http://git-wip-us.apache.org/repos/asf/incubator-airflow-site/blob/28a3eb60/_modules/ftp_hook.html ---------------------------------------------------------------------- diff --git a/_modules/ftp_hook.html b/_modules/ftp_hook.html index 894f72f..b8225ed 100644 --- a/_modules/ftp_hook.html +++ b/_modules/ftp_hook.html @@ -13,6 +13,8 @@ + + @@ -80,7 +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> @@ -179,11 +184,12 @@ <span class="kn">import</span> <span class="nn">datetime</span> <span class="kn">import</span> <span class="nn">ftplib</span> -<span class="kn">import</span> <span class="nn">logging</span> <span class="kn">import</span> <span class="nn">os.path</span> <span class="kn">from</span> <span class="nn">airflow.hooks.base_hook</span> <span class="k">import</span> <span class="n">BaseHook</span> <span class="kn">from</span> <span class="nn">past.builtins</span> <span class="k">import</span> <span class="n">basestring</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">mlsd</span><span class="p">(</span><span class="n">conn</span><span class="p">,</span> <span class="n">path</span><span class="o">=</span><span class="s2">""</span><span class="p">,</span> <span class="n">facts</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> <span class="sd">"""</span> @@ -218,7 +224,7 @@ <span class="k">yield</span> <span class="p">(</span><span class="n">name</span><span class="p">,</span> <span class="n">entry</span><span class="p">)</span> -<div class="viewcode-block" id="FTPHook"><a class="viewcode-back" href="../code.html#airflow.contrib.hooks.FTPHook">[docs]</a><span class="k">class</span> <span class="nc">FTPHook</span><span class="p">(</span><span class="n">BaseHook</span><span class="p">):</span> +<div class="viewcode-block" id="FTPHook"><a class="viewcode-back" href="../code.html#airflow.contrib.hooks.FTPHook">[docs]</a><span class="k">class</span> <span class="nc">FTPHook</span><span class="p">(</span><span class="n">BaseHook</span><span class="p">,</span> <span class="n">LoggingMixin</span><span class="p">):</span> <span class="sd">"""</span> <span class="sd"> Interact with FTP.</span> @@ -330,10 +336,9 @@ <span class="n">remote_path</span><span class="p">,</span> <span class="n">remote_file_name</span> <span class="o">=</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="n">remote_full_path</span><span class="p">)</span> <span class="n">conn</span><span class="o">.</span><span class="n">cwd</span><span class="p">(</span><span class="n">remote_path</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="s1">'Retrieving file from FTP: </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">remote_full_path</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">'Retrieving file from FTP: </span><span class="si">%s</span><span class="s1">'</span><span class="p">,</span> <span class="n">remote_full_path</span><span class="p">)</span> <span class="n">conn</span><span class="o">.</span><span class="n">retrbinary</span><span class="p">(</span><span class="s1">'RETR </span><span class="si">%s</span><span class="s1">'</span> <span class="o">%</span> <span class="n">remote_file_name</span><span class="p">,</span> <span class="n">output_handle</span><span class="o">.</span><span class="n">write</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="s1">'Finished retrieving file from FTP: </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">remote_full_path</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">'Finished retrieving file from FTP: </span><span class="si">%s</span><span class="s1">'</span><span class="p">,</span> <span class="n">remote_full_path</span><span class="p">)</span> <span class="k">if</span> <span class="n">is_path</span><span class="p">:</span> <span class="n">output_handle</span><span class="o">.</span><span class="n">close</span><span class="p">()</span></div> @@ -390,7 +395,12 @@ <span class="k">def</span> <span class="nf">get_mod_time</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">path</span><span class="p">):</span> <span class="n">conn</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">ftp_mdtm</span> <span class="o">=</span> <span class="n">conn</span><span class="o">.</span><span class="n">sendcmd</span><span class="p">(</span><span class="s1">'MDTM '</span> <span class="o">+</span> <span class="n">path</span><span class="p">)</span> - <span class="k">return</span> <span class="n">datetime</span><span class="o">.</span><span class="n">datetime</span><span class="o">.</span><span class="n">strptime</span><span class="p">(</span><span class="n">ftp_mdtm</span><span class="p">[</span><span class="mi">4</span><span class="p">:],</span> <span class="s1">'%Y%m</span><span class="si">%d</span><span class="s1">%H%M%S'</span><span class="p">)</span></div> + <span class="n">time_val</span> <span class="o">=</span> <span class="n">ftp_mdtm</span><span class="p">[</span><span class="mi">4</span><span class="p">:]</span> + <span class="c1"># time_val optionally has microseconds</span> + <span class="k">try</span><span class="p">:</span> + <span class="k">return</span> <span class="n">datetime</span><span class="o">.</span><span class="n">datetime</span><span class="o">.</span><span class="n">strptime</span><span class="p">(</span><span class="n">time_val</span><span class="p">,</span> <span class="s2">"%Y%m</span><span class="si">%d</span><span class="s2">%H%M%S.</span><span class="si">%f</span><span class="s2">"</span><span class="p">)</span> + <span class="k">except</span> <span class="ne">ValueError</span><span class="p">:</span> + <span class="k">return</span> <span class="n">datetime</span><span class="o">.</span><span class="n">datetime</span><span class="o">.</span><span class="n">strptime</span><span class="p">(</span><span class="n">time_val</span><span class="p">,</span> <span class="s1">'%Y%m</span><span class="si">%d</span><span class="s1">%H%M%S'</span><span class="p">)</span></div> <span class="k">class</span> <span class="nc">FTPSHook</span><span class="p">(</span><span class="n">FTPHook</span><span class="p">):</span> @@ -401,9 +411,14 @@ <span class="sd"> """</span> <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">conn</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> <span class="n">params</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_connection</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">ftp_conn_id</span><span class="p">)</span> + + <span class="k">if</span> <span class="n">params</span><span class="o">.</span><span class="n">port</span><span class="p">:</span> + <span class="n">ftplib</span><span class="o">.</span><span class="n">FTP_TLS</span><span class="o">.</span><span class="n">port</span><span class="o">=</span><span class="n">params</span><span class="o">.</span><span class="n">port</span> + <span class="bp">self</span><span class="o">.</span><span class="n">conn</span> <span class="o">=</span> <span class="n">ftplib</span><span class="o">.</span><span class="n">FTP_TLS</span><span class="p">(</span> <span class="n">params</span><span class="o">.</span><span class="n">host</span><span class="p">,</span> <span class="n">params</span><span class="o">.</span><span class="n">login</span><span class="p">,</span> <span class="n">params</span><span class="o">.</span><span class="n">password</span> <span class="p">)</span> + <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">conn</span> </pre></div>
http://git-wip-us.apache.org/repos/asf/incubator-airflow-site/blob/28a3eb60/_modules/gcs_hook.html ---------------------------------------------------------------------- diff --git a/_modules/gcs_hook.html b/_modules/gcs_hook.html index c118b86..46ee89d 100644 --- a/_modules/gcs_hook.html +++ b/_modules/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>gcs_hook</li> + + <li>gcs_hook</li> + + <li class="wy-breadcrumbs-aside"> - + </li> + </ul> + + <hr/> </div> <div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article"> @@ -151,14 +181,11 @@ <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.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> @@ -169,8 +196,9 @@ <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> <div class="viewcode-block" id="GoogleCloudStorageHook.get_conn"><a class="viewcode-back" href="../code.html#airflow.contrib.hooks.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> @@ -179,7 +207,54 @@ <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></div> -<div class="viewcode-block" id="GoogleCloudStorageHook.download"><a class="viewcode-back" href="../code.html#airflow.contrib.hooks.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="bp">False</span><span class="p">):</span> + + <span class="c1"># pylint:disable=redefined-builtin</span> +<div class="viewcode-block" id="GoogleCloudStorageHook.copy"><a class="viewcode-back" href="../code.html#airflow.contrib.hooks.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="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="../code.html#airflow.contrib.hooks.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> @@ -198,11 +273,13 @@ <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></div> + <span class="c1"># pylint:disable=redefined-builtin</span> <div class="viewcode-block" id="GoogleCloudStorageHook.upload"><a class="viewcode-back" href="../code.html#airflow.contrib.hooks.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> @@ -221,10 +298,146 @@ <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">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></div> + <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="../code.html#airflow.contrib.hooks.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="../code.html#airflow.contrib.hooks.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="../code.html#airflow.contrib.hooks.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="../code.html#airflow.contrib.hooks.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> http://git-wip-us.apache.org/repos/asf/incubator-airflow-site/blob/28a3eb60/_modules/generic_transfer.html ---------------------------------------------------------------------- diff --git a/_modules/generic_transfer.html b/_modules/generic_transfer.html index 71c5825..77f3de1 100644 --- a/_modules/generic_transfer.html +++ b/_modules/generic_transfer.html @@ -13,6 +13,8 @@ + + @@ -80,7 +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> @@ -175,9 +180,6 @@ <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">logging</span> - <span class="kn">from</span> <span class="nn">airflow.models</span> <span class="k">import</span> <span class="n">BaseOperator</span> <span class="kn">from</span> <span class="nn">airflow.utils.decorators</span> <span class="k">import</span> <span class="n">apply_defaults</span> <span class="kn">from</span> <span class="nn">airflow.hooks.base_hook</span> <span class="k">import</span> <span class="n">BaseHook</span> @@ -190,7 +192,7 @@ <span class="sd"> needs to expose a `get_records` method, and the destination a</span> <span class="sd"> `insert_rows` method.</span> -<span class="sd"> This is mean to be used on small-ish datasets that fit in memory.</span> +<span class="sd"> This is meant to be used on small-ish datasets that fit in memory.</span> <span class="sd"> :param sql: SQL query to execute against the source database</span> <span class="sd"> :type sql: str</span> @@ -218,7 +220,7 @@ <span class="n">destination_conn_id</span><span class="p">,</span> <span class="n">preoperator</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> - <span class="nb">super</span><span class="p">(</span><span class="n">GenericTransfer</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="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> + <span class="nb">super</span><span class="p">(</span><span class="n">GenericTransfer</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="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> <span class="bp">self</span><span class="o">.</span><span class="n">sql</span> <span class="o">=</span> <span class="n">sql</span> <span class="bp">self</span><span class="o">.</span><span class="n">destination_table</span> <span class="o">=</span> <span class="n">destination_table</span> <span class="bp">self</span><span class="o">.</span><span class="n">source_conn_id</span> <span class="o">=</span> <span class="n">source_conn_id</span> @@ -228,17 +230,17 @@ <span class="k">def</span> <span class="nf">execute</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">context</span><span class="p">):</span> <span class="n">source_hook</span> <span class="o">=</span> <span class="n">BaseHook</span><span class="o">.</span><span class="n">get_hook</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">source_conn_id</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="s2">"Extracting data from </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">source_conn_id</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="s2">"Executing: </span><span class="se">\n</span><span class="s2">"</span> <span class="o">+</span> <span class="bp">self</span><span class="o">.</span><span class="n">sql</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">"Extracting data from </span><span class="si">%s</span><span class="s2">"</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">source_conn_id</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">"Executing: </span><span class="se">\n</span><span class="s2"> </span><span class="si">%s</span><span class="s2">"</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">sql</span><span class="p">)</span> <span class="n">results</span> <span class="o">=</span> <span class="n">source_hook</span><span class="o">.</span><span class="n">get_records</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">sql</span><span class="p">)</span> <span class="n">destination_hook</span> <span class="o">=</span> <span class="n">BaseHook</span><span class="o">.</span><span class="n">get_hook</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">destination_conn_id</span><span class="p">)</span> <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">preoperator</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="s2">"Running preoperator"</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="bp">self</span><span class="o">.</span><span class="n">preoperator</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">"Running preoperator"</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="bp">self</span><span class="o">.</span><span class="n">preoperator</span><span class="p">)</span> <span class="n">destination_hook</span><span class="o">.</span><span class="n">run</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">preoperator</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="s2">"Inserting rows into </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">destination_conn_id</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">"Inserting rows into </span><span class="si">%s</span><span class="s2">"</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">destination_conn_id</span><span class="p">)</span> <span class="n">destination_hook</span><span class="o">.</span><span class="n">insert_rows</span><span class="p">(</span><span class="n">table</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">destination_table</span><span class="p">,</span> <span class="n">rows</span><span class="o">=</span><span class="n">results</span><span class="p">)</span></div> </pre></div>
