| |
| <html> |
| <head> |
| <title>Beam YAML Transform Index</title> |
| <style> |
| pre { line-height: 125%; } |
| td.linenos .normal { color: inherit; background-color: transparent; padding-left: 5px; padding-right: 5px; } |
| span.linenos { color: inherit; background-color: transparent; padding-left: 5px; padding-right: 5px; } |
| td.linenos .special { color: #000000; background-color: #ffffc0; padding-left: 5px; padding-right: 5px; } |
| span.linenos.special { color: #000000; background-color: #ffffc0; padding-left: 5px; padding-right: 5px; } |
| .codehilite .hll { background-color: #ffffcc } |
| .codehilite { background: #f8f8f8; } |
| .codehilite .c { color: #3D7B7B; font-style: italic } /* Comment */ |
| .codehilite .err { border: 1px solid #FF0000 } /* Error */ |
| .codehilite .k { color: #008000; font-weight: bold } /* Keyword */ |
| .codehilite .o { color: #666666 } /* Operator */ |
| .codehilite .ch { color: #3D7B7B; font-style: italic } /* Comment.Hashbang */ |
| .codehilite .cm { color: #3D7B7B; font-style: italic } /* Comment.Multiline */ |
| .codehilite .cp { color: #9C6500 } /* Comment.Preproc */ |
| .codehilite .cpf { color: #3D7B7B; font-style: italic } /* Comment.PreprocFile */ |
| .codehilite .c1 { color: #3D7B7B; font-style: italic } /* Comment.Single */ |
| .codehilite .cs { color: #3D7B7B; font-style: italic } /* Comment.Special */ |
| .codehilite .gd { color: #A00000 } /* Generic.Deleted */ |
| .codehilite .ge { font-style: italic } /* Generic.Emph */ |
| .codehilite .ges { font-weight: bold; font-style: italic } /* Generic.EmphStrong */ |
| .codehilite .gr { color: #E40000 } /* Generic.Error */ |
| .codehilite .gh { color: #000080; font-weight: bold } /* Generic.Heading */ |
| .codehilite .gi { color: #008400 } /* Generic.Inserted */ |
| .codehilite .go { color: #717171 } /* Generic.Output */ |
| .codehilite .gp { color: #000080; font-weight: bold } /* Generic.Prompt */ |
| .codehilite .gs { font-weight: bold } /* Generic.Strong */ |
| .codehilite .gu { color: #800080; font-weight: bold } /* Generic.Subheading */ |
| .codehilite .gt { color: #0044DD } /* Generic.Traceback */ |
| .codehilite .kc { color: #008000; font-weight: bold } /* Keyword.Constant */ |
| .codehilite .kd { color: #008000; font-weight: bold } /* Keyword.Declaration */ |
| .codehilite .kn { color: #008000; font-weight: bold } /* Keyword.Namespace */ |
| .codehilite .kp { color: #008000 } /* Keyword.Pseudo */ |
| .codehilite .kr { color: #008000; font-weight: bold } /* Keyword.Reserved */ |
| .codehilite .kt { color: #B00040 } /* Keyword.Type */ |
| .codehilite .m { color: #666666 } /* Literal.Number */ |
| .codehilite .s { color: #BA2121 } /* Literal.String */ |
| .codehilite .na { color: #687822 } /* Name.Attribute */ |
| .codehilite .nb { color: #008000 } /* Name.Builtin */ |
| .codehilite .nc { color: #0000FF; font-weight: bold } /* Name.Class */ |
| .codehilite .no { color: #880000 } /* Name.Constant */ |
| .codehilite .nd { color: #AA22FF } /* Name.Decorator */ |
| .codehilite .ni { color: #717171; font-weight: bold } /* Name.Entity */ |
| .codehilite .ne { color: #CB3F38; font-weight: bold } /* Name.Exception */ |
| .codehilite .nf { color: #0000FF } /* Name.Function */ |
| .codehilite .nl { color: #767600 } /* Name.Label */ |
| .codehilite .nn { color: #0000FF; font-weight: bold } /* Name.Namespace */ |
| .codehilite .nt { color: #008000; font-weight: bold } /* Name.Tag */ |
| .codehilite .nv { color: #19177C } /* Name.Variable */ |
| .codehilite .ow { color: #AA22FF; font-weight: bold } /* Operator.Word */ |
| .codehilite .w { color: #bbbbbb } /* Text.Whitespace */ |
| .codehilite .mb { color: #666666 } /* Literal.Number.Bin */ |
| .codehilite .mf { color: #666666 } /* Literal.Number.Float */ |
| .codehilite .mh { color: #666666 } /* Literal.Number.Hex */ |
| .codehilite .mi { color: #666666 } /* Literal.Number.Integer */ |
| .codehilite .mo { color: #666666 } /* Literal.Number.Oct */ |
| .codehilite .sa { color: #BA2121 } /* Literal.String.Affix */ |
| .codehilite .sb { color: #BA2121 } /* Literal.String.Backtick */ |
| .codehilite .sc { color: #BA2121 } /* Literal.String.Char */ |
| .codehilite .dl { color: #BA2121 } /* Literal.String.Delimiter */ |
| .codehilite .sd { color: #BA2121; font-style: italic } /* Literal.String.Doc */ |
| .codehilite .s2 { color: #BA2121 } /* Literal.String.Double */ |
| .codehilite .se { color: #AA5D1F; font-weight: bold } /* Literal.String.Escape */ |
| .codehilite .sh { color: #BA2121 } /* Literal.String.Heredoc */ |
| .codehilite .si { color: #A45A77; font-weight: bold } /* Literal.String.Interpol */ |
| .codehilite .sx { color: #008000 } /* Literal.String.Other */ |
| .codehilite .sr { color: #A45A77 } /* Literal.String.Regex */ |
| .codehilite .s1 { color: #BA2121 } /* Literal.String.Single */ |
| .codehilite .ss { color: #19177C } /* Literal.String.Symbol */ |
| .codehilite .bp { color: #008000 } /* Name.Builtin.Pseudo */ |
| .codehilite .fm { color: #0000FF } /* Name.Function.Magic */ |
| .codehilite .vc { color: #19177C } /* Name.Variable.Class */ |
| .codehilite .vg { color: #19177C } /* Name.Variable.Global */ |
| .codehilite .vi { color: #19177C } /* Name.Variable.Instance */ |
| .codehilite .vm { color: #19177C } /* Name.Variable.Magic */ |
| .codehilite .il { color: #666666 } /* Literal.Number.Integer.Long */ |
| |
| .nav { |
| height: 100%; |
| width: 12em; |
| position: fixed; |
| top: 0; |
| left: 0; |
| overflow-x: hidden; |
| } |
| .nav a { |
| color: #333; |
| padding: .2em; |
| display: block; |
| text-decoration: none; |
| } |
| .nav a:hover { |
| color: #888; |
| } |
| .nav li { |
| list-style-type: none; |
| margin: 0; |
| padding: 0; |
| } |
| .content { |
| margin-left: 12em; |
| } |
| h2 { |
| margin-top: 2em; |
| } |
| |
| </style> |
| </head> |
| <body> |
| <div class="nav"> |
| <div class="toc"> |
| <ul> |
| <li><a href="#assigntimestamps">AssignTimestamps</a></li> |
| <li><a href="#combine">Combine</a></li> |
| <li><a href="#create">Create</a></li> |
| <li><a href="#explode">Explode</a></li> |
| <li><a href="#filter">Filter</a></li> |
| <li><a href="#flatten">Flatten</a></li> |
| <li><a href="#logfortesting">LogForTesting</a></li> |
| <li><a href="#maptofields">MapToFields</a></li> |
| <li><a href="#pytransform">PyTransform</a></li> |
| <li><a href="#sql">Sql</a></li> |
| <li><a href="#windowinto">WindowInto</a></li> |
| <li><a href="#readfromavro">ReadFromAvro</a></li> |
| <li><a href="#writetoavro">WriteToAvro</a></li> |
| <li><a href="#readfrombigquery">ReadFromBigQuery</a></li> |
| <li><a href="#writetobigquery">WriteToBigQuery</a></li> |
| <li><a href="#readfromcsv">ReadFromCsv</a></li> |
| <li><a href="#writetocsv">WriteToCsv</a></li> |
| <li><a href="#readfromjdbc">ReadFromJdbc</a></li> |
| <li><a href="#writetojdbc">WriteToJdbc</a></li> |
| <li><a href="#readfromjson">ReadFromJson</a></li> |
| <li><a href="#writetojson">WriteToJson</a></li> |
| <li><a href="#readfromkafka">ReadFromKafka</a></li> |
| <li><a href="#writetokafka">WriteToKafka</a></li> |
| <li><a href="#readfrommysql">ReadFromMySql</a></li> |
| <li><a href="#writetomysql">WriteToMySql</a></li> |
| <li><a href="#readfromoracle">ReadFromOracle</a></li> |
| <li><a href="#writetooracle">WriteToOracle</a></li> |
| <li><a href="#readfromparquet">ReadFromParquet</a></li> |
| <li><a href="#writetoparquet">WriteToParquet</a></li> |
| <li><a href="#readfrompostgres">ReadFromPostgres</a></li> |
| <li><a href="#writetopostgres">WriteToPostgres</a></li> |
| <li><a href="#readfrompubsub">ReadFromPubSub</a></li> |
| <li><a href="#writetopubsub">WriteToPubSub</a></li> |
| <li><a href="#readfrompubsublite">ReadFromPubSubLite</a></li> |
| <li><a href="#writetopubsublite">WriteToPubSubLite</a></li> |
| <li><a href="#readfromsqlserver">ReadFromSqlServer</a></li> |
| <li><a href="#writetosqlserver">WriteToSqlServer</a></li> |
| <li><a href="#readfromtext">ReadFromText</a></li> |
| <li><a href="#writetotext">WriteToText</a></li> |
| </ul> |
| </div> |
| |
| </div> |
| <div class="content"> |
| <h1>Beam YAML Transform Index</h1> |
| <h2 id="assigntimestamps">AssignTimestamps</h2> |
| <p>Assigns a new timestamp each element of its input.</p> |
| <p>This can be useful when reading records that have the timestamp embedded |
| in them, for example with various file types or other sources that by default |
| set all timestamps to the infinite past.</p> |
| <p>Note that the timestamp should only be set forward, as setting it backwards |
| may not cause it to hold back an already advanced watermark and the data |
| could become droppably late.</p> |
| <p>Supported languages: generic, javascript, python</p> |
| <h3 id="configuration">Configuration</h3> |
| <ul> |
| <li> |
| <p><strong>timestamp</strong> <code>?</code> (Optional) : A field, callable, or expression giving the new timestamp.</p> |
| </li> |
| <li> |
| <p><strong>language</strong> <code>string</code> (Optional) : The language of the timestamp expression.</p> |
| </li> |
| <li> |
| <p><strong>error_handling</strong> <code>Row</code> : Whether and how to handle errors during iteration. </p> |
| <p>Row fields:</p> |
| <ul> |
| <li><strong>output</strong> <code>string</code></li> |
| </ul> |
| </li> |
| </ul> |
| <h3 id="usage">Usage</h3> |
| <div class="codehilite"><pre><span></span><code><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">AssignTimestamps</span> |
| <span class="nt">input</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">...</span> |
| <span class="nt">config</span><span class="p">:</span> |
| <span class="w"> </span><span class="nt">timestamp</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">timestamp</span> |
| <span class="w"> </span><span class="nt">language</span><span class="p">:</span><span class="w"> </span><span class="s">"language"</span> |
| <span class="w"> </span><span class="nt">error_handling</span><span class="p">:</span> |
| <span class="w"> </span><span class="nt">output</span><span class="p">:</span><span class="w"> </span><span class="s">"output"</span> |
| </code></pre></div> |
| |
| <h2 id="combine">Combine</h2> |
| <p>Groups and combines records sharing common fields.</p> |
| <p>Built-in combine functions are <code>sum</code>, <code>max</code>, <code>min</code>, <code>all</code>, <code>any</code>, <code>mean</code>, <code>count</code>, <code>group</code>, <code>concat</code> |
| but custom aggregation functions can be used as well.</p> |
| <p>See also the documentation on |
| <a href="https://beam.apache.org/documentation/sdks/yaml-combine/">YAML Aggregation</a>.</p> |
| <p>Supported languages: calcite, generic, javascript, python, sql</p> |
| <h3 id="configuration_1">Configuration</h3> |
| <ul> |
| <li> |
| <p><strong>group_by</strong> <code>Array[string]</code> </p> |
| </li> |
| <li> |
| <p><strong>combine</strong> <code>Map[string, Map[string, ?]]</code> </p> |
| </li> |
| <li> |
| <p><strong>language</strong> <code>string</code> (Optional)</p> |
| </li> |
| </ul> |
| <h3 id="usage_1">Usage</h3> |
| <div class="codehilite"><pre><span></span><code><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">Combine</span> |
| <span class="nt">input</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">...</span> |
| <span class="nt">config</span><span class="p">:</span> |
| <span class="w"> </span><span class="nt">group_by</span><span class="p">:</span> |
| <span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="s">"group_by"</span> |
| <span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">...</span> |
| <span class="w"> </span><span class="nt">combine</span><span class="p">:</span> |
| <span class="w"> </span><span class="nt">a</span><span class="p">:</span> |
| <span class="w"> </span><span class="nt">a</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">combine_value_a_value_a</span> |
| <span class="w"> </span><span class="nt">b</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">combine_value_a_value_b</span> |
| <span class="w"> </span><span class="nt">c</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">...</span> |
| <span class="w"> </span><span class="nt">b</span><span class="p">:</span> |
| <span class="w"> </span><span class="nt">a</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">combine_value_b_value_a</span> |
| <span class="w"> </span><span class="nt">b</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">combine_value_b_value_b</span> |
| <span class="w"> </span><span class="nt">c</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">...</span> |
| <span class="w"> </span><span class="nt">c</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">...</span> |
| <span class="w"> </span><span class="nt">language</span><span class="p">:</span><span class="w"> </span><span class="s">"language"</span> |
| </code></pre></div> |
| |
| <h2 id="create">Create</h2> |
| <p>Creates a collection containing a specified set of elements.</p> |
| <p>This transform always produces schema'd data. For example</p> |
| <div class="codehilite"><pre><span></span><code><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">Create</span> |
| <span class="nt">config</span><span class="p">:</span> |
| <span class="w"> </span><span class="nt">elements</span><span class="p">:</span><span class="w"> </span><span class="p p-Indicator">[</span><span class="nv">1</span><span class="p p-Indicator">,</span><span class="w"> </span><span class="nv">2</span><span class="p p-Indicator">,</span><span class="w"> </span><span class="nv">3</span><span class="p p-Indicator">]</span> |
| </code></pre></div> |
| |
| <p>will result in an output with three elements with a schema of |
| Row(element=int) whereas YAML/JSON-style mappings will be interpreted |
| directly as Beam rows, e.g.</p> |
| <div class="codehilite"><pre><span></span><code><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">Create</span> |
| <span class="nt">config</span><span class="p">:</span> |
| <span class="w"> </span><span class="nt">elements</span><span class="p">:</span> |
| <span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="p p-Indicator">{</span><span class="nt">first</span><span class="p">:</span><span class="w"> </span><span class="nv">0</span><span class="p p-Indicator">,</span><span class="nt"> second</span><span class="p">:</span><span class="w"> </span><span class="p p-Indicator">{</span><span class="nt">str</span><span class="p">:</span><span class="w"> </span><span class="s">"foo"</span><span class="p p-Indicator">,</span><span class="nt"> values</span><span class="p">:</span><span class="w"> </span><span class="p p-Indicator">[</span><span class="nv">1</span><span class="p p-Indicator">,</span><span class="w"> </span><span class="nv">2</span><span class="p p-Indicator">,</span><span class="w"> </span><span class="nv">3</span><span class="p p-Indicator">]}}</span> |
| <span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="p p-Indicator">{</span><span class="nt">first</span><span class="p">:</span><span class="w"> </span><span class="nv">1</span><span class="p p-Indicator">,</span><span class="nt"> second</span><span class="p">:</span><span class="w"> </span><span class="p p-Indicator">{</span><span class="nt">str</span><span class="p">:</span><span class="w"> </span><span class="s">"bar"</span><span class="p p-Indicator">,</span><span class="nt"> values</span><span class="p">:</span><span class="w"> </span><span class="p p-Indicator">[</span><span class="nv">4</span><span class="p p-Indicator">,</span><span class="w"> </span><span class="nv">5</span><span class="p p-Indicator">,</span><span class="w"> </span><span class="nv">6</span><span class="p p-Indicator">]}}</span> |
| </code></pre></div> |
| |
| <p>will result in a schema of the form (int, Row(string, List[int])).</p> |
| <p>This can also be expressed as YAML</p> |
| <div class="codehilite"><pre><span></span><code><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">Create</span> |
| <span class="nt">config</span><span class="p">:</span> |
| <span class="w"> </span><span class="nt">elements</span><span class="p">:</span> |
| <span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">first</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">0</span> |
| <span class="w"> </span><span class="nt">second</span><span class="p">:</span> |
| <span class="w"> </span><span class="nt">str</span><span class="p">:</span><span class="w"> </span><span class="s">"foo"</span> |
| <span class="w"> </span><span class="nt">values</span><span class="p">:</span><span class="w"> </span><span class="p p-Indicator">[</span><span class="nv">1</span><span class="p p-Indicator">,</span><span class="w"> </span><span class="nv">2</span><span class="p p-Indicator">,</span><span class="w"> </span><span class="nv">3</span><span class="p p-Indicator">]</span> |
| <span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">first</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">1</span> |
| <span class="w"> </span><span class="nt">second</span><span class="p">:</span> |
| <span class="w"> </span><span class="nt">str</span><span class="p">:</span><span class="w"> </span><span class="s">"bar"</span> |
| <span class="w"> </span><span class="nt">values</span><span class="p">:</span><span class="w"> </span><span class="p p-Indicator">[</span><span class="nv">4</span><span class="p p-Indicator">,</span><span class="w"> </span><span class="nv">5</span><span class="p p-Indicator">,</span><span class="w"> </span><span class="nv">6</span><span class="p p-Indicator">]</span> |
| </code></pre></div> |
| |
| <h3 id="configuration_2">Configuration</h3> |
| <ul> |
| <li> |
| <p><strong>elements</strong> <code>Array[?]</code> : The set of elements that should belong to the PCollection. |
| YAML/JSON-style mappings will be interpreted as Beam rows. |
| Primitives will be mapped to rows with a single "element" field.</p> |
| </li> |
| <li> |
| <p><strong>reshuffle</strong> <code>boolean</code> (Optional) : (optional) Whether to introduce a reshuffle (to possibly |
| redistribute the work) if there is more than one element in the |
| collection. Defaults to True.</p> |
| </li> |
| </ul> |
| <h3 id="usage_2">Usage</h3> |
| <div class="codehilite"><pre><span></span><code><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">Create</span> |
| <span class="nt">config</span><span class="p">:</span> |
| <span class="w"> </span><span class="nt">elements</span><span class="p">:</span> |
| <span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">elements</span> |
| <span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">...</span> |
| <span class="w"> </span><span class="nt">reshuffle</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true|false</span> |
| </code></pre></div> |
| |
| <h2 id="explode">Explode</h2> |
| <p>Explodes (aka unnest/flatten) one or more fields producing multiple rows.</p> |
| <p>Given one or more fields of iterable type, produces multiple rows, one for |
| each value of that field. For example, a row of the form <code>('a', [1, 2, 3])</code> |
| would expand to <code>('a', 1)</code>, <code>('a', 2')</code>, and <code>('a', 3)</code> when exploded on |
| the second field.</p> |
| <p>This is akin to a <code>FlatMap</code> when paired with the MapToFields transform.</p> |
| <p>See more complete documentation on |
| <a href="https://beam.apache.org/documentation/sdks/yaml-udf/#flatmap">YAML Mapping Functions</a>.</p> |
| <h3 id="configuration_3">Configuration</h3> |
| <ul> |
| <li> |
| <p><strong>fields</strong> <code>?</code> (Optional) : The list of fields to expand.</p> |
| </li> |
| <li> |
| <p><strong>cross_product</strong> <code>boolean</code> (Optional) : If multiple fields are specified, indicates whether the |
| full cross-product of combinations should be produced, or if the |
| first element of the first field corresponds to the first element |
| of the second field, etc. For example, the row |
| <code>(['a', 'b'], [1, 2])</code> would expand to the four rows |
| <code>('a', 1)</code>, <code>('a', 2)</code>, <code>('b', 1)</code>, and <code>('b', 2)</code> when |
| <code>cross_product</code> is set to <code>true</code> but only the two rows |
| <code>('a', 1)</code> and <code>('b', 2)</code> when it is set to <code>false</code>. |
| Only meaningful (and required) if multiple rows are specified.</p> |
| </li> |
| <li> |
| <p><strong>error_handling</strong> <code>Map[string, ?]</code> (Optional) : Whether and how to handle errors during iteration.</p> |
| </li> |
| </ul> |
| <h3 id="usage_3">Usage</h3> |
| <div class="codehilite"><pre><span></span><code><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">Explode</span> |
| <span class="nt">input</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">...</span> |
| <span class="nt">config</span><span class="p">:</span> |
| <span class="w"> </span><span class="nt">fields</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">fields</span> |
| <span class="w"> </span><span class="nt">cross_product</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true|false</span> |
| <span class="w"> </span><span class="nt">error_handling</span><span class="p">:</span> |
| <span class="w"> </span><span class="nt">a</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">error_handling_value_a</span> |
| <span class="w"> </span><span class="nt">b</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">error_handling_value_b</span> |
| <span class="w"> </span><span class="nt">c</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">...</span> |
| </code></pre></div> |
| |
| <h2 id="filter">Filter</h2> |
| <p>Keeps only records that satisfy the given criteria.</p> |
| <p>See more complete documentation on |
| <a href="https://beam.apache.org/documentation/sdks/yaml-udf/#filtering">YAML Filtering</a>.</p> |
| <p>Supported languages: calcite, java, javascript, python, sql</p> |
| <h3 id="configuration_4">Configuration</h3> |
| <ul> |
| <li> |
| <p><strong>language</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>keep</strong> <code>Row</code> </p> |
| <p>Row fields:</p> |
| <ul> |
| <li> |
| <p><strong>callable</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>expression</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>name</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>path</strong> <code>string</code> (Optional)</p> |
| </li> |
| </ul> |
| </li> |
| <li> |
| <p><strong>error_handling</strong> <code>Row</code> (Optional) </p> |
| <p>Row fields:</p> |
| <ul> |
| <li><strong>output</strong> <code>string</code></li> |
| </ul> |
| </li> |
| </ul> |
| <h3 id="usage_4">Usage</h3> |
| <div class="codehilite"><pre><span></span><code><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">Filter</span> |
| <span class="nt">input</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">...</span> |
| <span class="nt">config</span><span class="p">:</span> |
| <span class="w"> </span><span class="nt">language</span><span class="p">:</span><span class="w"> </span><span class="s">"language"</span> |
| <span class="w"> </span><span class="nt">keep</span><span class="p">:</span> |
| <span class="w"> </span><span class="nt">callable</span><span class="p">:</span><span class="w"> </span><span class="s">"callable"</span> |
| <span class="w"> </span><span class="nt">expression</span><span class="p">:</span><span class="w"> </span><span class="s">"expression"</span> |
| <span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="s">"name"</span> |
| <span class="w"> </span><span class="nt">path</span><span class="p">:</span><span class="w"> </span><span class="s">"path"</span> |
| <span class="w"> </span><span class="nt">error_handling</span><span class="p">:</span> |
| <span class="w"> </span><span class="nt">output</span><span class="p">:</span><span class="w"> </span><span class="s">"output"</span> |
| </code></pre></div> |
| |
| <h2 id="flatten">Flatten</h2> |
| <p>Flattens multiple PCollections into a single PCollection.</p> |
| <p>The elements of the resulting PCollection will be the (disjoint) union of |
| all the elements of all the inputs.</p> |
| <p>Note that in YAML transforms can always take a list of inputs which will |
| be implicitly flattened.</p> |
| <h3 id="configuration_5">Configuration</h3> |
| <p>No configuration parameters.</p> |
| <h3 id="usage_5">Usage</h3> |
| <div class="codehilite"><pre><span></span><code><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">Flatten</span> |
| <span class="nt">input</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">...</span> |
| </code></pre></div> |
| |
| <h2 id="logfortesting">LogForTesting</h2> |
| <p>Logs each element of its input PCollection.</p> |
| <p>The output of this transform is a copy of its input for ease of use in |
| chain-style pipelines.</p> |
| <h3 id="configuration_6">Configuration</h3> |
| <ul> |
| <li> |
| <p><strong>level</strong> <code>string</code> (Optional) : one of ERROR, INFO, or DEBUG, mapped to a corresponding |
| language-specific logging level</p> |
| </li> |
| <li> |
| <p><strong>prefix</strong> <code>string</code> (Optional) : an optional identifier that will get prepended to the element |
| being logged</p> |
| </li> |
| </ul> |
| <h3 id="usage_6">Usage</h3> |
| <div class="codehilite"><pre><span></span><code><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">LogForTesting</span> |
| <span class="nt">input</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">...</span> |
| <span class="nt">config</span><span class="p">:</span> |
| <span class="w"> </span><span class="nt">level</span><span class="p">:</span><span class="w"> </span><span class="s">"level"</span> |
| <span class="w"> </span><span class="nt">prefix</span><span class="p">:</span><span class="w"> </span><span class="s">"prefix"</span> |
| </code></pre></div> |
| |
| <h2 id="maptofields">MapToFields</h2> |
| <p>Creates records with new fields defined in terms of the input fields.</p> |
| <p>See more complete documentation on |
| <a href="https://beam.apache.org/documentation/sdks/yaml-udf/#mapping-functions">YAML Mapping Functions</a>.</p> |
| <p>Supported languages: calcite, generic, java, javascript, python, sql</p> |
| <h3 id="configuration_7">Configuration</h3> |
| <ul> |
| <li> |
| <p><strong>language</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>append</strong> <code>boolean</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>drop</strong> <code>Array[string]</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>fields</strong> <code>Map[string, Row]</code> </p> |
| </li> |
| <li> |
| <p><strong>error_handling</strong> <code>Row</code> (Optional) </p> |
| <p>Row fields:</p> |
| <ul> |
| <li><strong>output</strong> <code>string</code></li> |
| </ul> |
| </li> |
| </ul> |
| <h3 id="usage_7">Usage</h3> |
| <div class="codehilite"><pre><span></span><code><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">MapToFields</span> |
| <span class="nt">input</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">...</span> |
| <span class="nt">config</span><span class="p">:</span> |
| <span class="w"> </span><span class="nt">language</span><span class="p">:</span><span class="w"> </span><span class="s">"language"</span> |
| <span class="w"> </span><span class="nt">append</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true|false</span> |
| <span class="w"> </span><span class="nt">drop</span><span class="p">:</span> |
| <span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="s">"drop"</span> |
| <span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">...</span> |
| <span class="w"> </span><span class="nt">fields</span><span class="p">:</span> |
| <span class="w"> </span><span class="nt">a</span><span class="p">:</span> |
| <span class="w"> </span><span class="nt">callable</span><span class="p">:</span><span class="w"> </span><span class="s">"callable"</span> |
| <span class="w"> </span><span class="nt">expression</span><span class="p">:</span><span class="w"> </span><span class="s">"expression"</span> |
| <span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="s">"name"</span> |
| <span class="w"> </span><span class="nt">path</span><span class="p">:</span><span class="w"> </span><span class="s">"path"</span> |
| <span class="w"> </span><span class="nt">b</span><span class="p">:</span> |
| <span class="w"> </span><span class="nt">callable</span><span class="p">:</span><span class="w"> </span><span class="s">"callable"</span> |
| <span class="w"> </span><span class="nt">expression</span><span class="p">:</span><span class="w"> </span><span class="s">"expression"</span> |
| <span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="s">"name"</span> |
| <span class="w"> </span><span class="nt">path</span><span class="p">:</span><span class="w"> </span><span class="s">"path"</span> |
| <span class="w"> </span><span class="nt">c</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">...</span> |
| <span class="w"> </span><span class="nt">error_handling</span><span class="p">:</span> |
| <span class="w"> </span><span class="nt">output</span><span class="p">:</span><span class="w"> </span><span class="s">"output"</span> |
| </code></pre></div> |
| |
| <h2 id="pytransform">PyTransform</h2> |
| <p>A Python PTransform identified by fully qualified name.</p> |
| <p>This allows one to import, construct, and apply any Beam Python transform. |
| This can be useful for using transforms that have not yet been exposed |
| via a YAML interface. Note, however, that conversion may be required if this |
| transform does not accept or produce Beam Rows.</p> |
| <p>For example</p> |
| <div class="codehilite"><pre><span></span><code><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">PyTransform</span> |
| <span class="nt">config</span><span class="p">:</span> |
| <span class="w"> </span><span class="nt">constructor</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">apache_beam.pkg.mod.SomeClass</span> |
| <span class="w"> </span><span class="nt">args</span><span class="p">:</span><span class="w"> </span><span class="p p-Indicator">[</span><span class="nv">1</span><span class="p p-Indicator">,</span><span class="w"> </span><span class="s">'foo'</span><span class="p p-Indicator">]</span> |
| <span class="w"> </span><span class="nt">kwargs</span><span class="p">:</span> |
| <span class="w"> </span><span class="nt">baz</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">3</span> |
| </code></pre></div> |
| |
| <p>can be used to access the transform |
| <code>apache_beam.pkg.mod.SomeClass(1, 'foo', baz=3)</code>.</p> |
| <p>See also the documentation on |
| <a href="https://beam.apache.org/documentation/sdks/yaml-inline-python/">Inlining |
| Python</a>.</p> |
| <h3 id="configuration_8">Configuration</h3> |
| <ul> |
| <li> |
| <p><strong>constructor</strong> <code>string</code> : Fully qualified name of a callable used to construct the |
| transform. Often this is a class such as |
| <code>apache_beam.pkg.mod.SomeClass</code> but it can also be a function or |
| any other callable that returns a PTransform.</p> |
| </li> |
| <li> |
| <p><strong>args</strong> <code>Array[?]</code> (Optional) : A list of parameters to pass to the callable as positional |
| arguments.</p> |
| </li> |
| <li> |
| <p><strong>kwargs</strong> <code>Map[string, ?]</code> (Optional) : A list of parameters to pass to the callable as keyword |
| arguments.</p> |
| </li> |
| </ul> |
| <h3 id="usage_8">Usage</h3> |
| <div class="codehilite"><pre><span></span><code><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">PyTransform</span> |
| <span class="nt">input</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">...</span> |
| <span class="nt">config</span><span class="p">:</span> |
| <span class="w"> </span><span class="nt">constructor</span><span class="p">:</span><span class="w"> </span><span class="s">"constructor"</span> |
| <span class="w"> </span><span class="nt">args</span><span class="p">:</span> |
| <span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">args</span> |
| <span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">...</span> |
| <span class="w"> </span><span class="nt">kwargs</span><span class="p">:</span> |
| <span class="w"> </span><span class="nt">a</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">kwargs_value_a</span> |
| <span class="w"> </span><span class="nt">b</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">kwargs_value_b</span> |
| <span class="w"> </span><span class="nt">c</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">...</span> |
| </code></pre></div> |
| |
| <h2 id="sql">Sql</h2> |
| <h3 id="configuration_9">Configuration</h3> |
| <h3 id="usage_9">Usage</h3> |
| <div class="codehilite"><pre><span></span><code><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">Sql</span> |
| <span class="nt">input</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">...</span> |
| <span class="nt">config</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">...</span> |
| </code></pre></div> |
| |
| <h2 id="windowinto">WindowInto</h2> |
| <p>A window transform assigning windows to each element of a PCollection.</p> |
| <p>The assigned windows will affect all downstream aggregating operations, |
| which will aggregate by window as well as by key.</p> |
| <p>See <a href="https://beam.apache.org/documentation/programming-guide/#windowing">the Beam documentation on windowing</a> |
| for more details.</p> |
| <p>Sizes, offsets, periods and gaps (where applicable) must be defined using |
| a time unit suffix 'ms', 's', 'm', 'h' or 'd' for milliseconds, seconds, |
| minutes, hours or days, respectively. If a time unit is not specified, it |
| will default to 's'.</p> |
| <p>For example</p> |
| <div class="codehilite"><pre><span></span><code><span class="nt">windowing</span><span class="p">:</span> |
| <span class="w"> </span><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">fixed</span> |
| <span class="w"> </span><span class="nt">size</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">30s</span> |
| </code></pre></div> |
| |
| <p>Note that any Yaml transform can have a |
| <a href="https://github.com/apache/beam/blob/master/sdks/python/apache_beam/yaml/README.md#windowing">windowing parameter</a>, |
| which is applied to its inputs (if any) or outputs (if there are no inputs) |
| which means that explicit WindowInto operations are not typically needed.</p> |
| <h3 id="configuration_10">Configuration</h3> |
| <ul> |
| <li><strong>windowing</strong> <code>?</code> (Optional) : the type and parameters of the windowing to perform</li> |
| </ul> |
| <h3 id="usage_10">Usage</h3> |
| <div class="codehilite"><pre><span></span><code><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">WindowInto</span> |
| <span class="nt">input</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">...</span> |
| <span class="nt">config</span><span class="p">:</span> |
| <span class="w"> </span><span class="nt">windowing</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">windowing</span> |
| </code></pre></div> |
| |
| <h2 id="readfromavro">ReadFromAvro</h2> |
| <p>A <code>PTransform</code> for reading records from avro files.</p> |
| <p>Each record of the resulting PCollection will contain |
| a single record read from a source. Records that are of simple types will be |
| mapped to beam Rows with a single <code>record</code> field containing the records |
| value. Records that are of Avro type <code>RECORD</code> will be mapped to Beam rows |
| that comply with the schema contained in the Avro file that contains those |
| records.</p> |
| <h3 id="configuration_11">Configuration</h3> |
| <ul> |
| <li><strong>path</strong> <code>?</code> (Optional)</li> |
| </ul> |
| <h3 id="usage_11">Usage</h3> |
| <div class="codehilite"><pre><span></span><code><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">ReadFromAvro</span> |
| <span class="nt">config</span><span class="p">:</span> |
| <span class="w"> </span><span class="nt">path</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">path</span> |
| </code></pre></div> |
| |
| <h2 id="writetoavro">WriteToAvro</h2> |
| <p>A <code>PTransform</code> for writing avro files.</p> |
| <p>If the input has a schema, a corresponding avro schema will be automatically |
| generated and used to write the output records.</p> |
| <h3 id="configuration_12">Configuration</h3> |
| <ul> |
| <li><strong>path</strong> <code>?</code> (Optional)</li> |
| </ul> |
| <h3 id="usage_12">Usage</h3> |
| <div class="codehilite"><pre><span></span><code><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">WriteToAvro</span> |
| <span class="nt">input</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">...</span> |
| <span class="nt">config</span><span class="p">:</span> |
| <span class="w"> </span><span class="nt">path</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">path</span> |
| </code></pre></div> |
| |
| <h2 id="readfrombigquery">ReadFromBigQuery</h2> |
| <p>Reads data from BigQuery.</p> |
| <p>Exactly one of table or query must be set. |
| If query is set, neither row_restriction nor fields should be set.</p> |
| <h3 id="configuration_13">Configuration</h3> |
| <ul> |
| <li> |
| <p><strong>query</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>table</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>fields</strong> <code>Array[string]</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>row_restriction</strong> <code>string</code> (Optional)</p> |
| </li> |
| </ul> |
| <h3 id="usage_13">Usage</h3> |
| <div class="codehilite"><pre><span></span><code><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">ReadFromBigQuery</span> |
| <span class="nt">config</span><span class="p">:</span> |
| <span class="w"> </span><span class="nt">query</span><span class="p">:</span><span class="w"> </span><span class="s">"query"</span> |
| <span class="w"> </span><span class="nt">table</span><span class="p">:</span><span class="w"> </span><span class="s">"table"</span> |
| <span class="w"> </span><span class="nt">fields</span><span class="p">:</span> |
| <span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="s">"fields"</span> |
| <span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">...</span> |
| <span class="w"> </span><span class="nt">row_restriction</span><span class="p">:</span><span class="w"> </span><span class="s">"row_restriction"</span> |
| </code></pre></div> |
| |
| <h2 id="writetobigquery">WriteToBigQuery</h2> |
| <p>Writes data to BigQuery using the Storage Write API (https://cloud.google.com/bigquery/docs/write-api).</p> |
| <p>This expects a single PCollection of Beam Rows and outputs two dead-letter queues (DLQ) that contain failed rows. The first DLQ has tag [FailedRows] and contains the failed rows. The second DLQ has tag [FailedRowsWithErrors] and contains failed rows and along with their respective errors.</p> |
| <h3 id="configuration_14">Configuration</h3> |
| <ul> |
| <li> |
| <p><strong>table</strong> <code>string</code> </p> |
| </li> |
| <li> |
| <p><strong>create_disposition</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>write_disposition</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>error_handling</strong> <code>Row</code> (Optional) </p> |
| <p>Row fields:</p> |
| <ul> |
| <li><strong>output</strong> <code>string</code></li> |
| </ul> |
| </li> |
| <li> |
| <p><strong>num_streams</strong> <code>int32</code> (Optional)</p> |
| </li> |
| </ul> |
| <h3 id="usage_14">Usage</h3> |
| <div class="codehilite"><pre><span></span><code><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">WriteToBigQuery</span> |
| <span class="nt">input</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">...</span> |
| <span class="nt">config</span><span class="p">:</span> |
| <span class="w"> </span><span class="nt">table</span><span class="p">:</span><span class="w"> </span><span class="s">"table"</span> |
| <span class="w"> </span><span class="nt">create_disposition</span><span class="p">:</span><span class="w"> </span><span class="s">"create_disposition"</span> |
| <span class="w"> </span><span class="nt">write_disposition</span><span class="p">:</span><span class="w"> </span><span class="s">"write_disposition"</span> |
| <span class="w"> </span><span class="nt">error_handling</span><span class="p">:</span> |
| <span class="w"> </span><span class="nt">output</span><span class="p">:</span><span class="w"> </span><span class="s">"output"</span> |
| <span class="w"> </span><span class="nt">num_streams</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">num_streams</span> |
| </code></pre></div> |
| |
| <h2 id="readfromcsv">ReadFromCsv</h2> |
| <p>A PTransform for reading comma-separated values (csv) files into a |
| PCollection.</p> |
| <h3 id="configuration_15">Configuration</h3> |
| <ul> |
| <li> |
| <p><strong>path</strong> <code>string</code> : The file path to read from. The path can contain glob |
| characters such as <code>*</code> and <code>?</code>.</p> |
| </li> |
| <li> |
| <p><strong>delimiter</strong> <code>?</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>comment</strong> <code>?</code> (Optional)</p> |
| </li> |
| </ul> |
| <h3 id="usage_15">Usage</h3> |
| <div class="codehilite"><pre><span></span><code><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">ReadFromCsv</span> |
| <span class="nt">config</span><span class="p">:</span> |
| <span class="w"> </span><span class="nt">path</span><span class="p">:</span><span class="w"> </span><span class="s">"path"</span> |
| <span class="w"> </span><span class="nt">delimiter</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">delimiter</span> |
| <span class="w"> </span><span class="nt">comment</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">comment</span> |
| </code></pre></div> |
| |
| <h2 id="writetocsv">WriteToCsv</h2> |
| <p>A PTransform for writing a schema'd PCollection as a (set of) |
| comma-separated values (csv) files.</p> |
| <h3 id="configuration_16">Configuration</h3> |
| <ul> |
| <li> |
| <p><strong>path</strong> <code>string</code> : The file path to write to. The files written will |
| begin with this prefix, followed by a shard identifier (see |
| <code>num_shards</code>) according to the <code>file_naming</code> parameter.</p> |
| </li> |
| <li> |
| <p><strong>delimiter</strong> <code>?</code> (Optional)</p> |
| </li> |
| </ul> |
| <h3 id="usage_16">Usage</h3> |
| <div class="codehilite"><pre><span></span><code><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">WriteToCsv</span> |
| <span class="nt">input</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">...</span> |
| <span class="nt">config</span><span class="p">:</span> |
| <span class="w"> </span><span class="nt">delimiter</span><span class="p">:</span><span class="w"> </span><span class="s">"delimiter"</span> |
| <span class="w"> </span><span class="nt">path</span><span class="p">:</span><span class="w"> </span><span class="s">"path"</span> |
| </code></pre></div> |
| |
| <h2 id="readfromjdbc">ReadFromJdbc</h2> |
| <h3 id="configuration_17">Configuration</h3> |
| <ul> |
| <li> |
| <p><strong>driver_class_name</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>type</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>url</strong> <code>string</code> </p> |
| </li> |
| <li> |
| <p><strong>username</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>password</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>table</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>query</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>driver_jars</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>connection_properties</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>connection_init_sql</strong> <code>Array[string]</code> (Optional)</p> |
| </li> |
| </ul> |
| <h3 id="usage_17">Usage</h3> |
| <div class="codehilite"><pre><span></span><code><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">ReadFromJdbc</span> |
| <span class="nt">config</span><span class="p">:</span> |
| <span class="w"> </span><span class="nt">driver_class_name</span><span class="p">:</span><span class="w"> </span><span class="s">"driver_class_name"</span> |
| <span class="w"> </span><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="s">"type"</span> |
| <span class="w"> </span><span class="nt">url</span><span class="p">:</span><span class="w"> </span><span class="s">"url"</span> |
| <span class="w"> </span><span class="nt">username</span><span class="p">:</span><span class="w"> </span><span class="s">"username"</span> |
| <span class="w"> </span><span class="nt">password</span><span class="p">:</span><span class="w"> </span><span class="s">"password"</span> |
| <span class="w"> </span><span class="nt">table</span><span class="p">:</span><span class="w"> </span><span class="s">"table"</span> |
| <span class="w"> </span><span class="nt">query</span><span class="p">:</span><span class="w"> </span><span class="s">"query"</span> |
| <span class="w"> </span><span class="nt">driver_jars</span><span class="p">:</span><span class="w"> </span><span class="s">"driver_jars"</span> |
| <span class="w"> </span><span class="nt">connection_properties</span><span class="p">:</span><span class="w"> </span><span class="s">"connection_properties"</span> |
| <span class="w"> </span><span class="nt">connection_init_sql</span><span class="p">:</span> |
| <span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="s">"connection_init_sql"</span> |
| <span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">...</span> |
| </code></pre></div> |
| |
| <h2 id="writetojdbc">WriteToJdbc</h2> |
| <h3 id="configuration_18">Configuration</h3> |
| <ul> |
| <li> |
| <p><strong>driver_class_name</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>type</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>url</strong> <code>string</code> </p> |
| </li> |
| <li> |
| <p><strong>username</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>password</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>table</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>driver_jars</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>connection_properties</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>connection_init_sql</strong> <code>Array[string]</code> (Optional)</p> |
| </li> |
| </ul> |
| <h3 id="usage_18">Usage</h3> |
| <div class="codehilite"><pre><span></span><code><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">WriteToJdbc</span> |
| <span class="nt">input</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">...</span> |
| <span class="nt">config</span><span class="p">:</span> |
| <span class="w"> </span><span class="nt">driver_class_name</span><span class="p">:</span><span class="w"> </span><span class="s">"driver_class_name"</span> |
| <span class="w"> </span><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="s">"type"</span> |
| <span class="w"> </span><span class="nt">url</span><span class="p">:</span><span class="w"> </span><span class="s">"url"</span> |
| <span class="w"> </span><span class="nt">username</span><span class="p">:</span><span class="w"> </span><span class="s">"username"</span> |
| <span class="w"> </span><span class="nt">password</span><span class="p">:</span><span class="w"> </span><span class="s">"password"</span> |
| <span class="w"> </span><span class="nt">table</span><span class="p">:</span><span class="w"> </span><span class="s">"table"</span> |
| <span class="w"> </span><span class="nt">driver_jars</span><span class="p">:</span><span class="w"> </span><span class="s">"driver_jars"</span> |
| <span class="w"> </span><span class="nt">connection_properties</span><span class="p">:</span><span class="w"> </span><span class="s">"connection_properties"</span> |
| <span class="w"> </span><span class="nt">connection_init_sql</span><span class="p">:</span> |
| <span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="s">"connection_init_sql"</span> |
| <span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">...</span> |
| </code></pre></div> |
| |
| <h2 id="readfromjson">ReadFromJson</h2> |
| <p>A PTransform for reading json values from files into a PCollection.</p> |
| <h3 id="configuration_19">Configuration</h3> |
| <ul> |
| <li><strong>path</strong> <code>string</code> : The file path to read from. The path can contain glob |
| characters such as <code>*</code> and <code>?</code>.</li> |
| </ul> |
| <h3 id="usage_19">Usage</h3> |
| <div class="codehilite"><pre><span></span><code><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">ReadFromJson</span> |
| <span class="nt">config</span><span class="p">:</span> |
| <span class="w"> </span><span class="nt">path</span><span class="p">:</span><span class="w"> </span><span class="s">"path"</span> |
| </code></pre></div> |
| |
| <h2 id="writetojson">WriteToJson</h2> |
| <p>A PTransform for writing a PCollection as json values to files.</p> |
| <h3 id="configuration_20">Configuration</h3> |
| <ul> |
| <li><strong>path</strong> <code>string</code> : The file path to write to. The files written will |
| begin with this prefix, followed by a shard identifier (see |
| <code>num_shards</code>) according to the <code>file_naming</code> parameter.</li> |
| </ul> |
| <h3 id="usage_20">Usage</h3> |
| <div class="codehilite"><pre><span></span><code><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">WriteToJson</span> |
| <span class="nt">input</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">...</span> |
| <span class="nt">config</span><span class="p">:</span> |
| <span class="w"> </span><span class="nt">path</span><span class="p">:</span><span class="w"> </span><span class="s">"path"</span> |
| </code></pre></div> |
| |
| <h2 id="readfromkafka">ReadFromKafka</h2> |
| <h3 id="configuration_21">Configuration</h3> |
| <ul> |
| <li> |
| <p><strong>schema</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>consumer_config</strong> <code>Map[string, string]</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>format</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>topic</strong> <code>string</code> </p> |
| </li> |
| <li> |
| <p><strong>bootstrap_servers</strong> <code>string</code> </p> |
| </li> |
| <li> |
| <p><strong>confluent_schema_registry_url</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>confluent_schema_registry_subject</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>auto_offset_reset_config</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>error_handling</strong> <code>Row</code> (Optional) </p> |
| <p>Row fields:</p> |
| <ul> |
| <li><strong>output</strong> <code>string</code></li> |
| </ul> |
| </li> |
| <li> |
| <p><strong>file_descriptor_path</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>message_name</strong> <code>string</code> (Optional)</p> |
| </li> |
| </ul> |
| <h3 id="usage_21">Usage</h3> |
| <div class="codehilite"><pre><span></span><code><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">ReadFromKafka</span> |
| <span class="nt">config</span><span class="p">:</span> |
| <span class="w"> </span><span class="nt">schema</span><span class="p">:</span><span class="w"> </span><span class="s">"schema"</span> |
| <span class="w"> </span><span class="nt">consumer_config</span><span class="p">:</span> |
| <span class="w"> </span><span class="nt">a</span><span class="p">:</span><span class="w"> </span><span class="s">"consumer_config_value_a"</span> |
| <span class="w"> </span><span class="nt">b</span><span class="p">:</span><span class="w"> </span><span class="s">"consumer_config_value_b"</span> |
| <span class="w"> </span><span class="nt">c</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">...</span> |
| <span class="w"> </span><span class="nt">format</span><span class="p">:</span><span class="w"> </span><span class="s">"format"</span> |
| <span class="w"> </span><span class="nt">topic</span><span class="p">:</span><span class="w"> </span><span class="s">"topic"</span> |
| <span class="w"> </span><span class="nt">bootstrap_servers</span><span class="p">:</span><span class="w"> </span><span class="s">"bootstrap_servers"</span> |
| <span class="w"> </span><span class="nt">confluent_schema_registry_url</span><span class="p">:</span><span class="w"> </span><span class="s">"confluent_schema_registry_url"</span> |
| <span class="w"> </span><span class="nt">confluent_schema_registry_subject</span><span class="p">:</span><span class="w"> </span><span class="s">"confluent_schema_registry_subject"</span> |
| <span class="w"> </span><span class="nt">auto_offset_reset_config</span><span class="p">:</span><span class="w"> </span><span class="s">"auto_offset_reset_config"</span> |
| <span class="w"> </span><span class="nt">error_handling</span><span class="p">:</span> |
| <span class="w"> </span><span class="nt">output</span><span class="p">:</span><span class="w"> </span><span class="s">"output"</span> |
| <span class="w"> </span><span class="nt">file_descriptor_path</span><span class="p">:</span><span class="w"> </span><span class="s">"file_descriptor_path"</span> |
| <span class="w"> </span><span class="nt">message_name</span><span class="p">:</span><span class="w"> </span><span class="s">"message_name"</span> |
| </code></pre></div> |
| |
| <h2 id="writetokafka">WriteToKafka</h2> |
| <h3 id="configuration_22">Configuration</h3> |
| <ul> |
| <li> |
| <p><strong>format</strong> <code>string</code> </p> |
| </li> |
| <li> |
| <p><strong>topic</strong> <code>string</code> </p> |
| </li> |
| <li> |
| <p><strong>bootstrap_servers</strong> <code>string</code> </p> |
| </li> |
| <li> |
| <p><strong>producer_config_updates</strong> <code>Map[string, string]</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>error_handling</strong> <code>Row</code> (Optional) </p> |
| <p>Row fields:</p> |
| <ul> |
| <li><strong>output</strong> <code>string</code></li> |
| </ul> |
| </li> |
| <li> |
| <p><strong>file_descriptor_path</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>message_name</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>schema</strong> <code>string</code> (Optional)</p> |
| </li> |
| </ul> |
| <h3 id="usage_22">Usage</h3> |
| <div class="codehilite"><pre><span></span><code><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">WriteToKafka</span> |
| <span class="nt">input</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">...</span> |
| <span class="nt">config</span><span class="p">:</span> |
| <span class="w"> </span><span class="nt">format</span><span class="p">:</span><span class="w"> </span><span class="s">"format"</span> |
| <span class="w"> </span><span class="nt">topic</span><span class="p">:</span><span class="w"> </span><span class="s">"topic"</span> |
| <span class="w"> </span><span class="nt">bootstrap_servers</span><span class="p">:</span><span class="w"> </span><span class="s">"bootstrap_servers"</span> |
| <span class="w"> </span><span class="nt">producer_config_updates</span><span class="p">:</span> |
| <span class="w"> </span><span class="nt">a</span><span class="p">:</span><span class="w"> </span><span class="s">"producer_config_updates_value_a"</span> |
| <span class="w"> </span><span class="nt">b</span><span class="p">:</span><span class="w"> </span><span class="s">"producer_config_updates_value_b"</span> |
| <span class="w"> </span><span class="nt">c</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">...</span> |
| <span class="w"> </span><span class="nt">error_handling</span><span class="p">:</span> |
| <span class="w"> </span><span class="nt">output</span><span class="p">:</span><span class="w"> </span><span class="s">"output"</span> |
| <span class="w"> </span><span class="nt">file_descriptor_path</span><span class="p">:</span><span class="w"> </span><span class="s">"file_descriptor_path"</span> |
| <span class="w"> </span><span class="nt">message_name</span><span class="p">:</span><span class="w"> </span><span class="s">"message_name"</span> |
| <span class="w"> </span><span class="nt">schema</span><span class="p">:</span><span class="w"> </span><span class="s">"schema"</span> |
| </code></pre></div> |
| |
| <h2 id="readfrommysql">ReadFromMySql</h2> |
| <h3 id="configuration_23">Configuration</h3> |
| <ul> |
| <li> |
| <p><strong>driver_class_name</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>url</strong> <code>string</code> </p> |
| </li> |
| <li> |
| <p><strong>username</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>password</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>table</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>query</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>driver_jars</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>connection_properties</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>connection_init_sql</strong> <code>Array[string]</code> (Optional)</p> |
| </li> |
| </ul> |
| <h3 id="usage_23">Usage</h3> |
| <div class="codehilite"><pre><span></span><code><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">ReadFromMySql</span> |
| <span class="nt">config</span><span class="p">:</span> |
| <span class="w"> </span><span class="nt">driver_class_name</span><span class="p">:</span><span class="w"> </span><span class="s">"driver_class_name"</span> |
| <span class="w"> </span><span class="nt">url</span><span class="p">:</span><span class="w"> </span><span class="s">"url"</span> |
| <span class="w"> </span><span class="nt">username</span><span class="p">:</span><span class="w"> </span><span class="s">"username"</span> |
| <span class="w"> </span><span class="nt">password</span><span class="p">:</span><span class="w"> </span><span class="s">"password"</span> |
| <span class="w"> </span><span class="nt">table</span><span class="p">:</span><span class="w"> </span><span class="s">"table"</span> |
| <span class="w"> </span><span class="nt">query</span><span class="p">:</span><span class="w"> </span><span class="s">"query"</span> |
| <span class="w"> </span><span class="nt">driver_jars</span><span class="p">:</span><span class="w"> </span><span class="s">"driver_jars"</span> |
| <span class="w"> </span><span class="nt">connection_properties</span><span class="p">:</span><span class="w"> </span><span class="s">"connection_properties"</span> |
| <span class="w"> </span><span class="nt">connection_init_sql</span><span class="p">:</span> |
| <span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="s">"connection_init_sql"</span> |
| <span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">...</span> |
| </code></pre></div> |
| |
| <h2 id="writetomysql">WriteToMySql</h2> |
| <h3 id="configuration_24">Configuration</h3> |
| <ul> |
| <li> |
| <p><strong>driver_class_name</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>url</strong> <code>string</code> </p> |
| </li> |
| <li> |
| <p><strong>username</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>password</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>table</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>driver_jars</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>connection_properties</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>connection_init_sql</strong> <code>Array[string]</code> (Optional)</p> |
| </li> |
| </ul> |
| <h3 id="usage_24">Usage</h3> |
| <div class="codehilite"><pre><span></span><code><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">WriteToMySql</span> |
| <span class="nt">input</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">...</span> |
| <span class="nt">config</span><span class="p">:</span> |
| <span class="w"> </span><span class="nt">driver_class_name</span><span class="p">:</span><span class="w"> </span><span class="s">"driver_class_name"</span> |
| <span class="w"> </span><span class="nt">url</span><span class="p">:</span><span class="w"> </span><span class="s">"url"</span> |
| <span class="w"> </span><span class="nt">username</span><span class="p">:</span><span class="w"> </span><span class="s">"username"</span> |
| <span class="w"> </span><span class="nt">password</span><span class="p">:</span><span class="w"> </span><span class="s">"password"</span> |
| <span class="w"> </span><span class="nt">table</span><span class="p">:</span><span class="w"> </span><span class="s">"table"</span> |
| <span class="w"> </span><span class="nt">driver_jars</span><span class="p">:</span><span class="w"> </span><span class="s">"driver_jars"</span> |
| <span class="w"> </span><span class="nt">connection_properties</span><span class="p">:</span><span class="w"> </span><span class="s">"connection_properties"</span> |
| <span class="w"> </span><span class="nt">connection_init_sql</span><span class="p">:</span> |
| <span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="s">"connection_init_sql"</span> |
| <span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">...</span> |
| </code></pre></div> |
| |
| <h2 id="readfromoracle">ReadFromOracle</h2> |
| <h3 id="configuration_25">Configuration</h3> |
| <ul> |
| <li> |
| <p><strong>driver_class_name</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>url</strong> <code>string</code> </p> |
| </li> |
| <li> |
| <p><strong>username</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>password</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>table</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>query</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>driver_jars</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>connection_properties</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>connection_init_sql</strong> <code>Array[string]</code> (Optional)</p> |
| </li> |
| </ul> |
| <h3 id="usage_25">Usage</h3> |
| <div class="codehilite"><pre><span></span><code><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">ReadFromOracle</span> |
| <span class="nt">config</span><span class="p">:</span> |
| <span class="w"> </span><span class="nt">driver_class_name</span><span class="p">:</span><span class="w"> </span><span class="s">"driver_class_name"</span> |
| <span class="w"> </span><span class="nt">url</span><span class="p">:</span><span class="w"> </span><span class="s">"url"</span> |
| <span class="w"> </span><span class="nt">username</span><span class="p">:</span><span class="w"> </span><span class="s">"username"</span> |
| <span class="w"> </span><span class="nt">password</span><span class="p">:</span><span class="w"> </span><span class="s">"password"</span> |
| <span class="w"> </span><span class="nt">table</span><span class="p">:</span><span class="w"> </span><span class="s">"table"</span> |
| <span class="w"> </span><span class="nt">query</span><span class="p">:</span><span class="w"> </span><span class="s">"query"</span> |
| <span class="w"> </span><span class="nt">driver_jars</span><span class="p">:</span><span class="w"> </span><span class="s">"driver_jars"</span> |
| <span class="w"> </span><span class="nt">connection_properties</span><span class="p">:</span><span class="w"> </span><span class="s">"connection_properties"</span> |
| <span class="w"> </span><span class="nt">connection_init_sql</span><span class="p">:</span> |
| <span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="s">"connection_init_sql"</span> |
| <span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">...</span> |
| </code></pre></div> |
| |
| <h2 id="writetooracle">WriteToOracle</h2> |
| <h3 id="configuration_26">Configuration</h3> |
| <ul> |
| <li> |
| <p><strong>driver_class_name</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>url</strong> <code>string</code> </p> |
| </li> |
| <li> |
| <p><strong>username</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>password</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>table</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>driver_jars</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>connection_properties</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>connection_init_sql</strong> <code>Array[string]</code> (Optional)</p> |
| </li> |
| </ul> |
| <h3 id="usage_26">Usage</h3> |
| <div class="codehilite"><pre><span></span><code><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">WriteToOracle</span> |
| <span class="nt">input</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">...</span> |
| <span class="nt">config</span><span class="p">:</span> |
| <span class="w"> </span><span class="nt">driver_class_name</span><span class="p">:</span><span class="w"> </span><span class="s">"driver_class_name"</span> |
| <span class="w"> </span><span class="nt">url</span><span class="p">:</span><span class="w"> </span><span class="s">"url"</span> |
| <span class="w"> </span><span class="nt">username</span><span class="p">:</span><span class="w"> </span><span class="s">"username"</span> |
| <span class="w"> </span><span class="nt">password</span><span class="p">:</span><span class="w"> </span><span class="s">"password"</span> |
| <span class="w"> </span><span class="nt">table</span><span class="p">:</span><span class="w"> </span><span class="s">"table"</span> |
| <span class="w"> </span><span class="nt">driver_jars</span><span class="p">:</span><span class="w"> </span><span class="s">"driver_jars"</span> |
| <span class="w"> </span><span class="nt">connection_properties</span><span class="p">:</span><span class="w"> </span><span class="s">"connection_properties"</span> |
| <span class="w"> </span><span class="nt">connection_init_sql</span><span class="p">:</span> |
| <span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="s">"connection_init_sql"</span> |
| <span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">...</span> |
| </code></pre></div> |
| |
| <h2 id="readfromparquet">ReadFromParquet</h2> |
| <p>A <code>PTransform</code> for reading Parquet files.</p> |
| <h3 id="configuration_27">Configuration</h3> |
| <ul> |
| <li><strong>path</strong> <code>?</code> (Optional)</li> |
| </ul> |
| <h3 id="usage_27">Usage</h3> |
| <div class="codehilite"><pre><span></span><code><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">ReadFromParquet</span> |
| <span class="nt">config</span><span class="p">:</span> |
| <span class="w"> </span><span class="nt">path</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">path</span> |
| </code></pre></div> |
| |
| <h2 id="writetoparquet">WriteToParquet</h2> |
| <p>A <code>PTransform</code> for writing parquet files.</p> |
| <h3 id="configuration_28">Configuration</h3> |
| <ul> |
| <li><strong>path</strong> <code>?</code> (Optional)</li> |
| </ul> |
| <h3 id="usage_28">Usage</h3> |
| <div class="codehilite"><pre><span></span><code><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">WriteToParquet</span> |
| <span class="nt">input</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">...</span> |
| <span class="nt">config</span><span class="p">:</span> |
| <span class="w"> </span><span class="nt">path</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">path</span> |
| </code></pre></div> |
| |
| <h2 id="readfrompostgres">ReadFromPostgres</h2> |
| <h3 id="configuration_29">Configuration</h3> |
| <ul> |
| <li> |
| <p><strong>driver_class_name</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>url</strong> <code>string</code> </p> |
| </li> |
| <li> |
| <p><strong>username</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>password</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>table</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>query</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>driver_jars</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>connection_properties</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>connection_init_sql</strong> <code>Array[string]</code> (Optional)</p> |
| </li> |
| </ul> |
| <h3 id="usage_29">Usage</h3> |
| <div class="codehilite"><pre><span></span><code><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">ReadFromPostgres</span> |
| <span class="nt">config</span><span class="p">:</span> |
| <span class="w"> </span><span class="nt">driver_class_name</span><span class="p">:</span><span class="w"> </span><span class="s">"driver_class_name"</span> |
| <span class="w"> </span><span class="nt">url</span><span class="p">:</span><span class="w"> </span><span class="s">"url"</span> |
| <span class="w"> </span><span class="nt">username</span><span class="p">:</span><span class="w"> </span><span class="s">"username"</span> |
| <span class="w"> </span><span class="nt">password</span><span class="p">:</span><span class="w"> </span><span class="s">"password"</span> |
| <span class="w"> </span><span class="nt">table</span><span class="p">:</span><span class="w"> </span><span class="s">"table"</span> |
| <span class="w"> </span><span class="nt">query</span><span class="p">:</span><span class="w"> </span><span class="s">"query"</span> |
| <span class="w"> </span><span class="nt">driver_jars</span><span class="p">:</span><span class="w"> </span><span class="s">"driver_jars"</span> |
| <span class="w"> </span><span class="nt">connection_properties</span><span class="p">:</span><span class="w"> </span><span class="s">"connection_properties"</span> |
| <span class="w"> </span><span class="nt">connection_init_sql</span><span class="p">:</span> |
| <span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="s">"connection_init_sql"</span> |
| <span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">...</span> |
| </code></pre></div> |
| |
| <h2 id="writetopostgres">WriteToPostgres</h2> |
| <h3 id="configuration_30">Configuration</h3> |
| <ul> |
| <li> |
| <p><strong>driver_class_name</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>url</strong> <code>string</code> </p> |
| </li> |
| <li> |
| <p><strong>username</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>password</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>table</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>driver_jars</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>connection_properties</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>connection_init_sql</strong> <code>Array[string]</code> (Optional)</p> |
| </li> |
| </ul> |
| <h3 id="usage_30">Usage</h3> |
| <div class="codehilite"><pre><span></span><code><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">WriteToPostgres</span> |
| <span class="nt">input</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">...</span> |
| <span class="nt">config</span><span class="p">:</span> |
| <span class="w"> </span><span class="nt">driver_class_name</span><span class="p">:</span><span class="w"> </span><span class="s">"driver_class_name"</span> |
| <span class="w"> </span><span class="nt">url</span><span class="p">:</span><span class="w"> </span><span class="s">"url"</span> |
| <span class="w"> </span><span class="nt">username</span><span class="p">:</span><span class="w"> </span><span class="s">"username"</span> |
| <span class="w"> </span><span class="nt">password</span><span class="p">:</span><span class="w"> </span><span class="s">"password"</span> |
| <span class="w"> </span><span class="nt">table</span><span class="p">:</span><span class="w"> </span><span class="s">"table"</span> |
| <span class="w"> </span><span class="nt">driver_jars</span><span class="p">:</span><span class="w"> </span><span class="s">"driver_jars"</span> |
| <span class="w"> </span><span class="nt">connection_properties</span><span class="p">:</span><span class="w"> </span><span class="s">"connection_properties"</span> |
| <span class="w"> </span><span class="nt">connection_init_sql</span><span class="p">:</span> |
| <span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="s">"connection_init_sql"</span> |
| <span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">...</span> |
| </code></pre></div> |
| |
| <h2 id="readfrompubsub">ReadFromPubSub</h2> |
| <p>Reads messages from Cloud Pub/Sub.</p> |
| <h3 id="configuration_31">Configuration</h3> |
| <ul> |
| <li> |
| <p><strong>topic</strong> <code>string</code> (Optional) : Cloud Pub/Sub topic in the form |
| "projects/<project>/topics/<topic>". If provided, subscription must be |
| None.</p> |
| </li> |
| <li> |
| <p><strong>subscription</strong> <code>string</code> (Optional) : Existing Cloud Pub/Sub subscription to use in the |
| form "projects/<project>/subscriptions/<subscription>". If not |
| specified, a temporary subscription will be created from the specified |
| topic. If provided, topic must be None.</p> |
| </li> |
| <li> |
| <p><strong>format</strong> <code>string</code> : The expected format of the message payload. Currently suported |
| formats are</p> |
| <ul> |
| <li>raw: Produces records with a single <code>payload</code> field whose contents |
| are the raw bytes of the pubsub message.</li> |
| <li>avro: Parses records with a given avro schema.</li> |
| <li>json: Parses records with a given json schema.</li> |
| </ul> |
| </li> |
| <li> |
| <p><strong>schema</strong> <code>?</code> (Optional) : Schema specification for the given format.</p> |
| </li> |
| <li> |
| <p><strong>attributes</strong> <code>Array[string]</code> (Optional) : List of attribute keys whose values will be flattened into the |
| output message as additional fields. For example, if the format is <code>raw</code> |
| and attributes is <code>["a", "b"]</code> then this read will produce elements of |
| the form <code>Row(payload=..., a=..., b=...)</code>.</p> |
| </li> |
| <li> |
| <p><strong>attributes_map</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>id_attribute</strong> <code>string</code> (Optional) : The attribute on incoming Pub/Sub messages to use as a unique |
| record identifier. When specified, the value of this attribute (which |
| can be any string that uniquely identifies the record) will be used for |
| deduplication of messages. If not provided, we cannot guarantee |
| that no duplicate data will be delivered on the Pub/Sub stream. In this |
| case, deduplication of the stream will be strictly best effort.</p> |
| </li> |
| <li> |
| <p><strong>timestamp_attribute</strong> <code>string</code> (Optional) : Message value to use as element timestamp. If None, |
| uses message publishing time as the timestamp.</p> |
| <p>Timestamp values should be in one of two formats:</p> |
| <ul> |
| <li>A numerical value representing the number of milliseconds since the |
| Unix epoch.</li> |
| <li>A string in RFC 3339 format, UTC timezone. Example: |
| <code>2015-10-29T23:41:41.123Z</code>. The sub-second component of the |
| timestamp is optional, and digits beyond the first three (i.e., time |
| units smaller than milliseconds) may be ignored.</li> |
| </ul> |
| </li> |
| <li> |
| <p><strong>error_handling</strong> <code>Row</code> </p> |
| <p>Row fields:</p> |
| <ul> |
| <li><strong>output</strong> <code>string</code></li> |
| </ul> |
| </li> |
| </ul> |
| <h3 id="usage_31">Usage</h3> |
| <div class="codehilite"><pre><span></span><code><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">ReadFromPubSub</span> |
| <span class="nt">config</span><span class="p">:</span> |
| <span class="w"> </span><span class="nt">topic</span><span class="p">:</span><span class="w"> </span><span class="s">"topic"</span> |
| <span class="w"> </span><span class="nt">subscription</span><span class="p">:</span><span class="w"> </span><span class="s">"subscription"</span> |
| <span class="w"> </span><span class="nt">format</span><span class="p">:</span><span class="w"> </span><span class="s">"format"</span> |
| <span class="w"> </span><span class="nt">schema</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">schema</span> |
| <span class="w"> </span><span class="nt">attributes</span><span class="p">:</span> |
| <span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="s">"attributes"</span> |
| <span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">...</span> |
| <span class="w"> </span><span class="nt">attributes_map</span><span class="p">:</span><span class="w"> </span><span class="s">"attributes_map"</span> |
| <span class="w"> </span><span class="nt">id_attribute</span><span class="p">:</span><span class="w"> </span><span class="s">"id_attribute"</span> |
| <span class="w"> </span><span class="nt">timestamp_attribute</span><span class="p">:</span><span class="w"> </span><span class="s">"timestamp_attribute"</span> |
| <span class="w"> </span><span class="nt">error_handling</span><span class="p">:</span> |
| <span class="w"> </span><span class="nt">output</span><span class="p">:</span><span class="w"> </span><span class="s">"output"</span> |
| </code></pre></div> |
| |
| <h2 id="writetopubsub">WriteToPubSub</h2> |
| <p>Writes messages to Cloud Pub/Sub.</p> |
| <h3 id="configuration_32">Configuration</h3> |
| <ul> |
| <li> |
| <p><strong>topic</strong> <code>string</code> : Cloud Pub/Sub topic in the form "/topics/<project>/<topic>".</p> |
| </li> |
| <li> |
| <p><strong>format</strong> <code>string</code> : How to format the message payload. Currently suported |
| formats are</p> |
| <ul> |
| <li>raw: Expects a message with a single field (excluding |
| attribute-related fields) whose contents are used as the raw bytes |
| of the pubsub message.</li> |
| <li>avro: Encodes records with a given avro schema, which may be inferred |
| from the input PCollection schema.</li> |
| <li>json: Formats records with a given json schema, which may be inferred |
| from the input PCollection schema.</li> |
| </ul> |
| </li> |
| <li> |
| <p><strong>schema</strong> <code>?</code> (Optional) : Schema specification for the given format.</p> |
| </li> |
| <li> |
| <p><strong>attributes</strong> <code>Array[string]</code> (Optional) : List of attribute keys whose values will be pulled out as |
| PubSub message attributes. For example, if the format is <code>raw</code> |
| and attributes is <code>["a", "b"]</code> then elements of the form |
| <code>Row(any_field=..., a=..., b=...)</code> will result in PubSub messages whose |
| payload has the contents of any_field and whose attribute will be |
| populated with the values of <code>a</code> and <code>b</code>.</p> |
| </li> |
| <li> |
| <p><strong>attributes_map</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>id_attribute</strong> <code>string</code> (Optional) : If set, will set an attribute for each Cloud Pub/Sub message |
| with the given name and a unique value. This attribute can then be used |
| in a ReadFromPubSub PTransform to deduplicate messages.</p> |
| </li> |
| <li> |
| <p><strong>timestamp_attribute</strong> <code>string</code> (Optional) : If set, will set an attribute for each Cloud Pub/Sub |
| message with the given name and the message's publish time as the value.</p> |
| </li> |
| <li> |
| <p><strong>error_handling</strong> <code>Row</code> </p> |
| <p>Row fields:</p> |
| <ul> |
| <li><strong>output</strong> <code>string</code></li> |
| </ul> |
| </li> |
| </ul> |
| <h3 id="usage_32">Usage</h3> |
| <div class="codehilite"><pre><span></span><code><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">WriteToPubSub</span> |
| <span class="nt">input</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">...</span> |
| <span class="nt">config</span><span class="p">:</span> |
| <span class="w"> </span><span class="nt">topic</span><span class="p">:</span><span class="w"> </span><span class="s">"topic"</span> |
| <span class="w"> </span><span class="nt">format</span><span class="p">:</span><span class="w"> </span><span class="s">"format"</span> |
| <span class="w"> </span><span class="nt">schema</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">schema</span> |
| <span class="w"> </span><span class="nt">attributes</span><span class="p">:</span> |
| <span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="s">"attributes"</span> |
| <span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">...</span> |
| <span class="w"> </span><span class="nt">attributes_map</span><span class="p">:</span><span class="w"> </span><span class="s">"attributes_map"</span> |
| <span class="w"> </span><span class="nt">id_attribute</span><span class="p">:</span><span class="w"> </span><span class="s">"id_attribute"</span> |
| <span class="w"> </span><span class="nt">timestamp_attribute</span><span class="p">:</span><span class="w"> </span><span class="s">"timestamp_attribute"</span> |
| <span class="w"> </span><span class="nt">error_handling</span><span class="p">:</span> |
| <span class="w"> </span><span class="nt">output</span><span class="p">:</span><span class="w"> </span><span class="s">"output"</span> |
| </code></pre></div> |
| |
| <h2 id="readfrompubsublite">ReadFromPubSubLite</h2> |
| <h3 id="configuration_33">Configuration</h3> |
| <ul> |
| <li> |
| <p><strong>project</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>schema</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>format</strong> <code>string</code> </p> |
| </li> |
| <li> |
| <p><strong>subscription_name</strong> <code>string</code> </p> |
| </li> |
| <li> |
| <p><strong>location</strong> <code>string</code> </p> |
| </li> |
| <li> |
| <p><strong>attributes</strong> <code>Array[string]</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>attribute_map</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>attribute_id</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>error_handling</strong> <code>Row</code> (Optional) </p> |
| <p>Row fields:</p> |
| <ul> |
| <li><strong>output</strong> <code>string</code></li> |
| </ul> |
| </li> |
| <li> |
| <p><strong>file_descriptor_path</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>message_name</strong> <code>string</code> (Optional)</p> |
| </li> |
| </ul> |
| <h3 id="usage_33">Usage</h3> |
| <div class="codehilite"><pre><span></span><code><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">ReadFromPubSubLite</span> |
| <span class="nt">config</span><span class="p">:</span> |
| <span class="w"> </span><span class="nt">project</span><span class="p">:</span><span class="w"> </span><span class="s">"project"</span> |
| <span class="w"> </span><span class="nt">schema</span><span class="p">:</span><span class="w"> </span><span class="s">"schema"</span> |
| <span class="w"> </span><span class="nt">format</span><span class="p">:</span><span class="w"> </span><span class="s">"format"</span> |
| <span class="w"> </span><span class="nt">subscription_name</span><span class="p">:</span><span class="w"> </span><span class="s">"subscription_name"</span> |
| <span class="w"> </span><span class="nt">location</span><span class="p">:</span><span class="w"> </span><span class="s">"location"</span> |
| <span class="w"> </span><span class="nt">attributes</span><span class="p">:</span> |
| <span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="s">"attributes"</span> |
| <span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">...</span> |
| <span class="w"> </span><span class="nt">attribute_map</span><span class="p">:</span><span class="w"> </span><span class="s">"attribute_map"</span> |
| <span class="w"> </span><span class="nt">attribute_id</span><span class="p">:</span><span class="w"> </span><span class="s">"attribute_id"</span> |
| <span class="w"> </span><span class="nt">error_handling</span><span class="p">:</span> |
| <span class="w"> </span><span class="nt">output</span><span class="p">:</span><span class="w"> </span><span class="s">"output"</span> |
| <span class="w"> </span><span class="nt">file_descriptor_path</span><span class="p">:</span><span class="w"> </span><span class="s">"file_descriptor_path"</span> |
| <span class="w"> </span><span class="nt">message_name</span><span class="p">:</span><span class="w"> </span><span class="s">"message_name"</span> |
| </code></pre></div> |
| |
| <h2 id="writetopubsublite">WriteToPubSubLite</h2> |
| <h3 id="configuration_34">Configuration</h3> |
| <ul> |
| <li> |
| <p><strong>project</strong> <code>string</code> </p> |
| </li> |
| <li> |
| <p><strong>format</strong> <code>string</code> </p> |
| </li> |
| <li> |
| <p><strong>topic_name</strong> <code>string</code> </p> |
| </li> |
| <li> |
| <p><strong>location</strong> <code>string</code> </p> |
| </li> |
| <li> |
| <p><strong>attributes</strong> <code>Array[string]</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>attribute_id</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>error_handling</strong> <code>Row</code> (Optional) </p> |
| <p>Row fields:</p> |
| <ul> |
| <li><strong>output</strong> <code>string</code></li> |
| </ul> |
| </li> |
| <li> |
| <p><strong>file_descriptor_path</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>message_name</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>schema</strong> <code>string</code> (Optional)</p> |
| </li> |
| </ul> |
| <h3 id="usage_34">Usage</h3> |
| <div class="codehilite"><pre><span></span><code><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">WriteToPubSubLite</span> |
| <span class="nt">input</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">...</span> |
| <span class="nt">config</span><span class="p">:</span> |
| <span class="w"> </span><span class="nt">project</span><span class="p">:</span><span class="w"> </span><span class="s">"project"</span> |
| <span class="w"> </span><span class="nt">format</span><span class="p">:</span><span class="w"> </span><span class="s">"format"</span> |
| <span class="w"> </span><span class="nt">topic_name</span><span class="p">:</span><span class="w"> </span><span class="s">"topic_name"</span> |
| <span class="w"> </span><span class="nt">location</span><span class="p">:</span><span class="w"> </span><span class="s">"location"</span> |
| <span class="w"> </span><span class="nt">attributes</span><span class="p">:</span> |
| <span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="s">"attributes"</span> |
| <span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">...</span> |
| <span class="w"> </span><span class="nt">attribute_id</span><span class="p">:</span><span class="w"> </span><span class="s">"attribute_id"</span> |
| <span class="w"> </span><span class="nt">error_handling</span><span class="p">:</span> |
| <span class="w"> </span><span class="nt">output</span><span class="p">:</span><span class="w"> </span><span class="s">"output"</span> |
| <span class="w"> </span><span class="nt">file_descriptor_path</span><span class="p">:</span><span class="w"> </span><span class="s">"file_descriptor_path"</span> |
| <span class="w"> </span><span class="nt">message_name</span><span class="p">:</span><span class="w"> </span><span class="s">"message_name"</span> |
| <span class="w"> </span><span class="nt">schema</span><span class="p">:</span><span class="w"> </span><span class="s">"schema"</span> |
| </code></pre></div> |
| |
| <h2 id="readfromsqlserver">ReadFromSqlServer</h2> |
| <h3 id="configuration_35">Configuration</h3> |
| <ul> |
| <li> |
| <p><strong>driver_class_name</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>url</strong> <code>string</code> </p> |
| </li> |
| <li> |
| <p><strong>username</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>password</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>table</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>query</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>driver_jars</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>connection_properties</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>connection_init_sql</strong> <code>Array[string]</code> (Optional)</p> |
| </li> |
| </ul> |
| <h3 id="usage_35">Usage</h3> |
| <div class="codehilite"><pre><span></span><code><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">ReadFromSqlServer</span> |
| <span class="nt">config</span><span class="p">:</span> |
| <span class="w"> </span><span class="nt">driver_class_name</span><span class="p">:</span><span class="w"> </span><span class="s">"driver_class_name"</span> |
| <span class="w"> </span><span class="nt">url</span><span class="p">:</span><span class="w"> </span><span class="s">"url"</span> |
| <span class="w"> </span><span class="nt">username</span><span class="p">:</span><span class="w"> </span><span class="s">"username"</span> |
| <span class="w"> </span><span class="nt">password</span><span class="p">:</span><span class="w"> </span><span class="s">"password"</span> |
| <span class="w"> </span><span class="nt">table</span><span class="p">:</span><span class="w"> </span><span class="s">"table"</span> |
| <span class="w"> </span><span class="nt">query</span><span class="p">:</span><span class="w"> </span><span class="s">"query"</span> |
| <span class="w"> </span><span class="nt">driver_jars</span><span class="p">:</span><span class="w"> </span><span class="s">"driver_jars"</span> |
| <span class="w"> </span><span class="nt">connection_properties</span><span class="p">:</span><span class="w"> </span><span class="s">"connection_properties"</span> |
| <span class="w"> </span><span class="nt">connection_init_sql</span><span class="p">:</span> |
| <span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="s">"connection_init_sql"</span> |
| <span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">...</span> |
| </code></pre></div> |
| |
| <h2 id="writetosqlserver">WriteToSqlServer</h2> |
| <h3 id="configuration_36">Configuration</h3> |
| <ul> |
| <li> |
| <p><strong>driver_class_name</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>url</strong> <code>string</code> </p> |
| </li> |
| <li> |
| <p><strong>username</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>password</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>table</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>driver_jars</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>connection_properties</strong> <code>string</code> (Optional) </p> |
| </li> |
| <li> |
| <p><strong>connection_init_sql</strong> <code>Array[string]</code> (Optional)</p> |
| </li> |
| </ul> |
| <h3 id="usage_36">Usage</h3> |
| <div class="codehilite"><pre><span></span><code><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">WriteToSqlServer</span> |
| <span class="nt">input</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">...</span> |
| <span class="nt">config</span><span class="p">:</span> |
| <span class="w"> </span><span class="nt">driver_class_name</span><span class="p">:</span><span class="w"> </span><span class="s">"driver_class_name"</span> |
| <span class="w"> </span><span class="nt">url</span><span class="p">:</span><span class="w"> </span><span class="s">"url"</span> |
| <span class="w"> </span><span class="nt">username</span><span class="p">:</span><span class="w"> </span><span class="s">"username"</span> |
| <span class="w"> </span><span class="nt">password</span><span class="p">:</span><span class="w"> </span><span class="s">"password"</span> |
| <span class="w"> </span><span class="nt">table</span><span class="p">:</span><span class="w"> </span><span class="s">"table"</span> |
| <span class="w"> </span><span class="nt">driver_jars</span><span class="p">:</span><span class="w"> </span><span class="s">"driver_jars"</span> |
| <span class="w"> </span><span class="nt">connection_properties</span><span class="p">:</span><span class="w"> </span><span class="s">"connection_properties"</span> |
| <span class="w"> </span><span class="nt">connection_init_sql</span><span class="p">:</span> |
| <span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="s">"connection_init_sql"</span> |
| <span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">...</span> |
| </code></pre></div> |
| |
| <h2 id="readfromtext">ReadFromText</h2> |
| <p>Reads lines from a text files.</p> |
| <p>The resulting PCollection consists of rows with a single string filed named |
| "line."</p> |
| <h3 id="configuration_37">Configuration</h3> |
| <ul> |
| <li><strong>path</strong> <code>string</code> : The file path to read from. The path can contain glob |
| characters such as <code>*</code> and <code>?</code>.</li> |
| </ul> |
| <h3 id="usage_37">Usage</h3> |
| <div class="codehilite"><pre><span></span><code><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">ReadFromText</span> |
| <span class="nt">config</span><span class="p">:</span> |
| <span class="w"> </span><span class="nt">path</span><span class="p">:</span><span class="w"> </span><span class="s">"path"</span> |
| </code></pre></div> |
| |
| <h2 id="writetotext">WriteToText</h2> |
| <p>Writes a PCollection to a (set of) text files(s).</p> |
| <p>The input must be a PCollection whose schema has exactly one field.</p> |
| <h3 id="configuration_38">Configuration</h3> |
| <ul> |
| <li><strong>path</strong> <code>string</code> : The file path to write to. The files written will |
| begin with this prefix, followed by a shard identifier.</li> |
| </ul> |
| <h3 id="usage_38">Usage</h3> |
| <div class="codehilite"><pre><span></span><code><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">WriteToText</span> |
| <span class="nt">input</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">...</span> |
| <span class="nt">config</span><span class="p">:</span> |
| <span class="w"> </span><span class="nt">path</span><span class="p">:</span><span class="w"> </span><span class="s">"path"</span> |
| </code></pre></div> |
| </div> |
| </body> |
| </html> |
| |