| |
| |
| <!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 — Apache Beam 2.38.0 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"> |
| 2.38.0 |
| </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.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> |
| </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</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</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">"""BigQuery sources and sinks.</span> |
| |
| <span class="sd">This module implements reading from and writing to BigQuery tables. It relies</span> |
| <span class="sd">on several classes exposed by the BigQuery API: TableSchema, TableFieldSchema,</span> |
| <span class="sd">TableRow, and TableCell. The default mode is to return table rows read from a</span> |
| <span class="sd">BigQuery source as dictionaries. Similarly a Write transform to a BigQuerySink</span> |
| <span class="sd">accepts PCollections of dictionaries. This is done for more convenient</span> |
| <span class="sd">programming. If desired, the native TableRow objects can be used throughout to</span> |
| <span class="sd">represent rows (use an instance of TableRowJsonCoder as a coder argument when</span> |
| <span class="sd">creating the sources or sinks respectively).</span> |
| |
| <span class="sd">Also, for programming convenience, instances of TableReference and TableSchema</span> |
| <span class="sd">have a string representation that can be used for the corresponding arguments:</span> |
| |
| <span class="sd"> - TableReference can be a PROJECT:DATASET.TABLE or DATASET.TABLE string.</span> |
| <span class="sd"> - TableSchema can be a NAME:TYPE{,NAME:TYPE}* string</span> |
| <span class="sd"> (e.g. 'month:STRING,event_count:INTEGER').</span> |
| |
| <span class="sd">The syntax supported is described here:</span> |
| <span class="sd">https://cloud.google.com/bigquery/bq-command-line-tool-quickstart</span> |
| |
| <span class="sd">BigQuery sources can be used as main inputs or side inputs. A main input</span> |
| <span class="sd">(common case) is expected to be massive and will be split into manageable chunks</span> |
| <span class="sd">and processed in parallel. Side inputs are expected to be small and will be read</span> |
| <span class="sd">completely every time a ParDo DoFn gets executed. In the example below the</span> |
| <span class="sd">lambda function implementing the DoFn for the Map transform will get on each</span> |
| <span class="sd">call *one* row of the main table and *all* rows of the side table. The runner</span> |
| <span class="sd">may use some caching techniques to share the side inputs between calls in order</span> |
| <span class="sd">to avoid excessive reading:::</span> |
| |
| <span class="sd"> main_table = pipeline | 'VeryBig' >> beam.io.ReadFromBigQuery(...)</span> |
| <span class="sd"> side_table = pipeline | 'NotBig' >> beam.io.ReadFromBigQuery(...)</span> |
| <span class="sd"> results = (</span> |
| <span class="sd"> main_table</span> |
| <span class="sd"> | 'ProcessData' >> beam.Map(</span> |
| <span class="sd"> lambda element, side_input: ..., AsList(side_table)))</span> |
| |
| <span class="sd">There is no difference in how main and side inputs are read. What makes the</span> |
| <span class="sd">side_table a 'side input' is the AsList wrapper used when passing the table</span> |
| <span class="sd">as a parameter to the Map transform. AsList signals to the execution framework</span> |
| <span class="sd">that its input should be made available whole.</span> |
| |
| <span class="sd">The main and side inputs are implemented differently. Reading a BigQuery table</span> |
| <span class="sd">as main input entails exporting the table to a set of GCS files (in AVRO or in</span> |
| <span class="sd">JSON format) and then processing those files.</span> |
| |
| <span class="sd">Users may provide a query to read from rather than reading all of a BigQuery</span> |
| <span class="sd">table. If specified, the result obtained by executing the specified query will</span> |
| <span class="sd">be used as the data of the input transform.::</span> |
| |
| <span class="sd"> query_results = pipeline | beam.io.gcp.bigquery.ReadFromBigQuery(</span> |
| <span class="sd"> query='SELECT year, mean_temp FROM samples.weather_stations')</span> |
| |
| <span class="sd">When creating a BigQuery input transform, users should provide either a query</span> |
| <span class="sd">or a table. Pipeline construction will fail with a validation error if neither</span> |
| <span class="sd">or both are specified.</span> |
| |
| <span class="sd">When reading via `ReadFromBigQuery`, bytes are returned decoded as bytes.</span> |
| <span class="sd">This is due to the fact that ReadFromBigQuery uses Avro exports by default.</span> |
| <span class="sd">When reading from BigQuery using `apache_beam.io.BigQuerySource`, bytes are</span> |
| <span class="sd">returned as base64-encoded bytes. To get base64-encoded bytes using</span> |
| <span class="sd">`ReadFromBigQuery`, you can use the flag `use_json_exports` to export</span> |
| <span class="sd">data as JSON, and receive base64-encoded bytes.</span> |
| |
| <span class="sd">ReadAllFromBigQuery</span> |
| <span class="sd">-------------------</span> |
| <span class="sd">Beam 2.27.0 introduces a new transform called `ReadAllFromBigQuery` which</span> |
| <span class="sd">allows you to define table and query reads from BigQuery at pipeline</span> |
| <span class="sd">runtime.:::</span> |
| |
| <span class="sd"> read_requests = p | beam.Create([</span> |
| <span class="sd"> ReadFromBigQueryRequest(query='SELECT * FROM mydataset.mytable'),</span> |
| <span class="sd"> ReadFromBigQueryRequest(table='myproject.mydataset.mytable')])</span> |
| <span class="sd"> results = read_requests | ReadAllFromBigQuery()</span> |
| |
| <span class="sd">A good application for this transform is in streaming pipelines to</span> |
| <span class="sd">refresh a side input coming from BigQuery. This would work like so:::</span> |
| |
| <span class="sd"> side_input = (</span> |
| <span class="sd"> p</span> |
| <span class="sd"> | 'PeriodicImpulse' >> PeriodicImpulse(</span> |
| <span class="sd"> first_timestamp, last_timestamp, interval, True)</span> |
| <span class="sd"> | 'MapToReadRequest' >> beam.Map(</span> |
| <span class="sd"> lambda x: ReadFromBigQueryRequest(table='dataset.table'))</span> |
| <span class="sd"> | beam.io.ReadAllFromBigQuery())</span> |
| <span class="sd"> main_input = (</span> |
| <span class="sd"> p</span> |
| <span class="sd"> | 'MpImpulse' >> beam.Create(sample_main_input_elements)</span> |
| <span class="sd"> |</span> |
| <span class="sd"> 'MapMpToTimestamped' >> beam.Map(lambda src: TimestampedValue(src, src))</span> |
| <span class="sd"> | 'WindowMpInto' >> beam.WindowInto(</span> |
| <span class="sd"> window.FixedWindows(main_input_windowing_interval)))</span> |
| <span class="sd"> result = (</span> |
| <span class="sd"> main_input</span> |
| <span class="sd"> | 'ApplyCrossJoin' >> beam.FlatMap(</span> |
| <span class="sd"> cross_join, rights=beam.pvalue.AsIter(side_input)))</span> |
| |
| <span class="sd">**Note**: This transform is supported on Portable and Dataflow v2 runners.</span> |
| |
| <span class="sd">**Note**: This transform does not currently clean up temporary datasets</span> |
| <span class="sd">created for its execution. (BEAM-11359)</span> |
| |
| <span class="sd">Writing Data to BigQuery</span> |
| <span class="sd">========================</span> |
| |
| <span class="sd">The `WriteToBigQuery` transform is the recommended way of writing data to</span> |
| <span class="sd">BigQuery. It supports a large set of parameters to customize how you'd like to</span> |
| <span class="sd">write to BigQuery.</span> |
| |
| <span class="sd">Table References</span> |
| <span class="sd">----------------</span> |
| |
| <span class="sd">This transform allows you to provide static `project`, `dataset` and `table`</span> |
| <span class="sd">parameters which point to a specific BigQuery table to be created. The `table`</span> |
| <span class="sd">parameter can also be a dynamic parameter (i.e. a callable), which receives an</span> |
| <span class="sd">element to be written to BigQuery, and returns the table that that element</span> |
| <span class="sd">should be sent to.</span> |
| |
| <span class="sd">You may also provide a tuple of PCollectionView elements to be passed as side</span> |
| <span class="sd">inputs to your callable. For example, suppose that one wishes to send</span> |
| <span class="sd">events of different types to different tables, and the table names are</span> |
| <span class="sd">computed at pipeline runtime, one may do something like the following::</span> |
| |
| <span class="sd"> with Pipeline() as p:</span> |
| <span class="sd"> elements = (p | beam.Create([</span> |
| <span class="sd"> {'type': 'error', 'timestamp': '12:34:56', 'message': 'bad'},</span> |
| <span class="sd"> {'type': 'user_log', 'timestamp': '12:34:59', 'query': 'flu symptom'},</span> |
| <span class="sd"> ]))</span> |
| |
| <span class="sd"> table_names = (p | beam.Create([</span> |
| <span class="sd"> ('error', 'my_project:dataset1.error_table_for_today'),</span> |
| <span class="sd"> ('user_log', 'my_project:dataset1.query_table_for_today'),</span> |
| <span class="sd"> ])</span> |
| |
| <span class="sd"> table_names_dict = beam.pvalue.AsDict(table_names)</span> |
| |
| <span class="sd"> elements | beam.io.gcp.bigquery.WriteToBigQuery(</span> |
| <span class="sd"> table=lambda row, table_dict: table_dict[row['type']],</span> |
| <span class="sd"> table_side_inputs=(table_names_dict,))</span> |
| |
| <span class="sd">In the example above, the `table_dict` argument passed to the function in</span> |
| <span class="sd">`table_dict` is the side input coming from `table_names_dict`, which is passed</span> |
| <span class="sd">as part of the `table_side_inputs` argument.</span> |
| |
| <span class="sd">Schemas</span> |
| <span class="sd">---------</span> |
| |
| <span class="sd">This transform also allows you to provide a static or dynamic `schema`</span> |
| <span class="sd">parameter (i.e. a callable).</span> |
| |
| <span class="sd">If providing a callable, this should take in a table reference (as returned by</span> |
| <span class="sd">the `table` parameter), and return the corresponding schema for that table.</span> |
| <span class="sd">This allows to provide different schemas for different tables::</span> |
| |
| <span class="sd"> def compute_table_name(row):</span> |
| <span class="sd"> ...</span> |
| |
| <span class="sd"> errors_schema = {'fields': [</span> |
| <span class="sd"> {'name': 'type', 'type': 'STRING', 'mode': 'NULLABLE'},</span> |
| <span class="sd"> {'name': 'message', 'type': 'STRING', 'mode': 'NULLABLE'}]}</span> |
| <span class="sd"> queries_schema = {'fields': [</span> |
| <span class="sd"> {'name': 'type', 'type': 'STRING', 'mode': 'NULLABLE'},</span> |
| <span class="sd"> {'name': 'query', 'type': 'STRING', 'mode': 'NULLABLE'}]}</span> |
| |
| <span class="sd"> with Pipeline() as p:</span> |
| <span class="sd"> elements = (p | beam.Create([</span> |
| <span class="sd"> {'type': 'error', 'timestamp': '12:34:56', 'message': 'bad'},</span> |
| <span class="sd"> {'type': 'user_log', 'timestamp': '12:34:59', 'query': 'flu symptom'},</span> |
| <span class="sd"> ]))</span> |
| |
| <span class="sd"> elements | beam.io.gcp.bigquery.WriteToBigQuery(</span> |
| <span class="sd"> table=compute_table_name,</span> |
| <span class="sd"> schema=lambda table: (errors_schema</span> |
| <span class="sd"> if 'errors' in table</span> |
| <span class="sd"> else queries_schema))</span> |
| |
| <span class="sd">It may be the case that schemas are computed at pipeline runtime. In cases</span> |
| <span class="sd">like these, one can also provide a `schema_side_inputs` parameter, which is</span> |
| <span class="sd">a tuple of PCollectionViews to be passed to the schema callable (much like</span> |
| <span class="sd">the `table_side_inputs` parameter).</span> |
| |
| <span class="sd">Additional Parameters for BigQuery Tables</span> |
| <span class="sd">-----------------------------------------</span> |
| |
| <span class="sd">This sink is able to create tables in BigQuery if they don't already exist. It</span> |
| <span class="sd">also relies on creating temporary tables when performing file loads.</span> |
| |
| <span class="sd">The WriteToBigQuery transform creates tables using the BigQuery API by</span> |
| <span class="sd">inserting a load job (see the API reference [1]), or by inserting a new table</span> |
| <span class="sd">(see the API reference for that [2][3]).</span> |
| |
| <span class="sd">When creating a new BigQuery table, there are a number of extra parameters</span> |
| <span class="sd">that one may need to specify. For example, clustering, partitioning, data</span> |
| <span class="sd">encoding, etc. It is possible to provide these additional parameters by</span> |
| <span class="sd">passing a Python dictionary as `additional_bq_parameters` to the transform.</span> |
| <span class="sd">As an example, to create a table that has specific partitioning, and</span> |
| <span class="sd">clustering properties, one would do the following::</span> |
| |
| <span class="sd"> additional_bq_parameters = {</span> |
| <span class="sd"> 'timePartitioning': {'type': 'DAY'},</span> |
| <span class="sd"> 'clustering': {'fields': ['country']}}</span> |
| <span class="sd"> with Pipeline() as p:</span> |
| <span class="sd"> elements = (p | beam.Create([</span> |
| <span class="sd"> {'country': 'mexico', 'timestamp': '12:34:56', 'query': 'acapulco'},</span> |
| <span class="sd"> {'country': 'canada', 'timestamp': '12:34:59', 'query': 'influenza'},</span> |
| <span class="sd"> ]))</span> |
| |
| <span class="sd"> elements | beam.io.gcp.bigquery.WriteToBigQuery(</span> |
| <span class="sd"> table='project_name1:dataset_2.query_events_table',</span> |
| <span class="sd"> additional_bq_parameters=additional_bq_parameters)</span> |
| |
| <span class="sd">Much like the schema case, the parameter with `additional_bq_parameters` can</span> |
| <span class="sd">also take a callable that receives a table reference.</span> |
| |
| |
| <span class="sd">[1] https://cloud.google.com/bigquery/docs/reference/rest/v2/Job\</span> |
| <span class="sd"> #jobconfigurationload</span> |
| <span class="sd">[2] https://cloud.google.com/bigquery/docs/reference/rest/v2/tables/insert</span> |
| <span class="sd">[3] https://cloud.google.com/bigquery/docs/reference/rest/v2/tables#resource</span> |
| |
| |
| <span class="sd">*** Short introduction to BigQuery concepts ***</span> |
| <span class="sd">Tables have rows (TableRow) and each row has cells (TableCell).</span> |
| <span class="sd">A table has a schema (TableSchema), which in turn describes the schema of each</span> |
| <span class="sd">cell (TableFieldSchema). The terms field and cell are used interchangeably.</span> |
| |
| <span class="sd">TableSchema: Describes the schema (types and order) for values in each row.</span> |
| <span class="sd"> Has one attribute, 'field', which is list of TableFieldSchema objects.</span> |
| |
| <span class="sd">TableFieldSchema: Describes the schema (type, name) for one field.</span> |
| <span class="sd"> Has several attributes, including 'name' and 'type'. Common values for</span> |
| <span class="sd"> the type attribute are: 'STRING', 'INTEGER', 'FLOAT', 'BOOLEAN', 'NUMERIC',</span> |
| <span class="sd"> 'GEOGRAPHY'.</span> |
| <span class="sd"> All possible values are described at:</span> |
| <span class="sd"> https://cloud.google.com/bigquery/docs/reference/standard-sql/data-types</span> |
| |
| <span class="sd">TableRow: Holds all values in a table row. Has one attribute, 'f', which is a</span> |
| <span class="sd"> list of TableCell instances.</span> |
| |
| <span class="sd">TableCell: Holds the value for one cell (or field). Has one attribute,</span> |
| <span class="sd"> 'v', which is a JsonValue instance. This class is defined in</span> |
| <span class="sd"> apitools.base.py.extra_types.py module.</span> |
| |
| <span class="sd">As of Beam 2.7.0, the NUMERIC data type is supported. This data type supports</span> |
| <span class="sd">high-precision decimal numbers (precision of 38 digits, scale of 9 digits).</span> |
| <span class="sd">The GEOGRAPHY data type works with Well-Known Text (See</span> |
| <span class="sd">https://en.wikipedia.org/wiki/Well-known_text) format for reading and writing</span> |
| <span class="sd">to BigQuery.</span> |
| <span class="sd">BigQuery IO requires values of BYTES datatype to be encoded using base64</span> |
| <span class="sd">encoding when writing to BigQuery.</span> |
| <span class="sd">"""</span> |
| |
| <span class="c1"># pytype: skip-file</span> |
| |
| <span class="kn">import</span> <span class="nn">collections</span> |
| <span class="kn">import</span> <span class="nn">io</span> |
| <span class="kn">import</span> <span class="nn">itertools</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">Dict</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">fastavro</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</span> <span class="kn">import</span> <span class="n">coders</span> |
| <span class="kn">from</span> <span class="nn">apache_beam</span> <span class="kn">import</span> <span class="n">pvalue</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.internal.gcp.json_value</span> <span class="kn">import</span> <span class="n">from_json_value</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.internal.gcp.json_value</span> <span class="kn">import</span> <span class="n">to_json_value</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.io</span> <span class="kn">import</span> <span class="n">range_trackers</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="k">as</span> <span class="n">create_avro_source</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.io.filesystems</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.gcp.bigquery_read_internal</span> <span class="kn">import</span> <span class="n">_BigQueryReadSplit</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.io.gcp.bigquery_read_internal</span> <span class="kn">import</span> <span class="n">_JsonToDictCoder</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.io.gcp.bigquery_read_internal</span> <span class="kn">import</span> <span class="n">_PassThroughThenCleanup</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.io.gcp.bigquery_read_internal</span> <span class="kn">import</span> <span class="n">_PassThroughThenCleanupTempDatasets</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.io.gcp.bigquery_read_internal</span> <span class="kn">import</span> <span class="n">bigquery_export_destination_uri</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.io.gcp.bigquery_tools</span> <span class="kn">import</span> <span class="n">RetryStrategy</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.io.gcp.internal.clients</span> <span class="kn">import</span> <span class="n">bigquery</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.iobase</span> <span class="kn">import</span> <span class="n">RangeTracker</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.io.iobase</span> <span class="kn">import</span> <span class="n">SDFBoundedSourceReader</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.io.iobase</span> <span class="kn">import</span> <span class="n">SourceBundle</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="k">as</span> <span class="n">TextSource</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.metrics</span> <span class="kn">import</span> <span class="n">Metrics</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.options</span> <span class="kn">import</span> <span class="n">value_provider</span> <span class="k">as</span> <span class="n">vp</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.options.pipeline_options</span> <span class="kn">import</span> <span class="n">DebugOptions</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">StandardOptions</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.options.value_provider</span> <span class="kn">import</span> <span class="n">StaticValueProvider</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.options.value_provider</span> <span class="kn">import</span> <span class="n">check_accessible</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.runners.dataflow.native_io</span> <span class="kn">import</span> <span class="n">iobase</span> <span class="k">as</span> <span class="n">dataflow_io</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.transforms</span> <span class="kn">import</span> <span class="n">DoFn</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.transforms</span> <span class="kn">import</span> <span class="n">ParDo</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="kn">from</span> <span class="nn">apache_beam.transforms.display</span> <span class="kn">import</span> <span class="n">DisplayDataItem</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.transforms.sideinputs</span> <span class="kn">import</span> <span class="n">SIDE_INPUT_PREFIX</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.transforms.sideinputs</span> <span class="kn">import</span> <span class="n">get_sideinput_index</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.transforms.util</span> <span class="kn">import</span> <span class="n">ReshufflePerKey</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.transforms.window</span> <span class="kn">import</span> <span class="n">GlobalWindows</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.utils</span> <span class="kn">import</span> <span class="n">retry</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.utils.annotations</span> <span class="kn">import</span> <span class="n">deprecated</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.utils.annotations</span> <span class="kn">import</span> <span class="n">experimental</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> |
| |
| <span class="k">try</span><span class="p">:</span> |
| <span class="kn">import</span> <span class="nn">google.cloud.bigquery_storage_v1</span> <span class="k">as</span> <span class="nn">bq_storage</span> |
| <span class="k">except</span> <span class="ne">ImportError</span><span class="p">:</span> |
| <span class="n">_LOGGER</span><span class="o">.</span><span class="n">info</span><span class="p">(</span> |
| <span class="s1">'No module named google.cloud.bigquery_storage_v1. '</span> |
| <span class="s1">'As a result, the ReadFromBigQuery transform *CANNOT* be '</span> |
| <span class="s1">'used with `method=DIRECT_READ`.'</span><span class="p">)</span> |
| |
| <span class="n">__all__</span> <span class="o">=</span> <span class="p">[</span> |
| <span class="s1">'TableRowJsonCoder'</span><span class="p">,</span> |
| <span class="s1">'BigQueryDisposition'</span><span class="p">,</span> |
| <span class="s1">'BigQuerySource'</span><span class="p">,</span> |
| <span class="s1">'BigQuerySink'</span><span class="p">,</span> |
| <span class="s1">'BigQueryQueryPriority'</span><span class="p">,</span> |
| <span class="s1">'WriteToBigQuery'</span><span class="p">,</span> |
| <span class="s1">'ReadFromBigQuery'</span><span class="p">,</span> |
| <span class="s1">'ReadFromBigQueryRequest'</span><span class="p">,</span> |
| <span class="s1">'ReadAllFromBigQuery'</span><span class="p">,</span> |
| <span class="s1">'SCHEMA_AUTODETECT'</span><span class="p">,</span> |
| <span class="p">]</span> |
| <span class="sd">"""</span> |
| <span class="sd">Template for BigQuery jobs created by BigQueryIO. This template is:</span> |
| <span class="sd">`"beam_bq_job_{job_type}_{job_id}_{step_id}_{random}"`, where:</span> |
| |
| <span class="sd">- `job_type` represents the BigQuery job type (e.g. extract / copy / load /</span> |
| <span class="sd"> query).</span> |
| <span class="sd">- `job_id` is the Beam job name.</span> |
| <span class="sd">- `step_id` is a UUID representing the the Dataflow step that created the</span> |
| <span class="sd"> BQ job.</span> |
| <span class="sd">- `random` is a random string.</span> |
| |
| <span class="sd">NOTE: This job name template does not have backwards compatibility guarantees.</span> |
| <span class="sd">"""</span> |
| <span class="n">BQ_JOB_NAME_TEMPLATE</span> <span class="o">=</span> <span class="s2">"beam_bq_job_</span><span class="si">{job_type}</span><span class="s2">_</span><span class="si">{job_id}</span><span class="s2">_</span><span class="si">{step_id}{random}</span><span class="s2">"</span> |
| |
| |
| <span class="nd">@deprecated</span><span class="p">(</span><span class="n">since</span><span class="o">=</span><span class="s1">'2.11.0'</span><span class="p">,</span> <span class="n">current</span><span class="o">=</span><span class="s2">"bigquery_tools.parse_table_reference"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">_parse_table_reference</span><span class="p">(</span><span class="n">table</span><span class="p">,</span> <span class="n">dataset</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">project</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="k">return</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">table</span><span class="p">,</span> <span class="n">dataset</span><span class="p">,</span> <span class="n">project</span><span class="p">)</span> |
| |
| |
| <span class="nd">@deprecated</span><span class="p">(</span> |
| <span class="n">since</span><span class="o">=</span><span class="s1">'2.11.0'</span><span class="p">,</span> <span class="n">current</span><span class="o">=</span><span class="s2">"bigquery_tools.parse_table_schema_from_json"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">parse_table_schema_from_json</span><span class="p">(</span><span class="n">schema_string</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">bigquery_tools</span><span class="o">.</span><span class="n">parse_table_schema_from_json</span><span class="p">(</span><span class="n">schema_string</span><span class="p">)</span> |
| |
| |
| <span class="nd">@deprecated</span><span class="p">(</span><span class="n">since</span><span class="o">=</span><span class="s1">'2.11.0'</span><span class="p">,</span> <span class="n">current</span><span class="o">=</span><span class="s2">"bigquery_tools.default_encoder"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">default_encoder</span><span class="p">(</span><span class="n">obj</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">bigquery_tools</span><span class="o">.</span><span class="n">default_encoder</span><span class="p">(</span><span class="n">obj</span><span class="p">)</span> |
| |
| |
| <span class="nd">@deprecated</span><span class="p">(</span><span class="n">since</span><span class="o">=</span><span class="s1">'2.11.0'</span><span class="p">,</span> <span class="n">current</span><span class="o">=</span><span class="s2">"bigquery_tools.RowAsDictJsonCoder"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">RowAsDictJsonCoder</span><span class="p">(</span><span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">bigquery_tools</span><span class="o">.</span><span class="n">RowAsDictJsonCoder</span><span class="p">(</span><span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> |
| |
| |
| <span class="nd">@deprecated</span><span class="p">(</span><span class="n">since</span><span class="o">=</span><span class="s1">'2.11.0'</span><span class="p">,</span> <span class="n">current</span><span class="o">=</span><span class="s2">"bigquery_tools.BigQueryReader"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">BigQueryReader</span><span class="p">(</span><span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">bigquery_tools</span><span class="o">.</span><span class="n">BigQueryReader</span><span class="p">(</span><span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> |
| |
| |
| <span class="nd">@deprecated</span><span class="p">(</span><span class="n">since</span><span class="o">=</span><span class="s1">'2.11.0'</span><span class="p">,</span> <span class="n">current</span><span class="o">=</span><span class="s2">"bigquery_tools.BigQueryWriter"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">BigQueryWriter</span><span class="p">(</span><span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">bigquery_tools</span><span class="o">.</span><span class="n">BigQueryWriter</span><span class="p">(</span><span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> |
| |
| |
| <span class="nd">@deprecated</span><span class="p">(</span><span class="n">since</span><span class="o">=</span><span class="s1">'2.11.0'</span><span class="p">,</span> <span class="n">current</span><span class="o">=</span><span class="s2">"bigquery_tools.BigQueryWrapper"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">BigQueryWrapper</span><span class="p">(</span><span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">bigquery_tools</span><span class="o">.</span><span class="n">BigQueryWrapper</span><span class="p">(</span><span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> |
| |
| |
| <div class="viewcode-block" id="TableRowJsonCoder"><a class="viewcode-back" href="../../../../apache_beam.io.gcp.bigquery.html#apache_beam.io.gcp.bigquery.TableRowJsonCoder">[docs]</a><span class="k">class</span> <span class="nc">TableRowJsonCoder</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="sd">"""A coder for a TableRow instance to/from a JSON string.</span> |
| |
| <span class="sd"> Note that the encoding operation (used when writing to sinks) requires the</span> |
| <span class="sd"> table schema in order to obtain the ordered list of field names. Reading from</span> |
| <span class="sd"> sources on the other hand does not need the table schema.</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">table_schema</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="c1"># The table schema is needed for encoding TableRows as JSON (writing to</span> |
| <span class="c1"># sinks) because the ordered list of field names is used in the JSON</span> |
| <span class="c1"># representation.</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">table_schema</span> <span class="o">=</span> <span class="n">table_schema</span> |
| <span class="c1"># Precompute field names since we need them for row encoding.</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">table_schema</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">field_names</span> <span class="o">=</span> <span class="nb">tuple</span><span class="p">(</span><span class="n">fs</span><span class="o">.</span><span class="n">name</span> <span class="k">for</span> <span class="n">fs</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</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">field_types</span> <span class="o">=</span> <span class="nb">tuple</span><span class="p">(</span><span class="n">fs</span><span class="o">.</span><span class="n">type</span> <span class="k">for</span> <span class="n">fs</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">table_schema</span><span class="o">.</span><span class="n">fields</span><span class="p">)</span> |
| |
| <div class="viewcode-block" id="TableRowJsonCoder.encode"><a class="viewcode-back" href="../../../../apache_beam.io.gcp.bigquery.html#apache_beam.io.gcp.bigquery.TableRowJsonCoder.encode">[docs]</a> <span class="k">def</span> <span class="nf">encode</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">table_row</span><span class="p">):</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">table_schema</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">AttributeError</span><span class="p">(</span> |
| <span class="s1">'The TableRowJsonCoder requires a table schema for '</span> |
| <span class="s1">'encoding operations. Please specify a table_schema argument.'</span><span class="p">)</span> |
| <span class="k">try</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">json</span><span class="o">.</span><span class="n">dumps</span><span class="p">(</span> |
| <span class="n">collections</span><span class="o">.</span><span class="n">OrderedDict</span><span class="p">(</span> |
| <span class="nb">zip</span><span class="p">(</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">field_names</span><span class="p">,</span> |
| <span class="p">[</span><span class="n">from_json_value</span><span class="p">(</span><span class="n">f</span><span class="o">.</span><span class="n">v</span><span class="p">)</span> <span class="k">for</span> <span class="n">f</span> <span class="ow">in</span> <span class="n">table_row</span><span class="o">.</span><span class="n">f</span><span class="p">])),</span> |
| <span class="n">allow_nan</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> |
| <span class="n">default</span><span class="o">=</span><span class="n">bigquery_tools</span><span class="o">.</span><span class="n">default_encoder</span><span class="p">)</span> |
| <span class="k">except</span> <span class="ne">ValueError</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</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="n">e</span><span class="p">,</span> <span class="n">bigquery_tools</span><span class="o">.</span><span class="n">JSON_COMPLIANCE_ERROR</span><span class="p">))</span></div> |
| |
| <div class="viewcode-block" id="TableRowJsonCoder.decode"><a class="viewcode-back" href="../../../../apache_beam.io.gcp.bigquery.html#apache_beam.io.gcp.bigquery.TableRowJsonCoder.decode">[docs]</a> <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">encoded_table_row</span><span class="p">):</span> |
| <span class="n">od</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">encoded_table_row</span><span class="p">,</span> <span class="n">object_pairs_hook</span><span class="o">=</span><span class="n">collections</span><span class="o">.</span><span class="n">OrderedDict</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">bigquery</span><span class="o">.</span><span class="n">TableRow</span><span class="p">(</span> |
| <span class="n">f</span><span class="o">=</span><span class="p">[</span><span class="n">bigquery</span><span class="o">.</span><span class="n">TableCell</span><span class="p">(</span><span class="n">v</span><span class="o">=</span><span class="n">to_json_value</span><span class="p">(</span><span class="n">e</span><span class="p">))</span> <span class="k">for</span> <span class="n">e</span> <span class="ow">in</span> <span class="n">od</span><span class="o">.</span><span class="n">values</span><span class="p">()])</span></div></div> |
| |
| |
| <div class="viewcode-block" id="BigQueryDisposition"><a class="viewcode-back" href="../../../../apache_beam.io.gcp.bigquery.html#apache_beam.io.gcp.bigquery.BigQueryDisposition">[docs]</a><span class="k">class</span> <span class="nc">BigQueryDisposition</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span> |
| <span class="sd">"""Class holding standard strings used for create and write dispositions."""</span> |
| |
| <span class="n">CREATE_NEVER</span> <span class="o">=</span> <span class="s1">'CREATE_NEVER'</span> |
| <span class="n">CREATE_IF_NEEDED</span> <span class="o">=</span> <span class="s1">'CREATE_IF_NEEDED'</span> |
| <span class="n">WRITE_TRUNCATE</span> <span class="o">=</span> <span class="s1">'WRITE_TRUNCATE'</span> |
| <span class="n">WRITE_APPEND</span> <span class="o">=</span> <span class="s1">'WRITE_APPEND'</span> |
| <span class="n">WRITE_EMPTY</span> <span class="o">=</span> <span class="s1">'WRITE_EMPTY'</span> |
| |
| <div class="viewcode-block" id="BigQueryDisposition.validate_create"><a class="viewcode-back" href="../../../../apache_beam.io.gcp.bigquery.html#apache_beam.io.gcp.bigquery.BigQueryDisposition.validate_create">[docs]</a> <span class="nd">@staticmethod</span> |
| <span class="k">def</span> <span class="nf">validate_create</span><span class="p">(</span><span class="n">disposition</span><span class="p">):</span> |
| <span class="n">values</span> <span class="o">=</span> <span class="p">(</span> |
| <span class="n">BigQueryDisposition</span><span class="o">.</span><span class="n">CREATE_NEVER</span><span class="p">,</span> <span class="n">BigQueryDisposition</span><span class="o">.</span><span class="n">CREATE_IF_NEEDED</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">disposition</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">values</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span> |
| <span class="s1">'Invalid create disposition </span><span class="si">%s</span><span class="s1">. Expecting </span><span class="si">%s</span><span class="s1">'</span> <span class="o">%</span> <span class="p">(</span><span class="n">disposition</span><span class="p">,</span> <span class="n">values</span><span class="p">))</span> |
| <span class="k">return</span> <span class="n">disposition</span></div> |
| |
| <div class="viewcode-block" id="BigQueryDisposition.validate_write"><a class="viewcode-back" href="../../../../apache_beam.io.gcp.bigquery.html#apache_beam.io.gcp.bigquery.BigQueryDisposition.validate_write">[docs]</a> <span class="nd">@staticmethod</span> |
| <span class="k">def</span> <span class="nf">validate_write</span><span class="p">(</span><span class="n">disposition</span><span class="p">):</span> |
| <span class="n">values</span> <span class="o">=</span> <span class="p">(</span> |
| <span class="n">BigQueryDisposition</span><span class="o">.</span><span class="n">WRITE_TRUNCATE</span><span class="p">,</span> |
| <span class="n">BigQueryDisposition</span><span class="o">.</span><span class="n">WRITE_APPEND</span><span class="p">,</span> |
| <span class="n">BigQueryDisposition</span><span class="o">.</span><span class="n">WRITE_EMPTY</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">disposition</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">values</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span> |
| <span class="s1">'Invalid write disposition </span><span class="si">%s</span><span class="s1">. Expecting </span><span class="si">%s</span><span class="s1">'</span> <span class="o">%</span> <span class="p">(</span><span class="n">disposition</span><span class="p">,</span> <span class="n">values</span><span class="p">))</span> |
| <span class="k">return</span> <span class="n">disposition</span></div></div> |
| |
| |
| <div class="viewcode-block" id="BigQueryQueryPriority"><a class="viewcode-back" href="../../../../apache_beam.io.gcp.bigquery.html#apache_beam.io.gcp.bigquery.BigQueryQueryPriority">[docs]</a><span class="k">class</span> <span class="nc">BigQueryQueryPriority</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span> |
| <span class="sd">"""Class holding standard strings used for query priority."""</span> |
| |
| <span class="n">INTERACTIVE</span> <span class="o">=</span> <span class="s1">'INTERACTIVE'</span> |
| <span class="n">BATCH</span> <span class="o">=</span> <span class="s1">'BATCH'</span></div> |
| |
| |
| <span class="c1"># -----------------------------------------------------------------------------</span> |
| <span class="c1"># BigQuerySource, BigQuerySink.</span> |
| |
| |
| <div class="viewcode-block" id="BigQuerySource"><a class="viewcode-back" href="../../../../apache_beam.io.gcp.bigquery.html#apache_beam.io.gcp.bigquery.BigQuerySource">[docs]</a><span class="nd">@deprecated</span><span class="p">(</span><span class="n">since</span><span class="o">=</span><span class="s1">'2.25.0'</span><span class="p">,</span> <span class="n">current</span><span class="o">=</span><span class="s2">"ReadFromBigQuery"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">BigQuerySource</span><span class="p">(</span> |
| <span class="n">table</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">dataset</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">project</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">query</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">validate</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> |
| <span class="n">coder</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">use_standard_sql</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> |
| <span class="n">flatten_results</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> |
| <span class="n">kms_key</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">use_dataflow_native_source</span><span class="o">=</span><span class="kc">False</span><span class="p">):</span> |
| <span class="k">if</span> <span class="n">use_dataflow_native_source</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">_BigQuerySource</span><span class="p">(</span> |
| <span class="n">table</span><span class="p">,</span> |
| <span class="n">dataset</span><span class="p">,</span> |
| <span class="n">project</span><span class="p">,</span> |
| <span class="n">query</span><span class="p">,</span> |
| <span class="n">validate</span><span class="p">,</span> |
| <span class="n">coder</span><span class="p">,</span> |
| <span class="n">use_standard_sql</span><span class="p">,</span> |
| <span class="n">flatten_results</span><span class="p">,</span> |
| <span class="n">kms_key</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">ReadFromBigQuery</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">dataset</span><span class="o">=</span><span class="n">dataset</span><span class="p">,</span> |
| <span class="n">project</span><span class="o">=</span><span class="n">project</span><span class="p">,</span> |
| <span class="n">query</span><span class="o">=</span><span class="n">query</span><span class="p">,</span> |
| <span class="n">validate</span><span class="o">=</span><span class="n">validate</span><span class="p">,</span> |
| <span class="n">coder</span><span class="o">=</span><span class="n">coder</span><span class="p">,</span> |
| <span class="n">use_standard_sql</span><span class="o">=</span><span class="n">use_standard_sql</span><span class="p">,</span> |
| <span class="n">flatten_results</span><span class="o">=</span><span class="n">flatten_results</span><span class="p">,</span> |
| <span class="n">use_json_exports</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> |
| <span class="n">kms_key</span><span class="o">=</span><span class="n">kms_key</span><span class="p">)</span></div> |
| |
| |
| <span class="nd">@deprecated</span><span class="p">(</span><span class="n">since</span><span class="o">=</span><span class="s1">'2.25.0'</span><span class="p">,</span> <span class="n">current</span><span class="o">=</span><span class="s2">"ReadFromBigQuery"</span><span class="p">)</span> |
| <span class="k">class</span> <span class="nc">_BigQuerySource</span><span class="p">(</span><span class="n">dataflow_io</span><span class="o">.</span><span class="n">NativeSource</span><span class="p">):</span> |
| <span class="sd">"""A source based on a BigQuery table."""</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</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">dataset</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">project</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">query</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">validate</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> |
| <span class="n">coder</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">use_standard_sql</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> |
| <span class="n">flatten_results</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> |
| <span class="n">kms_key</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">temp_dataset</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="sd">"""Initialize a :class:`BigQuerySource`.</span> |
| |
| <span class="sd"> Args:</span> |
| <span class="sd"> table (str): The ID of a BigQuery table. If specified all data of the</span> |
| <span class="sd"> table will be used as input of the current source. The ID must contain</span> |
| <span class="sd"> only letters ``a-z``, ``A-Z``, numbers ``0-9``, or underscores</span> |
| <span class="sd"> ``_``. If dataset and query arguments are :data:`None` then the table</span> |
| <span class="sd"> argument must contain the entire table reference specified as:</span> |
| <span class="sd"> ``'DATASET.TABLE'`` or ``'PROJECT:DATASET.TABLE'``.</span> |
| <span class="sd"> dataset (str): The ID of the dataset containing this table or</span> |
| <span class="sd"> :data:`None` if the table reference is specified entirely by the table</span> |
| <span class="sd"> argument or a query is specified.</span> |
| <span class="sd"> project (str): The ID of the project containing this table or</span> |
| <span class="sd"> :data:`None` if the table reference is specified entirely by the table</span> |
| <span class="sd"> argument or a query is specified.</span> |
| <span class="sd"> query (str): A query to be used instead of arguments table, dataset, and</span> |
| <span class="sd"> project.</span> |
| <span class="sd"> validate (bool): If :data:`True`, various checks will be done when source</span> |
| <span class="sd"> gets initialized (e.g., is table present?). This should be</span> |
| <span class="sd"> :data:`True` for most scenarios in order to catch errors as early as</span> |
| <span class="sd"> possible (pipeline construction instead of pipeline execution). It</span> |
| <span class="sd"> should be :data:`False` if the table is created during pipeline</span> |
| <span class="sd"> execution by a previous step.</span> |
| <span class="sd"> coder (~apache_beam.coders.coders.Coder): The coder for the table</span> |
| <span class="sd"> rows if serialized to disk. If :data:`None`, then the default coder is</span> |
| <span class="sd"> :class:`~apache_beam.io.gcp.bigquery_tools.RowAsDictJsonCoder`,</span> |
| <span class="sd"> which will interpret every line in a file as a JSON serialized</span> |
| <span class="sd"> dictionary. This argument needs a value only in special cases when</span> |
| <span class="sd"> returning table rows as dictionaries is not desirable.</span> |
| <span class="sd"> use_standard_sql (bool): Specifies whether to use BigQuery's standard SQL</span> |
| <span class="sd"> dialect for this query. The default value is :data:`False`.</span> |
| <span class="sd"> If set to :data:`True`, the query will use BigQuery's updated SQL</span> |
| <span class="sd"> dialect with improved standards compliance.</span> |
| <span class="sd"> This parameter is ignored for table inputs.</span> |
| <span class="sd"> flatten_results (bool): Flattens all nested and repeated fields in the</span> |
| <span class="sd"> query results. The default value is :data:`True`.</span> |
| <span class="sd"> kms_key (str): Optional Cloud KMS key name for use when creating new</span> |
| <span class="sd"> tables.</span> |
| <span class="sd"> temp_dataset (``google.cloud.bigquery.dataset.DatasetReference``):</span> |
| <span class="sd"> The dataset in which to create temporary tables when performing file</span> |
| <span class="sd"> loads. By default, a new dataset is created in the execution project for</span> |
| <span class="sd"> temporary tables.</span> |
| |
| <span class="sd"> Raises:</span> |
| <span class="sd"> ValueError: if any of the following is true:</span> |
| |
| <span class="sd"> 1) the table reference as a string does not match the expected format</span> |
| <span class="sd"> 2) neither a table nor a query is specified</span> |
| <span class="sd"> 3) both a table and a query is specified.</span> |
| <span class="sd"> """</span> |
| |
| <span class="c1"># Import here to avoid adding the dependency for local running scenarios.</span> |
| <span class="k">try</span><span class="p">:</span> |
| <span class="c1"># pylint: disable=wrong-import-order, wrong-import-position</span> |
| <span class="kn">from</span> <span class="nn">apitools.base</span> <span class="kn">import</span> <span class="n">py</span> <span class="c1"># pylint: disable=unused-import</span> |
| <span class="k">except</span> <span class="ne">ImportError</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ImportError</span><span class="p">(</span> |
| <span class="s1">'Google Cloud IO not available, '</span> |
| <span class="s1">'please install apache_beam[gcp]'</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="n">table</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> <span class="ow">and</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="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span> |
| <span class="s1">'Both a BigQuery table and a query were specified.'</span> |
| <span class="s1">' Please specify only one of these.'</span><span class="p">)</span> |
| <span class="k">elif</span> <span class="n">table</span> <span class="ow">is</span> <span class="kc">None</span> <span class="ow">and</span> <span class="n">query</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="s1">'A BigQuery table or a query must be specified'</span><span class="p">)</span> |
| <span class="k">elif</span> <span class="n">table</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">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">table</span><span class="p">,</span> <span class="n">dataset</span><span class="p">,</span> <span class="n">project</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">query</span> <span class="o">=</span> <span class="kc">None</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">use_legacy_sql</span> <span class="o">=</span> <span class="kc">True</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">query</span> <span class="o">=</span> <span class="n">query</span> |
| <span class="c1"># TODO(BEAM-1082): Change the internal flag to be standard_sql</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">use_legacy_sql</span> <span class="o">=</span> <span class="ow">not</span> <span class="n">use_standard_sql</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">table_reference</span> <span class="o">=</span> <span class="kc">None</span> |
| |
| <span class="bp">self</span><span class="o">.</span><span class="n">validate</span> <span class="o">=</span> <span class="n">validate</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">flatten_results</span> <span class="o">=</span> <span class="n">flatten_results</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">coder</span> <span class="o">=</span> <span class="n">coder</span> <span class="ow">or</span> <span class="n">bigquery_tools</span><span class="o">.</span><span class="n">RowAsDictJsonCoder</span><span class="p">()</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">temp_dataset</span> <span class="o">=</span> <span class="n">temp_dataset</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">if</span> <span class="bp">self</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">res</span> <span class="o">=</span> <span class="p">{</span><span class="s1">'query'</span><span class="p">:</span> <span class="n">DisplayDataItem</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">query</span><span class="p">,</span> <span class="n">label</span><span class="o">=</span><span class="s1">'Query'</span><span class="p">)}</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">table_reference</span><span class="o">.</span><span class="n">projectId</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">tableSpec</span> <span class="o">=</span> <span class="s1">'</span><span class="si">{}</span><span class="s1">:</span><span class="si">{}</span><span class="s1">.</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">table_reference</span><span class="o">.</span><span class="n">projectId</span><span class="p">,</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">table_reference</span><span class="o">.</span><span class="n">datasetId</span><span class="p">,</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">table_reference</span><span class="o">.</span><span class="n">tableId</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">tableSpec</span> <span class="o">=</span> <span class="s1">'</span><span class="si">{}</span><span class="s1">.</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">table_reference</span><span class="o">.</span><span class="n">datasetId</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">table_reference</span><span class="o">.</span><span class="n">tableId</span><span class="p">)</span> |
| <span class="n">res</span> <span class="o">=</span> <span class="p">{</span><span class="s1">'table'</span><span class="p">:</span> <span class="n">DisplayDataItem</span><span class="p">(</span><span class="n">tableSpec</span><span class="p">,</span> <span class="n">label</span><span class="o">=</span><span class="s1">'Table'</span><span class="p">)}</span> |
| |
| <span class="n">res</span><span class="p">[</span><span class="s1">'validation'</span><span class="p">]</span> <span class="o">=</span> <span class="n">DisplayDataItem</span><span class="p">(</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">validate</span><span class="p">,</span> <span class="n">label</span><span class="o">=</span><span class="s1">'Validation Enabled'</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">res</span> |
| |
| <span class="nd">@property</span> |
| <span class="k">def</span> <span class="nf">format</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""Source format name required for remote execution."""</span> |
| <span class="k">return</span> <span class="s1">'bigquery'</span> |
| |
| <span class="k">def</span> <span class="nf">reader</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">test_bigquery_client</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">bigquery_tools</span><span class="o">.</span><span class="n">BigQueryReader</span><span class="p">(</span> |
| <span class="n">source</span><span class="o">=</span><span class="bp">self</span><span class="p">,</span> |
| <span class="n">test_bigquery_client</span><span class="o">=</span><span class="n">test_bigquery_client</span><span class="p">,</span> |
| <span class="n">use_legacy_sql</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">use_legacy_sql</span><span class="p">,</span> |
| <span class="n">flatten_results</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">flatten_results</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="k">class</span> <span class="nc">_CustomBigQuerySource</span><span class="p">(</span><span class="n">BoundedSource</span><span class="p">):</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">method</span><span class="p">,</span> |
| <span class="n">gcs_location</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">table</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">dataset</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">project</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">query</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">validate</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> |
| <span class="n">pipeline_options</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">coder</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">use_standard_sql</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> |
| <span class="n">flatten_results</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> |
| <span class="n">kms_key</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">bigquery_job_labels</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">use_json_exports</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> |
| <span class="n">job_name</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">step_name</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">unique_id</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">temp_dataset</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">query_priority</span><span class="o">=</span><span class="n">BigQueryQueryPriority</span><span class="o">.</span><span class="n">BATCH</span><span class="p">):</span> |
| <span class="k">if</span> <span class="n">table</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> <span class="ow">and</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="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span> |
| <span class="s1">'Both a BigQuery table and a query were specified.'</span> |
| <span class="s1">' Please specify only one of these.'</span><span class="p">)</span> |
| <span class="k">elif</span> <span class="n">table</span> <span class="ow">is</span> <span class="kc">None</span> <span class="ow">and</span> <span class="n">query</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="s1">'A BigQuery table or a query must be specified'</span><span class="p">)</span> |
| <span class="k">elif</span> <span class="n">table</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">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">table</span><span class="p">,</span> <span class="n">dataset</span><span class="p">,</span> <span class="n">project</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">query</span> <span class="o">=</span> <span class="kc">None</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">use_legacy_sql</span> <span class="o">=</span> <span class="kc">True</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">query</span><span class="p">,</span> <span class="nb">str</span><span class="p">):</span> |
| <span class="n">query</span> <span class="o">=</span> <span class="n">StaticValueProvider</span><span class="p">(</span><span class="nb">str</span><span class="p">,</span> <span class="n">query</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">query</span> <span class="o">=</span> <span class="n">query</span> |
| <span class="c1"># TODO(BEAM-1082): Change the internal flag to be standard_sql</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">use_legacy_sql</span> <span class="o">=</span> <span class="ow">not</span> <span class="n">use_standard_sql</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">table_reference</span> <span class="o">=</span> <span class="kc">None</span> |
| |
| <span class="bp">self</span><span class="o">.</span><span class="n">method</span> <span class="o">=</span> <span class="n">method</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">project</span> <span class="o">=</span> <span class="n">project</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">validate</span> <span class="o">=</span> <span class="n">validate</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">flatten_results</span> <span class="o">=</span> <span class="n">flatten_results</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">coder</span> <span class="o">=</span> <span class="n">coder</span> <span class="ow">or</span> <span class="n">_JsonToDictCoder</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">split_result</span> <span class="o">=</span> <span class="kc">None</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">options</span> <span class="o">=</span> <span class="n">pipeline_options</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="c1"># Populate in setup, as it may make an RPC</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">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">temp_dataset</span> <span class="o">=</span> <span class="n">temp_dataset</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">_job_name</span> <span class="o">=</span> <span class="n">job_name</span> <span class="ow">or</span> <span class="s1">'BQ_EXPORT_JOB'</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">_source_uuid</span> <span class="o">=</span> <span class="n">unique_id</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">display_data</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="n">export_format</span> <span class="o">=</span> <span class="s1">'JSON'</span> <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">use_json_exports</span> <span class="k">else</span> <span class="s1">'AVRO'</span> |
| <span class="k">return</span> <span class="p">{</span> |
| <span class="s1">'method'</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">method</span><span class="p">),</span> |
| <span class="s1">'table'</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">table_reference</span><span class="p">),</span> |
| <span class="s1">'query'</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">query</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">'use_legacy_sql'</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">use_legacy_sql</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">'export_file_format'</span><span class="p">:</span> <span class="n">export_format</span><span class="p">,</span> |
| <span class="s1">'launchesBigQueryJobs'</span><span class="p">:</span> <span class="n">DisplayDataItem</span><span class="p">(</span> |
| <span class="kc">True</span><span class="p">,</span> <span class="n">label</span><span class="o">=</span><span class="s2">"This Dataflow job launches bigquery jobs."</span><span class="p">),</span> |
| <span class="p">}</span> |
| |
| <span class="k">def</span> <span class="nf">estimate_size</span><span class="p">(</span><span class="bp">self</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="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">table_reference</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">table_ref</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">table_reference</span> |
| <span class="k">if</span> <span class="p">(</span><span class="nb">isinstance</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">table_reference</span><span class="p">,</span> <span class="n">vp</span><span class="o">.</span><span class="n">ValueProvider</span><span class="p">)</span> <span class="ow">and</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">table_reference</span><span class="o">.</span><span class="n">is_accessible</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="bp">self</span><span class="o">.</span><span class="n">table_reference</span><span class="o">.</span><span class="n">get</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">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">table_reference</span><span class="p">,</span> <span class="n">vp</span><span class="o">.</span><span class="n">ValueProvider</span><span class="p">):</span> |
| <span class="c1"># Size estimation is best effort. We return None as we have</span> |
| <span class="c1"># no access to the table that we're querying.</span> |
| <span class="k">return</span> <span class="kc">None</span> |
| <span class="k">if</span> <span class="ow">not</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">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">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="nb">int</span><span class="p">(</span><span class="n">table</span><span class="o">.</span><span class="n">numBytes</span><span class="p">)</span> |
| <span class="k">elif</span> <span class="bp">self</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="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">query</span><span class="o">.</span><span class="n">is_accessible</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">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="n">project</span><span class="p">,</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">query</span><span class="o">.</span><span class="n">get</span><span class="p">(),</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">use_legacy_sql</span><span class="p">,</span> |
| <span class="bp">self</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">dry_run</span><span class="o">=</span><span class="kc">True</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">size</span> <span class="o">=</span> <span class="nb">int</span><span class="p">(</span><span class="n">job</span><span class="o">.</span><span class="n">statistics</span><span class="o">.</span><span class="n">totalBytesProcessed</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">size</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="c1"># Size estimation is best effort. We return None as we have</span> |
| <span class="c1"># no access to the query that we're running.</span> |
| <span class="k">return</span> <span class="kc">None</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="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">vp</span><span class="o">.</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="bp">self</span><span class="o">.</span><span class="n">temp_dataset</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="o">.</span><span class="n">projectId</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="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="bp">self</span><span class="o">.</span><span class="n">coder</span><span class="p">(</span><span class="n">schema</span><span class="p">))</span> |
| |
| <span class="k">def</span> <span class="nf">split</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">desired_bundle_size</span><span class="p">,</span> <span class="n">start_position</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">stop_position</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">split_result</span> <span class="ow">is</span> <span class="kc">None</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="p">(</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">temp_dataset</span><span class="o">.</span><span class="n">datasetId</span> <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">temp_dataset</span> <span class="k">else</span> <span class="kc">None</span><span class="p">))</span> |
| |
| <span class="k">if</span> <span class="bp">self</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="bp">self</span><span class="o">.</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="k">if</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">table_reference</span><span class="o">.</span><span class="n">projectId</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</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="c1"># Sources to be created lazily within a generator as they're output.</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">split_result</span> <span class="o">=</span> <span class="p">(</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">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">if</span> <span class="bp">self</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">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">for</span> <span class="n">source</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">split_result</span><span class="p">:</span> |
| <span class="k">yield</span> <span class="n">SourceBundle</span><span class="p">(</span> |
| <span class="n">weight</span><span class="o">=</span><span class="mf">1.0</span><span class="p">,</span> <span class="n">source</span><span class="o">=</span><span class="n">source</span><span class="p">,</span> <span class="n">start_position</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">stop_position</span><span class="o">=</span><span class="kc">None</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">get_range_tracker</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">start_position</span><span class="p">,</span> <span class="n">stop_position</span><span class="p">):</span> |
| <span class="k">class</span> <span class="nc">CustomBigQuerySourceRangeTracker</span><span class="p">(</span><span class="n">RangeTracker</span><span class="p">):</span> |
| <span class="sd">"""A RangeTracker that always returns positions as None."""</span> |
| <span class="k">def</span> <span class="nf">start_position</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="k">return</span> <span class="kc">None</span> |
| |
| <span class="k">def</span> <span class="nf">stop_position</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="k">return</span> <span class="kc">None</span> |
| |
| <span class="k">return</span> <span class="n">CustomBigQuerySourceRangeTracker</span><span class="p">()</span> |
| |
| <span class="k">def</span> <span class="nf">read</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">range_tracker</span><span class="p">):</span> |
| <span class="k">raise</span> <span class="ne">NotImplementedError</span><span class="p">(</span><span class="s1">'BigQuery source must be split before being read'</span><span class="p">)</span> |
| |
| <span class="nd">@check_accessible</span><span class="p">([</span><span class="s1">'query'</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="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">temp_dataset</span><span class="p">:</span> |
| <span class="c1"># Temp dataset was provided by the user so we can just return.</span> |
| <span class="k">return</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="bp">self</span><span class="o">.</span><span class="n">query</span><span class="o">.</span><span class="n">get</span><span class="p">(),</span> <span class="bp">self</span><span class="o">.</span><span class="n">use_legacy_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="nd">@check_accessible</span><span class="p">([</span><span class="s1">'query'</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">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="bp">self</span><span class="o">.</span><span class="n">query</span><span class="o">.</span><span class="n">get</span><span class="p">(),</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">use_legacy_sql</span><span class="p">,</span> |
| <span class="bp">self</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="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="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">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="bp">self</span><span class="o">.</span><span class="n">_source_uuid</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="bp">self</span><span class="o">.</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="bp">self</span><span class="o">.</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="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="bp">self</span><span class="o">.</span><span class="n">table_reference</span><span class="p">,</span> <span class="n">vp</span><span class="o">.</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="bp">self</span><span class="o">.</span><span class="n">table_reference</span><span class="o">.</span><span class="n">get</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="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">table_ref</span> <span class="o">=</span> <span class="bp">self</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">class</span> <span class="nc">_CustomBigQueryStorageSource</span><span class="p">(</span><span class="n">BoundedSource</span><span class="p">):</span> |
| <span class="sd">"""A base class for BoundedSource implementations which read from BigQuery</span> |
| <span class="sd"> using the BigQuery Storage API.</span> |
| <span class="sd"> Args:</span> |
| <span class="sd"> table (str, TableReference): The ID of the table. The ID must contain only</span> |
| <span class="sd"> letters ``a-z``, ``A-Z``, numbers ``0-9``, or underscores ``_`` If</span> |
| <span class="sd"> **dataset** argument is :data:`None` then the table argument must</span> |
| <span class="sd"> contain the entire table reference specified as:</span> |
| <span class="sd"> ``'PROJECT:DATASET.TABLE'`` or must specify a TableReference.</span> |
| <span class="sd"> dataset (str): Optional ID of the dataset containing this table or</span> |
| <span class="sd"> :data:`None` if the table argument specifies a TableReference.</span> |
| <span class="sd"> project (str): Optional ID of the project containing this table or</span> |
| <span class="sd"> :data:`None` if the table argument specifies a TableReference.</span> |
| <span class="sd"> selected_fields (List[str]): Optional List of names of the fields in the</span> |
| <span class="sd"> table that should be read. If empty, all fields will be read. If the</span> |
| <span class="sd"> specified field is a nested field, all the sub-fields in the field will be</span> |
| <span class="sd"> selected. The output field order is unrelated to the order of fields in</span> |
| <span class="sd"> selected_fields.</span> |
| <span class="sd"> row_restriction (str): Optional SQL text filtering statement, similar to a</span> |
| <span class="sd"> WHERE clause in a query. Aggregates are not supported. Restricted to a</span> |
| <span class="sd"> maximum length for 1 MB.</span> |
| <span class="sd"> use_native_datetime (bool): If :data:`True`, BigQuery DATETIME fields will</span> |
| <span class="sd"> be returned as native Python datetime objects. If :data:`False`,</span> |
| <span class="sd"> DATETIME fields will be returned as formatted strings (for example:</span> |
| <span class="sd"> 2021-01-01T12:59:59). The default is :data:`False`.</span> |
| <span class="sd"> """</span> |
| |
| <span class="c1"># The maximum number of streams which will be requested when creating a read</span> |
| <span class="c1"># session, regardless of the desired bundle size.</span> |
| <span class="n">MAX_SPLIT_COUNT</span> <span class="o">=</span> <span class="mi">10000</span> |
| <span class="c1"># The minimum number of streams which will be requested when creating a read</span> |
| <span class="c1"># session, regardless of the desired bundle size. Note that the server may</span> |
| <span class="c1"># still choose to return fewer than ten streams based on the layout of the</span> |
| <span class="c1"># table.</span> |
| <span class="n">MIN_SPLIT_COUNT</span> <span class="o">=</span> <span class="mi">10</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">method</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> |
| <span class="n">query_priority</span><span class="p">:</span> <span class="p">[</span><span class="n">BigQueryQueryPriority</span><span class="p">]</span> <span class="o">=</span> <span class="n">BigQueryQueryPriority</span><span class="o">.</span><span class="n">BATCH</span><span class="p">,</span> |
| <span class="n">table</span><span class="p">:</span> <span class="n">Optional</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">TableReference</span><span class="p">]]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> |
| <span class="n">dataset</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="n">project</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="n">query</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="n">selected_fields</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">List</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">row_restriction</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="n">pipeline_options</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">GoogleCloudOptions</span><span class="p">]</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="n">Optional</span><span class="p">[</span><span class="n">uuid</span><span class="o">.</span><span class="n">UUID</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> |
| <span class="n">bigquery_job_labels</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">Dict</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> |
| <span class="n">bigquery_dataset_labels</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">Dict</span><span class="p">]</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="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="n">step_name</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="n">use_standard_sql</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">bool</span><span class="p">]</span> <span class="o">=</span> <span class="kc">False</span><span class="p">,</span> |
| <span class="n">flatten_results</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">bool</span><span class="p">]</span> <span class="o">=</span> <span class="kc">True</span><span class="p">,</span> |
| <span class="n">kms_key</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="n">temp_dataset</span><span class="p">:</span> <span class="n">Optional</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">temp_table</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">TableReference</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> |
| <span class="n">use_native_datetime</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">bool</span><span class="p">]</span> <span class="o">=</span> <span class="kc">False</span><span class="p">):</span> |
| |
| <span class="k">if</span> <span class="n">table</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> <span class="ow">and</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="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span> |
| <span class="s1">'Both a BigQuery table and a query were specified.'</span> |
| <span class="s1">' Please specify only one of these.'</span><span class="p">)</span> |
| <span class="k">elif</span> <span class="n">table</span> <span class="ow">is</span> <span class="kc">None</span> <span class="ow">and</span> <span class="n">query</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="s1">'A BigQuery table or a query must be specified'</span><span class="p">)</span> |
| <span class="k">elif</span> <span class="n">table</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">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">table</span><span class="p">,</span> <span class="n">dataset</span><span class="p">,</span> <span class="n">project</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">query</span> <span class="o">=</span> <span class="kc">None</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">use_legacy_sql</span> <span class="o">=</span> <span class="kc">True</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">query</span><span class="p">,</span> <span class="nb">str</span><span class="p">):</span> |
| <span class="n">query</span> <span class="o">=</span> <span class="n">StaticValueProvider</span><span class="p">(</span><span class="nb">str</span><span class="p">,</span> <span class="n">query</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">query</span> <span class="o">=</span> <span class="n">query</span> |
| <span class="c1"># TODO(BEAM-1082): Change the internal flag to be standard_sql</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">use_legacy_sql</span> <span class="o">=</span> <span class="ow">not</span> <span class="n">use_standard_sql</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">table_reference</span> <span class="o">=</span> <span class="kc">None</span> |
| |
| <span class="bp">self</span><span class="o">.</span><span class="n">method</span> <span class="o">=</span> <span class="n">method</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">selected_fields</span> <span class="o">=</span> <span class="n">selected_fields</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">row_restriction</span> <span class="o">=</span> <span class="n">row_restriction</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">pipeline_options</span> <span class="o">=</span> <span class="n">pipeline_options</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">split_result</span> <span class="o">=</span> <span class="kc">None</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">bigquery_dataset_labels</span> <span class="o">=</span> <span class="n">bigquery_dataset_labels</span> <span class="ow">or</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="kc">None</span> <span class="c1"># Populate in setup, as it may make an RPC</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">flatten_results</span> <span class="o">=</span> <span class="n">flatten_results</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">temp_table</span> <span class="o">=</span> <span class="n">temp_table</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">use_native_datetime</span> <span class="o">=</span> <span class="n">use_native_datetime</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_DIRECT_READ_JOB'</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">_source_uuid</span> <span class="o">=</span> <span class="n">unique_id</span> |
| |
| <span class="k">def</span> <span class="nf">_get_parent_project</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""Returns the project that will be billed."""</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">temp_table</span><span class="p">:</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">temp_table</span><span class="o">.</span><span class="n">projectId</span> |
| |
| <span class="n">project</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">pipeline_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">vp</span><span class="o">.</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="k">def</span> <span class="nf">_get_table_size</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">table_reference</span><span class="p">):</span> |
| <span class="n">project</span> <span class="o">=</span> <span class="p">(</span> |
| <span class="n">table_reference</span><span class="o">.</span><span class="n">projectId</span> |
| <span class="k">if</span> <span class="n">table_reference</span><span class="o">.</span><span class="n">projectId</span> <span class="k">else</span> <span class="bp">self</span><span class="o">.</span><span class="n">_get_parent_project</span><span class="p">())</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">project</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">return</span> <span class="n">table</span><span class="o">.</span><span class="n">numBytes</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="nd">@check_accessible</span><span class="p">([</span><span class="s1">'query'</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="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">temp_table</span><span class="p">:</span> |
| <span class="c1"># Temp dataset was provided by the user so we can just return.</span> |
| <span class="k">return</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_parent_project</span><span class="p">(),</span> <span class="bp">self</span><span class="o">.</span><span class="n">query</span><span class="o">.</span><span class="n">get</span><span class="p">(),</span> <span class="bp">self</span><span class="o">.</span><span class="n">use_legacy_sql</span><span class="p">)</span> |
| <span class="n">_LOGGER</span><span class="o">.</span><span class="n">warning</span><span class="p">(</span><span class="s2">"### Labels: </span><span class="si">%s</span><span class="s2">"</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">bigquery_dataset_labels</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_parent_project</span><span class="p">(),</span> <span class="n">location</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">bigquery_dataset_labels</span><span class="p">)</span> |
| |
| <span class="nd">@check_accessible</span><span class="p">([</span><span class="s1">'query'</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">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_parent_project</span><span class="p">(),</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">query</span><span class="o">.</span><span class="n">get</span><span class="p">(),</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">use_legacy_sql</span><span class="p">,</span> |
| <span class="bp">self</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="n">table_reference</span> <span class="o">=</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_parent_project</span><span class="p">())</span> |
| <span class="k">return</span> <span class="n">table_reference</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">'method'</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">method</span><span class="p">,</span> |
| <span class="s1">'output_format'</span><span class="p">:</span> <span class="s1">'ARROW'</span> <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">use_native_datetime</span> <span class="k">else</span> <span class="s1">'AVRO'</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">'table_reference'</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">table_reference</span><span class="p">),</span> |
| <span class="s1">'query'</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">query</span><span class="p">),</span> |
| <span class="s1">'use_legacy_sql'</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">use_legacy_sql</span><span class="p">,</span> |
| <span class="s1">'use_native_datetime'</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">use_native_datetime</span><span class="p">,</span> |
| <span class="s1">'selected_fields'</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">selected_fields</span><span class="p">),</span> |
| <span class="s1">'row_restriction'</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">row_restriction</span><span class="p">)</span> |
| <span class="p">}</span> |
| |
| <span class="k">def</span> <span class="nf">estimate_size</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="c1"># Returns the pre-filtering size of the (temporary) table being read.</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="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">table_reference</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_get_table_size</span><span class="p">(</span><span class="n">bq</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">table_reference</span><span class="p">)</span> |
| <span class="k">elif</span> <span class="bp">self</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="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">query</span><span class="o">.</span><span class="n">is_accessible</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_parent_project</span><span class="p">(),</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">query</span><span class="o">.</span><span class="n">get</span><span class="p">(),</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">use_legacy_sql</span><span class="p">,</span> |
| <span class="bp">self</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">dry_run</span><span class="o">=</span><span class="kc">True</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">size</span> <span class="o">=</span> <span class="nb">int</span><span class="p">(</span><span class="n">job</span><span class="o">.</span><span class="n">statistics</span><span class="o">.</span><span class="n">totalBytesProcessed</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">size</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="c1"># Size estimation is best effort. We return None as we have</span> |
| <span class="c1"># no access to the query that we're running.</span> |
| <span class="k">return</span> <span class="kc">None</span> |
| |
| <span class="k">def</span> <span class="nf">split</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">desired_bundle_size</span><span class="p">,</span> <span class="n">start_position</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">stop_position</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">split_result</span> <span class="ow">is</span> <span class="kc">None</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_table_ref</span><span class="o">=</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">temp_table</span> <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">temp_table</span> <span class="k">else</span> <span class="kc">None</span><span class="p">))</span> |
| |
| <span class="k">if</span> <span class="bp">self</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="bp">self</span><span class="o">.</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">requested_session</span> <span class="o">=</span> <span class="n">bq_storage</span><span class="o">.</span><span class="n">types</span><span class="o">.</span><span class="n">ReadSession</span><span class="p">()</span> |
| <span class="n">requested_session</span><span class="o">.</span><span class="n">table</span> <span class="o">=</span> <span class="s1">'projects/</span><span class="si">{}</span><span class="s1">/datasets/</span><span class="si">{}</span><span class="s1">/tables/</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">table_reference</span><span class="o">.</span><span class="n">projectId</span><span class="p">,</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">table_reference</span><span class="o">.</span><span class="n">datasetId</span><span class="p">,</span> |
| <span class="bp">self</span><span class="o">.</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="bp">self</span><span class="o">.</span><span class="n">use_native_datetime</span><span class="p">:</span> |
| <span class="n">requested_session</span><span class="o">.</span><span class="n">data_format</span> <span class="o">=</span> <span class="n">bq_storage</span><span class="o">.</span><span class="n">types</span><span class="o">.</span><span class="n">DataFormat</span><span class="o">.</span><span class="n">ARROW</span> |
| <span class="n">requested_session</span><span class="o">.</span><span class="n">read_options</span>\ |
| <span class="o">.</span><span class="n">arrow_serialization_options</span><span class="o">.</span><span class="n">buffer_compression</span> <span class="o">=</span> \ |
| <span class="n">bq_storage</span><span class="o">.</span><span class="n">types</span><span class="o">.</span><span class="n">ArrowSerializationOptions</span><span class="o">.</span><span class="n">CompressionCodec</span><span class="o">.</span><span class="n">LZ4_FRAME</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">requested_session</span><span class="o">.</span><span class="n">data_format</span> <span class="o">=</span> <span class="n">bq_storage</span><span class="o">.</span><span class="n">types</span><span class="o">.</span><span class="n">DataFormat</span><span class="o">.</span><span class="n">AVRO</span> |
| |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">selected_fields</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">requested_session</span><span class="o">.</span><span class="n">read_options</span><span class="o">.</span><span class="n">selected_fields</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">selected_fields</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">row_restriction</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">requested_session</span><span class="o">.</span><span class="n">read_options</span><span class="o">.</span><span class="n">row_restriction</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">row_restriction</span> |
| |
| <span class="n">storage_client</span> <span class="o">=</span> <span class="n">bq_storage</span><span class="o">.</span><span class="n">BigQueryReadClient</span><span class="p">()</span> |
| <span class="n">stream_count</span> <span class="o">=</span> <span class="mi">0</span> |
| <span class="k">if</span> <span class="n">desired_bundle_size</span> <span class="o">></span> <span class="mi">0</span><span class="p">:</span> |
| <span class="n">table_size</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_get_table_size</span><span class="p">(</span><span class="n">bq</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">table_reference</span><span class="p">)</span> |
| <span class="n">stream_count</span> <span class="o">=</span> <span class="nb">min</span><span class="p">(</span> |
| <span class="nb">int</span><span class="p">(</span><span class="n">table_size</span> <span class="o">/</span> <span class="n">desired_bundle_size</span><span class="p">),</span> |
| <span class="n">_CustomBigQueryStorageSource</span><span class="o">.</span><span class="n">MAX_SPLIT_COUNT</span><span class="p">)</span> |
| <span class="n">stream_count</span> <span class="o">=</span> <span class="nb">max</span><span class="p">(</span> |
| <span class="n">stream_count</span><span class="p">,</span> <span class="n">_CustomBigQueryStorageSource</span><span class="o">.</span><span class="n">MIN_SPLIT_COUNT</span><span class="p">)</span> |
| |
| <span class="n">parent</span> <span class="o">=</span> <span class="s1">'projects/</span><span class="si">{}</span><span class="s1">'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">table_reference</span><span class="o">.</span><span class="n">projectId</span><span class="p">)</span> |
| <span class="n">read_session</span> <span class="o">=</span> <span class="n">storage_client</span><span class="o">.</span><span class="n">create_read_session</span><span class="p">(</span> |
| <span class="n">parent</span><span class="o">=</span><span class="n">parent</span><span class="p">,</span> |
| <span class="n">read_session</span><span class="o">=</span><span class="n">requested_session</span><span class="p">,</span> |
| <span class="n">max_stream_count</span><span class="o">=</span><span class="n">stream_count</span><span class="p">)</span> |
| <span class="n">_LOGGER</span><span class="o">.</span><span class="n">info</span><span class="p">(</span> |
| <span class="s1">'Sent BigQuery Storage API CreateReadSession request: </span><span class="se">\n</span><span class="s1"> </span><span class="si">%s</span><span class="s1"> </span><span class="se">\n</span><span class="s1">'</span> |
| <span class="s1">'Received response </span><span class="se">\n</span><span class="s1"> </span><span class="si">%s</span><span class="s1">.'</span><span class="p">,</span> |
| <span class="n">requested_session</span><span class="p">,</span> |
| <span class="n">read_session</span><span class="p">)</span> |
| |
| <span class="bp">self</span><span class="o">.</span><span class="n">split_result</span> <span class="o">=</span> <span class="p">[</span> |
| <span class="n">_CustomBigQueryStorageStreamSource</span><span class="p">(</span> |
| <span class="n">stream</span><span class="o">.</span><span class="n">name</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">use_native_datetime</span><span class="p">)</span> |
| <span class="k">for</span> <span class="n">stream</span> <span class="ow">in</span> <span class="n">read_session</span><span class="o">.</span><span class="n">streams</span> |
| <span class="p">]</span> |
| |
| <span class="k">for</span> <span class="n">source</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">split_result</span><span class="p">:</span> |
| <span class="k">yield</span> <span class="n">SourceBundle</span><span class="p">(</span> |
| <span class="n">weight</span><span class="o">=</span><span class="mf">1.0</span><span class="p">,</span> <span class="n">source</span><span class="o">=</span><span class="n">source</span><span class="p">,</span> <span class="n">start_position</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">stop_position</span><span class="o">=</span><span class="kc">None</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">get_range_tracker</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">start_position</span><span class="p">,</span> <span class="n">stop_position</span><span class="p">):</span> |
| <span class="k">class</span> <span class="nc">NonePositionRangeTracker</span><span class="p">(</span><span class="n">RangeTracker</span><span class="p">):</span> |
| <span class="sd">"""A RangeTracker that always returns positions as None. Prevents the</span> |
| <span class="sd"> BigQuery Storage source from being read() before being split()."""</span> |
| <span class="k">def</span> <span class="nf">start_position</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="k">return</span> <span class="kc">None</span> |
| |
| <span class="k">def</span> <span class="nf">stop_position</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="k">return</span> <span class="kc">None</span> |
| |
| <span class="k">return</span> <span class="n">NonePositionRangeTracker</span><span class="p">()</span> |
| |
| <span class="k">def</span> <span class="nf">read</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">range_tracker</span><span class="p">):</span> |
| <span class="k">raise</span> <span class="ne">NotImplementedError</span><span class="p">(</span> |
| <span class="s1">'BigQuery storage source must be split before being read'</span><span class="p">)</span> |
| |
| |
| <span class="k">class</span> <span class="nc">_CustomBigQueryStorageStreamSource</span><span class="p">(</span><span class="n">BoundedSource</span><span class="p">):</span> |
| <span class="sd">"""A source representing a single stream in a read session."""</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">read_stream_name</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> <span class="n">use_native_datetime</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">bool</span><span class="p">]</span> <span class="o">=</span> <span class="kc">True</span><span class="p">):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">read_stream_name</span> <span class="o">=</span> <span class="n">read_stream_name</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">use_native_datetime</span> <span class="o">=</span> <span class="n">use_native_datetime</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">'output_format'</span><span class="p">:</span> <span class="s1">'ARROW'</span> <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">use_native_datetime</span> <span class="k">else</span> <span class="s1">'AVRO'</span><span class="p">,</span> |
| <span class="s1">'read_stream'</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">read_stream_name</span><span class="p">),</span> |
| <span class="s1">'use_native_datetime'</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_native_datetime</span><span class="p">)</span> |
| <span class="p">}</span> |
| |
| <span class="k">def</span> <span class="nf">estimate_size</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="c1"># The size of stream source cannot be estimate due to server-side liquid</span> |
| <span class="c1"># sharding.</span> |
| <span class="c1"># TODO(BEAM-12990): Implement progress reporting.</span> |
| <span class="k">return</span> <span class="kc">None</span> |
| |
| <span class="k">def</span> <span class="nf">split</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">desired_bundle_size</span><span class="p">,</span> <span class="n">start_position</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">stop_position</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="c1"># A stream source can't be split without reading from it due to</span> |
| <span class="c1"># server-side liquid sharding. A split will simply return the current source</span> |
| <span class="c1"># for now.</span> |
| <span class="k">return</span> <span class="n">SourceBundle</span><span class="p">(</span> |
| <span class="n">weight</span><span class="o">=</span><span class="mf">1.0</span><span class="p">,</span> |
| <span class="n">source</span><span class="o">=</span><span class="n">_CustomBigQueryStorageStreamSource</span><span class="p">(</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">read_stream_name</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">use_native_datetime</span><span class="p">),</span> |
| <span class="n">start_position</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">stop_position</span><span class="o">=</span><span class="kc">None</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">get_range_tracker</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">start_position</span><span class="p">,</span> <span class="n">stop_position</span><span class="p">):</span> |
| <span class="c1"># TODO(BEAM-12989): Implement dynamic work rebalancing.</span> |
| <span class="k">assert</span> <span class="n">start_position</span> <span class="ow">is</span> <span class="kc">None</span> |
| <span class="c1"># Defaulting to the start of the stream.</span> |
| <span class="n">start_position</span> <span class="o">=</span> <span class="mi">0</span> |
| <span class="c1"># Since the streams are unsplittable we choose OFFSET_INFINITY as the</span> |
| <span class="c1"># default end offset so that all data of the source gets read.</span> |
| <span class="n">stop_position</span> <span class="o">=</span> <span class="n">range_trackers</span><span class="o">.</span><span class="n">OffsetRangeTracker</span><span class="o">.</span><span class="n">OFFSET_INFINITY</span> |
| <span class="n">range_tracker</span> <span class="o">=</span> <span class="n">range_trackers</span><span class="o">.</span><span class="n">OffsetRangeTracker</span><span class="p">(</span> |
| <span class="n">start_position</span><span class="p">,</span> <span class="n">stop_position</span><span class="p">)</span> |
| <span class="c1"># Ensuring that all try_split() calls will be ignored by the Rangetracker.</span> |
| <span class="n">range_tracker</span> <span class="o">=</span> <span class="n">range_trackers</span><span class="o">.</span><span class="n">UnsplittableRangeTracker</span><span class="p">(</span><span class="n">range_tracker</span><span class="p">)</span> |
| |
| <span class="k">return</span> <span class="n">range_tracker</span> |
| |
| <span class="k">def</span> <span class="nf">read</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">range_tracker</span><span class="p">):</span> |
| <span class="n">_LOGGER</span><span class="o">.</span><span class="n">info</span><span class="p">(</span> |
| <span class="s2">"Started BigQuery Storage API read from stream </span><span class="si">%s</span><span class="s2">."</span><span class="p">,</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">read_stream_name</span><span class="p">)</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">use_native_datetime</span><span class="p">:</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">read_arrow</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">read_avro</span><span class="p">()</span> |
| |
| <span class="k">def</span> <span class="nf">read_arrow</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="n">storage_client</span> <span class="o">=</span> <span class="n">bq_storage</span><span class="o">.</span><span class="n">BigQueryReadClient</span><span class="p">()</span> |
| <span class="n">row_iter</span> <span class="o">=</span> <span class="nb">iter</span><span class="p">(</span><span class="n">storage_client</span><span class="o">.</span><span class="n">read_rows</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">read_stream_name</span><span class="p">)</span><span class="o">.</span><span class="n">rows</span><span class="p">())</span> |
| <span class="n">row</span> <span class="o">=</span> <span class="nb">next</span><span class="p">(</span><span class="n">row_iter</span><span class="p">,</span> <span class="kc">None</span><span class="p">)</span> |
| <span class="c1"># Handling the case where the user might provide very selective filters</span> |
| <span class="c1"># which can result in read_rows_response being empty.</span> |
| <span class="k">if</span> <span class="n">row</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="k">return</span> <span class="nb">iter</span><span class="p">([])</span> |
| |
| <span class="k">while</span> <span class="n">row</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">py_row</span> <span class="o">=</span> <span class="nb">dict</span><span class="p">(</span><span class="nb">map</span><span class="p">(</span><span class="k">lambda</span> <span class="n">item</span><span class="p">:</span> <span class="p">(</span><span class="n">item</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n">item</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span><span class="o">.</span><span class="n">as_py</span><span class="p">()),</span> <span class="n">row</span><span class="o">.</span><span class="n">items</span><span class="p">()))</span> |
| <span class="n">row</span> <span class="o">=</span> <span class="nb">next</span><span class="p">(</span><span class="n">row_iter</span><span class="p">,</span> <span class="kc">None</span><span class="p">)</span> |
| <span class="k">yield</span> <span class="n">py_row</span> |
| |
| <span class="k">def</span> <span class="nf">read_avro</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="n">storage_client</span> <span class="o">=</span> <span class="n">bq_storage</span><span class="o">.</span><span class="n">BigQueryReadClient</span><span class="p">()</span> |
| <span class="n">read_rows_iterator</span> <span class="o">=</span> <span class="nb">iter</span><span class="p">(</span><span class="n">storage_client</span><span class="o">.</span><span class="n">read_rows</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">read_stream_name</span><span class="p">))</span> |
| <span class="c1"># Handling the case where the user might provide very selective filters</span> |
| <span class="c1"># which can result in read_rows_response being empty.</span> |
| <span class="n">first_read_rows_response</span> <span class="o">=</span> <span class="nb">next</span><span class="p">(</span><span class="n">read_rows_iterator</span><span class="p">,</span> <span class="kc">None</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">first_read_rows_response</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="k">return</span> <span class="nb">iter</span><span class="p">([])</span> |
| |
| <span class="n">row_reader</span> <span class="o">=</span> <span class="n">_ReadReadRowsResponsesWithFastAvro</span><span class="p">(</span> |
| <span class="n">read_rows_iterator</span><span class="p">,</span> <span class="n">first_read_rows_response</span><span class="p">)</span> |
| <span class="k">return</span> <span class="nb">iter</span><span class="p">(</span><span class="n">row_reader</span><span class="p">)</span> |
| |
| |
| <span class="k">class</span> <span class="nc">_ReadReadRowsResponsesWithFastAvro</span><span class="p">():</span> |
| <span class="sd">"""An iterator that deserializes ReadRowsResponses using the fastavro</span> |
| <span class="sd"> library."""</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">read_rows_iterator</span><span class="p">,</span> <span class="n">read_rows_response</span><span class="p">):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">read_rows_iterator</span> <span class="o">=</span> <span class="n">read_rows_iterator</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">read_rows_response</span> <span class="o">=</span> <span class="n">read_rows_response</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">avro_schema</span> <span class="o">=</span> <span class="n">fastavro</span><span class="o">.</span><span class="n">parse_schema</span><span class="p">(</span> |
| <span class="n">json</span><span class="o">.</span><span class="n">loads</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">read_rows_response</span><span class="o">.</span><span class="n">avro_schema</span><span class="o">.</span><span class="n">schema</span><span class="p">))</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">bytes_reader</span> <span class="o">=</span> <span class="n">io</span><span class="o">.</span><span class="n">BytesIO</span><span class="p">(</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">read_rows_response</span><span class="o">.</span><span class="n">avro_rows</span><span class="o">.</span><span class="n">serialized_binary_rows</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="fm">__iter__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="k">return</span> <span class="bp">self</span> |
| |
| <span class="k">def</span> <span class="fm">__next__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="k">try</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">fastavro</span><span class="o">.</span><span class="n">schemaless_reader</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">bytes_reader</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">avro_schema</span><span class="p">)</span> |
| <span class="k">except</span> <span class="ne">StopIteration</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">read_rows_response</span> <span class="o">=</span> <span class="nb">next</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">read_rows_iterator</span><span class="p">,</span> <span class="kc">None</span><span class="p">)</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">read_rows_response</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">bytes_reader</span> <span class="o">=</span> <span class="n">io</span><span class="o">.</span><span class="n">BytesIO</span><span class="p">(</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">read_rows_response</span><span class="o">.</span><span class="n">avro_rows</span><span class="o">.</span><span class="n">serialized_binary_rows</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">fastavro</span><span class="o">.</span><span class="n">schemaless_reader</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">bytes_reader</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">avro_schema</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">StopIteration</span> |
| |
| |
| <div class="viewcode-block" id="BigQuerySink"><a class="viewcode-back" href="../../../../apache_beam.io.gcp.bigquery.html#apache_beam.io.gcp.bigquery.BigQuerySink">[docs]</a><span class="nd">@deprecated</span><span class="p">(</span><span class="n">since</span><span class="o">=</span><span class="s1">'2.11.0'</span><span class="p">,</span> <span class="n">current</span><span class="o">=</span><span class="s2">"WriteToBigQuery"</span><span class="p">)</span> |
| <span class="k">class</span> <span class="nc">BigQuerySink</span><span class="p">(</span><span class="n">dataflow_io</span><span class="o">.</span><span class="n">NativeSink</span><span class="p">):</span> |
| <span class="sd">"""A sink based on a BigQuery table.</span> |
| |
| <span class="sd"> This BigQuery sink triggers a Dataflow native sink for BigQuery</span> |
| <span class="sd"> that only supports batch pipelines.</span> |
| <span class="sd"> Instead of using this sink directly, please use WriteToBigQuery</span> |
| <span class="sd"> transform that works for both batch and streaming pipelines.</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">table</span><span class="p">,</span> |
| <span class="n">dataset</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">project</span><span class="o">=</span><span class="kc">None</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">create_disposition</span><span class="o">=</span><span class="n">BigQueryDisposition</span><span class="o">.</span><span class="n">CREATE_IF_NEEDED</span><span class="p">,</span> |
| <span class="n">write_disposition</span><span class="o">=</span><span class="n">BigQueryDisposition</span><span class="o">.</span><span class="n">WRITE_EMPTY</span><span class="p">,</span> |
| <span class="n">validate</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> |
| <span class="n">coder</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">kms_key</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="sd">"""Initialize a BigQuerySink.</span> |
| |
| <span class="sd"> Args:</span> |
| <span class="sd"> table (str): The ID of the table. The ID must contain only letters</span> |
| <span class="sd"> ``a-z``, ``A-Z``, numbers ``0-9``, or underscores ``_``. If</span> |
| <span class="sd"> **dataset** argument is :data:`None` then the table argument must</span> |
| <span class="sd"> contain the entire table reference specified as: ``'DATASET.TABLE'`` or</span> |
| <span class="sd"> ``'PROJECT:DATASET.TABLE'``.</span> |
| <span class="sd"> dataset (str): The ID of the dataset containing this table or</span> |
| <span class="sd"> :data:`None` if the table reference is specified entirely by the table</span> |
| <span class="sd"> argument.</span> |
| <span class="sd"> project (str): The ID of the project containing this table or</span> |
| <span class="sd"> :data:`None` if the table reference is specified entirely by the table</span> |
| <span class="sd"> argument.</span> |
| <span class="sd"> schema (str): The schema to be used if the BigQuery table to write has</span> |
| <span class="sd"> to be created. This can be either specified as a</span> |
| <span class="sd"> :class:`~apache_beam.io.gcp.internal.clients.bigquery.\</span> |
| <span class="sd">bigquery_v2_messages.TableSchema` object or a single string of the form</span> |
| <span class="sd"> ``'field1:type1,field2:type2,field3:type3'`` that defines a comma</span> |
| <span class="sd"> separated list of fields. Here ``'type'`` should specify the BigQuery</span> |
| <span class="sd"> type of the field. Single string based schemas do not support nested</span> |
| <span class="sd"> fields, repeated fields, or specifying a BigQuery mode for fields (mode</span> |
| <span class="sd"> will always be set to ``'NULLABLE'``).</span> |
| <span class="sd"> create_disposition (BigQueryDisposition): A string describing what</span> |
| <span class="sd"> happens if the table does not exist. Possible values are:</span> |
| |
| <span class="sd"> * :attr:`BigQueryDisposition.CREATE_IF_NEEDED`: create if does not</span> |
| <span class="sd"> exist.</span> |
| <span class="sd"> * :attr:`BigQueryDisposition.CREATE_NEVER`: fail the write if does not</span> |
| <span class="sd"> exist.</span> |
| |
| <span class="sd"> write_disposition (BigQueryDisposition): A string describing what</span> |
| <span class="sd"> happens if the table has already some data. Possible values are:</span> |
| |
| <span class="sd"> * :attr:`BigQueryDisposition.WRITE_TRUNCATE`: delete existing rows.</span> |
| <span class="sd"> * :attr:`BigQueryDisposition.WRITE_APPEND`: add to existing rows.</span> |
| <span class="sd"> * :attr:`BigQueryDisposition.WRITE_EMPTY`: fail the write if table not</span> |
| <span class="sd"> empty.</span> |
| |
| <span class="sd"> validate (bool): If :data:`True`, various checks will be done when sink</span> |
| <span class="sd"> gets initialized (e.g., is table present given the disposition</span> |
| <span class="sd"> arguments?). This should be :data:`True` for most scenarios in order to</span> |
| <span class="sd"> catch errors as early as possible (pipeline construction instead of</span> |
| <span class="sd"> pipeline execution). It should be :data:`False` if the table is created</span> |
| <span class="sd"> during pipeline execution by a previous step.</span> |
| <span class="sd"> coder (~apache_beam.coders.coders.Coder): The coder for the</span> |
| <span class="sd"> table rows if serialized to disk. If :data:`None`, then the default</span> |
| <span class="sd"> coder is :class:`~apache_beam.io.gcp.bigquery_tools.RowAsDictJsonCoder`,</span> |
| <span class="sd"> which will interpret every element written to the sink as a dictionary</span> |
| <span class="sd"> that will be JSON serialized as a line in a file. This argument needs a</span> |
| <span class="sd"> value only in special cases when writing table rows as dictionaries is</span> |
| <span class="sd"> not desirable.</span> |
| <span class="sd"> kms_key (str): Optional Cloud KMS key name for use when creating new</span> |
| <span class="sd"> tables.</span> |
| |
| <span class="sd"> Raises:</span> |
| <span class="sd"> TypeError: if the schema argument is not a :class:`str` or a</span> |
| <span class="sd"> :class:`~apache_beam.io.gcp.internal.clients.bigquery.\</span> |
| <span class="sd">bigquery_v2_messages.TableSchema` object.</span> |
| <span class="sd"> ValueError: if the table reference as a string does not</span> |
| <span class="sd"> match the expected format.</span> |
| <span class="sd"> """</span> |
| <span class="c1"># Import here to avoid adding the dependency for local running scenarios.</span> |
| <span class="k">try</span><span class="p">:</span> |
| <span class="c1"># pylint: disable=wrong-import-order, wrong-import-position</span> |
| <span class="kn">from</span> <span class="nn">apitools.base</span> <span class="kn">import</span> <span class="n">py</span> <span class="c1"># pylint: disable=unused-import</span> |
| <span class="k">except</span> <span class="ne">ImportError</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ImportError</span><span class="p">(</span> |
| <span class="s1">'Google Cloud IO not available, '</span> |
| <span class="s1">'please install apache_beam[gcp]'</span><span class="p">)</span> |
| |
| <span class="bp">self</span><span class="o">.</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">table</span><span class="p">,</span> <span class="n">dataset</span><span class="p">,</span> <span class="n">project</span><span class="p">)</span> |
| <span class="c1"># Transform the table schema into a bigquery.TableSchema instance.</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">schema</span><span class="p">,</span> <span class="nb">str</span><span class="p">):</span> |
| <span class="c1"># TODO(silviuc): Should add a regex-based validation of the format.</span> |
| <span class="n">table_schema</span> <span class="o">=</span> <span class="n">bigquery</span><span class="o">.</span><span class="n">TableSchema</span><span class="p">()</span> |
| <span class="n">schema_list</span> <span class="o">=</span> <span class="p">[</span><span class="n">s</span><span class="o">.</span><span class="n">strip</span><span class="p">(</span><span class="s1">' '</span><span class="p">)</span> <span class="k">for</span> <span class="n">s</span> <span class="ow">in</span> <span class="n">schema</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s1">','</span><span class="p">)]</span> |
| <span class="k">for</span> <span class="n">field_and_type</span> <span class="ow">in</span> <span class="n">schema_list</span><span class="p">:</span> |
| <span class="n">field_name</span><span class="p">,</span> <span class="n">field_type</span> <span class="o">=</span> <span class="n">field_and_type</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s1">':'</span><span class="p">)</span> |
| <span class="n">field_schema</span> <span class="o">=</span> <span class="n">bigquery</span><span class="o">.</span><span class="n">TableFieldSchema</span><span class="p">()</span> |
| <span class="n">field_schema</span><span class="o">.</span><span class="n">name</span> <span class="o">=</span> <span class="n">field_name</span> |
| <span class="n">field_schema</span><span class="o">.</span><span class="n">type</span> <span class="o">=</span> <span class="n">field_type</span> |
| <span class="n">field_schema</span><span class="o">.</span><span class="n">mode</span> <span class="o">=</span> <span class="s1">'NULLABLE'</span> |
| <span class="n">table_schema</span><span class="o">.</span><span class="n">fields</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">field_schema</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">table_schema</span> <span class="o">=</span> <span class="n">table_schema</span> |
| <span class="k">elif</span> <span class="n">schema</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="c1"># TODO(silviuc): Should check that table exists if no schema specified.</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">table_schema</span> <span class="o">=</span> <span class="n">schema</span> |
| <span class="k">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">schema</span><span class="p">,</span> <span class="n">bigquery</span><span class="o">.</span><span class="n">TableSchema</span><span class="p">):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">table_schema</span> <span class="o">=</span> <span class="n">schema</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">TypeError</span><span class="p">(</span><span class="s1">'Unexpected schema argument: </span><span class="si">%s</span><span class="s1">.'</span> <span class="o">%</span> <span class="n">schema</span><span class="p">)</span> |
| |
| <span class="bp">self</span><span class="o">.</span><span class="n">create_disposition</span> <span class="o">=</span> <span class="n">BigQueryDisposition</span><span class="o">.</span><span class="n">validate_create</span><span class="p">(</span> |
| <span class="n">create_disposition</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">write_disposition</span> <span class="o">=</span> <span class="n">BigQueryDisposition</span><span class="o">.</span><span class="n">validate_write</span><span class="p">(</span> |
| <span class="n">write_disposition</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">validate</span> <span class="o">=</span> <span class="n">validate</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">coder</span> <span class="o">=</span> <span class="n">coder</span> <span class="ow">or</span> <span class="n">bigquery_tools</span><span class="o">.</span><span class="n">RowAsDictJsonCoder</span><span class="p">()</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="k">def</span> <span class="nf">display_data</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="n">res</span> <span class="o">=</span> <span class="p">{}</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">table_reference</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">tableSpec</span> <span class="o">=</span> <span class="s1">'</span><span class="si">{}</span><span class="s1">.</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">table_reference</span><span class="o">.</span><span class="n">datasetId</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</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="bp">self</span><span class="o">.</span><span class="n">table_reference</span><span class="o">.</span><span class="n">projectId</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">tableSpec</span> <span class="o">=</span> <span class="s1">'</span><span class="si">{}</span><span class="s1">:</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">table_reference</span><span class="o">.</span><span class="n">projectId</span><span class="p">,</span> <span class="n">tableSpec</span><span class="p">)</span> |
| <span class="n">res</span><span class="p">[</span><span class="s1">'table'</span><span class="p">]</span> <span class="o">=</span> <span class="n">DisplayDataItem</span><span class="p">(</span><span class="n">tableSpec</span><span class="p">,</span> <span class="n">label</span><span class="o">=</span><span class="s1">'Table'</span><span class="p">)</span> |
| |
| <span class="n">res</span><span class="p">[</span><span class="s1">'validation'</span><span class="p">]</span> <span class="o">=</span> <span class="n">DisplayDataItem</span><span class="p">(</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">validate</span><span class="p">,</span> <span class="n">label</span><span class="o">=</span><span class="s2">"Validation Enabled"</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">res</span> |
| |
| <span class="k">def</span> <span class="nf">schema_as_json</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""Returns the TableSchema associated with the sink as a JSON string."""</span> |
| <span class="k">def</span> <span class="nf">schema_list_as_object</span><span class="p">(</span><span class="n">schema_list</span><span class="p">):</span> |
| <span class="sd">"""Returns a list of TableFieldSchema objects as a list of dicts."""</span> |
| <span class="n">fields</span> <span class="o">=</span> <span class="p">[]</span> |
| <span class="k">for</span> <span class="n">f</span> <span class="ow">in</span> <span class="n">schema_list</span><span class="p">:</span> |
| <span class="n">fs</span> <span class="o">=</span> <span class="p">{</span><span class="s1">'name'</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="s1">'type'</span><span class="p">:</span> <span class="n">f</span><span class="o">.</span><span class="n">type</span><span class="p">}</span> |
| <span class="k">if</span> <span class="n">f</span><span class="o">.</span><span class="n">description</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">fs</span><span class="p">[</span><span class="s1">'description'</span><span class="p">]</span> <span class="o">=</span> <span class="n">f</span><span class="o">.</span><span class="n">description</span> |
| <span class="k">if</span> <span class="n">f</span><span class="o">.</span><span class="n">mode</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">fs</span><span class="p">[</span><span class="s1">'mode'</span><span class="p">]</span> <span class="o">=</span> <span class="n">f</span><span class="o">.</span><span class="n">mode</span> |
| <span class="k">if</span> <span class="n">f</span><span class="o">.</span><span class="n">type</span><span class="o">.</span><span class="n">lower</span><span class="p">()</span> <span class="o">==</span> <span class="s1">'record'</span><span class="p">:</span> |
| <span class="n">fs</span><span class="p">[</span><span class="s1">'fields'</span><span class="p">]</span> <span class="o">=</span> <span class="n">schema_list_as_object</span><span class="p">(</span><span class="n">f</span><span class="o">.</span><span class="n">fields</span><span class="p">)</span> |
| <span class="n">fields</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">fs</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">fields</span> |
| |
| <span class="k">return</span> <span class="n">json</span><span class="o">.</span><span class="n">dumps</span><span class="p">(</span> |
| <span class="p">{</span><span class="s1">'fields'</span><span class="p">:</span> <span class="n">schema_list_as_object</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">table_schema</span><span class="o">.</span><span class="n">fields</span><span class="p">)})</span> |
| |
| <span class="nd">@property</span> |
| <span class="k">def</span> <span class="nf">format</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""Sink format name required for remote execution."""</span> |
| <span class="k">return</span> <span class="s1">'bigquery'</span> |
| |
| <span class="k">def</span> <span class="nf">writer</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">test_bigquery_client</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">buffer_size</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">bigquery_tools</span><span class="o">.</span><span class="n">BigQueryWriter</span><span class="p">(</span> |
| <span class="n">sink</span><span class="o">=</span><span class="bp">self</span><span class="p">,</span> |
| <span class="n">test_bigquery_client</span><span class="o">=</span><span class="n">test_bigquery_client</span><span class="p">,</span> |
| <span class="n">buffer_size</span><span class="o">=</span><span class="n">buffer_size</span><span class="p">)</span></div> |
| |
| |
| <span class="n">_KNOWN_TABLES</span> <span class="o">=</span> <span class="nb">set</span><span class="p">()</span> |
| |
| |
| <span class="k">class</span> <span class="nc">BigQueryWriteFn</span><span class="p">(</span><span class="n">DoFn</span><span class="p">):</span> |
| <span class="sd">"""A ``DoFn`` that streams writes to BigQuery once the table is created."""</span> |
| |
| <span class="n">DEFAULT_MAX_BUFFERED_ROWS</span> <span class="o">=</span> <span class="mi">2000</span> |
| <span class="n">DEFAULT_MAX_BATCH_SIZE</span> <span class="o">=</span> <span class="mi">500</span> |
| |
| <span class="n">FAILED_ROWS</span> <span class="o">=</span> <span class="s1">'FailedRows'</span> |
| <span class="n">STREAMING_API_LOGGING_FREQUENCY_SEC</span> <span class="o">=</span> <span class="mi">300</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">batch_size</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">create_disposition</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">write_disposition</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">kms_key</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">test_client</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">max_buffered_rows</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">retry_strategy</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">additional_bq_parameters</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">ignore_insert_ids</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> |
| <span class="n">with_batched_input</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> |
| <span class="n">ignore_unknown_columns</span><span class="o">=</span><span class="kc">False</span><span class="p">):</span> |
| <span class="sd">"""Initialize a WriteToBigQuery transform.</span> |
| |
| <span class="sd"> Args:</span> |
| <span class="sd"> batch_size: Number of rows to be written to BQ per streaming API insert.</span> |
| <span class="sd"> schema: The schema to be used if the BigQuery table to write has to be</span> |
| <span class="sd"> created. This can be either specified as a 'bigquery.TableSchema' object</span> |
| <span class="sd"> or a single string of the form 'field1:type1,field2:type2,field3:type3'</span> |
| <span class="sd"> that defines a comma separated list of fields. Here 'type' should</span> |
| <span class="sd"> specify the BigQuery type of the field. Single string based schemas do</span> |
| <span class="sd"> not support nested fields, repeated fields, or specifying a BigQuery</span> |
| <span class="sd"> mode for fields (mode will always be set to 'NULLABLE').</span> |
| <span class="sd"> create_disposition: A string describing what happens if the table does not</span> |
| <span class="sd"> exist. Possible values are:</span> |
| <span class="sd"> - BigQueryDisposition.CREATE_IF_NEEDED: create if does not exist.</span> |
| <span class="sd"> - BigQueryDisposition.CREATE_NEVER: fail the write if does not exist.</span> |
| <span class="sd"> write_disposition: A string describing what happens if the table has</span> |
| <span class="sd"> already some data. Possible values are:</span> |
| <span class="sd"> - BigQueryDisposition.WRITE_TRUNCATE: delete existing rows.</span> |
| <span class="sd"> - BigQueryDisposition.WRITE_APPEND: add to existing rows.</span> |
| <span class="sd"> - BigQueryDisposition.WRITE_EMPTY: fail the write if table not empty.</span> |
| <span class="sd"> For streaming pipelines WriteTruncate can not be used.</span> |
| <span class="sd"> kms_key: Optional Cloud KMS key name for use when creating new tables.</span> |
| <span class="sd"> test_client: Override the default bigquery client used for testing.</span> |
| |
| <span class="sd"> max_buffered_rows: The maximum number of rows that are allowed to stay</span> |
| <span class="sd"> buffered when running dynamic destinations. When destinations are</span> |
| <span class="sd"> dynamic, it is important to keep caches small even when a single</span> |
| <span class="sd"> batch has not been completely filled up.</span> |
| <span class="sd"> retry_strategy: The strategy to use when retrying streaming inserts</span> |
| <span class="sd"> into BigQuery. Options are shown in bigquery_tools.RetryStrategy attrs.</span> |
| <span class="sd"> additional_bq_parameters (dict, callable): A set of additional parameters</span> |
| <span class="sd"> to be passed when creating a BigQuery table. These are passed when</span> |
| <span class="sd"> triggering a load job for FILE_LOADS, and when creating a new table for</span> |
| <span class="sd"> STREAMING_INSERTS.</span> |
| <span class="sd"> ignore_insert_ids: When using the STREAMING_INSERTS method to write data</span> |
| <span class="sd"> to BigQuery, `insert_ids` are a feature of BigQuery that support</span> |
| <span class="sd"> deduplication of events. If your use case is not sensitive to</span> |
| <span class="sd"> duplication of data inserted to BigQuery, set `ignore_insert_ids`</span> |
| <span class="sd"> to True to increase the throughput for BQ writing. See:</span> |
| <span class="sd"> https://cloud.google.com/bigquery/streaming-data-into-bigquery#disabling_best_effort_de-duplication</span> |
| <span class="sd"> with_batched_input: Whether the input has already been batched per</span> |
| <span class="sd"> destination. If not, perform best-effort batching per destination within</span> |
| <span class="sd"> a bundle.</span> |
| <span class="sd"> ignore_unknown_columns: Accept rows that contain values that do not match</span> |
| <span class="sd"> the schema. The unknown values are ignored. Default is False,</span> |
| <span class="sd"> which treats unknown values as errors. See reference:</span> |
| <span class="sd"> https://cloud.google.com/bigquery/docs/reference/rest/v2/tabledata/insertAll</span> |
| |
| <span class="sd"> """</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">schema</span> <span class="o">=</span> <span class="n">schema</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">test_client</span> <span class="o">=</span> <span class="n">test_client</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">create_disposition</span> <span class="o">=</span> <span class="n">create_disposition</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">write_disposition</span> <span class="o">=</span> <span class="n">write_disposition</span> |
| <span class="k">if</span> <span class="n">write_disposition</span> <span class="ow">in</span> <span class="p">(</span><span class="n">BigQueryDisposition</span><span class="o">.</span><span class="n">WRITE_EMPTY</span><span class="p">,</span> |
| <span class="n">BigQueryDisposition</span><span class="o">.</span><span class="n">WRITE_TRUNCATE</span><span class="p">):</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span> |
| <span class="s1">'Write disposition </span><span class="si">%s</span><span class="s1"> is not supported for'</span> |
| <span class="s1">' streaming inserts to BigQuery'</span> <span class="o">%</span> <span class="n">write_disposition</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_rows_buffer</span> <span class="o">=</span> <span class="p">[]</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_reset_rows_buffer</span><span class="p">()</span> |
| |
| <span class="bp">self</span><span class="o">.</span><span class="n">_total_buffered_rows</span> <span class="o">=</span> <span class="mi">0</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">_max_batch_size</span> <span class="o">=</span> <span class="n">batch_size</span> <span class="ow">or</span> <span class="n">BigQueryWriteFn</span><span class="o">.</span><span class="n">DEFAULT_MAX_BATCH_SIZE</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_max_buffered_rows</span> <span class="o">=</span> <span class="p">(</span> |
| <span class="n">max_buffered_rows</span> <span class="ow">or</span> <span class="n">BigQueryWriteFn</span><span class="o">.</span><span class="n">DEFAULT_MAX_BUFFERED_ROWS</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_retry_strategy</span> <span class="o">=</span> <span class="n">retry_strategy</span> <span class="ow">or</span> <span class="n">RetryStrategy</span><span class="o">.</span><span class="n">RETRY_ALWAYS</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">ignore_insert_ids</span> <span class="o">=</span> <span class="n">ignore_insert_ids</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">with_batched_input</span> <span class="o">=</span> <span class="n">with_batched_input</span> |
| |
| <span class="bp">self</span><span class="o">.</span><span class="n">additional_bq_parameters</span> <span class="o">=</span> <span class="n">additional_bq_parameters</span> <span class="ow">or</span> <span class="p">{}</span> |
| |
| <span class="c1"># accumulate the total time spent in exponential backoff</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_throttled_secs</span> <span class="o">=</span> <span class="n">Metrics</span><span class="o">.</span><span class="n">counter</span><span class="p">(</span> |
| <span class="n">BigQueryWriteFn</span><span class="p">,</span> <span class="s2">"cumulativeThrottlingSeconds"</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">batch_size_metric</span> <span class="o">=</span> <span class="n">Metrics</span><span class="o">.</span><span class="n">distribution</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="vm">__class__</span><span class="p">,</span> <span class="s2">"batch_size"</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">batch_latency_metric</span> <span class="o">=</span> <span class="n">Metrics</span><span class="o">.</span><span class="n">distribution</span><span class="p">(</span> |
| <span class="bp">self</span><span class="o">.</span><span class="vm">__class__</span><span class="p">,</span> <span class="s2">"batch_latency_ms"</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">failed_rows_metric</span> <span class="o">=</span> <span class="n">Metrics</span><span class="o">.</span><span class="n">distribution</span><span class="p">(</span> |
| <span class="bp">self</span><span class="o">.</span><span class="vm">__class__</span><span class="p">,</span> <span class="s2">"rows_failed_per_batch"</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">bigquery_wrapper</span> <span class="o">=</span> <span class="kc">None</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">streaming_api_logging_frequency_sec</span> <span class="o">=</span> <span class="p">(</span> |
| <span class="n">BigQueryWriteFn</span><span class="o">.</span><span class="n">STREAMING_API_LOGGING_FREQUENCY_SEC</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">ignore_unknown_columns</span> <span class="o">=</span> <span class="n">ignore_unknown_columns</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">'max_batch_size'</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">_max_batch_size</span><span class="p">,</span> |
| <span class="s1">'max_buffered_rows'</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">_max_buffered_rows</span><span class="p">,</span> |
| <span class="s1">'retry_strategy'</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">_retry_strategy</span><span class="p">,</span> |
| <span class="s1">'create_disposition'</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">create_disposition</span><span class="p">),</span> |
| <span class="s1">'write_disposition'</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">write_disposition</span><span class="p">),</span> |
| <span class="s1">'additional_bq_parameters'</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">additional_bq_parameters</span><span class="p">),</span> |
| <span class="s1">'ignore_insert_ids'</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">ignore_insert_ids</span><span class="p">),</span> |
| <span class="s1">'ignore_unknown_columns'</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">ignore_unknown_columns</span><span class="p">)</span> |
| <span class="p">}</span> |
| |
| <span class="k">def</span> <span class="nf">_reset_rows_buffer</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_rows_buffer</span> <span class="o">=</span> <span class="n">collections</span><span class="o">.</span><span class="n">defaultdict</span><span class="p">(</span><span class="k">lambda</span><span class="p">:</span> <span class="p">[])</span> |
| |
| <span class="nd">@staticmethod</span> |
| <span class="k">def</span> <span class="nf">get_table_schema</span><span class="p">(</span><span class="n">schema</span><span class="p">):</span> |
| <span class="sd">"""Transform the table schema into a bigquery.TableSchema instance.</span> |
| |
| <span class="sd"> Args:</span> |
| <span class="sd"> schema: The schema to be used if the BigQuery table to write has to be</span> |
| <span class="sd"> created. This is a dictionary object created in the WriteToBigQuery</span> |
| <span class="sd"> transform.</span> |
| <span class="sd"> Returns:</span> |
| <span class="sd"> table_schema: The schema to be used if the BigQuery table to write has</span> |
| <span class="sd"> to be created but in the bigquery.TableSchema format.</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="n">schema</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">schema</span> |
| <span class="k">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">schema</span><span class="p">,</span> <span class="nb">str</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">bigquery_tools</span><span class="o">.</span><span class="n">parse_table_schema_from_json</span><span class="p">(</span><span class="n">schema</span><span class="p">)</span> |
| <span class="k">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">schema</span><span class="p">,</span> <span class="nb">dict</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">bigquery_tools</span><span class="o">.</span><span class="n">parse_table_schema_from_json</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="n">schema</span><span class="p">))</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">TypeError</span><span class="p">(</span><span class="s1">'Unexpected schema argument: </span><span class="si">%s</span><span class="s1">.'</span> <span class="o">%</span> <span class="n">schema</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">start_bundle</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_reset_rows_buffer</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">bigquery_wrapper</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">bigquery_wrapper</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">client</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">test_client</span><span class="p">)</span> |
| |
| <span class="p">(</span> |
| <span class="n">bigquery_tools</span><span class="o">.</span><span class="n">BigQueryWrapper</span><span class="o">.</span><span class="n">HISTOGRAM_METRIC_LOGGER</span><span class="o">.</span> |
| <span class="n">minimum_logging_frequency_msec</span> |
| <span class="p">)</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">streaming_api_logging_frequency_sec</span> <span class="o">*</span> <span class="mi">1000</span> |
| |
| <span class="bp">self</span><span class="o">.</span><span class="n">_backoff_calculator</span> <span class="o">=</span> <span class="nb">iter</span><span class="p">(</span> |
| <span class="n">retry</span><span class="o">.</span><span class="n">FuzzedExponentialIntervals</span><span class="p">(</span> |
| <span class="n">initial_delay_secs</span><span class="o">=</span><span class="mf">0.2</span><span class="p">,</span> <span class="n">num_retries</span><span class="o">=</span><span class="mi">10000</span><span class="p">,</span> <span class="n">max_delay_secs</span><span class="o">=</span><span class="mi">1500</span><span class="p">))</span> |
| |
| <span class="k">def</span> <span class="nf">_create_table_if_needed</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">table_reference</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">str_table_reference</span> <span class="o">=</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="si">%s</span><span class="s1">'</span> <span class="o">%</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">str_table_reference</span> <span class="ow">in</span> <span class="n">_KNOWN_TABLES</span><span class="p">:</span> |
| <span class="k">return</span> |
| |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">create_disposition</span> <span class="o">==</span> <span class="n">BigQueryDisposition</span><span class="o">.</span><span class="n">CREATE_NEVER</span><span class="p">:</span> |
| <span class="c1"># If we never want to create the table, we assume it already exists,</span> |
| <span class="c1"># and avoid the get-or-create step.</span> |
| <span class="k">return</span> |
| |
| <span class="n">_LOGGER</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span> |
| <span class="s1">'Creating or getting table </span><span class="si">%s</span><span class="s1"> with schema </span><span class="si">%s</span><span class="s1">.'</span><span class="p">,</span> <span class="n">table_reference</span><span class="p">,</span> <span class="n">schema</span><span class="p">)</span> |
| |
| <span class="n">table_schema</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_table_schema</span><span class="p">(</span><span class="n">schema</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="n">table_reference</span><span class="o">.</span><span class="n">projectId</span> <span class="ow">is</span> <span class="kc">None</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="n">vp</span><span class="o">.</span><span class="n">RuntimeValueProvider</span><span class="o">.</span><span class="n">get_value</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="s1">''</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">bigquery_wrapper</span><span class="o">.</span><span class="n">get_or_create_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="n">table_schema</span><span class="p">,</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">create_disposition</span><span class="p">,</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">write_disposition</span><span class="p">,</span> |
| <span class="n">additional_create_parameters</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">additional_bq_parameters</span><span class="p">)</span> |
| <span class="n">_KNOWN_TABLES</span><span class="o">.</span><span class="n">add</span><span class="p">(</span><span class="n">str_table_reference</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="o">*</span><span class="n">schema_side_inputs</span><span class="p">):</span> |
| <span class="n">destination</span> <span class="o">=</span> <span class="n">bigquery_tools</span><span class="o">.</span><span class="n">get_hashable_destination</span><span class="p">(</span><span class="n">element</span><span class="p">[</span><span class="mi">0</span><span class="p">])</span> |
| |
| <span class="k">if</span> <span class="n">callable</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">schema</span><span class="p">):</span> |
| <span class="n">schema</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">schema</span><span class="p">(</span><span class="n">destination</span><span class="p">,</span> <span class="o">*</span><span class="n">schema_side_inputs</span><span class="p">)</span> |
| <span class="k">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">schema</span><span class="p">,</span> <span class="n">vp</span><span class="o">.</span><span class="n">ValueProvider</span><span class="p">):</span> |
| <span class="n">schema</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">schema</span><span class="o">.</span><span class="n">get</span><span class="p">()</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">schema</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">schema</span> |
| |
| <span class="bp">self</span><span class="o">.</span><span class="n">_create_table_if_needed</span><span class="p">(</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">destination</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">with_batched_input</span><span class="p">:</span> |
| <span class="n">row_and_insert_id</span> <span class="o">=</span> <span class="n">element</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">_rows_buffer</span><span class="p">[</span><span class="n">destination</span><span class="p">]</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">row_and_insert_id</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_total_buffered_rows</span> <span class="o">+=</span> <span class="mi">1</span> |
| <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_rows_buffer</span><span class="p">[</span><span class="n">destination</span><span class="p">])</span> <span class="o">>=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_max_batch_size</span><span class="p">:</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_flush_batch</span><span class="p">(</span><span class="n">destination</span><span class="p">)</span> |
| <span class="k">elif</span> <span class="bp">self</span><span class="o">.</span><span class="n">_total_buffered_rows</span> <span class="o">>=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_max_buffered_rows</span><span class="p">:</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_flush_all_batches</span><span class="p">()</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="c1"># The input is already batched per destination, flush the rows now.</span> |
| <span class="n">batched_rows</span> <span class="o">=</span> <span class="n">element</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">_rows_buffer</span><span class="p">[</span><span class="n">destination</span><span class="p">]</span><span class="o">.</span><span class="n">extend</span><span class="p">(</span><span class="n">batched_rows</span><span class="p">)</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_flush_batch</span><span class="p">(</span><span class="n">destination</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">finish_bundle</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="n">bigquery_tools</span><span class="o">.</span><span class="n">BigQueryWrapper</span><span class="o">.</span><span class="n">HISTOGRAM_METRIC_LOGGER</span><span class="o">.</span><span class="n">log_metrics</span><span class="p">(</span> |
| <span class="n">reset_after_logging</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_flush_all_batches</span><span class="p">()</span> |
| |
| <span class="k">def</span> <span class="nf">_flush_all_batches</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="n">_LOGGER</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span> |
| <span class="s1">'Attempting to flush to all destinations. Total buffered: </span><span class="si">%s</span><span class="s1">'</span><span class="p">,</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_total_buffered_rows</span><span class="p">)</span> |
| |
| <span class="k">return</span> <span class="n">itertools</span><span class="o">.</span><span class="n">chain</span><span class="p">(</span> |
| <span class="o">*</span><span class="p">[</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_flush_batch</span><span class="p">(</span><span class="n">destination</span><span class="p">)</span> |
| <span class="k">for</span> <span class="n">destination</span> <span class="ow">in</span> <span class="nb">list</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_rows_buffer</span><span class="o">.</span><span class="n">keys</span><span class="p">())</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_rows_buffer</span><span class="p">[</span><span class="n">destination</span><span class="p">]</span> |
| <span class="p">])</span> |
| |
| <span class="k">def</span> <span class="nf">_flush_batch</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">destination</span><span class="p">):</span> |
| |
| <span class="c1"># Flush the current batch of rows to BigQuery.</span> |
| <span class="n">rows_and_insert_ids</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_rows_buffer</span><span class="p">[</span><span class="n">destination</span><span class="p">]</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">destination</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="n">table_reference</span><span class="o">.</span><span class="n">projectId</span> <span class="ow">is</span> <span class="kc">None</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="n">vp</span><span class="o">.</span><span class="n">RuntimeValueProvider</span><span class="o">.</span><span class="n">get_value</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="s1">''</span><span class="p">)</span> |
| |
| <span class="n">_LOGGER</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span> |
| <span class="s1">'Flushing data to </span><span class="si">%s</span><span class="s1">. Total </span><span class="si">%s</span><span class="s1"> rows.'</span><span class="p">,</span> |
| <span class="n">destination</span><span class="p">,</span> |
| <span class="nb">len</span><span class="p">(</span><span class="n">rows_and_insert_ids</span><span class="p">))</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">batch_size_metric</span><span class="o">.</span><span class="n">update</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">rows_and_insert_ids</span><span class="p">))</span> |
| |
| <span class="n">rows</span> <span class="o">=</span> <span class="p">[</span><span class="n">r</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="k">for</span> <span class="n">r</span> <span class="ow">in</span> <span class="n">rows_and_insert_ids</span><span class="p">]</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">ignore_insert_ids</span><span class="p">:</span> |
| <span class="n">insert_ids</span> <span class="o">=</span> <span class="p">[</span><span class="kc">None</span> <span class="k">for</span> <span class="n">r</span> <span class="ow">in</span> <span class="n">rows_and_insert_ids</span><span class="p">]</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">insert_ids</span> <span class="o">=</span> <span class="p">[</span><span class="n">r</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> <span class="k">for</span> <span class="n">r</span> <span class="ow">in</span> <span class="n">rows_and_insert_ids</span><span class="p">]</span> |
| |
| <span class="k">while</span> <span class="kc">True</span><span class="p">:</span> |
| <span class="n">start</span> <span class="o">=</span> <span class="n">time</span><span class="o">.</span><span class="n">time</span><span class="p">()</span> |
| <span class="n">passed</span><span class="p">,</span> <span class="n">errors</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">bigquery_wrapper</span><span class="o">.</span><span class="n">insert_rows</span><span class="p">(</span> |
| <span class="n">project_id</span><span class="o">=</span><span class="n">table_reference</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">table_reference</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">table_reference</span><span class="o">.</span><span class="n">tableId</span><span class="p">,</span> |
| <span class="n">rows</span><span class="o">=</span><span class="n">rows</span><span class="p">,</span> |
| <span class="n">insert_ids</span><span class="o">=</span><span class="n">insert_ids</span><span class="p">,</span> |
| <span class="n">skip_invalid_rows</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> |
| <span class="n">ignore_unknown_values</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">ignore_unknown_columns</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">batch_latency_metric</span><span class="o">.</span><span class="n">update</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="o">-</span> <span class="n">start</span><span class="p">)</span> <span class="o">*</span> <span class="mi">1000</span><span class="p">)</span> |
| |
| <span class="n">failed_rows</span> <span class="o">=</span> <span class="p">[</span><span class="n">rows</span><span class="p">[</span><span class="n">entry</span><span class="p">[</span><span class="s1">'index'</span><span class="p">]]</span> <span class="k">for</span> <span class="n">entry</span> <span class="ow">in</span> <span class="n">errors</span><span class="p">]</span> |
| <span class="n">should_retry</span> <span class="o">=</span> <span class="nb">any</span><span class="p">(</span> |
| <span class="n">RetryStrategy</span><span class="o">.</span><span class="n">should_retry</span><span class="p">(</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_retry_strategy</span><span class="p">,</span> <span class="n">entry</span><span class="p">[</span><span class="s1">'errors'</span><span class="p">][</span><span class="mi">0</span><span class="p">][</span><span class="s1">'reason'</span><span class="p">])</span> |
| <span class="k">for</span> <span class="n">entry</span> <span class="ow">in</span> <span class="n">errors</span><span class="p">)</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="n">passed</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">failed_rows_metric</span><span class="o">.</span><span class="n">update</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">failed_rows</span><span class="p">))</span> |
| <span class="n">message</span> <span class="o">=</span> <span class="p">(</span> |
| <span class="s1">'There were errors inserting to BigQuery. Will</span><span class="si">{}</span><span class="s1"> retry. '</span> |
| <span class="s1">'Errors were </span><span class="si">{}</span><span class="s1">'</span><span class="o">.</span><span class="n">format</span><span class="p">((</span><span class="s2">""</span> <span class="k">if</span> <span class="n">should_retry</span> <span class="k">else</span> <span class="s2">" not"</span><span class="p">),</span> <span class="n">errors</span><span class="p">))</span> |
| <span class="k">if</span> <span class="n">should_retry</span><span class="p">:</span> |
| <span class="n">_LOGGER</span><span class="o">.</span><span class="n">warning</span><span class="p">(</span><span class="n">message</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">_LOGGER</span><span class="o">.</span><span class="n">error</span><span class="p">(</span><span class="n">message</span><span class="p">)</span> |
| |
| <span class="n">rows</span> <span class="o">=</span> <span class="n">failed_rows</span> |
| |
| <span class="k">if</span> <span class="ow">not</span> <span class="n">should_retry</span><span class="p">:</span> |
| <span class="k">break</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">retry_backoff</span> <span class="o">=</span> <span class="nb">next</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_backoff_calculator</span><span class="p">)</span> |
| <span class="n">_LOGGER</span><span class="o">.</span><span class="n">info</span><span class="p">(</span> |
| <span class="s1">'Sleeping </span><span class="si">%s</span><span class="s1"> seconds before retrying insertion.'</span><span class="p">,</span> <span class="n">retry_backoff</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="n">retry_backoff</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_throttled_secs</span><span class="o">.</span><span class="n">inc</span><span class="p">(</span><span class="n">retry_backoff</span><span class="p">)</span> |
| |
| <span class="bp">self</span><span class="o">.</span><span class="n">_total_buffered_rows</span> <span class="o">-=</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_rows_buffer</span><span class="p">[</span><span class="n">destination</span><span class="p">])</span> |
| <span class="k">del</span> <span class="bp">self</span><span class="o">.</span><span class="n">_rows_buffer</span><span class="p">[</span><span class="n">destination</span><span class="p">]</span> |
| |
| <span class="k">return</span> <span class="p">[</span> |
| <span class="n">pvalue</span><span class="o">.</span><span class="n">TaggedOutput</span><span class="p">(</span> |
| <span class="n">BigQueryWriteFn</span><span class="o">.</span><span class="n">FAILED_ROWS</span><span class="p">,</span> |
| <span class="n">GlobalWindows</span><span class="o">.</span><span class="n">windowed_value</span><span class="p">((</span><span class="n">destination</span><span class="p">,</span> <span class="n">row</span><span class="p">)))</span> |
| <span class="k">for</span> <span class="n">row</span> <span class="ow">in</span> <span class="n">failed_rows</span> |
| <span class="p">]</span> |
| |
| |
| <span class="c1"># The number of shards per destination when writing via streaming inserts.</span> |
| <span class="n">DEFAULT_SHARDS_PER_DESTINATION</span> <span class="o">=</span> <span class="mi">500</span> |
| <span class="c1"># The max duration a batch of elements is allowed to be buffered before being</span> |
| <span class="c1"># flushed to BigQuery.</span> |
| <span class="n">DEFAULT_BATCH_BUFFERING_DURATION_LIMIT_SEC</span> <span class="o">=</span> <span class="mf">0.2</span> |
| |
| |
| <span class="k">class</span> <span class="nc">_StreamToBigQuery</span><span class="p">(</span><span class="n">PTransform</span><span class="p">):</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_reference</span><span class="p">,</span> |
| <span class="n">table_side_inputs</span><span class="p">,</span> |
| <span class="n">schema_side_inputs</span><span class="p">,</span> |
| <span class="n">schema</span><span class="p">,</span> |
| <span class="n">batch_size</span><span class="p">,</span> |
| <span class="n">triggering_frequency</span><span class="p">,</span> |
| <span class="n">create_disposition</span><span class="p">,</span> |
| <span class="n">write_disposition</span><span class="p">,</span> |
| <span class="n">kms_key</span><span class="p">,</span> |
| <span class="n">retry_strategy</span><span class="p">,</span> |
| <span class="n">additional_bq_parameters</span><span class="p">,</span> |
| <span class="n">ignore_insert_ids</span><span class="p">,</span> |
| <span class="n">ignore_unknown_columns</span><span class="p">,</span> |
| <span class="n">with_auto_sharding</span><span class="p">,</span> |
| <span class="n">test_client</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">table_reference</span> <span class="o">=</span> <span class="n">table_reference</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">table_side_inputs</span> <span class="o">=</span> <span class="n">table_side_inputs</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">schema_side_inputs</span> <span class="o">=</span> <span class="n">schema_side_inputs</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">schema</span> <span class="o">=</span> <span class="n">schema</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">batch_size</span> <span class="o">=</span> <span class="n">batch_size</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">triggering_frequency</span> <span class="o">=</span> <span class="n">triggering_frequency</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">create_disposition</span> <span class="o">=</span> <span class="n">create_disposition</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">write_disposition</span> <span class="o">=</span> <span class="n">write_disposition</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">retry_strategy</span> <span class="o">=</span> <span class="n">retry_strategy</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">test_client</span> <span class="o">=</span> <span class="n">test_client</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">additional_bq_parameters</span> <span class="o">=</span> <span class="n">additional_bq_parameters</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">ignore_insert_ids</span> <span class="o">=</span> <span class="n">ignore_insert_ids</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">ignore_unknown_columns</span> <span class="o">=</span> <span class="n">ignore_unknown_columns</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">with_auto_sharding</span> <span class="o">=</span> <span class="n">with_auto_sharding</span> |
| |
| <span class="k">class</span> <span class="nc">InsertIdPrefixFn</span><span class="p">(</span><span class="n">DoFn</span><span class="p">):</span> |
| <span class="k">def</span> <span class="nf">start_bundle</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">prefix</span> <span class="o">=</span> <span class="nb">str</span><span class="p">(</span><span class="n">uuid</span><span class="o">.</span><span class="n">uuid4</span><span class="p">())</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_row_count</span> <span class="o">=</span> <span class="mi">0</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="n">key</span> <span class="o">=</span> <span class="n">element</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> |
| <span class="n">value</span> <span class="o">=</span> <span class="n">element</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> |
| <span class="n">insert_id</span> <span class="o">=</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="bp">self</span><span class="o">.</span><span class="n">prefix</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_row_count</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_row_count</span> <span class="o">+=</span> <span class="mi">1</span> |
| <span class="k">yield</span> <span class="p">(</span><span class="n">key</span><span class="p">,</span> <span class="p">(</span><span class="n">value</span><span class="p">,</span> <span class="n">insert_id</span><span class="p">))</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="n">bigquery_write_fn</span> <span class="o">=</span> <span class="n">BigQueryWriteFn</span><span class="p">(</span> |
| <span class="n">schema</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">schema</span><span class="p">,</span> |
| <span class="n">batch_size</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">batch_size</span><span class="p">,</span> |
| <span class="n">create_disposition</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">create_disposition</span><span class="p">,</span> |
| <span class="n">write_disposition</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">write_disposition</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">retry_strategy</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">retry_strategy</span><span class="p">,</span> |
| <span class="n">test_client</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">test_client</span><span class="p">,</span> |
| <span class="n">additional_bq_parameters</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">additional_bq_parameters</span><span class="p">,</span> |
| <span class="n">ignore_insert_ids</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">ignore_insert_ids</span><span class="p">,</span> |
| <span class="n">ignore_unknown_columns</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">ignore_unknown_columns</span><span class="p">,</span> |
| <span class="n">with_batched_input</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">with_auto_sharding</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">_add_random_shard</span><span class="p">(</span><span class="n">element</span><span class="p">):</span> |
| <span class="n">key</span> <span class="o">=</span> <span class="n">element</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> |
| <span class="n">value</span> <span class="o">=</span> <span class="n">element</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> |
| <span class="k">return</span> <span class="p">((</span><span class="n">key</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="n">DEFAULT_SHARDS_PER_DESTINATION</span><span class="p">)),</span> <span class="n">value</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">_restore_table_ref</span><span class="p">(</span><span class="n">sharded_table_ref_elems_kv</span><span class="p">):</span> |
| <span class="n">sharded_table_ref</span> <span class="o">=</span> <span class="n">sharded_table_ref_elems_kv</span><span class="p">[</span><span class="mi">0</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">sharded_table_ref</span><span class="p">)</span> |
| <span class="k">return</span> <span class="p">(</span><span class="n">table_ref</span><span class="p">,</span> <span class="n">sharded_table_ref_elems_kv</span><span class="p">[</span><span class="mi">1</span><span class="p">])</span> |
| |
| <span class="n">tagged_data</span> <span class="o">=</span> <span class="p">(</span> |
| <span class="nb">input</span> |
| <span class="o">|</span> <span class="s1">'AppendDestination'</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">bigquery_tools</span><span class="o">.</span><span class="n">AppendDestinationsFn</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">table_reference</span><span class="p">),</span> |
| <span class="o">*</span><span class="bp">self</span><span class="o">.</span><span class="n">table_side_inputs</span><span class="p">)</span> |
| <span class="o">|</span> <span class="s1">'AddInsertIds'</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">_StreamToBigQuery</span><span class="o">.</span><span class="n">InsertIdPrefixFn</span><span class="p">())</span> |
| <span class="o">|</span> |
| <span class="s1">'ToHashableTableRef'</span> <span class="o">>></span> <span class="n">beam</span><span class="o">.</span><span class="n">Map</span><span class="p">(</span><span class="n">bigquery_tools</span><span class="o">.</span><span class="n">to_hashable_table_ref</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">with_auto_sharding</span><span class="p">:</span> |
| <span class="n">tagged_data</span> <span class="o">=</span> <span class="p">(</span> |
| <span class="n">tagged_data</span> |
| <span class="o">|</span> <span class="s1">'WithFixedSharding'</span> <span class="o">>></span> <span class="n">beam</span><span class="o">.</span><span class="n">Map</span><span class="p">(</span><span class="n">_add_random_shard</span><span class="p">)</span> |
| <span class="o">|</span> <span class="s1">'CommitInsertIds'</span> <span class="o">>></span> <span class="n">ReshufflePerKey</span><span class="p">()</span> |
| <span class="o">|</span> <span class="s1">'DropShard'</span> <span class="o">>></span> <span class="n">beam</span><span class="o">.</span><span class="n">Map</span><span class="p">(</span><span class="k">lambda</span> <span class="n">kv</span><span class="p">:</span> <span class="p">(</span><span class="n">kv</span><span class="p">[</span><span class="mi">0</span><span class="p">][</span><span class="mi">0</span><span class="p">],</span> <span class="n">kv</span><span class="p">[</span><span class="mi">1</span><span class="p">])))</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="c1"># Auto-sharding is achieved via GroupIntoBatches.WithShardedKey</span> |
| <span class="c1"># transform which shards, groups and at the same time batches the table</span> |
| <span class="c1"># rows to be inserted to BigQuery.</span> |
| |
| <span class="c1"># Firstly the keys of tagged_data (table references) are converted to a</span> |
| <span class="c1"># hashable format. This is needed to work with the keyed states used by</span> |
| <span class="c1"># GroupIntoBatches. After grouping and batching is done, original table</span> |
| <span class="c1"># references are restored.</span> |
| <span class="n">tagged_data</span> <span class="o">=</span> <span class="p">(</span> |
| <span class="n">tagged_data</span> |
| <span class="o">|</span> <span class="s1">'WithAutoSharding'</span> <span class="o">>></span> <span class="n">beam</span><span class="o">.</span><span class="n">GroupIntoBatches</span><span class="o">.</span><span class="n">WithShardedKey</span><span class="p">(</span> |
| <span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">batch_size</span> <span class="ow">or</span> <span class="n">BigQueryWriteFn</span><span class="o">.</span><span class="n">DEFAULT_MAX_BUFFERED_ROWS</span><span class="p">),</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">triggering_frequency</span> <span class="ow">or</span> |
| <span class="n">DEFAULT_BATCH_BUFFERING_DURATION_LIMIT_SEC</span><span class="p">)</span> |
| <span class="o">|</span> <span class="s1">'DropShard'</span> <span class="o">>></span> <span class="n">beam</span><span class="o">.</span><span class="n">Map</span><span class="p">(</span><span class="k">lambda</span> <span class="n">kv</span><span class="p">:</span> <span class="p">(</span><span class="n">kv</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">key</span><span class="p">,</span> <span class="n">kv</span><span class="p">[</span><span class="mi">1</span><span class="p">])))</span> |
| |
| <span class="k">return</span> <span class="p">(</span> |
| <span class="n">tagged_data</span> |
| <span class="o">|</span> <span class="s1">'FromHashableTableRef'</span> <span class="o">>></span> <span class="n">beam</span><span class="o">.</span><span class="n">Map</span><span class="p">(</span><span class="n">_restore_table_ref</span><span class="p">)</span> |
| <span class="o">|</span> <span class="s1">'StreamInsertRows'</span> <span class="o">>></span> <span class="n">ParDo</span><span class="p">(</span> |
| <span class="n">bigquery_write_fn</span><span class="p">,</span> <span class="o">*</span><span class="bp">self</span><span class="o">.</span><span class="n">schema_side_inputs</span><span class="p">)</span><span class="o">.</span><span class="n">with_outputs</span><span class="p">(</span> |
| <span class="n">BigQueryWriteFn</span><span class="o">.</span><span class="n">FAILED_ROWS</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="c1"># Flag to be passed to WriteToBigQuery to force schema autodetection</span> |
| <span class="n">SCHEMA_AUTODETECT</span> <span class="o">=</span> <span class="s1">'SCHEMA_AUTODETECT'</span> |
| |
| |
| <div class="viewcode-block" id="WriteToBigQuery"><a class="viewcode-back" href="../../../../apache_beam.io.gcp.bigquery.html#apache_beam.io.gcp.bigquery.WriteToBigQuery">[docs]</a><span class="k">class</span> <span class="nc">WriteToBigQuery</span><span class="p">(</span><span class="n">PTransform</span><span class="p">):</span> |
| <span class="sd">"""Write data to BigQuery.</span> |
| |
| <span class="sd"> This transform receives a PCollection of elements to be inserted into BigQuery</span> |
| <span class="sd"> tables. The elements would come in as Python dictionaries, or as `TableRow`</span> |
| <span class="sd"> instances.</span> |
| <span class="sd"> """</span> |
| <div class="viewcode-block" id="WriteToBigQuery.Method"><a class="viewcode-back" href="../../../../apache_beam.io.gcp.bigquery.html#apache_beam.io.gcp.bigquery.WriteToBigQuery.Method">[docs]</a> <span class="k">class</span> <span class="nc">Method</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span> |
| <span class="n">DEFAULT</span> <span class="o">=</span> <span class="s1">'DEFAULT'</span> |
| <span class="n">STREAMING_INSERTS</span> <span class="o">=</span> <span class="s1">'STREAMING_INSERTS'</span> |
| <span class="n">FILE_LOADS</span> <span class="o">=</span> <span class="s1">'FILE_LOADS'</span></div> |
| |
| <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</span><span class="p">,</span> |
| <span class="n">dataset</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">project</span><span class="o">=</span><span class="kc">None</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">create_disposition</span><span class="o">=</span><span class="n">BigQueryDisposition</span><span class="o">.</span><span class="n">CREATE_IF_NEEDED</span><span class="p">,</span> |
| <span class="n">write_disposition</span><span class="o">=</span><span class="n">BigQueryDisposition</span><span class="o">.</span><span class="n">WRITE_APPEND</span><span class="p">,</span> |
| <span class="n">kms_key</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">batch_size</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">max_file_size</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">max_files_per_bundle</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">test_client</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">custom_gcs_temp_location</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">method</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">insert_retry_strategy</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">additional_bq_parameters</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">table_side_inputs</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">schema_side_inputs</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">triggering_frequency</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">validate</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> |
| <span class="n">temp_file_format</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">ignore_insert_ids</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> |
| <span class="c1"># TODO(BEAM-11857): Switch the default when the feature is mature.</span> |
| <span class="n">with_auto_sharding</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> |
| <span class="n">ignore_unknown_columns</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> |
| <span class="n">load_job_project_id</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="sd">"""Initialize a WriteToBigQuery transform.</span> |
| |
| <span class="sd"> Args:</span> |
| <span class="sd"> table (str, callable, ValueProvider): The ID of the table, or a callable</span> |
| <span class="sd"> that returns it. The ID must contain only letters ``a-z``, ``A-Z``,</span> |
| <span class="sd"> numbers ``0-9``, or connectors ``-_``. If dataset argument is</span> |
| <span class="sd"> :data:`None` then the table argument must contain the entire table</span> |
| <span class="sd"> reference specified as: ``'DATASET.TABLE'``</span> |
| <span class="sd"> or ``'PROJECT:DATASET.TABLE'``. If it's a callable, it must receive one</span> |
| <span class="sd"> argument representing an element to be written to BigQuery, and return</span> |
| <span class="sd"> a TableReference, or a string table name as specified above.</span> |
| <span class="sd"> dataset (str): The ID of the dataset containing this table or</span> |
| <span class="sd"> :data:`None` if the table reference is specified entirely by the table</span> |
| <span class="sd"> argument.</span> |
| <span class="sd"> project (str): The ID of the project containing this table or</span> |
| <span class="sd"> :data:`None` if the table reference is specified entirely by the table</span> |
| <span class="sd"> argument.</span> |
| <span class="sd"> schema (str,dict,ValueProvider,callable): The schema to be used if the</span> |
| <span class="sd"> BigQuery table to write has to be created. This can be either specified</span> |
| <span class="sd"> as a :class:`~apache_beam.io.gcp.internal.clients.bigquery.\</span> |
| <span class="sd">bigquery_v2_messages.TableSchema`. or a `ValueProvider` that has a JSON string,</span> |
| <span class="sd"> or a python dictionary, or the string or dictionary itself,</span> |
| <span class="sd"> object or a single string of the form</span> |
| <span class="sd"> ``'field1:type1,field2:type2,field3:type3'`` that defines a comma</span> |
| <span class="sd"> separated list of fields. Here ``'type'`` should specify the BigQuery</span> |
| <span class="sd"> type of the field. Single string based schemas do not support nested</span> |
| <span class="sd"> fields, repeated fields, or specifying a BigQuery mode for fields</span> |
| <span class="sd"> (mode will always be set to ``'NULLABLE'``).</span> |
| <span class="sd"> If a callable, then it should receive a destination (in the form of</span> |
| <span class="sd"> a str, and return a str, dict or TableSchema).</span> |
| <span class="sd"> One may also pass ``SCHEMA_AUTODETECT`` here when using JSON-based</span> |
| <span class="sd"> file loads, and BigQuery will try to infer the schema for the files</span> |
| <span class="sd"> that are being loaded.</span> |
| <span class="sd"> create_disposition (BigQueryDisposition): A string describing what</span> |
| <span class="sd"> happens if the table does not exist. Possible values are:</span> |
| |
| <span class="sd"> * :attr:`BigQueryDisposition.CREATE_IF_NEEDED`: create if does not</span> |
| <span class="sd"> exist.</span> |
| <span class="sd"> * :attr:`BigQueryDisposition.CREATE_NEVER`: fail the write if does not</span> |
| <span class="sd"> exist.</span> |
| |
| <span class="sd"> write_disposition (BigQueryDisposition): A string describing what happens</span> |
| <span class="sd"> if the table has already some data. Possible values are:</span> |
| |
| <span class="sd"> * :attr:`BigQueryDisposition.WRITE_TRUNCATE`: delete existing rows.</span> |
| <span class="sd"> * :attr:`BigQueryDisposition.WRITE_APPEND`: add to existing rows.</span> |
| <span class="sd"> * :attr:`BigQueryDisposition.WRITE_EMPTY`: fail the write if table not</span> |
| <span class="sd"> empty.</span> |
| |
| <span class="sd"> For streaming pipelines WriteTruncate can not be used.</span> |
| <span class="sd"> kms_key (str): Optional Cloud KMS key name for use when creating new</span> |
| <span class="sd"> tables.</span> |
| <span class="sd"> batch_size (int): Number of rows to be written to BQ per streaming API</span> |
| <span class="sd"> insert. The default is 500.</span> |
| <span class="sd"> test_client: Override the default bigquery client used for testing.</span> |
| <span class="sd"> max_file_size (int): The maximum size for a file to be written and then</span> |
| <span class="sd"> loaded into BigQuery. The default value is 4TB, which is 80% of the</span> |
| <span class="sd"> limit of 5TB for BigQuery to load any file.</span> |
| <span class="sd"> max_files_per_bundle(int): The maximum number of files to be concurrently</span> |
| <span class="sd"> written by a worker. The default here is 20. Larger values will allow</span> |
| <span class="sd"> writing to multiple destinations without having to reshard - but they</span> |
| <span class="sd"> increase the memory burden on the workers.</span> |
| <span class="sd"> custom_gcs_temp_location (str): A GCS location to store files to be used</span> |
| <span class="sd"> for file loads into BigQuery. By default, this will use the pipeline's</span> |
| <span class="sd"> temp_location, but for pipelines whose temp_location is not appropriate</span> |
| <span class="sd"> for BQ File Loads, users should pass a specific one.</span> |
| <span class="sd"> method: The method to use to write to BigQuery. It may be</span> |
| <span class="sd"> STREAMING_INSERTS, FILE_LOADS, or DEFAULT. An introduction on loading</span> |
| <span class="sd"> data to BigQuery: https://cloud.google.com/bigquery/docs/loading-data.</span> |
| <span class="sd"> DEFAULT will use STREAMING_INSERTS on Streaming pipelines and</span> |
| <span class="sd"> FILE_LOADS on Batch pipelines.</span> |
| <span class="sd"> insert_retry_strategy: The strategy to use when retrying streaming inserts</span> |
| <span class="sd"> into BigQuery. Options are shown in bigquery_tools.RetryStrategy attrs.</span> |
| <span class="sd"> Default is to retry always. This means that whenever there are rows</span> |
| <span class="sd"> that fail to be inserted to BigQuery, they will be retried indefinitely.</span> |
| <span class="sd"> Other retry strategy settings will produce a deadletter PCollection</span> |
| <span class="sd"> as output. Appropriate values are:</span> |
| |
| <span class="sd"> * `RetryStrategy.RETRY_ALWAYS`: retry all rows if</span> |
| <span class="sd"> there are any kind of errors. Note that this will hold your pipeline</span> |
| <span class="sd"> back if there are errors until you cancel or update it.</span> |
| <span class="sd"> * `RetryStrategy.RETRY_NEVER`: rows with errors</span> |
| <span class="sd"> will not be retried. Instead they will be output to a dead letter</span> |
| <span class="sd"> queue under the `'FailedRows'` tag.</span> |
| <span class="sd"> * `RetryStrategy.RETRY_ON_TRANSIENT_ERROR`: retry</span> |
| <span class="sd"> rows with transient errors (e.g. timeouts). Rows with permanent errors</span> |
| <span class="sd"> will be output to dead letter queue under `'FailedRows'` tag.</span> |
| |
| <span class="sd"> additional_bq_parameters (dict, callable): Additional parameters to pass</span> |
| <span class="sd"> to BQ when creating / loading data into a table. If a callable, it</span> |
| <span class="sd"> should be a function that receives a table reference indicating</span> |
| <span class="sd"> the destination and returns a dictionary.</span> |
| <span class="sd"> These can be 'timePartitioning', 'clustering', etc. They are passed</span> |
| <span class="sd"> directly to the job load configuration. See</span> |
| <span class="sd"> https://cloud.google.com/bigquery/docs/reference/rest/v2/Job#jobconfigurationload</span> |
| <span class="sd"> table_side_inputs (tuple): A tuple with ``AsSideInput`` PCollections to be</span> |
| <span class="sd"> passed to the table callable (if one is provided).</span> |
| <span class="sd"> schema_side_inputs: A tuple with ``AsSideInput`` PCollections to be</span> |
| <span class="sd"> passed to the schema callable (if one is provided).</span> |
| <span class="sd"> triggering_frequency (float):</span> |
| <span class="sd"> When method is FILE_LOADS:</span> |
| <span class="sd"> Value will be converted to int. Every triggering_frequency seconds, a</span> |
| <span class="sd"> BigQuery load job will be triggered for all the data written since the</span> |
| <span class="sd"> last load job. BigQuery has limits on how many load jobs can be</span> |
| <span class="sd"> triggered per day, so be careful not to set this duration too low, or</span> |
| <span class="sd"> you may exceed daily quota. Often this is set to 5 or 10 minutes to</span> |
| <span class="sd"> ensure that the project stays well under the BigQuery quota. See</span> |
| <span class="sd"> https://cloud.google.com/bigquery/quota-policy for more information</span> |
| <span class="sd"> about BigQuery quotas.</span> |
| |
| <span class="sd"> When method is STREAMING_INSERTS and with_auto_sharding=True:</span> |
| <span class="sd"> A streaming inserts batch will be submitted at least every</span> |
| <span class="sd"> triggering_frequency seconds when data is waiting. The batch can be</span> |
| <span class="sd"> sent earlier if it reaches the maximum batch size set by batch_size.</span> |
| <span class="sd"> Default value is 0.2 seconds.</span> |
| <span class="sd"> validate: Indicates whether to perform validation checks on</span> |
| <span class="sd"> inputs. This parameter is primarily used for testing.</span> |
| <span class="sd"> temp_file_format: The format to use for file loads into BigQuery. The</span> |
| <span class="sd"> options are NEWLINE_DELIMITED_JSON or AVRO, with NEWLINE_DELIMITED_JSON</span> |
| <span class="sd"> being used by default. For advantages and limitations of the two</span> |
| <span class="sd"> formats, see</span> |
| <span class="sd"> https://cloud.google.com/bigquery/docs/loading-data-cloud-storage-avro</span> |
| <span class="sd"> and</span> |
| <span class="sd"> https://cloud.google.com/bigquery/docs/loading-data-cloud-storage-json.</span> |
| <span class="sd"> ignore_insert_ids: When using the STREAMING_INSERTS method to write data</span> |
| <span class="sd"> to BigQuery, `insert_ids` are a feature of BigQuery that support</span> |
| <span class="sd"> deduplication of events. If your use case is not sensitive to</span> |
| <span class="sd"> duplication of data inserted to BigQuery, set `ignore_insert_ids`</span> |
| <span class="sd"> to True to increase the throughput for BQ writing. See:</span> |
| <span class="sd"> https://cloud.google.com/bigquery/streaming-data-into-bigquery#disabling_best_effort_de-duplication</span> |
| <span class="sd"> with_auto_sharding: Experimental. If true, enables using a dynamically</span> |
| <span class="sd"> determined number of shards to write to BigQuery. This can be used for</span> |
| <span class="sd"> both FILE_LOADS and STREAMING_INSERTS. Only applicable to unbounded</span> |
| <span class="sd"> input.</span> |
| <span class="sd"> ignore_unknown_columns: Accept rows that contain values that do not match</span> |
| <span class="sd"> the schema. The unknown values are ignored. Default is False,</span> |
| <span class="sd"> which treats unknown values as errors. This option is only valid for</span> |
| <span class="sd"> method=STREAMING_INSERTS. See reference:</span> |
| <span class="sd"> https://cloud.google.com/bigquery/docs/reference/rest/v2/tabledata/insertAll</span> |
| <span class="sd"> load_job_project_id: Specifies an alternate GCP project id to use for</span> |
| <span class="sd"> billingBatch File Loads. By default, the project id of the table is</span> |
| <span class="sd"> used.</span> |
| <span class="sd"> """</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_table</span> <span class="o">=</span> <span class="n">table</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_dataset</span> <span class="o">=</span> <span class="n">dataset</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">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">table</span><span class="p">,</span> <span class="n">dataset</span><span class="p">,</span> <span class="n">project</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">create_disposition</span> <span class="o">=</span> <span class="n">BigQueryDisposition</span><span class="o">.</span><span class="n">validate_create</span><span class="p">(</span> |
| <span class="n">create_disposition</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">write_disposition</span> <span class="o">=</span> <span class="n">BigQueryDisposition</span><span class="o">.</span><span class="n">validate_write</span><span class="p">(</span> |
| <span class="n">write_disposition</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">schema</span> <span class="o">==</span> <span class="n">SCHEMA_AUTODETECT</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">schema</span> <span class="o">=</span> <span class="n">schema</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">schema</span> <span class="o">=</span> <span class="n">bigquery_tools</span><span class="o">.</span><span class="n">get_dict_table_schema</span><span class="p">(</span><span class="n">schema</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">batch_size</span> <span class="o">=</span> <span class="n">batch_size</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">test_client</span> <span class="o">=</span> <span class="n">test_client</span> |
| |
| <span class="c1"># TODO(pabloem): Consider handling ValueProvider for this location.</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">custom_gcs_temp_location</span> <span class="o">=</span> <span class="n">custom_gcs_temp_location</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">max_file_size</span> <span class="o">=</span> <span class="n">max_file_size</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">max_files_per_bundle</span> <span class="o">=</span> <span class="n">max_files_per_bundle</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">method</span> <span class="o">=</span> <span class="n">method</span> <span class="ow">or</span> <span class="n">WriteToBigQuery</span><span class="o">.</span><span class="n">Method</span><span class="o">.</span><span class="n">DEFAULT</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">triggering_frequency</span> <span class="o">=</span> <span class="n">triggering_frequency</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">with_auto_sharding</span> <span class="o">=</span> <span class="n">with_auto_sharding</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">insert_retry_strategy</span> <span class="o">=</span> <span class="n">insert_retry_strategy</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_validate</span> <span class="o">=</span> <span class="n">validate</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_temp_file_format</span> <span class="o">=</span> <span class="n">temp_file_format</span> <span class="ow">or</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="bp">self</span><span class="o">.</span><span class="n">additional_bq_parameters</span> <span class="o">=</span> <span class="n">additional_bq_parameters</span> <span class="ow">or</span> <span class="p">{}</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">table_side_inputs</span> <span class="o">=</span> <span class="n">table_side_inputs</span> <span class="ow">or</span> <span class="p">()</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">schema_side_inputs</span> <span class="o">=</span> <span class="n">schema_side_inputs</span> <span class="ow">or</span> <span class="p">()</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_ignore_insert_ids</span> <span class="o">=</span> <span class="n">ignore_insert_ids</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_ignore_unknown_columns</span> <span class="o">=</span> <span class="n">ignore_unknown_columns</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">load_job_project_id</span> <span class="o">=</span> <span class="n">load_job_project_id</span> |
| |
| <span class="c1"># Dict/schema methods were moved to bigquery_tools, but keep references</span> |
| <span class="c1"># here for backward compatibility.</span> |
| <span class="n">get_table_schema_from_string</span> <span class="o">=</span> \ |
| <span class="nb">staticmethod</span><span class="p">(</span><span class="n">bigquery_tools</span><span class="o">.</span><span class="n">get_table_schema_from_string</span><span class="p">)</span> |
| <span class="n">table_schema_to_dict</span> <span class="o">=</span> <span class="nb">staticmethod</span><span class="p">(</span><span class="n">bigquery_tools</span><span class="o">.</span><span class="n">table_schema_to_dict</span><span class="p">)</span> |
| <span class="n">get_dict_table_schema</span> <span class="o">=</span> <span class="nb">staticmethod</span><span class="p">(</span><span class="n">bigquery_tools</span><span class="o">.</span><span class="n">get_dict_table_schema</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">_compute_method</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">experiments</span><span class="p">,</span> <span class="n">is_streaming_pipeline</span><span class="p">):</span> |
| <span class="c1"># If the new BQ sink is not activated for experiment flags, then we use</span> |
| <span class="c1"># streaming inserts by default (it gets overridden in dataflow_runner.py).</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">method</span> <span class="o">==</span> <span class="bp">self</span><span class="o">.</span><span class="n">Method</span><span class="o">.</span><span class="n">DEFAULT</span> <span class="ow">and</span> <span class="n">is_streaming_pipeline</span><span class="p">:</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">Method</span><span class="o">.</span><span class="n">STREAMING_INSERTS</span> |
| <span class="k">elif</span> <span class="bp">self</span><span class="o">.</span><span class="n">method</span> <span class="o">==</span> <span class="bp">self</span><span class="o">.</span><span class="n">Method</span><span class="o">.</span><span class="n">DEFAULT</span> <span class="ow">and</span> <span class="ow">not</span> <span class="n">is_streaming_pipeline</span><span class="p">:</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">Method</span><span class="o">.</span><span class="n">FILE_LOADS</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">method</span> |
| |
| <div class="viewcode-block" id="WriteToBigQuery.expand"><a class="viewcode-back" href="../../../../apache_beam.io.gcp.bigquery.html#apache_beam.io.gcp.bigquery.WriteToBigQuery.expand">[docs]</a> <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="n">pcoll</span><span class="p">):</span> |
| <span class="n">p</span> <span class="o">=</span> <span class="n">pcoll</span><span class="o">.</span><span class="n">pipeline</span> |
| |
| <span class="k">if</span> <span class="p">(</span><span class="nb">isinstance</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">table_reference</span><span class="p">,</span> <span class="n">TableReference</span><span class="p">)</span> <span class="ow">and</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">table_reference</span><span class="o">.</span><span class="n">projectId</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">table_reference</span><span class="o">.</span><span class="n">projectId</span> <span class="o">=</span> <span class="n">pcoll</span><span class="o">.</span><span class="n">pipeline</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="c1"># TODO(pabloem): Use a different method to determine if streaming or batch.</span> |
| <span class="n">is_streaming_pipeline</span> <span class="o">=</span> <span class="n">p</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">StandardOptions</span><span class="p">)</span><span class="o">.</span><span class="n">streaming</span> |
| |
| <span class="k">if</span> <span class="ow">not</span> <span class="n">is_streaming_pipeline</span> <span class="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">with_auto_sharding</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span> |
| <span class="s1">'with_auto_sharding is not applicable to batch pipelines.'</span><span class="p">)</span> |
| |
| <span class="n">experiments</span> <span class="o">=</span> <span class="n">p</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">DebugOptions</span><span class="p">)</span><span class="o">.</span><span class="n">experiments</span> <span class="ow">or</span> <span class="p">[]</span> |
| <span class="n">method_to_use</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_compute_method</span><span class="p">(</span><span class="n">experiments</span><span class="p">,</span> <span class="n">is_streaming_pipeline</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="n">method_to_use</span> <span class="o">==</span> <span class="n">WriteToBigQuery</span><span class="o">.</span><span class="n">Method</span><span class="o">.</span><span class="n">STREAMING_INSERTS</span><span class="p">:</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">schema</span> <span class="o">==</span> <span class="n">SCHEMA_AUTODETECT</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span> |
| <span class="s1">'Schema auto-detection is not supported for streaming '</span> |
| <span class="s1">'inserts into BigQuery. Only for File Loads.'</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">triggering_frequency</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> <span class="ow">and</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">with_auto_sharding</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span> |
| <span class="s1">'triggering_frequency with STREAMING_INSERTS can only be used with '</span> |
| <span class="s1">'with_auto_sharding=True.'</span><span class="p">)</span> |
| |
| <span class="n">outputs</span> <span class="o">=</span> <span class="n">pcoll</span> <span class="o">|</span> <span class="n">_StreamToBigQuery</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">table_reference</span><span class="p">,</span> |
| <span class="n">table_side_inputs</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">table_side_inputs</span><span class="p">,</span> |
| <span class="n">schema_side_inputs</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">schema_side_inputs</span><span class="p">,</span> |
| <span class="n">schema</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">schema</span><span class="p">,</span> |
| <span class="n">batch_size</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">batch_size</span><span class="p">,</span> |
| <span class="n">triggering_frequency</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">triggering_frequency</span><span class="p">,</span> |
| <span class="n">create_disposition</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">create_disposition</span><span class="p">,</span> |
| <span class="n">write_disposition</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">write_disposition</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">retry_strategy</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">insert_retry_strategy</span><span class="p">,</span> |
| <span class="n">additional_bq_parameters</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">additional_bq_parameters</span><span class="p">,</span> |
| <span class="n">ignore_insert_ids</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_ignore_insert_ids</span><span class="p">,</span> |
| <span class="n">ignore_unknown_columns</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_ignore_unknown_columns</span><span class="p">,</span> |
| <span class="n">with_auto_sharding</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">with_auto_sharding</span><span class="p">,</span> |
| <span class="n">test_client</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">test_client</span><span class="p">)</span> |
| |
| <span class="k">return</span> <span class="p">{</span><span class="n">BigQueryWriteFn</span><span class="o">.</span><span class="n">FAILED_ROWS</span><span class="p">:</span> <span class="n">outputs</span><span class="p">[</span><span class="n">BigQueryWriteFn</span><span class="o">.</span><span class="n">FAILED_ROWS</span><span class="p">]}</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_temp_file_format</span> <span class="o">==</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="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">schema</span> <span class="o">==</span> <span class="n">SCHEMA_AUTODETECT</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span> |
| <span class="s1">'Schema auto-detection is not supported when using Avro based '</span> |
| <span class="s1">'file loads into BigQuery. Please specify a schema or set '</span> |
| <span class="s1">'temp_file_format="NEWLINE_DELIMITED_JSON"'</span><span class="p">)</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">schema</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="s1">'A schema must be provided when writing to BigQuery using '</span> |
| <span class="s1">'Avro based file loads'</span><span class="p">)</span> |
| |
| <span class="kn">from</span> <span class="nn">apache_beam.io.gcp</span> <span class="kn">import</span> <span class="n">bigquery_file_loads</span> |
| <span class="c1"># Only cast to int when a value is given.</span> |
| <span class="c1"># We only use an int for BigQueryBatchFileLoads</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">triggering_frequency</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">triggering_frequency</span> <span class="o">=</span> <span class="nb">int</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">triggering_frequency</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">triggering_frequency</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">triggering_frequency</span> |
| <span class="k">return</span> <span class="n">pcoll</span> <span class="o">|</span> <span class="n">bigquery_file_loads</span><span class="o">.</span><span class="n">BigQueryBatchFileLoads</span><span class="p">(</span> |
| <span class="n">destination</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">table_reference</span><span class="p">,</span> |
| <span class="n">schema</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">schema</span><span class="p">,</span> |
| <span class="n">create_disposition</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">create_disposition</span><span class="p">,</span> |
| <span class="n">write_disposition</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">write_disposition</span><span class="p">,</span> |
| <span class="n">triggering_frequency</span><span class="o">=</span><span class="n">triggering_frequency</span><span class="p">,</span> |
| <span class="n">with_auto_sharding</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">with_auto_sharding</span><span class="p">,</span> |
| <span class="n">temp_file_format</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_temp_file_format</span><span class="p">,</span> |
| <span class="n">max_file_size</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">max_file_size</span><span class="p">,</span> |
| <span class="n">max_files_per_bundle</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">max_files_per_bundle</span><span class="p">,</span> |
| <span class="n">custom_gcs_temp_location</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">custom_gcs_temp_location</span><span class="p">,</span> |
| <span class="n">test_client</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">test_client</span><span class="p">,</span> |
| <span class="n">table_side_inputs</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">table_side_inputs</span><span class="p">,</span> |
| <span class="n">schema_side_inputs</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">schema_side_inputs</span><span class="p">,</span> |
| <span class="n">additional_bq_parameters</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">additional_bq_parameters</span><span class="p">,</span> |
| <span class="n">validate</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_validate</span><span class="p">,</span> |
| <span class="n">is_streaming_pipeline</span><span class="o">=</span><span class="n">is_streaming_pipeline</span><span class="p">,</span> |
| <span class="n">load_job_project_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">load_job_project_id</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="WriteToBigQuery.display_data"><a class="viewcode-back" href="../../../../apache_beam.io.gcp.bigquery.html#apache_beam.io.gcp.bigquery.WriteToBigQuery.display_data">[docs]</a> <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="n">res</span> <span class="o">=</span> <span class="p">{}</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">table_reference</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> <span class="ow">and</span> <span class="nb">isinstance</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">table_reference</span><span class="p">,</span> |
| <span class="n">TableReference</span><span class="p">):</span> |
| <span class="n">tableSpec</span> <span class="o">=</span> <span class="s1">'</span><span class="si">{}</span><span class="s1">.</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">table_reference</span><span class="o">.</span><span class="n">datasetId</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</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="bp">self</span><span class="o">.</span><span class="n">table_reference</span><span class="o">.</span><span class="n">projectId</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">tableSpec</span> <span class="o">=</span> <span class="s1">'</span><span class="si">{}</span><span class="s1">:</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">table_reference</span><span class="o">.</span><span class="n">projectId</span><span class="p">,</span> <span class="n">tableSpec</span><span class="p">)</span> |
| <span class="n">res</span><span class="p">[</span><span class="s1">'table'</span><span class="p">]</span> <span class="o">=</span> <span class="n">DisplayDataItem</span><span class="p">(</span><span class="n">tableSpec</span><span class="p">,</span> <span class="n">label</span><span class="o">=</span><span class="s1">'Table'</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">res</span></div> |
| |
| <div class="viewcode-block" id="WriteToBigQuery.to_runner_api_parameter"><a class="viewcode-back" href="../../../../apache_beam.io.gcp.bigquery.html#apache_beam.io.gcp.bigquery.WriteToBigQuery.to_runner_api_parameter">[docs]</a> <span class="k">def</span> <span class="nf">to_runner_api_parameter</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">context</span><span class="p">):</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.internal</span> <span class="kn">import</span> <span class="n">pickler</span> |
| |
| <span class="c1"># It'd be nice to name these according to their actual</span> |
| <span class="c1"># names/positions in the orignal argument list, but such a</span> |
| <span class="c1"># transformation is currently irreversible given how</span> |
| <span class="c1"># remove_objects_from_args and insert_values_in_args</span> |
| <span class="c1"># are currently implemented.</span> |
| <span class="k">def</span> <span class="nf">serialize</span><span class="p">(</span><span class="n">side_inputs</span><span class="p">):</span> |
| <span class="k">return</span> <span class="p">{(</span><span class="n">SIDE_INPUT_PREFIX</span> <span class="o">+</span> <span class="s1">'</span><span class="si">%s</span><span class="s1">'</span><span class="p">)</span> <span class="o">%</span> <span class="n">ix</span><span class="p">:</span> |
| <span class="n">si</span><span class="o">.</span><span class="n">to_runner_api</span><span class="p">(</span><span class="n">context</span><span class="p">)</span><span class="o">.</span><span class="n">SerializeToString</span><span class="p">()</span> |
| <span class="k">for</span> <span class="n">ix</span><span class="p">,</span> |
| <span class="n">si</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">(</span><span class="n">side_inputs</span><span class="p">)}</span> |
| |
| <span class="n">table_side_inputs</span> <span class="o">=</span> <span class="n">serialize</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">table_side_inputs</span><span class="p">)</span> |
| <span class="n">schema_side_inputs</span> <span class="o">=</span> <span class="n">serialize</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">schema_side_inputs</span><span class="p">)</span> |
| |
| <span class="n">config</span> <span class="o">=</span> <span class="p">{</span> |
| <span class="s1">'table'</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">_table</span><span class="p">,</span> |
| <span class="s1">'dataset'</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">_dataset</span><span class="p">,</span> |
| <span class="s1">'project'</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">'schema'</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">schema</span><span class="p">,</span> |
| <span class="s1">'create_disposition'</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">create_disposition</span><span class="p">,</span> |
| <span class="s1">'write_disposition'</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">write_disposition</span><span class="p">,</span> |
| <span class="s1">'kms_key'</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">'batch_size'</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">batch_size</span><span class="p">,</span> |
| <span class="s1">'max_file_size'</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">max_file_size</span><span class="p">,</span> |
| <span class="s1">'max_files_per_bundle'</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">max_files_per_bundle</span><span class="p">,</span> |
| <span class="s1">'custom_gcs_temp_location'</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">custom_gcs_temp_location</span><span class="p">,</span> |
| <span class="s1">'method'</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">method</span><span class="p">,</span> |
| <span class="s1">'insert_retry_strategy'</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">insert_retry_strategy</span><span class="p">,</span> |
| <span class="s1">'additional_bq_parameters'</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">additional_bq_parameters</span><span class="p">,</span> |
| <span class="s1">'table_side_inputs'</span><span class="p">:</span> <span class="n">table_side_inputs</span><span class="p">,</span> |
| <span class="s1">'schema_side_inputs'</span><span class="p">:</span> <span class="n">schema_side_inputs</span><span class="p">,</span> |
| <span class="s1">'triggering_frequency'</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">triggering_frequency</span><span class="p">,</span> |
| <span class="s1">'validate'</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">_validate</span><span class="p">,</span> |
| <span class="s1">'temp_file_format'</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">_temp_file_format</span><span class="p">,</span> |
| <span class="s1">'ignore_insert_ids'</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">_ignore_insert_ids</span><span class="p">,</span> |
| <span class="s1">'with_auto_sharding'</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">with_auto_sharding</span><span class="p">,</span> |
| <span class="p">}</span> |
| <span class="k">return</span> <span class="s1">'beam:transform:write_to_big_query:v0'</span><span class="p">,</span> <span class="n">pickler</span><span class="o">.</span><span class="n">dumps</span><span class="p">(</span><span class="n">config</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="WriteToBigQuery.from_runner_api"><a class="viewcode-back" href="../../../../apache_beam.io.gcp.bigquery.html#apache_beam.io.gcp.bigquery.WriteToBigQuery.from_runner_api">[docs]</a> <span class="nd">@PTransform</span><span class="o">.</span><span class="n">register_urn</span><span class="p">(</span><span class="s1">'beam:transform:write_to_big_query:v0'</span><span class="p">,</span> <span class="nb">bytes</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">from_runner_api</span><span class="p">(</span><span class="n">unused_ptransform</span><span class="p">,</span> <span class="n">payload</span><span class="p">,</span> <span class="n">context</span><span class="p">):</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.internal</span> <span class="kn">import</span> <span class="n">pickler</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.portability.api.beam_runner_api_pb2</span> <span class="kn">import</span> <span class="n">SideInput</span> |
| |
| <span class="n">config</span> <span class="o">=</span> <span class="n">pickler</span><span class="o">.</span><span class="n">loads</span><span class="p">(</span><span class="n">payload</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">deserialize</span><span class="p">(</span><span class="n">side_inputs</span><span class="p">):</span> |
| <span class="n">deserialized_side_inputs</span> <span class="o">=</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">side_inputs</span><span class="o">.</span><span class="n">items</span><span class="p">():</span> |
| <span class="n">side_input</span> <span class="o">=</span> <span class="n">SideInput</span><span class="p">()</span> |
| <span class="n">side_input</span><span class="o">.</span><span class="n">ParseFromString</span><span class="p">(</span><span class="n">v</span><span class="p">)</span> |
| <span class="n">deserialized_side_inputs</span><span class="p">[</span><span class="n">k</span><span class="p">]</span> <span class="o">=</span> <span class="n">side_input</span> |
| |
| <span class="c1"># This is an ordered list stored as a dict (see the comments in</span> |
| <span class="c1"># to_runner_api_parameter above).</span> |
| <span class="n">indexed_side_inputs</span> <span class="o">=</span> <span class="p">[(</span> |
| <span class="n">get_sideinput_index</span><span class="p">(</span><span class="n">tag</span><span class="p">),</span> |
| <span class="n">pvalue</span><span class="o">.</span><span class="n">AsSideInput</span><span class="o">.</span><span class="n">from_runner_api</span><span class="p">(</span><span class="n">si</span><span class="p">,</span> <span class="n">context</span><span class="p">))</span> <span class="k">for</span> <span class="n">tag</span><span class="p">,</span> |
| <span class="n">si</span> <span class="ow">in</span> <span class="n">deserialized_side_inputs</span><span class="o">.</span><span class="n">items</span><span class="p">()]</span> |
| <span class="k">return</span> <span class="p">[</span><span class="n">si</span> <span class="k">for</span> <span class="n">_</span><span class="p">,</span> <span class="n">si</span> <span class="ow">in</span> <span class="nb">sorted</span><span class="p">(</span><span class="n">indexed_side_inputs</span><span class="p">)]</span> |
| |
| <span class="n">config</span><span class="p">[</span><span class="s1">'table_side_inputs'</span><span class="p">]</span> <span class="o">=</span> <span class="n">deserialize</span><span class="p">(</span><span class="n">config</span><span class="p">[</span><span class="s1">'table_side_inputs'</span><span class="p">])</span> |
| <span class="n">config</span><span class="p">[</span><span class="s1">'schema_side_inputs'</span><span class="p">]</span> <span class="o">=</span> <span class="n">deserialize</span><span class="p">(</span><span class="n">config</span><span class="p">[</span><span class="s1">'schema_side_inputs'</span><span class="p">])</span> |
| |
| <span class="k">return</span> <span class="n">WriteToBigQuery</span><span class="p">(</span><span class="o">**</span><span class="n">config</span><span class="p">)</span></div></div> |
| |
| |
| <div class="viewcode-block" id="ReadFromBigQuery"><a class="viewcode-back" href="../../../../apache_beam.io.gcp.bigquery.html#apache_beam.io.gcp.bigquery.ReadFromBigQuery">[docs]</a><span class="k">class</span> <span class="nc">ReadFromBigQuery</span><span class="p">(</span><span class="n">PTransform</span><span class="p">):</span> |
| <span class="sd">"""Read data from BigQuery.</span> |
| |
| <span class="sd"> This PTransform uses a BigQuery export job to take a snapshot of the table</span> |
| <span class="sd"> on GCS, and then reads from each produced file. File format is Avro by</span> |
| <span class="sd"> default.</span> |
| |
| <span class="sd"> Args:</span> |
| <span class="sd"> method: The method to use to read from BigQuery. It may be EXPORT or</span> |
| <span class="sd"> DIRECT_READ. EXPORT invokes a BigQuery export request</span> |
| <span class="sd"> (https://cloud.google.com/bigquery/docs/exporting-data). DIRECT_READ reads</span> |
| <span class="sd"> directly from BigQuery storage using the BigQuery Read API</span> |
| <span class="sd"> (https://cloud.google.com/bigquery/docs/reference/storage). If</span> |
| <span class="sd"> unspecified, the default is currently EXPORT.</span> |
| <span class="sd"> use_native_datetime (bool): By default this transform exports BigQuery</span> |
| <span class="sd"> DATETIME fields as formatted strings (for example:</span> |
| <span class="sd"> 2021-01-01T12:59:59). If :data:`True`, BigQuery DATETIME fields will</span> |
| <span class="sd"> be returned as native Python datetime objects. This can only be used when</span> |
| <span class="sd"> 'method' is 'DIRECT_READ'.</span> |
| <span class="sd"> table (str, callable, ValueProvider): The ID of the table, or a callable</span> |
| <span class="sd"> that returns it. The ID must contain only letters ``a-z``, ``A-Z``,</span> |
| <span class="sd"> numbers ``0-9``, or underscores ``_``. If dataset argument is</span> |
| <span class="sd"> :data:`None` then the table argument must contain the entire table</span> |
| <span class="sd"> reference specified as: ``'DATASET.TABLE'``</span> |
| <span class="sd"> or ``'PROJECT:DATASET.TABLE'``. If it's a callable, it must receive one</span> |
| <span class="sd"> argument representing an element to be written to BigQuery, and return</span> |
| <span class="sd"> a TableReference, or a string table name as specified above.</span> |
| <span class="sd"> dataset (str): The ID of the dataset containing this table or</span> |
| <span class="sd"> :data:`None` if the table reference is specified entirely by the table</span> |
| <span class="sd"> argument.</span> |
| <span class="sd"> project (str): The ID of the project containing this table.</span> |
| <span class="sd"> query (str, ValueProvider): A query to be used instead of arguments</span> |
| <span class="sd"> table, dataset, and project.</span> |
| <span class="sd"> validate (bool): If :data:`True`, various checks will be done when source</span> |
| <span class="sd"> gets initialized (e.g., is table present?). This should be</span> |
| <span class="sd"> :data:`True` for most scenarios in order to catch errors as early as</span> |
| <span class="sd"> possible (pipeline construction instead of pipeline execution). It</span> |
| <span class="sd"> should be :data:`False` if the table is created during pipeline</span> |
| <span class="sd"> execution by a previous step.</span> |
| <span class="sd"> coder (~apache_beam.coders.coders.Coder): The coder for the table</span> |
| <span class="sd"> rows. If :data:`None`, then the default coder is</span> |
| <span class="sd"> _JsonToDictCoder, which will interpret every row as a JSON</span> |
| <span class="sd"> serialized dictionary.</span> |
| <span class="sd"> use_standard_sql (bool): Specifies whether to use BigQuery's standard SQL</span> |
| <span class="sd"> dialect for this query. The default value is :data:`False`.</span> |
| <span class="sd"> If set to :data:`True`, the query will use BigQuery's updated SQL</span> |
| <span class="sd"> dialect with improved standards compliance.</span> |
| <span class="sd"> This parameter is ignored for table inputs.</span> |
| <span class="sd"> flatten_results (bool): Flattens all nested and repeated fields in the</span> |
| <span class="sd"> query results. The default value is :data:`True`.</span> |
| <span class="sd"> kms_key (str): Optional Cloud KMS key name for use when creating new</span> |
| <span class="sd"> temporary tables.</span> |
| <span class="sd"> gcs_location (str, ValueProvider): The name of the Google Cloud Storage</span> |
| <span class="sd"> bucket where the extracted table should be written as a string or</span> |
| <span class="sd"> a :class:`~apache_beam.options.value_provider.ValueProvider`. If</span> |
| <span class="sd"> :data:`None`, then the temp_location parameter is used.</span> |
| <span class="sd"> bigquery_job_labels (dict): A dictionary with string labels to be passed</span> |
| <span class="sd"> to BigQuery export and query jobs created by this transform. See:</span> |
| <span class="sd"> https://cloud.google.com/bigquery/docs/reference/rest/v2/\</span> |
| <span class="sd"> Job#JobConfiguration</span> |
| <span class="sd"> use_json_exports (bool): By default, this transform works by exporting</span> |
| <span class="sd"> BigQuery data into Avro files, and reading those files. With this</span> |
| <span class="sd"> parameter, the transform will instead export to JSON files. JSON files</span> |
| <span class="sd"> are slower to read due to their larger size.</span> |
| <span class="sd"> When using JSON exports, the BigQuery types for DATE, DATETIME, TIME, and</span> |
| <span class="sd"> TIMESTAMP will be exported as strings. This behavior is consistent with</span> |
| <span class="sd"> BigQuerySource.</span> |
| <span class="sd"> When using Avro exports, these fields will be exported as native Python</span> |
| <span class="sd"> types (datetime.date, datetime.datetime, datetime.datetime,</span> |
| <span class="sd"> and datetime.datetime respectively). Avro exports are recommended.</span> |
| <span class="sd"> To learn more about BigQuery types, and Time-related type</span> |
| <span class="sd"> representations, see: https://cloud.google.com/bigquery/docs/reference/\</span> |
| <span class="sd"> standard-sql/data-types</span> |
| <span class="sd"> To learn more about type conversions between BigQuery and Avro, see:</span> |
| <span class="sd"> https://cloud.google.com/bigquery/docs/loading-data-cloud-storage-avro\</span> |
| <span class="sd"> #avro_conversions</span> |
| <span class="sd"> temp_dataset (``apache_beam.io.gcp.internal.clients.bigquery.\</span> |
| <span class="sd"> DatasetReference``):</span> |
| <span class="sd"> Temporary dataset reference to use when reading from BigQuery using a</span> |
| <span class="sd"> query. When reading using a query, BigQuery source will create a</span> |
| <span class="sd"> temporary dataset and a temporary table to store the results of the</span> |
| <span class="sd"> query. With this option, you can set an existing dataset to create the</span> |
| <span class="sd"> temporary table in. BigQuery source will create a temporary table in</span> |
| <span class="sd"> that dataset, and will remove it once it is not needed. Job needs access</span> |
| <span class="sd"> to create and delete tables within the given dataset. Dataset name</span> |
| <span class="sd"> should *not* start with the reserved prefix `beam_temp_dataset_`.</span> |
| <span class="sd"> query_priority (BigQueryQueryPriority): By default, this transform runs</span> |
| <span class="sd"> queries with BATCH priority. Use :attr:`BigQueryQueryPriority.INTERACTIVE`</span> |
| <span class="sd"> to run queries with INTERACTIVE priority. This option is ignored when</span> |
| <span class="sd"> reading from a table rather than a query. To learn more about query</span> |
| <span class="sd"> priority, see: https://cloud.google.com/bigquery/docs/running-queries</span> |
| <span class="sd"> """</span> |
| <div class="viewcode-block" id="ReadFromBigQuery.Method"><a class="viewcode-back" href="../../../../apache_beam.io.gcp.bigquery.html#apache_beam.io.gcp.bigquery.ReadFromBigQuery.Method">[docs]</a> <span class="k">class</span> <span class="nc">Method</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span> |
| <span class="n">EXPORT</span> <span class="o">=</span> <span class="s1">'EXPORT'</span> <span class="c1"># This is currently the default.</span> |
| <span class="n">DIRECT_READ</span> <span class="o">=</span> <span class="s1">'DIRECT_READ'</span></div> |
| |
| <span class="n">COUNTER</span> <span class="o">=</span> <span class="mi">0</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">gcs_location</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">method</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">use_native_datetime</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> |
| <span class="o">*</span><span class="n">args</span><span class="p">,</span> |
| <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">method</span> <span class="o">=</span> <span class="n">method</span> <span class="ow">or</span> <span class="n">ReadFromBigQuery</span><span class="o">.</span><span class="n">Method</span><span class="o">.</span><span class="n">EXPORT</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">use_native_datetime</span> <span class="o">=</span> <span class="n">use_native_datetime</span> |
| |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">method</span> <span class="ow">is</span> <span class="n">ReadFromBigQuery</span><span class="o">.</span><span class="n">Method</span><span class="o">.</span><span class="n">EXPORT</span> \ |
| <span class="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">use_native_datetime</span> <span class="ow">is</span> <span class="kc">True</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">TypeError</span><span class="p">(</span> |
| <span class="s1">'The "use_native_datetime" parameter cannot be True for EXPORT.'</span> |
| <span class="s1">' Please set the "use_native_datetime" parameter to False *OR*'</span> |
| <span class="s1">' set the "method" parameter to ReadFromBigQuery.Method.DIRECT_READ.'</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="n">gcs_location</span> <span class="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">method</span> <span class="ow">is</span> <span class="n">ReadFromBigQuery</span><span class="o">.</span><span class="n">Method</span><span class="o">.</span><span class="n">EXPORT</span><span class="p">:</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">gcs_location</span><span class="p">,</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="k">raise</span> <span class="ne">TypeError</span><span class="p">(</span> |
| <span class="s1">'</span><span class="si">%s</span><span class="s1">: gcs_location must be of type string'</span> |
| <span class="s1">' or ValueProvider; got </span><span class="si">%r</span><span class="s1"> instead'</span> <span class="o">%</span> |
| <span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="vm">__class__</span><span class="o">.</span><span class="vm">__name__</span><span class="p">,</span> <span class="nb">type</span><span class="p">(</span><span class="n">gcs_location</span><span class="p">)))</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">gcs_location</span><span class="p">,</span> <span class="nb">str</span><span class="p">):</span> |
| <span class="n">gcs_location</span> <span class="o">=</span> <span class="n">StaticValueProvider</span><span class="p">(</span><span class="nb">str</span><span class="p">,</span> <span class="n">gcs_location</span><span class="p">)</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_dataset_labels</span> <span class="o">=</span> <span class="p">{</span> |
| <span class="s1">'type'</span><span class="p">:</span> <span class="s1">'bq_direct_read_'</span> <span class="o">+</span> <span class="nb">str</span><span class="p">(</span><span class="n">uuid</span><span class="o">.</span><span class="n">uuid4</span><span class="p">())[</span><span class="mi">0</span><span class="p">:</span><span class="mi">10</span><span class="p">]</span> |
| <span class="p">}</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_args</span> <span class="o">=</span> <span class="n">args</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_kwargs</span> <span class="o">=</span> <span class="n">kwargs</span> |
| |
| <div class="viewcode-block" id="ReadFromBigQuery.expand"><a class="viewcode-back" href="../../../../apache_beam.io.gcp.bigquery.html#apache_beam.io.gcp.bigquery.ReadFromBigQuery.expand">[docs]</a> <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="n">pcoll</span><span class="p">):</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">method</span> <span class="ow">is</span> <span class="n">ReadFromBigQuery</span><span class="o">.</span><span class="n">Method</span><span class="o">.</span><span class="n">EXPORT</span><span class="p">:</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_expand_export</span><span class="p">(</span><span class="n">pcoll</span><span class="p">)</span> |
| <span class="k">elif</span> <span class="bp">self</span><span class="o">.</span><span class="n">method</span> <span class="ow">is</span> <span class="n">ReadFromBigQuery</span><span class="o">.</span><span class="n">Method</span><span class="o">.</span><span class="n">DIRECT_READ</span><span class="p">:</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_expand_direct_read</span><span class="p">(</span><span class="n">pcoll</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">'The method to read from BigQuery must be either EXPORT'</span> |
| <span class="s1">'or DIRECT_READ.'</span><span class="p">)</span></div> |
| |
| <span class="k">def</span> <span class="nf">_expand_export</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">pcoll</span><span class="p">):</span> |
| <span class="c1"># TODO(BEAM-11115): Make ReadFromBQ rely on ReadAllFromBQ implementation.</span> |
| <span class="n">temp_location</span> <span class="o">=</span> <span class="n">pcoll</span><span class="o">.</span><span class="n">pipeline</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">job_name</span> <span class="o">=</span> <span class="n">pcoll</span><span class="o">.</span><span class="n">pipeline</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">job_name</span> |
| <span class="n">gcs_location_vp</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">gcs_location</span> |
| <span class="n">unique_id</span> <span class="o">=</span> <span class="nb">str</span><span class="p">(</span><span class="n">uuid</span><span class="o">.</span><span class="n">uuid4</span><span class="p">())[</span><span class="mi">0</span><span class="p">:</span><span class="mi">10</span><span class="p">]</span> |
| |
| <span class="k">def</span> <span class="nf">file_path_to_remove</span><span class="p">(</span><span class="n">unused_elm</span><span class="p">):</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="n">gcs_location_vp</span><span class="p">,</span> <span class="n">temp_location</span><span class="p">,</span> <span class="n">unique_id</span><span class="p">,</span> <span class="kc">True</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">gcs_location</span> <span class="o">+</span> <span class="s1">'/'</span> |
| |
| <span class="n">files_to_remove_pcoll</span> <span class="o">=</span> <span class="n">beam</span><span class="o">.</span><span class="n">pvalue</span><span class="o">.</span><span class="n">AsList</span><span class="p">(</span> |
| <span class="n">pcoll</span><span class="o">.</span><span class="n">pipeline</span> |
| <span class="o">|</span> <span class="s1">'FilesToRemoveImpulse'</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="o">|</span> <span class="s1">'MapFilesToRemove'</span> <span class="o">>></span> <span class="n">beam</span><span class="o">.</span><span class="n">Map</span><span class="p">(</span><span class="n">file_path_to_remove</span><span class="p">))</span> |
| |
| <span class="k">try</span><span class="p">:</span> |
| <span class="n">step_name</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">label</span> |
| <span class="k">except</span> <span class="ne">AttributeError</span><span class="p">:</span> |
| <span class="n">step_name</span> <span class="o">=</span> <span class="s1">'ReadFromBigQuery_</span><span class="si">%d</span><span class="s1">'</span> <span class="o">%</span> <span class="n">ReadFromBigQuery</span><span class="o">.</span><span class="n">COUNTER</span> |
| <span class="n">ReadFromBigQuery</span><span class="o">.</span><span class="n">COUNTER</span> <span class="o">+=</span> <span class="mi">1</span> |
| <span class="k">return</span> <span class="p">(</span> |
| <span class="n">pcoll</span> |
| <span class="o">|</span> <span class="n">beam</span><span class="o">.</span><span class="n">io</span><span class="o">.</span><span class="n">Read</span><span class="p">(</span> |
| <span class="n">_CustomBigQuerySource</span><span class="p">(</span> |
| <span class="n">gcs_location</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">gcs_location</span><span class="p">,</span> |
| <span class="n">pipeline_options</span><span class="o">=</span><span class="n">pcoll</span><span class="o">.</span><span class="n">pipeline</span><span class="o">.</span><span class="n">options</span><span class="p">,</span> |
| <span class="n">method</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">method</span><span class="p">,</span> |
| <span class="n">job_name</span><span class="o">=</span><span class="n">job_name</span><span class="p">,</span> |
| <span class="n">step_name</span><span class="o">=</span><span class="n">step_name</span><span class="p">,</span> |
| <span class="n">unique_id</span><span class="o">=</span><span class="n">unique_id</span><span class="p">,</span> |
| <span class="o">*</span><span class="bp">self</span><span class="o">.</span><span class="n">_args</span><span class="p">,</span> |
| <span class="o">**</span><span class="bp">self</span><span class="o">.</span><span class="n">_kwargs</span><span class="p">))</span> |
| <span class="o">|</span> <span class="n">_PassThroughThenCleanup</span><span class="p">(</span><span class="n">files_to_remove_pcoll</span><span class="p">))</span> |
| |
| <span class="k">def</span> <span class="nf">_expand_direct_read</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">pcoll</span><span class="p">):</span> |
| <span class="n">project_id</span> <span class="o">=</span> <span class="kc">None</span> |
| <span class="n">temp_table_ref</span> <span class="o">=</span> <span class="kc">None</span> |
| <span class="k">if</span> <span class="s1">'temp_dataset'</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_kwargs</span><span class="p">:</span> |
| <span class="n">temp_table_ref</span> <span class="o">=</span> <span class="n">bigquery</span><span class="o">.</span><span class="n">TableReference</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">_kwargs</span><span class="p">[</span><span class="s1">'temp_dataset'</span><span class="p">]</span><span class="o">.</span><span class="n">projectId</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">_kwargs</span><span class="p">[</span><span class="s1">'temp_dataset'</span><span class="p">]</span><span class="o">.</span><span class="n">datasetId</span><span class="p">,</span> |
| <span class="n">tableId</span><span class="o">=</span><span class="s1">'beam_temp_table_'</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="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">project_id</span> <span class="o">=</span> <span class="n">pcoll</span><span class="o">.</span><span class="n">pipeline</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">def</span> <span class="nf">_get_pipeline_details</span><span class="p">(</span><span class="n">unused_elm</span><span class="p">):</span> |
| <span class="n">pipeline_details</span> <span class="o">=</span> <span class="p">{}</span> |
| <span class="k">if</span> <span class="n">temp_table_ref</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">pipeline_details</span><span class="p">[</span><span class="s1">'temp_table_ref'</span><span class="p">]</span> <span class="o">=</span> <span class="n">temp_table_ref</span> |
| <span class="k">elif</span> <span class="n">project_id</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">pipeline_details</span><span class="p">[</span><span class="s1">'project_id'</span><span class="p">]</span> <span class="o">=</span> <span class="n">project_id</span> |
| <span class="n">pipeline_details</span><span class="p">[</span> |
| <span class="s1">'bigquery_dataset_labels'</span><span class="p">]</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">bigquery_dataset_labels</span> |
| <span class="k">return</span> <span class="n">pipeline_details</span> |
| |
| <span class="n">project_to_cleanup_pcoll</span> <span class="o">=</span> <span class="n">beam</span><span class="o">.</span><span class="n">pvalue</span><span class="o">.</span><span class="n">AsList</span><span class="p">(</span> |
| <span class="n">pcoll</span><span class="o">.</span><span class="n">pipeline</span> |
| <span class="o">|</span> <span class="s1">'ProjectToCleanupImpulse'</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="o">|</span> <span class="s1">'MapProjectToCleanup'</span> <span class="o">>></span> <span class="n">beam</span><span class="o">.</span><span class="n">Map</span><span class="p">(</span><span class="n">_get_pipeline_details</span><span class="p">))</span> |
| |
| <span class="k">return</span> <span class="p">(</span> |
| <span class="n">pcoll</span> |
| <span class="o">|</span> <span class="n">beam</span><span class="o">.</span><span class="n">io</span><span class="o">.</span><span class="n">Read</span><span class="p">(</span> |
| <span class="n">_CustomBigQueryStorageSource</span><span class="p">(</span> |
| <span class="n">pipeline_options</span><span class="o">=</span><span class="n">pcoll</span><span class="o">.</span><span class="n">pipeline</span><span class="o">.</span><span class="n">options</span><span class="p">,</span> |
| <span class="n">method</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">method</span><span class="p">,</span> |
| <span class="n">use_native_datetime</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">use_native_datetime</span><span class="p">,</span> |
| <span class="n">temp_table</span><span class="o">=</span><span class="n">temp_table_ref</span><span class="p">,</span> |
| <span class="n">bigquery_dataset_labels</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">bigquery_dataset_labels</span><span class="p">,</span> |
| <span class="o">*</span><span class="bp">self</span><span class="o">.</span><span class="n">_args</span><span class="p">,</span> |
| <span class="o">**</span><span class="bp">self</span><span class="o">.</span><span class="n">_kwargs</span><span class="p">))</span> |
| <span class="o">|</span> <span class="n">_PassThroughThenCleanupTempDatasets</span><span class="p">(</span><span class="n">project_to_cleanup_pcoll</span><span class="p">))</span></div> |
| |
| |
| <div class="viewcode-block" id="ReadFromBigQueryRequest"><a class="viewcode-back" href="../../../../apache_beam.io.gcp.bigquery.html#apache_beam.io.gcp.bigquery.ReadFromBigQueryRequest">[docs]</a><span class="k">class</span> <span class="nc">ReadFromBigQueryRequest</span><span class="p">:</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Class that defines data to read from BQ.</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">query</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">use_standard_sql</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">True</span><span class="p">,</span> |
| <span class="n">table</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">TableReference</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> |
| <span class="n">flatten_results</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="sd">"""</span> |
| <span class="sd"> Only one of query or table should be specified.</span> |
| |
| <span class="sd"> :param query: SQL query to fetch data.</span> |
| <span class="sd"> :param use_standard_sql:</span> |
| <span class="sd"> Specifies whether to use BigQuery's standard SQL dialect for this query.</span> |
| <span class="sd"> The default value is :data:`True`. If set to :data:`False`,</span> |
| <span class="sd"> the query will use BigQuery's legacy SQL dialect.</span> |
| <span class="sd"> This parameter is ignored for table inputs.</span> |
| <span class="sd"> :param table:</span> |
| <span class="sd"> The ID of the table to read. The ID must contain only letters</span> |
| <span class="sd"> ``a-z``, ``A-Z``, numbers ``0-9``, or underscores ``_``. Table should</span> |
| <span class="sd"> define project and dataset (ex.: ``'PROJECT:DATASET.TABLE'``).</span> |
| <span class="sd"> :param flatten_results:</span> |
| <span class="sd"> Flattens all nested and repeated fields in the query results.</span> |
| <span class="sd"> The default value is :data:`False`.</span> |
| <span class="sd"> """</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">flatten_results</span> <span class="o">=</span> <span class="n">flatten_results</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">query</span> <span class="o">=</span> <span class="n">query</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">use_standard_sql</span> <span class="o">=</span> <span class="n">use_standard_sql</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">table</span> <span class="o">=</span> <span class="n">table</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">validate</span><span class="p">()</span> |
| |
| <span class="c1"># We use this internal object ID to generate BigQuery export directories.</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">obj_id</span> <span class="o">=</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">100000</span><span class="p">)</span> |
| |
| <div class="viewcode-block" id="ReadFromBigQueryRequest.validate"><a class="viewcode-back" href="../../../../apache_beam.io.gcp.bigquery.html#apache_beam.io.gcp.bigquery.ReadFromBigQueryRequest.validate">[docs]</a> <span class="k">def</span> <span class="nf">validate</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">table</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> <span class="ow">and</span> <span class="bp">self</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="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span> |
| <span class="s1">'Both a BigQuery table and a query were specified.'</span> |
| <span class="s1">' Please specify only one of these.'</span><span class="p">)</span> |
| <span class="k">elif</span> <span class="bp">self</span><span class="o">.</span><span class="n">table</span> <span class="ow">is</span> <span class="kc">None</span> <span class="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">query</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="s1">'A BigQuery table or a query must be specified'</span><span class="p">)</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">table</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">table</span><span class="p">,</span> <span class="nb">str</span><span class="p">):</span> |
| <span class="k">assert</span> <span class="bp">self</span><span class="o">.</span><span class="n">table</span><span class="o">.</span><span class="n">find</span><span class="p">(</span><span class="s1">'.'</span><span class="p">),</span> <span class="p">(</span> |
| <span class="s1">'Expected a table reference '</span> |
| <span class="s1">'(PROJECT:DATASET.TABLE or DATASET.TABLE) instead of </span><span class="si">%s</span><span class="s1">'</span> |
| <span class="o">%</span> <span class="bp">self</span><span class="o">.</span><span class="n">table</span><span class="p">)</span></div></div> |
| |
| |
| <div class="viewcode-block" id="ReadAllFromBigQuery"><a class="viewcode-back" href="../../../../apache_beam.io.gcp.bigquery.html#apache_beam.io.gcp.bigquery.ReadAllFromBigQuery">[docs]</a><span class="nd">@experimental</span><span class="p">()</span> |
| <span class="k">class</span> <span class="nc">ReadAllFromBigQuery</span><span class="p">(</span><span class="n">PTransform</span><span class="p">):</span> |
| <span class="sd">"""Read data from BigQuery.</span> |
| |
| <span class="sd"> PTransform:ReadFromBigQueryRequest->Rows</span> |
| |
| <span class="sd"> This PTransform uses a BigQuery export job to take a snapshot of the table</span> |
| <span class="sd"> on GCS, and then reads from each produced file. Data is exported into</span> |
| <span class="sd"> a new subdirectory for each export using UUIDs generated in</span> |
| <span class="sd"> `ReadFromBigQueryRequest` objects.</span> |
| |
| <span class="sd"> It is recommended not to use this PTransform for streaming jobs on</span> |
| <span class="sd"> GlobalWindow, since it will not be able to cleanup snapshots.</span> |
| |
| <span class="sd"> Args:</span> |
| <span class="sd"> gcs_location (str): The name of the Google Cloud Storage</span> |
| <span class="sd"> bucket where the extracted table should be written as a string. If</span> |
| <span class="sd"> :data:`None`, then the temp_location parameter is used.</span> |
| <span class="sd"> validate (bool): If :data:`True`, various checks will be done when source</span> |
| <span class="sd"> gets initialized (e.g., is table present?).</span> |
| <span class="sd"> kms_key (str): Experimental. Optional Cloud KMS key name for use when</span> |
| <span class="sd"> creating new temporary tables.</span> |
| <span class="sd"> """</span> |
| <span class="n">COUNTER</span> <span class="o">=</span> <span class="mi">0</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">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">validate</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">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">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">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">query_priority</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="n">BigQueryQueryPriority</span><span class="o">.</span><span class="n">BATCH</span><span class="p">):</span> |
| <span class="k">if</span> <span class="n">gcs_location</span><span class="p">:</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">gcs_location</span><span class="p">,</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="k">raise</span> <span class="ne">TypeError</span><span class="p">(</span> |
| <span class="s1">'</span><span class="si">%s</span><span class="s1">: gcs_location must be of type string'</span> |
| <span class="s1">' or ValueProvider; got </span><span class="si">%r</span><span class="s1"> instead'</span> <span class="o">%</span> |
| <span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="vm">__class__</span><span class="o">.</span><span class="vm">__name__</span><span class="p">,</span> <span class="nb">type</span><span class="p">(</span><span class="n">gcs_location</span><span class="p">)))</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">validate</span> <span class="o">=</span> <span class="n">validate</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">bigquery_job_labels</span> <span class="o">=</span> <span class="n">bigquery_job_labels</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="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="k">def</span> <span class="nf">expand</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">pcoll</span><span class="p">):</span> |
| <span class="n">job_name</span> <span class="o">=</span> <span class="n">pcoll</span><span class="o">.</span><span class="n">pipeline</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">job_name</span> |
| <span class="n">project</span> <span class="o">=</span> <span class="n">pcoll</span><span class="o">.</span><span class="n">pipeline</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="n">unique_id</span> <span class="o">=</span> <span class="nb">str</span><span class="p">(</span><span class="n">uuid</span><span class="o">.</span><span class="n">uuid4</span><span class="p">())[</span><span class="mi">0</span><span class="p">:</span><span class="mi">10</span><span class="p">]</span> |
| |
| <span class="k">try</span><span class="p">:</span> |
| <span class="n">step_name</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">label</span> |
| <span class="k">except</span> <span class="ne">AttributeError</span><span class="p">:</span> |
| <span class="n">step_name</span> <span class="o">=</span> <span class="s1">'ReadAllFromBigQuery_</span><span class="si">%d</span><span class="s1">'</span> <span class="o">%</span> <span class="n">ReadAllFromBigQuery</span><span class="o">.</span><span class="n">COUNTER</span> |
| <span class="n">ReadAllFromBigQuery</span><span class="o">.</span><span class="n">COUNTER</span> <span class="o">+=</span> <span class="mi">1</span> |
| |
| <span class="n">sources_to_read</span><span class="p">,</span> <span class="n">cleanup_locations</span> <span class="o">=</span> <span class="p">(</span> |
| <span class="n">pcoll</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">_BigQueryReadSplit</span><span class="p">(</span> |
| <span class="n">options</span><span class="o">=</span><span class="n">pcoll</span><span class="o">.</span><span class="n">pipeline</span><span class="o">.</span><span class="n">options</span><span class="p">,</span> |
| <span class="n">gcs_location</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">gcs_location</span><span class="p">,</span> |
| <span class="n">bigquery_job_labels</span><span class="o">=</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_name</span><span class="o">=</span><span class="n">job_name</span><span class="p">,</span> |
| <span class="n">step_name</span><span class="o">=</span><span class="n">step_name</span><span class="p">,</span> |
| <span class="n">unique_id</span><span class="o">=</span><span class="n">unique_id</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">project</span><span class="o">=</span><span class="n">project</span><span class="p">,</span> |
| <span class="n">temp_dataset</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">query_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="o">.</span><span class="n">with_outputs</span><span class="p">(</span> |
| <span class="s2">"location_to_cleanup"</span><span class="p">,</span> <span class="n">main</span><span class="o">=</span><span class="s2">"files_to_read"</span><span class="p">)</span> |
| <span class="p">)</span> |
| |
| <span class="k">return</span> <span class="p">(</span> |
| <span class="n">sources_to_read</span> |
| <span class="o">|</span> <span class="n">SDFBoundedSourceReader</span><span class="p">(</span><span class="n">data_to_display</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">display_data</span><span class="p">())</span> |
| <span class="o">|</span> <span class="n">_PassThroughThenCleanup</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">AsIter</span><span class="p">(</span><span class="n">cleanup_locations</span><span class="p">)))</span></div> |
| </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> |
