You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@airflow.apache.org by cr...@apache.org on 2018/01/03 17:48:15 UTC
[15/35] incubator-airflow-site git commit: 1.9.0
http://git-wip-us.apache.org/repos/asf/incubator-airflow-site/blob/28a3eb60/_modules/hive_hooks.html
----------------------------------------------------------------------
diff --git a/_modules/hive_hooks.html b/_modules/hive_hooks.html
index 926b54c..5063de3 100644
--- a/_modules/hive_hooks.html
+++ b/_modules/hive_hooks.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>hive_hooks</li>
+
+ <li>hive_hooks</li>
+
+
<li class="wy-breadcrumbs-aside">
-
+
</li>
+
</ul>
+
+
<hr/>
</div>
<div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
@@ -152,32 +182,29 @@
<span class="c1"># limitations under the License.</span>
<span class="c1">#</span>
-<span class="kn">from</span> <span class="nn">__future__</span> <span class="kn">import</span> <span class="n">print_function</span>
-<span class="kn">from</span> <span class="nn">builtins</span> <span class="kn">import</span> <span class="nb">zip</span>
-<span class="kn">from</span> <span class="nn">past.builtins</span> <span class="kn">import</span> <span class="nb">basestring</span>
+<span class="kn">from</span> <span class="nn">__future__</span> <span class="k">import</span> <span class="n">print_function</span>
+<span class="kn">from</span> <span class="nn">six.moves</span> <span class="k">import</span> <span class="nb">zip</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">import</span> <span class="nn">collections</span>
-<span class="kn">import</span> <span class="nn">unicodecsv</span> <span class="kn">as</span> <span class="nn">csv</span>
+<span class="kn">import</span> <span class="nn">unicodecsv</span> <span class="k">as</span> <span class="nn">csv</span>
<span class="kn">import</span> <span class="nn">itertools</span>
-<span class="kn">import</span> <span class="nn">logging</span>
<span class="kn">import</span> <span class="nn">re</span>
<span class="kn">import</span> <span class="nn">subprocess</span>
<span class="kn">import</span> <span class="nn">time</span>
-<span class="kn">from</span> <span class="nn">tempfile</span> <span class="kn">import</span> <span class="n">NamedTemporaryFile</span>
+<span class="kn">from</span> <span class="nn">tempfile</span> <span class="k">import</span> <span class="n">NamedTemporaryFile</span>
<span class="kn">import</span> <span class="nn">hive_metastore</span>
-<span class="kn">from</span> <span class="nn">airflow.exceptions</span> <span class="kn">import</span> <span class="n">AirflowException</span>
-<span class="kn">from</span> <span class="nn">airflow.hooks.base_hook</span> <span class="kn">import</span> <span class="n">BaseHook</span>
-<span class="kn">from</span> <span class="nn">airflow.utils.helpers</span> <span class="kn">import</span> <span class="n">as_flattened_list</span>
-<span class="kn">from</span> <span class="nn">airflow.utils.file</span> <span class="kn">import</span> <span class="n">TemporaryDirectory</span>
-<span class="kn">from</span> <span class="nn">airflow</span> <span class="kn">import</span> <span class="n">configuration</span>
-<span class="kn">import</span> <span class="nn">airflow.security.utils</span> <span class="kn">as</span> <span class="nn">utils</span>
+<span class="kn">from</span> <span class="nn">airflow.exceptions</span> <span class="k">import</span> <span class="n">AirflowException</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">airflow.utils.helpers</span> <span class="k">import</span> <span class="n">as_flattened_list</span>
+<span class="kn">from</span> <span class="nn">airflow.utils.file</span> <span class="k">import</span> <span class="n">TemporaryDirectory</span>
+<span class="kn">from</span> <span class="nn">airflow</span> <span class="k">import</span> <span class="n">configuration</span>
+<span class="kn">import</span> <span class="nn">airflow.security.utils</span> <span class="k">as</span> <span class="nn">utils</span>
<span class="n">HIVE_QUEUE_PRIORITIES</span> <span class="o">=</span> <span class="p">[</span><span class="s1">'VERY_HIGH'</span><span class="p">,</span> <span class="s1">'HIGH'</span><span class="p">,</span> <span class="s1">'NORMAL'</span><span class="p">,</span> <span class="s1">'LOW'</span><span class="p">,</span> <span class="s1">'VERY_LOW'</span><span class="p">]</span>
<div class="viewcode-block" id="HiveCliHook"><a class="viewcode-back" href="../code.html#airflow.hooks.HiveCliHook">[docs]</a><span class="k">class</span> <span class="nc">HiveCliHook</span><span class="p">(</span><span class="n">BaseHook</span><span class="p">):</span>
-
<span class="sd">"""Simple wrapper around the hive CLI.</span>
<span class="sd"> It also supports the ``beeline``</span>
@@ -206,13 +233,13 @@
<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">hive_cli_conn_id</span><span class="o">=</span><span class="s2">"hive_cli_default"</span><span class="p">,</span>
- <span class="n">run_as</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span>
- <span class="n">mapred_queue</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span>
- <span class="n">mapred_queue_priority</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span>
- <span class="n">mapred_job_name</span><span class="o">=</span><span class="bp">None</span><span class="p">):</span>
+ <span class="n">run_as</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
+ <span class="n">mapred_queue</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
+ <span class="n">mapred_queue_priority</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
+ <span class="n">mapred_job_name</span><span class="o">=</span><span class="kc">None</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_connection</span><span class="p">(</span><span class="n">hive_cli_conn_id</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">hive_cli_params</span> <span class="o">=</span> <span class="n">conn</span><span class="o">.</span><span class="n">extra_dejson</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'hive_cli_params'</span><span class="p">,</span> <span class="s1">''</span><span class="p">)</span>
- <span class="bp">self</span><span class="o">.</span><span class="n">use_beeline</span> <span class="o">=</span> <span class="n">conn</span><span class="o">.</span><span class="n">extra_dejson</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'use_beeline'</span><span class="p">,</span> <span class="bp">False</span><span class="p">)</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">use_beeline</span> <span class="o">=</span> <span class="n">conn</span><span class="o">.</span><span class="n">extra_dejson</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'use_beeline'</span><span class="p">,</span> <span class="kc">False</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">auth</span> <span class="o">=</span> <span class="n">conn</span><span class="o">.</span><span class="n">extra_dejson</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'auth'</span><span class="p">,</span> <span class="s1">'noSasl'</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">conn</span>
<span class="bp">self</span><span class="o">.</span><span class="n">run_as</span> <span class="o">=</span> <span class="n">run_as</span>
@@ -222,7 +249,7 @@
<span class="k">if</span> <span class="n">mapred_queue_priority</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">HIVE_QUEUE_PRIORITIES</span><span class="p">:</span>
<span class="k">raise</span> <span class="n">AirflowException</span><span class="p">(</span>
<span class="s2">"Invalid Mapred Queue Priority. Valid values are: "</span>
- <span class="s2">"{}"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="s1">', '</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">HIVE_QUEUE_PRIORITIES</span><span class="p">)))</span>
+ <span class="s2">"</span><span class="si">{}</span><span class="s2">"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="s1">', '</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">HIVE_QUEUE_PRIORITIES</span><span class="p">)))</span>
<span class="bp">self</span><span class="o">.</span><span class="n">mapred_queue</span> <span class="o">=</span> <span class="n">mapred_queue</span>
<span class="bp">self</span><span class="o">.</span><span class="n">mapred_queue_priority</span> <span class="o">=</span> <span class="n">mapred_queue_priority</span>
@@ -238,7 +265,7 @@
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">use_beeline</span><span class="p">:</span>
<span class="n">hive_bin</span> <span class="o">=</span> <span class="s1">'beeline'</span>
- <span class="n">jdbc_url</span> <span class="o">=</span> <span class="s2">"jdbc:hive2://{conn.host}:{conn.port}/{conn.schema}"</span>
+ <span class="n">jdbc_url</span> <span class="o">=</span> <span class="s2">"jdbc:hive2://</span><span class="si">{conn.host}</span><span class="s2">:</span><span class="si">{conn.port}</span><span class="s2">/</span><span class="si">{conn.schema}</span><span class="s2">"</span>
<span class="k">if</span> <span class="n">configuration</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'core'</span><span class="p">,</span> <span class="s1">'security'</span><span class="p">)</span> <span class="o">==</span> <span class="s1">'kerberos'</span><span class="p">:</span>
<span class="n">template</span> <span class="o">=</span> <span class="n">conn</span><span class="o">.</span><span class="n">extra_dejson</span><span class="o">.</span><span class="n">get</span><span class="p">(</span>
<span class="s1">'principal'</span><span class="p">,</span> <span class="s2">"hive/_HOST@EXAMPLE.COM"</span><span class="p">)</span>
@@ -248,11 +275,11 @@
<span class="n">proxy_user</span> <span class="o">=</span> <span class="s2">""</span> <span class="c1"># noqa</span>
<span class="k">if</span> <span class="n">conn</span><span class="o">.</span><span class="n">extra_dejson</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'proxy_user'</span><span class="p">)</span> <span class="o">==</span> <span class="s2">"login"</span> <span class="ow">and</span> <span class="n">conn</span><span class="o">.</span><span class="n">login</span><span class="p">:</span>
- <span class="n">proxy_user</span> <span class="o">=</span> <span class="s2">"hive.server2.proxy.user={0}"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">conn</span><span class="o">.</span><span class="n">login</span><span class="p">)</span>
+ <span class="n">proxy_user</span> <span class="o">=</span> <span class="s2">"hive.server2.proxy.user=</span><span class="si">{0}</span><span class="s2">"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">conn</span><span class="o">.</span><span class="n">login</span><span class="p">)</span>
<span class="k">elif</span> <span class="n">conn</span><span class="o">.</span><span class="n">extra_dejson</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'proxy_user'</span><span class="p">)</span> <span class="o">==</span> <span class="s2">"owner"</span> <span class="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">run_as</span><span class="p">:</span>
- <span class="n">proxy_user</span> <span class="o">=</span> <span class="s2">"hive.server2.proxy.user={0}"</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">run_as</span><span class="p">)</span>
+ <span class="n">proxy_user</span> <span class="o">=</span> <span class="s2">"hive.server2.proxy.user=</span><span class="si">{0}</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">run_as</span><span class="p">)</span>
- <span class="n">jdbc_url</span> <span class="o">+=</span> <span class="s2">";principal={template};{proxy_user}"</span>
+ <span class="n">jdbc_url</span> <span class="o">+=</span> <span class="s2">";principal=</span><span class="si">{template}</span><span class="s2">;</span><span class="si">{proxy_user}</span><span class="s2">"</span>
<span class="k">elif</span> <span class="bp">self</span><span class="o">.</span><span class="n">auth</span><span class="p">:</span>
<span class="n">jdbc_url</span> <span class="o">+=</span> <span class="s2">";auth="</span> <span class="o">+</span> <span class="bp">self</span><span class="o">.</span><span class="n">auth</span>
@@ -286,13 +313,11 @@
<span class="k">if</span> <span class="ow">not</span> <span class="n">d</span><span class="p">:</span>
<span class="k">return</span> <span class="p">[]</span>
<span class="k">return</span> <span class="n">as_flattened_list</span><span class="p">(</span>
- <span class="n">itertools</span><span class="o">.</span><span class="n">izip</span><span class="p">(</span>
- <span class="p">[</span><span class="s2">"-hiveconf"</span><span class="p">]</span> <span class="o">*</span> <span class="nb">len</span><span class="p">(</span><span class="n">d</span><span class="p">),</span>
- <span class="p">[</span><span class="s2">"{}={}"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">k</span><span class="p">,</span> <span class="n">v</span><span class="p">)</span> <span class="k">for</span> <span class="n">k</span><span class="p">,</span> <span class="n">v</span> <span class="ow">in</span> <span class="n">d</span><span class="o">.</span><span class="n">items</span><span class="p">()]</span>
- <span class="p">)</span>
- <span class="p">)</span>
+ <span class="nb">zip</span><span class="p">([</span><span class="s2">"-hiveconf"</span><span class="p">]</span> <span class="o">*</span> <span class="nb">len</span><span class="p">(</span><span class="n">d</span><span class="p">),</span>
+ <span class="p">[</span><span class="s2">"</span><span class="si">{}</span><span class="s2">=</span><span class="si">{}</span><span class="s2">"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">k</span><span class="p">,</span> <span class="n">v</span><span class="p">)</span> <span class="k">for</span> <span class="n">k</span><span class="p">,</span> <span class="n">v</span> <span class="ow">in</span> <span class="n">d</span><span class="o">.</span><span class="n">items</span><span class="p">()])</span>
+ <span class="p">)</span>
-<div class="viewcode-block" id="HiveCliHook.run_cli"><a class="viewcode-back" href="../code.html#airflow.hooks.HiveCliHook.run_cli">[docs]</a> <span class="k">def</span> <span class="nf">run_cli</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">hql</span><span class="p">,</span> <span class="n">schema</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span> <span class="n">verbose</span><span class="o">=</span><span class="bp">True</span><span class="p">,</span> <span class="n">hive_conf</span><span class="o">=</span><span class="bp">None</span><span class="p">):</span>
+<div class="viewcode-block" id="HiveCliHook.run_cli"><a class="viewcode-back" href="../code.html#airflow.hooks.HiveCliHook.run_cli">[docs]</a> <span class="k">def</span> <span class="nf">run_cli</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">hql</span><span class="p">,</span> <span class="n">schema</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">verbose</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">hive_conf</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Run an hql statement using the hive cli. If hive_conf is specified</span>
<span class="sd"> it should be a dict and the entries will be set as key/value pairs</span>
@@ -313,7 +338,7 @@
<span class="n">conn</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">conn</span>
<span class="n">schema</span> <span class="o">=</span> <span class="n">schema</span> <span class="ow">or</span> <span class="n">conn</span><span class="o">.</span><span class="n">schema</span>
<span class="k">if</span> <span class="n">schema</span><span class="p">:</span>
- <span class="n">hql</span> <span class="o">=</span> <span class="s2">"USE {schema};</span><span class="se">\n</span><span class="s2">{hql}"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="o">**</span><span class="nb">locals</span><span class="p">())</span>
+ <span class="n">hql</span> <span class="o">=</span> <span class="s2">"USE </span><span class="si">{schema}</span><span class="s2">;</span><span class="se">\n</span><span class="si">{hql}</span><span class="s2">"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="o">**</span><span class="nb">locals</span><span class="p">())</span>
<span class="k">with</span> <span class="n">TemporaryDirectory</span><span class="p">(</span><span class="n">prefix</span><span class="o">=</span><span class="s1">'airflow_hiveop_'</span><span class="p">)</span> <span class="k">as</span> <span class="n">tmp_dir</span><span class="p">:</span>
<span class="k">with</span> <span class="n">NamedTemporaryFile</span><span class="p">(</span><span class="nb">dir</span><span class="o">=</span><span class="n">tmp_dir</span><span class="p">)</span> <span class="k">as</span> <span class="n">f</span><span class="p">:</span>
@@ -324,26 +349,26 @@
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">mapred_queue</span><span class="p">:</span>
<span class="n">hive_conf_params</span><span class="o">.</span><span class="n">extend</span><span class="p">(</span>
<span class="p">[</span><span class="s1">'-hiveconf'</span><span class="p">,</span>
- <span class="s1">'mapreduce.job.queuename={}'</span>
+ <span class="s1">'mapreduce.job.queuename=</span><span class="si">{}</span><span class="s1">'</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">mapred_queue</span><span class="p">)])</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">mapred_queue_priority</span><span class="p">:</span>
<span class="n">hive_conf_params</span><span class="o">.</span><span class="n">extend</span><span class="p">(</span>
<span class="p">[</span><span class="s1">'-hiveconf'</span><span class="p">,</span>
- <span class="s1">'mapreduce.job.priority={}'</span>
+ <span class="s1">'mapreduce.job.priority=</span><span class="si">{}</span><span class="s1">'</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">mapred_queue_priority</span><span class="p">)])</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">mapred_job_name</span><span class="p">:</span>
<span class="n">hive_conf_params</span><span class="o">.</span><span class="n">extend</span><span class="p">(</span>
<span class="p">[</span><span class="s1">'-hiveconf'</span><span class="p">,</span>
- <span class="s1">'mapred.job.name={}'</span>
+ <span class="s1">'mapred.job.name=</span><span class="si">{}</span><span class="s1">'</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">mapred_job_name</span><span class="p">)])</span>
<span class="n">hive_cmd</span><span class="o">.</span><span class="n">extend</span><span class="p">(</span><span class="n">hive_conf_params</span><span class="p">)</span>
<span class="n">hive_cmd</span><span class="o">.</span><span class="n">extend</span><span class="p">([</span><span class="s1">'-f'</span><span class="p">,</span> <span class="n">f</span><span class="o">.</span><span class="n">name</span><span class="p">])</span>
<span class="k">if</span> <span class="n">verbose</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">" "</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">hive_cmd</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">" "</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">hive_cmd</span><span class="p">))</span>
<span class="n">sp</span> <span class="o">=</span> <span class="n">subprocess</span><span class="o">.</span><span class="n">Popen</span><span class="p">(</span>
<span class="n">hive_cmd</span><span class="p">,</span>
<span class="n">stdout</span><span class="o">=</span><span class="n">subprocess</span><span class="o">.</span><span class="n">PIPE</span><span class="p">,</span>
@@ -351,13 +376,13 @@
<span class="n">cwd</span><span class="o">=</span><span class="n">tmp_dir</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">sp</span> <span class="o">=</span> <span class="n">sp</span>
<span class="n">stdout</span> <span class="o">=</span> <span class="s1">''</span>
- <span class="k">while</span> <span class="bp">True</span><span class="p">:</span>
+ <span class="k">while</span> <span class="kc">True</span><span class="p">:</span>
<span class="n">line</span> <span class="o">=</span> <span class="n">sp</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="k">if</span> <span class="ow">not</span> <span class="n">line</span><span class="p">:</span>
<span class="k">break</span>
<span class="n">stdout</span> <span class="o">+=</span> <span class="n">line</span><span class="o">.</span><span class="n">decode</span><span class="p">(</span><span class="s1">'UTF-8'</span><span class="p">)</span>
<span class="k">if</span> <span class="n">verbose</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="n">line</span><span class="o">.</span><span class="n">decode</span><span class="p">(</span><span class="s1">'UTF-8'</span><span class="p">)</span><span class="o">.</span><span class="n">strip</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="o">.</span><span class="n">decode</span><span class="p">(</span><span class="s1">'UTF-8'</span><span class="p">)</span><span class="o">.</span><span class="n">strip</span><span class="p">())</span>
<span class="n">sp</span><span class="o">.</span><span class="n">wait</span><span class="p">()</span>
<span class="k">if</span> <span class="n">sp</span><span class="o">.</span><span class="n">returncode</span><span class="p">:</span>
@@ -388,36 +413,102 @@
<span class="k">for</span> <span class="n">query</span> <span class="ow">in</span> <span class="n">query_set</span><span class="p">:</span>
<span class="n">query_preview</span> <span class="o">=</span> <span class="s1">' '</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">query</span><span class="o">.</span><span class="n">split</span><span class="p">())[:</span><span class="mi">50</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">"Testing HQL [{0} (...)]"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">query_preview</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">"Testing HQL [</span><span class="si">%s</span><span class="s2"> (...)]"</span><span class="p">,</span> <span class="n">query_preview</span><span class="p">)</span>
<span class="k">if</span> <span class="n">query_set</span> <span class="o">==</span> <span class="n">insert</span><span class="p">:</span>
<span class="n">query</span> <span class="o">=</span> <span class="n">other</span> <span class="o">+</span> <span class="s1">'; explain '</span> <span class="o">+</span> <span class="n">query</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">query</span> <span class="o">=</span> <span class="s1">'explain '</span> <span class="o">+</span> <span class="n">query</span>
<span class="k">try</span><span class="p">:</span>
- <span class="bp">self</span><span class="o">.</span><span class="n">run_cli</span><span class="p">(</span><span class="n">query</span><span class="p">,</span> <span class="n">verbose</span><span class="o">=</span><span class="bp">False</span><span class="p">)</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">run_cli</span><span class="p">(</span><span class="n">query</span><span class="p">,</span> <span class="n">verbose</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span>
<span class="k">except</span> <span class="n">AirflowException</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span>
<span class="n">message</span> <span class="o">=</span> <span class="n">e</span><span class="o">.</span><span class="n">args</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s1">'</span><span class="se">\n</span><span class="s1">'</span><span class="p">)[</span><span class="o">-</span><span class="mi">2</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="n">message</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">message</span><span class="p">)</span>
<span class="n">error_loc</span> <span class="o">=</span> <span class="n">re</span><span class="o">.</span><span class="n">search</span><span class="p">(</span><span class="s1">'(\d+):(\d+)'</span><span class="p">,</span> <span class="n">message</span><span class="p">)</span>
<span class="k">if</span> <span class="n">error_loc</span> <span class="ow">and</span> <span class="n">error_loc</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">isdigit</span><span class="p">():</span>
<span class="n">l</span> <span class="o">=</span> <span class="nb">int</span><span class="p">(</span><span class="n">error_loc</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="n">begin</span> <span class="o">=</span> <span class="nb">max</span><span class="p">(</span><span class="n">l</span><span class="o">-</span><span class="mi">2</span><span class="p">,</span> <span class="mi">0</span><span class="p">)</span>
<span class="n">end</span> <span class="o">=</span> <span class="nb">min</span><span class="p">(</span><span class="n">l</span><span class="o">+</span><span class="mi">3</span><span class="p">,</span> <span class="nb">len</span><span class="p">(</span><span class="n">query</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s1">'</span><span class="se">\n</span><span class="s1">'</span><span class="p">)))</span>
<span class="n">context</span> <span class="o">=</span> <span class="s1">'</span><span class="se">\n</span><span class="s1">'</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">query</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s1">'</span><span class="se">\n</span><span class="s1">'</span><span class="p">)[</span><span class="n">begin</span><span class="p">:</span><span class="n">end</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">"Context :</span><span class="se">\n</span><span class="s2"> {0}"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">context</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">"Context :</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="n">context</span><span class="p">)</span>
<span class="k">else</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">"SUCCESS"</span><span class="p">)</span></div>
+ <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">"SUCCESS"</span><span class="p">)</span></div>
+
+<div class="viewcode-block" id="HiveCliHook.load_df"><a class="viewcode-back" href="../code.html#airflow.hooks.HiveCliHook.load_df">[docs]</a> <span class="k">def</span> <span class="nf">load_df</span><span class="p">(</span>
+ <span class="bp">self</span><span class="p">,</span>
+ <span class="n">df</span><span class="p">,</span>
+ <span class="n">table</span><span class="p">,</span>
+ <span class="n">create</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
+ <span class="n">recreate</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
+ <span class="n">field_dict</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
+ <span class="n">delimiter</span><span class="o">=</span><span class="s1">','</span><span class="p">,</span>
+ <span class="n">encoding</span><span class="o">=</span><span class="s1">'utf8'</span><span class="p">,</span>
+ <span class="n">pandas_kwargs</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
+ <span class="sd">"""</span>
+<span class="sd"> Loads a pandas DataFrame into hive.</span>
+
+<span class="sd"> Hive data types will be inferred if not passed but column names will</span>
+<span class="sd"> not be sanitized.</span>
+
+<span class="sd"> :param table: target Hive table, use dot notation to target a</span>
+<span class="sd"> specific database</span>
+<span class="sd"> :type table: str</span>
+<span class="sd"> :param create: whether to create the table if it doesn't exist</span>
+<span class="sd"> :type create: bool</span>
+<span class="sd"> :param recreate: whether to drop and recreate the table at every</span>
+<span class="sd"> execution</span>
+<span class="sd"> :type recreate: bool</span>
+<span class="sd"> :param field_dict: mapping from column name to hive data type</span>
+<span class="sd"> :type field_dict: dict</span>
+<span class="sd"> :param encoding: string encoding to use when writing DataFrame to file</span>
+<span class="sd"> :type encoding: str</span>
+<span class="sd"> :param pandas_kwargs: passed to DataFrame.to_csv</span>
+<span class="sd"> :type pandas_kwargs: dict</span>
+<span class="sd"> :param kwargs: passed to self.load_file</span>
+<span class="sd"> """</span>
+
+ <span class="k">def</span> <span class="nf">_infer_field_types_from_df</span><span class="p">(</span><span class="n">df</span><span class="p">):</span>
+ <span class="n">DTYPE_KIND_HIVE_TYPE</span> <span class="o">=</span> <span class="p">{</span>
+ <span class="s1">'b'</span><span class="p">:</span> <span class="s1">'BOOLEAN'</span><span class="p">,</span> <span class="c1"># boolean</span>
+ <span class="s1">'i'</span><span class="p">:</span> <span class="s1">'BIGINT'</span><span class="p">,</span> <span class="c1"># signed integer</span>
+ <span class="s1">'u'</span><span class="p">:</span> <span class="s1">'BIGINT'</span><span class="p">,</span> <span class="c1"># unsigned integer</span>
+ <span class="s1">'f'</span><span class="p">:</span> <span class="s1">'DOUBLE'</span><span class="p">,</span> <span class="c1"># floating-point</span>
+ <span class="s1">'c'</span><span class="p">:</span> <span class="s1">'STRING'</span><span class="p">,</span> <span class="c1"># complex floating-point</span>
+ <span class="s1">'O'</span><span class="p">:</span> <span class="s1">'STRING'</span><span class="p">,</span> <span class="c1"># object</span>
+ <span class="s1">'S'</span><span class="p">:</span> <span class="s1">'STRING'</span><span class="p">,</span> <span class="c1"># (byte-)string</span>
+ <span class="s1">'U'</span><span class="p">:</span> <span class="s1">'STRING'</span><span class="p">,</span> <span class="c1"># Unicode</span>
+ <span class="s1">'V'</span><span class="p">:</span> <span class="s1">'STRING'</span> <span class="c1"># void</span>
+ <span class="p">}</span>
+
+ <span class="k">return</span> <span class="nb">dict</span><span class="p">((</span><span class="n">col</span><span class="p">,</span> <span class="n">DTYPE_KIND_HIVE_TYPE</span><span class="p">[</span><span class="n">dtype</span><span class="o">.</span><span class="n">kind</span><span class="p">])</span> <span class="k">for</span> <span class="n">col</span><span class="p">,</span> <span class="n">dtype</span> <span class="ow">in</span> <span class="n">df</span><span class="o">.</span><span class="n">dtypes</span><span class="o">.</span><span class="n">iteritems</span><span class="p">())</span>
+
+ <span class="k">if</span> <span class="n">pandas_kwargs</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
+ <span class="n">pandas_kwargs</span> <span class="o">=</span> <span class="p">{}</span>
+
+ <span class="k">with</span> <span class="n">TemporaryDirectory</span><span class="p">(</span><span class="n">prefix</span><span class="o">=</span><span class="s1">'airflow_hiveop_'</span><span class="p">)</span> <span class="k">as</span> <span class="n">tmp_dir</span><span class="p">:</span>
+ <span class="k">with</span> <span class="n">NamedTemporaryFile</span><span class="p">(</span><span class="nb">dir</span><span class="o">=</span><span class="n">tmp_dir</span><span class="p">)</span> <span class="k">as</span> <span class="n">f</span><span class="p">:</span>
+
+ <span class="k">if</span> <span class="n">field_dict</span> <span class="ow">is</span> <span class="kc">None</span> <span class="ow">and</span> <span class="p">(</span><span class="n">create</span> <span class="ow">or</span> <span class="n">recreate</span><span class="p">):</span>
+ <span class="n">field_dict</span> <span class="o">=</span> <span class="n">_infer_field_types_from_df</span><span class="p">(</span><span class="n">df</span><span class="p">)</span>
+
+ <span class="n">df</span><span class="o">.</span><span class="n">to_csv</span><span class="p">(</span><span class="n">f</span><span class="p">,</span> <span class="n">sep</span><span class="o">=</span><span class="n">delimiter</span><span class="p">,</span> <span class="o">**</span><span class="n">pandas_kwargs</span><span class="p">)</span>
+
+ <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">load_file</span><span class="p">(</span><span class="n">filepath</span><span class="o">=</span><span class="n">f</span><span class="o">.</span><span class="n">name</span><span class="p">,</span>
+ <span class="n">table</span><span class="o">=</span><span class="n">table</span><span class="p">,</span>
+ <span class="n">delimiter</span><span class="o">=</span><span class="n">delimiter</span><span class="p">,</span>
+ <span class="n">field_dict</span><span class="o">=</span><span class="n">field_dict</span><span class="p">,</span>
+ <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span></div>
<div class="viewcode-block" id="HiveCliHook.load_file"><a class="viewcode-back" href="../code.html#airflow.hooks.HiveCliHook.load_file">[docs]</a> <span class="k">def</span> <span class="nf">load_file</span><span class="p">(</span>
<span class="bp">self</span><span class="p">,</span>
<span class="n">filepath</span><span class="p">,</span>
<span class="n">table</span><span class="p">,</span>
<span class="n">delimiter</span><span class="o">=</span><span class="s2">","</span><span class="p">,</span>
- <span class="n">field_dict</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span>
- <span class="n">create</span><span class="o">=</span><span class="bp">True</span><span class="p">,</span>
- <span class="n">overwrite</span><span class="o">=</span><span class="bp">True</span><span class="p">,</span>
- <span class="n">partition</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span>
- <span class="n">recreate</span><span class="o">=</span><span class="bp">False</span><span class="p">):</span>
+ <span class="n">field_dict</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
+ <span class="n">create</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
+ <span class="n">overwrite</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
+ <span class="n">partition</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
+ <span class="n">recreate</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
+ <span class="n">tblproperties</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Loads a local file into Hive</span>
@@ -428,53 +519,69 @@
<span class="sd"> stage the data into a temporary table before loading it into its</span>
<span class="sd"> final destination using a ``HiveOperator``.</span>
+<span class="sd"> :param filepath: local filepath of the file to load</span>
+<span class="sd"> :type filepath: str</span>
<span class="sd"> :param table: target Hive table, use dot notation to target a</span>
<span class="sd"> specific database</span>
<span class="sd"> :type table: str</span>
+<span class="sd"> :param delimiter: field delimiter in the file</span>
+<span class="sd"> :type delimiter: str</span>
+<span class="sd"> :param field_dict: A dictionary of the fields name in the file</span>
+<span class="sd"> as keys and their Hive types as values</span>
+<span class="sd"> :type field_dict: dict</span>
<span class="sd"> :param create: whether to create the table if it doesn't exist</span>
<span class="sd"> :type create: bool</span>
-<span class="sd"> :param recreate: whether to drop and recreate the table at every</span>
-<span class="sd"> execution</span>
-<span class="sd"> :type recreate: bool</span>
+<span class="sd"> :param overwrite: whether to overwrite the data in table or partition</span>
+<span class="sd"> :type overwrite: bool</span>
<span class="sd"> :param partition: target partition as a dict of partition columns</span>
<span class="sd"> and values</span>
<span class="sd"> :type partition: dict</span>
-<span class="sd"> :param delimiter: field delimiter in the file</span>
-<span class="sd"> :type delimiter: str</span>
+<span class="sd"> :param recreate: whether to drop and recreate the table at every</span>
+<span class="sd"> execution</span>
+<span class="sd"> :type recreate: bool</span>
+<span class="sd"> :param tblproperties: TBLPROPERTIES of the hive table being created</span>
+<span class="sd"> :type tblproperties: dict</span>
<span class="sd"> """</span>
<span class="n">hql</span> <span class="o">=</span> <span class="s1">''</span>
<span class="k">if</span> <span class="n">recreate</span><span class="p">:</span>
- <span class="n">hql</span> <span class="o">+=</span> <span class="s2">"DROP TABLE IF EXISTS {table};</span><span class="se">\n</span><span class="s2">"</span>
+ <span class="n">hql</span> <span class="o">+=</span> <span class="s2">"DROP TABLE IF EXISTS </span><span class="si">{table}</span><span class="s2">;</span><span class="se">\n</span><span class="s2">"</span>
<span class="k">if</span> <span class="n">create</span> <span class="ow">or</span> <span class="n">recreate</span><span class="p">:</span>
+ <span class="k">if</span> <span class="n">field_dict</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
+ <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">"Must provide a field dict when creating a table"</span><span class="p">)</span>
<span class="n">fields</span> <span class="o">=</span> <span class="s2">",</span><span class="se">\n</span><span class="s2"> "</span><span class="o">.</span><span class="n">join</span><span class="p">(</span>
<span class="p">[</span><span class="n">k</span> <span class="o">+</span> <span class="s1">' '</span> <span class="o">+</span> <span class="n">v</span> <span class="k">for</span> <span class="n">k</span><span class="p">,</span> <span class="n">v</span> <span class="ow">in</span> <span class="n">field_dict</span><span class="o">.</span><span class="n">items</span><span class="p">()])</span>
- <span class="n">hql</span> <span class="o">+=</span> <span class="s2">"CREATE TABLE IF NOT EXISTS {table} (</span><span class="se">\n</span><span class="s2">{fields})</span><span class="se">\n</span><span class="s2">"</span>
+ <span class="n">hql</span> <span class="o">+=</span> <span class="s2">"CREATE TABLE IF NOT EXISTS </span><span class="si">{table}</span><span class="s2"> (</span><span class="se">\n</span><span class="si">{fields}</span><span class="s2">)</span><span class="se">\n</span><span class="s2">"</span>
<span class="k">if</span> <span class="n">partition</span><span class="p">:</span>
<span class="n">pfields</span> <span class="o">=</span> <span class="s2">",</span><span class="se">\n</span><span class="s2"> "</span><span class="o">.</span><span class="n">join</span><span class="p">(</span>
<span class="p">[</span><span class="n">p</span> <span class="o">+</span> <span class="s2">" STRING"</span> <span class="k">for</span> <span class="n">p</span> <span class="ow">in</span> <span class="n">partition</span><span class="p">])</span>
- <span class="n">hql</span> <span class="o">+=</span> <span class="s2">"PARTITIONED BY ({pfields})</span><span class="se">\n</span><span class="s2">"</span>
+ <span class="n">hql</span> <span class="o">+=</span> <span class="s2">"PARTITIONED BY (</span><span class="si">{pfields}</span><span class="s2">)</span><span class="se">\n</span><span class="s2">"</span>
<span class="n">hql</span> <span class="o">+=</span> <span class="s2">"ROW FORMAT DELIMITED</span><span class="se">\n</span><span class="s2">"</span>
- <span class="n">hql</span> <span class="o">+=</span> <span class="s2">"FIELDS TERMINATED BY '{delimiter}'</span><span class="se">\n</span><span class="s2">"</span>
- <span class="n">hql</span> <span class="o">+=</span> <span class="s2">"STORED AS textfile;"</span>
+ <span class="n">hql</span> <span class="o">+=</span> <span class="s2">"FIELDS TERMINATED BY '</span><span class="si">{delimiter}</span><span class="s2">'</span><span class="se">\n</span><span class="s2">"</span>
+ <span class="n">hql</span> <span class="o">+=</span> <span class="s2">"STORED AS textfile</span><span class="se">\n</span><span class="s2">"</span>
+ <span class="k">if</span> <span class="n">tblproperties</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
+ <span class="n">tprops</span> <span class="o">=</span> <span class="s2">", "</span><span class="o">.</span><span class="n">join</span><span class="p">(</span>
+ <span class="p">[</span><span class="s2">"'</span><span class="si">{0}</span><span class="s2">'='</span><span class="si">{1}</span><span class="s2">'"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">k</span><span class="p">,</span> <span class="n">v</span><span class="p">)</span> <span class="k">for</span> <span class="n">k</span><span class="p">,</span> <span class="n">v</span> <span class="ow">in</span> <span class="n">tblproperties</span><span class="o">.</span><span class="n">items</span><span class="p">()])</span>
+ <span class="n">hql</span> <span class="o">+=</span> <span class="s2">"TBLPROPERTIES(</span><span class="si">{tprops}</span><span class="s2">)</span><span class="se">\n</span><span class="s2">"</span>
+ <span class="n">hql</span> <span class="o">+=</span> <span class="s2">";"</span>
<span class="n">hql</span> <span class="o">=</span> <span class="n">hql</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="o">**</span><span class="nb">locals</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="n">hql</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">hql</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">run_cli</span><span class="p">(</span><span class="n">hql</span><span class="p">)</span>
- <span class="n">hql</span> <span class="o">=</span> <span class="s2">"LOAD DATA LOCAL INPATH '{filepath}' "</span>
+ <span class="n">hql</span> <span class="o">=</span> <span class="s2">"LOAD DATA LOCAL INPATH '</span><span class="si">{filepath}</span><span class="s2">' "</span>
<span class="k">if</span> <span class="n">overwrite</span><span class="p">:</span>
<span class="n">hql</span> <span class="o">+=</span> <span class="s2">"OVERWRITE "</span>
- <span class="n">hql</span> <span class="o">+=</span> <span class="s2">"INTO TABLE {table} "</span>
+ <span class="n">hql</span> <span class="o">+=</span> <span class="s2">"INTO TABLE </span><span class="si">{table}</span><span class="s2"> "</span>
<span class="k">if</span> <span class="n">partition</span><span class="p">:</span>
<span class="n">pvals</span> <span class="o">=</span> <span class="s2">", "</span><span class="o">.</span><span class="n">join</span><span class="p">(</span>
- <span class="p">[</span><span class="s2">"{0}='{1}'"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">k</span><span class="p">,</span> <span class="n">v</span><span class="p">)</span> <span class="k">for</span> <span class="n">k</span><span class="p">,</span> <span class="n">v</span> <span class="ow">in</span> <span class="n">partition</span><span class="o">.</span><span class="n">items</span><span class="p">()])</span>
- <span class="n">hql</span> <span class="o">+=</span> <span class="s2">"PARTITION ({pvals});"</span>
+ <span class="p">[</span><span class="s2">"</span><span class="si">{0}</span><span class="s2">='</span><span class="si">{1}</span><span class="s2">'"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">k</span><span class="p">,</span> <span class="n">v</span><span class="p">)</span> <span class="k">for</span> <span class="n">k</span><span class="p">,</span> <span class="n">v</span> <span class="ow">in</span> <span class="n">partition</span><span class="o">.</span><span class="n">items</span><span class="p">()])</span>
+ <span class="n">hql</span> <span class="o">+=</span> <span class="s2">"PARTITION (</span><span class="si">{pvals}</span><span class="s2">);"</span>
<span class="n">hql</span> <span class="o">=</span> <span class="n">hql</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="o">**</span><span class="nb">locals</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="n">hql</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">hql</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">run_cli</span><span class="p">(</span><span class="n">hql</span><span class="p">)</span></div>
<span class="k">def</span> <span class="nf">kill</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="k">if</span> <span class="nb">hasattr</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="s1">'sp'</span><span class="p">):</span>
- <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">sp</span><span class="o">.</span><span class="n">poll</span><span class="p">()</span> <span class="ow">is</span> <span class="bp">None</span><span class="p">:</span>
- <span class="k">print</span><span class="p">(</span><span class="s2">"Killing the Hive job"</span><span class="p">)</span>
+ <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">sp</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="nb">print</span><span class="p">(</span><span class="s2">"Killing the Hive job"</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">sp</span><span class="o">.</span><span class="n">terminate</span><span class="p">()</span>
<span class="n">time</span><span class="o">.</span><span class="n">sleep</span><span class="p">(</span><span class="mi">60</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">sp</span><span class="o">.</span><span class="n">kill</span><span class="p">()</span></div>
@@ -491,21 +598,21 @@
<span class="k">def</span> <span class="nf">__getstate__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="c1"># This is for pickling to work despite the thirft hive client not</span>
<span class="c1"># being pickable</span>
- <span class="n">d</span> <span class="o">=</span> <span class="nb">dict</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">__dict__</span><span class="p">)</span>
+ <span class="n">d</span> <span class="o">=</span> <span class="nb">dict</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="vm">__dict__</span><span class="p">)</span>
<span class="k">del</span> <span class="n">d</span><span class="p">[</span><span class="s1">'metastore'</span><span class="p">]</span>
<span class="k">return</span> <span class="n">d</span>
<span class="k">def</span> <span class="nf">__setstate__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">d</span><span class="p">):</span>
- <span class="bp">self</span><span class="o">.</span><span class="n">__dict__</span><span class="o">.</span><span class="n">update</span><span class="p">(</span><span class="n">d</span><span class="p">)</span>
- <span class="bp">self</span><span class="o">.</span><span class="n">__dict__</span><span class="p">[</span><span class="s1">'metastore'</span><span class="p">]</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_metastore_client</span><span class="p">()</span>
+ <span class="bp">self</span><span class="o">.</span><span class="vm">__dict__</span><span class="o">.</span><span class="n">update</span><span class="p">(</span><span class="n">d</span><span class="p">)</span>
+ <span class="bp">self</span><span class="o">.</span><span class="vm">__dict__</span><span class="p">[</span><span class="s1">'metastore'</span><span class="p">]</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_metastore_client</span><span class="p">()</span>
<div class="viewcode-block" id="HiveMetastoreHook.get_metastore_client"><a class="viewcode-back" href="../code.html#airflow.hooks.HiveMetastoreHook.get_metastore_client">[docs]</a> <span class="k">def</span> <span class="nf">get_metastore_client</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Returns a Hive thrift client.</span>
<span class="sd"> """</span>
- <span class="kn">from</span> <span class="nn">thrift.transport</span> <span class="kn">import</span> <span class="n">TSocket</span><span class="p">,</span> <span class="n">TTransport</span>
- <span class="kn">from</span> <span class="nn">thrift.protocol</span> <span class="kn">import</span> <span class="n">TBinaryProtocol</span>
- <span class="kn">from</span> <span class="nn">hive_service</span> <span class="kn">import</span> <span class="n">ThriftHive</span>
+ <span class="kn">from</span> <span class="nn">thrift.transport</span> <span class="k">import</span> <span class="n">TSocket</span><span class="p">,</span> <span class="n">TTransport</span>
+ <span class="kn">from</span> <span class="nn">thrift.protocol</span> <span class="k">import</span> <span class="n">TBinaryProtocol</span>
+ <span class="kn">from</span> <span class="nn">hive_service</span> <span class="k">import</span> <span class="n">ThriftHive</span>
<span class="n">ms</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">metastore_conn</span>
<span class="n">auth_mechanism</span> <span class="o">=</span> <span class="n">ms</span><span class="o">.</span><span class="n">extra_dejson</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'authMechanism'</span><span class="p">,</span> <span class="s1">'NOSASL'</span><span class="p">)</span>
<span class="k">if</span> <span class="n">configuration</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'core'</span><span class="p">,</span> <span class="s1">'security'</span><span class="p">)</span> <span class="o">==</span> <span class="s1">'kerberos'</span><span class="p">:</span>
@@ -515,7 +622,7 @@
<span class="n">socket</span> <span class="o">=</span> <span class="n">TSocket</span><span class="o">.</span><span class="n">TSocket</span><span class="p">(</span><span class="n">ms</span><span class="o">.</span><span class="n">host</span><span class="p">,</span> <span class="n">ms</span><span class="o">.</span><span class="n">port</span><span class="p">)</span>
<span class="k">if</span> <span class="n">configuration</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'core'</span><span class="p">,</span> <span class="s1">'security'</span><span class="p">)</span> <span class="o">==</span> <span class="s1">'kerberos'</span> <span class="ow">and</span> <span class="n">auth_mechanism</span> <span class="o">==</span> <span class="s1">'GSSAPI'</span><span class="p">:</span>
<span class="k">try</span><span class="p">:</span>
- <span class="kn">import</span> <span class="nn">saslwrapper</span> <span class="kn">as</span> <span class="nn">sasl</span>
+ <span class="kn">import</span> <span class="nn">saslwrapper</span> <span class="k">as</span> <span class="nn">sasl</span>
<span class="k">except</span> <span class="ne">ImportError</span><span class="p">:</span>
<span class="kn">import</span> <span class="nn">sasl</span>
@@ -526,7 +633,7 @@
<span class="n">sasl_client</span><span class="o">.</span><span class="n">init</span><span class="p">()</span>
<span class="k">return</span> <span class="n">sasl_client</span>
- <span class="kn">from</span> <span class="nn">thrift_sasl</span> <span class="kn">import</span> <span class="n">TSaslClientTransport</span>
+ <span class="kn">from</span> <span class="nn">thrift_sasl</span> <span class="k">import</span> <span class="n">TSaslClientTransport</span>
<span class="n">transport</span> <span class="o">=</span> <span class="n">TSaslClientTransport</span><span class="p">(</span><span class="n">sasl_factory</span><span class="p">,</span> <span class="s2">"GSSAPI"</span><span class="p">,</span> <span class="n">socket</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">transport</span> <span class="o">=</span> <span class="n">TTransport</span><span class="o">.</span><span class="n">TBufferedTransport</span><span class="p">(</span><span class="n">socket</span><span class="p">)</span>
@@ -561,9 +668,9 @@
<span class="n">schema</span><span class="p">,</span> <span class="n">table</span><span class="p">,</span> <span class="n">partition</span><span class="p">,</span> <span class="mi">1</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">metastore</span><span class="o">.</span><span class="n">_oprot</span><span class="o">.</span><span class="n">trans</span><span class="o">.</span><span class="n">close</span><span class="p">()</span>
<span class="k">if</span> <span class="n">partitions</span><span class="p">:</span>
- <span class="k">return</span> <span class="bp">True</span>
+ <span class="k">return</span> <span class="kc">True</span>
<span class="k">else</span><span class="p">:</span>
- <span class="k">return</span> <span class="bp">False</span></div>
+ <span class="k">return</span> <span class="kc">False</span></div>
<div class="viewcode-block" id="HiveMetastoreHook.check_for_named_partition"><a class="viewcode-back" href="../code.html#airflow.hooks.HiveMetastoreHook.check_for_named_partition">[docs]</a> <span class="k">def</span> <span class="nf">check_for_named_partition</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">schema</span><span class="p">,</span> <span class="n">table</span><span class="p">,</span> <span class="n">partition_name</span><span class="p">):</span>
<span class="sd">"""</span>
@@ -588,9 +695,9 @@
<span class="k">try</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">metastore</span><span class="o">.</span><span class="n">get_partition_by_name</span><span class="p">(</span>
<span class="n">schema</span><span class="p">,</span> <span class="n">table</span><span class="p">,</span> <span class="n">partition_name</span><span class="p">)</span>
- <span class="k">return</span> <span class="bp">True</span>
+ <span class="k">return</span> <span class="kc">True</span>
<span class="k">except</span> <span class="n">hive_metastore</span><span class="o">.</span><span class="n">ttypes</span><span class="o">.</span><span class="n">NoSuchObjectException</span><span class="p">:</span>
- <span class="k">return</span> <span class="bp">False</span>
+ <span class="k">return</span> <span class="kc">False</span>
<span class="k">finally</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">metastore</span><span class="o">.</span><span class="n">_oprot</span><span class="o">.</span><span class="n">trans</span><span class="o">.</span><span class="n">close</span><span class="p">()</span></div>
@@ -631,7 +738,7 @@
<span class="k">return</span> <span class="n">dbs</span></div>
<div class="viewcode-block" id="HiveMetastoreHook.get_partitions"><a class="viewcode-back" href="../code.html#airflow.hooks.HiveMetastoreHook.get_partitions">[docs]</a> <span class="k">def</span> <span class="nf">get_partitions</span><span class="p">(</span>
- <span class="bp">self</span><span class="p">,</span> <span class="n">schema</span><span class="p">,</span> <span class="n">table_name</span><span class="p">,</span> <span class="nb">filter</span><span class="o">=</span><span class="bp">None</span><span class="p">):</span>
+ <span class="bp">self</span><span class="p">,</span> <span class="n">schema</span><span class="p">,</span> <span class="n">table_name</span><span class="p">,</span> <span class="nb">filter</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Returns a list of all partitions in a table. Works only</span>
<span class="sd"> for tables with less than 32767 (java short max val).</span>
@@ -662,7 +769,7 @@
<span class="n">pnames</span> <span class="o">=</span> <span class="p">[</span><span class="n">p</span><span class="o">.</span><span class="n">name</span> <span class="k">for</span> <span class="n">p</span> <span class="ow">in</span> <span class="n">table</span><span class="o">.</span><span class="n">partitionKeys</span><span class="p">]</span>
<span class="k">return</span> <span class="p">[</span><span class="nb">dict</span><span class="p">(</span><span class="nb">zip</span><span class="p">(</span><span class="n">pnames</span><span class="p">,</span> <span class="n">p</span><span class="o">.</span><span class="n">values</span><span class="p">))</span> <span class="k">for</span> <span class="n">p</span> <span class="ow">in</span> <span class="n">parts</span><span class="p">]</span></div>
-<div class="viewcode-block" id="HiveMetastoreHook.max_partition"><a class="viewcode-back" href="../code.html#airflow.hooks.HiveMetastoreHook.max_partition">[docs]</a> <span class="k">def</span> <span class="nf">max_partition</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">schema</span><span class="p">,</span> <span class="n">table_name</span><span class="p">,</span> <span class="n">field</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span> <span class="nb">filter</span><span class="o">=</span><span class="bp">None</span><span class="p">):</span>
+<div class="viewcode-block" id="HiveMetastoreHook.max_partition"><a class="viewcode-back" href="../code.html#airflow.hooks.HiveMetastoreHook.max_partition">[docs]</a> <span class="k">def</span> <span class="nf">max_partition</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">schema</span><span class="p">,</span> <span class="n">table_name</span><span class="p">,</span> <span class="n">field</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="nb">filter</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Returns the maximum value for all partitions in a table. Works only</span>
<span class="sd"> for tables that have a single partition key. For subpartitioned</span>
@@ -675,7 +782,7 @@
<span class="sd"> """</span>
<span class="n">parts</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_partitions</span><span class="p">(</span><span class="n">schema</span><span class="p">,</span> <span class="n">table_name</span><span class="p">,</span> <span class="nb">filter</span><span class="p">)</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">parts</span><span class="p">:</span>
- <span class="k">return</span> <span class="bp">None</span>
+ <span class="k">return</span> <span class="kc">None</span>
<span class="k">elif</span> <span class="nb">len</span><span class="p">(</span><span class="n">parts</span><span class="p">[</span><span class="mi">0</span><span class="p">])</span> <span class="o">==</span> <span class="mi">1</span><span class="p">:</span>
<span class="n">field</span> <span class="o">=</span> <span class="nb">list</span><span class="p">(</span><span class="n">parts</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">keys</span><span class="p">())[</span><span class="mi">0</span><span class="p">]</span>
<span class="k">elif</span> <span class="ow">not</span> <span class="n">field</span><span class="p">:</span>
@@ -697,9 +804,9 @@
<span class="sd"> """</span>
<span class="k">try</span><span class="p">:</span>
<span class="n">t</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_table</span><span class="p">(</span><span class="n">table_name</span><span class="p">,</span> <span class="n">db</span><span class="p">)</span>
- <span class="k">return</span> <span class="bp">True</span>
+ <span class="k">return</span> <span class="kc">True</span>
<span class="k">except</span> <span class="ne">Exception</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span>
- <span class="k">return</span> <span class="bp">False</span></div></div>
+ <span class="k">return</span> <span class="kc">False</span></div></div>
<div class="viewcode-block" id="HiveServer2Hook"><a class="viewcode-back" href="../code.html#airflow.hooks.HiveServer2Hook">[docs]</a><span class="k">class</span> <span class="nc">HiveServer2Hook</span><span class="p">(</span><span class="n">BaseHook</span><span class="p">):</span>
@@ -712,33 +819,35 @@
<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">hiveserver2_conn_id</span><span class="o">=</span><span class="s1">'hiveserver2_default'</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">hiveserver2_conn_id</span> <span class="o">=</span> <span class="n">hiveserver2_conn_id</span>
- <span class="k">def</span> <span class="nf">get_conn</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
+ <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="n">schema</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="n">db</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">hiveserver2_conn_id</span><span class="p">)</span>
<span class="n">auth_mechanism</span> <span class="o">=</span> <span class="n">db</span><span class="o">.</span><span class="n">extra_dejson</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'authMechanism'</span><span class="p">,</span> <span class="s1">'PLAIN'</span><span class="p">)</span>
- <span class="n">kerberos_service_name</span> <span class="o">=</span> <span class="bp">None</span>
+ <span class="n">kerberos_service_name</span> <span class="o">=</span> <span class="kc">None</span>
<span class="k">if</span> <span class="n">configuration</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'core'</span><span class="p">,</span> <span class="s1">'security'</span><span class="p">)</span> <span class="o">==</span> <span class="s1">'kerberos'</span><span class="p">:</span>
<span class="n">auth_mechanism</span> <span class="o">=</span> <span class="n">db</span><span class="o">.</span><span class="n">extra_dejson</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'authMechanism'</span><span class="p">,</span> <span class="s1">'GSSAPI'</span><span class="p">)</span>
<span class="n">kerberos_service_name</span> <span class="o">=</span> <span class="n">db</span><span class="o">.</span><span class="n">extra_dejson</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'kerberos_service_name'</span><span class="p">,</span> <span class="s1">'hive'</span><span class="p">)</span>
<span class="c1"># impyla uses GSSAPI instead of KERBEROS as a auth_mechanism identifier</span>
<span class="k">if</span> <span class="n">auth_mechanism</span> <span class="o">==</span> <span class="s1">'KERBEROS'</span><span class="p">:</span>
- <span class="n">logging</span><span class="o">.</span><span class="n">warning</span><span class="p">(</span><span class="s2">"Detected deprecated 'KERBEROS' for authMechanism for </span><span class="si">%s</span><span class="s2">. Please use 'GSSAPI' instead"</span><span class="p">,</span>
- <span class="bp">self</span><span class="o">.</span><span class="n">hiveserver2_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">warning</span><span class="p">(</span>
+ <span class="s2">"Detected deprecated 'KERBEROS' for authMechanism for </span><span class="si">%s</span><span class="s2">. Please use 'GSSAPI' instead"</span><span class="p">,</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">hiveserver2_conn_id</span>
+ <span class="p">)</span>
<span class="n">auth_mechanism</span> <span class="o">=</span> <span class="s1">'GSSAPI'</span>
- <span class="kn">from</span> <span class="nn">impala.dbapi</span> <span class="kn">import</span> <span class="n">connect</span>
+ <span class="kn">from</span> <span class="nn">impala.dbapi</span> <span class="k">import</span> <span class="n">connect</span>
<span class="k">return</span> <span class="n">connect</span><span class="p">(</span>
<span class="n">host</span><span class="o">=</span><span class="n">db</span><span class="o">.</span><span class="n">host</span><span class="p">,</span>
<span class="n">port</span><span class="o">=</span><span class="n">db</span><span class="o">.</span><span class="n">port</span><span class="p">,</span>
<span class="n">auth_mechanism</span><span class="o">=</span><span class="n">auth_mechanism</span><span class="p">,</span>
<span class="n">kerberos_service_name</span><span class="o">=</span><span class="n">kerberos_service_name</span><span class="p">,</span>
<span class="n">user</span><span class="o">=</span><span class="n">db</span><span class="o">.</span><span class="n">login</span><span class="p">,</span>
- <span class="n">database</span><span class="o">=</span><span class="n">db</span><span class="o">.</span><span class="n">schema</span> <span class="ow">or</span> <span class="s1">'default'</span><span class="p">)</span>
+ <span class="n">database</span><span class="o">=</span><span class="n">schema</span> <span class="ow">or</span> <span class="n">db</span><span class="o">.</span><span class="n">schema</span> <span class="ow">or</span> <span class="s1">'default'</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">get_results</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">hql</span><span class="p">,</span> <span class="n">schema</span><span class="o">=</span><span class="s1">'default'</span><span class="p">,</span> <span class="n">arraysize</span><span class="o">=</span><span class="mi">1000</span><span class="p">):</span>
- <span class="kn">from</span> <span class="nn">impala.error</span> <span class="kn">import</span> <span class="n">ProgrammingError</span>
- <span class="k">with</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_conn</span><span class="p">()</span> <span class="k">as</span> <span class="n">conn</span><span class="p">:</span>
- <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">hql</span><span class="p">,</span> <span class="nb">basestring</span><span class="p">):</span>
+ <span class="kn">from</span> <span class="nn">impala.error</span> <span class="k">import</span> <span class="n">ProgrammingError</span>
+ <span class="k">with</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_conn</span><span class="p">(</span><span class="n">schema</span><span class="p">)</span> <span class="k">as</span> <span class="n">conn</span><span class="p">:</span>
+ <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">hql</span><span class="p">,</span> <span class="n">basestring</span><span class="p">):</span>
<span class="n">hql</span> <span class="o">=</span> <span class="p">[</span><span class="n">hql</span><span class="p">]</span>
<span class="n">results</span> <span class="o">=</span> <span class="p">{</span>
<span class="s1">'data'</span><span class="p">:</span> <span class="p">[],</span>
@@ -754,7 +863,7 @@
<span class="c1"># may be `SET` or DDL</span>
<span class="n">records</span> <span class="o">=</span> <span class="n">cur</span><span class="o">.</span><span class="n">fetchall</span><span class="p">()</span>
<span class="k">except</span> <span class="n">ProgrammingError</span><span class="p">:</span>
- <span class="n">logging</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="s2">"get_results returned no records"</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="s2">"get_results returned no records"</span><span class="p">)</span>
<span class="k">if</span> <span class="n">records</span><span class="p">:</span>
<span class="n">results</span> <span class="o">=</span> <span class="p">{</span>
<span class="s1">'data'</span><span class="p">:</span> <span class="n">records</span><span class="p">,</span>
@@ -769,12 +878,12 @@
<span class="n">schema</span><span class="o">=</span><span class="s1">'default'</span><span class="p">,</span>
<span class="n">delimiter</span><span class="o">=</span><span class="s1">','</span><span class="p">,</span>
<span class="n">lineterminator</span><span class="o">=</span><span class="s1">'</span><span class="se">\r\n</span><span class="s1">'</span><span class="p">,</span>
- <span class="n">output_header</span><span class="o">=</span><span class="bp">True</span><span class="p">,</span>
+ <span class="n">output_header</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
<span class="n">fetch_size</span><span class="o">=</span><span class="mi">1000</span><span class="p">):</span>
<span class="n">schema</span> <span class="o">=</span> <span class="n">schema</span> <span class="ow">or</span> <span class="s1">'default'</span>
- <span class="k">with</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_conn</span><span class="p">()</span> <span class="k">as</span> <span class="n">conn</span><span class="p">:</span>
+ <span class="k">with</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_conn</span><span class="p">(</span><span class="n">schema</span><span class="p">)</span> <span class="k">as</span> <span class="n">conn</span><span class="p">:</span>
<span class="k">with</span> <span class="n">conn</span><span class="o">.</span><span class="n">cursor</span><span class="p">()</span> <span class="k">as</span> <span class="n">cur</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 query: "</span> <span class="o">+</span> <span class="n">hql</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 query: </span><span class="si">%s</span><span class="s2">"</span><span class="p">,</span> <span class="n">hql</span><span class="p">)</span>
<span class="n">cur</span><span class="o">.</span><span class="n">execute</span><span class="p">(</span><span class="n">hql</span><span class="p">)</span>
<span class="n">schema</span> <span class="o">=</span> <span class="n">cur</span><span class="o">.</span><span class="n">description</span>
<span class="k">with</span> <span class="nb">open</span><span class="p">(</span><span class="n">csv_filepath</span><span class="p">,</span> <span class="s1">'wb'</span><span class="p">)</span> <span class="k">as</span> <span class="n">f</span><span class="p">:</span>
@@ -785,15 +894,15 @@
<span class="k">if</span> <span class="n">output_header</span><span class="p">:</span>
<span class="n">writer</span><span class="o">.</span><span class="n">writerow</span><span class="p">([</span><span class="n">c</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="k">for</span> <span class="n">c</span> <span class="ow">in</span> <span class="n">cur</span><span class="o">.</span><span class="n">description</span><span class="p">])</span>
<span class="n">i</span> <span class="o">=</span> <span class="mi">0</span>
- <span class="k">while</span> <span class="bp">True</span><span class="p">:</span>
+ <span class="k">while</span> <span class="kc">True</span><span class="p">:</span>
<span class="n">rows</span> <span class="o">=</span> <span class="p">[</span><span class="n">row</span> <span class="k">for</span> <span class="n">row</span> <span class="ow">in</span> <span class="n">cur</span><span class="o">.</span><span class="n">fetchmany</span><span class="p">(</span><span class="n">fetch_size</span><span class="p">)</span> <span class="k">if</span> <span class="n">row</span><span class="p">]</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">rows</span><span class="p">:</span>
<span class="k">br
<TRUNCATED>