Examples of cascading.tap.Tap

cascading.tap.Tap
A Tap represents the physical data source or sink in a connected {@link cascading.flow.Flow}.
That is, a source Tap is the head end of a connected {@link Pipe} and {@link Tuple} stream, anda sink Tap is the tail end. Kinds of Tap types are used to manage files from a local disk, distributed disk, remote storage like Amazon S3, or via FTP. It simply abstracts out the complexity of connecting to these types of data sources.
A Tap takes a {@link Scheme} instance, which is used to identify the type of resource (text file, binary file, etc).A Tap is responsible for how the resource is reached.
By default when planning a Flow, Tap equality is a function of the {@link #getIdentifier()} and {@link #getScheme()}values. That is, two Tap instances are the same Tap instance if they sink/source the same resource and sink/source the same fields.
Some more advanced taps, like a database tap, may need to extend equality to include any filtering, like the {@code where} clause in a SQL statement so two taps reading from the same SQL table aren't considered equal.
Taps are also used to determine dependencies between two or more {@link Flow} instances when used with a{@link cascading.cascade.Cascade}. In that case the {@link #getFullIdentifier(Object)} value is used and the Schemeis ignored.




    @Test
    public void testUpdate() throws Exception {
        // local file-system source
        Tap in = sourceTap();
        Tap out = new EsTap("json-cascading-local/createwithid", new Fields("line"));
        Properties props = new TestSettings().getProperties();
        props.put(ConfigurationOptions.ES_MAPPING_ID, "number");
        props.put(ConfigurationOptions.ES_INPUT_JSON, "yes");


        Pipe pipe = new Pipe("copy");

View Full Code Here

        properties.put(ConfigurationOptions.ES_UPDATE_RETRY_ON_CONFLICT, "3");
        properties.put(ConfigurationOptions.ES_UPDATE_SCRIPT, "counter = 3");
        properties.put(ConfigurationOptions.ES_UPDATE_SCRIPT_LANG, "groovy");
        properties.put(ConfigurationOptions.ES_INPUT_JSON, "yes");


        Tap in = sourceTap();
        // use an existing id to allow the update to succeed
        Tap out = new EsTap("json-cascading-local/createwithid", new Fields("line"));


        Pipe pipe = new Pipe("copy");
        build(properties, in, out, pipe);
    }

View Full Code Here

        properties.put(ConfigurationOptions.ES_UPDATE_SCRIPT, "counter = param1; anothercounter = param2");
        properties.put(ConfigurationOptions.ES_UPDATE_SCRIPT_LANG, "groovy");
        properties.put(ConfigurationOptions.ES_UPDATE_SCRIPT_PARAMS, " param1:<1>,   param2:number ");
        properties.put(ConfigurationOptions.ES_INPUT_JSON, "yes");


        Tap in = sourceTap();
        // use an existing id to allow the update to succeed
        Tap out = new EsTap("json-cascading-local/createwithid", new Fields("line"));


        Pipe pipe = new Pipe("copy");
        build(properties, in, out, pipe);
    }

View Full Code Here

        properties.put(ConfigurationOptions.ES_UPDATE_SCRIPT, "counter = param1; anothercounter = param2");
        properties.put(ConfigurationOptions.ES_UPDATE_SCRIPT_LANG, "groovy");
        properties.put(ConfigurationOptions.ES_UPDATE_SCRIPT_PARAMS_JSON, "{ \"param1\":1, \"param2\":2}");
        properties.put(ConfigurationOptions.ES_INPUT_JSON, "yes");


        Tap in = sourceTap();
        // use an existing id to allow the update to succeed
        Tap out = new EsTap("json-cascading-local/createwithid", new Fields("line"));


        Pipe pipe = new Pipe("copy");
        build(properties, in, out, pipe);
    }

View Full Code Here

        Properties properties = new TestSettings().getProperties();
        properties.put(ConfigurationOptions.ES_WRITE_OPERATION, "upsert");
        properties.put(ConfigurationOptions.ES_MAPPING_ID, "number");
        properties.put(ConfigurationOptions.ES_INPUT_JSON, "yes");


        Tap in = sourceTap();
        Tap out = new EsTap("json-cascading-local/upsert", new Fields("line"));


        Pipe pipe = new Pipe("copy");
        build(properties, in, out, pipe);
    }

View Full Code Here

        properties.put(ConfigurationOptions.ES_WRITE_OPERATION, "upsert");
        properties.put(ConfigurationOptions.ES_MAPPING_ID, "number");
        properties.put(ConfigurationOptions.ES_INPUT_JSON, "yes");
        properties.put(ConfigurationOptions.ES_UPDATE_SCRIPT, "counter = 1");


        Tap in = sourceTap();
        // use an existing id to allow the update to succeed
        Tap out = new EsTap("json-cascading-local/upsert-script", new Fields("line"));


        Pipe pipe = new Pipe("copy");
        build(properties, in, out, pipe);
    }

View Full Code Here

        properties.put(ConfigurationOptions.ES_INPUT_JSON, "yes");
        properties.put(ConfigurationOptions.ES_UPDATE_SCRIPT, "counter += param1; anothercounter += param2");
        properties.put(ConfigurationOptions.ES_UPDATE_SCRIPT_LANG, "groovy");
        properties.put(ConfigurationOptions.ES_UPDATE_SCRIPT_PARAMS, " param1:<1>,   param2:number ");


        Tap in = sourceTap();
        // use an existing id to allow the update to succeed
        Tap out = new EsTap("json-cascading-local/upsert-param-script", new Fields("line"));


        Pipe pipe = new Pipe("copy");
        build(properties, in, out, pipe);
    }

View Full Code Here

        properties.put(ConfigurationOptions.ES_INPUT_JSON, "yes");
        properties.put(ConfigurationOptions.ES_UPDATE_SCRIPT, "counter += param1; anothercounter += param2");
        properties.put(ConfigurationOptions.ES_UPDATE_SCRIPT_LANG, "groovy");
        properties.put(ConfigurationOptions.ES_UPDATE_SCRIPT_PARAMS_JSON, "{ \"param1\":1, \"param2\":2}");


        Tap in = sourceTap();
        // use an existing id to allow the update to succeed
        Tap out = new EsTap("json-cascading-local/upsert-script-json-script", new Fields("line"));


        Pipe pipe = new Pipe("copy");
        build(properties, in, out, pipe);
    }

View Full Code Here

    }




    @Test
    public void testReadFromES() throws Exception {
        Tap in = new EsTap(indexPrefix + "cascading-hadoop/artists");
        Pipe pipe = new Pipe("copy");
        pipe = new Each(pipe, new FilterNotNull());
        pipe = new Each(pipe, AssertionLevel.STRICT, new AssertSizeLessThan(5));
        // can't select when using unknown
        //pipe = new Each(pipe, new Fields("name"), AssertionLevel.STRICT, new AssertNotNull());
        pipe = new GroupBy(pipe);
        pipe = new Every(pipe, new Count());


        // print out
        Tap out = new HadoopPrintStreamTap(Stream.NULL);
        build(cfg(), in, out, pipe);
    }

View Full Code Here

        RestUtils.refresh(indexPrefix + "cascading-hadoop");


        Properties cfg = cfg();
        cfg.setProperty("es.mapping.names", "nested:data.map.key");


        Tap in = new EsTap(indexPrefix + "cascading-hadoop/nestedmap", new Fields("nested"));
        Pipe pipe = new Pipe("copy");
        pipe = new Each(pipe, new FilterNotNull());
        pipe = new Each(pipe, AssertionLevel.STRICT, new AssertSizeLessThan(2));


        // print out
        Tap out = new HadoopPrintStreamTap(Stream.NULL);
        build(cfg, in, out, pipe);
    }

View Full Code Here

0 1 2 3 4 5 6 7 8 9

TOP

Related Classes of cascading.tap.Tap

bixo.examples.crawl.DemoStatusTool

bixo.examples.crawl.LatestUrlDatumBufferTest

bixo.examples.webmining.DemoWebMiningWorkflow

bixo.examples.webmining.DemoWebMiningWorkflowTest

bixo.fetcher.FetcherTest

bixo.pipes.AbstractFetchPipeTest

cascading.BasicPipesPlatformTest

cascading.BasicTrapPlatformTest

cascading.BufferPipesPlatformTest

cascading.cascade.CascadePlatformTest

All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.