span class="p">,</span> <span class="s1">'-'</span><span class="p">)</span> + + <span class="k">if</span> <span class="ow">not</span> <span class="n">re</span><span class="o">.</span><span class="n">match</span><span class="p">(</span><span class="sa">r</span><span class="s2">"^[a-z]([-a-z0-9]*[a-z0-9])?$"</span><span class="p">,</span> <span class="n">task_id</span><span class="p">):</span> + <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span> + <span class="s1">'Invalid job_name (</span><span class="si">{}</span><span class="s1">); the name must consist of'</span> + <span class="s1">'only the characters [-a-z0-9], starting with a '</span> + <span class="s1">'letter and ending with a letter or number '</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">task_id</span><span class="p">))</span> + + <span class="k">if</span> <span class="n">append_job_name</span><span class="p">:</span> + <span class="n">job_name</span> <span class="o">=</span> <span class="n">task_id</span> <span class="o">+</span> <span class="s2">"-"</span> <span class="o">+</span> <span class="nb">str</span><span class="p">(</span><span class="n">uuid</span><span class="o">.</span><span class="n">uuid1</span><span class="p">())[:</span><span class="mi">8</span><span class="p">]</span> + <span class="k">else</span><span class="p">:</span> + <span class="n">job_name</span> <span class="o">=</span> <span class="n">task_id</span> + + <span class="k">return</span> <span class="n">job_name</span> + + <span class="nd">@staticmethod</span> + <span class="k">def</span> <span class="nf">_build_cmd</span><span class="p">(</span><span class="n">task_id</span><span class="p">,</span> <span class="n">variables</span><span class="p">,</span> <span class="n">label_formatter</span><span class="p">):</span> <span class="n">command</span> <span class="o">=</span> <span class="p">[</span><span class="s2">"--runner=DataflowRunner"</span><span class="p">]</span> <span class="k">if</span> <span class="n">variables</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> <span class="k">for</span> <span class="n">attr</span><span class="p">,</span> <span class="n">value</span> <span class="ow">in</span> <span class="n">variables</span><span class="o">.</span><span class="n">items</span><span class="p">():</span> @@ -402,7 +430,8 @@ <span class="n">command</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="s2">"--"</span> <span class="o">+</span> <span class="n">attr</span> <span class="o">+</span> <span class="s2">"="</span> <span class="o">+</span> <span class="n">value</span><span class="p">)</span> <span class="k">return</span> <span class="n">command</span> - <span class="k">def</span> <span class="nf">_start_template_dataflow</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">name</span><span class="p">,</span> <span class="n">variables</span><span class="p">,</span> <span class="n">parameters</span><span class="p">,</span> <span class="n">dataflow_template</span><span class="p">):</span> + <span class="k">def</span> <span class="nf">_start_template_dataflow</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">name</span><span class="p">,</span> <span class="n">variables</span><span class="p">,</span> <span class="n">parameters</span><span class="p">,</span> + <span class="n">dataflow_template</span><span class="p">):</span> <span class="c1"># Builds RuntimeEnvironment from variables dictionary</span> <span class="c1"># https://cloud.google.com/dataflow/docs/reference/rest/v1b3/RuntimeEnvironment</span> <span class="n">environment</span> <span class="o">=</span> <span class="p">{}</span> @@ -414,9 +443,11 @@ <span class="s2">"parameters"</span><span class="p">:</span> <span class="n">parameters</span><span class="p">,</span> <span class="s2">"environment"</span><span class="p">:</span> <span class="n">environment</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="n">request</span> <span class="o">=</span> <span class="n">service</span><span class="o">.</span><span class="n">projects</span><span class="p">()</span><span class="o">.</span><span class="n">templates</span><span class="p">()</span><span class="o">.</span><span class="n">launch</span><span class="p">(</span><span class="n">projectId</span><span class="o">=</span><span class="n">variables</span><span class="p">[</span><span class="s1">'project'</span><span class="p">],</span> - <span class="n">gcsPath</span><span class="o">=</span><span class="n">dataflow_template</span><span class="p">,</span> - <span class="n">body</span><span class="o">=</span><span class="n">body</span><span class="p">)</span> + <span class="n">request</span> <span class="o">=</span> <span class="n">service</span><span class="o">.</span><span class="n">projects</span><span class="p">()</span><span class="o">.</span><span class="n">templates</span><span class="p">()</span><span class="o">.</span><span class="n">launch</span><span class="p">(</span> + <span class="n">projectId</span><span class="o">=</span><span class="n">variables</span><span class="p">[</span><span class="s1">'project'</span><span class="p">],</span> + <span class="n">gcsPath</span><span class="o">=</span><span class="n">dataflow_template</span><span class="p">,</span> + <span class="n">body</span><span class="o">=</span><span class="n">body</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">variables</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set_variables</span><span class="p">(</span><span class="n">variables</span><span class="p">)</span> <span class="n">_DataflowJob</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">get_conn</span><span class="p">(),</span> <span class="n">variables</span><span class="p">[</span><span class="s1">'project'</span><span class="p">],</span> <span class="n">name</span><span class="p">,</span> <span class="n">variables</span><span class="p">[</span><span class="s1">'region'</span><span class="p">],</span> @@ -452,20 +483,13 @@ - <script type="text/javascript"> - var DOCUMENTATION_OPTIONS = { - URL_ROOT:'../../../../', - VERSION:'', - LANGUAGE:'None', - 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" 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> +
http://git-wip-us.apache.org/repos/asf/incubator-airflow-site/blob/1f06fa0e/_modules/airflow/contrib/hooks/gcp_dataproc_hook.html ---------------------------------------------------------------------- diff --git a/_modules/airflow/contrib/hooks/gcp_dataproc_hook.html b/_modules/airflow/contrib/hooks/gcp_dataproc_hook.html index d22dfa5..2f062a9 100644 --- a/_modules/airflow/contrib/hooks/gcp_dataproc_hook.html +++ b/_modules/airflow/contrib/hooks/gcp_dataproc_hook.html @@ -429,20 +429,13 @@ - <script type="text/javascript"> - var DOCUMENTATION_OPTIONS = { - URL_ROOT:'../../../../', - VERSION:'', - LANGUAGE:'None', - 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" 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> + http://git-wip-us.apache.org/repos/asf/incubator-airflow-site/blob/1f06fa0e/_modules/airflow/contrib/hooks/gcp_function_hook.html ---------------------------------------------------------------------- diff --git a/_modules/airflow/contrib/hooks/gcp_function_hook.html b/_modules/airflow/contrib/hooks/gcp_function_hook.html new file mode 100644 index 0000000..366b837 --- /dev/null +++ b/_modules/airflow/contrib/hooks/gcp_function_hook.html @@ -0,0 +1,406 @@ + + +<!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_function_hook — Airflow Documentation</title> + + + + + + + + + + + + + + + + <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 src="../../../../_static/js/modernizr.min.js"></script> + +</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 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 & 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="../../../../lineage.html">Lineage</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" 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_function_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_function_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"># "License"); 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"># "AS IS" 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="kn">import</span> <span class="nn">time</span> +<span class="kn">import</span> <span class="nn">requests</span> +<span class="kn">from</span> <span class="nn">googleapiclient.discovery</span> <span class="k">import</span> <span class="n">build</span> + +<span class="kn">from</span> <span class="nn">airflow</span> <span class="k">import</span> <span class="n">AirflowException</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="c1"># Number of retries - used by googleapiclient method calls to perform retries</span> +<span class="c1"># For requests that are "retriable"</span> +<span class="n">NUM_RETRIES</span> <span class="o">=</span> <span class="mi">5</span> + +<span class="c1"># Time to sleep between active checks of the operation results</span> +<span class="n">TIME_TO_SLEEP_IN_SECONDS</span> <span class="o">=</span> <span class="mi">1</span> + + +<span class="c1"># noinspection PyAbstractClass</span> +<div class="viewcode-block" id="GcfHook"><a class="viewcode-back" href="../../../../integration.html#airflow.contrib.hooks.gcp_function_hook.GcfHook">[docs]</a><span class="k">class</span> <span class="nc">GcfHook</span><span class="p">(</span><span class="n">GoogleCloudBaseHook</span><span class="p">):</span> + <span class="sd">"""</span> +<span class="sd"> Hook for the Google Cloud Functions APIs.</span> +<span class="sd"> """</span> + <span class="n">_conn</span> <span class="o">=</span> <span class="kc">None</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">api_version</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">GcfHook</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">api_version</span> <span class="o">=</span> <span class="n">api_version</span> + +<div class="viewcode-block" id="GcfHook.get_conn"><a class="viewcode-back" href="../../../../integration.html#airflow.contrib.hooks.gcp_function_hook.GcfHook.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"> Retrieves the connection to Cloud Functions.</span> + +<span class="sd"> :return: Google Cloud Function services object</span> +<span class="sd"> :rtype: dict</span> +<span class="sd"> """</span> + <span class="k">if</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">_conn</span><span class="p">:</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="bp">self</span><span class="o">.</span><span class="n">_conn</span> <span class="o">=</span> <span class="n">build</span><span class="p">(</span><span class="s1">'cloudfunctions'</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">api_version</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="n">cache_discovery</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span> + <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_conn</span></div> + +<div class="viewcode-block" id="GcfHook.get_function"><a class="viewcode-back" href="../../../../integration.html#airflow.contrib.hooks.gcp_function_hook.GcfHook.get_function">[docs]</a> <span class="k">def</span> <span class="nf">get_function</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">name</span><span class="p">):</span> + <span class="sd">"""</span> +<span class="sd"> Returns the Cloud Function with the given name.</span> + +<span class="sd"> :param name: name of the function</span> +<span class="sd"> :type name: str</span> +<span class="sd"> :return: a CloudFunction object representing the function</span> +<span class="sd"> :rtype: dict</span> +<span class="sd"> """</span> + <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_conn</span><span class="p">()</span><span class="o">.</span><span class="n">projects</span><span class="p">()</span><span class="o">.</span><span class="n">locations</span><span class="p">()</span><span class="o">.</span><span class="n">functions</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">name</span><span class="p">)</span><span class="o">.</span><span class="n">execute</span><span class="p">(</span><span class="n">num_retries</span><span class="o">=</span><span class="n">NUM_RETRIES</span><span class="p">)</span></div> + +<div class="viewcode-block" id="GcfHook.list_functions"><a class="viewcode-back" href="../../../../integration.html#airflow.contrib.hooks.gcp_function_hook.GcfHook.list_functions">[docs]</a> <span class="k">def</span> <span class="nf">list_functions</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">full_location</span><span class="p">):</span> + <span class="sd">"""</span> +<span class="sd"> Lists all Cloud Functions created in the location.</span> + +<span class="sd"> :param full_location: full location including the project in the form of</span> +<span class="sd"> of /projects/<PROJECT>/location/<LOCATION></span> +<span class="sd"> :type full_location: str</span> +<span class="sd"> :return: array of CloudFunction objects - representing functions in the location</span> +<span class="sd"> :rtype: [dict]</span> +<span class="sd"> """</span> + <span class="n">list_response</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="o">.</span><span class="n">projects</span><span class="p">()</span><span class="o">.</span><span class="n">locations</span><span class="p">()</span><span class="o">.</span><span class="n">functions</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_location</span><span class="p">)</span><span class="o">.</span><span class="n">execute</span><span class="p">(</span><span class="n">num_retries</span><span class="o">=</span><span class="n">NUM_RETRIES</span><span class="p">)</span> + <span class="k">return</span> <span class="n">list_response</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">"functions"</span><span class="p">,</span> <span class="p">[])</span></div> + +<div class="viewcode-block" id="GcfHook.create_new_function"><a class="viewcode-back" href="../../../../integration.html#airflow.contrib.hooks.gcp_function_hook.GcfHook.create_new_function">[docs]</a> <span class="k">def</span> <span class="nf">create_new_function</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">full_location</span><span class="p">,</span> <span class="n">body</span><span class="p">):</span> + <span class="sd">"""</span> +<span class="sd"> Creates a new function in Cloud Function in the location specified in the body.</span> + +<span class="sd"> :param full_location: full location including the project in the form of</span> +<span class="sd"> of /projects/<PROJECT>/location/<LOCATION></span> +<span class="sd"> :type full_location: str</span> +<span class="sd"> :param body: body required by the Cloud Functions insert API</span> +<span class="sd"> :type body: dict</span> +<span class="sd"> :return: response returned by the operation</span> +<span class="sd"> :rtype: dict</span> +<span class="sd"> """</span> + <span class="n">response</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="o">.</span><span class="n">projects</span><span class="p">()</span><span class="o">.</span><span class="n">locations</span><span class="p">()</span><span class="o">.</span><span class="n">functions</span><span class="p">()</span><span class="o">.</span><span class="n">create</span><span class="p">(</span> + <span class="n">location</span><span class="o">=</span><span class="n">full_location</span><span class="p">,</span> + <span class="n">body</span><span class="o">=</span><span class="n">body</span> + <span class="p">)</span><span class="o">.</span><span class="n">execute</span><span class="p">(</span><span class="n">num_retries</span><span class="o">=</span><span class="n">NUM_RETRIES</span><span class="p">)</span> + <span class="n">operation_name</span> <span class="o">=</span> <span class="n">response</span><span class="p">[</span><span class="s2">"name"</span><span class="p">]</span> + <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_wait_for_operation_to_complete</span><span class="p">(</span><span class="n">operation_name</span><span class="p">)</span></div> + +<div class="viewcode-block" id="GcfHook.update_function"><a class="viewcode-back" href="../../../../integration.html#airflow.contrib.hooks.gcp_function_hook.GcfHook.update_function">[docs]</a> <span class="k">def</span> <span class="nf">update_function</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">name</span><span class="p">,</span> <span class="n">body</span><span class="p">,</span> <span class="n">update_mask</span><span class="p">):</span> + <span class="sd">"""</span> +<span class="sd"> Updates Cloud Functions according to the specified update mask.</span> + +<span class="sd"> :param name: name of the function</span> +<span class="sd"> :type name: str</span> +<span class="sd"> :param body: body required by the cloud function patch API</span> +<span class="sd"> :type body: str</span> +<span class="sd"> :param update_mask: update mask - array of fields that should be patched</span> +<span class="sd"> :type update_mask: [str]</span> +<span class="sd"> :return: response returned by the operation</span> +<span class="sd"> :rtype: dict</span> +<span class="sd"> """</span> + <span class="n">response</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="o">.</span><span class="n">projects</span><span class="p">()</span><span class="o">.</span><span class="n">locations</span><span class="p">()</span><span class="o">.</span><span class="n">functions</span><span class="p">()</span><span class="o">.</span><span class="n">patch</span><span class="p">(</span> + <span class="n">updateMask</span><span class="o">=</span><span class="s2">","</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">update_mask</span><span class="p">),</span> + <span class="n">name</span><span class="o">=</span><span class="n">name</span><span class="p">,</span> + <span class="n">body</span><span class="o">=</span><span class="n">body</span> + <span class="p">)</span><span class="o">.</span><span class="n">execute</span><span class="p">(</span><span class="n">num_retries</span><span class="o">=</span><span class="n">NUM_RETRIES</span><span class="p">)</span> + <span class="n">operation_name</span> <span class="o">=</span> <span class="n">response</span><span class="p">[</span><span class="s2">"name"</span><span class="p">]</span> + <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_wait_for_operation_to_complete</span><span class="p">(</span><span class="n">operation_name</span><span class="p">)</span></div> + +<div class="viewcode-block" id="GcfHook.upload_function_zip"><a class="viewcode-back" href="../../../../integration.html#airflow.contrib.hooks.gcp_function_hook.GcfHook.upload_function_zip">[docs]</a> <span class="k">def</span> <span class="nf">upload_function_zip</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">parent</span><span class="p">,</span> <span class="n">zip_path</span><span class="p">):</span> + <span class="sd">"""</span> +<span class="sd"> Uploads zip file with sources.</span> + +<span class="sd"> :param parent: Google Cloud Platform project id and region where zip file should</span> +<span class="sd"> be uploaded in the form of /projects/<PROJECT>/location/<LOCATION></span> +<span class="sd"> :type parent: str</span> +<span class="sd"> :param zip_path: path of the valid .zip file to upload</span> +<span class="sd"> :type zip_path: str</span> +<span class="sd"> :return: Upload URL that was returned by generateUploadUrl method</span> +<span class="sd"> """</span> + <span class="n">response</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="o">.</span><span class="n">projects</span><span class="p">()</span><span class="o">.</span><span class="n">locations</span><span class="p">()</span><span class="o">.</span><span class="n">functions</span><span class="p">()</span><span class="o">.</span><span class="n">generateUploadUrl</span><span class="p">(</span> + <span class="n">parent</span><span class="o">=</span><span class="n">parent</span> + <span class="p">)</span><span class="o">.</span><span class="n">execute</span><span class="p">(</span><span class="n">num_retries</span><span class="o">=</span><span class="n">NUM_RETRIES</span><span class="p">)</span> + <span class="n">upload_url</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">'uploadUrl'</span><span class="p">)</span> + <span class="k">with</span> <span class="nb">open</span><span class="p">(</span><span class="n">zip_path</span><span class="p">,</span> <span class="s1">'rb'</span><span class="p">)</span> <span class="k">as</span> <span class="n">fp</span><span class="p">:</span> + <span class="n">requests</span><span class="o">.</span><span class="n">put</span><span class="p">(</span> + <span class="n">url</span><span class="o">=</span><span class="n">upload_url</span><span class="p">,</span> + <span class="n">data</span><span class="o">=</span><span class="n">fp</span><span class="o">.</span><span class="n">read</span><span class="p">(),</span> + <span class="c1"># Those two headers needs to be specified according to:</span> + <span class="c1"># https://cloud.google.com/functions/docs/reference/rest/v1/projects.locations.functions/generateUploadUrl</span> + <span class="c1"># nopep8</span> + <span class="n">headers</span><span class="o">=</span><span class="p">{</span> + <span class="s1">'Content-type'</span><span class="p">:</span> <span class="s1">'application/zip'</span><span class="p">,</span> + <span class="s1">'x-goog-content-length-range'</span><span class="p">:</span> <span class="s1">'0,104857600'</span><span class="p">,</span> + <span class="p">}</span> + <span class="p">)</span> + <span class="k">return</span> <span class="n">upload_url</span></div> + +<div class="viewcode-block" id="GcfHook.delete_function"><a class="viewcode-back" href="../../../../integration.html#airflow.contrib.hooks.gcp_function_hook.GcfHook.delete_function">[docs]</a> <span class="k">def</span> <span class="nf">delete_function</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">name</span><span class="p">):</span> + <span class="sd">"""</span> +<span class="sd"> Deletes the specified Cloud Function.</span> + +<span class="sd"> :param name: name of the function</span> +<span class="sd"> :type name: str</span> +<span class="sd"> :return: response returned by the operation</span> +<span class="sd"> :rtype: dict</span> +<span class="sd"> """</span> + <span class="n">response</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="o">.</span><span class="n">projects</span><span class="p">()</span><span class="o">.</span><span class="n">locations</span><span class="p">()</span><span class="o">.</span><span class="n">functions</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">name</span><span class="p">)</span><span class="o">.</span><span class="n">execute</span><span class="p">(</span><span class="n">num_retries</span><span class="o">=</span><span class="n">NUM_RETRIES</span><span class="p">)</span> + <span class="n">operation_name</span> <span class="o">=</span> <span class="n">response</span><span class="p">[</span><span class="s2">"name"</span><span class="p">]</span> + <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_wait_for_operation_to_complete</span><span class="p">(</span><span class="n">operation_name</span><span class="p">)</span></div> + + <span class="k">def</span> <span class="nf">_wait_for_operation_to_complete</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">operation_name</span><span class="p">):</span> + <span class="sd">"""</span> +<span class="sd"> Waits for the named operation to complete - checks status of the</span> +<span class="sd"> asynchronous call.</span> + +<span class="sd"> :param operation_name: name of the operation</span> +<span class="sd"> :type operation_name: str</span> +<span class="sd"> :return: response returned by the operation</span> +<span class="sd"> :rtype: dict</span> +<span class="sd"> :exception: AirflowException in case error is returned</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">while</span> <span class="kc">True</span><span class="p">:</span> + <span class="n">operation_response</span> <span class="o">=</span> <span class="n">service</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">operation_name</span><span class="p">,</span> + <span class="p">)</span><span class="o">.</span><span class="n">execute</span><span class="p">(</span><span class="n">num_retries</span><span class="o">=</span><span class="n">NUM_RETRIES</span><span class="p">)</span> + <span class="k">if</span> <span class="n">operation_response</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">"done"</span><span class="p">):</span> + <span class="n">response</span> <span class="o">=</span> <span class="n">operation_response</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">"response"</span><span class="p">)</span> + <span class="n">error</span> <span class="o">=</span> <span class="n">operation_response</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">"error"</span><span class="p">)</span> + <span class="c1"># Note, according to documentation always either response or error is</span> + <span class="c1"># set when "done" == True</span> + <span class="k">if</span> <span class="n">error</span><span class="p">:</span> + <span class="k">raise</span> <span class="n">AirflowException</span><span class="p">(</span><span class="nb">str</span><span class="p">(</span><span class="n">error</span><span class="p">))</span> + <span class="k">return</span> <span class="n">response</span> + <span class="n">time</span><span class="o">.</span><span class="n">sleep</span><span class="p">(</span><span class="n">TIME_TO_SLEEP_IN_SECONDS</span><span class="p">)</span></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" 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/js/theme.js"></script> + + <script type="text/javascript"> + jQuery(function () { + SphinxRtdTheme.Navigation.enable(true); + }); + </script> + +</body> +</html> \ No newline at end of file http://git-wip-us.apache.org/repos/asf/incubator-airflow-site/blob/1f06fa0e/_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 index b961738..f3b1782 100644 --- a/_modules/airflow/contrib/hooks/gcp_mlengine_hook.html +++ b/_modules/airflow/contrib/hooks/gcp_mlengine_hook.html @@ -313,7 +313,8 @@ <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">if</span> <span class="n">interval</span> <span class="o"><=</span> <span class="mi">0</span><span class="p">:</span> + <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">"Interval must be > 0"</span><span class="p">)</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> @@ -403,7 +404,9 @@ <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="k">if</span> <span class="ow">not</span> <span class="n">model</span><span class="p">[</span><span class="s1">'name'</span><span class="p">]:</span> + <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">"Model name must be provided and "</span> + <span class="s2">"could not be an empty string"</span><span class="p">)</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> @@ -414,7 +417,9 @@ <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="k">if</span> <span class="ow">not</span> <span class="n">model_name</span><span class="p">:</span> + <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">"Model name must be provided and "</span> + <span class="s2">"it could not be an empty string"</span><span class="p">)</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> @@ -455,20 +460,13 @@ - <script type="text/javascript"> - var DOCUMENTATION_OPTIONS = { - URL_ROOT:'../../../../', - VERSION:'', - LANGUAGE:'None', - 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" 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> + http://git-wip-us.apache.org/repos/asf/incubator-airflow-site/blob/1f06fa0e/_modules/airflow/contrib/hooks/gcp_pubsub_hook.html ---------------------------------------------------------------------- diff --git a/_modules/airflow/contrib/hooks/gcp_pubsub_hook.html b/_modules/airflow/contrib/hooks/gcp_pubsub_hook.html index 1cb0cac..231392a 100644 --- a/_modules/airflow/contrib/hooks/gcp_pubsub_hook.html +++ b/_modules/airflow/contrib/hooks/gcp_pubsub_hook.html @@ -474,20 +474,13 @@ - <script type="text/javascript"> - var DOCUMENTATION_OPTIONS = { - URL_ROOT:'../../../../', - VERSION:'', - LANGUAGE:'None', - 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" 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> +
