| |
| |
| <!DOCTYPE html> |
| <!--[if IE 8]><html class="no-js lt-ie9" lang="en" > <![endif]--> |
| <!--[if gt IE 8]><!--> <html class="no-js" lang="en" > <!--<![endif]--> |
| <head> |
| <meta charset="utf-8"> |
| |
| <meta name="viewport" content="width=device-width, initial-scale=1.0"> |
| |
| <title>apache_beam.io.gcp.bigquery_read_internal — Apache Beam 2.47.0 documentation</title> |
| |
| |
| |
| |
| |
| |
| |
| |
| <script type="text/javascript" src="../../../../_static/js/modernizr.min.js"></script> |
| |
| |
| <script type="text/javascript" id="documentation_options" data-url_root="../../../../" src="../../../../_static/documentation_options.js"></script> |
| <script type="text/javascript" src="../../../../_static/jquery.js"></script> |
| <script type="text/javascript" src="../../../../_static/underscore.js"></script> |
| <script type="text/javascript" src="../../../../_static/doctools.js"></script> |
| <script type="text/javascript" src="../../../../_static/language_data.js"></script> |
| <script async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/latest.js?config=TeX-AMS-MML_HTMLorMML"></script> |
| |
| <script type="text/javascript" src="../../../../_static/js/theme.js"></script> |
| |
| |
| |
| |
| <link rel="stylesheet" href="../../../../_static/css/theme.css" type="text/css" /> |
| <link rel="stylesheet" href="../../../../_static/pygments.css" type="text/css" /> |
| <link rel="index" title="Index" href="../../../../genindex.html" /> |
| <link rel="search" title="Search" href="../../../../search.html" /> |
| </head> |
| |
| <body class="wy-body-for-nav"> |
| |
| |
| <div class="wy-grid-for-nav"> |
| |
| <nav data-toggle="wy-nav-shift" class="wy-nav-side"> |
| <div class="wy-side-scroll"> |
| <div class="wy-side-nav-search" > |
| |
| |
| |
| <a href="../../../../index.html" class="icon icon-home"> Apache Beam |
| |
| |
| |
| </a> |
| |
| |
| |
| |
| <div class="version"> |
| 2.47.0 |
| </div> |
| |
| |
| |
| |
| <div role="search"> |
| <form id="rtd-search-form" class="wy-form" action="../../../../search.html" method="get"> |
| <input type="text" name="q" placeholder="Search docs" /> |
| <input type="hidden" name="check_keywords" value="yes" /> |
| <input type="hidden" name="area" value="default" /> |
| </form> |
| </div> |
| |
| |
| </div> |
| |
| <div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation"> |
| |
| |
| |
| |
| |
| |
| <ul> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.coders.html">apache_beam.coders package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.dataframe.html">apache_beam.dataframe package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.io.html">apache_beam.io package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.metrics.html">apache_beam.metrics package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.ml.html">apache_beam.ml package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.options.html">apache_beam.options package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.portability.html">apache_beam.portability package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.runners.html">apache_beam.runners package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.testing.html">apache_beam.testing package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.transforms.html">apache_beam.transforms package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.typehints.html">apache_beam.typehints package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.utils.html">apache_beam.utils package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.yaml.html">apache_beam.yaml package</a></li> |
| </ul> |
| <ul> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.error.html">apache_beam.error module</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.pipeline.html">apache_beam.pipeline module</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.pvalue.html">apache_beam.pvalue module</a></li> |
| </ul> |
| |
| |
| |
| </div> |
| </div> |
| </nav> |
| |
| <section data-toggle="wy-nav-shift" class="wy-nav-content-wrap"> |
| |
| |
| <nav class="wy-nav-top" aria-label="top navigation"> |
| |
| <i data-toggle="wy-nav-top" class="fa fa-bars"></i> |
| <a href="../../../../index.html">Apache Beam</a> |
| |
| </nav> |
| |
| |
| <div class="wy-nav-content"> |
| |
| <div class="rst-content"> |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| <div role="navigation" aria-label="breadcrumbs navigation"> |
| |
| <ul class="wy-breadcrumbs"> |
| |
| <li><a href="../../../../index.html">Docs</a> »</li> |
| |
| <li><a href="../../../index.html">Module code</a> »</li> |
| |
| <li>apache_beam.io.gcp.bigquery_read_internal</li> |
| |
| |
| <li class="wy-breadcrumbs-aside"> |
| |
| </li> |
| |
| </ul> |
| |
| |
| <hr/> |
| </div> |
| <div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article"> |
| <div itemprop="articleBody"> |
| |
| <h1>Source code for apache_beam.io.gcp.bigquery_read_internal</h1><div class="highlight"><pre> |
| <span></span><span class="c1">#</span> |
| <span class="c1"># Licensed to the Apache Software Foundation (ASF) under one or more</span> |
| <span class="c1"># contributor license agreements. See the NOTICE file distributed with</span> |
| <span class="c1"># this work for additional information regarding copyright ownership.</span> |
| <span class="c1"># The ASF licenses this file to You under the Apache License, Version 2.0</span> |
| <span class="c1"># (the "License"); you may not use this file except in compliance with</span> |
| <span class="c1"># the License. You may obtain a copy of the License at</span> |
| <span class="c1">#</span> |
| <span class="c1"># http://www.apache.org/licenses/LICENSE-2.0</span> |
| <span class="c1">#</span> |
| <span class="c1"># Unless required by applicable law or agreed to in writing, software</span> |
| <span class="c1"># distributed under the License is distributed on an "AS IS" BASIS,</span> |
| <span class="c1"># WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.</span> |
| <span class="c1"># See the License for the specific language governing permissions and</span> |
| <span class="c1"># limitations under the License.</span> |
| <span class="c1">#</span> |
| |
| <span class="sd">"""</span> |
| <span class="sd">Internal library for reading data from BigQuery.</span> |
| |
| <span class="sd">NOTHING IN THIS FILE HAS BACKWARDS COMPATIBILITY GUARANTEES.</span> |
| <span class="sd">"""</span> |
| <span class="kn">import</span> <span class="nn">collections</span> |
| <span class="kn">import</span> <span class="nn">decimal</span> |
| <span class="kn">import</span> <span class="nn">json</span> |
| <span class="kn">import</span> <span class="nn">logging</span> |
| <span class="kn">import</span> <span class="nn">random</span> |
| <span class="kn">import</span> <span class="nn">time</span> |
| <span class="kn">import</span> <span class="nn">uuid</span> |
| <span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">TYPE_CHECKING</span> |
| <span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">Any</span> |
| <span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">Dict</span> |
| <span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">Iterable</span> |
| <span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">List</span> |
| <span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">Optional</span> |
| <span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">Union</span> |
| |
| <span class="kn">import</span> <span class="nn">apache_beam</span> <span class="k">as</span> <span class="nn">beam</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.coders</span> <span class="kn">import</span> <span class="n">coders</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.io.avroio</span> <span class="kn">import</span> <span class="n">_create_avro_source</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.io.filesystem</span> <span class="kn">import</span> <span class="n">CompressionTypes</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.io.filesystems</span> <span class="kn">import</span> <span class="n">FileSystems</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.io.gcp</span> <span class="kn">import</span> <span class="n">bigquery_tools</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.io.gcp.bigquery_io_metadata</span> <span class="kn">import</span> <span class="n">create_bigquery_io_metadata</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.io.iobase</span> <span class="kn">import</span> <span class="n">BoundedSource</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.io.textio</span> <span class="kn">import</span> <span class="n">_TextSource</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.options.pipeline_options</span> <span class="kn">import</span> <span class="n">GoogleCloudOptions</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.options.pipeline_options</span> <span class="kn">import</span> <span class="n">PipelineOptions</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.options.value_provider</span> <span class="kn">import</span> <span class="n">ValueProvider</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.transforms</span> <span class="kn">import</span> <span class="n">PTransform</span> |
| |
| <span class="k">if</span> <span class="n">TYPE_CHECKING</span><span class="p">:</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.io.gcp.bigquery</span> <span class="kn">import</span> <span class="n">ReadFromBigQueryRequest</span> |
| |
| <span class="k">try</span><span class="p">:</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.io.gcp.internal.clients.bigquery</span> <span class="kn">import</span> <span class="n">DatasetReference</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.io.gcp.internal.clients.bigquery</span> <span class="kn">import</span> <span class="n">TableReference</span> |
| <span class="k">except</span> <span class="ne">ImportError</span><span class="p">:</span> |
| <span class="n">DatasetReference</span> <span class="o">=</span> <span class="kc">None</span> |
| <span class="n">TableReference</span> <span class="o">=</span> <span class="kc">None</span> |
| |
| <span class="n">_LOGGER</span> <span class="o">=</span> <span class="n">logging</span><span class="o">.</span><span class="n">getLogger</span><span class="p">(</span><span class="vm">__name__</span><span class="p">)</span> |
| |
| |
| <div class="viewcode-block" id="bigquery_export_destination_uri"><a class="viewcode-back" href="../../../../apache_beam.io.gcp.bigquery_read_internal.html#apache_beam.io.gcp.bigquery_read_internal.bigquery_export_destination_uri">[docs]</a><span class="k">def</span> <span class="nf">bigquery_export_destination_uri</span><span class="p">(</span> |
| <span class="n">gcs_location_vp</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">ValueProvider</span><span class="p">],</span> |
| <span class="n">temp_location</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">],</span> |
| <span class="n">unique_id</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> |
| <span class="n">directory_only</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">False</span><span class="p">,</span> |
| <span class="p">)</span> <span class="o">-></span> <span class="nb">str</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""Returns the fully qualified Google Cloud Storage URI where the</span> |
| <span class="sd"> extracted table should be written.</span> |
| <span class="sd"> """</span> |
| <span class="n">file_pattern</span> <span class="o">=</span> <span class="s1">'bigquery-table-dump-*.json'</span> |
| |
| <span class="n">gcs_location</span> <span class="o">=</span> <span class="kc">None</span> |
| <span class="k">if</span> <span class="n">gcs_location_vp</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">gcs_location</span> <span class="o">=</span> <span class="n">gcs_location_vp</span><span class="o">.</span><span class="n">get</span><span class="p">()</span> |
| |
| <span class="k">if</span> <span class="n">gcs_location</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">gcs_base</span> <span class="o">=</span> <span class="n">gcs_location</span> |
| <span class="k">elif</span> <span class="n">temp_location</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">gcs_base</span> <span class="o">=</span> <span class="n">temp_location</span> |
| <span class="n">_LOGGER</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="s2">"gcs_location is empty, using temp_location instead"</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span> |
| <span class="s1">'ReadFromBigQuery requires a GCS location to be provided. Neither '</span> |
| <span class="s1">'gcs_location in the constructor nor the fallback option '</span> |
| <span class="s1">'--temp_location is set.'</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="ow">not</span> <span class="n">unique_id</span><span class="p">:</span> |
| <span class="n">unique_id</span> <span class="o">=</span> <span class="n">uuid</span><span class="o">.</span><span class="n">uuid4</span><span class="p">()</span><span class="o">.</span><span class="n">hex</span> |
| |
| <span class="k">if</span> <span class="n">directory_only</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">FileSystems</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">gcs_base</span><span class="p">,</span> <span class="n">unique_id</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">FileSystems</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">gcs_base</span><span class="p">,</span> <span class="n">unique_id</span><span class="p">,</span> <span class="n">file_pattern</span><span class="p">)</span></div> |
| |
| |
| <span class="k">class</span> <span class="nc">_PassThroughThenCleanup</span><span class="p">(</span><span class="n">PTransform</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""A PTransform that invokes a DoFn after the input PCollection has been</span> |
| <span class="sd"> processed.</span> |
| |
| <span class="sd"> DoFn should have arguments (element, side_input, cleanup_signal).</span> |
| |
| <span class="sd"> Utilizes readiness of PCollection to trigger DoFn.</span> |
| <span class="sd"> """</span> |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">side_input</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">side_input</span> <span class="o">=</span> <span class="n">side_input</span> |
| |
| <span class="k">def</span> <span class="nf">expand</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="nb">input</span><span class="p">):</span> |
| <span class="k">class</span> <span class="nc">PassThrough</span><span class="p">(</span><span class="n">beam</span><span class="o">.</span><span class="n">DoFn</span><span class="p">):</span> |
| <span class="k">def</span> <span class="nf">process</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">element</span><span class="p">):</span> |
| <span class="k">yield</span> <span class="n">element</span> |
| |
| <span class="k">class</span> <span class="nc">RemoveExtractedFiles</span><span class="p">(</span><span class="n">beam</span><span class="o">.</span><span class="n">DoFn</span><span class="p">):</span> |
| <span class="k">def</span> <span class="nf">process</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">unused_element</span><span class="p">,</span> <span class="n">unused_signal</span><span class="p">,</span> <span class="n">gcs_locations</span><span class="p">):</span> |
| <span class="n">FileSystems</span><span class="o">.</span><span class="n">delete</span><span class="p">(</span><span class="nb">list</span><span class="p">(</span><span class="n">gcs_locations</span><span class="p">))</span> |
| |
| <span class="n">main_output</span><span class="p">,</span> <span class="n">cleanup_signal</span> <span class="o">=</span> <span class="nb">input</span> <span class="o">|</span> <span class="n">beam</span><span class="o">.</span><span class="n">ParDo</span><span class="p">(</span> |
| <span class="n">PassThrough</span><span class="p">())</span><span class="o">.</span><span class="n">with_outputs</span><span class="p">(</span> |
| <span class="s1">'cleanup_signal'</span><span class="p">,</span> <span class="n">main</span><span class="o">=</span><span class="s1">'main'</span><span class="p">)</span> |
| |
| <span class="n">cleanup_input</span> <span class="o">=</span> <span class="nb">input</span><span class="o">.</span><span class="n">pipeline</span> <span class="o">|</span> <span class="n">beam</span><span class="o">.</span><span class="n">Create</span><span class="p">([</span><span class="kc">None</span><span class="p">])</span> |
| |
| <span class="n">_</span> <span class="o">=</span> <span class="n">cleanup_input</span> <span class="o">|</span> <span class="n">beam</span><span class="o">.</span><span class="n">ParDo</span><span class="p">(</span> |
| <span class="n">RemoveExtractedFiles</span><span class="p">(),</span> |
| <span class="n">beam</span><span class="o">.</span><span class="n">pvalue</span><span class="o">.</span><span class="n">AsSingleton</span><span class="p">(</span><span class="n">cleanup_signal</span><span class="p">),</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">side_input</span><span class="p">,</span> |
| <span class="p">)</span> |
| |
| <span class="k">return</span> <span class="n">main_output</span> |
| |
| |
| <span class="k">class</span> <span class="nc">_PassThroughThenCleanupTempDatasets</span><span class="p">(</span><span class="n">PTransform</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""A PTransform that invokes a DoFn after the input PCollection has been</span> |
| <span class="sd"> processed.</span> |
| |
| <span class="sd"> DoFn should have arguments (element, side_input, cleanup_signal).</span> |
| |
| <span class="sd"> Utilizes readiness of PCollection to trigger DoFn.</span> |
| <span class="sd"> """</span> |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">side_input</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">side_input</span> <span class="o">=</span> <span class="n">side_input</span> |
| |
| <span class="k">def</span> <span class="nf">expand</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="nb">input</span><span class="p">):</span> |
| <span class="k">class</span> <span class="nc">PassThrough</span><span class="p">(</span><span class="n">beam</span><span class="o">.</span><span class="n">DoFn</span><span class="p">):</span> |
| <span class="k">def</span> <span class="nf">process</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">element</span><span class="p">):</span> |
| <span class="k">yield</span> <span class="n">element</span> |
| |
| <span class="k">class</span> <span class="nc">CleanUpProjects</span><span class="p">(</span><span class="n">beam</span><span class="o">.</span><span class="n">DoFn</span><span class="p">):</span> |
| <span class="k">def</span> <span class="nf">process</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">unused_element</span><span class="p">,</span> <span class="n">unused_signal</span><span class="p">,</span> <span class="n">pipeline_details</span><span class="p">):</span> |
| <span class="n">bq</span> <span class="o">=</span> <span class="n">bigquery_tools</span><span class="o">.</span><span class="n">BigQueryWrapper</span><span class="p">()</span> |
| <span class="n">pipeline_details</span> <span class="o">=</span> <span class="n">pipeline_details</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> |
| <span class="k">if</span> <span class="s1">'temp_table_ref'</span> <span class="ow">in</span> <span class="n">pipeline_details</span><span class="o">.</span><span class="n">keys</span><span class="p">():</span> |
| <span class="n">temp_table_ref</span> <span class="o">=</span> <span class="n">pipeline_details</span><span class="p">[</span><span class="s1">'temp_table_ref'</span><span class="p">]</span> |
| <span class="n">bq</span><span class="o">.</span><span class="n">_clean_up_beam_labelled_temporary_datasets</span><span class="p">(</span> |
| <span class="n">project_id</span><span class="o">=</span><span class="n">temp_table_ref</span><span class="o">.</span><span class="n">projectId</span><span class="p">,</span> |
| <span class="n">dataset_id</span><span class="o">=</span><span class="n">temp_table_ref</span><span class="o">.</span><span class="n">datasetId</span><span class="p">,</span> |
| <span class="n">table_id</span><span class="o">=</span><span class="n">temp_table_ref</span><span class="o">.</span><span class="n">tableId</span><span class="p">)</span> |
| <span class="k">elif</span> <span class="s1">'project_id'</span> <span class="ow">in</span> <span class="n">pipeline_details</span><span class="o">.</span><span class="n">keys</span><span class="p">():</span> |
| <span class="n">bq</span><span class="o">.</span><span class="n">_clean_up_beam_labelled_temporary_datasets</span><span class="p">(</span> |
| <span class="n">project_id</span><span class="o">=</span><span class="n">pipeline_details</span><span class="p">[</span><span class="s1">'project_id'</span><span class="p">],</span> |
| <span class="n">labels</span><span class="o">=</span><span class="n">pipeline_details</span><span class="p">[</span><span class="s1">'bigquery_dataset_labels'</span><span class="p">])</span> |
| |
| <span class="n">main_output</span><span class="p">,</span> <span class="n">cleanup_signal</span> <span class="o">=</span> <span class="nb">input</span> <span class="o">|</span> <span class="n">beam</span><span class="o">.</span><span class="n">ParDo</span><span class="p">(</span> |
| <span class="n">PassThrough</span><span class="p">())</span><span class="o">.</span><span class="n">with_outputs</span><span class="p">(</span> |
| <span class="s1">'cleanup_signal'</span><span class="p">,</span> <span class="n">main</span><span class="o">=</span><span class="s1">'main'</span><span class="p">)</span> |
| |
| <span class="n">cleanup_input</span> <span class="o">=</span> <span class="nb">input</span><span class="o">.</span><span class="n">pipeline</span> <span class="o">|</span> <span class="n">beam</span><span class="o">.</span><span class="n">Create</span><span class="p">([</span><span class="kc">None</span><span class="p">])</span> |
| |
| <span class="n">_</span> <span class="o">=</span> <span class="n">cleanup_input</span> <span class="o">|</span> <span class="n">beam</span><span class="o">.</span><span class="n">ParDo</span><span class="p">(</span> |
| <span class="n">CleanUpProjects</span><span class="p">(),</span> |
| <span class="n">beam</span><span class="o">.</span><span class="n">pvalue</span><span class="o">.</span><span class="n">AsSingleton</span><span class="p">(</span><span class="n">cleanup_signal</span><span class="p">),</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">side_input</span><span class="p">,</span> |
| <span class="p">)</span> |
| |
| <span class="k">return</span> <span class="n">main_output</span> |
| |
| |
| <span class="k">class</span> <span class="nc">_BigQueryReadSplit</span><span class="p">(</span><span class="n">beam</span><span class="o">.</span><span class="n">transforms</span><span class="o">.</span><span class="n">DoFn</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""Starts the process of reading from BigQuery.</span> |
| |
| <span class="sd"> This transform will start a BigQuery export job, and output a number of</span> |
| <span class="sd"> file sources that are consumed downstream.</span> |
| <span class="sd"> """</span> |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span> |
| <span class="bp">self</span><span class="p">,</span> |
| <span class="n">options</span><span class="p">:</span> <span class="n">PipelineOptions</span><span class="p">,</span> |
| <span class="n">gcs_location</span><span class="p">:</span> <span class="n">Union</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">ValueProvider</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> |
| <span class="n">use_json_exports</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">False</span><span class="p">,</span> |
| <span class="n">bigquery_job_labels</span><span class="p">:</span> <span class="n">Dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> |
| <span class="n">step_name</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> |
| <span class="n">job_name</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> |
| <span class="n">unique_id</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> |
| <span class="n">kms_key</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> |
| <span class="n">project</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> |
| <span class="n">temp_dataset</span><span class="p">:</span> <span class="n">Union</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">DatasetReference</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> |
| <span class="n">query_priority</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">options</span> <span class="o">=</span> <span class="n">options</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">use_json_exports</span> <span class="o">=</span> <span class="n">use_json_exports</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">gcs_location</span> <span class="o">=</span> <span class="n">gcs_location</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">bigquery_job_labels</span> <span class="o">=</span> <span class="n">bigquery_job_labels</span> <span class="ow">or</span> <span class="p">{}</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_step_name</span> <span class="o">=</span> <span class="n">step_name</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_job_name</span> <span class="o">=</span> <span class="n">job_name</span> <span class="ow">or</span> <span class="s1">'BQ_READ_SPLIT'</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_source_uuid</span> <span class="o">=</span> <span class="n">unique_id</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">kms_key</span> <span class="o">=</span> <span class="n">kms_key</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">project</span> <span class="o">=</span> <span class="n">project</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">temp_dataset</span> <span class="o">=</span> <span class="n">temp_dataset</span> <span class="ow">or</span> <span class="s1">'bq_read_all_</span><span class="si">%s</span><span class="s1">'</span> <span class="o">%</span> <span class="n">uuid</span><span class="o">.</span><span class="n">uuid4</span><span class="p">()</span><span class="o">.</span><span class="n">hex</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">query_priority</span> <span class="o">=</span> <span class="n">query_priority</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">bq_io_metadata</span> <span class="o">=</span> <span class="kc">None</span> |
| |
| <span class="k">def</span> <span class="nf">display_data</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="k">return</span> <span class="p">{</span> |
| <span class="s1">'use_json_exports'</span><span class="p">:</span> <span class="nb">str</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">use_json_exports</span><span class="p">),</span> |
| <span class="s1">'gcs_location'</span><span class="p">:</span> <span class="nb">str</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">gcs_location</span><span class="p">),</span> |
| <span class="s1">'bigquery_job_labels'</span><span class="p">:</span> <span class="n">json</span><span class="o">.</span><span class="n">dumps</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">bigquery_job_labels</span><span class="p">),</span> |
| <span class="s1">'kms_key'</span><span class="p">:</span> <span class="nb">str</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">kms_key</span><span class="p">),</span> |
| <span class="s1">'project'</span><span class="p">:</span> <span class="nb">str</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">project</span><span class="p">),</span> |
| <span class="s1">'temp_dataset'</span><span class="p">:</span> <span class="nb">str</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">temp_dataset</span><span class="p">)</span> |
| <span class="p">}</span> |
| |
| <span class="k">def</span> <span class="nf">_get_temp_dataset</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">temp_dataset</span><span class="p">,</span> <span class="nb">str</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">DatasetReference</span><span class="p">(</span> |
| <span class="n">datasetId</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">temp_dataset</span><span class="p">,</span> <span class="n">projectId</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_get_project</span><span class="p">())</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">temp_dataset</span> |
| |
| <span class="k">def</span> <span class="nf">process</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> |
| <span class="n">element</span><span class="p">:</span> <span class="s1">'ReadFromBigQueryRequest'</span><span class="p">)</span> <span class="o">-></span> <span class="n">Iterable</span><span class="p">[</span><span class="n">BoundedSource</span><span class="p">]:</span> |
| <span class="n">bq</span> <span class="o">=</span> <span class="n">bigquery_tools</span><span class="o">.</span><span class="n">BigQueryWrapper</span><span class="p">(</span> |
| <span class="n">temp_dataset_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_get_temp_dataset</span><span class="p">()</span><span class="o">.</span><span class="n">datasetId</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="n">element</span><span class="o">.</span><span class="n">query</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_setup_temporary_dataset</span><span class="p">(</span><span class="n">bq</span><span class="p">,</span> <span class="n">element</span><span class="p">)</span> |
| <span class="n">table_reference</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_execute_query</span><span class="p">(</span><span class="n">bq</span><span class="p">,</span> <span class="n">element</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">assert</span> <span class="n">element</span><span class="o">.</span><span class="n">table</span> |
| <span class="n">table_reference</span> <span class="o">=</span> <span class="n">bigquery_tools</span><span class="o">.</span><span class="n">parse_table_reference</span><span class="p">(</span> |
| <span class="n">element</span><span class="o">.</span><span class="n">table</span><span class="p">,</span> <span class="n">project</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_get_project</span><span class="p">())</span> |
| |
| <span class="k">if</span> <span class="ow">not</span> <span class="n">table_reference</span><span class="o">.</span><span class="n">projectId</span><span class="p">:</span> |
| <span class="n">table_reference</span><span class="o">.</span><span class="n">projectId</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_get_project</span><span class="p">()</span> |
| |
| <span class="n">schema</span><span class="p">,</span> <span class="n">metadata_list</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_export_files</span><span class="p">(</span><span class="n">bq</span><span class="p">,</span> <span class="n">element</span><span class="p">,</span> <span class="n">table_reference</span><span class="p">)</span> |
| |
| <span class="k">for</span> <span class="n">metadata</span> <span class="ow">in</span> <span class="n">metadata_list</span><span class="p">:</span> |
| <span class="k">yield</span> <span class="bp">self</span><span class="o">.</span><span class="n">_create_source</span><span class="p">(</span><span class="n">metadata</span><span class="o">.</span><span class="n">path</span><span class="p">,</span> <span class="n">schema</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="n">element</span><span class="o">.</span><span class="n">query</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">bq</span><span class="o">.</span><span class="n">_delete_table</span><span class="p">(</span> |
| <span class="n">table_reference</span><span class="o">.</span><span class="n">projectId</span><span class="p">,</span> |
| <span class="n">table_reference</span><span class="o">.</span><span class="n">datasetId</span><span class="p">,</span> |
| <span class="n">table_reference</span><span class="o">.</span><span class="n">tableId</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="n">bq</span><span class="o">.</span><span class="n">created_temp_dataset</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_clean_temporary_dataset</span><span class="p">(</span><span class="n">bq</span><span class="p">,</span> <span class="n">element</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">_get_bq_metadata</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">bq_io_metadata</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">bq_io_metadata</span> <span class="o">=</span> <span class="n">create_bigquery_io_metadata</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_step_name</span><span class="p">)</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">bq_io_metadata</span> |
| |
| <span class="k">def</span> <span class="nf">_create_source</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">schema</span><span class="p">):</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">use_json_exports</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">_create_avro_source</span><span class="p">(</span><span class="n">path</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">_TextSource</span><span class="p">(</span> |
| <span class="n">path</span><span class="p">,</span> |
| <span class="n">min_bundle_size</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> |
| <span class="n">compression_type</span><span class="o">=</span><span class="n">CompressionTypes</span><span class="o">.</span><span class="n">UNCOMPRESSED</span><span class="p">,</span> |
| <span class="n">strip_trailing_newlines</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> |
| <span class="n">coder</span><span class="o">=</span><span class="n">_JsonToDictCoder</span><span class="p">(</span><span class="n">schema</span><span class="p">))</span> |
| |
| <span class="k">def</span> <span class="nf">_setup_temporary_dataset</span><span class="p">(</span> |
| <span class="bp">self</span><span class="p">,</span> |
| <span class="n">bq</span><span class="p">:</span> <span class="n">bigquery_tools</span><span class="o">.</span><span class="n">BigQueryWrapper</span><span class="p">,</span> |
| <span class="n">element</span><span class="p">:</span> <span class="s1">'ReadFromBigQueryRequest'</span><span class="p">):</span> |
| <span class="n">location</span> <span class="o">=</span> <span class="n">bq</span><span class="o">.</span><span class="n">get_query_location</span><span class="p">(</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_get_project</span><span class="p">(),</span> <span class="n">element</span><span class="o">.</span><span class="n">query</span><span class="p">,</span> <span class="ow">not</span> <span class="n">element</span><span class="o">.</span><span class="n">use_standard_sql</span><span class="p">)</span> |
| <span class="n">bq</span><span class="o">.</span><span class="n">create_temporary_dataset</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_get_project</span><span class="p">(),</span> <span class="n">location</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">_clean_temporary_dataset</span><span class="p">(</span> |
| <span class="bp">self</span><span class="p">,</span> |
| <span class="n">bq</span><span class="p">:</span> <span class="n">bigquery_tools</span><span class="o">.</span><span class="n">BigQueryWrapper</span><span class="p">,</span> |
| <span class="n">element</span><span class="p">:</span> <span class="s1">'ReadFromBigQueryRequest'</span><span class="p">):</span> |
| <span class="n">bq</span><span class="o">.</span><span class="n">clean_up_temporary_dataset</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_get_project</span><span class="p">())</span> |
| |
| <span class="k">def</span> <span class="nf">_execute_query</span><span class="p">(</span> |
| <span class="bp">self</span><span class="p">,</span> |
| <span class="n">bq</span><span class="p">:</span> <span class="n">bigquery_tools</span><span class="o">.</span><span class="n">BigQueryWrapper</span><span class="p">,</span> |
| <span class="n">element</span><span class="p">:</span> <span class="s1">'ReadFromBigQueryRequest'</span><span class="p">):</span> |
| <span class="n">query_job_name</span> <span class="o">=</span> <span class="n">bigquery_tools</span><span class="o">.</span><span class="n">generate_bq_job_name</span><span class="p">(</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_job_name</span><span class="p">,</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_source_uuid</span><span class="p">,</span> |
| <span class="n">bigquery_tools</span><span class="o">.</span><span class="n">BigQueryJobTypes</span><span class="o">.</span><span class="n">QUERY</span><span class="p">,</span> |
| <span class="s1">'</span><span class="si">%s</span><span class="s1">_</span><span class="si">%s</span><span class="s1">'</span> <span class="o">%</span> <span class="p">(</span><span class="nb">int</span><span class="p">(</span><span class="n">time</span><span class="o">.</span><span class="n">time</span><span class="p">()),</span> <span class="n">random</span><span class="o">.</span><span class="n">randint</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="mi">1000</span><span class="p">)))</span> |
| <span class="n">job</span> <span class="o">=</span> <span class="n">bq</span><span class="o">.</span><span class="n">_start_query_job</span><span class="p">(</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_get_project</span><span class="p">(),</span> |
| <span class="n">element</span><span class="o">.</span><span class="n">query</span><span class="p">,</span> |
| <span class="ow">not</span> <span class="n">element</span><span class="o">.</span><span class="n">use_standard_sql</span><span class="p">,</span> |
| <span class="n">element</span><span class="o">.</span><span class="n">flatten_results</span><span class="p">,</span> |
| <span class="n">job_id</span><span class="o">=</span><span class="n">query_job_name</span><span class="p">,</span> |
| <span class="n">priority</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">query_priority</span><span class="p">,</span> |
| <span class="n">kms_key</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">kms_key</span><span class="p">,</span> |
| <span class="n">job_labels</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_get_bq_metadata</span><span class="p">()</span><span class="o">.</span><span class="n">add_additional_bq_job_labels</span><span class="p">(</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">bigquery_job_labels</span><span class="p">))</span> |
| <span class="n">job_ref</span> <span class="o">=</span> <span class="n">job</span><span class="o">.</span><span class="n">jobReference</span> |
| <span class="n">bq</span><span class="o">.</span><span class="n">wait_for_bq_job</span><span class="p">(</span><span class="n">job_ref</span><span class="p">,</span> <span class="n">max_retries</span><span class="o">=</span><span class="mi">0</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">bq</span><span class="o">.</span><span class="n">_get_temp_table</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_get_project</span><span class="p">())</span> |
| |
| <span class="k">def</span> <span class="nf">_export_files</span><span class="p">(</span> |
| <span class="bp">self</span><span class="p">,</span> |
| <span class="n">bq</span><span class="p">:</span> <span class="n">bigquery_tools</span><span class="o">.</span><span class="n">BigQueryWrapper</span><span class="p">,</span> |
| <span class="n">element</span><span class="p">:</span> <span class="s1">'ReadFromBigQueryRequest'</span><span class="p">,</span> |
| <span class="n">table_reference</span><span class="p">:</span> <span class="n">TableReference</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""Runs a BigQuery export job.</span> |
| |
| <span class="sd"> Returns:</span> |
| <span class="sd"> bigquery.TableSchema instance, a list of FileMetadata instances</span> |
| <span class="sd"> """</span> |
| <span class="n">job_labels</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_get_bq_metadata</span><span class="p">()</span><span class="o">.</span><span class="n">add_additional_bq_job_labels</span><span class="p">(</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">bigquery_job_labels</span><span class="p">)</span> |
| <span class="n">export_job_name</span> <span class="o">=</span> <span class="n">bigquery_tools</span><span class="o">.</span><span class="n">generate_bq_job_name</span><span class="p">(</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_job_name</span><span class="p">,</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_source_uuid</span><span class="p">,</span> |
| <span class="n">bigquery_tools</span><span class="o">.</span><span class="n">BigQueryJobTypes</span><span class="o">.</span><span class="n">EXPORT</span><span class="p">,</span> |
| <span class="n">element</span><span class="o">.</span><span class="n">obj_id</span><span class="p">)</span> |
| <span class="n">temp_location</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">options</span><span class="o">.</span><span class="n">view_as</span><span class="p">(</span><span class="n">GoogleCloudOptions</span><span class="p">)</span><span class="o">.</span><span class="n">temp_location</span> |
| <span class="n">gcs_location</span> <span class="o">=</span> <span class="n">bigquery_export_destination_uri</span><span class="p">(</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">gcs_location</span><span class="p">,</span> |
| <span class="n">temp_location</span><span class="p">,</span> |
| <span class="s1">'</span><span class="si">%s%s</span><span class="s1">'</span> <span class="o">%</span> <span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_source_uuid</span><span class="p">,</span> <span class="n">element</span><span class="o">.</span><span class="n">obj_id</span><span class="p">))</span> |
| <span class="k">try</span><span class="p">:</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">use_json_exports</span><span class="p">:</span> |
| <span class="n">job_ref</span> <span class="o">=</span> <span class="n">bq</span><span class="o">.</span><span class="n">perform_extract_job</span><span class="p">([</span><span class="n">gcs_location</span><span class="p">],</span> |
| <span class="n">export_job_name</span><span class="p">,</span> |
| <span class="n">table_reference</span><span class="p">,</span> |
| <span class="n">bigquery_tools</span><span class="o">.</span><span class="n">FileFormat</span><span class="o">.</span><span class="n">JSON</span><span class="p">,</span> |
| <span class="n">project</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_get_project</span><span class="p">(),</span> |
| <span class="n">job_labels</span><span class="o">=</span><span class="n">job_labels</span><span class="p">,</span> |
| <span class="n">include_header</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">job_ref</span> <span class="o">=</span> <span class="n">bq</span><span class="o">.</span><span class="n">perform_extract_job</span><span class="p">([</span><span class="n">gcs_location</span><span class="p">],</span> |
| <span class="n">export_job_name</span><span class="p">,</span> |
| <span class="n">table_reference</span><span class="p">,</span> |
| <span class="n">bigquery_tools</span><span class="o">.</span><span class="n">FileFormat</span><span class="o">.</span><span class="n">AVRO</span><span class="p">,</span> |
| <span class="n">project</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_get_project</span><span class="p">(),</span> |
| <span class="n">include_header</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> |
| <span class="n">job_labels</span><span class="o">=</span><span class="n">job_labels</span><span class="p">,</span> |
| <span class="n">use_avro_logical_types</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span> |
| <span class="n">bq</span><span class="o">.</span><span class="n">wait_for_bq_job</span><span class="p">(</span><span class="n">job_ref</span><span class="p">)</span> |
| <span class="k">except</span> <span class="ne">Exception</span> <span class="k">as</span> <span class="n">exn</span><span class="p">:</span> <span class="c1"># pylint: disable=broad-except</span> |
| <span class="c1"># The error messages thrown in this case are generic and misleading,</span> |
| <span class="c1"># so leave this breadcrumb in case it's the root cause.</span> |
| <span class="n">logging</span><span class="o">.</span><span class="n">warning</span><span class="p">(</span> |
| <span class="s2">"Error exporting table: </span><span class="si">%s</span><span class="s2">. "</span> |
| <span class="s2">"Note that external tables cannot be exported: "</span> |
| <span class="s2">"https://cloud.google.com/bigquery/docs/external-tables"</span> |
| <span class="s2">"#external_table_limitations"</span><span class="p">,</span> |
| <span class="n">exn</span><span class="p">)</span> |
| <span class="k">raise</span> |
| <span class="n">metadata_list</span> <span class="o">=</span> <span class="n">FileSystems</span><span class="o">.</span><span class="n">match</span><span class="p">([</span><span class="n">gcs_location</span><span class="p">])[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">metadata_list</span> |
| |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">table_reference</span><span class="p">,</span> <span class="n">ValueProvider</span><span class="p">):</span> |
| <span class="n">table_ref</span> <span class="o">=</span> <span class="n">bigquery_tools</span><span class="o">.</span><span class="n">parse_table_reference</span><span class="p">(</span> |
| <span class="n">element</span><span class="o">.</span><span class="n">table</span><span class="p">,</span> <span class="n">project</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_get_project</span><span class="p">())</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">table_ref</span> <span class="o">=</span> <span class="n">table_reference</span> |
| <span class="n">table</span> <span class="o">=</span> <span class="n">bq</span><span class="o">.</span><span class="n">get_table</span><span class="p">(</span> |
| <span class="n">table_ref</span><span class="o">.</span><span class="n">projectId</span><span class="p">,</span> <span class="n">table_ref</span><span class="o">.</span><span class="n">datasetId</span><span class="p">,</span> <span class="n">table_ref</span><span class="o">.</span><span class="n">tableId</span><span class="p">)</span> |
| |
| <span class="k">return</span> <span class="n">table</span><span class="o">.</span><span class="n">schema</span><span class="p">,</span> <span class="n">metadata_list</span> |
| |
| <span class="k">def</span> <span class="nf">_get_project</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""Returns the project that queries and exports will be billed to."""</span> |
| |
| <span class="n">project</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">options</span><span class="o">.</span><span class="n">view_as</span><span class="p">(</span><span class="n">GoogleCloudOptions</span><span class="p">)</span><span class="o">.</span><span class="n">project</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">project</span><span class="p">,</span> <span class="n">ValueProvider</span><span class="p">):</span> |
| <span class="n">project</span> <span class="o">=</span> <span class="n">project</span><span class="o">.</span><span class="n">get</span><span class="p">()</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="n">project</span><span class="p">:</span> |
| <span class="n">project</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">project</span> |
| <span class="k">return</span> <span class="n">project</span> |
| |
| |
| <span class="n">FieldSchema</span> <span class="o">=</span> <span class="n">collections</span><span class="o">.</span><span class="n">namedtuple</span><span class="p">(</span><span class="s1">'FieldSchema'</span><span class="p">,</span> <span class="s1">'fields mode name type'</span><span class="p">)</span> |
| |
| |
| <span class="k">class</span> <span class="nc">_JsonToDictCoder</span><span class="p">(</span><span class="n">coders</span><span class="o">.</span><span class="n">Coder</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""A coder for a JSON string to a Python dict."""</span> |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">table_schema</span><span class="p">):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">fields</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_convert_to_tuple</span><span class="p">(</span><span class="n">table_schema</span><span class="o">.</span><span class="n">fields</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_converters</span> <span class="o">=</span> <span class="p">{</span> |
| <span class="s1">'INTEGER'</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> |
| <span class="s1">'INT64'</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> |
| <span class="s1">'FLOAT'</span><span class="p">:</span> <span class="nb">float</span><span class="p">,</span> |
| <span class="s1">'FLOAT64'</span><span class="p">:</span> <span class="nb">float</span><span class="p">,</span> |
| <span class="s1">'NUMERIC'</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">_to_decimal</span><span class="p">,</span> |
| <span class="s1">'BYTES'</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">_to_bytes</span><span class="p">,</span> |
| <span class="p">}</span> |
| |
| <span class="nd">@staticmethod</span> |
| <span class="k">def</span> <span class="nf">_to_decimal</span><span class="p">(</span><span class="n">value</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">decimal</span><span class="o">.</span><span class="n">Decimal</span><span class="p">(</span><span class="n">value</span><span class="p">)</span> |
| |
| <span class="nd">@staticmethod</span> |
| <span class="k">def</span> <span class="nf">_to_bytes</span><span class="p">(</span><span class="n">value</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""Converts value from str to bytes."""</span> |
| <span class="k">return</span> <span class="n">value</span><span class="o">.</span><span class="n">encode</span><span class="p">(</span><span class="s1">'utf-8'</span><span class="p">)</span> |
| |
| <span class="nd">@classmethod</span> |
| <span class="k">def</span> <span class="nf">_convert_to_tuple</span><span class="p">(</span><span class="bp">cls</span><span class="p">,</span> <span class="n">table_field_schemas</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""Recursively converts the list of TableFieldSchema instances to the</span> |
| <span class="sd"> list of tuples to prevent errors when pickling and unpickling</span> |
| <span class="sd"> TableFieldSchema instances.</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="n">table_field_schemas</span><span class="p">:</span> |
| <span class="k">return</span> <span class="p">[]</span> |
| |
| <span class="k">return</span> <span class="p">[</span> |
| <span class="n">FieldSchema</span><span class="p">(</span><span class="bp">cls</span><span class="o">.</span><span class="n">_convert_to_tuple</span><span class="p">(</span><span class="n">x</span><span class="o">.</span><span class="n">fields</span><span class="p">),</span> <span class="n">x</span><span class="o">.</span><span class="n">mode</span><span class="p">,</span> <span class="n">x</span><span class="o">.</span><span class="n">name</span><span class="p">,</span> <span class="n">x</span><span class="o">.</span><span class="n">type</span><span class="p">)</span> |
| <span class="k">for</span> <span class="n">x</span> <span class="ow">in</span> <span class="n">table_field_schemas</span> |
| <span class="p">]</span> |
| |
| <span class="k">def</span> <span class="nf">decode</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span> |
| <span class="n">value</span> <span class="o">=</span> <span class="n">json</span><span class="o">.</span><span class="n">loads</span><span class="p">(</span><span class="n">value</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">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_decode_row</span><span class="p">(</span><span class="n">value</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">fields</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">_decode_row</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">row</span><span class="p">:</span> <span class="n">Dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Any</span><span class="p">],</span> <span class="n">schema_fields</span><span class="p">:</span> <span class="n">List</span><span class="p">[</span><span class="n">FieldSchema</span><span class="p">]):</span> |
| <span class="k">for</span> <span class="n">field</span> <span class="ow">in</span> <span class="n">schema_fields</span><span class="p">:</span> |
| <span class="k">if</span> <span class="n">field</span><span class="o">.</span><span class="n">name</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">row</span><span class="p">:</span> |
| <span class="c1"># The field exists in the schema, but it doesn't exist in this row.</span> |
| <span class="c1"># It probably means its value was null, as the extract to JSON job</span> |
| <span class="c1"># doesn't preserve null fields</span> |
| <span class="n">row</span><span class="p">[</span><span class="n">field</span><span class="o">.</span><span class="n">name</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span> |
| <span class="k">continue</span> |
| |
| <span class="k">if</span> <span class="n">field</span><span class="o">.</span><span class="n">mode</span> <span class="o">==</span> <span class="s1">'REPEATED'</span><span class="p">:</span> |
| <span class="k">for</span> <span class="n">i</span><span class="p">,</span> <span class="n">elem</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">(</span><span class="n">row</span><span class="p">[</span><span class="n">field</span><span class="o">.</span><span class="n">name</span><span class="p">]):</span> |
| <span class="n">row</span><span class="p">[</span><span class="n">field</span><span class="o">.</span><span class="n">name</span><span class="p">][</span><span class="n">i</span><span class="p">]</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_decode_data</span><span class="p">(</span><span class="n">elem</span><span class="p">,</span> <span class="n">field</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">row</span><span class="p">[</span><span class="n">field</span><span class="o">.</span><span class="n">name</span><span class="p">]</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_decode_data</span><span class="p">(</span><span class="n">row</span><span class="p">[</span><span class="n">field</span><span class="o">.</span><span class="n">name</span><span class="p">],</span> <span class="n">field</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">row</span> |
| |
| <span class="k">def</span> <span class="nf">_decode_data</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">obj</span><span class="p">:</span> <span class="n">Any</span><span class="p">,</span> <span class="n">field</span><span class="p">:</span> <span class="n">FieldSchema</span><span class="p">):</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="n">field</span><span class="o">.</span><span class="n">fields</span><span class="p">:</span> |
| <span class="k">try</span><span class="p">:</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_converters</span><span class="p">[</span><span class="n">field</span><span class="o">.</span><span class="n">type</span><span class="p">](</span><span class="n">obj</span><span class="p">)</span> |
| <span class="k">except</span> <span class="ne">KeyError</span><span class="p">:</span> |
| <span class="c1"># No need to do any conversion</span> |
| <span class="k">return</span> <span class="n">obj</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_decode_row</span><span class="p">(</span><span class="n">obj</span><span class="p">,</span> <span class="n">field</span><span class="o">.</span><span class="n">fields</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">is_deterministic</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="k">return</span> <span class="kc">True</span> |
| |
| <span class="k">def</span> <span class="nf">to_type_hint</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="k">return</span> <span class="nb">dict</span> |
| </pre></div> |
| |
| </div> |
| |
| </div> |
| <footer> |
| |
| |
| <hr/> |
| |
| <div role="contentinfo"> |
| <p> |
| © Copyright |
| |
| </p> |
| </div> |
| Built with <a href="http://sphinx-doc.org/">Sphinx</a> using a <a href="https://github.com/rtfd/sphinx_rtd_theme">theme</a> provided by <a href="https://readthedocs.org">Read the Docs</a>. |
| |
| </footer> |
| |
| </div> |
| </div> |
| |
| </section> |
| |
| </div> |
| |
| |
| |
| <script type="text/javascript"> |
| jQuery(function () { |
| SphinxRtdTheme.Navigation.enable(true); |
| }); |
| </script> |
| |
| |
| |
| |
| |
| |
| </body> |
| </html> |